2489 files changed, 71325 insertions, 34526 deletions

diff --git a/CREDITS b/CREDITS
index c58560701d13..c5626bf06264 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2478,12 +2478,11 @@ S: D-90453 Nuernberg
 S: Germany
 
 N: Arnaldo Carvalho de Melo
-E: acme@ghostprotocols.net
+E: acme@kernel.org
 E: arnaldo.melo@gmail.com
 E: acme@redhat.com
-W: http://oops.ghostprotocols.net:81/blog/
 P: 1024D/9224DF01 D5DF E3BB E3C8 BCBB F8AD  841A B6AB 4681 9224 DF01
-D: IPX, LLC, DCCP, cyc2x, wl3501_cs, net/ hacks
+D: tools/, IPX, LLC, DCCP, cyc2x, wl3501_cs, net/ hacks
 S: Brazil
 
 N: Karsten Merker
diff --git a/Documentation/ABI/testing/sysfs-class-devfreq-event b/Documentation/ABI/testing/sysfs-class-devfreq-event
new file mode 100644
index 000000000000..ceaf0f686d4a
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-class-devfreq-event
@@ -0,0 +1,25 @@
+What:		/sys/class/devfreq-event/event(x)/
+Date:		January 2017
+Contact:	Chanwoo Choi <cw00.choi@samsung.com>
+Description:
+		Provide a place in sysfs for the devfreq-event objects.
+		This allows accessing various devfreq-event specific variables.
+		The name of devfreq-event object denoted as 'event(x)' which
+		includes the unique number of 'x' for each devfreq-event object.
+
+What:		/sys/class/devfreq-event/event(x)/name
+Date:		January 2017
+Contact:	Chanwoo Choi <cw00.choi@samsung.com>
+Description:
+		The /sys/class/devfreq-event/event(x)/name attribute contains
+		the name of the devfreq-event object. This attribute is
+		read-only.
+
+What:		/sys/class/devfreq-event/event(x)/enable_count
+Date:		January 2017
+Contact:	Chanwoo Choi <cw00.choi@samsung.com>
+Description:
+		The /sys/class/devfreq-event/event(x)/enable_count attribute
+		contains the reference count to enable the devfreq-event
+		object. If the device is enabled, the value of attribute is
+		greater than zero.
diff --git a/Documentation/ABI/testing/sysfs-class-led b/Documentation/ABI/testing/sysfs-class-led
index 491cdeedc195..5f67f7ab277b 100644
--- a/Documentation/ABI/testing/sysfs-class-led
+++ b/Documentation/ABI/testing/sysfs-class-led
@@ -23,6 +23,23 @@ Description:
 		If the LED does not support different brightness levels, this
 		should be 1.
 
+What:		/sys/class/leds/<led>/brightness_hw_changed
+Date:		January 2017
+KernelVersion:	4.11
+Description:
+		Last hardware set brightness level for this LED. Some LEDs
+		may be changed autonomously by hardware/firmware. Only LEDs
+		where this happens and the driver can detect this, will have
+		this file.
+
+		This file supports poll() to detect when the hardware changes
+		the brightness.
+
+		Reading this file will return the last brightness level set
+		by the hardware, this may be different from the current
+		brightness. Reading this file when no hw brightness change
+		event has happened will return an ENODATA error.
+
 What:		/sys/class/leds/<led>/trigger
 Date:		March 2006
 KernelVersion:	2.6.17
diff --git a/Documentation/ABI/testing/sysfs-devices-edac b/Documentation/ABI/testing/sysfs-devices-edac
index 6568e0010e1a..46ff929fd52a 100644
--- a/Documentation/ABI/testing/sysfs-devices-edac
+++ b/Documentation/ABI/testing/sysfs-devices-edac
@@ -138,3 +138,20 @@ Contact:	Mauro Carvalho Chehab <m.chehab@samsung.com>
 Description:	This attribute file will display what type of memory is
 		currently on this csrow. Normally, either buffered or
 		unbuffered memory (for example, Unbuffered-DDR3).
+
+What:		/sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_ce_count
+Date:		October 2016
+Contact:	linux-edac@vger.kernel.org
+Description:	This attribute file displays the total count of correctable
+		errors that have occurred on this DIMM. This count is very important
+		to examine. CEs provide early indications that a DIMM is beginning
+		to fail. This count field should be monitored for non-zero values
+		and report such information to the system administrator.
+
+What:		/sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_ue_count
+Date:		October 2016
+Contact:	linux-edac@vger.kernel.org
+Description:	This attribute file displays the total count of uncorrectable
+		errors that have occurred on this DIMM. If panic_on_ue is set, this
+		counter will not have a chance to increment, since EDAC will panic the
+		system
diff --git a/Documentation/ABI/testing/sysfs-kernel-iommu_groups b/Documentation/ABI/testing/sysfs-kernel-iommu_groups
index 9b31556cfdda..35c64e00b35c 100644
--- a/Documentation/ABI/testing/sysfs-kernel-iommu_groups
+++ b/Documentation/ABI/testing/sysfs-kernel-iommu_groups
@@ -12,3 +12,15 @@ Description:	/sys/kernel/iommu_groups/ contains a number of sub-
 		file if the IOMMU driver has chosen to register a more
 		common name for the group.
 Users:
+
+What:		/sys/kernel/iommu_groups/reserved_regions
+Date: 		January 2017
+KernelVersion:  v4.11
+Contact: 	Eric Auger <eric.auger@redhat.com>
+Description:    /sys/kernel/iommu_groups/reserved_regions list IOVA
+		regions that are reserved. Not necessarily all
+		reserved regions are listed. This is typically used to
+		output direct-mapped, MSI, non mappable regions. Each
+		region is described on a single line: the 1st field is
+		the base IOVA, the second is the end IOVA and the third
+		field describes the type of the region.
diff --git a/Documentation/DMA-attributes.txt b/Documentation/DMA-attributes.txt
index 98bf7ac29aad..44c6bc496eee 100644
--- a/Documentation/DMA-attributes.txt
+++ b/Documentation/DMA-attributes.txt
@@ -143,3 +143,13 @@ So, this provides a way for drivers to avoid those error messages on calls
 where allocation failures are not a problem, and shouldn't bother the logs.
 
 NOTE: At the moment DMA_ATTR_NO_WARN is only implemented on PowerPC.
+
+DMA_ATTR_PRIVILEGED
+------------------------------
+
+Some advanced peripherals such as remote processors and GPUs perform
+accesses to DMA buffers in both privileged "supervisor" and unprivileged
+"user" modes.  This attribute is used to indicate to the DMA-mapping
+subsystem that the buffer is fully accessible at the elevated privilege
+level (and ideally inaccessible or at least read-only at the
+lesser-privileged levels).
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
index 7eb47ac25ad7..d583c653a703 100644
--- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html
+++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
@@ -4,7 +4,7 @@
         <head><title>A Tour Through TREE_RCU's Data Structures [LWN.net]</title>
         <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">
 
-           <p>January 27, 2016</p>
+           <p>December 18, 2016</p>
            <p>This article was contributed by Paul E.&nbsp;McKenney</p>
 
 <h3>Introduction</h3>
@@ -31,9 +31,6 @@ to each other.
 	Accessor Functions</a>
 </ol>
 
-At the end we have the
-<a href="#Answers to Quick Quizzes">answers to the quick quizzes</a>.
-
 <h3><a name="Data-Structure Relationships">Data-Structure Relationships</a></h3>
 
 <p>RCU is for all intents and purposes a large state machine, and its
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/ExpRCUFlow.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpRCUFlow.svg
new file mode 100644
index 000000000000..7c6c90bd02c9
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpRCUFlow.svg
@@ -0,0 +1,830 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Creator: fig2dev Version 3.2 Patchlevel 5e -->
+
+<!-- CreationDate: Wed Dec  9 17:39:46 2015 -->
+
+<!-- Magnification: 3.000 -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="952.6817"
+   height="1219.6219"
+   viewBox="-66 -66 12729.905 16296.808"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="ExpRCUFlow.svg">
+  <metadata
+     id="metadata94">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <defs
+     id="defs92">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path4146"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow1Mend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow1Mend"
+       style="overflow:visible">
+      <path
+         id="path3852"
+         d="M 0,0 5,-5 -12.5,0 5,5 0,0 z"
+         style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt"
+         transform="matrix(-0.4,0,0,-0.4,-4,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow1Mend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow1Mend-9"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path3852-7"
+         d="M 0,0 5,-5 -12.5,0 5,5 0,0 z"
+         style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt"
+         transform="matrix(-0.4,0,0,-0.4,-4,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-7"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-6"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-1"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-16"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-8"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-160"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-5"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-78"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-66"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-8"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-56"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-19"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-89"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-85"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-3"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-73"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-55"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-5"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-88"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-198"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-2"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-22"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="marker5072"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path5074"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-87"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-63"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-6"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-26"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-0"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-51"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1"
+     objecttolerance="10"
+     gridtolerance="10"
+     guidetolerance="10"
+     inkscape:pageopacity="0"
+     inkscape:pageshadow="2"
+     inkscape:window-width="1090"
+     inkscape:window-height="1148"
+     id="namedview90"
+     showgrid="true"
+     inkscape:zoom="0.80021373"
+     inkscape:cx="462.49289"
+     inkscape:cy="623.19585"
+     inkscape:window-x="557"
+     inkscape:window-y="24"
+     inkscape:window-maximized="0"
+     inkscape:current-layer="g4"
+     inkscape:snap-grids="false"
+     fit-margin-top="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5"
+     fit-margin-left="5" />
+  <g
+     style="fill:none;stroke-width:0.025in"
+     id="g4"
+     transform="translate(23.312813,523.41305)">
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 11475 2250 - 11475 3465-->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 11475 5625 - 11475 6840-->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 7875 225 - 10665 225-->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 9675 675 - 7785 675-->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 9675 4725 - 10665 4725-->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 9225 5175 - 10665 5175-->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 8775 11475 - 10665 11475-->
+    <!-- Line: box -->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 11475 9000 - 11475 10215-->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <g
+       id="g4104"
+       transform="translate(-1068.9745,0)">
+      <rect
+         transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)"
+         y="-7383.8755"
+         x="-6124.8989"
+         height="1966.2251"
+         width="1953.6969"
+         id="rect3032-1-0"
+         style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4098"
+         y="818.40338"
+         x="8168.2671"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="818.40338"
+           x="8168.2671"
+           id="tspan4100"
+           sodipodi:role="line">Idle or</tspan><tspan
+           id="tspan4102"
+           y="1152.4579"
+           x="8168.2671"
+           sodipodi:role="line">offline?</tspan></text>
+    </g>
+    <g
+       id="g4114"
+       transform="translate(0,147.96969)">
+      <rect
+         id="rect6"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1475.6636"
+         width="4401.7612"
+         y="0"
+         x="0" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110"
+         y="835.11212"
+         x="2206.4917"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="835.11212"
+           x="2206.4917"
+           id="tspan4112"
+           sodipodi:role="line">CPU N Start</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="M 4432.5052,897.4924 5684.8749,880.79414"
+       id="path4119"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="M 8503.0006,874.12161 9755.3703,857.42334"
+       id="path4119-8"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="8617.0977"
+       y="705.50983"
+       id="text4593"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4595"
+         x="8617.0977"
+         y="705.50983">Y</tspan></text>
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9"
+       transform="translate(9722.4732,131.27105)">
+      <rect
+         id="rect6-0"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="0"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5"
+         y="835.11212"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="835.11212"
+           x="1460.1007"
+           id="tspan4112-9"
+           sodipodi:role="line">Done</tspan></text>
+    </g>
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-5"
+       transform="translate(0,3705.3456)">
+      <rect
+         id="rect6-1"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1475.6636"
+         width="4401.7612"
+         y="0"
+         x="0" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-9"
+         y="835.11212"
+         x="2206.4917"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="835.11212"
+           x="2206.4917"
+           sodipodi:role="line"
+           id="tspan4776">Send IPI to CPU N</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="M 7102.5627,2263.5171 4430.8404,3682.8694"
+       id="path4119-3"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4104-1"
+       transform="translate(-1065.3349,6403.5782)">
+      <rect
+         transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)"
+         y="-7383.8755"
+         x="-6124.8989"
+         height="1966.2251"
+         width="1953.6969"
+         id="rect3032-1-0-6"
+         style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4098-3"
+         y="482.00006"
+         x="8168.2671"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           id="tspan4102-8"
+           y="482.00006"
+           x="8168.2671"
+           sodipodi:role="line">In RCU</tspan><tspan
+           y="816.05457"
+           x="8168.2671"
+           sodipodi:role="line"
+           id="tspan4833">read-side</tspan><tspan
+           y="1150.109"
+           x="8168.2671"
+           sodipodi:role="line"
+           id="tspan4835">critical</tspan><tspan
+           y="1484.1636"
+           x="8168.2671"
+           sodipodi:role="line"
+           id="tspan4837">section?</tspan></text>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="6463.0864"
+       y="2285.6765"
+       id="text4593-0"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4595-6"
+         x="6463.0864"
+         y="2285.6765">N</tspan></text>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654108, 80.17308215;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 2189.1897,5219.361 16.6983,1252.3697"
+       id="path4119-0"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-5-2"
+       transform="translate(0,6551.5479)">
+      <rect
+         id="rect6-1-7"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1475.6636"
+         width="4401.7612"
+         y="0"
+         x="0" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-9-5"
+         y="835.11212"
+         x="2206.4917"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="835.11212"
+           x="2206.4917"
+           sodipodi:role="line"
+           id="tspan4776-5">IPI Handler</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="m 4432.5052,7297.9678 1252.3697,-16.6982"
+       id="path4119-2"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="m 8503.0013,7278.6595 1252.369,-16.6982"
+       id="path4119-8-7"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="8617.0977"
+       y="7110.0186"
+       id="text4593-4"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4595-0"
+         x="8617.0977"
+         y="7110.0186">N</tspan></text>
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3"
+       transform="translate(9722.4732,6535.809)">
+      <rect
+         id="rect6-0-7"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7"
+         y="503.71591"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="503.71591"
+           x="1460.1007"
+           id="tspan4112-9-0"
+           sodipodi:role="line">Report CPU</tspan><tspan
+           y="837.77039"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4923">Quiescent</tspan><tspan
+           y="1171.825"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925">State</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654335, 80.17308669;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 7102.5627,8725.7454 16.6983,1252.3697"
+       id="path4119-0-0"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="6797.0522"
+       y="9018.6807"
+       id="text4593-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4595-2"
+         x="6797.0522"
+         y="9018.6807">Y</tspan></text>
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3-8"
+       transform="translate(-80.17308,11381.108)">
+      <rect
+         id="rect6-0-7-5"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7-6"
+         y="841.88086"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="841.88086"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-1">rcu_read_unlock()</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654562, 80.17309124;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 1362.6256,10071.26 16.6983,1252.369"
+       id="path4119-0-0-7"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 1362.6256,12883.919 16.6983,1252.369"
+       id="path4119-0-0-7-7"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3-8-1"
+       transform="translate(9722.4732,11389.458)">
+      <rect
+         id="rect6-0-7-5-1"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7-6-2"
+         y="841.88086"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="841.88086"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-1-2">Context Switch</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654789, 80.17309578;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 11165.272,10071.26 16.698,1252.369"
+       id="path4119-0-0-7-8"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3-9"
+       transform="translate(-80.17308,14163.046)">
+      <rect
+         id="rect6-0-7-1"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7-3"
+         y="503.71591"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="503.71591"
+           x="1460.1007"
+           id="tspan4112-9-0-4"
+           sodipodi:role="line">Report CPU</tspan><tspan
+           y="837.77039"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4923-3">and Task</tspan><tspan
+           y="1171.825"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-9">Quiescent States</tspan></text>
+    </g>
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3-8-1-8"
+       transform="translate(5663.2978,11389.458)">
+      <rect
+         id="rect6-0-7-5-1-1"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7-6-2-4"
+         y="841.88086"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="841.88086"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-1-2-4">Enqueue Task</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="M 9827.612,12141.988 8575.243,12125.29"
+       id="path4119-8-7-5"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 7106.0965,12818.962 16.6983,1252.369"
+       id="path4119-0-0-7-7-5"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3-9-2"
+       transform="translate(5663.2978,14098.088)">
+      <rect
+         id="rect6-0-7-1-8"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7-3-4"
+         y="503.71591"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="503.71591"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4923-3-2">Report CPU</tspan><tspan
+           y="837.77039"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-9-9">Quiescent</tspan><tspan
+           y="1171.825"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan5239">State</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654562, 80.17309124;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="M 5733.305,14095.542 2761.014,12809.774"
+       id="path4119-0-0-2"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654107, 80.17308214;stroke-dashoffset:0"
+       d="m 1353.3524,10079.499 9701.6916,0 100.189,-16.698"
+       id="path5265"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="ccc" />
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg
new file mode 100644
index 000000000000..e4233ac93c2b
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/ExpSchedFlow.svg
@@ -0,0 +1,826 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Creator: fig2dev Version 3.2 Patchlevel 5e -->
+
+<!-- CreationDate: Wed Dec  9 17:39:46 2015 -->
+
+<!-- Magnification: 3.000 -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="952.6817"
+   height="1425.6191"
+   viewBox="-66 -66 12729.905 19049.38"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="ExpSchedFlow.svg">
+  <metadata
+     id="metadata94">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <defs
+     id="defs92">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path4146"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow1Mend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow1Mend"
+       style="overflow:visible">
+      <path
+         id="path3852"
+         d="M 0,0 5,-5 -12.5,0 5,5 0,0 z"
+         style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt"
+         transform="matrix(-0.4,0,0,-0.4,-4,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow1Mend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow1Mend-9"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path3852-7"
+         d="M 0,0 5,-5 -12.5,0 5,5 0,0 z"
+         style="fill-rule:evenodd;stroke:#000000;stroke-width:1pt"
+         transform="matrix(-0.4,0,0,-0.4,-4,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-7"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-6"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-1"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-16"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-8"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-160"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-5"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-78"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-66"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-8"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-56"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-19"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-89"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-85"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-3"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-73"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-55"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-5"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-88"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-198"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-2"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-22"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="marker5072"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path5074"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-87"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-63"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-6"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-26"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-0"
+       style="overflow:visible">
+      <path
+         inkscape:connector-curvature="0"
+         id="path4146-51"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-58"
+       style="overflow:visible">
+      <path
+         id="path4146-61"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1"
+     objecttolerance="10"
+     gridtolerance="10"
+     guidetolerance="10"
+     inkscape:pageopacity="0"
+     inkscape:pageshadow="2"
+     inkscape:window-width="1090"
+     inkscape:window-height="1148"
+     id="namedview90"
+     showgrid="true"
+     inkscape:zoom="0.80021373"
+     inkscape:cx="462.49289"
+     inkscape:cy="473.6718"
+     inkscape:window-x="770"
+     inkscape:window-y="24"
+     inkscape:window-maximized="0"
+     inkscape:current-layer="g4114-9-3-9"
+     inkscape:snap-grids="false"
+     fit-margin-top="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5"
+     fit-margin-left="5" />
+  <g
+     style="fill:none;stroke-width:0.025in"
+     id="g4"
+     transform="translate(23.312814,523.41265)">
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 11475 2250 - 11475 3465-->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line: box -->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 11475 5625 - 11475 6840-->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 7875 225 - 10665 225-->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 9675 675 - 7785 675-->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 9675 4725 - 10665 4725-->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 9225 5175 - 10665 5175-->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 8775 11475 - 10665 11475-->
+    <!-- Line: box -->
+    <!-- Line -->
+    <!-- Arrowhead on XXXpoint 11475 9000 - 11475 10215-->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <!-- Text -->
+    <g
+       id="g4104"
+       transform="translate(-1068.9745,0)">
+      <rect
+         transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)"
+         y="-7383.8755"
+         x="-6124.8989"
+         height="1966.2251"
+         width="1953.6969"
+         id="rect3032-1-0"
+         style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4098"
+         y="818.40338"
+         x="8168.2671"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="818.40338"
+           x="8168.2671"
+           id="tspan4100"
+           sodipodi:role="line">Idle or</tspan><tspan
+           id="tspan4102"
+           y="1152.4579"
+           x="8168.2671"
+           sodipodi:role="line">offline?</tspan></text>
+    </g>
+    <g
+       id="g4114"
+       transform="translate(0,147.96969)">
+      <rect
+         id="rect6"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1475.6636"
+         width="4401.7612"
+         y="0"
+         x="0" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110"
+         y="835.11212"
+         x="2206.4917"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="835.11212"
+           x="2206.4917"
+           id="tspan4112"
+           sodipodi:role="line">CPU N Start</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="M 4432.5052,897.4924 5684.8749,880.79414"
+       id="path4119"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="M 8503.0006,874.12161 9755.3703,857.42334"
+       id="path4119-8"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="8617.0977"
+       y="705.50983"
+       id="text4593"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4595"
+         x="8617.0977"
+         y="705.50983">Y</tspan></text>
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9"
+       transform="translate(9722.4732,131.27105)">
+      <rect
+         id="rect6-0"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="0"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5"
+         y="835.11212"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="835.11212"
+           x="1460.1007"
+           id="tspan4112-9"
+           sodipodi:role="line">Done</tspan></text>
+    </g>
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-5"
+       transform="translate(0,3705.3456)">
+      <rect
+         id="rect6-1"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1475.6636"
+         width="4401.7612"
+         y="0"
+         x="0" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-9"
+         y="835.11212"
+         x="2206.4917"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="835.11212"
+           x="2206.4917"
+           sodipodi:role="line"
+           id="tspan4776">Send IPI to CPU N</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="M 7102.5627,2263.5171 4430.8404,3682.8694"
+       id="path4119-3"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4104-1"
+       transform="translate(-1065.3349,6403.5782)">
+      <rect
+         transform="matrix(-0.70710678,0.70710678,-0.70710678,-0.70710678,0,0)"
+         y="-7383.8755"
+         x="-6124.8989"
+         height="1966.2251"
+         width="1953.6969"
+         id="rect3032-1-0-6"
+         style="fill:#96ff96;fill-opacity:1;stroke:#000000;stroke-width:45.00382233;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4098-3"
+         y="985.4306"
+         x="8168.2671"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="985.4306"
+           x="8168.2671"
+           sodipodi:role="line"
+           id="tspan3109">CPU idle?</tspan></text>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="6463.0864"
+       y="2285.6765"
+       id="text4593-0"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4595-6"
+         x="6463.0864"
+         y="2285.6765">N</tspan></text>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654108, 80.17308215;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 2189.1897,5219.361 16.6983,1252.3697"
+       id="path4119-0"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-5-2"
+       transform="translate(0,6551.5479)">
+      <rect
+         id="rect6-1-7"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1475.6636"
+         width="4401.7612"
+         y="0"
+         x="0" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-9-5"
+         y="835.11212"
+         x="2206.4917"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="835.11212"
+           x="2206.4917"
+           sodipodi:role="line"
+           id="tspan4776-5">IPI Handler</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="m 4432.5052,7297.9678 1252.3697,-16.6982"
+       id="path4119-2"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow2Lend)"
+       d="m 8503.0013,7278.6595 1252.369,-16.6982"
+       id="path4119-8-7"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="8617.0977"
+       y="7110.0186"
+       id="text4593-4"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4595-0"
+         x="8617.0977"
+         y="7110.0186">Y</tspan></text>
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3"
+       transform="translate(9722.4732,6535.809)">
+      <rect
+         id="rect6-0-7"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7"
+         y="503.71591"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="503.71591"
+           x="1460.1007"
+           id="tspan4112-9-0"
+           sodipodi:role="line">Report CPU</tspan><tspan
+           y="837.77039"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4923">Quiescent</tspan><tspan
+           y="1171.825"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925">State</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654335, 80.17308669;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 7102.5627,11478.337 16.6983,1252.35"
+       id="path4119-0-0"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       style="font-size:267.24362183px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="6797.0522"
+       y="9018.6807"
+       id="text4593-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4595-2"
+         x="6797.0522"
+         y="9018.6807">N</tspan></text>
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3-8"
+       transform="translate(-80.17308,14133.68)">
+      <rect
+         id="rect6-0-7-5"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7-6"
+         y="841.88086"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="841.88086"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-1">Context Switch</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654562, 80.17309124;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 1362.6256,12823.832 16.6983,1252.369"
+       id="path4119-0-0-7"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 1362.6256,15636.491 16.6983,1252.369"
+       id="path4119-0-0-7-7"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3-8-1"
+       transform="translate(9722.4732,14142.03)">
+      <rect
+         id="rect6-0-7-5-1"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7-6-2"
+         y="841.88086"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="841.88086"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-1-2">CPU Offline</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654789, 80.17309578;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 11165.272,12823.832 16.698,1252.369"
+       id="path4119-0-0-7-8"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3-9"
+       transform="translate(-80.17308,16915.618)">
+      <rect
+         id="rect6-0-7-1"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7-3"
+         y="505.47754"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="505.47754"
+           x="1460.1007"
+           id="tspan4112-9-0-4"
+           sodipodi:role="line">Report CPU</tspan><tspan
+           y="839.53204"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-9">Quiescent</tspan><tspan
+           y="1173.5865"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan3168">State</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 11165.272,15571.534 16.698,1252.369"
+       id="path4119-0-0-7-7-5"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3-9-2"
+       transform="translate(9722.4732,16850.66)">
+      <rect
+         id="rect6-0-7-1-8"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7-3-4"
+         y="503.71591"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="503.71591"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4923-3-2">Report CPU</tspan><tspan
+           y="837.77039"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-9-9">Quiescent</tspan><tspan
+           y="1171.825"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan5239">State</tspan></text>
+    </g>
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:40.08654107, 80.17308214;stroke-dashoffset:0"
+       d="m 1353.3524,12832.071 9701.6916,0 100.189,-16.698"
+       id="path5265"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="ccc" />
+    <path
+       style="fill:none;stroke:#000000;stroke-width:40.08654022;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;marker-end:url(#Arrow2Lend)"
+       d="m 7112.6465,8669.1867 16.6983,1252.369"
+       id="path4119-0-0-7-7-5-7"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="cc" />
+    <g
+       style="fill:none;stroke-width:0.025in"
+       id="g4114-9-3-8-1-8-3"
+       transform="translate(5663.1399,9972.3627)">
+      <rect
+         id="rect6-0-7-5-1-1-9"
+         style="fill:#87cfff;stroke:#000000;stroke-width:45.00382233;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none"
+         rx="0"
+         height="1425.5687"
+         width="2748.6331"
+         y="29.467337"
+         x="80.17308" />
+      <text
+         sodipodi:linespacing="125%"
+         id="text4110-5-7-6-2-4-0"
+         y="841.88086"
+         x="1460.1007"
+         style="font-size:267.24359131px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         xml:space="preserve"><tspan
+           y="841.88086"
+           x="1460.1007"
+           sodipodi:role="line"
+           id="tspan4925-1-2-4-5">reched_cpu()</tspan></text>
+    </g>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
new file mode 100644
index 000000000000..7a3194c5559a
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
@@ -0,0 +1,626 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
+        "http://www.w3.org/TR/html4/loose.dtd">
+        <html>
+        <head><title>A Tour Through TREE_RCU's Expedited Grace Periods</title>
+        <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">
+
+<h2>Introduction</h2>
+
+This document describes RCU's expedited grace periods.
+Unlike RCU's normal grace periods, which accept long latencies to attain
+high efficiency and minimal disturbance, expedited grace periods accept
+lower efficiency and significant disturbance to attain shorter latencies.
+
+<p>
+There are three flavors of RCU (RCU-bh, RCU-preempt, and RCU-sched),
+but only two flavors of expedited grace periods because the RCU-bh
+expedited grace period maps onto the RCU-sched expedited grace period.
+Each of the remaining two implementations is covered in its own section.
+
+<ol>
+<li>	<a href="#Expedited Grace Period Design">
+	Expedited Grace Period Design</a>
+<li>	<a href="#RCU-preempt Expedited Grace Periods">
+	RCU-preempt Expedited Grace Periods</a>
+<li>	<a href="#RCU-sched Expedited Grace Periods">
+	RCU-sched Expedited Grace Periods</a>
+<li>	<a href="#Expedited Grace Period and CPU Hotplug">
+	Expedited Grace Period and CPU Hotplug</a>
+<li>	<a href="#Expedited Grace Period Refinements">
+	Expedited Grace Period Refinements</a>
+</ol>
+
+<h2><a name="Expedited Grace Period Design">
+Expedited Grace Period Design</a></h2>
+
+<p>
+The expedited RCU grace periods cannot be accused of being subtle,
+given that they for all intents and purposes hammer every CPU that
+has not yet provided a quiescent state for the current expedited
+grace period.
+The one saving grace is that the hammer has grown a bit smaller
+over time:  The old call to <tt>try_stop_cpus()</tt> has been
+replaced with a set of calls to <tt>smp_call_function_single()</tt>,
+each of which results in an IPI to the target CPU.
+The corresponding handler function checks the CPU's state, motivating
+a faster quiescent state where possible, and triggering a report
+of that quiescent state.
+As always for RCU, once everything has spent some time in a quiescent
+state, the expedited grace period has completed.
+
+<p>
+The details of the <tt>smp_call_function_single()</tt> handler's
+operation depend on the RCU flavor, as described in the following
+sections.
+
+<h2><a name="RCU-preempt Expedited Grace Periods">
+RCU-preempt Expedited Grace Periods</a></h2>
+
+<p>
+The overall flow of the handling of a given CPU by an RCU-preempt
+expedited grace period is shown in the following diagram:
+
+<p><img src="ExpRCUFlow.svg" alt="ExpRCUFlow.svg" width="55%">
+
+<p>
+The solid arrows denote direct action, for example, a function call.
+The dotted arrows denote indirect action, for example, an IPI
+or a state that is reached after some time.
+
+<p>
+If a given CPU is offline or idle, <tt>synchronize_rcu_expedited()</tt>
+will ignore it because idle and offline CPUs are already residing
+in quiescent states.
+Otherwise, the expedited grace period will use
+<tt>smp_call_function_single()</tt> to send the CPU an IPI, which
+is handled by <tt>sync_rcu_exp_handler()</tt>.
+
+<p>
+However, because this is preemptible RCU, <tt>sync_rcu_exp_handler()</tt>
+can check to see if the CPU is currently running in an RCU read-side
+critical section.
+If not, the handler can immediately report a quiescent state.
+Otherwise, it sets flags so that the outermost <tt>rcu_read_unlock()</tt>
+invocation will provide the needed quiescent-state report.
+This flag-setting avoids the previous forced preemption of all
+CPUs that might have RCU read-side critical sections.
+In addition, this flag-setting is done so as to avoid increasing
+the overhead of the common-case fastpath through the scheduler.
+
+<p>
+Again because this is preemptible RCU, an RCU read-side critical section
+can be preempted.
+When that happens, RCU will enqueue the task, which will the continue to
+block the current expedited grace period until it resumes and finds its
+outermost <tt>rcu_read_unlock()</tt>.
+The CPU will report a quiescent state just after enqueuing the task because
+the CPU is no longer blocking the grace period.
+It is instead the preempted task doing the blocking.
+The list of blocked tasks is managed by <tt>rcu_preempt_ctxt_queue()</tt>,
+which is called from <tt>rcu_preempt_note_context_switch()</tt>, which
+in turn is called from <tt>rcu_note_context_switch()</tt>, which in
+turn is called from the scheduler.
+
+<table>
+<tr><th>&nbsp;</th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+	Why not just have the expedited grace period check the
+	state of all the CPUs?
+	After all, that would avoid all those real-time-unfriendly IPIs.
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+	Because we want the RCU read-side critical sections to run fast,
+	which means no memory barriers.
+	Therefore, it is not possible to safely check the state from some
+	other CPU.
+	And even if it was possible to safely check the state, it would
+	still be necessary to IPI the CPU to safely interact with the
+	upcoming <tt>rcu_read_unlock()</tt> invocation, which means that
+	the remote state testing would not help the worst-case
+	latency that real-time applications care about.
+
+	<p><font color="ffffff">One way to prevent your real-time
+	application from getting hit with these IPIs is to
+	build your kernel with <tt>CONFIG_NO_HZ_FULL=y</tt>.
+	RCU would then perceive the CPU running your application
+	as being idle, and it would be able to safely detect that
+	state without needing to IPI the CPU.
+</font></td></tr>
+<tr><td>&nbsp;</td></tr>
+</table>
+
+<p>
+Please note that this is just the overall flow:
+Additional complications can arise due to races with CPUs going idle
+or offline, among other things.
+
+<h2><a name="RCU-sched Expedited Grace Periods">
+RCU-sched Expedited Grace Periods</a></h2>
+
+<p>
+The overall flow of the handling of a given CPU by an RCU-sched
+expedited grace period is shown in the following diagram:
+
+<p><img src="ExpSchedFlow.svg" alt="ExpSchedFlow.svg" width="55%">
+
+<p>
+As with RCU-preempt's <tt>synchronize_rcu_expedited()</tt>,
+<tt>synchronize_sched_expedited()</tt> ignores offline and
+idle CPUs, again because they are in remotely detectable
+quiescent states.
+However, the <tt>synchronize_rcu_expedited()</tt> handler
+is <tt>sync_sched_exp_handler()</tt>, and because the
+<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt>
+leave no trace of their invocation, in general it is not possible to tell
+whether or not the current CPU is in an RCU read-side critical section.
+The best that <tt>sync_sched_exp_handler()</tt> can do is to check
+for idle, on the off-chance that the CPU went idle while the IPI
+was in flight.
+If the CPU is idle, then tt>sync_sched_exp_handler()</tt> reports
+the quiescent state.
+
+<p>
+Otherwise, the handler invokes <tt>resched_cpu()</tt>, which forces
+a future context switch.
+At the time of the context switch, the CPU reports the quiescent state.
+Should the CPU go offline first, it will report the quiescent state
+at that time.
+
+<h2><a name="Expedited Grace Period and CPU Hotplug">
+Expedited Grace Period and CPU Hotplug</a></h2>
+
+<p>
+The expedited nature of expedited grace periods require a much tighter
+interaction with CPU hotplug operations than is required for normal
+grace periods.
+In addition, attempting to IPI offline CPUs will result in splats, but
+failing to IPI online CPUs can result in too-short grace periods.
+Neither option is acceptable in production kernels.
+
+<p>
+The interaction between expedited grace periods and CPU hotplug operations
+is carried out at several levels:
+
+<ol>
+<li>	The number of CPUs that have ever been online is tracked
+	by the <tt>rcu_state</tt> structure's <tt>-&gt;ncpus</tt>
+	field.
+	The <tt>rcu_state</tt> structure's <tt>-&gt;ncpus_snap</tt>
+	field tracks the number of CPUs that have ever been online
+	at the beginning of an RCU expedited grace period.
+	Note that this number never decreases, at least in the absence
+	of a time machine.
+<li>	The identities of the CPUs that have ever been online is
+	tracked by the <tt>rcu_node</tt> structure's
+	<tt>-&gt;expmaskinitnext</tt> field.
+	The <tt>rcu_node</tt> structure's <tt>-&gt;expmaskinit</tt>
+	field tracks the identities of the CPUs that were online
+	at least once at the beginning of the most recent RCU
+	expedited grace period.
+	The <tt>rcu_state</tt> structure's <tt>-&gt;ncpus</tt> and
+	<tt>-&gt;ncpus_snap</tt> fields are used to detect when
+	new CPUs have come online for the first time, that is,
+	when the <tt>rcu_node</tt> structure's <tt>-&gt;expmaskinitnext</tt>
+	field has changed since the beginning of the last RCU
+	expedited grace period, which triggers an update of each
+	<tt>rcu_node</tt> structure's <tt>-&gt;expmaskinit</tt>
+	field from its <tt>-&gt;expmaskinitnext</tt> field.
+<li>	Each <tt>rcu_node</tt> structure's <tt>-&gt;expmaskinit</tt>
+	field is used to initialize that structure's
+	<tt>-&gt;expmask</tt> at the beginning of each RCU
+	expedited grace period.
+	This means that only those CPUs that have been online at least
+	once will be considered for a given grace period.
+<li>	Any CPU that goes offline will clear its bit in its leaf
+	<tt>rcu_node</tt> structure's <tt>-&gt;qsmaskinitnext</tt>
+	field, so any CPU with that bit clear can safely be ignored.
+	However, it is possible for a CPU coming online or going offline
+	to have this bit set for some time while <tt>cpu_online</tt>
+	returns <tt>false</tt>.
+<li>	For each non-idle CPU that RCU believes is currently online, the grace
+	period invokes <tt>smp_call_function_single()</tt>.
+	If this succeeds, the CPU was fully online.
+	Failure indicates that the CPU is in the process of coming online
+	or going offline, in which case it is necessary to wait for a
+	short time period and try again.
+	The purpose of this wait (or series of waits, as the case may be)
+	is to permit a concurrent CPU-hotplug operation to complete.
+<li>	In the case of RCU-sched, one of the last acts of an outgoing CPU
+	is to invoke <tt>rcu_report_dead()</tt>, which
+	reports a quiescent state for that CPU.
+	However, this is likely paranoia-induced redundancy. <!-- @@@ -->
+</ol>
+
+<table>
+<tr><th>&nbsp;</th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+	Why all the dancing around with multiple counters and masks
+	tracking CPUs that were once online?
+	Why not just have a single set of masks tracking the currently
+	online CPUs and be done with it?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+	Maintaining single set of masks tracking the online CPUs <i>sounds</i>
+	easier, at least until you try working out all the race conditions
+	between grace-period initialization and CPU-hotplug operations.
+	For example, suppose initialization is progressing down the
+	tree while a CPU-offline operation is progressing up the tree.
+	This situation can result in bits set at the top of the tree
+	that have no counterparts at the bottom of the tree.
+	Those bits will never be cleared, which will result in
+	grace-period hangs.
+	In short, that way lies madness, to say nothing of a great many
+	bugs, hangs, and deadlocks.
+
+	<p><font color="ffffff">
+	In contrast, the current multi-mask multi-counter scheme ensures
+	that grace-period initialization will always see consistent masks
+	up and down the tree, which brings significant simplifications
+	over the single-mask method.
+
+	<p><font color="ffffff">
+	This is an instance of
+	<a href="http://www.cs.columbia.edu/~library/TR-repository/reports/reports-1992/cucs-039-92.ps.gz"><font color="ffffff">
+	deferring work in order to avoid synchronization</a>.
+	Lazily recording CPU-hotplug events at the beginning of the next
+	grace period greatly simplifies maintenance of the CPU-tracking
+	bitmasks in the <tt>rcu_node</tt> tree.
+</font></td></tr>
+<tr><td>&nbsp;</td></tr>
+</table>
+
+<h2><a name="Expedited Grace Period Refinements">
+Expedited Grace Period Refinements</a></h2>
+
+<ol>
+<li>	<a href="#Idle-CPU Checks">Idle-CPU checks</a>.
+<li>	<a href="#Batching via Sequence Counter">
+	Batching via sequence counter</a>.
+<li>	<a href="#Funnel Locking and Wait/Wakeup">
+	Funnel locking and wait/wakeup</a>.
+<li>	<a href="#Use of Workqueues">Use of Workqueues</a>.
+<li>	<a href="#Stall Warnings">Stall warnings</a>.
+</ol>
+
+<h3><a name="Idle-CPU Checks">Idle-CPU Checks</a></h3>
+
+<p>
+Each expedited grace period checks for idle CPUs when initially forming
+the mask of CPUs to be IPIed and again just before IPIing a CPU
+(both checks are carried out by <tt>sync_rcu_exp_select_cpus()</tt>).
+If the CPU is idle at any time between those two times, the CPU will
+not be IPIed.
+Instead, the task pushing the grace period forward will include the
+idle CPUs in the mask passed to <tt>rcu_report_exp_cpu_mult()</tt>.
+
+<p>
+For RCU-sched, there is an additional check for idle in the IPI
+handler, <tt>sync_sched_exp_handler()</tt>.
+If the IPI has interrupted the idle loop, then
+<tt>sync_sched_exp_handler()</tt> invokes <tt>rcu_report_exp_rdp()</tt>
+to report the corresponding quiescent state.
+
+<p>
+For RCU-preempt, there is no specific check for idle in the
+IPI handler (<tt>sync_rcu_exp_handler()</tt>), but because
+RCU read-side critical sections are not permitted within the
+idle loop, if <tt>sync_rcu_exp_handler()</tt> sees that the CPU is within
+RCU read-side critical section, the CPU cannot possibly be idle.
+Otherwise, <tt>sync_rcu_exp_handler()</tt> invokes
+<tt>rcu_report_exp_rdp()</tt> to report the corresponding quiescent
+state, regardless of whether or not that quiescent state was due to
+the CPU being idle.
+
+<p>
+In summary, RCU expedited grace periods check for idle when building
+the bitmask of CPUs that must be IPIed, just before sending each IPI,
+and (either explicitly or implicitly) within the IPI handler.
+
+<h3><a name="Batching via Sequence Counter">
+Batching via Sequence Counter</a></h3>
+
+<p>
+If each grace-period request was carried out separately, expedited
+grace periods would have abysmal scalability and
+problematic high-load characteristics.
+Because each grace-period operation can serve an unlimited number of
+updates, it is important to <i>batch</i> requests, so that a single
+expedited grace-period operation will cover all requests in the
+corresponding batch.
+
+<p>
+This batching is controlled by a sequence counter named
+<tt>-&gt;expedited_sequence</tt> in the <tt>rcu_state</tt> structure.
+This counter has an odd value when there is an expedited grace period
+in progress and an even value otherwise, so that dividing the counter
+value by two gives the number of completed grace periods.
+During any given update request, the counter must transition from
+even to odd and then back to even, thus indicating that a grace
+period has elapsed.
+Therefore, if the initial value of the counter is <tt>s</tt>,
+the updater must wait until the counter reaches at least the
+value <tt>(s+3)&amp;~0x1</tt>.
+This counter is managed by the following access functions:
+
+<ol>
+<li>	<tt>rcu_exp_gp_seq_start()</tt>, which marks the start of
+	an expedited grace period.
+<li>	<tt>rcu_exp_gp_seq_end()</tt>, which marks the end of an
+	expedited grace period.
+<li>	<tt>rcu_exp_gp_seq_snap()</tt>, which obtains a snapshot of
+	the counter.
+<li>	<tt>rcu_exp_gp_seq_done()</tt>, which returns <tt>true</tt>
+	if a full expedited grace period has elapsed since the
+	corresponding call to <tt>rcu_exp_gp_seq_snap()</tt>.
+</ol>
+
+<p>
+Again, only one request in a given batch need actually carry out
+a grace-period operation, which means there must be an efficient
+way to identify which of many concurrent reqeusts will initiate
+the grace period, and that there be an efficient way for the
+remaining requests to wait for that grace period to complete.
+However, that is the topic of the next section.
+
+<h3><a name="Funnel Locking and Wait/Wakeup">
+Funnel Locking and Wait/Wakeup</a></h3>
+
+<p>
+The natural way to sort out which of a batch of updaters will initiate
+the expedited grace period is to use the <tt>rcu_node</tt> combining
+tree, as implemented by the <tt>exp_funnel_lock()</tt> function.
+The first updater corresponding to a given grace period arriving
+at a given <tt>rcu_node</tt> structure records its desired grace-period
+sequence number in the <tt>-&gt;exp_seq_rq</tt> field and moves up
+to the next level in the tree.
+Otherwise, if the <tt>-&gt;exp_seq_rq</tt> field already contains
+the sequence number for the desired grace period or some later one,
+the updater blocks on one of four wait queues in the
+<tt>-&gt;exp_wq[]</tt> array, using the second-from-bottom
+and third-from bottom bits as an index.
+An <tt>-&gt;exp_lock</tt> field in the <tt>rcu_node</tt> structure
+synchronizes access to these fields.
+
+<p>
+An empty <tt>rcu_node</tt> tree is shown in the following diagram,
+with the white cells representing the <tt>-&gt;exp_seq_rq</tt> field
+and the red cells representing the elements of the
+<tt>-&gt;exp_wq[]</tt> array.
+
+<p><img src="Funnel0.svg" alt="Funnel0.svg" width="75%">
+
+<p>
+The next diagram shows the situation after the arrival of Task&nbsp;A
+and Task&nbsp;B at the leftmost and rightmost leaf <tt>rcu_node</tt>
+structures, respectively.
+The current value of the <tt>rcu_state</tt> structure's
+<tt>-&gt;expedited_sequence</tt> field is zero, so adding three and
+clearing the bottom bit results in the value two, which both tasks
+record in the <tt>-&gt;exp_seq_rq</tt> field of their respective
+<tt>rcu_node</tt> structures:
+
+<p><img src="Funnel1.svg" alt="Funnel1.svg" width="75%">
+
+<p>
+Each of Tasks&nbsp;A and&nbsp;B will move up to the root
+<tt>rcu_node</tt> structure.
+Suppose that Task&nbsp;A wins, recording its desired grace-period sequence
+number and resulting in the state shown below:
+
+<p><img src="Funnel2.svg" alt="Funnel2.svg" width="75%">
+
+<p>
+Task&nbsp;A now advances to initiate a new grace period, while Task&nbsp;B
+moves up to the root <tt>rcu_node</tt> structure, and, seeing that
+its desired sequence number is already recorded, blocks on
+<tt>-&gt;exp_wq[1]</tt>.
+
+<table>
+<tr><th>&nbsp;</th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+	Why <tt>-&gt;exp_wq[1]</tt>?
+	Given that the value of these tasks' desired sequence number is
+	two, so shouldn't they instead block on <tt>-&gt;exp_wq[2]</tt>?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+	No.
+
+	<p><font color="ffffff">
+	Recall that the bottom bit of the desired sequence number indicates
+	whether or not a grace period is currently in progress.
+	It is therefore necessary to shift the sequence number right one
+	bit position to obtain the number of the grace period.
+	This results in <tt>-&gt;exp_wq[1]</tt>.
+</font></td></tr>
+<tr><td>&nbsp;</td></tr>
+</table>
+
+<p>
+If Tasks&nbsp;C and&nbsp;D also arrive at this point, they will compute the
+same desired grace-period sequence number, and see that both leaf
+<tt>rcu_node</tt> structures already have that value recorded.
+They will therefore block on their respective <tt>rcu_node</tt>
+structures' <tt>-&gt;exp_wq[1]</tt> fields, as shown below:
+
+<p><img src="Funnel3.svg" alt="Funnel3.svg" width="75%">
+
+<p>
+Task&nbsp;A now acquires the <tt>rcu_state</tt> structure's
+<tt>-&gt;exp_mutex</tt> and initiates the grace period, which
+increments <tt>-&gt;expedited_sequence</tt>.
+Therefore, if Tasks&nbsp;E and&nbsp;F arrive, they will compute
+a desired sequence number of 4 and will record this value as
+shown below:
+
+<p><img src="Funnel4.svg" alt="Funnel4.svg" width="75%">
+
+<p>
+Tasks&nbsp;E and&nbsp;F will propagate up the <tt>rcu_node</tt>
+combining tree, with Task&nbsp;F blocking on the root <tt>rcu_node</tt>
+structure and Task&nbsp;E wait for Task&nbsp;A to finish so that
+it can start the next grace period.
+The resulting state is as shown below:
+
+<p><img src="Funnel5.svg" alt="Funnel5.svg" width="75%">
+
+<p>
+Once the grace period completes, Task&nbsp;A
+starts waking up the tasks waiting for this grace period to complete,
+increments the <tt>-&gt;expedited_sequence</tt>,
+acquires the <tt>-&gt;exp_wake_mutex</tt> and then releases the
+<tt>-&gt;exp_mutex</tt>.
+This results in the following state:
+
+<p><img src="Funnel6.svg" alt="Funnel6.svg" width="75%">
+
+<p>
+Task&nbsp;E can then acquire <tt>-&gt;exp_mutex</tt> and increment
+<tt>-&gt;expedited_sequence</tt> to the value three.
+If new tasks&nbsp;G and&nbsp;H arrive and moves up the combining tree at the
+same time, the state will be as follows:
+
+<p><img src="Funnel7.svg" alt="Funnel7.svg" width="75%">
+
+<p>
+Note that three of the root <tt>rcu_node</tt> structure's
+waitqueues are now occupied.
+However, at some point, Task&nbsp;A will wake up the
+tasks blocked on the <tt>-&gt;exp_wq</tt> waitqueues, resulting
+in the following state:
+
+<p><img src="Funnel8.svg" alt="Funnel8.svg" width="75%">
+
+<p>
+Execution will continue with Tasks&nbsp;E and&nbsp;H completing
+their grace periods and carrying out their wakeups.
+
+<table>
+<tr><th>&nbsp;</th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+	What happens if Task&nbsp;A takes so long to do its wakeups
+	that Task&nbsp;E's grace period completes?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+	Then Task&nbsp;E will block on the <tt>-&gt;exp_wake_mutex</tt>,
+	which will also prevent it from releasing <tt>-&gt;exp_mutex</tt>,
+	which in turn will prevent the next grace period from starting.
+	This last is important in preventing overflow of the
+	<tt>-&gt;exp_wq[]</tt> array.
+</font></td></tr>
+<tr><td>&nbsp;</td></tr>
+</table>
+
+<h3><a name="Use of Workqueues">Use of Workqueues</a></h3>
+
+<p>
+In earlier implementations, the task requesting the expedited
+grace period also drove it to completion.
+This straightforward approach had the disadvantage of needing to
+account for signals sent to user tasks,
+so more recent implemementations use the Linux kernel's
+<a href="https://www.kernel.org/doc/Documentation/workqueue.txt">workqueues</a>.
+
+<p>
+The requesting task still does counter snapshotting and funnel-lock
+processing, but the task reaching the top of the funnel lock
+does a <tt>schedule_work()</tt> (from <tt>_synchronize_rcu_expedited()</tt>
+so that a workqueue kthread does the actual grace-period processing.
+Because workqueue kthreads do not accept signals, grace-period-wait
+processing need not allow for signals.
+
+In addition, this approach allows wakeups for the previous expedited
+grace period to be overlapped with processing for the next expedited
+grace period.
+Because there are only four sets of waitqueues, it is necessary to
+ensure that the previous grace period's wakeups complete before the
+next grace period's wakeups start.
+This is handled by having the <tt>-&gt;exp_mutex</tt>
+guard expedited grace-period processing and the
+<tt>-&gt;exp_wake_mutex</tt> guard wakeups.
+The key point is that the <tt>-&gt;exp_mutex</tt> is not released
+until the first wakeup is complete, which means that the
+<tt>-&gt;exp_wake_mutex</tt> has already been acquired at that point.
+This approach ensures that the previous grace period's wakeups can
+be carried out while the current grace period is in process, but
+that these wakeups will complete before the next grace period starts.
+This means that only three waitqueues are required, guaranteeing that
+the four that are provided are sufficient.
+
+<h3><a name="Stall Warnings">Stall Warnings</a></h3>
+
+<p>
+Expediting grace periods does nothing to speed things up when RCU
+readers take too long, and therefore expedited grace periods check
+for stalls just as normal grace periods do.
+
+<table>
+<tr><th>&nbsp;</th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+	But why not just let the normal grace-period machinery
+	detect the stalls, given that a given reader must block
+	both normal and expedited grace periods?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+	Because it is quite possible that at a given time there
+	is no normal grace period in progress, in which case the
+	normal grace period cannot emit a stall warning.
+</font></td></tr>
+<tr><td>&nbsp;</td></tr>
+</table>
+
+The <tt>synchronize_sched_expedited_wait()</tt> function loops waiting
+for the expedited grace period to end, but with a timeout set to the
+current RCU CPU stall-warning time.
+If this time is exceeded, any CPUs or <tt>rcu_node</tt> structures
+blocking the current grace period are printed.
+Each stall warning results in another pass through the loop, but the
+second and subsequent passes use longer stall times.
+
+<h3><a name="Summary">
+Summary</a></h3>
+
+<p>
+Expedited grace periods use a sequence-number approach to promote
+batching, so that a single grace-period operation can serve numerous
+requests.
+A funnel lock is used to efficiently identify the one task out of
+a concurrent group that will request the grace period.
+All members of the group will block on waitqueues provided in
+the <tt>rcu_node</tt> structure.
+The actual grace-period processing is carried out by a workqueue.
+
+<p>
+CPU-hotplug operations are noted lazily in order to prevent the need
+for tight synchronization between expedited grace periods and
+CPU-hotplug operations.
+The dyntick-idle counters are used to avoid sending IPIs to idle CPUs,
+at least in the common case.
+RCU-preempt and RCU-sched use different IPI handlers and different
+code to respond to the state changes carried out by those handlers,
+but otherwise use common code.
+
+<p>
+Quiescent states are tracked using the <tt>rcu_node</tt> tree,
+and once all necessary quiescent states have been reported,
+all tasks waiting on this expedited grace period are awakened.
+A pair of mutexes are used to allow one grace period's wakeups
+to proceed concurrently with the next grace period's processing.
+
+<p>
+This combination of mechanisms allows expedited grace periods to
+run reasonably efficiently.
+However, for non-time-critical tasks, normal grace periods should be
+used instead because their longer duration permits much higher
+degrees of batching, and thus much lower per-request overheads.
+
+</body></html>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel0.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel0.svg
new file mode 100644
index 000000000000..98af66557908
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel0.svg
@@ -0,0 +1,275 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="490.05093"
+   height="125.78741"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="Funnel0.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="201.06495"
+     inkscape:cy="-86.548414"
+     inkscape:document-units="px"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="171"
+     inkscape:window-y="279"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-117.08462,-249.92053)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="362.371"
+       y="262.51819"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="362.371"
+         y="262.51819">-&gt;expedited_sequence: 0</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101"
+       width="43.158947"
+       height="26.33428"
+       x="253.55223"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3"
+       width="43.158947"
+       height="26.33428"
+       x="297.04141"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6"
+       width="43.158947"
+       height="26.33428"
+       x="427.509"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7"
+       width="43.158947"
+       height="26.33428"
+       x="384.01981"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7-5"
+       width="43.158947"
+       height="26.33428"
+       x="340.53061"
+       y="275.07489" />
+    <g
+       id="g3997"
+       transform="translate(-0.87295532,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="145.45404"
+         y="360.25174"
+         id="text3013"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015"
+           x="145.45404"
+           y="360.25174"
+           style="font-size:10px">:0</tspan></text>
+    </g>
+    <g
+       id="g3997-7"
+       transform="translate(260.06223,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35-0"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9-3"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1-6"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2-0"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="145.45404"
+         y="360.25174"
+         id="text3013-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6"
+           x="145.45404"
+           y="360.25174"
+           style="font-size:10px">:0</tspan></text>
+    </g>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel1.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel1.svg
new file mode 100644
index 000000000000..e0184a37aec7
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel1.svg
@@ -0,0 +1,275 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="490.05093"
+   height="125.78741"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="Funnel1.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="201.06495"
+     inkscape:cy="-86.548414"
+     inkscape:document-units="px"
+     inkscape:current-layer="g3997-7"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="363"
+     inkscape:window-y="336"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-117.08462,-249.92053)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="362.371"
+       y="262.51819"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="362.371"
+         y="262.51819">-&gt;expedited_sequence: 0</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101"
+       width="43.158947"
+       height="26.33428"
+       x="253.55223"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3"
+       width="43.158947"
+       height="26.33428"
+       x="297.04141"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6"
+       width="43.158947"
+       height="26.33428"
+       x="427.509"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7"
+       width="43.158947"
+       height="26.33428"
+       x="384.01981"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7-5"
+       width="43.158947"
+       height="26.33428"
+       x="340.53061"
+       y="275.07489" />
+    <g
+       id="g3997"
+       transform="translate(-0.87295532,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="146.00092"
+         y="360.25174"
+         id="text3013"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015"
+           x="146.00092"
+           y="360.25174"
+           style="font-size:10px">A:2</tspan></text>
+    </g>
+    <g
+       id="g3997-7"
+       transform="translate(260.06223,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35-0"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9-3"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1-6"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2-0"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="145.54926"
+         y="360.25174"
+         id="text3013-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6"
+           x="145.54926"
+           y="360.25174"
+           style="font-size:10px">B:2</tspan></text>
+    </g>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel2.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel2.svg
new file mode 100644
index 000000000000..1bc3fed54d58
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel2.svg
@@ -0,0 +1,287 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="490.05093"
+   height="125.78741"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="Funnel2.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="114.01552"
+     inkscape:cy="-86.548414"
+     inkscape:document-units="px"
+     inkscape:current-layer="g3997-7"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="363"
+     inkscape:window-y="336"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-117.08462,-249.92053)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="362.371"
+       y="262.51819"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="362.371"
+         y="262.51819">-&gt;expedited_sequence: 0</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101"
+       width="43.158947"
+       height="26.33428"
+       x="253.55223"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3"
+       width="43.158947"
+       height="26.33428"
+       x="297.04141"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6"
+       width="43.158947"
+       height="26.33428"
+       x="427.509"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7"
+       width="43.158947"
+       height="26.33428"
+       x="384.01981"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7-5"
+       width="43.158947"
+       height="26.33428"
+       x="340.53061"
+       y="275.07489" />
+    <g
+       id="g3997"
+       transform="translate(-0.87295532,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="146.00092"
+         y="360.25174"
+         id="text3013"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015"
+           x="146.00092"
+           y="360.25174"
+           style="font-size:10px">:2</tspan></text>
+    </g>
+    <g
+       id="g3997-7"
+       transform="translate(260.06223,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35-0"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9-3"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1-6"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2-0"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="145.54926"
+         y="360.25174"
+         id="text3013-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6"
+           x="145.54926"
+           y="360.25174"
+           style="font-size:10px">B:2</tspan></text>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="275.59558"
+       y="291.95297"
+       id="text3013-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-7"
+         x="275.59558"
+         y="291.95297"
+         style="font-size:10px">A:2</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel3.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel3.svg
new file mode 100644
index 000000000000..6d8a1bffb3e4
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel3.svg
@@ -0,0 +1,323 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="490.05093"
+   height="125.78741"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="Funnel3.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="114.01552"
+     inkscape:cy="-86.548414"
+     inkscape:document-units="px"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="68"
+     inkscape:window-y="180"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-117.08462,-249.92053)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="362.371"
+       y="262.51819"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="362.371"
+         y="262.51819">-&gt;expedited_sequence: 0  GP: A</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101"
+       width="43.158947"
+       height="26.33428"
+       x="253.55223"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3"
+       width="43.158947"
+       height="26.33428"
+       x="297.04141"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6"
+       width="43.158947"
+       height="26.33428"
+       x="427.509"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7"
+       width="43.158947"
+       height="26.33428"
+       x="384.01981"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7-5"
+       width="43.158947"
+       height="26.33428"
+       x="340.53061"
+       y="275.07489" />
+    <g
+       id="g3997"
+       transform="translate(-0.87295532,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="146.00092"
+         y="360.25174"
+         id="text3013"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015"
+           x="146.00092"
+           y="360.25174"
+           style="font-size:10px">:2</tspan></text>
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="232.51051"
+         y="360.18094"
+         id="text3013-3-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6-6"
+           x="232.51051"
+           y="360.18094"
+           style="font-size:10px">C</tspan></text>
+    </g>
+    <g
+       id="g3019"
+       transform="translate(260.06223,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35-0"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62-9"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9-3"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1-6"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2-0"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="145.54926"
+         y="360.25174"
+         id="text3013-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6"
+           x="145.54926"
+           y="360.25174"
+           style="font-size:10px">:2</tspan></text>
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="232.31764"
+         y="360.18582"
+         id="text3013-3-3-7"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6-6-5"
+           x="232.31764"
+           y="360.18582"
+           style="font-size:10px">D</tspan></text>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="275.59558"
+       y="291.95297"
+       id="text3013-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-7"
+         x="275.59558"
+         y="291.95297"
+         style="font-size:10px">:2</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="361.97092"
+       y="291.88705"
+       id="text3013-3-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7"
+         x="361.97092"
+         y="291.88705"
+         style="font-size:10px">B</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel4.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel4.svg
new file mode 100644
index 000000000000..44018fd6342b
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel4.svg
@@ -0,0 +1,323 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="490.05093"
+   height="125.78741"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="Funnel4.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="114.01552"
+     inkscape:cy="-86.548414"
+     inkscape:document-units="px"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="68"
+     inkscape:window-y="180"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-117.08462,-249.92053)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="362.371"
+       y="262.51819"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="362.371"
+         y="262.51819">-&gt;expedited_sequence: 1  GP: A</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101"
+       width="43.158947"
+       height="26.33428"
+       x="253.55223"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3"
+       width="43.158947"
+       height="26.33428"
+       x="297.04141"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6"
+       width="43.158947"
+       height="26.33428"
+       x="427.509"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7"
+       width="43.158947"
+       height="26.33428"
+       x="384.01981"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7-5"
+       width="43.158947"
+       height="26.33428"
+       x="340.53061"
+       y="275.07489" />
+    <g
+       id="g3997"
+       transform="translate(-0.87295532,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="146.00092"
+         y="360.25174"
+         id="text3013"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015"
+           x="146.00092"
+           y="360.25174"
+           style="font-size:10px">E:4</tspan></text>
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="232.51051"
+         y="360.18094"
+         id="text3013-3-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6-6"
+           x="232.51051"
+           y="360.18094"
+           style="font-size:10px">C</tspan></text>
+    </g>
+    <g
+       id="g3019"
+       transform="translate(260.06223,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35-0"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62-9"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9-3"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1-6"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2-0"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="145.54926"
+         y="360.25174"
+         id="text3013-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6"
+           x="145.54926"
+           y="360.25174"
+           style="font-size:10px">F:4</tspan></text>
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="232.31764"
+         y="360.18582"
+         id="text3013-3-3-7"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6-6-5"
+           x="232.31764"
+           y="360.18582"
+           style="font-size:10px">D</tspan></text>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="275.59558"
+       y="291.95297"
+       id="text3013-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-7"
+         x="275.59558"
+         y="291.95297"
+         style="font-size:10px">:2</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="361.97092"
+       y="291.88705"
+       id="text3013-3-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7"
+         x="361.97092"
+         y="291.88705"
+         style="font-size:10px">B</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel5.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel5.svg
new file mode 100644
index 000000000000..e5eef50454fb
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel5.svg
@@ -0,0 +1,335 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="490.05093"
+   height="125.78741"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="Funnel5.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="114.01552"
+     inkscape:cy="-86.548414"
+     inkscape:document-units="px"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="68"
+     inkscape:window-y="180"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-117.08462,-249.92053)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="362.371"
+       y="262.51819"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="362.371"
+         y="262.51819">-&gt;expedited_sequence: 1  GP: A,E</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101"
+       width="43.158947"
+       height="26.33428"
+       x="253.55223"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3"
+       width="43.158947"
+       height="26.33428"
+       x="297.04141"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6"
+       width="43.158947"
+       height="26.33428"
+       x="427.509"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7"
+       width="43.158947"
+       height="26.33428"
+       x="384.01981"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7-5"
+       width="43.158947"
+       height="26.33428"
+       x="340.53061"
+       y="275.07489" />
+    <g
+       id="g3997"
+       transform="translate(-0.87295532,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="146.00092"
+         y="360.25174"
+         id="text3013"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015"
+           x="146.00092"
+           y="360.25174"
+           style="font-size:10px">:4</tspan></text>
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="232.51051"
+         y="360.18094"
+         id="text3013-3-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6-6"
+           x="232.51051"
+           y="360.18094"
+           style="font-size:10px">C</tspan></text>
+    </g>
+    <g
+       id="g3019"
+       transform="translate(260.06223,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35-0"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62-9"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9-3"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1-6"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2-0"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="145.54926"
+         y="360.25174"
+         id="text3013-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6"
+           x="145.54926"
+           y="360.25174"
+           style="font-size:10px">:4</tspan></text>
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="232.31764"
+         y="360.18582"
+         id="text3013-3-3-7"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6-6-5"
+           x="232.31764"
+           y="360.18582"
+           style="font-size:10px">D</tspan></text>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="275.59558"
+       y="291.95297"
+       id="text3013-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-7"
+         x="275.59558"
+         y="291.95297"
+         style="font-size:10px">:4</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="361.97092"
+       y="291.88705"
+       id="text3013-3-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7"
+         x="361.97092"
+         y="291.88705"
+         style="font-size:10px">B</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="405.40396"
+       y="291.88705"
+       id="text3013-3-36-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7-6"
+         x="405.40396"
+         y="291.88705"
+         style="font-size:10px">F</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel6.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel6.svg
new file mode 100644
index 000000000000..fbd2c1892886
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel6.svg
@@ -0,0 +1,335 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="490.05093"
+   height="125.78741"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="Funnel6.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="114.01552"
+     inkscape:cy="-86.548414"
+     inkscape:document-units="px"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="68"
+     inkscape:window-y="180"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-117.08462,-249.92053)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="362.371"
+       y="262.51819"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="362.371"
+         y="262.51819">-&gt;expedited_sequence: 2  GP: E  Wakeup: A</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101"
+       width="43.158947"
+       height="26.33428"
+       x="253.55223"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3"
+       width="43.158947"
+       height="26.33428"
+       x="297.04141"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6"
+       width="43.158947"
+       height="26.33428"
+       x="427.509"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7"
+       width="43.158947"
+       height="26.33428"
+       x="384.01981"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7-5"
+       width="43.158947"
+       height="26.33428"
+       x="340.53061"
+       y="275.07489" />
+    <g
+       id="g3997"
+       transform="translate(-0.87295532,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="146.00092"
+         y="360.25174"
+         id="text3013"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015"
+           x="146.00092"
+           y="360.25174"
+           style="font-size:10px">:4</tspan></text>
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="232.51051"
+         y="360.18094"
+         id="text3013-3-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6-6"
+           x="232.51051"
+           y="360.18094"
+           style="font-size:10px">C</tspan></text>
+    </g>
+    <g
+       id="g3019"
+       transform="translate(260.06223,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35-0"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62-9"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9-3"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1-6"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2-0"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="145.54926"
+         y="360.25174"
+         id="text3013-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6"
+           x="145.54926"
+           y="360.25174"
+           style="font-size:10px">:4</tspan></text>
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="232.31764"
+         y="360.18582"
+         id="text3013-3-3-7"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6-6-5"
+           x="232.31764"
+           y="360.18582"
+           style="font-size:10px">D</tspan></text>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="275.59558"
+       y="291.95297"
+       id="text3013-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-7"
+         x="275.59558"
+         y="291.95297"
+         style="font-size:10px">:4</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="361.97092"
+       y="291.88705"
+       id="text3013-3-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7"
+         x="361.97092"
+         y="291.88705"
+         style="font-size:10px">B</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="405.40396"
+       y="291.88705"
+       id="text3013-3-36-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7-6"
+         x="405.40396"
+         y="291.88705"
+         style="font-size:10px">F</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel7.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel7.svg
new file mode 100644
index 000000000000..502e159ed278
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel7.svg
@@ -0,0 +1,347 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="490.05093"
+   height="125.78741"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="Funnel7.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="114.01552"
+     inkscape:cy="-86.548414"
+     inkscape:document-units="px"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="68"
+     inkscape:window-y="180"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-117.08462,-249.92053)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="362.371"
+       y="262.51819"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="362.371"
+         y="262.51819">-&gt;expedited_sequence: 3  GP: E,H  Wakeup: A</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101"
+       width="43.158947"
+       height="26.33428"
+       x="253.55223"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3"
+       width="43.158947"
+       height="26.33428"
+       x="297.04141"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101-3-6"
+       width="43.158947"
+       height="26.33428"
+       x="427.509"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7"
+       width="43.158947"
+       height="26.33428"
+       x="384.01981"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7-5"
+       width="43.158947"
+       height="26.33428"
+       x="340.53061"
+       y="275.07489" />
+    <g
+       id="g3997"
+       transform="translate(-0.87295532,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="146.00092"
+         y="360.25174"
+         id="text3013"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015"
+           x="146.00092"
+           y="360.25174"
+           style="font-size:10px">:4</tspan></text>
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="232.51051"
+         y="360.18094"
+         id="text3013-3-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6-6"
+           x="232.51051"
+           y="360.18094"
+           style="font-size:10px">C</tspan></text>
+    </g>
+    <g
+       id="g3019"
+       transform="translate(260.06223,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35-0"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62-9"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9-3"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1-6"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2-0"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="145.54926"
+         y="360.25174"
+         id="text3013-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6"
+           x="145.54926"
+           y="360.25174"
+           style="font-size:10px">:6</tspan></text>
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="232.31764"
+         y="360.18582"
+         id="text3013-3-3-7"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6-6-5"
+           x="232.31764"
+           y="360.18582"
+           style="font-size:10px">D</tspan></text>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="275.59558"
+       y="291.95297"
+       id="text3013-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-7"
+         x="275.59558"
+         y="291.95297"
+         style="font-size:10px">:6</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="361.97092"
+       y="291.88705"
+       id="text3013-3-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7"
+         x="361.97092"
+         y="291.88705"
+         style="font-size:10px">B</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="405.40396"
+       y="291.88705"
+       id="text3013-3-36-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7-6"
+         x="405.40396"
+         y="291.88705"
+         style="font-size:10px">F</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="449.22031"
+       y="291.88217"
+       id="text3013-3-36-3-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7-6-6"
+         x="449.22031"
+         y="291.88217"
+         style="font-size:10px">G</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel8.svg b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel8.svg
new file mode 100644
index 000000000000..677401551c7d
--- /dev/null
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Funnel8.svg
@@ -0,0 +1,311 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="490.05093"
+   height="125.78741"
+   id="svg2"
+   version="1.1"
+   inkscape:version="0.48.4 r9939"
+   sodipodi:docname="Funnel8.svg">
+  <defs
+     id="defs4">
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend"
+       style="overflow:visible">
+      <path
+         id="path3792"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart"
+       style="overflow:visible">
+      <path
+         id="path3789"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lstart"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lstart-4"
+       style="overflow:visible">
+      <path
+         id="path3789-9"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(1.1,0,0,1.1,1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+    <marker
+       inkscape:stockid="Arrow2Lend"
+       orient="auto"
+       refY="0"
+       refX="0"
+       id="Arrow2Lend-4"
+       style="overflow:visible">
+      <path
+         id="path3792-4"
+         style="fill-rule:evenodd;stroke-width:0.625;stroke-linejoin:round"
+         d="M 8.7185878,4.0337352 -2.2072895,0.01601326 8.7185884,-4.0017078 c -1.7454984,2.3720609 -1.7354408,5.6174519 -6e-7,8.035443 z"
+         transform="matrix(-1.1,0,0,-1.1,-1.1,0)"
+         inkscape:connector-curvature="0" />
+    </marker>
+  </defs>
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.3670394"
+     inkscape:cx="114.01552"
+     inkscape:cy="-86.548414"
+     inkscape:document-units="px"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     inkscape:window-width="1351"
+     inkscape:window-height="836"
+     inkscape:window-x="68"
+     inkscape:window-y="180"
+     inkscape:window-maximized="0"
+     fit-margin-top="5"
+     fit-margin-left="5"
+     fit-margin-right="5"
+     fit-margin-bottom="5" />
+  <metadata
+     id="metadata7">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Layer 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(-117.08462,-249.92053)">
+    <flowRoot
+       xml:space="preserve"
+       id="flowRoot2985"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"><flowRegion
+         id="flowRegion2987"><rect
+           id="rect2989"
+           width="82.85714"
+           height="11.428572"
+           x="240"
+           y="492.36218" /></flowRegion><flowPara
+         id="flowPara2991" /></flowRoot>    <text
+       xml:space="preserve"
+       style="font-size:10px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;writing-mode:lr-tb;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Symbol;-inkscape-font-specification:Symbol"
+       x="362.371"
+       y="262.51819"
+       id="text4441"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan4443"
+         x="362.371"
+         y="262.51819">-&gt;expedited_sequence: 3  GP: E,H</tspan></text>
+    <rect
+       style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101"
+       width="43.158947"
+       height="26.33428"
+       x="253.55223"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3"
+       width="43.158947"
+       height="26.33428"
+       x="297.04141"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0"
+       id="rect3101-3-6"
+       width="43.158947"
+       height="26.33428"
+       x="427.509"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7"
+       width="43.158947"
+       height="26.33428"
+       x="384.01981"
+       y="275.07489" />
+    <rect
+       style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1"
+       id="rect3101-3-6-7-5"
+       width="43.158947"
+       height="26.33428"
+       x="340.53061"
+       y="275.07489" />
+    <g
+       id="g3997"
+       transform="translate(-0.87295532,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2"
+         style="fill:#ff8282;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0;fill-opacity:1" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="146.00092"
+         y="360.25174"
+         id="text3013"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015"
+           x="146.00092"
+           y="360.25174"
+           style="font-size:10px">:4</tspan></text>
+    </g>
+    <g
+       id="g3019"
+       transform="translate(260.06223,0)">
+      <rect
+         y="343.37366"
+         x="123.95757"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-35-0"
+         style="fill:none;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="167.44673"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-62-9"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="297.91437"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-9-3"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="254.42516"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-1-6"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <rect
+         y="343.37366"
+         x="210.93593"
+         height="26.33428"
+         width="43.158947"
+         id="rect3101-3-6-7-5-2-0"
+         style="fill:#ff8282;fill-opacity:1;stroke:#000000;stroke-width:2;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;stroke-dashoffset:0" />
+      <text
+         xml:space="preserve"
+         style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+         x="145.54926"
+         y="360.25174"
+         id="text3013-3"
+         sodipodi:linespacing="125%"><tspan
+           sodipodi:role="line"
+           id="tspan3015-6"
+           x="145.54926"
+           y="360.25174"
+           style="font-size:10px">:6</tspan></text>
+    </g>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="275.59558"
+       y="291.95297"
+       id="text3013-36"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-7"
+         x="275.59558"
+         y="291.95297"
+         style="font-size:10px">:6</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="405.40396"
+       y="291.88705"
+       id="text3013-3-36-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7-6"
+         x="405.40396"
+         y="291.88705"
+         style="font-size:10px">F</tspan></text>
+    <text
+       xml:space="preserve"
+       style="font-size:20px;font-style:normal;font-weight:normal;text-align:center;line-height:125%;letter-spacing:0px;word-spacing:0px;text-anchor:middle;fill:#000000;fill-opacity:1;stroke:none;font-family:Sans"
+       x="449.22031"
+       y="291.88217"
+       id="text3013-3-36-3-3"
+       sodipodi:linespacing="125%"><tspan
+         sodipodi:role="line"
+         id="tspan3015-6-7-6-6"
+         x="449.22031"
+         y="291.88217"
+         style="font-size:10px">G</tspan></text>
+  </g>
+</svg>
diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html
index 39bcb74ea733..21593496aca6 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.html
+++ b/Documentation/RCU/Design/Requirements/Requirements.html
@@ -1480,7 +1480,7 @@ speed-of-light delays if nothing else.
 
 <p>
 Furthermore, uncertainty about external state is inherent in many cases.
-For example, a pair of veternarians might use heartbeat to determine
+For example, a pair of veterinarians might use heartbeat to determine
 whether or not a given cat was alive.
 But how long should they wait after the last heartbeat to decide that
 the cat is in fact dead?
@@ -1489,9 +1489,9 @@ mean that a relaxed cat would be considered to cycle between death
 and life more than 100 times per minute.
 Moreover, just as with human beings, a cat's heart might stop for
 some period of time, so the exact wait period is a judgment call.
-One of our pair of veternarians might wait 30 seconds before pronouncing
+One of our pair of veterinarians might wait 30 seconds before pronouncing
 the cat dead, while the other might insist on waiting a full minute.
-The two veternarians would then disagree on the state of the cat during
+The two veterinarians would then disagree on the state of the cat during
 the final 30 seconds of the minute following the last heartbeat.
 
 <p>
@@ -1945,7 +1945,7 @@ guard against mishaps and misuse:
 <ol>
 <li>	It is all too easy to forget to use <tt>rcu_read_lock()</tt>
 	everywhere that it is needed, so kernels built with
-	<tt>CONFIG_PROVE_RCU=y</tt> will spat if
+	<tt>CONFIG_PROVE_RCU=y</tt> will splat if
 	<tt>rcu_dereference()</tt> is used outside of an
 	RCU read-side critical section.
 	Update-side code can use <tt>rcu_dereference_protected()</tt>,
@@ -2421,7 +2421,7 @@ However, there are some restrictions on the code placed within
 <li>	Blocking is prohibited.
 	In practice, this is not a serious restriction given that idle
 	tasks are prohibited from blocking to begin with.
-<li>	Although nesting <tt>RCU_NONIDLE()</tt> is permited, they cannot
+<li>	Although nesting <tt>RCU_NONIDLE()</tt> is permitted, they cannot
 	nest indefinitely deeply.
 	However, given that they can be nested on the order of a million
 	deep, even on 32-bit systems, this should not be a serious
@@ -2885,7 +2885,7 @@ APIs for defining and initializing <tt>srcu_struct</tt> structures.
 <h3><a name="Tasks RCU">Tasks RCU</a></h3>
 
 <p>
-Some forms of tracing use &ldquo;tramopolines&rdquo; to handle the
+Some forms of tracing use &ldquo;trampolines&rdquo; to handle the
 binary rewriting required to install different types of probes.
 It would be good to be able to free old trampolines, which sounds
 like a job for some form of RCU.
diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt
index 00a3a38b375a..6549012033f9 100644
--- a/Documentation/RCU/trace.txt
+++ b/Documentation/RCU/trace.txt
@@ -237,7 +237,7 @@ o	"ktl" is the low-order 16 bits (in hexadecimal) of the count of
 
 The output of "cat rcu/rcu_preempt/rcuexp" looks as follows:
 
-s=21872 wd1=0 wd2=0 wd3=5 n=0 enq=0 sc=21872
+s=21872 wd1=0 wd2=0 wd3=5 enq=0 sc=21872
 
 These fields are as follows:
 
@@ -249,9 +249,6 @@ o	"wd1", "wd2", and "wd3" are the number of times that an attempt
 	completed an expedited grace period that satisfies the attempted
 	request.  "Our work is done."
 
-o	"n" is number of times that a concurrent CPU-hotplug operation
-	forced a fallback to a normal grace period.
-
 o	"enq" is the number of quiescent states still outstanding.
 
 o	"sc" is the number of times that the attempt to start a
diff --git a/Documentation/acpi/acpi-lid.txt b/Documentation/acpi/acpi-lid.txt
index effe7af3a5af..22cb3091f297 100644
--- a/Documentation/acpi/acpi-lid.txt
+++ b/Documentation/acpi/acpi-lid.txt
@@ -59,28 +59,20 @@ button driver uses the following 3 modes in order not to trigger issues.
 If the userspace hasn't been prepared to ignore the unreliable "opened"
 events and the unreliable initial state notification, Linux users can use
 the following kernel parameters to handle the possible issues:
-A. button.lid_init_state=method:
-   When this option is specified, the ACPI button driver reports the
-   initial lid state using the returning value of the _LID control method
-   and whether the "opened"/"closed" events are paired fully relies on the
-   firmware implementation.
-   This option can be used to fix some platforms where the returning value
-   of the _LID control method is reliable but the initial lid state
-   notification is missing.
-   This option is the default behavior during the period the userspace
-   isn't ready to handle the buggy AML tables.
-B. button.lid_init_state=open:
+A. button.lid_init_state=open:
    When this option is specified, the ACPI button driver always reports the
    initial lid state as "opened" and whether the "opened"/"closed" events
    are paired fully relies on the firmware implementation.
    This may fix some platforms where the returning value of the _LID
    control method is not reliable and the initial lid state notification is
    missing.
+   This option is the default behavior during the period the userspace
+   isn't ready to handle the buggy AML tables.
 
 If the userspace has been prepared to ignore the unreliable "opened" events
 and the unreliable initial state notification, Linux users should always
 use the following kernel parameter:
-C. button.lid_init_state=ignore:
+B. button.lid_init_state=ignore:
    When this option is specified, the ACPI button driver never reports the
    initial lid state and there is a compensation mechanism implemented to
    ensure that the reliable "closed" notifications can always be delievered
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index be7c0d9506b1..635d11135090 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -549,15 +549,6 @@
 			loops can be debugged more effectively on production
 			systems.
 
-	clocksource.arm_arch_timer.fsl-a008585=
-			[ARM64]
-			Format: <bool>
-			Enable/disable the workaround of Freescale/NXP
-			erratum A-008585.  This can be useful for KVM
-			guests, if the guest device tree doesn't show the
-			erratum.  If unspecified, the workaround is
-			enabled based on the device tree.
-
 	clearcpuid=BITNUM [X86]
 			Disable CPUID feature X for the kernel. See
 			arch/x86/include/asm/cpufeatures.h for the valid bit
@@ -3278,6 +3269,13 @@
 			Lazy RCU callbacks are those which RCU can
 			prove do nothing more than free memory.
 
+	rcutree.rcu_kick_kthreads= [KNL]
+			Cause the grace-period kthread to get an extra
+			wake_up() if it sleeps three times longer than
+			it should at force-quiescent-state time.
+			This wake_up() will be accompanied by a
+			WARN_ONCE() splat and an ftrace_dump().
+
 	rcuperf.gp_exp= [KNL]
 			Measure performance of expedited synchronous
 			grace-period primitives.
@@ -3563,6 +3561,10 @@
 	rhash_entries=	[KNL,NET]
 			Set number of hash buckets for route cache
 
+	ring3mwait=disable
+			[KNL] Disable ring 3 MONITOR/MWAIT feature on supported
+			CPUs.
+
 	ro		[KNL] Mount root device read-only on boot
 
 	rodata=		[KNL]
diff --git a/Documentation/admin-guide/ras.rst b/Documentation/admin-guide/ras.rst
index d71340e86c27..9939348bd4a3 100644
--- a/Documentation/admin-guide/ras.rst
+++ b/Documentation/admin-guide/ras.rst
@@ -438,11 +438,13 @@ A typical EDAC system has the following structure under
 	│   │   ├── ce_count
 	│   │   ├── ce_noinfo_count
 	│   │   ├── dimm0
+	│   │   │   ├── dimm_ce_count
 	│   │   │   ├── dimm_dev_type
 	│   │   │   ├── dimm_edac_mode
 	│   │   │   ├── dimm_label
 	│   │   │   ├── dimm_location
 	│   │   │   ├── dimm_mem_type
+	│   │   │   ├── dimm_ue_count
 	│   │   │   ├── size
 	│   │   │   └── uevent
 	│   │   ├── max_location
@@ -457,11 +459,13 @@ A typical EDAC system has the following structure under
 	│   │   ├── ce_count
 	│   │   ├── ce_noinfo_count
 	│   │   ├── dimm0
+	│   │   │   ├── dimm_ce_count
 	│   │   │   ├── dimm_dev_type
 	│   │   │   ├── dimm_edac_mode
 	│   │   │   ├── dimm_label
 	│   │   │   ├── dimm_location
 	│   │   │   ├── dimm_mem_type
+	│   │   │   ├── dimm_ue_count
 	│   │   │   ├── size
 	│   │   │   └── uevent
 	│   │   ├── max_location
@@ -483,6 +487,22 @@ this ``X`` memory module:
 	This attribute file displays, in count of megabytes, the memory
 	that this csrow contains.
 
+- ``dimm_ue_count`` - Uncorrectable Errors count attribute file
+
+	This attribute file displays the total count of uncorrectable
+	errors that have occurred on this DIMM. If panic_on_ue is set
+	this counter will not have a chance to increment, since EDAC
+	will panic the system.
+
+- ``dimm_ce_count`` - Correctable Errors count attribute file
+
+	This attribute file displays the total count of correctable
+	errors that have occurred on this DIMM. This count is very
+	important to examine. CEs provide early indications that a
+	DIMM is beginning to fail. This count field should be
+	monitored for non-zero values and report such information
+	to the system administrator.
+
 - ``dimm_dev_type``  - Device type attribute file
 
 	This attribute file will display what type of DRAM device is
diff --git a/Documentation/cdrom/cdrom-standard.tex b/Documentation/cdrom/cdrom-standard.tex
index c06233fe52ac..8f85b0e41046 100644
--- a/Documentation/cdrom/cdrom-standard.tex
+++ b/Documentation/cdrom/cdrom-standard.tex
@@ -249,7 +249,6 @@ struct& cdrom_device_ops\ \{ \hidewidth\cr
         unsigned\ long);\cr
 \noalign{\medskip}
   &const\ int& capability;& capability flags \cr
-  &int& n_minors;& number of active minor devices \cr
 \};\cr
 }
 $$
@@ -258,13 +257,7 @@ it should add a function pointer to this $struct$. When a particular
 function is not implemented, however, this $struct$ should contain a
 NULL instead. The $capability$ flags specify the capabilities of the
 \cdrom\ hardware and/or low-level \cdrom\ driver when a \cdrom\ drive
-is registered with the \UCD. The value $n_minors$ should be a positive
-value indicating the number of minor devices that are supported by
-the low-level device driver, normally~1. Although these two variables
-are `informative' rather than `operational,' they are included in
-$cdrom_device_ops$ because they describe the capability of the {\em
-driver\/} rather than the {\em drive}. Nomenclature has always been
-difficult in computer programming.
+is registered with the \UCD.
 
 Note that most functions have fewer parameters than their
 $blkdev_fops$ counterparts. This is because very little of the
diff --git a/Documentation/cpu-freq/core.txt b/Documentation/cpu-freq/core.txt
index 4bc7287806de..978463a7c81e 100644
--- a/Documentation/cpu-freq/core.txt
+++ b/Documentation/cpu-freq/core.txt
@@ -8,6 +8,8 @@
 
 		    Dominik Brodowski  <linux@brodo.de>
 		     David Kimdon <dwhedon@debian.org>
+		Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+		   Viresh Kumar <viresh.kumar@linaro.org>
 
 
 
@@ -36,10 +38,11 @@ speed limits (like LCD drivers on ARM architecture). Additionally, the
 kernel "constant" loops_per_jiffy is updated on frequency changes
 here.
 
-Reference counting is done by cpufreq_get_cpu and cpufreq_put_cpu,
-which make sure that the cpufreq processor driver is correctly
-registered with the core, and will not be unloaded until
-cpufreq_put_cpu is called.
+Reference counting of the cpufreq policies is done by cpufreq_cpu_get
+and cpufreq_cpu_put, which make sure that the cpufreq driver is
+correctly registered with the core, and will not be unloaded until
+cpufreq_put_cpu is called. That also ensures that the respective cpufreq
+policy doesn't get freed while being used.
 
 2. CPUFreq notifiers
 ====================
@@ -69,18 +72,16 @@ CPUFreq policy notifier is called twice for a policy transition:
 The phase is specified in the second argument to the notifier.
 
 The third argument, a void *pointer, points to a struct cpufreq_policy
-consisting of five values: cpu, min, max, policy and max_cpu_freq. min 
-and max are the lower and upper frequencies (in kHz) of the new
-policy, policy the new policy, cpu the number of the affected CPU; and 
-max_cpu_freq the maximum supported CPU frequency. This value is given 
-for informational purposes only.
+consisting of several values, including min, max (the lower and upper
+frequencies (in kHz) of the new policy).
 
 
 2.2 CPUFreq transition notifiers
 --------------------------------
 
-These are notified twice when the CPUfreq driver switches the CPU core
-frequency and this change has any external implications.
+These are notified twice for each online CPU in the policy, when the
+CPUfreq driver switches the CPU core frequency and this change has no
+any external implications.
 
 The second argument specifies the phase - CPUFREQ_PRECHANGE or
 CPUFREQ_POSTCHANGE.
@@ -90,6 +91,7 @@ values:
 cpu	- number of the affected CPU
 old	- old frequency
 new	- new frequency
+flags	- flags of the cpufreq driver
 
 3. CPUFreq Table Generation with Operating Performance Point (OPP)
 ==================================================================
diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt
index 772b94fde264..f71e6be26b83 100644
--- a/Documentation/cpu-freq/cpu-drivers.txt
+++ b/Documentation/cpu-freq/cpu-drivers.txt
@@ -9,6 +9,8 @@
 
 
 		    Dominik Brodowski  <linux@brodo.de>
+		Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+		   Viresh Kumar <viresh.kumar@linaro.org>
 
 
 
@@ -49,49 +51,65 @@ using cpufreq_register_driver()
 
 What shall this struct cpufreq_driver contain? 
 
-cpufreq_driver.name -		The name of this driver.
+ .name - The name of this driver.
 
-cpufreq_driver.init -		A pointer to the per-CPU initialization 
-				function.
+ .init - A pointer to the per-policy initialization function.
 
-cpufreq_driver.verify -		A pointer to a "verification" function.
+ .verify - A pointer to a "verification" function.
 
-cpufreq_driver.setpolicy _or_ 
-cpufreq_driver.target/
-target_index		-	See below on the differences.
+ .setpolicy _or_ .fast_switch _or_ .target _or_ .target_index - See
+ below on the differences.
 
 And optionally
 
-cpufreq_driver.exit -		A pointer to a per-CPU cleanup
-				function called during CPU_POST_DEAD
-				phase of cpu hotplug process.
+ .flags - Hints for the cpufreq core.
 
-cpufreq_driver.stop_cpu -	A pointer to a per-CPU stop function
-				called during CPU_DOWN_PREPARE phase of
-				cpu hotplug process.
+ .driver_data - cpufreq driver specific data.
 
-cpufreq_driver.resume -		A pointer to a per-CPU resume function
-				which is called with interrupts disabled
-				and _before_ the pre-suspend frequency
-				and/or policy is restored by a call to
-				->target/target_index or ->setpolicy.
+ .resolve_freq - Returns the most appropriate frequency for a target
+ frequency. Doesn't change the frequency though.
 
-cpufreq_driver.attr -		A pointer to a NULL-terminated list of
-				"struct freq_attr" which allow to
-				export values to sysfs.
+ .get_intermediate and target_intermediate - Used to switch to stable
+ frequency while changing CPU frequency.
 
-cpufreq_driver.get_intermediate
-and target_intermediate		Used to switch to stable frequency while
-				changing CPU frequency.
+ .get - Returns current frequency of the CPU.
+
+ .bios_limit - Returns HW/BIOS max frequency limitations for the CPU.
+
+ .exit - A pointer to a per-policy cleanup function called during
+ CPU_POST_DEAD phase of cpu hotplug process.
+
+ .stop_cpu - A pointer to a per-policy stop function called during
+ CPU_DOWN_PREPARE phase of cpu hotplug process.
+
+ .suspend - A pointer to a per-policy suspend function which is called
+ with interrupts disabled and _after_ the governor is stopped for the
+ policy.
+
+ .resume - A pointer to a per-policy resume function which is called
+ with interrupts disabled and _before_ the governor is started again.
+
+ .ready - A pointer to a per-policy ready function which is called after
+ the policy is fully initialized.
+
+ .attr - A pointer to a NULL-terminated list of "struct freq_attr" which
+ allow to export values to sysfs.
+
+ .boost_enabled - If set, boost frequencies are enabled.
+
+ .set_boost - A pointer to a per-policy function to enable/disable boost
+ frequencies.
 
 
 1.2 Per-CPU Initialization
 --------------------------
 
 Whenever a new CPU is registered with the device model, or after the
-cpufreq driver registers itself, the per-CPU initialization function 
-cpufreq_driver.init is called. It takes a struct cpufreq_policy
-*policy as argument. What to do now?
+cpufreq driver registers itself, the per-policy initialization function
+cpufreq_driver.init is called if no cpufreq policy existed for the CPU.
+Note that the .init() and .exit() routines are called only once for the
+policy and not for each CPU managed by the policy. It takes a struct
+cpufreq_policy *policy as argument. What to do now?
 
 If necessary, activate the CPUfreq support on your CPU.
 
@@ -117,47 +135,45 @@ policy->governor		must contain the "default policy" for
 				cpufreq_driver.setpolicy or
 				cpufreq_driver.target/target_index is called
 				with these values.
+policy->cpus			Update this with the masks of the
+				(online + offline) CPUs that do DVFS
+				along with this CPU (i.e.  that share
+				clock/voltage rails with it).
 
 For setting some of these values (cpuinfo.min[max]_freq, policy->min[max]), the
 frequency table helpers might be helpful. See the section 2 for more information
 on them.
 
-SMP systems normally have same clock source for a group of cpus. For these the
-.init() would be called only once for the first online cpu. Here the .init()
-routine must initialize policy->cpus with mask of all possible cpus (Online +
-Offline) that share the clock. Then the core would copy this mask onto
-policy->related_cpus and will reset policy->cpus to carry only online cpus.
-
 
 1.3 verify
-------------
+----------
 
 When the user decides a new policy (consisting of
 "policy,governor,min,max") shall be set, this policy must be validated
 so that incompatible values can be corrected. For verifying these
-values, a frequency table helper and/or the
-cpufreq_verify_within_limits(struct cpufreq_policy *policy, unsigned
-int min_freq, unsigned int max_freq) function might be helpful. See
-section 2 for details on frequency table helpers.
+values cpufreq_verify_within_limits(struct cpufreq_policy *policy,
+unsigned int min_freq, unsigned int max_freq) function might be helpful.
+See section 2 for details on frequency table helpers.
 
 You need to make sure that at least one valid frequency (or operating
 range) is within policy->min and policy->max. If necessary, increase
 policy->max first, and only if this is no solution, decrease policy->min.
 
 
-1.4 target/target_index or setpolicy?
-----------------------------
+1.4 target or target_index or setpolicy or fast_switch?
+-------------------------------------------------------
 
 Most cpufreq drivers or even most cpu frequency scaling algorithms 
-only allow the CPU to be set to one frequency. For these, you use the
-->target/target_index call.
+only allow the CPU frequency to be set to predefined fixed values. For
+these, you use the ->target(), ->target_index() or ->fast_switch()
+callbacks.
 
-Some cpufreq-capable processors switch the frequency between certain
-limits on their own. These shall use the ->setpolicy call
+Some cpufreq capable processors switch the frequency between certain
+limits on their own. These shall use the ->setpolicy() callback.
 
 
 1.5. target/target_index
--------------
+------------------------
 
 The target_index call has two arguments: struct cpufreq_policy *policy,
 and unsigned int index (into the exposed frequency table).
@@ -186,9 +202,20 @@ actual frequency must be determined using the following rules:
 Here again the frequency table helper might assist you - see section 2
 for details.
 
+1.6. fast_switch
+----------------
 
-1.6 setpolicy
----------------
+This function is used for frequency switching from scheduler's context.
+Not all drivers are expected to implement it, as sleeping from within
+this callback isn't allowed. This callback must be highly optimized to
+do switching as fast as possible.
+
+This function has two arguments: struct cpufreq_policy *policy and
+unsigned int target_frequency.
+
+
+1.7 setpolicy
+-------------
 
 The setpolicy call only takes a struct cpufreq_policy *policy as
 argument. You need to set the lower limit of the in-processor or
@@ -198,7 +225,7 @@ setting when policy->policy is CPUFREQ_POLICY_PERFORMANCE, and a
 powersaving-oriented setting when CPUFREQ_POLICY_POWERSAVE. Also check
 the reference implementation in drivers/cpufreq/longrun.c
 
-1.7 get_intermediate and target_intermediate
+1.8 get_intermediate and target_intermediate
 --------------------------------------------
 
 Only for drivers with target_index() and CPUFREQ_ASYNC_NOTIFICATION unset.
@@ -222,42 +249,36 @@ failures as core would send notifications for that.
 
 As most cpufreq processors only allow for being set to a few specific
 frequencies, a "frequency table" with some functions might assist in
-some work of the processor driver. Such a "frequency table" consists
-of an array of struct cpufreq_frequency_table entries, with any value in
-"driver_data" you want to use, and the corresponding frequency in
-"frequency". At the end of the table, you need to add a
-cpufreq_frequency_table entry with frequency set to CPUFREQ_TABLE_END. And
-if you want to skip one entry in the table, set the frequency to 
-CPUFREQ_ENTRY_INVALID. The entries don't need to be in ascending
-order.
-
-By calling cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
-					struct cpufreq_frequency_table *table);
-the cpuinfo.min_freq and cpuinfo.max_freq values are detected, and
-policy->min and policy->max are set to the same values. This is
-helpful for the per-CPU initialization stage.
-
-int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
-                                   struct cpufreq_frequency_table *table);
-assures that at least one valid frequency is within policy->min and
-policy->max, and all other criteria are met. This is helpful for the
-->verify call.
-
-int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
-                                   unsigned int target_freq,
-                                   unsigned int relation);
-
-is the corresponding frequency table helper for the ->target
-stage. Just pass the values to this function, and this function
-returns the number of the frequency table entry which contains
-the frequency the CPU shall be set to.
+some work of the processor driver. Such a "frequency table" consists of
+an array of struct cpufreq_frequency_table entries, with driver specific
+values in "driver_data", the corresponding frequency in "frequency" and
+flags set. At the end of the table, you need to add a
+cpufreq_frequency_table entry with frequency set to CPUFREQ_TABLE_END.
+And if you want to skip one entry in the table, set the frequency to
+CPUFREQ_ENTRY_INVALID. The entries don't need to be in sorted in any
+particular order, but if they are cpufreq core will do DVFS a bit
+quickly for them as search for best match is faster.
+
+By calling cpufreq_table_validate_and_show(), the cpuinfo.min_freq and
+cpuinfo.max_freq values are detected, and policy->min and policy->max
+are set to the same values. This is helpful for the per-CPU
+initialization stage.
+
+cpufreq_frequency_table_verify() assures that at least one valid
+frequency is within policy->min and policy->max, and all other criteria
+are met. This is helpful for the ->verify call.
+
+cpufreq_frequency_table_target() is the corresponding frequency table
+helper for the ->target stage. Just pass the values to this function,
+and this function returns the of the frequency table entry which
+contains the frequency the CPU shall be set to.
 
 The following macros can be used as iterators over cpufreq_frequency_table:
 
 cpufreq_for_each_entry(pos, table) - iterates over all entries of frequency
 table.
 
-cpufreq-for_each_valid_entry(pos, table) - iterates over all entries,
+cpufreq_for_each_valid_entry(pos, table) - iterates over all entries,
 excluding CPUFREQ_ENTRY_INVALID frequencies.
 Use arguments "pos" - a cpufreq_frequency_table * as a loop cursor and
 "table" - the cpufreq_frequency_table * you want to iterate over.
diff --git a/Documentation/cpu-freq/cpufreq-stats.txt b/Documentation/cpu-freq/cpufreq-stats.txt
index 3c355f6ad834..2bbe207354ed 100644
--- a/Documentation/cpu-freq/cpufreq-stats.txt
+++ b/Documentation/cpu-freq/cpufreq-stats.txt
@@ -34,10 +34,10 @@ cpufreq stats provides following statistics (explained in detail below).
 -  total_trans
 -  trans_table
 
-All the statistics will be from the time the stats driver has been inserted 
-to the time when a read of a particular statistic is done. Obviously, stats 
-driver will not have any information about the frequency transitions before
-the stats driver insertion.
+All the statistics will be from the time the stats driver has been inserted
+(or the time the stats were reset) to the time when a read of a particular
+statistic is done. Obviously, stats driver will not have any information
+about the frequency transitions before the stats driver insertion.
 
 --------------------------------------------------------------------------------
 <mysystem>:/sys/devices/system/cpu/cpu0/cpufreq/stats # ls -l
@@ -110,25 +110,13 @@ Config Main Menu
 		CPU Frequency scaling  --->
 			[*] CPU Frequency scaling
 			[*]   CPU frequency translation statistics
-			[*]     CPU frequency translation statistics details
 
 
 "CPU Frequency scaling" (CONFIG_CPU_FREQ) should be enabled to configure
 cpufreq-stats.
 
 "CPU frequency translation statistics" (CONFIG_CPU_FREQ_STAT) provides the
-basic statistics which includes time_in_state and total_trans.
+statistics which includes time_in_state, total_trans and trans_table.
 
-"CPU frequency translation statistics details" (CONFIG_CPU_FREQ_STAT_DETAILS)
-provides fine grained cpufreq stats by trans_table. The reason for having a
-separate config option for trans_table is:
-- trans_table goes against the traditional /sysfs rule of one value per
-  interface. It provides a whole bunch of value in a 2 dimensional matrix
-  form.
-
-Once these two options are enabled and your CPU supports cpufrequency, you
+Once this option is enabled and your CPU supports cpufrequency, you
 will be able to see the CPU frequency statistics in /sysfs.
-
-
-
-
diff --git a/Documentation/cpu-freq/governors.txt b/Documentation/cpu-freq/governors.txt
index c15aa75f5227..61b3184b6c24 100644
--- a/Documentation/cpu-freq/governors.txt
+++ b/Documentation/cpu-freq/governors.txt
@@ -10,6 +10,8 @@
 
 		    Dominik Brodowski  <linux@brodo.de>
             some additions and corrections by Nico Golde <nico@ngolde.de>
+		Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+		   Viresh Kumar <viresh.kumar@linaro.org>
 
 
 
@@ -28,32 +30,27 @@ Contents:
 2.3  Userspace
 2.4  Ondemand
 2.5  Conservative
+2.6  Schedutil
 
 3.   The Governor Interface in the CPUfreq Core
 
+4.   References
 
 
 1. What Is A CPUFreq Governor?
 ==============================
 
 Most cpufreq drivers (except the intel_pstate and longrun) or even most
-cpu frequency scaling algorithms only offer the CPU to be set to one
-frequency. In order to offer dynamic frequency scaling, the cpufreq
-core must be able to tell these drivers of a "target frequency". So
-these specific drivers will be transformed to offer a "->target/target_index"
-call instead of the existing "->setpolicy" call. For "longrun", all
-stays the same, though.
+cpu frequency scaling algorithms only allow the CPU frequency to be set
+to predefined fixed values.  In order to offer dynamic frequency
+scaling, the cpufreq core must be able to tell these drivers of a
+"target frequency". So these specific drivers will be transformed to
+offer a "->target/target_index/fast_switch()" call instead of the
+"->setpolicy()" call. For set_policy drivers, all stays the same,
+though.
 
 How to decide what frequency within the CPUfreq policy should be used?
-That's done using "cpufreq governors". Two are already in this patch
--- they're the already existing "powersave" and "performance" which
-set the frequency statically to the lowest or highest frequency,
-respectively. At least two more such governors will be ready for
-addition in the near future, but likely many more as there are various
-different theories and models about dynamic frequency scaling
-around. Using such a generic interface as cpufreq offers to scaling
-governors, these can be tested extensively, and the best one can be
-selected for each specific use.
+That's done using "cpufreq governors".
 
 Basically, it's the following flow graph:
 
@@ -71,7 +68,7 @@ CPU can be set to switch independently	 |	   CPU can only be set
 		    /			       the limits of policy->{min,max}
 		   /			            \
 		  /				     \
-	Using the ->setpolicy call,		 Using the ->target/target_index call,
+	Using the ->setpolicy call,		 Using the ->target/target_index/fast_switch call,
 	    the limits and the			  the frequency closest
 	     "policy" is set.			  to target_freq is set.
 						  It is assured that it
@@ -109,114 +106,159 @@ directory.
 2.4 Ondemand
 ------------
 
-The CPUfreq governor "ondemand" sets the CPU depending on the
-current usage. To do this the CPU must have the capability to
-switch the frequency very quickly.  There are a number of sysfs file
-accessible parameters:
-
-sampling_rate: measured in uS (10^-6 seconds), this is how often you
-want the kernel to look at the CPU usage and to make decisions on
-what to do about the frequency.  Typically this is set to values of
-around '10000' or more. It's default value is (cmp. with users-guide.txt):
-transition_latency * 1000
-Be aware that transition latency is in ns and sampling_rate is in us, so you
-get the same sysfs value by default.
-Sampling rate should always get adjusted considering the transition latency
-To set the sampling rate 750 times as high as the transition latency
-in the bash (as said, 1000 is default), do:
-echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) \
-    >ondemand/sampling_rate
-
-sampling_rate_min:
-The sampling rate is limited by the HW transition latency:
-transition_latency * 100
-Or by kernel restrictions:
-If CONFIG_NO_HZ_COMMON is set, the limit is 10ms fixed.
-If CONFIG_NO_HZ_COMMON is not set or nohz=off boot parameter is used, the
-limits depend on the CONFIG_HZ option:
-HZ=1000: min=20000us  (20ms)
-HZ=250:  min=80000us  (80ms)
-HZ=100:  min=200000us (200ms)
-The highest value of kernel and HW latency restrictions is shown and
-used as the minimum sampling rate.
-
-up_threshold: defines what the average CPU usage between the samplings
-of 'sampling_rate' needs to be for the kernel to make a decision on
-whether it should increase the frequency.  For example when it is set
-to its default value of '95' it means that between the checking
-intervals the CPU needs to be on average more than 95% in use to then
-decide that the CPU frequency needs to be increased.  
-
-ignore_nice_load: this parameter takes a value of '0' or '1'. When
-set to '0' (its default), all processes are counted towards the
-'cpu utilisation' value.  When set to '1', the processes that are
-run with a 'nice' value will not count (and thus be ignored) in the
-overall usage calculation.  This is useful if you are running a CPU
-intensive calculation on your laptop that you do not care how long it
-takes to complete as you can 'nice' it and prevent it from taking part
-in the deciding process of whether to increase your CPU frequency.
-
-sampling_down_factor: this parameter controls the rate at which the
-kernel makes a decision on when to decrease the frequency while running
-at top speed. When set to 1 (the default) decisions to reevaluate load
-are made at the same interval regardless of current clock speed. But
-when set to greater than 1 (e.g. 100) it acts as a multiplier for the
-scheduling interval for reevaluating load when the CPU is at its top
-speed due to high load. This improves performance by reducing the overhead
-of load evaluation and helping the CPU stay at its top speed when truly
-busy, rather than shifting back and forth in speed. This tunable has no
-effect on behavior at lower speeds/lower CPU loads.
-
-powersave_bias: this parameter takes a value between 0 to 1000. It
-defines the percentage (times 10) value of the target frequency that
-will be shaved off of the target. For example, when set to 100 -- 10%,
-when ondemand governor would have targeted 1000 MHz, it will target
-1000 MHz - (10% of 1000 MHz) = 900 MHz instead. This is set to 0
-(disabled) by default.
-When AMD frequency sensitivity powersave bias driver --
-drivers/cpufreq/amd_freq_sensitivity.c is loaded, this parameter
-defines the workload frequency sensitivity threshold in which a lower
-frequency is chosen instead of ondemand governor's original target.
-The frequency sensitivity is a hardware reported (on AMD Family 16h
-Processors and above) value between 0 to 100% that tells software how
-the performance of the workload running on a CPU will change when
-frequency changes. A workload with sensitivity of 0% (memory/IO-bound)
-will not perform any better on higher core frequency, whereas a
-workload with sensitivity of 100% (CPU-bound) will perform better
-higher the frequency. When the driver is loaded, this is set to 400
-by default -- for CPUs running workloads with sensitivity value below
-40%, a lower frequency is chosen. Unloading the driver or writing 0
-will disable this feature.
+The CPUfreq governor "ondemand" sets the CPU frequency depending on the
+current system load. Load estimation is triggered by the scheduler
+through the update_util_data->func hook; when triggered, cpufreq checks
+the CPU-usage statistics over the last period and the governor sets the
+CPU accordingly.  The CPU must have the capability to switch the
+frequency very quickly.
+
+Sysfs files:
+
+* sampling_rate:
+
+  Measured in uS (10^-6 seconds), this is how often you want the kernel
+  to look at the CPU usage and to make decisions on what to do about the
+  frequency.  Typically this is set to values of around '10000' or more.
+  It's default value is (cmp. with users-guide.txt): transition_latency
+  * 1000.  Be aware that transition latency is in ns and sampling_rate
+  is in us, so you get the same sysfs value by default.  Sampling rate
+  should always get adjusted considering the transition latency to set
+  the sampling rate 750 times as high as the transition latency in the
+  bash (as said, 1000 is default), do:
+
+  $ echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) > ondemand/sampling_rate
+
+* sampling_rate_min:
+
+  The sampling rate is limited by the HW transition latency:
+  transition_latency * 100
+
+  Or by kernel restrictions:
+  - If CONFIG_NO_HZ_COMMON is set, the limit is 10ms fixed.
+  - If CONFIG_NO_HZ_COMMON is not set or nohz=off boot parameter is
+    used, the limits depend on the CONFIG_HZ option:
+    HZ=1000: min=20000us  (20ms)
+    HZ=250:  min=80000us  (80ms)
+    HZ=100:  min=200000us (200ms)
+
+  The highest value of kernel and HW latency restrictions is shown and
+  used as the minimum sampling rate.
+
+* up_threshold:
+
+  This defines what the average CPU usage between the samplings of
+  'sampling_rate' needs to be for the kernel to make a decision on
+  whether it should increase the frequency.  For example when it is set
+  to its default value of '95' it means that between the checking
+  intervals the CPU needs to be on average more than 95% in use to then
+  decide that the CPU frequency needs to be increased.
+
+* ignore_nice_load:
+
+  This parameter takes a value of '0' or '1'. When set to '0' (its
+  default), all processes are counted towards the 'cpu utilisation'
+  value.  When set to '1', the processes that are run with a 'nice'
+  value will not count (and thus be ignored) in the overall usage
+  calculation.  This is useful if you are running a CPU intensive
+  calculation on your laptop that you do not care how long it takes to
+  complete as you can 'nice' it and prevent it from taking part in the
+  deciding process of whether to increase your CPU frequency.
+
+* sampling_down_factor:
+
+  This parameter controls the rate at which the kernel makes a decision
+  on when to decrease the frequency while running at top speed. When set
+  to 1 (the default) decisions to reevaluate load are made at the same
+  interval regardless of current clock speed. But when set to greater
+  than 1 (e.g. 100) it acts as a multiplier for the scheduling interval
+  for reevaluating load when the CPU is at its top speed due to high
+  load. This improves performance by reducing the overhead of load
+  evaluation and helping the CPU stay at its top speed when truly busy,
+  rather than shifting back and forth in speed. This tunable has no
+  effect on behavior at lower speeds/lower CPU loads.
+
+* powersave_bias:
+
+  This parameter takes a value between 0 to 1000. It defines the
+  percentage (times 10) value of the target frequency that will be
+  shaved off of the target. For example, when set to 100 -- 10%, when
+  ondemand governor would have targeted 1000 MHz, it will target
+  1000 MHz - (10% of 1000 MHz) = 900 MHz instead. This is set to 0
+  (disabled) by default.
+
+  When AMD frequency sensitivity powersave bias driver --
+  drivers/cpufreq/amd_freq_sensitivity.c is loaded, this parameter
+  defines the workload frequency sensitivity threshold in which a lower
+  frequency is chosen instead of ondemand governor's original target.
+  The frequency sensitivity is a hardware reported (on AMD Family 16h
+  Processors and above) value between 0 to 100% that tells software how
+  the performance of the workload running on a CPU will change when
+  frequency changes. A workload with sensitivity of 0% (memory/IO-bound)
+  will not perform any better on higher core frequency, whereas a
+  workload with sensitivity of 100% (CPU-bound) will perform better
+  higher the frequency. When the driver is loaded, this is set to 400 by
+  default -- for CPUs running workloads with sensitivity value below
+  40%, a lower frequency is chosen. Unloading the driver or writing 0
+  will disable this feature.
 
 
 2.5 Conservative
 ----------------
 
 The CPUfreq governor "conservative", much like the "ondemand"
-governor, sets the CPU depending on the current usage.  It differs in
-behaviour in that it gracefully increases and decreases the CPU speed
-rather than jumping to max speed the moment there is any load on the
-CPU.  This behaviour more suitable in a battery powered environment.
-The governor is tweaked in the same manner as the "ondemand" governor
-through sysfs with the addition of:
-
-freq_step: this describes what percentage steps the cpu freq should be
-increased and decreased smoothly by.  By default the cpu frequency will
-increase in 5% chunks of your maximum cpu frequency.  You can change this
-value to anywhere between 0 and 100 where '0' will effectively lock your
-CPU at a speed regardless of its load whilst '100' will, in theory, make
-it behave identically to the "ondemand" governor.
-
-down_threshold: same as the 'up_threshold' found for the "ondemand"
-governor but for the opposite direction.  For example when set to its
-default value of '20' it means that if the CPU usage needs to be below
-20% between samples to have the frequency decreased.
-
-sampling_down_factor: similar functionality as in "ondemand" governor.
-But in "conservative", it controls the rate at which the kernel makes
-a decision on when to decrease the frequency while running in any
-speed. Load for frequency increase is still evaluated every
-sampling rate.
+governor, sets the CPU frequency depending on the current usage.  It
+differs in behaviour in that it gracefully increases and decreases the
+CPU speed rather than jumping to max speed the moment there is any load
+on the CPU. This behaviour is more suitable in a battery powered
+environment.  The governor is tweaked in the same manner as the
+"ondemand" governor through sysfs with the addition of:
+
+* freq_step:
+
+  This describes what percentage steps the cpu freq should be increased
+  and decreased smoothly by.  By default the cpu frequency will increase
+  in 5% chunks of your maximum cpu frequency.  You can change this value
+  to anywhere between 0 and 100 where '0' will effectively lock your CPU
+  at a speed regardless of its load whilst '100' will, in theory, make
+  it behave identically to the "ondemand" governor.
+
+* down_threshold:
+
+  Same as the 'up_threshold' found for the "ondemand" governor but for
+  the opposite direction.  For example when set to its default value of
+  '20' it means that if the CPU usage needs to be below 20% between
+  samples to have the frequency decreased.
+
+* sampling_down_factor:
+
+  Similar functionality as in "ondemand" governor.  But in
+  "conservative", it controls the rate at which the kernel makes a
+  decision on when to decrease the frequency while running in any speed.
+  Load for frequency increase is still evaluated every sampling rate.
+
+
+2.6 Schedutil
+-------------
+
+The "schedutil" governor aims at better integration with the Linux
+kernel scheduler.  Load estimation is achieved through the scheduler's
+Per-Entity Load Tracking (PELT) mechanism, which also provides
+information about the recent load [1].  This governor currently does
+load based DVFS only for tasks managed by CFS. RT and DL scheduler tasks
+are always run at the highest frequency.  Unlike all the other
+governors, the code is located under the kernel/sched/ directory.
+
+Sysfs files:
+
+* rate_limit_us:
+
+  This contains a value in microseconds. The governor waits for
+  rate_limit_us time before reevaluating the load again, after it has
+  evaluated the load once.
+
+For an in-depth comparison with the other governors refer to [2].
+
 
 3. The Governor Interface in the CPUfreq Core
 =============================================
@@ -225,26 +267,10 @@ A new governor must register itself with the CPUfreq core using
 "cpufreq_register_governor". The struct cpufreq_governor, which has to
 be passed to that function, must contain the following values:
 
-governor->name -	    A unique name for this governor
-governor->governor -	    The governor callback function
-governor->owner	-	    .THIS_MODULE for the governor module (if 
-			    appropriate)
-
-The governor->governor callback is called with the current (or to-be-set)
-cpufreq_policy struct for that CPU, and an unsigned int event. The
-following events are currently defined:
-
-CPUFREQ_GOV_START:   This governor shall start its duty for the CPU
-		     policy->cpu
-CPUFREQ_GOV_STOP:    This governor shall end its duty for the CPU
-		     policy->cpu
-CPUFREQ_GOV_LIMITS:  The limits for CPU policy->cpu have changed to
-		     policy->min and policy->max.
-
-If you need other "events" externally of your driver, _only_ use the
-cpufreq_governor_l(unsigned int cpu, unsigned int event) call to the
-CPUfreq core to ensure proper locking.
+governor->name - A unique name for this governor.
+governor->owner - .THIS_MODULE for the governor module (if appropriate).
 
+plus a set of hooks to the functions implementing the governor's logic.
 
 The CPUfreq governor may call the CPU processor driver using one of
 these two functions:
@@ -258,12 +284,18 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
                                    unsigned int relation);
 
 target_freq must be within policy->min and policy->max, of course.
-What's the difference between these two functions? When your governor
-still is in a direct code path of a call to governor->governor, the
-per-CPU cpufreq lock is still held in the cpufreq core, and there's
-no need to lock it again (in fact, this would cause a deadlock). So
-use __cpufreq_driver_target only in these cases. In all other cases 
-(for example, when there's a "daemonized" function that wakes up 
-every second), use cpufreq_driver_target to lock the cpufreq per-CPU
-lock before the command is passed to the cpufreq processor driver.
+What's the difference between these two functions? When your governor is
+in a direct code path of a call to governor callbacks, like
+governor->start(), the policy->rwsem is still held in the cpufreq core,
+and there's no need to lock it again (in fact, this would cause a
+deadlock). So use __cpufreq_driver_target only in these cases. In all
+other cases (for example, when there's a "daemonized" function that
+wakes up every second), use cpufreq_driver_target to take policy->rwsem
+before the command is passed to the cpufreq driver.
+
+4. References
+=============
+
+[1] Per-entity load tracking: https://lwn.net/Articles/531853/
+[2] Improvements in CPU frequency management: https://lwn.net/Articles/682391/
 
diff --git a/Documentation/cpu-freq/index.txt b/Documentation/cpu-freq/index.txt
index dc024ab4054f..ef1d39247b05 100644
--- a/Documentation/cpu-freq/index.txt
+++ b/Documentation/cpu-freq/index.txt
@@ -18,16 +18,29 @@
 
 Documents in this directory:
 ----------------------------
+
+amd-powernow.txt -	AMD powernow driver specific file.
+
+boost.txt -		Frequency boosting support.
+
 core.txt	-	General description of the CPUFreq core and
-			of CPUFreq notifiers
+			of CPUFreq notifiers.
+
+cpu-drivers.txt -	How to implement a new cpufreq processor driver.
 
-cpu-drivers.txt -	How to implement a new cpufreq processor driver
+cpufreq-nforce2.txt -	nVidia nForce2 platform specific file.
+
+cpufreq-stats.txt -	General description of sysfs cpufreq stats.
 
 governors.txt	-	What are cpufreq governors and how to
 			implement them?
 
 index.txt	-	File index, Mailing list and Links (this document)
 
+intel-pstate.txt -	Intel pstate cpufreq driver specific file.
+
+pcc-cpufreq.txt -	PCC cpufreq driver specific file.
+
 user-guide.txt	-	User Guide to CPUFreq
 
 
@@ -35,9 +48,7 @@ Mailing List
 ------------
 There is a CPU frequency changing CVS commit and general list where
 you can report bugs, problems or submit patches. To post a message,
-send an email to linux-pm@vger.kernel.org, to subscribe go to
-http://vger.kernel.org/vger-lists.html#linux-pm and follow the
-instructions there.
+send an email to linux-pm@vger.kernel.org.
 
 Links
 -----
@@ -48,7 +59,7 @@ how to access the CVS repository:
 * http://cvs.arm.linux.org.uk/
 
 the CPUFreq Mailing list:
-* http://vger.kernel.org/vger-lists.html#cpufreq
+* http://vger.kernel.org/vger-lists.html#linux-pm
 
 Clock and voltage scaling for the SA-1100:
 * http://www.lartmaker.nl/projects/scaling
diff --git a/Documentation/cpu-freq/intel-pstate.txt b/Documentation/cpu-freq/intel-pstate.txt
index 1953994ef5e6..3fdcdfd968ba 100644
--- a/Documentation/cpu-freq/intel-pstate.txt
+++ b/Documentation/cpu-freq/intel-pstate.txt
@@ -85,6 +85,21 @@ Sysfs will show :
 Refer to "Intel® 64 and IA-32 Architectures Software Developer’s Manual
 Volume 3: System Programming Guide" to understand ratios.
 
+There is one more sysfs attribute in /sys/devices/system/cpu/intel_pstate/
+that can be used for controlling the operation mode of the driver:
+
+      status: Three settings are possible:
+      "off"     - The driver is not in use at this time.
+      "active"  - The driver works as a P-state governor (default).
+      "passive" - The driver works as a regular cpufreq one and collaborates
+                  with the generic cpufreq governors (it sets P-states as
+                  requested by those governors).
+      The current setting is returned by reads from this attribute.  Writing one
+      of the above strings to it changes the operation mode as indicated by that
+      string, if possible.  If HW-managed P-states (HWP) are enabled, it is not
+      possible to change the driver's operation mode and attempts to write to
+      this attribute will fail.
+
 cpufreq sysfs for Intel P-State
 
 Since this driver registers with cpufreq, cpufreq sysfs is also presented.
diff --git a/Documentation/cpu-freq/user-guide.txt b/Documentation/cpu-freq/user-guide.txt
index 109e97bbab77..107f6fdd7d14 100644
--- a/Documentation/cpu-freq/user-guide.txt
+++ b/Documentation/cpu-freq/user-guide.txt
@@ -18,7 +18,7 @@
 Contents:
 ---------
 1. Supported Architectures and Processors
-1.1 ARM
+1.1 ARM and ARM64
 1.2 x86
 1.3 sparc64
 1.4 ppc
@@ -37,16 +37,10 @@ Contents:
 1. Supported Architectures and Processors
 =========================================
 
-1.1 ARM
--------
-
-The following ARM processors are supported by cpufreq:
-
-ARM Integrator
-ARM-SA1100
-ARM-SA1110
-Intel PXA
+1.1 ARM and ARM64
+-----------------
 
+Almost all ARM and ARM64 platforms support CPU frequency scaling.
 
 1.2 x86
 -------
@@ -69,6 +63,7 @@ Transmeta Crusoe
 Transmeta Efficeon
 VIA Cyrix 3 / C3
 various processors on some ACPI 2.0-compatible systems [*]
+And many more
 
 [*] Only if "ACPI Processor Performance States" are available
 to the ACPI<->BIOS interface.
@@ -147,10 +142,19 @@ mounted it at /sys, the cpufreq interface is located in a subdirectory
 "cpufreq" within the cpu-device directory
 (e.g. /sys/devices/system/cpu/cpu0/cpufreq/ for the first CPU).
 
+affected_cpus :			List of Online CPUs that require software
+				coordination of frequency.
+
+cpuinfo_cur_freq :		Current frequency of the CPU as obtained from
+				the hardware, in KHz. This is the frequency
+				the CPU actually runs at.
+
 cpuinfo_min_freq :		this file shows the minimum operating
 				frequency the processor can run at(in kHz) 
+
 cpuinfo_max_freq :		this file shows the maximum operating
 				frequency the processor can run at(in kHz) 
+
 cpuinfo_transition_latency	The time it takes on this CPU to
 				switch between two frequencies in nano
 				seconds. If unknown or known to be
@@ -163,25 +167,30 @@ cpuinfo_transition_latency	The time it takes on this CPU to
 				userspace daemon. Make sure to not
 				switch the frequency too often
 				resulting in performance loss.
-scaling_driver :		this file shows what cpufreq driver is
-				used to set the frequency on this CPU
+
+related_cpus :			List of Online + Offline CPUs that need software
+				coordination of frequency.
+
+scaling_available_frequencies : List of available frequencies, in KHz.
 
 scaling_available_governors :	this file shows the CPUfreq governors
 				available in this kernel. You can see the
 				currently activated governor in
 
+scaling_cur_freq :		Current frequency of the CPU as determined by
+				the governor and cpufreq core, in KHz. This is
+				the frequency the kernel thinks the CPU runs
+				at.
+
+scaling_driver :		this file shows what cpufreq driver is
+				used to set the frequency on this CPU
+
 scaling_governor,		and by "echoing" the name of another
 				governor you can change it. Please note
 				that some governors won't load - they only
 				work on some specific architectures or
 				processors.
 
-cpuinfo_cur_freq :		Current frequency of the CPU as obtained from
-				the hardware, in KHz. This is the frequency
-				the CPU actually runs at.
-
-scaling_available_frequencies : List of available frequencies, in KHz.
-
 scaling_min_freq and
 scaling_max_freq		show the current "policy limits" (in
 				kHz). By echoing new values into these
@@ -190,16 +199,11 @@ scaling_max_freq		show the current "policy limits" (in
 				first set scaling_max_freq, then
 				scaling_min_freq.
 
-affected_cpus :			List of Online CPUs that require software
-				coordination of frequency.
-
-related_cpus :			List of Online + Offline CPUs that need software
-				coordination of frequency.
-
-scaling_cur_freq :		Current frequency of the CPU as determined by
-				the governor and cpufreq core, in KHz. This is
-				the frequency the kernel thinks the CPU runs
-				at.
+scaling_setspeed		This can be read to get the currently programmed
+				value by the governor. This can be written to
+				change the current frequency for a group of
+				CPUs, represented by a policy. This is supported
+				currently only by the userspace governor.
 
 bios_limit :			If the BIOS tells the OS to limit a CPU to
 				lower frequencies, the user can read out the
diff --git a/Documentation/devicetree/bindings/arm/arch_timer.txt b/Documentation/devicetree/bindings/arm/arch_timer.txt
index ad440a2b8051..e926aea1147d 100644
--- a/Documentation/devicetree/bindings/arm/arch_timer.txt
+++ b/Documentation/devicetree/bindings/arm/arch_timer.txt
@@ -31,6 +31,12 @@ to deliver its interrupts via SPIs.
   This also affects writes to the tval register, due to the implicit
   counter read.
 
+- hisilicon,erratum-161010101 : A boolean property. Indicates the
+  presence of Hisilicon erratum 161010101, which says that reading the
+  counters is unreliable in some cases, and reads may return a value 32
+  beyond the correct value. This also affects writes to the tval
+  registers, due to the implicit counter read.
+
 ** Optional properties:
 
 - arm,cpu-registers-not-fw-configured : Firmware does not initialize
diff --git a/Documentation/devicetree/bindings/cpufreq/ti-cpufreq.txt b/Documentation/devicetree/bindings/cpufreq/ti-cpufreq.txt
new file mode 100644
index 000000000000..ba0e15ad5bd9
--- /dev/null
+++ b/Documentation/devicetree/bindings/cpufreq/ti-cpufreq.txt
@@ -0,0 +1,128 @@
+TI CPUFreq and OPP bindings
+================================
+
+Certain TI SoCs, like those in the am335x, am437x, am57xx, and dra7xx
+families support different OPPs depending on the silicon variant in use.
+The ti-cpufreq driver can use revision and an efuse value from the SoC to
+provide the OPP framework with supported hardware information. This is
+used to determine which OPPs from the operating-points-v2 table get enabled
+when it is parsed by the OPP framework.
+
+Required properties:
+--------------------
+In 'cpus' nodes:
+- operating-points-v2: Phandle to the operating-points-v2 table to use.
+
+In 'operating-points-v2' table:
+- compatible: Should be
+	- 'operating-points-v2-ti-cpu' for am335x, am43xx, and dra7xx/am57xx SoCs
+- syscon: A phandle pointing to a syscon node representing the control module
+	  register space of the SoC.
+
+Optional properties:
+--------------------
+For each opp entry in 'operating-points-v2' table:
+- opp-supported-hw: Two bitfields indicating:
+	1. Which revision of the SoC the OPP is supported by
+	2. Which eFuse bits indicate this OPP is available
+
+	A bitwise AND is performed against these values and if any bit
+	matches, the OPP gets enabled.
+
+Example:
+--------
+
+/* From arch/arm/boot/dts/am33xx.dtsi */
+cpus {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	cpu@0 {
+		compatible = "arm,cortex-a8";
+		device_type = "cpu";
+		reg = <0>;
+
+		operating-points-v2 = <&cpu0_opp_table>;
+
+		clocks = <&dpll_mpu_ck>;
+		clock-names = "cpu";
+
+		clock-latency = <300000>; /* From omap-cpufreq driver */
+	};
+};
+
+/*
+ * cpu0 has different OPPs depending on SoC revision and some on revisions
+ * 0x2 and 0x4 have eFuse bits that indicate if they are available or not
+ */
+cpu0_opp_table: opp-table {
+	compatible = "operating-points-v2-ti-cpu";
+	syscon = <&scm_conf>;
+
+	/*
+	 * The three following nodes are marked with opp-suspend
+	 * because they can not be enabled simultaneously on a
+	 * single SoC.
+	 */
+	opp50@300000000 {
+		opp-hz = /bits/ 64 <300000000>;
+		opp-microvolt = <950000 931000 969000>;
+		opp-supported-hw = <0x06 0x0010>;
+		opp-suspend;
+	};
+
+	opp100@275000000 {
+		opp-hz = /bits/ 64 <275000000>;
+		opp-microvolt = <1100000 1078000 1122000>;
+		opp-supported-hw = <0x01 0x00FF>;
+		opp-suspend;
+	};
+
+	opp100@300000000 {
+		opp-hz = /bits/ 64 <300000000>;
+		opp-microvolt = <1100000 1078000 1122000>;
+		opp-supported-hw = <0x06 0x0020>;
+		opp-suspend;
+	};
+
+	opp100@500000000 {
+		opp-hz = /bits/ 64 <500000000>;
+		opp-microvolt = <1100000 1078000 1122000>;
+		opp-supported-hw = <0x01 0xFFFF>;
+	};
+
+	opp100@600000000 {
+		opp-hz = /bits/ 64 <600000000>;
+		opp-microvolt = <1100000 1078000 1122000>;
+		opp-supported-hw = <0x06 0x0040>;
+	};
+
+	opp120@600000000 {
+		opp-hz = /bits/ 64 <600000000>;
+		opp-microvolt = <1200000 1176000 1224000>;
+		opp-supported-hw = <0x01 0xFFFF>;
+	};
+
+	opp120@720000000 {
+		opp-hz = /bits/ 64 <720000000>;
+		opp-microvolt = <1200000 1176000 1224000>;
+		opp-supported-hw = <0x06 0x0080>;
+	};
+
+	oppturbo@720000000 {
+		opp-hz = /bits/ 64 <720000000>;
+		opp-microvolt = <1260000 1234800 1285200>;
+		opp-supported-hw = <0x01 0xFFFF>;
+	};
+
+	oppturbo@800000000 {
+		opp-hz = /bits/ 64 <800000000>;
+		opp-microvolt = <1260000 1234800 1285200>;
+		opp-supported-hw = <0x06 0x0100>;
+	};
+
+	oppnitro@1000000000 {
+		opp-hz = /bits/ 64 <1000000000>;
+		opp-microvolt = <1325000 1298500 1351500>;
+		opp-supported-hw = <0x04 0x0200>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/devfreq/exynos-bus.txt b/Documentation/devicetree/bindings/devfreq/exynos-bus.txt
index d3ec8e676b6b..d085ef90d27c 100644
--- a/Documentation/devicetree/bindings/devfreq/exynos-bus.txt
+++ b/Documentation/devicetree/bindings/devfreq/exynos-bus.txt
@@ -123,6 +123,20 @@ Detailed correlation between sub-blocks and power line according to Exynos SoC:
 		|--- FSYS
 		|--- FSYS2
 
+- In case of Exynos5433, there is VDD_INT power line as following:
+	VDD_INT |--- G2D (parent device)
+		|--- MSCL
+		|--- GSCL
+		|--- JPEG
+		|--- MFC
+		|--- HEVC
+		|--- BUS0
+		|--- BUS1
+		|--- BUS2
+		|--- PERIS (Fixed clock rate)
+		|--- PERIC (Fixed clock rate)
+		|--- FSYS  (Fixed clock rate)
+
 Example1:
 	Show the AXI buses of Exynos3250 SoC. Exynos3250 divides the buses to
 	power line (regulator). The MIF (Memory Interface) AXI bus is used to
diff --git a/Documentation/devicetree/bindings/hwmon/adc128d818.txt b/Documentation/devicetree/bindings/hwmon/adc128d818.txt
new file mode 100644
index 000000000000..08bab0e94d25
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/adc128d818.txt
@@ -0,0 +1,38 @@
+TI ADC128D818 ADC System Monitor With Temperature Sensor
+--------------------------------------------------------
+
+Operation modes:
+
+ - Mode 0:  7 single-ended voltage readings (IN0-IN6),
+            1 temperature reading (internal)
+ - Mode 1:  8 single-ended voltage readings (IN0-IN7),
+            no temperature
+ - Mode 2:  4 pseudo-differential voltage readings
+              (IN0-IN1, IN3-IN2, IN4-IN5, IN7-IN6),
+            1 temperature reading (internal)
+ - Mode 3:  4 single-ended voltage readings (IN0-IN3),
+            2 pseudo-differential voltage readings
+              (IN4-IN5, IN7-IN6),
+            1 temperature reading (internal)
+
+If no operation mode is configured via device tree, the driver keeps the
+currently active chip operation mode (default is mode 0).
+
+
+Required node properties:
+
+ - compatible:  must be set to "ti,adc128d818"
+ - reg:         I2C address of the device
+
+Optional node properties:
+
+ - ti,mode:     Operation mode (see above).
+
+
+Example (operation mode 2):
+
+	adc128d818@1d {
+		compatible = "ti,adc128d818";
+		reg = <0x1d>;
+		ti,mode = <2>;
+	};
diff --git a/Documentation/devicetree/bindings/hwmon/lm70.txt b/Documentation/devicetree/bindings/hwmon/lm70.txt
index e7fd921aa4f1..ea417a0d32af 100644
--- a/Documentation/devicetree/bindings/hwmon/lm70.txt
+++ b/Documentation/devicetree/bindings/hwmon/lm70.txt
@@ -4,6 +4,7 @@ Required properties:
 - compatible: one of
 		"ti,lm70"
 		"ti,tmp121"
+		"ti,tmp122"
 		"ti,lm71"
 		"ti,lm74"
 
diff --git a/Documentation/devicetree/bindings/hwmon/lm90.txt b/Documentation/devicetree/bindings/hwmon/lm90.txt
index e8632486b9ef..97581266e329 100644
--- a/Documentation/devicetree/bindings/hwmon/lm90.txt
+++ b/Documentation/devicetree/bindings/hwmon/lm90.txt
@@ -33,6 +33,11 @@ Optional properties:
               LM90 "-ALERT" pin output.
               See interrupt-controller/interrupts.txt for the format.
 
+- #thermal-sensor-cells: should be set to 1. See thermal/thermal.txt for
+	      details. See <include/dt-bindings/thermal/lm90.h> for the
+	      definition of the local, remote and 2nd remote sensor index
+	      constants.
+
 Example LM90 node:
 
 temp-sensor {
@@ -41,4 +46,5 @@ temp-sensor {
 	vcc-supply = <&palmas_ldo6_reg>;
 	interrupt-parent = <&gpio>;
 	interrupts = <TEGRA_GPIO(O, 4) IRQ_TYPE_LEVEL_LOW>;
+	#thermal-sensor-cells = <1>;
 }
diff --git a/Documentation/devicetree/bindings/hwmon/sht15.txt b/Documentation/devicetree/bindings/hwmon/sht15.txt
new file mode 100644
index 000000000000..6a80277cc426
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/sht15.txt
@@ -0,0 +1,19 @@
+Sensirion SHT15 Humidity and Temperature Sensor
+
+Required properties:
+
+ - "compatible": must be "sensirion,sht15".
+ - "data-gpios": GPIO connected to the data line.
+ - "clk-gpios": GPIO connected to the clock line.
+ - "vcc-supply": regulator that drives the VCC pin.
+
+Example:
+
+	sensor {
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_sensor>;
+		compatible = "sensirion,sht15";
+		clk-gpios = <&gpio4 12 0>;
+		data-gpios = <&gpio4 13 0>;
+		vcc-supply = <&reg_sht15>;
+	};
diff --git a/Documentation/devicetree/bindings/hwmon/stts751.txt b/Documentation/devicetree/bindings/hwmon/stts751.txt
new file mode 100644
index 000000000000..3ee1dc30e72f
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/stts751.txt
@@ -0,0 +1,15 @@
+* STTS751 thermometer.
+
+Required node properties:
+- compatible: "stts751"
+- reg: I2C bus address of the device
+
+Optional properties:
+- smbus-timeout-disable: when set, the smbus timeout function will be disabled
+
+Example stts751 node:
+
+temp-sensor {
+	compatible = "stts751";
+	reg = <0x48>;
+}
diff --git a/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt b/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt
new file mode 100644
index 000000000000..97c1167fa533
--- /dev/null
+++ b/Documentation/devicetree/bindings/interrupt-controller/cortina,gemini-interrupt-controller.txt
@@ -0,0 +1,22 @@
+* Cortina Systems Gemini interrupt controller
+
+This interrupt controller is found on the Gemini SoCs.
+
+Required properties:
+- compatible: must be "cortina,gemini-interrupt-controller"
+- reg: The register bank for the interrupt controller.
+- interrupt-controller: Identifies the node as an interrupt controller
+- #interrupt-cells: The number of cells to define the interrupts.
+  Must be 2 as the controller can specify level or rising edge
+  IRQs. The bindings follows the standard binding for controllers
+  with two cells specified in
+  interrupt-controller/interrupts.txt
+
+Example:
+
+interrupt-controller@48000000 {
+	compatible = "cortina,gemini-interrupt-controller";
+	reg = <0x48000000 0x1000>;
+	interrupt-controller;
+	#interrupt-cells = <2>;
+};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
index 0dcb7c7d3e40..944657684d73 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
@@ -15,6 +15,9 @@ Properties:
   Second cell specifies the irq distribution mode to cores
      0=Round Robin; 1=cpu0, 2=cpu1, 4=cpu2, 8=cpu3
 
+  The second cell in interrupts property is deprecated and may be ignored by
+  the kernel.
+
   intc accessed via the special ARC AUX register interface, hence "reg" property
   is not specified.
 
diff --git a/Documentation/devicetree/bindings/leds/common.txt b/Documentation/devicetree/bindings/leds/common.txt
index 696be5792625..24b656014089 100644
--- a/Documentation/devicetree/bindings/leds/common.txt
+++ b/Documentation/devicetree/bindings/leds/common.txt
@@ -61,16 +61,24 @@ property can be omitted.
 
 Examples:
 
-system-status {
-	label = "Status";
-	linux,default-trigger = "heartbeat";
-	...
+gpio-leds {
+	compatible = "gpio-leds";
+
+	system-status {
+		label = "Status";
+		linux,default-trigger = "heartbeat";
+		gpios = <&gpio0 0 GPIO_ACTIVE_HIGH>;
+	};
 };
 
-camera-flash {
-	label = "Flash";
-	led-sources = <0>, <1>;
-	led-max-microamp = <50000>;
-	flash-max-microamp = <320000>;
-	flash-max-timeout-us = <500000>;
+max77693-led {
+	compatible = "maxim,max77693-led";
+
+	camera-flash {
+		label = "Flash";
+		led-sources = <0>, <1>;
+		led-max-microamp = <50000>;
+		flash-max-microamp = <320000>;
+		flash-max-timeout-us = <500000>;
+	};
 };
diff --git a/Documentation/devicetree/bindings/mmc/amlogic,meson-gx.txt b/Documentation/devicetree/bindings/mmc/amlogic,meson-gx.txt
index 7f95ec400863..50bf611a4d2c 100644
--- a/Documentation/devicetree/bindings/mmc/amlogic,meson-gx.txt
+++ b/Documentation/devicetree/bindings/mmc/amlogic,meson-gx.txt
@@ -17,7 +17,7 @@ Required properties:
 	"core" - Main peripheral bus clock
 	"clkin0" - Parent clock of internal mux
 	"clkin1" - Other parent clock of internal mux
-  The driver has an interal mux clock which switches between clkin0 and clkin1 depending on the
+  The driver has an internal mux clock which switches between clkin0 and clkin1 depending on the
   clock rate requested by the MMC core.
 
 Example:
diff --git a/Documentation/devicetree/bindings/mmc/mmc-pwrseq-sd8787.txt b/Documentation/devicetree/bindings/mmc/mmc-pwrseq-sd8787.txt
new file mode 100644
index 000000000000..22e9340e4ba2
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/mmc-pwrseq-sd8787.txt
@@ -0,0 +1,16 @@
+* Marvell SD8787 power sequence provider
+
+Required properties:
+- compatible: must be "mmc-pwrseq-sd8787".
+- powerdown-gpios: contains a power down GPIO specifier with the
+		   default active state
+- reset-gpios: contains a reset GPIO specifier with the default
+		   active state
+
+Example:
+
+	wifi_pwrseq: wifi_pwrseq {
+		compatible = "mmc-pwrseq-sd8787";
+		powerdown-gpios = <&twl_gpio 0 GPIO_ACTIVE_LOW>;
+		reset-gpios = <&twl_gpio 1 GPIO_ACTIVE_LOW>;
+	}
diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index 8a377827695b..c7f4a0ec48ed 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -40,6 +40,7 @@ Optional properties:
 - cap-mmc-hw-reset: eMMC hardware reset is supported
 - cap-sdio-irq: enable SDIO IRQ signalling on this interface
 - full-pwr-cycle: full power cycle of the card is supported
+- mmc-ddr-3_3v: eMMC high-speed DDR mode(3.3V I/O) is supported
 - mmc-ddr-1_8v: eMMC high-speed DDR mode(1.8V I/O) is supported
 - mmc-ddr-1_2v: eMMC high-speed DDR mode(1.2V I/O) is supported
 - mmc-hs200-1_8v: eMMC HS200 mode(1.8V I/O) is supported
diff --git a/Documentation/devicetree/bindings/mmc/sdhci-st.txt b/Documentation/devicetree/bindings/mmc/sdhci-st.txt
index 3cd4c43a3260..230fd696eb92 100644
--- a/Documentation/devicetree/bindings/mmc/sdhci-st.txt
+++ b/Documentation/devicetree/bindings/mmc/sdhci-st.txt
@@ -38,7 +38,7 @@ Optional properties:
 - bus-width:		Number of data lines.
 			See:  Documentation/devicetree/bindings/mmc/mmc.txt.
 
-- max-frequency:	Can be 200MHz, 100Mz or 50MHz (default) and used for
+- max-frequency:	Can be 200MHz, 100MHz or 50MHz (default) and used for
 			configuring the CCONFIG3 in the mmcss.
 			See:  Documentation/devicetree/bindings/mmc/mmc.txt.
 
diff --git a/Documentation/devicetree/bindings/mmc/sdhci.txt b/Documentation/devicetree/bindings/mmc/sdhci.txt
index 1c95a1a555c3..0e9923a64024 100644
--- a/Documentation/devicetree/bindings/mmc/sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/sdhci.txt
@@ -5,7 +5,7 @@ host controllers refer to the mmc[1] bindings.
 
 Optional properties:
 - sdhci-caps-mask: The sdhci capabilities register is incorrect. This 64bit
-  property corresponds to the bits in the sdhci capabilty register. If the bit
+  property corresponds to the bits in the sdhci capability register. If the bit
   is on in the mask then the bit is incorrect in the register and should be
   turned off, before applying sdhci-caps.
 - sdhci-caps: The sdhci capabilities register is incorrect. This 64bit
diff --git a/Documentation/devicetree/bindings/mmc/sunxi-mmc.txt b/Documentation/devicetree/bindings/mmc/sunxi-mmc.txt
index 55cdd804cdba..7d53a799f140 100644
--- a/Documentation/devicetree/bindings/mmc/sunxi-mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/sunxi-mmc.txt
@@ -13,6 +13,7 @@ Required properties:
    * "allwinner,sun5i-a13-mmc"
    * "allwinner,sun7i-a20-mmc"
    * "allwinner,sun9i-a80-mmc"
+   * "allwinner,sun50i-a64-emmc"
    * "allwinner,sun50i-a64-mmc"
  - reg : mmc controller base registers
  - clocks : a list with 4 phandle + clock specifier pairs
diff --git a/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
index 7fd17c3da116..9cb55ca57461 100644
--- a/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
@@ -16,7 +16,7 @@ Required Properties:
   each child-node representing a supported slot. There should be atleast one
   child node representing a card slot. The name of the child node representing
   the slot is recommended to be slot@n where n is the unique number of the slot
-  connnected to the controller. The following are optional properties which
+  connected to the controller. The following are optional properties which
   can be included in the slot child node.
 
 	* reg: specifies the physical slot number. The valid values of this
@@ -75,6 +75,17 @@ Optional properties:
 * card-detect-delay: Delay in milli-seconds before detecting card after card
   insert event. The default value is 0.
 
+* data-addr: Override fifo address with value provided by DT. The default FIFO reg
+  offset is assumed as 0x100 (version < 0x240A) and 0x200(version >= 0x240A) by
+  driver. If the controller does not follow this rule, please use this property
+  to set fifo address in device tree.
+
+* fifo-watermark-aligned: Data done irq is expected if data length is less than
+  watermark in PIO mode. But fifo watermark is requested to be aligned with data
+  length in some SoC so that TX/RX irq can be generated with data done irq. Add this
+  watermark quirk to mark this requirement and force fifo watermark setting
+  accordingly.
+
 * vmmc-supply: The phandle to the regulator to use for vmmc.  If this is
   specified we'll defer probe until we can find this regulator.
 
@@ -102,6 +113,8 @@ board specific portions as listed below.
 		interrupts = <0 75 0>;
 		#address-cells = <1>;
 		#size-cells = <0>;
+		data-addr = <0x200>;
+		fifo-watermark-aligned;
 		resets = <&rst 20>;
 		reset-names = "reset";
 	};
diff --git a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
index a1650edfd2b7..4fd8b7acc510 100644
--- a/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/tmio_mmc.txt
@@ -25,6 +25,19 @@ Required properties:
 		"renesas,sdhi-r8a7795" - SDHI IP on R8A7795 SoC
 		"renesas,sdhi-r8a7796" - SDHI IP on R8A7796 SoC
 
+- clocks: Most controllers only have 1 clock source per channel. However, on
+	  some variations of this controller, the internal card detection
+	  logic that exists in this controller is sectioned off to be run by a
+	  separate second clock source to allow the main core clock to be turned
+	  off to save power.
+	  If 2 clocks are specified by the hardware, you must name them as
+	  "core" and "cd". If the controller only has 1 clock, naming is not
+	  required.
+	  Below is the number clocks for each supported SoC:
+	   1: SH73A0, R8A73A4, R8A7740, R8A7778, R8A7779, R8A7790
+	      R8A7791, R8A7792, R8A7793, R8A7794, R8A7795, R8A7796
+	   2: R7S72100
+
 Optional properties:
 - toshiba,mmc-wrprotect-disable: write-protect detection is unavailable
 - pinctrl-names: should be "default", "state_uhs"
diff --git a/Documentation/devicetree/bindings/mmc/zx-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/zx-dw-mshc.txt
new file mode 100644
index 000000000000..eaade0e5adeb
--- /dev/null
+++ b/Documentation/devicetree/bindings/mmc/zx-dw-mshc.txt
@@ -0,0 +1,33 @@
+* ZTE specific extensions to the Synopsys Designware Mobile Storage
+  Host Controller
+
+The Synopsys designware mobile storage host controller is used to interface
+a SoC with storage medium such as eMMC or SD/MMC cards. This file documents
+differences between the core Synopsys dw mshc controller properties described
+by synopsys-dw-mshc.txt and the properties used by the ZTE specific
+extensions to the Synopsys Designware Mobile Storage Host Controller.
+
+Required Properties:
+
+* compatible: should be
+	- "zte,zx296718-dw-mshc": for ZX SoCs
+
+Example:
+
+	mmc1: mmc@1110000 {
+		compatible = "zte,zx296718-dw-mshc";
+		reg = <0x01110000 0x1000>;
+		interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
+		fifo-depth = <32>;
+		data-addr = <0x200>;
+		fifo-watermark-aligned;
+		bus-width = <4>;
+		clock-frequency = <50000000>;
+		clocks = <&topcrm SD0_AHB>, <&topcrm SD0_WCLK>;
+		clock-names = "biu", "ciu";
+		num-slots = <1>;
+		max-frequency = <50000000>;
+		cap-sdio-irq;
+		cap-sd-highspeed;
+		status = "disabled";
+	};
diff --git a/Documentation/devicetree/bindings/mtd/aspeed-smc.txt b/Documentation/devicetree/bindings/mtd/aspeed-smc.txt
new file mode 100644
index 000000000000..49f6528ef547
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/aspeed-smc.txt
@@ -0,0 +1,51 @@
+* Aspeed Firmware Memory controller
+* Aspeed SPI Flash Memory Controller
+
+The Firmware Memory Controller in the Aspeed AST2500 SoC supports
+three chip selects, two of which are always of SPI type and the third
+can be SPI or NOR type flash. These bindings only describe SPI.
+
+The two SPI flash memory controllers in the AST2500 each support two
+chip selects.
+
+Required properties:
+  - compatible : Should be one of
+	"aspeed,ast2400-fmc" for the AST2400 Firmware Memory Controller
+	"aspeed,ast2400-spi" for the AST2400 SPI Flash memory Controller
+	"aspeed,ast2500-fmc" for the AST2500 Firmware Memory Controller
+	"aspeed,ast2500-spi" for the AST2500 SPI flash memory controllers
+
+  - reg : the first contains the control register location and length,
+          the second contains the memory window mapping address and length
+  - #address-cells : must be 1 corresponding to chip select child binding
+  - #size-cells : must be 0 corresponding to chip select child binding
+
+Optional properties:
+  - interrupts : Should contain the interrupt for the dma device if an
+    FMC
+
+The child nodes are the SPI flash modules which must have a compatible
+property as specified in bindings/mtd/jedec,spi-nor.txt
+
+Optionally, the child node can contain properties for SPI mode (may be
+ignored):
+  - spi-max-frequency - max frequency of spi bus
+
+
+Example:
+fmc: fmc@1e620000 {
+	compatible = "aspeed,ast2500-fmc";
+	reg = < 0x1e620000 0x94
+		0x20000000 0x02000000 >;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	interrupts = <19>;
+	flash@0 {
+		reg = < 0 >;
+		compatible = "jedec,spi-nor";
+		/* spi-max-frequency = <>; */
+		/* m25p,fast-read; */
+		#address-cells = <1>;
+		#size-cells = <1>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/mtd/common.txt b/Documentation/devicetree/bindings/mtd/common.txt
new file mode 100644
index 000000000000..fc068b923d7a
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/common.txt
@@ -0,0 +1,15 @@
+* Common properties of all MTD devices
+
+Optional properties:
+- label: user-defined MTD device name. Can be used to assign user
+  friendly names to MTD devices (instead of the flash model or flash
+  controller based name) in order to ease flash device identification
+  and/or describe what they are used for.
+
+Example:
+
+	flash@0 {
+		label = "System-firmware";
+
+		/* flash type specific properties */
+	};
diff --git a/Documentation/devicetree/bindings/mtd/cortina,gemini-flash.txt b/Documentation/devicetree/bindings/mtd/cortina,gemini-flash.txt
new file mode 100644
index 000000000000..3fa1b34d69ad
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/cortina,gemini-flash.txt
@@ -0,0 +1,24 @@
+Flash device on Cortina Systems Gemini SoC
+
+This flash is regular CFI compatible (Intel or AMD extended) flash chips with
+some special bits that can be controlled by the machine's system controller.
+
+Required properties:
+- compatible : must be "cortina,gemini-flash", "cfi-flash";
+- reg : memory address for the flash chip
+- syscon : must be a phandle to the system controller
+- bank-width : width in bytes of flash interface, should be <2>
+
+For the rest of the properties, see mtd-physmap.txt.
+
+The device tree may optionally contain sub-nodes describing partitions of the
+address space. See partition.txt for more detail.
+
+Example:
+
+flash@30000000 {
+	compatible = "cortina,gemini-flash", "cfi-flash";
+	reg = <0x30000000 0x01000000>;
+	syscon = <&syscon>;
+	bank-width = <2>;
+};
diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
index 2c91c03e7eb0..3e920ec5c4d3 100644
--- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
+++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
@@ -14,6 +14,8 @@ Required properties:
                  at25df641
                  at26df081a
                  mr25h256
+                 mr25h10
+                 mr25h40
                  mx25l4005a
                  mx25l1606e
                  mx25l6405d
diff --git a/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt b/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt
index fb314f09861b..5ded66ad7aef 100644
--- a/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt
+++ b/Documentation/devicetree/bindings/mtd/mtk-quadspi.txt
@@ -1,7 +1,13 @@
 * Serial NOR flash controller for MTK MT81xx (and similar)
 
 Required properties:
-- compatible: 	  should be "mediatek,mt8173-nor";
+- compatible: 	  The possible values are:
+		  "mediatek,mt2701-nor"
+		  "mediatek,mt7623-nor"
+		  "mediatek,mt8173-nor"
+		  For mt8173, compatible should be "mediatek,mt8173-nor".
+		  For every other SoC, should contain both the SoC-specific compatible string
+		  and "mediatek,mt8173-nor".
 - reg: 		  physical base address and length of the controller's register
 - clocks: 	  the phandle of the clocks needed by the nor controller
 - clock-names: 	  the names of the clocks
diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt
index c010fafc66a8..c7194e87d5f4 100644
--- a/Documentation/devicetree/bindings/net/mediatek-net.txt
+++ b/Documentation/devicetree/bindings/net/mediatek-net.txt
@@ -7,7 +7,7 @@ have dual GMAC each represented by a child node..
 * Ethernet controller node
 
 Required properties:
-- compatible: Should be "mediatek,mt7623-eth"
+- compatible: Should be "mediatek,mt2701-eth"
 - reg: Address and length of the register set for the device
 - interrupts: Should contain the three frame engines interrupts in numeric
 	order. These are fe_int0, fe_int1 and fe_int2.
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index ff1bc4b1bb3b..fb5056b22685 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -19,8 +19,9 @@ Optional Properties:
   specifications. If neither of these are specified, the default is to
   assume clause 22.
 
-  If the phy's identifier is known then the list may contain an entry
-  of the form: "ethernet-phy-idAAAA.BBBB" where
+  If the PHY reports an incorrect ID (or none at all) then the
+  "compatible" list may contain an entry with the correct PHY ID in the
+  form: "ethernet-phy-idAAAA.BBBB" where
      AAAA - The value of the 16 bit Phy Identifier 1 register as
             4 hex digits. This is the chip vendor OUI bits 3:18
      BBBB - The value of the 16 bit Phy Identifier 2 register as
diff --git a/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt b/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
index 980b16df74c3..0854451ff91d 100644
--- a/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
+++ b/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
@@ -1,4 +1,4 @@
-Marvell 8897/8997 (sd8897/sd8997/pcie8997) SDIO/PCIE devices
+Marvell 8787/8897/8997 (sd8787/sd8897/sd8997/pcie8997) SDIO/PCIE devices
 ------
 
 This node provides properties for controlling the Marvell SDIO/PCIE wireless device.
@@ -8,6 +8,7 @@ connects the device to the system.
 Required properties:
 
   - compatible : should be one of the following:
+	* "marvell,sd8787"
 	* "marvell,sd8897"
 	* "marvell,sd8997"
 	* "pci11ab,2b42"
@@ -34,6 +35,9 @@ Optional properties:
 		 so that the wifi chip can wakeup host platform under certain condition.
 		 during system resume, the irq will be disabled to make sure
 		 unnecessary interrupt is not received.
+  - vmmc-supply: a phandle of a regulator, supplying VCC to the card
+  - mmc-pwrseq:  phandle to the MMC power sequence node. See "mmc-pwrseq-*"
+		 for documentation of MMC power sequence bindings.
 
 Example:
 
@@ -46,6 +50,7 @@ so that firmware can wakeup host using this device side pin.
 &mmc3 {
 	status = "okay";
 	vmmc-supply = <&wlan_en_reg>;
+	mmc-pwrseq = <&wifi_pwrseq>;
 	bus-width = <4>;
 	cap-power-off-card;
 	keep-power-in-suspend;
diff --git a/Documentation/devicetree/bindings/power/supply/axp20x_ac_power.txt b/Documentation/devicetree/bindings/power/supply/axp20x_ac_power.txt
new file mode 100644
index 000000000000..826e8a879121
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/axp20x_ac_power.txt
@@ -0,0 +1,22 @@
+AXP20X and AXP22X PMICs' AC power supply
+
+Required Properties:
+ - compatible: One of:
+			"x-powers,axp202-ac-power-supply"
+			"x-powers,axp221-ac-power-supply"
+
+This node is a subnode of the axp20x PMIC.
+
+The AXP20X can read the current current and voltage supplied by AC by
+reading ADC channels from the AXP20X ADC.
+
+The AXP22X is only able to tell if an AC power supply is present and
+usable.
+
+Example:
+
+&axp209 {
+	ac_power_supply: ac-power-supply {
+		compatible = "x-powers,axp202-ac-power-supply";
+	};
+};
diff --git a/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt b/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt
index f1d7beec45bf..ba8d35f66cbe 100644
--- a/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt
+++ b/Documentation/devicetree/bindings/power/supply/axp20x_usb_power.txt
@@ -3,6 +3,11 @@ AXP20x USB power supply
 Required Properties:
 -compatible: One of: "x-powers,axp202-usb-power-supply"
                      "x-powers,axp221-usb-power-supply"
+                     "x-powers,axp223-usb-power-supply"
+
+The AXP223 PMIC shares most of its behaviour with the AXP221 but has slight
+variations such as the former being able to set the VBUS power supply max
+current to 100mA, unlike the latter.
 
 This node is a subnode of the axp20x PMIC.
 
diff --git a/Documentation/devicetree/bindings/power/supply/bq27xxx.txt b/Documentation/devicetree/bindings/power/supply/bq27xxx.txt
new file mode 100644
index 000000000000..b0c95ef63e68
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/bq27xxx.txt
@@ -0,0 +1,36 @@
+Binding for TI BQ27XXX fuel gauge family
+
+Required properties:
+- compatible: Should contain one of the following:
+ * "ti,bq27200" - BQ27200
+ * "ti,bq27210" - BQ27210
+ * "ti,bq27500" - deprecated, use revision specific property below
+ * "ti,bq27510" - deprecated, use revision specific property below
+ * "ti,bq27520" - deprecated, use revision specific property below
+ * "ti,bq27500-1" - BQ27500/1
+ * "ti,bq27510g1" - BQ27510-g1
+ * "ti,bq27510g2" - BQ27510-g2
+ * "ti,bq27510g3" - BQ27510-g3
+ * "ti,bq27520g1" - BQ27520-g1
+ * "ti,bq27520g2" - BQ27520-g2
+ * "ti,bq27520g3" - BQ27520-g3
+ * "ti,bq27520g4" - BQ27520-g4
+ * "ti,bq27530" - BQ27530
+ * "ti,bq27531" - BQ27531
+ * "ti,bq27541" - BQ27541
+ * "ti,bq27542" - BQ27542
+ * "ti,bq27546" - BQ27546
+ * "ti,bq27742" - BQ27742
+ * "ti,bq27545" - BQ27545
+ * "ti,bq27421" - BQ27421
+ * "ti,bq27425" - BQ27425
+ * "ti,bq27441" - BQ27441
+ * "ti,bq27621" - BQ27621
+- reg: integer, i2c address of the device.
+
+Example:
+
+bq27510g3 {
+    compatible = "ti,bq27510g3";
+    reg = <0x55>;
+};
diff --git a/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt b/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt
index 65b88fac854b..06f8a5ddb68e 100644
--- a/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt
+++ b/Documentation/devicetree/bindings/power/supply/qcom_smbb.txt
@@ -105,6 +105,22 @@ PROPERTIES
                regulation must be done externally to fully comply with
                the JEITA safety guidelines if this flag is set.
 
+- usb_otg_in-supply:
+  Usage: optional
+  Value type: <phandle>
+  Description: Reference to the regulator supplying power to the USB_OTG_IN
+               pin.
+
+child nodes:
+- otg-vbus:
+  Usage: optional
+  Description: This node defines a regulator used to control the direction
+               of VBUS voltage - specifically: whether to supply voltage
+               to VBUS for host mode operation of the OTG port, or allow
+               input voltage from external VBUS for charging.  In the
+               hardware, the supply for this regulator comes from
+               usb_otg_in-supply.
+
 EXAMPLE
 charger@1000 {
        compatible = "qcom,pm8941-charger";
@@ -128,4 +144,7 @@ charger@1000 {
 
        qcom,fast-charge-current-limit = <1000000>;
        qcom,dc-charge-current-limit = <1000000>;
+       usb_otg_in-supply = <&pm8941_5vs1>;
+
+       otg-vbus {};
 };
diff --git a/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt b/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt
new file mode 100644
index 000000000000..a3719623a94f
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt
@@ -0,0 +1,23 @@
+SBS sbs-charger
+~~~~~~~~~~
+
+Required properties:
+ - compatible: "<vendor>,<part-number>", "sbs,sbs-charger" as fallback. The part
+     number compatible string might be used in order to take care of vendor
+     specific registers.
+
+Optional properties:
+- interrupt-parent: Should be the phandle for the interrupt controller. Use in
+    conjunction with "interrupts".
+- interrupts: Interrupt mapping for GPIO IRQ. Use in conjunction with
+    "interrupt-parent". If an interrupt is not provided the driver will switch
+    automatically to polling.
+
+Example:
+
+	ltc4100@9 {
+		compatible = "lltc,ltc4100", "sbs,sbs-charger";
+		reg = <0x9>;
+		interrupt-parent = <&gpio6>;
+		interrupts = <7 IRQ_TYPE_LEVEL_LOW>;
+	};
diff --git a/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt b/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt
index 3bf55757ceec..de45e1a2a4d9 100644
--- a/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt
+++ b/Documentation/devicetree/bindings/power/supply/ti,bq24735.txt
@@ -8,8 +8,10 @@ Optional properties :
  - interrupts : Specify the interrupt to be used to trigger when the AC
    adapter is either plugged in or removed.
  - ti,ac-detect-gpios : This GPIO is optionally used to read the AC adapter
-   presence. This is a Host GPIO that is configured as an input and
-   connected to the bq24735.
+   status. This is a Host GPIO that is configured as an input and connected
+   to the ACOK pin on the bq24735. Note: for backwards compatibility reasons,
+   the GPIO must be active on AC adapter absence despite ACOK being active
+   (high) on AC adapter presence.
  - ti,charge-current : Used to control and set the charging current. This value
    must be between 128mA and 8.128A with a 64mA step resolution. The POR value
    is 0x0000h. This number is in mA (e.g. 8192), see spec for more information
@@ -25,6 +27,8 @@ Optional properties :
  - ti,external-control : Indicates that the charger is configured externally
    and that the host should not attempt to enable/disable charging or set the
    charge voltage/current.
+ - poll-interval : In case 'interrupts' is not specified, poll AC adapter
+   presence with this interval (milliseconds).
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/power_supply/maxim,max14656.txt b/Documentation/devicetree/bindings/power_supply/maxim,max14656.txt
new file mode 100644
index 000000000000..e03e85ae6572
--- /dev/null
+++ b/Documentation/devicetree/bindings/power_supply/maxim,max14656.txt
@@ -0,0 +1,25 @@
+Maxim MAX14656 / AL32 USB Charger Detector
+
+Required properties :
+- compatible : "maxim,max14656";
+- reg: i2c slave address
+- interrupt-parent: the phandle for the interrupt controller
+- interrupts: interrupt line
+
+Example:
+
+&i2c2 {
+	clock-frequency = <50000>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pinctrl_i2c2>;
+	status = "okay";
+
+	max14656@35 {
+		compatible = "maxim,max14656";
+		reg = <0x35>;
+		pinctrl-names = "default";
+		pinctrl-0 = <&pinctrl_charger_detect>;
+		interrupt-parent = <&gpio6>;
+		interrupts = <26 IRQ_TYPE_LEVEL_HIGH>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/regulator/anatop-regulator.txt b/Documentation/devicetree/bindings/regulator/anatop-regulator.txt
index 37c4ea076f88..1d58c8cfdbc0 100644
--- a/Documentation/devicetree/bindings/regulator/anatop-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/anatop-regulator.txt
@@ -14,6 +14,7 @@ Optional properties:
 - anatop-delay-bit-shift: Bit shift for the step time register
 - anatop-delay-bit-width: Number of bits used in the step time register
 - vin-supply: The supply for this regulator
+- anatop-enable-bit: Regulator enable bit offset
 
 Any property defined as part of the core regulator
 binding, defined in regulator.txt, can also be used.
diff --git a/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt b/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt
new file mode 100644
index 000000000000..675f4437ce92
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt
@@ -0,0 +1,34 @@
+Motorola CPCAP PMIC voltage regulators
+------------------------------------
+
+Requires node properties:
+- "compatible" value one of:
+    "motorola,cpcap-regulator"
+    "motorola,mapphone-cpcap-regulator"
+
+Required regulator properties:
+- "regulator-name"
+- "regulator-enable-ramp-delay"
+- "regulator-min-microvolt"
+- "regulator-max-microvolt"
+
+Optional regulator properties:
+- "regulator-boot-on"
+
+See Documentation/devicetree/bindings/regulator/regulator.txt
+for more details about the regulator properties.
+
+Example:
+
+cpcap_regulator: regulator {
+	compatible = "motorola,cpcap-regulator";
+
+	cpcap_regulators: regulators {
+		sw5: SW5 {
+			regulator-min-microvolt = <5050000>;
+			regulator-max-microvolt = <5050000>;
+			regulator-enable-ramp-delay = <50000>;
+			regulator-boot-on;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/regulator/gpio-regulator.txt b/Documentation/devicetree/bindings/regulator/gpio-regulator.txt
index e5cac1e0ca8a..dd1ed789728e 100644
--- a/Documentation/devicetree/bindings/regulator/gpio-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/gpio-regulator.txt
@@ -13,7 +13,7 @@ Optional properties:
 - startup-delay-us	: Startup time in microseconds.
 - enable-active-high	: Polarity of GPIO is active high (default is low).
 - regulator-type	: Specifies what is being regulated, must be either
-			  "voltage" or "current", defaults to current.
+			  "voltage" or "current", defaults to voltage.
 
 Any property defined as part of the core regulator binding defined in
 regulator.txt can also be used.
diff --git a/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.txt
index 1f8d6f84b657..4e3dfb5b5f16 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.txt
@@ -22,6 +22,7 @@ Regulator nodes are identified by their compatible:
 		    "qcom,rpm-pm8841-regulators"
 		    "qcom,rpm-pm8916-regulators"
 		    "qcom,rpm-pm8941-regulators"
+		    "qcom,rpm-pm8994-regulators"
 		    "qcom,rpm-pma8084-regulators"
 
 - vdd_s1-supply:
@@ -80,6 +81,56 @@ Regulator nodes are identified by their compatible:
 - vdd_s10-supply:
 - vdd_s11-supply:
 - vdd_s12-supply:
+- vdd_l1-supply:
+- vdd_l2_l26_l28-supply:
+- vdd_l3_l11-supply:
+- vdd_l4_l27_l31-supply:
+- vdd_l5_l7-supply:
+- vdd_l6_l12_l32-supply:
+- vdd_l5_l7-supply:
+- vdd_l8_l16_l30-supply:
+- vdd_l9_l10_l18_l22-supply:
+- vdd_l9_l10_l18_l22-supply:
+- vdd_l3_l11-supply:
+- vdd_l6_l12_l32-supply:
+- vdd_l13_l19_l23_l24-supply:
+- vdd_l14_l15-supply:
+- vdd_l14_l15-supply:
+- vdd_l8_l16_l30-supply:
+- vdd_l17_l29-supply:
+- vdd_l9_l10_l18_l22-supply:
+- vdd_l13_l19_l23_l24-supply:
+- vdd_l20_l21-supply:
+- vdd_l20_l21-supply:
+- vdd_l9_l10_l18_l22-supply:
+- vdd_l13_l19_l23_l24-supply:
+- vdd_l13_l19_l23_l24-supply:
+- vdd_l25-supply:
+- vdd_l2_l26_l28-supply:
+- vdd_l4_l27_l31-supply:
+- vdd_l2_l26_l28-supply:
+- vdd_l17_l29-supply:
+- vdd_l8_l16_l30-supply:
+- vdd_l4_l27_l31-supply:
+- vdd_l6_l12_l32-supply:
+- vdd_lvs1_2-supply:
+	Usage: optional (pm8994 only)
+	Value type: <phandle>
+	Definition: reference to regulator supplying the input pin, as
+		    described in the data sheet
+
+- vdd_s1-supply:
+- vdd_s2-supply:
+- vdd_s3-supply:
+- vdd_s4-supply:
+- vdd_s5-supply:
+- vdd_s6-supply:
+- vdd_s7-supply:
+- vdd_s8-supply:
+- vdd_s9-supply:
+- vdd_s10-supply:
+- vdd_s11-supply:
+- vdd_s12-supply:
 - vdd_l1_l11-supply:
 - vdd_l2_l3_l4_l27-supply:
 - vdd_l5_l7-supply:
@@ -113,6 +164,11 @@ pm8941:
 	l14, l15, l16, l17, l18, l19, l20, l21, l22, l23, l24, lvs1, lvs2,
 	lvs3, 5vs1, 5vs2
 
+pm8994:
+	s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, l1, l2, l3, l4, l5,
+	l6, l7, l8, l9, l10, l11, l12, l13, l14, l15, l16, l17, l18, l19, l20,
+	l21, l22, l23, l24, l25, l26, l27, l28, l29, l30, l31, l32, lvs1, lvs2
+
 pma8084:
 	s1, s2, s3, s4, s5, s6, s7, s8, s9, s10, s11, s12, l1, l2, l3, l4, l5,
 	l6, l7, l8, l9, l10, l11, l12, l13, l14, l15, l16, l17, l18, l19, l20,
diff --git a/Documentation/devicetree/bindings/spi/spi-lantiq-ssc.txt b/Documentation/devicetree/bindings/spi/spi-lantiq-ssc.txt
new file mode 100644
index 000000000000..6069b95a883d
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-lantiq-ssc.txt
@@ -0,0 +1,29 @@
+Lantiq Synchronous Serial Controller (SSC) SPI master driver
+
+Required properties:
+- compatible: "lantiq,ase-spi", "lantiq,falcon-spi", "lantiq,xrx100-spi"
+- #address-cells: see spi-bus.txt
+- #size-cells: see spi-bus.txt
+- reg: address and length of the spi master registers
+- interrupts: should contain the "spi_rx", "spi_tx" and "spi_err" interrupt.
+
+
+Optional properties:
+- clocks: spi clock phandle
+- num-cs: see spi-bus.txt, set to 8 if unset
+- base-cs: the number of the first chip select, set to 1 if unset.
+
+Example:
+
+
+spi: spi@E100800 {
+	compatible = "lantiq,xrx200-spi", "lantiq,xrx100-spi";
+	reg = <0xE100800 0x100>;
+	interrupt-parent = <&icu0>;
+	interrupts = <22 23 24>;
+	interrupt-names = "spi_rx", "spi_tx", "spi_err";
+	#address-cells = <1>;
+	#size-cells = <1>;
+	num-cs = <6>;
+	base-cs = <1>;
+};
diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.txt b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
index d2ca153614f9..83da4931d832 100644
--- a/Documentation/devicetree/bindings/spi/spi-rockchip.txt
+++ b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
@@ -31,6 +31,10 @@ Optional Properties:
 - rx-sample-delay-ns: nanoseconds to delay after the SCLK edge before sampling
 		Rx data (may need to be fine tuned for high capacitance lines).
 		No delay (0) by default.
+- pinctrl-names: Names for the pin configuration(s); may be "default" or
+		"sleep", where the "sleep" configuration may describe the state
+		the pins should be in during system suspend. See also
+		pinctrl/pinctrl-bindings.txt.
 
 
 Example:
@@ -46,4 +50,7 @@ Example:
 		interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&cru SCLK_SPI0>, <&cru PCLK_SPI0>;
 		clock-names = "spiclk", "apb_pclk";
+		pinctrl-0 = <&spi1_pins>;
+		pinctrl-1 = <&spi1_sleep>;
+		pinctrl-names = "default", "sleep";
 	};
diff --git a/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt b/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt
new file mode 100644
index 000000000000..16ea1d3b2e9e
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/cortina,gemini-timer.txt
@@ -0,0 +1,22 @@
+Cortina Systems Gemini timer
+
+This timer is embedded in the Cortina Systems Gemini SoCs.
+
+Required properties:
+
+- compatible : Must be "cortina,gemini-timer"
+- reg : Should contain registers location and length
+- interrupts : Should contain the three timer interrupts with
+  flags for rising edge
+- syscon : a phandle to the global Gemini system controller
+
+Example:
+
+timer@43000000 {
+	compatible = "cortina,gemini-timer";
+	reg = <0x43000000 0x1000>;
+	interrupts = <14 IRQ_TYPE_EDGE_RISING>, /* Timer 1 */
+		   <15 IRQ_TYPE_EDGE_RISING>, /* Timer 2 */
+		   <16 IRQ_TYPE_EDGE_RISING>; /* Timer 3 */
+	syscon = <&syscon>;
+};
diff --git a/Documentation/devicetree/bindings/timer/renesas,ostm.txt b/Documentation/devicetree/bindings/timer/renesas,ostm.txt
new file mode 100644
index 000000000000..be3ae0fdf775
--- /dev/null
+++ b/Documentation/devicetree/bindings/timer/renesas,ostm.txt
@@ -0,0 +1,30 @@
+* Renesas OS Timer (OSTM)
+
+The OSTM is a multi-channel 32-bit timer/counter with fixed clock
+source that can operate in either interval count down timer or free-running
+compare match mode.
+
+Channels are independent from each other.
+
+Required Properties:
+
+  - compatible: must be one or more of the following:
+    - "renesas,r7s72100-ostm" for the r7s72100 OSTM
+    - "renesas,ostm" for any OSTM
+		This is a fallback for the above renesas,*-ostm entries
+
+  - reg: base address and length of the register block for a timer channel.
+
+  - interrupts: interrupt specifier for the timer channel.
+
+  - clocks: clock specifier for the timer channel.
+
+Example: R7S72100 (RZ/A1H) OSTM node
+
+	ostm0: timer@fcfec000 {
+		compatible = "renesas,r7s72100-ostm", "renesas,ostm";
+		reg = <0xfcfec000 0x30>;
+		interrupts = <GIC_SPI 102 IRQ_TYPE_EDGE_RISING>;
+		clocks = <&mstp5_clks R7S72100_CLK_OSTM0>;
+		power-domains = <&cpg_clocks>;
+	};
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index ca9d1eb46bc0..bf34d5b3a733 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -306,6 +306,11 @@ IRQ
   devm_request_any_context_irq()
   devm_request_irq()
   devm_request_threaded_irq()
+  devm_irq_alloc_descs()
+  devm_irq_alloc_desc()
+  devm_irq_alloc_desc_at()
+  devm_irq_alloc_desc_from()
+  devm_irq_alloc_descs_from()
 
 LED
   devm_led_classdev_register()
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 72624a16b792..c94b4675d021 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -212,10 +212,11 @@ asynchronous manner and the value may not be very precise. To see a precise
 snapshot of a moment, you can see /proc/<pid>/smaps file and scan page table.
 It's slow but very precise.
 
-Table 1-2: Contents of the status files (as of 4.1)
+Table 1-2: Contents of the status files (as of 4.8)
 ..............................................................................
  Field                       Content
  Name                        filename of the executable
+ Umask                       file mode creation mask
  State                       state (R is running, S is sleeping, D is sleeping
                              in an uninterruptible wait, Z is zombie,
 			     T is traced or stopped)
@@ -226,7 +227,6 @@ Table 1-2: Contents of the status files (as of 4.1)
  TracerPid                   PID of process tracing this process (0 if not)
  Uid                         Real, effective, saved set, and  file system UIDs
  Gid                         Real, effective, saved set, and  file system GIDs
- Umask                       file mode creation mask
  FDSize                      number of file descriptor slots currently allocated
  Groups                      supplementary group list
  NStgid                      descendant namespace thread group ID hierarchy
@@ -236,6 +236,7 @@ Table 1-2: Contents of the status files (as of 4.1)
  VmPeak                      peak virtual memory size
  VmSize                      total program size
  VmLck                       locked memory size
+ VmPin                       pinned memory size
  VmHWM                       peak resident set size ("high water mark")
  VmRSS                       size of memory portions. It contains the three
                              following parts (VmRSS = RssAnon + RssFile + RssShmem)
diff --git a/Documentation/hwmon/hwmon-kernel-api.txt b/Documentation/hwmon/hwmon-kernel-api.txt
index 2505ae67e2b6..53a806696c64 100644
--- a/Documentation/hwmon/hwmon-kernel-api.txt
+++ b/Documentation/hwmon/hwmon-kernel-api.txt
@@ -89,6 +89,10 @@ the call to devm_hwmon_device_register_with_groups or
 hwmon_device_register_with_info and if the automatic (device managed)
 removal would be too late.
 
+All supported hwmon device registration functions only accept valid device
+names. Device names including invalid characters (whitespace, '*', or '-')
+will be rejected. The 'name' parameter is mandatory.
+
 Using devm_hwmon_device_register_with_info()
 --------------------------------------------
 
diff --git a/Documentation/hwmon/lm70 b/Documentation/hwmon/lm70
index 1bb2db440671..c3a1f2ea017d 100644
--- a/Documentation/hwmon/lm70
+++ b/Documentation/hwmon/lm70
@@ -6,6 +6,8 @@ Supported chips:
     Datasheet: http://www.national.com/pf/LM/LM70.html
   * Texas Instruments TMP121/TMP123
     Information: http://focus.ti.com/docs/prod/folders/print/tmp121.html
+  * Texas Instruments TMP122/TMP124
+    Information: http://www.ti.com/product/tmp122
   * National Semiconductor LM71
     Datasheet: http://www.ti.com/product/LM71
   * National Semiconductor LM74
@@ -35,8 +37,10 @@ As a real (in-tree) example of this "SPI protocol driver" interfacing
 with a "SPI master controller driver", see drivers/spi/spi_lm70llp.c
 and its associated documentation.
 
-The LM74 and TMP121/TMP123 are very similar; main difference is 13-bit
-temperature data (0.0625 degrees celsius resolution).
+The LM74 and TMP121/TMP122/TMP123/TMP124 are very similar; main difference is
+13-bit temperature data (0.0625 degrees celsius resolution).
+
+The TMP122/TMP124 also feature configurable temperature thresholds.
 
 The LM71 is also very similar; main difference is 14-bit temperature
 data (0.03125 degrees celsius resolution).
diff --git a/Documentation/hwmon/sht21 b/Documentation/hwmon/sht21
index db17fda45c3e..47f4765db256 100644
--- a/Documentation/hwmon/sht21
+++ b/Documentation/hwmon/sht21
@@ -35,6 +35,7 @@ sysfs-Interface
 
 temp1_input - temperature input
 humidity1_input - humidity input
+eic - Electronic Identification Code
 
 Notes
 -----
@@ -45,5 +46,5 @@ humidity and 66 ms for temperature. To keep self heating below 0.1 degree
 Celsius, the device should not be active for more than 10% of the time,
 e.g. maximum two measurements per second at the given resolution.
 
-Different resolutions, the on-chip heater, using the CRC checksum and reading
-the serial number are not supported yet.
+Different resolutions, the on-chip heater, and using the CRC checksum
+are not supported yet.
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index 2cc95ad46604..fc337c317c67 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -86,8 +86,9 @@ given driver if the chip has the feature.
 
 name		The chip name.
 		This should be a short, lowercase string, not containing
-		spaces nor dashes, representing the chip name. This is
-		the only mandatory attribute.
+		whitespace, dashes, or the wildcard character '*'.
+		This attribute represents the chip name. It is the only
+		mandatory attribute.
 		I2C devices get this attribute created automatically.
 		RO
 
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index f1f7ec9f5cc5..836cb16d6f09 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -65,6 +65,21 @@ LED subsystem core exposes following API for setting brightness:
 		blinking, returns -EBUSY if software blink fallback is enabled.
 
 
+LED registration API
+====================
+
+A driver wanting to register a LED classdev for use by other drivers /
+userspace needs to allocate and fill a led_classdev struct and then call
+[devm_]led_classdev_register. If the non devm version is used the driver
+must call led_classdev_unregister from its remove function before
+free-ing the led_classdev struct.
+
+If the driver can detect hardware initiated brightness changes and thus
+wants to have a brightness_hw_changed attribute then the LED_BRIGHT_HW_CHANGED
+flag must be set in flags before registering. Calling
+led_classdev_notify_brightness_hw_changed on a classdev not registered with
+the LED_BRIGHT_HW_CHANGED flag is a bug and will trigger a WARN_ON.
+
 Hardware accelerated blink of LEDs
 ==================================
 
diff --git a/Documentation/livepatch/livepatch.txt b/Documentation/livepatch/livepatch.txt
index f5967316deb9..7f04e13ec53d 100644
--- a/Documentation/livepatch/livepatch.txt
+++ b/Documentation/livepatch/livepatch.txt
@@ -329,25 +329,6 @@ The current Livepatch implementation has several limitations:
     by "notrace".
 
 
-  + Anything inlined into __schedule() can not be patched.
-
-    The switch_to macro is inlined into __schedule(). It switches the
-    context between two processes in the middle of the macro. It does
-    not save RIP in x86_64 version (contrary to 32-bit version). Instead,
-    the currently used __schedule()/switch_to() handles both processes.
-
-    Now, let's have two different tasks. One calls the original
-    __schedule(), its registers are stored in a defined order and it
-    goes to sleep in the switch_to macro and some other task is restored
-    using the original __schedule(). Then there is the second task which
-    calls patched__schedule(), it goes to sleep there and the first task
-    is picked by the patched__schedule(). Its RSP is restored and now
-    the registers should be restored as well. But the order is different
-    in the new patched__schedule(), so...
-
-    There is work in progress to remove this limitation.
-
-
   + Livepatch modules can not be removed.
 
     The current implementation just redirects the functions at the very
diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt
index 8a112dc304c3..34c3a1b50b9a 100644
--- a/Documentation/locking/ww-mutex-design.txt
+++ b/Documentation/locking/ww-mutex-design.txt
@@ -309,11 +309,15 @@ Design:
   normal mutex locks, which are far more common. As such there is only a small
   increase in code size if wait/wound mutexes are not used.
 
+  We maintain the following invariants for the wait list:
+  (1) Waiters with an acquire context are sorted by stamp order; waiters
+      without an acquire context are interspersed in FIFO order.
+  (2) Among waiters with contexts, only the first one can have other locks
+      acquired already (ctx->acquired > 0). Note that this waiter may come
+      after other waiters without contexts in the list.
+
   In general, not much contention is expected. The locks are typically used to
-  serialize access to resources for devices. The only way to make wakeups
-  smarter would be at the cost of adding a field to struct mutex_waiter. This
-  would add overhead to all cases where normal mutexes are used, and
-  ww_mutexes are generally less performance sensitive.
+  serialize access to resources for devices.
 
 Lockdep:
   Special care has been taken to warn for as many cases of api abuse
diff --git a/Documentation/media/uapi/cec/cec-func-close.rst b/Documentation/media/uapi/cec/cec-func-close.rst
index 8267c31b317d..895d9c2d1c04 100644
--- a/Documentation/media/uapi/cec/cec-func-close.rst
+++ b/Documentation/media/uapi/cec/cec-func-close.rst
@@ -33,11 +33,6 @@ Arguments
 Description
 ===========
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 Closes the cec device. Resources associated with the file descriptor are
 freed. The device configuration remain unchanged.
 
diff --git a/Documentation/media/uapi/cec/cec-func-ioctl.rst b/Documentation/media/uapi/cec/cec-func-ioctl.rst
index 9e8dbb118d6a..7dcfd178fb24 100644
--- a/Documentation/media/uapi/cec/cec-func-ioctl.rst
+++ b/Documentation/media/uapi/cec/cec-func-ioctl.rst
@@ -39,11 +39,6 @@ Arguments
 Description
 ===========
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 The :c:func:`ioctl()` function manipulates cec device parameters. The
 argument ``fd`` must be an open file descriptor.
 
diff --git a/Documentation/media/uapi/cec/cec-func-open.rst b/Documentation/media/uapi/cec/cec-func-open.rst
index af3f5b5c24c6..0304388cd159 100644
--- a/Documentation/media/uapi/cec/cec-func-open.rst
+++ b/Documentation/media/uapi/cec/cec-func-open.rst
@@ -46,11 +46,6 @@ Arguments
 Description
 ===========
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 To open a cec device applications call :c:func:`open()` with the
 desired device name. The function has no side effects; the device
 configuration remain unchanged.
diff --git a/Documentation/media/uapi/cec/cec-func-poll.rst b/Documentation/media/uapi/cec/cec-func-poll.rst
index cfb73e6027a5..6a863cfda6e0 100644
--- a/Documentation/media/uapi/cec/cec-func-poll.rst
+++ b/Documentation/media/uapi/cec/cec-func-poll.rst
@@ -39,11 +39,6 @@ Arguments
 Description
 ===========
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 With the :c:func:`poll()` function applications can wait for CEC
 events.
 
diff --git a/Documentation/media/uapi/cec/cec-intro.rst b/Documentation/media/uapi/cec/cec-intro.rst
index 4a19ea5323a9..07ee2b8f89d6 100644
--- a/Documentation/media/uapi/cec/cec-intro.rst
+++ b/Documentation/media/uapi/cec/cec-intro.rst
@@ -3,11 +3,6 @@
 Introduction
 ============
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 HDMI connectors provide a single pin for use by the Consumer Electronics
 Control protocol. This protocol allows different devices connected by an
 HDMI cable to communicate. The protocol for CEC version 1.4 is defined
@@ -31,3 +26,15 @@ control just the CEC pin.
 Drivers that support CEC will create a CEC device node (/dev/cecX) to
 give userspace access to the CEC adapter. The
 :ref:`CEC_ADAP_G_CAPS` ioctl will tell userspace what it is allowed to do.
+
+In order to check the support and test it, it is suggested to download
+the `v4l-utils <https://git.linuxtv.org/v4l-utils.git/>`_ package. It
+provides three tools to handle CEC:
+
+- cec-ctl: the Swiss army knife of CEC. Allows you to configure, transmit
+  and monitor CEC messages.
+
+- cec-compliance: does a CEC compliance test of a remote CEC device to
+  determine how compliant the CEC implementation is.
+
+- cec-follower: emulates a CEC follower.
diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst
index 2b0ddb14b280..a0e961f11017 100644
--- a/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-caps.rst
@@ -29,11 +29,6 @@ Arguments
 Description
 ===========
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 All cec devices must support :ref:`ioctl CEC_ADAP_G_CAPS <CEC_ADAP_G_CAPS>`. To query
 device information, applications call the ioctl with a pointer to a
 struct :c:type:`cec_caps`. The driver fills the structure and
diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst
index b878637e91b3..09f09bbe28d4 100644
--- a/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-log-addrs.rst
@@ -35,11 +35,6 @@ Arguments
 Description
 ===========
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 To query the current CEC logical addresses, applications call
 :ref:`ioctl CEC_ADAP_G_LOG_ADDRS <CEC_ADAP_G_LOG_ADDRS>` with a pointer to a
 struct :c:type:`cec_log_addrs` where the driver stores the logical addresses.
diff --git a/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst b/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst
index 3357deb43c85..a3cdc75cec3e 100644
--- a/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-adap-g-phys-addr.rst
@@ -35,11 +35,6 @@ Arguments
 Description
 ===========
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 To query the current physical address applications call
 :ref:`ioctl CEC_ADAP_G_PHYS_ADDR <CEC_ADAP_G_PHYS_ADDR>` with a pointer to a __u16 where the
 driver stores the physical address.
diff --git a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
index e256c6605de7..6e589a1fae17 100644
--- a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
@@ -30,11 +30,6 @@ Arguments
 Description
 ===========
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 CEC devices can send asynchronous events. These can be retrieved by
 calling :c:func:`CEC_DQEVENT`. If the file descriptor is in
 non-blocking mode and no event is pending, then it will return -1 and
diff --git a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst
index 4f5818b9d277..e4ded9df0a84 100644
--- a/Documentation/media/uapi/cec/cec-ioc-g-mode.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-g-mode.rst
@@ -31,11 +31,6 @@ Arguments
 Description
 ===========
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 By default any filehandle can use :ref:`CEC_TRANSMIT`, but in order to prevent
 applications from stepping on each others toes it must be possible to
 obtain exclusive access to the CEC adapter. This ioctl sets the
diff --git a/Documentation/media/uapi/cec/cec-ioc-receive.rst b/Documentation/media/uapi/cec/cec-ioc-receive.rst
index bdf015b1d1dc..dc2adb391c0a 100644
--- a/Documentation/media/uapi/cec/cec-ioc-receive.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-receive.rst
@@ -34,11 +34,6 @@ Arguments
 Description
 ===========
 
-.. note::
-
-   This documents the proposed CEC API. This API is not yet finalized
-   and is currently only available as a staging kernel module.
-
 To receive a CEC message the application has to fill in the
 ``timeout`` field of struct :c:type:`cec_msg` and pass it to
 :ref:`ioctl CEC_RECEIVE <CEC_RECEIVE>`.
diff --git a/Documentation/media/uapi/v4l/pixfmt-007.rst b/Documentation/media/uapi/v4l/pixfmt-007.rst
index 44bb5a7059b3..95a23a28c595 100644
--- a/Documentation/media/uapi/v4l/pixfmt-007.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-007.rst
@@ -211,7 +211,13 @@ Colorspace sRGB (V4L2_COLORSPACE_SRGB)
 The :ref:`srgb` standard defines the colorspace used by most webcams
 and computer graphics. The default transfer function is
 ``V4L2_XFER_FUNC_SRGB``. The default Y'CbCr encoding is
-``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is full range.
+``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is limited range.
+
+Note that the :ref:`sycc` standard specifies full range quantization,
+however all current capture hardware supported by the kernel convert
+R'G'B' to limited range Y'CbCr. So choosing full range as the default
+would break how applications interpret the quantization range.
+
 The chromaticities of the primary colors and the white reference are:
 
 
@@ -276,7 +282,7 @@ the following ``V4L2_YCBCR_ENC_601`` encoding as defined by :ref:`sycc`:
 
 Y' is clamped to the range [0…1] and Cb and Cr are clamped to the range
 [-0.5…0.5]. This transform is identical to one defined in SMPTE
-170M/BT.601. The Y'CbCr quantization is full range.
+170M/BT.601. The Y'CbCr quantization is limited range.
 
 
 .. _col-adobergb:
@@ -288,10 +294,15 @@ The :ref:`adobergb` standard defines the colorspace used by computer
 graphics that use the AdobeRGB colorspace. This is also known as the
 :ref:`oprgb` standard. The default transfer function is
 ``V4L2_XFER_FUNC_ADOBERGB``. The default Y'CbCr encoding is
-``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is full
-range. The chromaticities of the primary colors and the white reference
-are:
+``V4L2_YCBCR_ENC_601``. The default Y'CbCr quantization is limited
+range.
+
+Note that the :ref:`oprgb` standard specifies full range quantization,
+however all current capture hardware supported by the kernel convert
+R'G'B' to limited range Y'CbCr. So choosing full range as the default
+would break how applications interpret the quantization range.
 
+The chromaticities of the primary colors and the white reference are:
 
 
 .. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.7cm}|
@@ -344,7 +355,7 @@ the following ``V4L2_YCBCR_ENC_601`` encoding:
 
 Y' is clamped to the range [0…1] and Cb and Cr are clamped to the range
 [-0.5…0.5]. This transform is identical to one defined in SMPTE
-170M/BT.601. The Y'CbCr quantization is full range.
+170M/BT.601. The Y'CbCr quantization is limited range.
 
 
 .. _col-bt2020:
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index ba818ecce6f9..d2b0a8d81258 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -640,6 +640,10 @@ See also the subsection on "Cache Coherency" for a more thorough example.
 CONTROL DEPENDENCIES
 --------------------
 
+Control dependencies can be a bit tricky because current compilers do
+not understand them.  The purpose of this section is to help you prevent
+the compiler's ignorance from breaking your code.
+
 A load-load control dependency requires a full read memory barrier, not
 simply a data dependency barrier to make it work correctly.  Consider the
 following bit of code:
@@ -667,14 +671,15 @@ for load-store control dependencies, as in the following example:
 
 	q = READ_ONCE(a);
 	if (q) {
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 	}
 
-Control dependencies pair normally with other types of barriers.  That
-said, please note that READ_ONCE() is not optional! Without the
-READ_ONCE(), the compiler might combine the load from 'a' with other
-loads from 'a', and the store to 'b' with other stores to 'b', with
-possible highly counterintuitive effects on ordering.
+Control dependencies pair normally with other types of barriers.
+That said, please note that neither READ_ONCE() nor WRITE_ONCE()
+are optional! Without the READ_ONCE(), the compiler might combine the
+load from 'a' with other loads from 'a'.  Without the WRITE_ONCE(),
+the compiler might combine the store to 'b' with other stores to 'b'.
+Either can result in highly counterintuitive effects on ordering.
 
 Worse yet, if the compiler is able to prove (say) that the value of
 variable 'a' is always non-zero, it would be well within its rights
@@ -682,7 +687,7 @@ to optimize the original example by eliminating the "if" statement
 as follows:
 
 	q = a;
-	b = p;  /* BUG: Compiler and CPU can both reorder!!! */
+	b = 1;  /* BUG: Compiler and CPU can both reorder!!! */
 
 So don't leave out the READ_ONCE().
 
@@ -692,11 +697,11 @@ branches of the "if" statement as follows:
 	q = READ_ONCE(a);
 	if (q) {
 		barrier();
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 		do_something();
 	} else {
 		barrier();
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 		do_something_else();
 	}
 
@@ -705,12 +710,12 @@ optimization levels:
 
 	q = READ_ONCE(a);
 	barrier();
-	WRITE_ONCE(b, p);  /* BUG: No ordering vs. load from a!!! */
+	WRITE_ONCE(b, 1);  /* BUG: No ordering vs. load from a!!! */
 	if (q) {
-		/* WRITE_ONCE(b, p); -- moved up, BUG!!! */
+		/* WRITE_ONCE(b, 1); -- moved up, BUG!!! */
 		do_something();
 	} else {
-		/* WRITE_ONCE(b, p); -- moved up, BUG!!! */
+		/* WRITE_ONCE(b, 1); -- moved up, BUG!!! */
 		do_something_else();
 	}
 
@@ -723,10 +728,10 @@ memory barriers, for example, smp_store_release():
 
 	q = READ_ONCE(a);
 	if (q) {
-		smp_store_release(&b, p);
+		smp_store_release(&b, 1);
 		do_something();
 	} else {
-		smp_store_release(&b, p);
+		smp_store_release(&b, 1);
 		do_something_else();
 	}
 
@@ -735,10 +740,10 @@ ordering is guaranteed only when the stores differ, for example:
 
 	q = READ_ONCE(a);
 	if (q) {
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 		do_something();
 	} else {
-		WRITE_ONCE(b, r);
+		WRITE_ONCE(b, 2);
 		do_something_else();
 	}
 
@@ -751,10 +756,10 @@ the needed conditional.  For example:
 
 	q = READ_ONCE(a);
 	if (q % MAX) {
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 		do_something();
 	} else {
-		WRITE_ONCE(b, r);
+		WRITE_ONCE(b, 2);
 		do_something_else();
 	}
 
@@ -763,7 +768,7 @@ equal to zero, in which case the compiler is within its rights to
 transform the above code into the following:
 
 	q = READ_ONCE(a);
-	WRITE_ONCE(b, p);
+	WRITE_ONCE(b, 1);
 	do_something_else();
 
 Given this transformation, the CPU is not required to respect the ordering
@@ -776,10 +781,10 @@ one, perhaps as follows:
 	q = READ_ONCE(a);
 	BUILD_BUG_ON(MAX <= 1); /* Order load from a with store to b. */
 	if (q % MAX) {
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 		do_something();
 	} else {
-		WRITE_ONCE(b, r);
+		WRITE_ONCE(b, 2);
 		do_something_else();
 	}
 
@@ -812,30 +817,28 @@ not necessarily apply to code following the if-statement:
 
 	q = READ_ONCE(a);
 	if (q) {
-		WRITE_ONCE(b, p);
+		WRITE_ONCE(b, 1);
 	} else {
-		WRITE_ONCE(b, r);
+		WRITE_ONCE(b, 2);
 	}
-	WRITE_ONCE(c, 1);  /* BUG: No ordering against the read from "a". */
+	WRITE_ONCE(c, 1);  /* BUG: No ordering against the read from 'a'. */
 
 It is tempting to argue that there in fact is ordering because the
 compiler cannot reorder volatile accesses and also cannot reorder
-the writes to "b" with the condition.  Unfortunately for this line
-of reasoning, the compiler might compile the two writes to "b" as
+the writes to 'b' with the condition.  Unfortunately for this line
+of reasoning, the compiler might compile the two writes to 'b' as
 conditional-move instructions, as in this fanciful pseudo-assembly
 language:
 
 	ld r1,a
-	ld r2,p
-	ld r3,r
 	cmp r1,$0
-	cmov,ne r4,r2
-	cmov,eq r4,r3
+	cmov,ne r4,$1
+	cmov,eq r4,$2
 	st r4,b
 	st $1,c
 
 A weakly ordered CPU would have no dependency of any sort between the load
-from "a" and the store to "c".  The control dependencies would extend
+from 'a' and the store to 'c'.  The control dependencies would extend
 only to the pair of cmov instructions and the store depending on them.
 In short, control dependencies apply only to the stores in the then-clause
 and else-clause of the if-statement in question (including functions
@@ -843,7 +846,7 @@ invoked by those two clauses), not to code following that if-statement.
 
 Finally, control dependencies do -not- provide transitivity.  This is
 demonstrated by two related examples, with the initial values of
-x and y both being zero:
+'x' and 'y' both being zero:
 
 	CPU 0                     CPU 1
 	=======================   =======================
@@ -915,6 +918,9 @@ In summary:
   (*) Control dependencies do -not- provide transitivity.  If you
       need transitivity, use smp_mb().
 
+  (*) Compilers do not understand control dependencies.  It is therefore
+      your job to ensure that they do not break your code.
+
 
 SMP BARRIER PAIRING
 -------------------
diff --git a/Documentation/mtd/intel-spi.txt b/Documentation/mtd/intel-spi.txt
new file mode 100644
index 000000000000..bc357729c2cb
--- /dev/null
+++ b/Documentation/mtd/intel-spi.txt
@@ -0,0 +1,88 @@
+Upgrading BIOS using intel-spi
+------------------------------
+
+Many Intel CPUs like Baytrail and Braswell include SPI serial flash host
+controller which is used to hold BIOS and other platform specific data.
+Since contents of the SPI serial flash is crucial for machine to function,
+it is typically protected by different hardware protection mechanisms to
+avoid accidental (or on purpose) overwrite of the content.
+
+Not all manufacturers protect the SPI serial flash, mainly because it
+allows upgrading the BIOS image directly from an OS.
+
+The intel-spi driver makes it possible to read and write the SPI serial
+flash, if certain protection bits are not set and locked. If it finds
+any of them set, the whole MTD device is made read-only to prevent
+partial overwrites. By default the driver exposes SPI serial flash
+contents as read-only but it can be changed from kernel command line,
+passing "intel-spi.writeable=1".
+
+Please keep in mind that overwriting the BIOS image on SPI serial flash
+might render the machine unbootable and requires special equipment like
+Dediprog to revive. You have been warned!
+
+Below are the steps how to upgrade MinnowBoard MAX BIOS directly from
+Linux.
+
+ 1) Download and extract the latest Minnowboard MAX BIOS SPI image
+    [1]. At the time writing this the latest image is v92.
+
+ 2) Install mtd-utils package [2]. We need this in order to erase the SPI
+    serial flash. Distros like Debian and Fedora have this prepackaged with
+    name "mtd-utils".
+
+ 3) Add "intel-spi.writeable=1" to the kernel command line and reboot
+    the board (you can also reload the driver passing "writeable=1" as
+    module parameter to modprobe).
+
+ 4) Once the board is up and running again, find the right MTD partition
+    (it is named as "BIOS"):
+
+    # cat /proc/mtd
+    dev:    size   erasesize  name
+    mtd0: 00800000 00001000 "BIOS"
+
+    So here it will be /dev/mtd0 but it may vary.
+
+ 5) Make backup of the existing image first:
+
+    # dd if=/dev/mtd0ro of=bios.bak
+    16384+0 records in
+    16384+0 records out
+    8388608 bytes (8.4 MB) copied, 10.0269 s, 837 kB/s
+
+ 6) Verify the backup
+
+    # sha1sum /dev/mtd0ro bios.bak
+    fdbb011920572ca6c991377c4b418a0502668b73  /dev/mtd0ro
+    fdbb011920572ca6c991377c4b418a0502668b73  bios.bak
+
+    The SHA1 sums must match. Otherwise do not continue any further!
+
+ 7) Erase the SPI serial flash. After this step, do not reboot the
+    board! Otherwise it will not start anymore.
+
+    # flash_erase /dev/mtd0 0 0
+    Erasing 4 Kibyte @ 7ff000 -- 100 % complete
+
+ 8) Once completed without errors you can write the new BIOS image:
+
+    # dd if=MNW2MAX1.X64.0092.R01.1605221712.bin of=/dev/mtd0
+
+ 9) Verify that the new content of the SPI serial flash matches the new
+    BIOS image:
+
+    # sha1sum /dev/mtd0ro MNW2MAX1.X64.0092.R01.1605221712.bin
+    9b4df9e4be2057fceec3a5529ec3d950836c87a2  /dev/mtd0ro
+    9b4df9e4be2057fceec3a5529ec3d950836c87a2 MNW2MAX1.X64.0092.R01.1605221712.bin
+
+    The SHA1 sums should match.
+
+ 10) Now you can reboot your board and observe the new BIOS starting up
+     properly.
+
+References
+----------
+
+[1] https://firmware.intel.com/sites/default/files/MinnowBoard.MAX_.X64.92.R01.zip
+[2] http://www.linux-mtd.infradead.org/
diff --git a/Documentation/power/opp.txt b/Documentation/power/opp.txt
index c6279c2be47c..0c007e250cd1 100644
--- a/Documentation/power/opp.txt
+++ b/Documentation/power/opp.txt
@@ -79,22 +79,6 @@ dependent subsystems such as cpufreq are left to the discretion of the SoC
 specific framework which uses the OPP library. Similar care needs to be taken
 care to refresh the cpufreq table in cases of these operations.
 
-WARNING on OPP List locking mechanism:
--------------------------------------------------
-OPP library uses RCU for exclusivity. RCU allows the query functions to operate
-in multiple contexts and this synchronization mechanism is optimal for a read
-intensive operations on data structure as the OPP library caters to.
-
-To ensure that the data retrieved are sane, the users such as SoC framework
-should ensure that the section of code operating on OPP queries are locked
-using RCU read locks. The opp_find_freq_{exact,ceil,floor},
-opp_get_{voltage, freq, opp_count} fall into this category.
-
-opp_{add,enable,disable} are updaters which use mutex and implement it's own
-RCU locking mechanisms. These functions should *NOT* be called under RCU locks
-and other contexts that prevent blocking functions in RCU or mutex operations
-from working.
-
 2. Initial OPP List Registration
 ================================
 The SoC implementation calls dev_pm_opp_add function iteratively to add OPPs per
@@ -137,15 +121,18 @@ functions return the matching pointer representing the opp if a match is
 found, else returns error. These errors are expected to be handled by standard
 error checks such as IS_ERR() and appropriate actions taken by the caller.
 
+Callers of these functions shall call dev_pm_opp_put() after they have used the
+OPP. Otherwise the memory for the OPP will never get freed and result in
+memleak.
+
 dev_pm_opp_find_freq_exact - Search for an OPP based on an *exact* frequency and
 	availability. This function is especially useful to enable an OPP which
 	is not available by default.
 	Example: In a case when SoC framework detects a situation where a
 	higher frequency could be made available, it can use this function to
 	find the OPP prior to call the dev_pm_opp_enable to actually make it available.
-	 rcu_read_lock();
 	 opp = dev_pm_opp_find_freq_exact(dev, 1000000000, false);
-	 rcu_read_unlock();
+	 dev_pm_opp_put(opp);
 	 /* dont operate on the pointer.. just do a sanity check.. */
 	 if (IS_ERR(opp)) {
 		pr_err("frequency not disabled!\n");
@@ -163,9 +150,8 @@ dev_pm_opp_find_freq_floor - Search for an available OPP which is *at most* the
 	frequency.
 	Example: To find the highest opp for a device:
 	 freq = ULONG_MAX;
-	 rcu_read_lock();
-	 dev_pm_opp_find_freq_floor(dev, &freq);
-	 rcu_read_unlock();
+	 opp = dev_pm_opp_find_freq_floor(dev, &freq);
+	 dev_pm_opp_put(opp);
 
 dev_pm_opp_find_freq_ceil - Search for an available OPP which is *at least* the
 	provided frequency. This function is useful while searching for a
@@ -173,17 +159,15 @@ dev_pm_opp_find_freq_ceil - Search for an available OPP which is *at least* the
 	frequency.
 	Example 1: To find the lowest opp for a device:
 	 freq = 0;
-	 rcu_read_lock();
-	 dev_pm_opp_find_freq_ceil(dev, &freq);
-	 rcu_read_unlock();
+	 opp = dev_pm_opp_find_freq_ceil(dev, &freq);
+	 dev_pm_opp_put(opp);
 	Example 2: A simplified implementation of a SoC cpufreq_driver->target:
 	 soc_cpufreq_target(..)
 	 {
 		/* Do stuff like policy checks etc. */
 		/* Find the best frequency match for the req */
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		if (!IS_ERR(opp))
 			soc_switch_to_freq_voltage(freq);
 		else
@@ -208,9 +192,8 @@ dev_pm_opp_enable - Make a OPP available for operation.
 	implementation might choose to do something as follows:
 	 if (cur_temp < temp_low_thresh) {
 		/* Enable 1GHz if it was disabled */
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_exact(dev, 1000000000, false);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		/* just error check */
 		if (!IS_ERR(opp))
 			ret = dev_pm_opp_enable(dev, 1000000000);
@@ -224,9 +207,8 @@ dev_pm_opp_disable - Make an OPP to be not available for operation
 	choose to do something as follows:
 	 if (cur_temp > temp_high_thresh) {
 		/* Disable 1GHz if it was enabled */
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_exact(dev, 1000000000, true);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		/* just error check */
 		if (!IS_ERR(opp))
 			ret = dev_pm_opp_disable(dev, 1000000000);
@@ -249,10 +231,9 @@ dev_pm_opp_get_voltage - Retrieve the voltage represented by the opp pointer.
 	 soc_switch_to_freq_voltage(freq)
 	 {
 		/* do things */
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
 		v = dev_pm_opp_get_voltage(opp);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		if (v)
 			regulator_set_voltage(.., v);
 		/* do other things */
@@ -266,12 +247,12 @@ dev_pm_opp_get_freq - Retrieve the freq represented by the opp pointer.
 	 {
 		/* do things.. */
 		 max_freq = ULONG_MAX;
-		 rcu_read_lock();
 		 max_opp = dev_pm_opp_find_freq_floor(dev,&max_freq);
 		 requested_opp = dev_pm_opp_find_freq_ceil(dev,&freq);
 		 if (!IS_ERR(max_opp) && !IS_ERR(requested_opp))
 			r = soc_test_validity(max_opp, requested_opp);
-		 rcu_read_unlock();
+		 dev_pm_opp_put(max_opp);
+		 dev_pm_opp_put(requested_opp);
 		/* do other things */
 	 }
 	 soc_test_validity(..)
@@ -289,7 +270,6 @@ dev_pm_opp_get_opp_count - Retrieve the number of available opps for a device
 	 soc_notify_coproc_available_frequencies()
 	 {
 		/* Do things */
-		rcu_read_lock();
 		num_available = dev_pm_opp_get_opp_count(dev);
 		speeds = kzalloc(sizeof(u32) * num_available, GFP_KERNEL);
 		/* populate the table in increasing order */
@@ -298,8 +278,8 @@ dev_pm_opp_get_opp_count - Retrieve the number of available opps for a device
 			speeds[i] = freq;
 			freq++;
 			i++;
+			dev_pm_opp_put(opp);
 		}
-		rcu_read_unlock();
 
 		soc_notify_coproc(AVAILABLE_FREQs, speeds, num_available);
 		/* Do other things */
diff --git a/Documentation/power/states.txt b/Documentation/power/states.txt
index 8a39ce45d8a0..bc4548245a24 100644
--- a/Documentation/power/states.txt
+++ b/Documentation/power/states.txt
@@ -25,7 +25,7 @@ to be used subsequently to change to the one represented by that string.
 Consequently, there are two ways to cause the system to go into the
 Suspend-To-Idle sleep state.  The first one is to write "freeze" directly to
 /sys/power/state.  The second one is to write "s2idle" to /sys/power/mem_sleep
-and then to wrtie "mem" to /sys/power/state.  Similarly, there are two ways
+and then to write "mem" to /sys/power/state.  Similarly, there are two ways
 to cause the system to go into the Power-On Suspend sleep state (the strings to
 write to the control files in that case are "standby" or "shallow" and "mem",
 respectively) if that state is supported by the platform.  In turn, there is
@@ -35,9 +35,7 @@ only one way to cause the system to go into the Suspend-To-RAM state (write
 The default suspend mode (ie. the one to be used without writing anything into
 /sys/power/mem_sleep) is either "deep" (if Suspend-To-RAM is supported) or
 "s2idle", but it can be overridden by the value of the "mem_sleep_default"
-parameter in the kernel command line.  On some ACPI-based systems, depending on
-the information in the FADT, the default may be "s2idle" even if Suspend-To-RAM
-is supported.
+parameter in the kernel command line.
 
 The properties of all of the sleep states are described below.
 
diff --git a/Documentation/scheduler/sched-deadline.txt b/Documentation/scheduler/sched-deadline.txt
index 8e37b0ba2c9d..cbc1b46cbf70 100644
--- a/Documentation/scheduler/sched-deadline.txt
+++ b/Documentation/scheduler/sched-deadline.txt
@@ -408,6 +408,11 @@ CONTENTS
   * the new scheduling related syscalls that manipulate it, i.e.,
     sched_setattr() and sched_getattr() are implemented.
 
+ For debugging purposes, the leftover runtime and absolute deadline of a
+ SCHED_DEADLINE task can be retrieved through /proc/<pid>/sched (entries
+ dl.runtime and dl.deadline, both values in ns). A programmatic way to
+ retrieve these values from production code is under discussion.
+
 
 4.3 Default behavior
 ---------------------
@@ -476,6 +481,7 @@ CONTENTS
 
  Still missing:
 
+  - programmatic way to retrieve current runtime and absolute deadline
   - refinements to deadline inheritance, especially regarding the possibility
     of retaining bandwidth isolation among non-interacting tasks. This is
     being studied from both theoretical and practical points of view, and
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index a03f0d944fe6..d8fce3e78457 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -158,11 +158,11 @@ as its prone to starvation without deadline scheduling.
 Consider two sibling groups A and B; both have 50% bandwidth, but A's
 period is twice the length of B's.
 
-* group A: period=100000us, runtime=10000us
-	- this runs for 0.01s once every 0.1s
+* group A: period=100000us, runtime=50000us
+	- this runs for 0.05s once every 0.1s
 
-* group B: period= 50000us, runtime=10000us
-	- this runs for 0.01s twice every 0.1s (or once every 0.05 sec).
+* group B: period= 50000us, runtime=25000us
+	- this runs for 0.025s twice every 0.1s (or once every 0.05 sec).
 
 This means that currently a while (1) loop in A will run for the full period of
 B and can starve B's tasks (assuming they are of lower priority) for a whole
diff --git a/Documentation/spi/ep93xx_spi b/Documentation/spi/ep93xx_spi
deleted file mode 100644
index 832ddce6e5fb..000000000000
--- a/Documentation/spi/ep93xx_spi
+++ /dev/null
@@ -1,105 +0,0 @@
-Cirrus EP93xx SPI controller driver HOWTO
-=========================================
-
-ep93xx_spi driver brings SPI master support for EP93xx SPI controller.  Chip
-selects are implemented with GPIO lines.
-
-NOTE: If possible, don't use SFRMOUT (SFRM1) signal as a chip select. It will
-not work correctly (it cannot be controlled by software). Use GPIO lines
-instead.
-
-Sample configuration
-====================
-
-Typically driver configuration is done in platform board files (the files under
-arch/arm/mach-ep93xx/*.c). In this example we configure MMC over SPI through
-this driver on TS-7260 board. You can adapt the code to suit your needs.
-
-This example uses EGPIO9 as SD/MMC card chip select (this is wired in DIO1
-header on the board).
-
-You need to select CONFIG_MMC_SPI to use mmc_spi driver.
-
-arch/arm/mach-ep93xx/ts72xx.c:
-
-...
-#include <linux/gpio.h>
-#include <linux/spi/spi.h>
-
-#include <linux/platform_data/spi-ep93xx.h>
-
-/* this is our GPIO line used for chip select */
-#define MMC_CHIP_SELECT_GPIO EP93XX_GPIO_LINE_EGPIO9
-
-static int ts72xx_mmc_spi_setup(struct spi_device *spi)
-{
-	int err;
-
-	err = gpio_request(MMC_CHIP_SELECT_GPIO, spi->modalias);
-	if (err)
-		return err;
-
-	gpio_direction_output(MMC_CHIP_SELECT_GPIO, 1);
-
-	return 0;
-}
-
-static void ts72xx_mmc_spi_cleanup(struct spi_device *spi)
-{
-	gpio_set_value(MMC_CHIP_SELECT_GPIO, 1);
-	gpio_direction_input(MMC_CHIP_SELECT_GPIO);
-	gpio_free(MMC_CHIP_SELECT_GPIO);
-}
-
-static void ts72xx_mmc_spi_cs_control(struct spi_device *spi, int value)
-{
-	gpio_set_value(MMC_CHIP_SELECT_GPIO, value);
-}
-
-static struct ep93xx_spi_chip_ops ts72xx_mmc_spi_ops = {
-	.setup		= ts72xx_mmc_spi_setup,
-	.cleanup	= ts72xx_mmc_spi_cleanup,
-	.cs_control	= ts72xx_mmc_spi_cs_control,
-};
-
-static struct spi_board_info ts72xx_spi_devices[] __initdata = {
-	{
-		.modalias		= "mmc_spi",
-		.controller_data	= &ts72xx_mmc_spi_ops,
-		/*
-		 * We use 10 MHz even though the maximum is 7.4 MHz. The driver
-		 * will limit it automatically to max. frequency.
-		 */
-		.max_speed_hz		= 10 * 1000 * 1000,
-		.bus_num		= 0,
-		.chip_select		= 0,
-		.mode			= SPI_MODE_0,
-	},
-};
-
-static struct ep93xx_spi_info ts72xx_spi_info = {
-	.num_chipselect	= ARRAY_SIZE(ts72xx_spi_devices),
-};
-
-static void __init ts72xx_init_machine(void)
-{
-	...
-	ep93xx_register_spi(&ts72xx_spi_info, ts72xx_spi_devices,
-			    ARRAY_SIZE(ts72xx_spi_devices));
-}
-
-The driver can use DMA for the transfers also. In this case ts72xx_spi_info
-becomes:
-
-static struct ep93xx_spi_info ts72xx_spi_info = {
-	.num_chipselect	= ARRAY_SIZE(ts72xx_spi_devices),
-	.use_dma	= true;
-};
-
-Note that CONFIG_EP93XX_DMA should be enabled as well.
-
-Thanks to
-=========
-Martin Guy, H. Hartley Sweeten and others who helped me during development of
-the driver. Simplemachines.it donated me a Sim.One board which I used testing
-the driver on EP9307.
diff --git a/Documentation/timers/timer_stats.txt b/Documentation/timers/timer_stats.txt
deleted file mode 100644
index de835ee97455..000000000000
--- a/Documentation/timers/timer_stats.txt
+++ /dev/null
@@ -1,73 +0,0 @@
-timer_stats - timer usage statistics
-------------------------------------
-
-timer_stats is a debugging facility to make the timer (ab)usage in a Linux
-system visible to kernel and userspace developers. If enabled in the config
-but not used it has almost zero runtime overhead, and a relatively small
-data structure overhead. Even if collection is enabled runtime all the
-locking is per-CPU and lookup is hashed.
-
-timer_stats should be used by kernel and userspace developers to verify that
-their code does not make unduly use of timers. This helps to avoid unnecessary
-wakeups, which should be avoided to optimize power consumption.
-
-It can be enabled by CONFIG_TIMER_STATS in the "Kernel hacking" configuration
-section.
-
-timer_stats collects information about the timer events which are fired in a
-Linux system over a sample period:
-
-- the pid of the task(process) which initialized the timer
-- the name of the process which initialized the timer
-- the function where the timer was initialized
-- the callback function which is associated to the timer
-- the number of events (callbacks)
-
-timer_stats adds an entry to /proc: /proc/timer_stats
-
-This entry is used to control the statistics functionality and to read out the
-sampled information.
-
-The timer_stats functionality is inactive on bootup.
-
-To activate a sample period issue:
-# echo 1 >/proc/timer_stats
-
-To stop a sample period issue:
-# echo 0 >/proc/timer_stats
-
-The statistics can be retrieved by:
-# cat /proc/timer_stats
-
-While sampling is enabled, each readout from /proc/timer_stats will see
-newly updated statistics. Once sampling is disabled, the sampled information
-is kept until a new sample period is started. This allows multiple readouts.
-
-Sample output of /proc/timer_stats:
-
-Timerstats sample period: 3.888770 s
-  12,     0 swapper          hrtimer_stop_sched_tick (hrtimer_sched_tick)
-  15,     1 swapper          hcd_submit_urb (rh_timer_func)
-   4,   959 kedac            schedule_timeout (process_timeout)
-   1,     0 swapper          page_writeback_init (wb_timer_fn)
-  28,     0 swapper          hrtimer_stop_sched_tick (hrtimer_sched_tick)
-  22,  2948 IRQ 4            tty_flip_buffer_push (delayed_work_timer_fn)
-   3,  3100 bash             schedule_timeout (process_timeout)
-   1,     1 swapper          queue_delayed_work_on (delayed_work_timer_fn)
-   1,     1 swapper          queue_delayed_work_on (delayed_work_timer_fn)
-   1,     1 swapper          neigh_table_init_no_netlink (neigh_periodic_timer)
-   1,  2292 ip               __netdev_watchdog_up (dev_watchdog)
-   1,    23 events/1         do_cache_clean (delayed_work_timer_fn)
-90 total events, 30.0 events/sec
-
-The first column is the number of events, the second column the pid, the third
-column is the name of the process. The forth column shows the function which
-initialized the timer and in parenthesis the callback function which was
-executed on expiry.
-
-    Thomas, Ingo
-
-Added flag to indicate 'deferrable timer' in /proc/timer_stats. A deferrable
-timer will appear as follows
-  10D,     1 swapper          queue_delayed_work_on (delayed_work_timer_fn)
-
diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt
index 95a4d34af3fd..b8527c6b7646 100644
--- a/Documentation/x86/zero-page.txt
+++ b/Documentation/x86/zero-page.txt
@@ -31,6 +31,8 @@ Offset	Proto	Name		Meaning
 1E9/001	ALL	eddbuf_entries	Number of entries in eddbuf (below)
 1EA/001	ALL	edd_mbr_sig_buf_entries	Number of entries in edd_mbr_sig_buffer
 				(below)
+1EB/001	ALL     kbd_status      Numlock is enabled
+1EC/001	ALL     secure_boot	Secure boot is enabled in the firmware
 1EF/001	ALL	sentinel	Used to detect broken bootloaders
 290/040	ALL	edd_mbr_sig_buffer EDD MBR signatures
 2D0/A00	ALL	e820_map	E820 memory map table
diff --git a/MAINTAINERS b/MAINTAINERS
index 26edd832c64e..d5dee50d7c69 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -643,7 +643,7 @@ S:	Maintained
 F:	drivers/gpio/gpio-altera.c
 
 ALTERA SYSTEM RESOURCE DRIVER FOR ARRIA10 DEVKIT
-M:	Thor Thayer <tthayer@opensource.altera.com>
+M:	Thor Thayer <thor.thayer@linux.intel.com>
 S:	Maintained
 F:	drivers/gpio/gpio-altera-a10sr.c
 F:	drivers/mfd/altera-a10sr.c
@@ -877,8 +877,8 @@ S:	Odd fixes
 F:	drivers/hwmon/applesmc.c
 
 APPLETALK NETWORK LAYER
-M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
-S:	Maintained
+L:	netdev@vger.kernel.org
+S:	Odd fixes
 F:	drivers/net/appletalk/
 F:	net/appletalk/
 
@@ -1091,7 +1091,7 @@ F:	arch/arm/boot/dts/aspeed-*
 F:	drivers/*/*aspeed*
 
 ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
+M:	Nicolas Ferre <nicolas.ferre@microchip.com>
 M:	Alexandre Belloni <alexandre.belloni@free-electrons.com>
 M:	Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1773,7 +1773,7 @@ F:	drivers/soc/renesas/
 F:	include/linux/soc/renesas/
 
 ARM/SOCFPGA ARCHITECTURE
-M:	Dinh Nguyen <dinguyen@opensource.altera.com>
+M:	Dinh Nguyen <dinguyen@kernel.org>
 S:	Maintained
 F:	arch/arm/mach-socfpga/
 F:	arch/arm/boot/dts/socfpga*
@@ -1783,12 +1783,12 @@ W:	http://www.rocketboards.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dinguyen/linux.git
 
 ARM/SOCFPGA CLOCK FRAMEWORK SUPPORT
-M:	Dinh Nguyen <dinguyen@opensource.altera.com>
+M:	Dinh Nguyen <dinguyen@kernel.org>
 S:	Maintained
 F:	drivers/clk/socfpga/
 
 ARM/SOCFPGA EDAC SUPPORT
-M:	Thor Thayer <tthayer@opensource.altera.com>
+M:	Thor Thayer <thor.thayer@linux.intel.com>
 S:	Maintained
 F:	drivers/edac/altera_edac.
 
@@ -2175,56 +2175,56 @@ F:	include/linux/atm*
 F:	include/uapi/linux/atm*
 
 ATMEL AT91 / AT32 MCI DRIVER
-M:	Ludovic Desroches <ludovic.desroches@atmel.com>
+M:	Ludovic Desroches <ludovic.desroches@microchip.com>
 S:	Maintained
 F:	drivers/mmc/host/atmel-mci.c
 
 ATMEL AT91 SAMA5D2-Compatible Shutdown Controller
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
+M:	Nicolas Ferre <nicolas.ferre@microchip.com>
 S:	Supported
 F:	drivers/power/reset/at91-sama5d2_shdwc.c
 
 ATMEL SAMA5D2 ADC DRIVER
-M:	Ludovic Desroches <ludovic.desroches@atmel.com>
+M:	Ludovic Desroches <ludovic.desroches@microchip.com>
 L:	linux-iio@vger.kernel.org
 S:	Supported
 F:	drivers/iio/adc/at91-sama5d2_adc.c
 
 ATMEL Audio ALSA driver
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
+M:	Nicolas Ferre <nicolas.ferre@microchip.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
 F:	sound/soc/atmel
 
 ATMEL XDMA DRIVER
-M:	Ludovic Desroches <ludovic.desroches@atmel.com>
+M:	Ludovic Desroches <ludovic.desroches@microchip.com>
 L:	linux-arm-kernel@lists.infradead.org
 L:	dmaengine@vger.kernel.org
 S:	Supported
 F:	drivers/dma/at_xdmac.c
 
 ATMEL I2C DRIVER
-M:	Ludovic Desroches <ludovic.desroches@atmel.com>
+M:	Ludovic Desroches <ludovic.desroches@microchip.com>
 L:	linux-i2c@vger.kernel.org
 S:	Supported
 F:	drivers/i2c/busses/i2c-at91.c
 
 ATMEL ISI DRIVER
-M:	Ludovic Desroches <ludovic.desroches@atmel.com>
+M:	Ludovic Desroches <ludovic.desroches@microchip.com>
 L:	linux-media@vger.kernel.org
 S:	Supported
 F:	drivers/media/platform/soc_camera/atmel-isi.c
 F:	include/media/atmel-isi.h
 
 ATMEL LCDFB DRIVER
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
+M:	Nicolas Ferre <nicolas.ferre@microchip.com>
 L:	linux-fbdev@vger.kernel.org
 S:	Maintained
 F:	drivers/video/fbdev/atmel_lcdfb.c
 F:	include/video/atmel_lcdc.h
 
 ATMEL MACB ETHERNET DRIVER
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
+M:	Nicolas Ferre <nicolas.ferre@microchip.com>
 S:	Supported
 F:	drivers/net/ethernet/cadence/
 
@@ -2236,32 +2236,32 @@ S:	Supported
 F:	drivers/mtd/nand/atmel_nand*
 
 ATMEL SDMMC DRIVER
-M:	Ludovic Desroches <ludovic.desroches@atmel.com>
+M:	Ludovic Desroches <ludovic.desroches@microchip.com>
 L:	linux-mmc@vger.kernel.org
 S:	Supported
 F:	drivers/mmc/host/sdhci-of-at91.c
 
 ATMEL SPI DRIVER
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
+M:	Nicolas Ferre <nicolas.ferre@microchip.com>
 S:	Supported
 F:	drivers/spi/spi-atmel.*
 
 ATMEL SSC DRIVER
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
+M:	Nicolas Ferre <nicolas.ferre@microchip.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/misc/atmel-ssc.c
 F:	include/linux/atmel-ssc.h
 
 ATMEL Timer Counter (TC) AND CLOCKSOURCE DRIVERS
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
+M:	Nicolas Ferre <nicolas.ferre@microchip.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/misc/atmel_tclib.c
 F:	drivers/clocksource/tcb_clksrc.c
 
 ATMEL USBA UDC DRIVER
-M:	Nicolas Ferre <nicolas.ferre@atmel.com>
+M:	Nicolas Ferre <nicolas.ferre@microchip.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Supported
 F:	drivers/usb/gadget/udc/atmel_usba_udc.*
@@ -2692,6 +2692,13 @@ F:	drivers/irqchip/irq-brcmstb*
 F:	include/linux/bcm963xx_nvram.h
 F:	include/linux/bcm963xx_tag.h
 
+BROADCOM BMIPS CPUFREQ DRIVER
+M:	Markus Mayer <mmayer@broadcom.com>
+M:	bcm-kernel-feedback-list@broadcom.com
+L:	linux-pm@vger.kernel.org
+S:	Maintained
+F:	drivers/cpufreq/bmips-cpufreq.c
+
 BROADCOM TG3 GIGABIT ETHERNET DRIVER
 M:	Siva Reddy Kallam <siva.kallam@broadcom.com>
 M:	Prashant Sreedharan <prashant@broadcom.com>
@@ -3567,7 +3574,7 @@ F:	drivers/infiniband/hw/cxgb3/
 F:	include/uapi/rdma/cxgb3-abi.h
 
 CXGB4 ETHERNET DRIVER (CXGB4)
-M:	Hariprasad S <hariprasad@chelsio.com>
+M:	Ganesh Goudar <ganeshgr@chelsio.com>
 L:	netdev@vger.kernel.org
 W:	http://www.chelsio.com
 S:	Supported
@@ -4100,12 +4107,18 @@ F:	drivers/gpu/drm/bridge/
 
 DRM DRIVER FOR BOCHS VIRTUAL GPU
 M:	Gerd Hoffmann <kraxel@redhat.com>
-S:	Odd Fixes
+L:	virtualization@lists.linux-foundation.org
+T:	git git://git.kraxel.org/linux drm-qemu
+S:	Maintained
 F:	drivers/gpu/drm/bochs/
 
 DRM DRIVER FOR QEMU'S CIRRUS DEVICE
 M:	Dave Airlie <airlied@redhat.com>
-S:	Odd Fixes
+M:	Gerd Hoffmann <kraxel@redhat.com>
+L:	virtualization@lists.linux-foundation.org
+T:	git git://git.kraxel.org/linux drm-qemu
+S:	Obsolete
+W:	https://www.kraxel.org/blog/2014/10/qemu-using-cirrus-considered-harmful/
 F:	drivers/gpu/drm/cirrus/
 
 RADEON and AMDGPU DRM DRIVERS
@@ -4147,7 +4160,7 @@ F:	Documentation/gpu/i915.rst
 INTEL GVT-g DRIVERS (Intel GPU Virtualization)
 M:      Zhenyu Wang <zhenyuw@linux.intel.com>
 M:      Zhi Wang <zhi.a.wang@intel.com>
-L:      igvt-g-dev@lists.01.org
+L:      intel-gvt-dev@lists.freedesktop.org
 L:      intel-gfx@lists.freedesktop.org
 W:      https://01.org/igvt-g
 T:      git https://github.com/01org/gvt-linux.git
@@ -4298,7 +4311,10 @@ F:	Documentation/devicetree/bindings/display/renesas,du.txt
 
 DRM DRIVER FOR QXL VIRTUAL GPU
 M:	Dave Airlie <airlied@redhat.com>
-S:	Odd Fixes
+M:	Gerd Hoffmann <kraxel@redhat.com>
+L:	virtualization@lists.linux-foundation.org
+T:	git git://git.kraxel.org/linux drm-qemu
+S:	Maintained
 F:	drivers/gpu/drm/qxl/
 F:	include/uapi/drm/qxl_drm.h
 
@@ -5265,7 +5281,7 @@ M:	Jaegeuk Kim <jaegeuk@kernel.org>
 L:	linux-fsdevel@vger.kernel.org
 S:	Supported
 F:	fs/crypto/
-F:	include/linux/fscrypto.h
+F:	include/linux/fscrypt*.h
 
 F2FS FILE SYSTEM
 M:	Jaegeuk Kim <jaegeuk@kernel.org>
@@ -6718,9 +6734,8 @@ S:	Odd Fixes
 F:	drivers/tty/ipwireless/
 
 IPX NETWORK LAYER
-M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Odd fixes
 F:	include/net/ipx.h
 F:	include/uapi/linux/ipx.h
 F:	net/ipx/
@@ -7492,8 +7507,8 @@ S:	Maintained
 F:	drivers/misc/lkdtm*
 
 LLC (802.2)
-M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
-S:	Maintained
+L:	netdev@vger.kernel.org
+S:	Odd fixes
 F:	include/linux/llc.h
 F:	include/uapi/linux/llc.h
 F:	include/net/llc*
@@ -7526,6 +7541,7 @@ S:	Maintained
 F:	Documentation/hwmon/lm90
 F:	Documentation/devicetree/bindings/hwmon/lm90.txt
 F:	drivers/hwmon/lm90.c
+F:	include/dt-bindings/thermal/lm90.h
 
 LM95234 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
@@ -8604,10 +8620,10 @@ S:	Maintained
 F:	drivers/net/ethernet/netronome/
 
 NETWORK BLOCK DEVICE (NBD)
-M:	Markus Pargmann <mpa@pengutronix.de>
+M:	Josef Bacik <jbacik@fb.com>
 S:	Maintained
+L:	linux-block@vger.kernel.org
 L:	nbd-general@lists.sourceforge.net
-T:	git git://git.pengutronix.de/git/mpa/linux-nbd.git
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
 F:	include/uapi/linux/nbd.h
@@ -9727,7 +9743,7 @@ S:	Maintained
 F:	drivers/pinctrl/pinctrl-at91.*
 
 PIN CONTROLLER - ATMEL AT91 PIO4
-M:	Ludovic Desroches <ludovic.desroches@atmel.com>
+M:	Ludovic Desroches <ludovic.desroches@microchip.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-gpio@vger.kernel.org
 S:	Supported
@@ -10186,7 +10202,6 @@ F:	drivers/media/tuners/qt1010*
 QUALCOMM ATHEROS ATH9K WIRELESS DRIVER
 M:	QCA ath9k Development <ath9k-devel@qca.qualcomm.com>
 L:	linux-wireless@vger.kernel.org
-L:	ath9k-devel@lists.ath9k.org
 W:	http://wireless.kernel.org/en/users/Drivers/ath9k
 S:	Supported
 F:	drivers/net/wireless/ath/ath9k/
@@ -10879,7 +10894,6 @@ SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
 M:	Jaehoon Chung <jh80.chung@samsung.com>
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
-F:	include/linux/mmc/dw_mmc.h
 F:	drivers/mmc/host/dw_mmc*
 
 SYSTEM TRACE MODULE CLASS
@@ -11082,6 +11096,17 @@ L:	linux-mmc@vger.kernel.org
 S:	Maintained
 F:	drivers/mmc/host/sdhci-spear.c
 
+SECURE ENCRYPTING DEVICE (SED) OPAL DRIVER
+M:	Scott Bauer <scott.bauer@intel.com>
+M:	Jonathan Derrick <jonathan.derrick@intel.com>
+M:	Rafael Antognolli <rafael.antognolli@intel.com>
+L:	linux-block@vger.kernel.org
+S:	Supported
+F:	block/sed*
+F:	block/opal_proto.h
+F:	include/linux/sed*
+F:	include/uapi/linux/sed*
+
 SECURITY SUBSYSTEM
 M:	James Morris <james.l.morris@oracle.com>
 M:	"Serge E. Hallyn" <serge@hallyn.com>
@@ -13057,7 +13082,7 @@ F:	drivers/input/serio/userio.c
 F:	include/uapi/linux/userio.h
 
 VIRTIO CONSOLE DRIVER
-M:	Amit Shah <amit.shah@redhat.com>
+M:	Amit Shah <amit@kernel.org>
 L:	virtualization@lists.linux-foundation.org
 S:	Maintained
 F:	drivers/char/virtio_console.c
@@ -13092,6 +13117,7 @@ M:	David Airlie <airlied@linux.ie>
 M:	Gerd Hoffmann <kraxel@redhat.com>
 L:	dri-devel@lists.freedesktop.org
 L:	virtualization@lists.linux-foundation.org
+T:	git git://git.kraxel.org/linux drm-qemu
 S:	Maintained
 F:	drivers/gpu/drm/virtio/
 F:	include/uapi/linux/virtio_gpu.h
@@ -13364,10 +13390,8 @@ S:	Maintained
 F:	drivers/input/misc/wistron_btns.c
 
 WL3501 WIRELESS PCMCIA CARD DRIVER
-M:	Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 L:	linux-wireless@vger.kernel.org
-W:	http://oops.ghostprotocols.net:81/blog
-S:	Maintained
+S:	Odd fixes
 F:	drivers/net/wireless/wl3501*
 
 WOLFSON MICROELECTRONICS DRIVERS
@@ -13443,6 +13467,7 @@ F:	arch/x86/
 
 X86 PLATFORM DRIVERS
 M:	Darren Hart <dvhart@infradead.org>
+M:	Andy Shevchenko <andy@infradead.org>
 L:	platform-driver-x86@vger.kernel.org
 T:	git git://git.infradead.org/users/dvhart/linux-platform-drivers-x86.git
 S:	Maintained
@@ -13614,6 +13639,7 @@ F:	drivers/net/hamradio/z8530.h
 
 ZBUD COMPRESSED PAGE ALLOCATOR
 M:	Seth Jennings <sjenning@redhat.com>
+M:	Dan Streetman <ddstreet@ieee.org>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/zbud.c
@@ -13669,6 +13695,7 @@ F:	Documentation/vm/zsmalloc.txt
 
 ZSWAP COMPRESSED SWAP CACHING
 M:	Seth Jennings <sjenning@redhat.com>
+M:	Dan Streetman <ddstreet@ieee.org>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/zswap.c
diff --git a/Makefile b/Makefile
index 098840012b9b..4e2abc36e14b 100644
--- a/Makefile
+++ b/Makefile
@@ -1,8 +1,8 @@
 VERSION = 4
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
-NAME = Anniversary Edition
+EXTRAVERSION =
+NAME = Fearless Coyote
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
@@ -87,10 +87,12 @@ endif
 ifneq ($(filter 4.%,$(MAKE_VERSION)),)	# make-4
 ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
   quiet=silent_
+  tools_silent=s
 endif
 else					# make-3.8x
 ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
   quiet=silent_
+  tools_silent=-s
 endif
 endif
 
@@ -797,7 +799,7 @@ KBUILD_CFLAGS   += $(call cc-option,-Werror=incompatible-pointer-types)
 KBUILD_ARFLAGS := $(call ar-option,D)
 
 # check for 'asm goto'
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC)), y)
+ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLAGS)), y)
 	KBUILD_CFLAGS += -DCC_HAVE_ASM_GOTO
 	KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
 endif
@@ -1607,11 +1609,11 @@ image_name:
 # Clear a bunch of variables before executing the submake
 tools/: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/
 
 tools/%: FORCE
 	$(Q)mkdir -p $(objtree)/tools
-	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $*
+	$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(shell cd $(objtree) && /bin/pwd) subdir=tools -C $(src)/tools/ $*
 
 # Single targets
 # ---------------------------------------------------------------------------
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index bf8475ce85ee..baa152b9348e 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -1,7 +1,6 @@
 
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += exec.h
 generic-y += export.h
 generic-y += irq_work.h
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 54d8616644e2..9d27a7d333dc 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1145,7 +1145,7 @@ struct rusage32 {
 SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 {
 	struct rusage32 r;
-	cputime_t utime, stime;
+	u64 utime, stime;
 	unsigned long utime_jiffies, stime_jiffies;
 
 	if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
@@ -1155,16 +1155,16 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 	switch (who) {
 	case RUSAGE_SELF:
 		task_cputime(current, &utime, &stime);
-		utime_jiffies = cputime_to_jiffies(utime);
-		stime_jiffies = cputime_to_jiffies(stime);
+		utime_jiffies = nsecs_to_jiffies(utime);
+		stime_jiffies = nsecs_to_jiffies(stime);
 		jiffies_to_timeval32(utime_jiffies, &r.ru_utime);
 		jiffies_to_timeval32(stime_jiffies, &r.ru_stime);
 		r.ru_minflt = current->min_flt;
 		r.ru_majflt = current->maj_flt;
 		break;
 	case RUSAGE_CHILDREN:
-		utime_jiffies = cputime_to_jiffies(current->signal->cutime);
-		stime_jiffies = cputime_to_jiffies(current->signal->cstime);
+		utime_jiffies = nsecs_to_jiffies(current->signal->cutime);
+		stime_jiffies = nsecs_to_jiffies(current->signal->cstime);
 		jiffies_to_timeval32(utime_jiffies, &r.ru_utime);
 		jiffies_to_timeval32(stime_jiffies, &r.ru_stime);
 		r.ru_minflt = current->signal->cmin_flt;
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index c332604606dd..63a04013d05a 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -2,7 +2,6 @@ generic-y += auxvec.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index a36e8601114d..d5da2115d78a 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -26,7 +26,9 @@ static inline void __delay(unsigned long loops)
 	"	lp  1f			\n"
 	"	nop			\n"
 	"1:				\n"
-	: : "r"(loops));
+	:
+        : "r"(loops)
+        : "lp_count");
 }
 
 extern void __bad_udelay(void);
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 689dd867fdff..8b90d25a15cc 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -71,14 +71,14 @@ ENTRY(stext)
 	GET_CPU_ID  r5
 	cmp	r5, 0
 	mov.nz	r0, r5
-#ifdef CONFIG_ARC_SMP_HALT_ON_RESET
-	; Non-Master can proceed as system would be booted sufficiently
-	jnz	first_lines_of_secondary
-#else
+	bz	.Lmaster_proceed
+
 	; Non-Masters wait for Master to boot enough and bring them up
-	jnz	arc_platform_smp_wait_to_boot
-#endif
-	; Master falls thru
+	; when they resume, tail-call to entry point
+	mov	blink, @first_lines_of_secondary
+	j	arc_platform_smp_wait_to_boot
+
+.Lmaster_proceed:
 #endif
 
 	; Clear BSS before updating any globals
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 9274f8ade8c7..9f6b68fd4f3b 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -93,11 +93,10 @@ static void mcip_probe_n_setup(void)
 	READ_BCR(ARC_REG_MCIP_BCR, mp);
 
 	sprintf(smp_cpuinfo_buf,
-		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n",
+		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n",
 		mp.ver, mp.num_cores,
 		IS_AVAIL1(mp.ipi, "IPI "),
 		IS_AVAIL1(mp.idu, "IDU "),
-		IS_AVAIL1(mp.llm, "LLM "),
 		IS_AVAIL1(mp.dbg, "DEBUG "),
 		IS_AVAIL1(mp.gfrc, "GFRC"));
 
@@ -175,7 +174,6 @@ static void idu_irq_unmask(struct irq_data *data)
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
 }
 
-#ifdef CONFIG_SMP
 static int
 idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
 		     bool force)
@@ -205,12 +203,27 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
 
 	return IRQ_SET_MASK_OK;
 }
-#endif
+
+static void idu_irq_enable(struct irq_data *data)
+{
+	/*
+	 * By default send all common interrupts to all available online CPUs.
+	 * The affinity of common interrupts in IDU must be set manually since
+	 * in some cases the kernel will not call irq_set_affinity() by itself:
+	 *   1. When the kernel is not configured with support of SMP.
+	 *   2. When the kernel is configured with support of SMP but upper
+	 *      interrupt controllers does not support setting of the affinity
+	 *      and cannot propagate it to IDU.
+	 */
+	idu_irq_set_affinity(data, cpu_online_mask, false);
+	idu_irq_unmask(data);
+}
 
 static struct irq_chip idu_irq_chip = {
 	.name			= "MCIP IDU Intc",
 	.irq_mask		= idu_irq_mask,
 	.irq_unmask		= idu_irq_unmask,
+	.irq_enable		= idu_irq_enable,
 #ifdef CONFIG_SMP
 	.irq_set_affinity       = idu_irq_set_affinity,
 #endif
@@ -243,36 +256,14 @@ static int idu_irq_xlate(struct irq_domain *d, struct device_node *n,
 			 const u32 *intspec, unsigned int intsize,
 			 irq_hw_number_t *out_hwirq, unsigned int *out_type)
 {
-	irq_hw_number_t hwirq = *out_hwirq = intspec[0];
-	int distri = intspec[1];
-	unsigned long flags;
-
+	/*
+	 * Ignore value of interrupt distribution mode for common interrupts in
+	 * IDU which resides in intspec[1] since setting an affinity using value
+	 * from Device Tree is deprecated in ARC.
+	 */
+	*out_hwirq = intspec[0];
 	*out_type = IRQ_TYPE_NONE;
 
-	/* XXX: validate distribution scheme again online cpu mask */
-	if (distri == 0) {
-		/* 0 - Round Robin to all cpus, otherwise 1 bit per core */
-		raw_spin_lock_irqsave(&mcip_lock, flags);
-		idu_set_dest(hwirq, BIT(num_online_cpus()) - 1);
-		idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
-		raw_spin_unlock_irqrestore(&mcip_lock, flags);
-	} else {
-		/*
-		 * DEST based distribution for Level Triggered intr can only
-		 * have 1 CPU, so generalize it to always contain 1 cpu
-		 */
-		int cpu = ffs(distri);
-
-		if (cpu != fls(distri))
-			pr_warn("IDU irq %lx distri mode set to cpu %x\n",
-				hwirq, cpu);
-
-		raw_spin_lock_irqsave(&mcip_lock, flags);
-		idu_set_dest(hwirq, cpu);
-		idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_DEST);
-		raw_spin_unlock_irqrestore(&mcip_lock, flags);
-	}
-
 	return 0;
 }
 
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 88674d972c9d..2afbafadb6ab 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -90,22 +90,37 @@ void __init smp_cpus_done(unsigned int max_cpus)
  */
 static volatile int wake_flag;
 
+#ifdef CONFIG_ISA_ARCOMPACT
+
+#define __boot_read(f)		f
+#define __boot_write(f, v)	f = v
+
+#else
+
+#define __boot_read(f)		arc_read_uncached_32(&f)
+#define __boot_write(f, v)	arc_write_uncached_32(&f, v)
+
+#endif
+
 static void arc_default_smp_cpu_kick(int cpu, unsigned long pc)
 {
 	BUG_ON(cpu == 0);
-	wake_flag = cpu;
+
+	__boot_write(wake_flag, cpu);
 }
 
 void arc_platform_smp_wait_to_boot(int cpu)
 {
-	while (wake_flag != cpu)
+	/* for halt-on-reset, we've waited already */
+	if (IS_ENABLED(CONFIG_ARC_SMP_HALT_ON_RESET))
+		return;
+
+	while (__boot_read(wake_flag) != cpu)
 		;
 
-	wake_flag = 0;
-	__asm__ __volatile__("j @first_lines_of_secondary	\n");
+	__boot_write(wake_flag, 0);
 }
 
-
 const char *arc_platform_smp_cpuinfo(void)
 {
 	return plat_smp_ops.info ? : "";
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index abd961f3e763..5f69c3bd59bb 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -241,8 +241,9 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 	if (state.fault)
 		goto fault;
 
+	/* clear any remanants of delay slot */
 	if (delay_mode(regs)) {
-		regs->ret = regs->bta;
+		regs->ret = regs->bta & ~1U;
 		regs->status32 &= ~STATUS_DE_MASK;
 	} else {
 		regs->ret += state.instr_len;
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile
index f10fe8526239..01d178a2009f 100644
--- a/arch/arm/boot/dts/Makefile
+++ b/arch/arm/boot/dts/Makefile
@@ -617,7 +617,7 @@ dtb-$(CONFIG_ARCH_ORION5X) += \
 	orion5x-lacie-ethernet-disk-mini-v2.dtb \
 	orion5x-linkstation-lsgl.dtb \
 	orion5x-linkstation-lswtgl.dtb \
-	orion5x-lschl.dtb \
+	orion5x-linkstation-lschl.dtb \
 	orion5x-lswsgl.dtb \
 	orion5x-maxtor-shared-storage-2.dtb \
 	orion5x-netgear-wnr854t.dtb \
diff --git a/arch/arm/boot/dts/imx1.dtsi b/arch/arm/boot/dts/imx1.dtsi
index b792eee3899b..2ee40bc9ec21 100644
--- a/arch/arm/boot/dts/imx1.dtsi
+++ b/arch/arm/boot/dts/imx1.dtsi
@@ -18,6 +18,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		gpio0 = &gpio1;
diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi
index ac2a9da62b6c..43ccbbf754a3 100644
--- a/arch/arm/boot/dts/imx23.dtsi
+++ b/arch/arm/boot/dts/imx23.dtsi
@@ -16,6 +16,14 @@
 	#size-cells = <1>;
 
 	interrupt-parent = <&icoll>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		gpio0 = &gpio0;
diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi
index 831d09a28155..acd475659156 100644
--- a/arch/arm/boot/dts/imx25.dtsi
+++ b/arch/arm/boot/dts/imx25.dtsi
@@ -14,6 +14,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index 9d8b5969ee3b..b397384248f4 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -19,6 +19,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 3aabf65a6a52..d6a2190b60ef 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -17,6 +17,14 @@
 	#size-cells = <1>;
 
 	interrupt-parent = <&icoll>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		ethernet0 = &mac0;
diff --git a/arch/arm/boot/dts/imx31.dtsi b/arch/arm/boot/dts/imx31.dtsi
index 85cd8be22f71..23b0d2cf9acd 100644
--- a/arch/arm/boot/dts/imx31.dtsi
+++ b/arch/arm/boot/dts/imx31.dtsi
@@ -12,6 +12,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		serial0 = &uart1;
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index 9f40e6229189..d0496c65cea2 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -13,6 +13,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx50.dtsi b/arch/arm/boot/dts/imx50.dtsi
index fe0221e4cbf7..ceae909e2201 100644
--- a/arch/arm/boot/dts/imx50.dtsi
+++ b/arch/arm/boot/dts/imx50.dtsi
@@ -17,6 +17,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi
index 33526cade735..1ee1d542d9ad 100644
--- a/arch/arm/boot/dts/imx51.dtsi
+++ b/arch/arm/boot/dts/imx51.dtsi
@@ -19,6 +19,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index ca51dc03e327..2e516f4985e4 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -19,6 +19,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx6dl.dtsi b/arch/arm/boot/dts/imx6dl.dtsi
index 1ade1951e620..7aa120fbdc71 100644
--- a/arch/arm/boot/dts/imx6dl.dtsi
+++ b/arch/arm/boot/dts/imx6dl.dtsi
@@ -137,7 +137,7 @@
 &gpio4 {
 	gpio-ranges = <&iomuxc  5 136 1>, <&iomuxc  6 145 1>, <&iomuxc  7 150 1>,
 		      <&iomuxc  8 146 1>, <&iomuxc  9 151 1>, <&iomuxc 10 147 1>,
-		      <&iomuxc 11 151 1>, <&iomuxc 12 148 1>, <&iomuxc 13 153 1>,
+		      <&iomuxc 11 152 1>, <&iomuxc 12 148 1>, <&iomuxc 13 153 1>,
 		      <&iomuxc 14 149 1>, <&iomuxc 15 154 1>, <&iomuxc 16  39 7>,
 		      <&iomuxc 23  56 1>, <&iomuxc 24  61 7>, <&iomuxc 31  46 1>;
 };
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index 89b834f3fa17..e7d30f45b161 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -16,6 +16,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx6sl.dtsi b/arch/arm/boot/dts/imx6sl.dtsi
index 19cbd879c448..cc9572ea2860 100644
--- a/arch/arm/boot/dts/imx6sl.dtsi
+++ b/arch/arm/boot/dts/imx6sl.dtsi
@@ -14,6 +14,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		ethernet0 = &fec;
diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi
index 10f333016197..dd4ec85ecbaa 100644
--- a/arch/arm/boot/dts/imx6sx.dtsi
+++ b/arch/arm/boot/dts/imx6sx.dtsi
@@ -15,6 +15,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		can0 = &flexcan1;
diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi
index 39845a7e0463..53d3f8e41e9b 100644
--- a/arch/arm/boot/dts/imx6ul.dtsi
+++ b/arch/arm/boot/dts/imx6ul.dtsi
@@ -15,6 +15,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		ethernet0 = &fec1;
diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi
index 8ff2cbdd8f0d..be33dfc86838 100644
--- a/arch/arm/boot/dts/imx7s.dtsi
+++ b/arch/arm/boot/dts/imx7s.dtsi
@@ -50,6 +50,14 @@
 / {
 	#address-cells = <1>;
 	#size-cells = <1>;
+	/*
+	 * The decompressor and also some bootloaders rely on a
+	 * pre-existing /chosen node to be available to insert the
+	 * command line and merge other ATAGS info.
+	 * Also for U-Boot there must be a pre-existing /memory node.
+	 */
+	chosen {};
+	memory { device_type = "memory"; reg = <0 0>; };
 
 	aliases {
 		gpio0 = &gpio1;
diff --git a/arch/arm/boot/dts/orion5x-lschl.dts b/arch/arm/boot/dts/orion5x-linkstation-lschl.dts
index 947409252845..ea6c881634b9 100644
--- a/arch/arm/boot/dts/orion5x-lschl.dts
+++ b/arch/arm/boot/dts/orion5x-linkstation-lschl.dts
@@ -2,7 +2,7 @@
  * Device Tree file for Buffalo Linkstation LS-CHLv3
  *
  * Copyright (C) 2016 Ash Hughes <ashley.hughes@blueyonder.co.uk>
- * Copyright (C) 2015, 2016
+ * Copyright (C) 2015-2017
  * Roger Shimizu <rogershimizu@gmail.com>
  *
  * This file is dual-licensed: you can use it either under the terms
@@ -52,7 +52,7 @@
 #include <dt-bindings/gpio/gpio.h>
 
 / {
-	model = "Buffalo Linkstation Live v3 (LS-CHL)";
+	model = "Buffalo Linkstation LiveV3 (LS-CHL)";
 	compatible = "buffalo,lschl", "marvell,orion5x-88f5182", "marvell,orion5x";
 
 	memory { /* 128 MB */
diff --git a/arch/arm/boot/dts/stih407-family.dtsi b/arch/arm/boot/dts/stih407-family.dtsi
index c8b2944e304a..ace97e8576db 100644
--- a/arch/arm/boot/dts/stih407-family.dtsi
+++ b/arch/arm/boot/dts/stih407-family.dtsi
@@ -680,6 +680,7 @@
 				phy-names	= "usb2-phy", "usb3-phy";
 				phys		= <&usb2_picophy0>,
 						  <&phy_port2 PHY_TYPE_USB3>;
+				snps,dis_u3_susphy_quirk;
 			};
 		};
 
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 79c415c33f69..809f0bf3042a 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -24,7 +24,7 @@ CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CMDLINE="root=/dev/ram0 rw ramdisk=8192 initrd=0x41000000,8M console=ttySAC1,115200 init=/linuxrc mem=256M"
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_STAT_DETAILS=y
+CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=m
 CONFIG_CPU_FREQ_GOV_USERSPACE=m
diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig
index ea316c4b890e..d3f1768840e2 100644
--- a/arch/arm/configs/ezx_defconfig
+++ b/arch/arm/configs/ezx_defconfig
@@ -64,8 +64,8 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_QUEUE=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig
index 18e59feaa307..7f479cdb3479 100644
--- a/arch/arm/configs/imote2_defconfig
+++ b/arch/arm/configs/imote2_defconfig
@@ -56,8 +56,8 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_QUEUE=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_EVENTS=y
-CONFIG_NF_CT_PROTO_SCTP=m
-CONFIG_NF_CT_PROTO_UDPLITE=m
+CONFIG_NF_CT_PROTO_SCTP=y
+CONFIG_NF_CT_PROTO_UDPLITE=y
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig
index 361686a362f1..69a4bd13eea5 100644
--- a/arch/arm/configs/multi_v5_defconfig
+++ b/arch/arm/configs/multi_v5_defconfig
@@ -58,7 +58,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_STAT_DETAILS=y
+CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_IDLE=y
 CONFIG_ARM_KIRKWOOD_CPUIDLE=y
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 028d2b70e3b5..2e7a63f35bd3 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -132,7 +132,7 @@ CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_KEXEC=y
 CONFIG_EFI=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_STAT_DETAILS=y
+CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=m
 CONFIG_CPU_FREQ_GOV_USERSPACE=m
@@ -824,6 +824,7 @@ CONFIG_QCOM_SMSM=y
 CONFIG_QCOM_WCNSS_CTRL=m
 CONFIG_ROCKCHIP_PM_DOMAINS=y
 CONFIG_COMMON_CLK_QCOM=y
+CONFIG_QCOM_CLK_RPM=y
 CONFIG_CHROME_PLATFORMS=y
 CONFIG_STAGING_BOARD=y
 CONFIG_CROS_EC_CHARDEV=m
diff --git a/arch/arm/configs/mvebu_v5_defconfig b/arch/arm/configs/mvebu_v5_defconfig
index f7f6039419aa..4b598da0d086 100644
--- a/arch/arm/configs/mvebu_v5_defconfig
+++ b/arch/arm/configs/mvebu_v5_defconfig
@@ -44,7 +44,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_STAT_DETAILS=y
+CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_IDLE=y
 CONFIG_ARM_KIRKWOOD_CPUIDLE=y
diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig
index e4314b1227a3..271dc7e78e43 100644
--- a/arch/arm/configs/pxa_defconfig
+++ b/arch/arm/configs/pxa_defconfig
@@ -97,7 +97,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="root=/dev/ram0 ro"
 CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_STAT_DETAILS=y
+CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=m
 CONFIG_CPU_FREQ_GOV_USERSPACE=m
diff --git a/arch/arm/configs/shmobile_defconfig b/arch/arm/configs/shmobile_defconfig
index 1b0f8ae36fb3..adeaecd831a4 100644
--- a/arch/arm/configs/shmobile_defconfig
+++ b/arch/arm/configs/shmobile_defconfig
@@ -38,7 +38,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_ARM_APPENDED_DTB=y
 CONFIG_KEXEC=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_STAT_DETAILS=y
+CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_ONDEMAND=y
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index efb21757d41f..b14e8c7d71bd 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -2,7 +2,6 @@
 
 generic-y += bitsperlong.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += early_ioremap.h
 generic-y += emergency-restart.h
diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index 0b06f5341b45..e4e6a9d6a825 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -55,6 +55,7 @@ void efi_virtmap_unload(void);
 
 #define efi_call_early(f, ...)		sys_table_arg->boottime->f(__VA_ARGS__)
 #define __efi_call_early(f, ...)	f(__VA_ARGS__)
+#define efi_call_runtime(f, ...)	sys_table_arg->runtime->f(__VA_ARGS__)
 #define efi_is_64bit()			(false)
 
 #define efi_call_proto(protocol, f, instance, ...)			\
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 1f59ea051bab..b7e0125c0bbf 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -478,11 +478,10 @@ extern unsigned long __must_check
 arm_copy_from_user(void *to, const void __user *from, unsigned long n);
 
 static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
+__arch_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	unsigned int __ua_flags;
 
-	check_object_size(to, n, false);
 	__ua_flags = uaccess_save_and_enable();
 	n = arm_copy_from_user(to, from, n);
 	uaccess_restore(__ua_flags);
@@ -495,18 +494,15 @@ extern unsigned long __must_check
 __copy_to_user_std(void __user *to, const void *from, unsigned long n);
 
 static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+__arch_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 #ifndef CONFIG_UACCESS_WITH_MEMCPY
 	unsigned int __ua_flags;
-
-	check_object_size(from, n, true);
 	__ua_flags = uaccess_save_and_enable();
 	n = arm_copy_to_user(to, from, n);
 	uaccess_restore(__ua_flags);
 	return n;
 #else
-	check_object_size(from, n, true);
 	return arm_copy_to_user(to, from, n);
 #endif
 }
@@ -526,25 +522,49 @@ __clear_user(void __user *addr, unsigned long n)
 }
 
 #else
-#define __copy_from_user(to, from, n)	(memcpy(to, (void __force *)from, n), 0)
-#define __copy_to_user(to, from, n)	(memcpy((void __force *)to, from, n), 0)
+#define __arch_copy_from_user(to, from, n)	\
+					(memcpy(to, (void __force *)from, n), 0)
+#define __arch_copy_to_user(to, from, n)	\
+					(memcpy((void __force *)to, from, n), 0)
 #define __clear_user(addr, n)		(memset((void __force *)addr, 0, n), 0)
 #endif
 
-static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
+static inline unsigned long __must_check
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	check_object_size(to, n, false);
+	return __arch_copy_from_user(to, from, n);
+}
+
+static inline unsigned long __must_check
+copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	unsigned long res = n;
+
+	check_object_size(to, n, false);
+
 	if (likely(access_ok(VERIFY_READ, from, n)))
-		res = __copy_from_user(to, from, n);
+		res = __arch_copy_from_user(to, from, n);
 	if (unlikely(res))
 		memset(to + (n - res), 0, res);
 	return res;
 }
 
-static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)
+static inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
 {
+	check_object_size(from, n, true);
+
+	return __arch_copy_to_user(to, from, n);
+}
+
+static inline unsigned long __must_check
+copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	check_object_size(from, n, true);
+
 	if (access_ok(VERIFY_WRITE, to, n))
-		n = __copy_to_user(to, from, n);
+		n = __arch_copy_to_user(to, from, n);
 	return n;
 }
 
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index ce131ed5939d..ae738a6319f6 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -600,7 +600,7 @@ static int gpr_set(struct task_struct *target,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct pt_regs newregs;
+	struct pt_regs newregs = *task_pt_regs(target);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
 				 &newregs,
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index 8ecfd15c3a02..df73914e81c8 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -67,7 +67,7 @@ ENTRY(__get_user_4)
 ENDPROC(__get_user_4)
 
 ENTRY(__get_user_8)
-	check_uaccess r0, 8, r1, r2, __get_user_bad
+	check_uaccess r0, 8, r1, r2, __get_user_bad8
 #ifdef CONFIG_THUMB2_KERNEL
 5: TUSER(ldr)	r2, [r0]
 6: TUSER(ldr)	r3, [r0, #4]
diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c
index aac3ab1a044f..df3ca38778af 100644
--- a/arch/arm/mach-davinci/board-da850-evm.c
+++ b/arch/arm/mach-davinci/board-da850-evm.c
@@ -18,6 +18,7 @@
 #include <linux/gpio/machine.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/leds.h>
 #include <linux/i2c.h>
 #include <linux/platform_data/at24.h>
 #include <linux/platform_data/pca953x.h>
diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c
index 521e40977265..023480b75244 100644
--- a/arch/arm/mach-davinci/board-dm644x-evm.c
+++ b/arch/arm/mach-davinci/board-dm644x-evm.c
@@ -25,6 +25,7 @@
 #include <linux/videodev2.h>
 #include <linux/v4l2-dv-timings.h>
 #include <linux/export.h>
+#include <linux/leds.h>
 
 #include <media/i2c/tvp514x.h>
 
diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c
index ad10017203c1..0a7838852649 100644
--- a/arch/arm/mach-davinci/board-neuros-osd2.c
+++ b/arch/arm/mach-davinci/board-neuros-osd2.c
@@ -25,6 +25,7 @@
  */
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
+#include <linux/leds.h>
 #include <linux/mtd/partitions.h>
 #include <linux/platform_data/gpio-davinci.h>
 #include <linux/platform_data/i2c-davinci.h>
diff --git a/arch/arm/mach-davinci/board-omapl138-hawk.c b/arch/arm/mach-davinci/board-omapl138-hawk.c
index 41d5500996b2..a3e78074be70 100644
--- a/arch/arm/mach-davinci/board-omapl138-hawk.c
+++ b/arch/arm/mach-davinci/board-omapl138-hawk.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/console.h>
+#include <linux/interrupt.h>
 #include <linux/gpio.h>
 #include <linux/gpio/machine.h>
 #include <linux/platform_data/gpio-davinci.h>
diff --git a/arch/arm/mach-ep93xx/edb93xx.c b/arch/arm/mach-ep93xx/edb93xx.c
index ad92d9f7e4df..0ac176386789 100644
--- a/arch/arm/mach-ep93xx/edb93xx.c
+++ b/arch/arm/mach-ep93xx/edb93xx.c
@@ -27,7 +27,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/gpio.h>
 #include <linux/i2c.h>
 #include <linux/i2c-gpio.h>
 #include <linux/spi/spi.h>
@@ -106,33 +105,10 @@ static struct cs4271_platform_data edb93xx_cs4271_data = {
 	.gpio_nreset	= -EINVAL,	/* filled in later */
 };
 
-static int edb93xx_cs4271_hw_setup(struct spi_device *spi)
-{
-	return gpio_request_one(EP93XX_GPIO_LINE_EGPIO6,
-				GPIOF_OUT_INIT_HIGH, spi->modalias);
-}
-
-static void edb93xx_cs4271_hw_cleanup(struct spi_device *spi)
-{
-	gpio_free(EP93XX_GPIO_LINE_EGPIO6);
-}
-
-static void edb93xx_cs4271_hw_cs_control(struct spi_device *spi, int value)
-{
-	gpio_set_value(EP93XX_GPIO_LINE_EGPIO6, value);
-}
-
-static struct ep93xx_spi_chip_ops edb93xx_cs4271_hw = {
-	.setup		= edb93xx_cs4271_hw_setup,
-	.cleanup	= edb93xx_cs4271_hw_cleanup,
-	.cs_control	= edb93xx_cs4271_hw_cs_control,
-};
-
 static struct spi_board_info edb93xx_spi_board_info[] __initdata = {
 	{
 		.modalias		= "cs4271",
 		.platform_data		= &edb93xx_cs4271_data,
-		.controller_data	= &edb93xx_cs4271_hw,
 		.max_speed_hz		= 6000000,
 		.bus_num		= 0,
 		.chip_select		= 0,
@@ -140,8 +116,13 @@ static struct spi_board_info edb93xx_spi_board_info[] __initdata = {
 	},
 };
 
+static int edb93xx_spi_chipselects[] __initdata = {
+	EP93XX_GPIO_LINE_EGPIO6,
+};
+
 static struct ep93xx_spi_info edb93xx_spi_info __initdata = {
-	.num_chipselect	= ARRAY_SIZE(edb93xx_spi_board_info),
+	.chipselect	= edb93xx_spi_chipselects,
+	.num_chipselect	= ARRAY_SIZE(edb93xx_spi_chipselects),
 };
 
 static void __init edb93xx_register_spi(void)
diff --git a/arch/arm/mach-ep93xx/simone.c b/arch/arm/mach-ep93xx/simone.c
index 7bb540c421ee..c7a40f245892 100644
--- a/arch/arm/mach-ep93xx/simone.c
+++ b/arch/arm/mach-ep93xx/simone.c
@@ -49,56 +49,6 @@ static struct ep93xxfb_mach_info __initdata simone_fb_info = {
 #define MMC_CARD_DETECT_GPIO EP93XX_GPIO_LINE_EGPIO0
 
 /*
- * Up to v1.3, the Sim.One used SFRMOUT as SD card chip select, but this goes
- * low between multi-message command blocks. From v1.4, it uses a GPIO instead.
- * v1.3 parts will still work, since the signal on SFRMOUT is automatic.
- */
-#define MMC_CHIP_SELECT_GPIO EP93XX_GPIO_LINE_EGPIO1
-
-/*
- * MMC SPI chip select GPIO handling. If you are using SFRMOUT (SFRM1) signal,
- * you can leave these empty and pass NULL as .controller_data.
- */
-
-static int simone_mmc_spi_setup(struct spi_device *spi)
-{
-	unsigned int gpio = MMC_CHIP_SELECT_GPIO;
-	int err;
-
-	err = gpio_request(gpio, spi->modalias);
-	if (err)
-		return err;
-
-	err = gpio_direction_output(gpio, 1);
-	if (err) {
-		gpio_free(gpio);
-		return err;
-	}
-
-	return 0;
-}
-
-static void simone_mmc_spi_cleanup(struct spi_device *spi)
-{
-	unsigned int gpio = MMC_CHIP_SELECT_GPIO;
-
-	gpio_set_value(gpio, 1);
-	gpio_direction_input(gpio);
-	gpio_free(gpio);
-}
-
-static void simone_mmc_spi_cs_control(struct spi_device *spi, int value)
-{
-	gpio_set_value(MMC_CHIP_SELECT_GPIO, value);
-}
-
-static struct ep93xx_spi_chip_ops simone_mmc_spi_ops = {
-	.setup		= simone_mmc_spi_setup,
-	.cleanup	= simone_mmc_spi_cleanup,
-	.cs_control	= simone_mmc_spi_cs_control,
-};
-
-/*
  * MMC card detection GPIO setup.
  */
 
@@ -152,7 +102,6 @@ static struct mmc_spi_platform_data simone_mmc_spi_data = {
 static struct spi_board_info simone_spi_devices[] __initdata = {
 	{
 		.modalias		= "mmc_spi",
-		.controller_data	= &simone_mmc_spi_ops,
 		.platform_data		= &simone_mmc_spi_data,
 		/*
 		 * We use 10 MHz even though the maximum is 3.7 MHz. The driver
@@ -165,8 +114,18 @@ static struct spi_board_info simone_spi_devices[] __initdata = {
 	},
 };
 
+/*
+ * Up to v1.3, the Sim.One used SFRMOUT as SD card chip select, but this goes
+ * low between multi-message command blocks. From v1.4, it uses a GPIO instead.
+ * v1.3 parts will still work, since the signal on SFRMOUT is automatic.
+ */
+static int simone_spi_chipselects[] __initdata = {
+	EP93XX_GPIO_LINE_EGPIO1,
+};
+
 static struct ep93xx_spi_info simone_spi_info __initdata = {
-	.num_chipselect	= ARRAY_SIZE(simone_spi_devices),
+	.chipselect	= simone_spi_chipselects,
+	.num_chipselect	= ARRAY_SIZE(simone_spi_chipselects),
 	.use_dma = 1,
 };
 
diff --git a/arch/arm/mach-ep93xx/vision_ep9307.c b/arch/arm/mach-ep93xx/vision_ep9307.c
index 5cced5988498..1daf9441058c 100644
--- a/arch/arm/mach-ep93xx/vision_ep9307.c
+++ b/arch/arm/mach-ep93xx/vision_ep9307.c
@@ -175,33 +175,9 @@ static struct cs4271_platform_data vision_cs4271_data = {
 	.gpio_nreset	= EP93XX_GPIO_LINE_H(2),
 };
 
-static int vision_cs4271_hw_setup(struct spi_device *spi)
-{
-	return gpio_request_one(EP93XX_GPIO_LINE_EGPIO6,
-				GPIOF_OUT_INIT_HIGH, spi->modalias);
-}
-
-static void vision_cs4271_hw_cleanup(struct spi_device *spi)
-{
-	gpio_free(EP93XX_GPIO_LINE_EGPIO6);
-}
-
-static void vision_cs4271_hw_cs_control(struct spi_device *spi, int value)
-{
-	gpio_set_value(EP93XX_GPIO_LINE_EGPIO6, value);
-}
-
-static struct ep93xx_spi_chip_ops vision_cs4271_hw = {
-	.setup		= vision_cs4271_hw_setup,
-	.cleanup	= vision_cs4271_hw_cleanup,
-	.cs_control	= vision_cs4271_hw_cs_control,
-};
-
 /*************************************************************************
  * SPI Flash
  *************************************************************************/
-#define VISION_SPI_FLASH_CS	EP93XX_GPIO_LINE_EGPIO7
-
 static struct mtd_partition vision_spi_flash_partitions[] = {
 	{
 		.name	= "SPI bootstrap",
@@ -224,68 +200,20 @@ static struct flash_platform_data vision_spi_flash_data = {
 	.nr_parts	= ARRAY_SIZE(vision_spi_flash_partitions),
 };
 
-static int vision_spi_flash_hw_setup(struct spi_device *spi)
-{
-	return gpio_request_one(VISION_SPI_FLASH_CS, GPIOF_INIT_HIGH,
-				spi->modalias);
-}
-
-static void vision_spi_flash_hw_cleanup(struct spi_device *spi)
-{
-	gpio_free(VISION_SPI_FLASH_CS);
-}
-
-static void vision_spi_flash_hw_cs_control(struct spi_device *spi, int value)
-{
-	gpio_set_value(VISION_SPI_FLASH_CS, value);
-}
-
-static struct ep93xx_spi_chip_ops vision_spi_flash_hw = {
-	.setup		= vision_spi_flash_hw_setup,
-	.cleanup	= vision_spi_flash_hw_cleanup,
-	.cs_control	= vision_spi_flash_hw_cs_control,
-};
-
 /*************************************************************************
  * SPI SD/MMC host
  *************************************************************************/
-#define VISION_SPI_MMC_CS	EP93XX_GPIO_LINE_G(2)
-#define VISION_SPI_MMC_WP	EP93XX_GPIO_LINE_F(0)
-#define VISION_SPI_MMC_CD	EP93XX_GPIO_LINE_EGPIO15
-
 static struct mmc_spi_platform_data vision_spi_mmc_data = {
 	.detect_delay	= 100,
 	.powerup_msecs	= 100,
 	.ocr_mask	= MMC_VDD_32_33 | MMC_VDD_33_34,
 	.flags		= MMC_SPI_USE_CD_GPIO | MMC_SPI_USE_RO_GPIO,
-	.cd_gpio	= VISION_SPI_MMC_CD,
+	.cd_gpio	= EP93XX_GPIO_LINE_EGPIO15,
 	.cd_debounce	= 1,
-	.ro_gpio	= VISION_SPI_MMC_WP,
+	.ro_gpio	= EP93XX_GPIO_LINE_F(0),
 	.caps2		= MMC_CAP2_RO_ACTIVE_HIGH,
 };
 
-static int vision_spi_mmc_hw_setup(struct spi_device *spi)
-{
-	return gpio_request_one(VISION_SPI_MMC_CS, GPIOF_INIT_HIGH,
-				spi->modalias);
-}
-
-static void vision_spi_mmc_hw_cleanup(struct spi_device *spi)
-{
-	gpio_free(VISION_SPI_MMC_CS);
-}
-
-static void vision_spi_mmc_hw_cs_control(struct spi_device *spi, int value)
-{
-	gpio_set_value(VISION_SPI_MMC_CS, value);
-}
-
-static struct ep93xx_spi_chip_ops vision_spi_mmc_hw = {
-	.setup		= vision_spi_mmc_hw_setup,
-	.cleanup	= vision_spi_mmc_hw_cleanup,
-	.cs_control	= vision_spi_mmc_hw_cs_control,
-};
-
 /*************************************************************************
  * SPI Bus
  *************************************************************************/
@@ -293,7 +221,6 @@ static struct spi_board_info vision_spi_board_info[] __initdata = {
 	{
 		.modalias		= "cs4271",
 		.platform_data		= &vision_cs4271_data,
-		.controller_data	= &vision_cs4271_hw,
 		.max_speed_hz		= 6000000,
 		.bus_num		= 0,
 		.chip_select		= 0,
@@ -301,7 +228,6 @@ static struct spi_board_info vision_spi_board_info[] __initdata = {
 	}, {
 		.modalias		= "sst25l",
 		.platform_data		= &vision_spi_flash_data,
-		.controller_data	= &vision_spi_flash_hw,
 		.max_speed_hz		= 20000000,
 		.bus_num		= 0,
 		.chip_select		= 1,
@@ -309,7 +235,6 @@ static struct spi_board_info vision_spi_board_info[] __initdata = {
 	}, {
 		.modalias		= "mmc_spi",
 		.platform_data		= &vision_spi_mmc_data,
-		.controller_data	= &vision_spi_mmc_hw,
 		.max_speed_hz		= 20000000,
 		.bus_num		= 0,
 		.chip_select		= 2,
@@ -317,8 +242,15 @@ static struct spi_board_info vision_spi_board_info[] __initdata = {
 	},
 };
 
+static int vision_spi_chipselects[] __initdata = {
+	EP93XX_GPIO_LINE_EGPIO6,
+	EP93XX_GPIO_LINE_EGPIO7,
+	EP93XX_GPIO_LINE_G(2),
+};
+
 static struct ep93xx_spi_info vision_spi_master __initdata = {
-	.num_chipselect	= ARRAY_SIZE(vision_spi_board_info),
+	.chipselect	= vision_spi_chipselects,
+	.num_chipselect	= ARRAY_SIZE(vision_spi_chipselects),
 	.use_dma	= 1,
 };
 
diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c
index 699157759120..c03bf28d8bbc 100644
--- a/arch/arm/mach-imx/mmdc.c
+++ b/arch/arm/mach-imx/mmdc.c
@@ -60,7 +60,6 @@
 
 #define to_mmdc_pmu(p) container_of(p, struct mmdc_pmu, pmu)
 
-static enum cpuhp_state cpuhp_mmdc_state;
 static int ddr_type;
 
 struct fsl_mmdc_devtype_data {
@@ -82,6 +81,7 @@ static const struct of_device_id imx_mmdc_dt_ids[] = {
 
 #ifdef CONFIG_PERF_EVENTS
 
+static enum cpuhp_state cpuhp_mmdc_state;
 static DEFINE_IDA(mmdc_ida);
 
 PMU_EVENT_ATTR_STRING(total-cycles, mmdc_pmu_total_cycles, "event=0x00")
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 76b0454ddc49..0598630c1778 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -130,17 +130,16 @@ static int __init omap2_set_init_voltage(char *vdd_name, char *clk_name,
 	freq = clk_get_rate(clk);
 	clk_put(clk);
 
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(dev, &freq);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		pr_err("%s: unable to find boot up OPP for vdd_%s\n",
 			__func__, vdd_name);
 		goto exit;
 	}
 
 	bootup_volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
+
 	if (!bootup_volt) {
 		pr_err("%s: unable to find voltage corresponding to the bootup OPP for vdd_%s\n",
 		       __func__, vdd_name);
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index 8a3c409294bf..d452a49c0396 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -17,6 +17,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
+#include <linux/leds.h>
 #include <linux/sched.h>
 #include <linux/bitops.h>
 #include <linux/fb.h>
diff --git a/arch/arm/mach-pxa/colibri-pxa270-income.c b/arch/arm/mach-pxa/colibri-pxa270-income.c
index 8cff770e6a00..d7cf47d03618 100644
--- a/arch/arm/mach-pxa/colibri-pxa270-income.c
+++ b/arch/arm/mach-pxa/colibri-pxa270-income.c
@@ -17,6 +17,7 @@
 #include <linux/gpio.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/leds.h>
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index 183cd3446f25..7270f0db3432 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -19,6 +19,7 @@
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/interrupt.h>
+#include <linux/leds.h>
 #include <linux/mmc/host.h>
 #include <linux/mtd/physmap.h>
 #include <linux/pm.h>
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index ea78bc5c4198..3dd13b44c311 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -16,6 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/interrupt.h>
+#include <linux/leds.h>
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/bitops.h>
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index c006ee902a8f..70ab3ad28237 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -15,6 +15,7 @@
 #include <linux/irq.h>
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
+#include <linux/leds.h>
 #include <linux/gpio.h>
 #include <linux/usb/gpio_vbus.h>
 #include <linux/mtd/mtd.h>
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index 3b94ecfb9426..ecbcaee5a2d5 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -13,6 +13,7 @@
 
 #include <linux/cpufreq.h>
 #include <linux/interrupt.h>
+#include <linux/leds.h>
 #include <linux/irq.h>
 #include <linux/pm.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-pxa/zylonite.c b/arch/arm/mach-pxa/zylonite.c
index 3642389b301a..4268552d600d 100644
--- a/arch/arm/mach-pxa/zylonite.c
+++ b/arch/arm/mach-pxa/zylonite.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
+#include <linux/leds.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 2bb4b09f079e..ad7d604ff001 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -57,6 +57,7 @@ config ARCH_R7S72100
 	select PM
 	select PM_GENERIC_DOMAINS
 	select SYS_SUPPORTS_SH_MTU2
+	select RENESAS_OSTM
 
 config ARCH_R8A73A4
 	bool "R-Mobile APE6 (R8A73A40)"
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ab7710002ba6..82d3e79ec82b 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1171,6 +1171,25 @@ core_initcall(dma_debug_do_init);
 
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 
+static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs)
+{
+	int prot = 0;
+
+	if (attrs & DMA_ATTR_PRIVILEGED)
+		prot |= IOMMU_PRIV;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+		return prot | IOMMU_READ | IOMMU_WRITE;
+	case DMA_TO_DEVICE:
+		return prot | IOMMU_READ;
+	case DMA_FROM_DEVICE:
+		return prot | IOMMU_WRITE;
+	default:
+		return prot;
+	}
+}
+
 /* IOMMU */
 
 static int extend_iommu_mapping(struct dma_iommu_mapping *mapping);
@@ -1394,7 +1413,8 @@ __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
  * Create a mapping in device IO address space for specified pages
  */
 static dma_addr_t
-__iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
+__iommu_create_mapping(struct device *dev, struct page **pages, size_t size,
+		       unsigned long attrs)
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
@@ -1419,7 +1439,7 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
 
 		len = (j - i) << PAGE_SHIFT;
 		ret = iommu_map(mapping->domain, iova, phys, len,
-				IOMMU_READ|IOMMU_WRITE);
+				__dma_info_to_prot(DMA_BIDIRECTIONAL, attrs));
 		if (ret < 0)
 			goto fail;
 		iova += len;
@@ -1476,7 +1496,8 @@ static struct page **__iommu_get_pages(void *cpu_addr, unsigned long attrs)
 }
 
 static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
-				  dma_addr_t *handle, int coherent_flag)
+				  dma_addr_t *handle, int coherent_flag,
+				  unsigned long attrs)
 {
 	struct page *page;
 	void *addr;
@@ -1488,7 +1509,7 @@ static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
 	if (!addr)
 		return NULL;
 
-	*handle = __iommu_create_mapping(dev, &page, size);
+	*handle = __iommu_create_mapping(dev, &page, size, attrs);
 	if (*handle == DMA_ERROR_CODE)
 		goto err_mapping;
 
@@ -1522,7 +1543,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 
 	if (coherent_flag  == COHERENT || !gfpflags_allow_blocking(gfp))
 		return __iommu_alloc_simple(dev, size, gfp, handle,
-					    coherent_flag);
+					    coherent_flag, attrs);
 
 	/*
 	 * Following is a work-around (a.k.a. hack) to prevent pages
@@ -1537,7 +1558,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	if (!pages)
 		return NULL;
 
-	*handle = __iommu_create_mapping(dev, pages, size);
+	*handle = __iommu_create_mapping(dev, pages, size, attrs);
 	if (*handle == DMA_ERROR_CODE)
 		goto err_buffer;
 
@@ -1672,27 +1693,6 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 					 GFP_KERNEL);
 }
 
-static int __dma_direction_to_prot(enum dma_data_direction dir)
-{
-	int prot;
-
-	switch (dir) {
-	case DMA_BIDIRECTIONAL:
-		prot = IOMMU_READ | IOMMU_WRITE;
-		break;
-	case DMA_TO_DEVICE:
-		prot = IOMMU_READ;
-		break;
-	case DMA_FROM_DEVICE:
-		prot = IOMMU_WRITE;
-		break;
-	default:
-		prot = 0;
-	}
-
-	return prot;
-}
-
 /*
  * Map a part of the scatter-gather list into contiguous io address space
  */
@@ -1722,7 +1722,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		if (!is_coherent && (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
 			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 
-		prot = __dma_direction_to_prot(dir);
+		prot = __dma_info_to_prot(dir, attrs);
 
 		ret = iommu_map(mapping->domain, iova, phys, len, prot);
 		if (ret < 0)
@@ -1930,7 +1930,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	if (dma_addr == DMA_ERROR_CODE)
 		return dma_addr;
 
-	prot = __dma_direction_to_prot(dir);
+	prot = __dma_info_to_prot(dir, attrs);
 
 	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot);
 	if (ret < 0)
@@ -2036,7 +2036,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev,
 	if (dma_addr == DMA_ERROR_CODE)
 		return dma_addr;
 
-	prot = __dma_direction_to_prot(dir) | IOMMU_MMIO;
+	prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO;
 
 	ret = iommu_map(mapping->domain, dma_addr, addr, len, prot);
 	if (ret < 0)
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 3a2e678b8d30..0122ad1a6027 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -610,9 +610,9 @@ static int __init early_abort_handler(unsigned long addr, unsigned int fsr,
 
 void __init early_abt_enable(void)
 {
-	fsr_info[22].fn = early_abort_handler;
+	fsr_info[FSR_FS_AEA].fn = early_abort_handler;
 	local_abt_enable();
-	fsr_info[22].fn = do_bad;
+	fsr_info[FSR_FS_AEA].fn = do_bad;
 }
 
 #ifndef CONFIG_ARM_LPAE
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index 67532f242271..afc1f84e763b 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -11,11 +11,15 @@
 #define FSR_FS5_0		(0x3f)
 
 #ifdef CONFIG_ARM_LPAE
+#define FSR_FS_AEA		17
+
 static inline int fsr_fs(unsigned int fsr)
 {
 	return fsr & FSR_FS5_0;
 }
 #else
+#define FSR_FS_AEA		22
+
 static inline int fsr_fs(unsigned int fsr)
 {
 	return (fsr & FSR_FS3_0) | (fsr & FSR_FS4) >> 6;
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 111742126897..f7dfd6d58659 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -96,7 +96,7 @@ config ARM64
 	select HAVE_RCU_TABLE_FREE
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KPROBES
-	select HAVE_KRETPROBES if HAVE_KPROBES
+	select HAVE_KRETPROBES
 	select IOMMU_DMA if IOMMU_SUPPORT
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index eada0b58ba1c..0cbe24b49710 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -55,6 +55,24 @@
 	#address-cells = <2>;
 	#size-cells = <2>;
 
+	reserved-memory {
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges;
+
+		/* 16 MiB reserved for Hardware ROM Firmware */
+		hwrom_reserved: hwrom@0 {
+			reg = <0x0 0x0 0x0 0x1000000>;
+			no-map;
+		};
+
+		/* 2 MiB reserved for ARM Trusted Firmware (BL31) */
+		secmon_reserved: secmon@10000000 {
+			reg = <0x0 0x10000000 0x0 0x200000>;
+			no-map;
+		};
+	};
+
 	cpus {
 		#address-cells = <0x2>;
 		#size-cells = <0x0>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
index 5d28e1cdc998..c59403adb387 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts
@@ -151,6 +151,18 @@
 	status = "okay";
 	pinctrl-0 = <&eth_rgmii_pins>;
 	pinctrl-names = "default";
+	phy-handle = <&eth_phy0>;
+
+	mdio {
+		compatible = "snps,dwmac-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		eth_phy0: ethernet-phy@0 {
+			reg = <0>;
+			eee-broken-1000t;
+		};
+	};
 };
 
 &ir {
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index c53dbeae79f2..838dad5c209f 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -193,15 +193,16 @@ AES_ENTRY(aes_cbc_encrypt)
 	cbz		w6, .Lcbcencloop
 
 	ld1		{v0.16b}, [x5]			/* get iv */
-	enc_prepare	w3, x2, x5
+	enc_prepare	w3, x2, x6
 
 .Lcbcencloop:
 	ld1		{v1.16b}, [x1], #16		/* get next pt block */
 	eor		v0.16b, v0.16b, v1.16b		/* ..and xor with iv */
-	encrypt_block	v0, w3, x2, x5, w6
+	encrypt_block	v0, w3, x2, x6, w7
 	st1		{v0.16b}, [x0], #16
 	subs		w4, w4, #1
 	bne		.Lcbcencloop
+	st1		{v0.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_encrypt)
 
@@ -211,7 +212,7 @@ AES_ENTRY(aes_cbc_decrypt)
 	cbz		w6, .LcbcdecloopNx
 
 	ld1		{v7.16b}, [x5]			/* get iv */
-	dec_prepare	w3, x2, x5
+	dec_prepare	w3, x2, x6
 
 .LcbcdecloopNx:
 #if INTERLEAVE >= 2
@@ -248,7 +249,7 @@ AES_ENTRY(aes_cbc_decrypt)
 .Lcbcdecloop:
 	ld1		{v1.16b}, [x1], #16		/* get next ct block */
 	mov		v0.16b, v1.16b			/* ...and copy to v0 */
-	decrypt_block	v0, w3, x2, x5, w6
+	decrypt_block	v0, w3, x2, x6, w7
 	eor		v0.16b, v0.16b, v7.16b		/* xor with iv => pt */
 	mov		v7.16b, v1.16b			/* ct is next iv */
 	st1		{v0.16b}, [x0], #16
@@ -256,6 +257,7 @@ AES_ENTRY(aes_cbc_decrypt)
 	bne		.Lcbcdecloop
 .Lcbcdecout:
 	FRAME_POP
+	st1		{v7.16b}, [x5]			/* return iv */
 	ret
 AES_ENDPROC(aes_cbc_decrypt)
 
@@ -267,24 +269,15 @@ AES_ENDPROC(aes_cbc_decrypt)
 
 AES_ENTRY(aes_ctr_encrypt)
 	FRAME_PUSH
-	cbnz		w6, .Lctrfirst		/* 1st time around? */
-	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
-	rev		x5, x5
-#if INTERLEAVE >= 2
-	cmn		w5, w4			/* 32 bit overflow? */
-	bcs		.Lctrinc
-	add		x5, x5, #1		/* increment BE ctr */
-	b		.LctrincNx
-#else
-	b		.Lctrinc
-#endif
-.Lctrfirst:
+	cbz		w6, .Lctrnotfirst	/* 1st time around? */
 	enc_prepare	w3, x2, x6
 	ld1		{v4.16b}, [x5]
-	umov		x5, v4.d[1]		/* keep swabbed ctr in reg */
-	rev		x5, x5
+
+.Lctrnotfirst:
+	umov		x8, v4.d[1]		/* keep swabbed ctr in reg */
+	rev		x8, x8
 #if INTERLEAVE >= 2
-	cmn		w5, w4			/* 32 bit overflow? */
+	cmn		w8, w4			/* 32 bit overflow? */
 	bcs		.Lctrloop
 .LctrloopNx:
 	subs		w4, w4, #INTERLEAVE
@@ -292,11 +285,11 @@ AES_ENTRY(aes_ctr_encrypt)
 #if INTERLEAVE == 2
 	mov		v0.8b, v4.8b
 	mov		v1.8b, v4.8b
-	rev		x7, x5
-	add		x5, x5, #1
+	rev		x7, x8
+	add		x8, x8, #1
 	ins		v0.d[1], x7
-	rev		x7, x5
-	add		x5, x5, #1
+	rev		x7, x8
+	add		x8, x8, #1
 	ins		v1.d[1], x7
 	ld1		{v2.16b-v3.16b}, [x1], #32	/* get 2 input blocks */
 	do_encrypt_block2x
@@ -305,7 +298,7 @@ AES_ENTRY(aes_ctr_encrypt)
 	st1		{v0.16b-v1.16b}, [x0], #32
 #else
 	ldr		q8, =0x30000000200000001	/* addends 1,2,3[,0] */
-	dup		v7.4s, w5
+	dup		v7.4s, w8
 	mov		v0.16b, v4.16b
 	add		v7.4s, v7.4s, v8.4s
 	mov		v1.16b, v4.16b
@@ -323,18 +316,12 @@ AES_ENTRY(aes_ctr_encrypt)
 	eor		v2.16b, v7.16b, v2.16b
 	eor		v3.16b, v5.16b, v3.16b
 	st1		{v0.16b-v3.16b}, [x0], #64
-	add		x5, x5, #INTERLEAVE
+	add		x8, x8, #INTERLEAVE
 #endif
-	cbz		w4, .LctroutNx
-.LctrincNx:
-	rev		x7, x5
+	rev		x7, x8
 	ins		v4.d[1], x7
+	cbz		w4, .Lctrout
 	b		.LctrloopNx
-.LctroutNx:
-	sub		x5, x5, #1
-	rev		x7, x5
-	ins		v4.d[1], x7
-	b		.Lctrout
 .Lctr1x:
 	adds		w4, w4, #INTERLEAVE
 	beq		.Lctrout
@@ -342,30 +329,39 @@ AES_ENTRY(aes_ctr_encrypt)
 .Lctrloop:
 	mov		v0.16b, v4.16b
 	encrypt_block	v0, w3, x2, x6, w7
+
+	adds		x8, x8, #1		/* increment BE ctr */
+	rev		x7, x8
+	ins		v4.d[1], x7
+	bcs		.Lctrcarry		/* overflow? */
+
+.Lctrcarrydone:
 	subs		w4, w4, #1
 	bmi		.Lctrhalfblock		/* blocks < 0 means 1/2 block */
 	ld1		{v3.16b}, [x1], #16
 	eor		v3.16b, v0.16b, v3.16b
 	st1		{v3.16b}, [x0], #16
-	beq		.Lctrout
-.Lctrinc:
-	adds		x5, x5, #1		/* increment BE ctr */
-	rev		x7, x5
-	ins		v4.d[1], x7
-	bcc		.Lctrloop		/* no overflow? */
-	umov		x7, v4.d[0]		/* load upper word of ctr  */
-	rev		x7, x7			/* ... to handle the carry */
-	add		x7, x7, #1
-	rev		x7, x7
-	ins		v4.d[0], x7
-	b		.Lctrloop
+	bne		.Lctrloop
+
+.Lctrout:
+	st1		{v4.16b}, [x5]		/* return next CTR value */
+	FRAME_POP
+	ret
+
 .Lctrhalfblock:
 	ld1		{v3.8b}, [x1]
 	eor		v3.8b, v0.8b, v3.8b
 	st1		{v3.8b}, [x0]
-.Lctrout:
 	FRAME_POP
 	ret
+
+.Lctrcarry:
+	umov		x7, v4.d[0]		/* load upper word of ctr  */
+	rev		x7, x7			/* ... to handle the carry */
+	add		x7, x7, #1
+	rev		x7, x7
+	ins		v4.d[0], x7
+	b		.Lctrcarrydone
 AES_ENDPROC(aes_ctr_encrypt)
 	.ltorg
 
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 8365a84c2640..a12f1afc95a3 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -1,6 +1,5 @@
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index eaa5bbe3fa87..b4b34004a21e 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -29,41 +29,29 @@
 
 #include <clocksource/arm_arch_timer.h>
 
-#if IS_ENABLED(CONFIG_FSL_ERRATUM_A008585)
+#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND)
 extern struct static_key_false arch_timer_read_ool_enabled;
-#define needs_fsl_a008585_workaround() \
+#define needs_unstable_timer_counter_workaround() \
 	static_branch_unlikely(&arch_timer_read_ool_enabled)
 #else
-#define needs_fsl_a008585_workaround()  false
+#define needs_unstable_timer_counter_workaround()  false
 #endif
 
-u32 __fsl_a008585_read_cntp_tval_el0(void);
-u32 __fsl_a008585_read_cntv_tval_el0(void);
-u64 __fsl_a008585_read_cntvct_el0(void);
 
-/*
- * The number of retries is an arbitrary value well beyond the highest number
- * of iterations the loop has been observed to take.
- */
-#define __fsl_a008585_read_reg(reg) ({			\
-	u64 _old, _new;					\
-	int _retries = 200;				\
-							\
-	do {						\
-		_old = read_sysreg(reg);		\
-		_new = read_sysreg(reg);		\
-		_retries--;				\
-	} while (unlikely(_old != _new) && _retries);	\
-							\
-	WARN_ON_ONCE(!_retries);			\
-	_new;						\
-})
+struct arch_timer_erratum_workaround {
+	const char *id;		/* Indicate the Erratum ID */
+	u32 (*read_cntp_tval_el0)(void);
+	u32 (*read_cntv_tval_el0)(void);
+	u64 (*read_cntvct_el0)(void);
+};
+
+extern const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround;
 
 #define arch_timer_reg_read_stable(reg) 		\
 ({							\
 	u64 _val;					\
-	if (needs_fsl_a008585_workaround())		\
-		_val = __fsl_a008585_read_##reg();	\
+	if (needs_unstable_timer_counter_workaround())		\
+		_val = timer_unstable_counter_workaround->read_##reg();\
 	else						\
 		_val = read_sysreg(reg);		\
 	_val;						\
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 0b6b1633017f..e7445281e534 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -50,6 +50,7 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
 
 #define efi_call_early(f, ...)		sys_table_arg->boottime->f(__VA_ARGS__)
 #define __efi_call_early(f, ...)	f(__VA_ARGS__)
+#define efi_call_runtime(f, ...)	sys_table_arg->runtime->f(__VA_ARGS__)
 #define efi_is_64bit()			(true)
 
 #define efi_call_proto(protocol, f, instance, ...)			\
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 23e9e13bd2aa..655e65f38f31 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -11,6 +11,7 @@
  * for more details.
  */
 
+#include <linux/acpi.h>
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/init.h>
@@ -209,7 +210,12 @@ static struct notifier_block init_cpu_capacity_notifier = {
 
 static int __init register_cpufreq_notifier(void)
 {
-	if (cap_parsing_failed)
+	/*
+	 * on ACPI-based systems we need to use the default cpu capacity
+	 * until we have the necessary code to parse the cpu capacity, so
+	 * skip registering cpufreq notifier.
+	 */
+	if (!acpi_disabled || cap_parsing_failed)
 		return -EINVAL;
 
 	if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index e04082700bb1..4a14b25163fb 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -558,7 +558,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 				 unsigned long attrs)
 {
 	bool coherent = is_device_dma_coherent(dev);
-	int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent);
+	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
 	size_t iosize = size;
 	void *addr;
 
@@ -712,7 +712,7 @@ static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
 				   unsigned long attrs)
 {
 	bool coherent = is_device_dma_coherent(dev);
-	int prot = dma_direction_to_prot(dir, coherent);
+	int prot = dma_info_to_prot(dir, coherent, attrs);
 	dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
 
 	if (!iommu_dma_mapping_error(dev, dev_addr) &&
@@ -770,7 +770,7 @@ static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
 		__iommu_sync_sg_for_device(dev, sgl, nelems, dir);
 
 	return iommu_dma_map_sg(dev, sgl, nelems,
-			dma_direction_to_prot(dir, coherent));
+				dma_info_to_prot(dir, coherent, attrs));
 }
 
 static void __iommu_unmap_sg_attrs(struct device *dev,
@@ -799,7 +799,6 @@ static struct dma_map_ops iommu_dma_ops = {
 	.sync_sg_for_device = __iommu_sync_sg_for_device,
 	.map_resource = iommu_dma_map_resource,
 	.unmap_resource = iommu_dma_unmap_resource,
-	.dma_supported = iommu_dma_supported,
 	.mapping_error = iommu_dma_mapping_error,
 };
 
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 241b9b9729d8..3d7ef2c17a7c 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -1,6 +1,5 @@
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += delay.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 2fb67b59d188..d6fa60b158be 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -2,7 +2,6 @@
 generic-y += auxvec.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 64465e7e2245..4e9f57433f3a 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -5,7 +5,6 @@ generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index 1778805f6380..9f19e19bff9d 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -4,7 +4,6 @@ generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
 generic-y += cmpxchg.h
-generic-y += cputime.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += errno.h
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 1fa084cf1a43..0f5b0d5d313c 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -1,6 +1,5 @@
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
diff --git a/arch/frv/include/asm/atomic.h b/arch/frv/include/asm/atomic.h
index 1c2a5e264fc7..e93c9494503a 100644
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -139,7 +139,7 @@ static inline void atomic64_dec(atomic64_t *v)
 #define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i), (v)) == 0)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_and_test(v)	(atomic64_inc_return((v)) == 0)
-
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&(v)->counter, old, new))
 #define atomic_xchg(v, new)		(xchg(&(v)->counter, new))
@@ -161,6 +161,39 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
+static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
+{
+	long long c, old;
+
+	c = atomic64_read(v);
+	for (;;) {
+		if (unlikely(c == u))
+			break;
+		old = atomic64_cmpxchg(v, c, c + i);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return c != u;
+}
+
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long c, old, dec;
+
+	c = atomic64_read(v);
+	for (;;) {
+		dec = c - 1;
+		if (unlikely(dec < 0))
+			break;
+		old = atomic64_cmpxchg((v), c, dec);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+		return dec;
+}
+
 #define ATOMIC_OP(op)							\
 static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 {									\
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 373cb23301e3..5efd0c87f3c0 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -5,7 +5,6 @@ generic-y += bugs.h
 generic-y += cacheflush.h
 generic-y += checksum.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += device.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index db8ddabc6bd2..a43a7c90e4af 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -6,7 +6,6 @@ generic-y += barrier.h
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/ia64/include/asm/cputime.h b/arch/ia64/include/asm/cputime.h
index e2d3f5baf265..3d665c0627a8 100644
--- a/arch/ia64/include/asm/cputime.h
+++ b/arch/ia64/include/asm/cputime.h
@@ -18,11 +18,7 @@
 #ifndef __IA64_CPUTIME_H
 #define __IA64_CPUTIME_H
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-# include <asm-generic/cputime.h>
-#else
-# include <asm/processor.h>
-# include <asm-generic/cputime_nsecs.h>
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 extern void arch_vtime_task_switch(struct task_struct *tsk);
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h
index c7026429816b..8742d741d19a 100644
--- a/arch/ia64/include/asm/thread_info.h
+++ b/arch/ia64/include/asm/thread_info.h
@@ -27,6 +27,12 @@ struct thread_info {
 	mm_segment_t addr_limit;	/* user-level address space limit */
 	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	__u64 utime;
+	__u64 stime;
+	__u64 gtime;
+	__u64 hardirq_time;
+	__u64 softirq_time;
+	__u64 idle_time;
 	__u64 ac_stamp;
 	__u64 ac_leave;
 	__u64 ac_stime;
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 9273e034b730..7508c306aa9e 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -887,7 +887,8 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 }
 
 /* wrapper to silence section mismatch warning */
-int __ref acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu)
+int __ref acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id,
+		       int *pcpu)
 {
 	return _acpi_map_lsapic(handle, physid, pcpu);
 }
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index c9b5e942f671..3204fddc439c 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -1031,7 +1031,7 @@ GLOBAL_ENTRY(ia64_native_sched_clock)
 END(ia64_native_sched_clock)
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-GLOBAL_ENTRY(cycle_to_cputime)
+GLOBAL_ENTRY(cycle_to_nsec)
 	alloc r16=ar.pfs,1,0,0,0
 	addl r8=THIS_CPU(ia64_cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
 	;;
@@ -1047,7 +1047,7 @@ GLOBAL_ENTRY(cycle_to_cputime)
 	;;
 	shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
 	br.ret.sptk.many rp
-END(cycle_to_cputime)
+END(cycle_to_nsec)
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_IA64_BRL_EMU
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 7ec7acc844c2..c483ece3eb84 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -619,6 +619,8 @@ setup_arch (char **cmdline_p)
 	check_sal_cache_flush();
 #endif
 	paging_init();
+
+	clear_sched_clock_stable();
 }
 
 /*
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 71775b95d6cc..faa116822c4c 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -21,6 +21,7 @@
 #include <linux/timex.h>
 #include <linux/timekeeper_internal.h>
 #include <linux/platform_device.h>
+#include <linux/cputime.h>
 
 #include <asm/machvec.h>
 #include <asm/delay.h>
@@ -59,18 +60,43 @@ static struct clocksource *itc_clocksource;
 
 #include <linux/kernel_stat.h>
 
-extern cputime_t cycle_to_cputime(u64 cyc);
+extern u64 cycle_to_nsec(u64 cyc);
 
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
 {
-	cputime_t delta_utime;
 	struct thread_info *ti = task_thread_info(tsk);
+	u64 delta;
 
-	if (ti->ac_utime) {
-		delta_utime = cycle_to_cputime(ti->ac_utime);
-		account_user_time(tsk, delta_utime);
-		ti->ac_utime = 0;
+	if (ti->utime)
+		account_user_time(tsk, cycle_to_nsec(ti->utime));
+
+	if (ti->gtime)
+		account_guest_time(tsk, cycle_to_nsec(ti->gtime));
+
+	if (ti->idle_time)
+		account_idle_time(cycle_to_nsec(ti->idle_time));
+
+	if (ti->stime) {
+		delta = cycle_to_nsec(ti->stime);
+		account_system_index_time(tsk, delta, CPUTIME_SYSTEM);
+	}
+
+	if (ti->hardirq_time) {
+		delta = cycle_to_nsec(ti->hardirq_time);
+		account_system_index_time(tsk, delta, CPUTIME_IRQ);
+	}
+
+	if (ti->softirq_time) {
+		delta = cycle_to_nsec(ti->softirq_time));
+		account_system_index_time(tsk, delta, CPUTIME_SOFTIRQ);
 	}
+
+	ti->utime = 0;
+	ti->gtime = 0;
+	ti->idle_time = 0;
+	ti->stime = 0;
+	ti->hardirq_time = 0;
+	ti->softirq_time = 0;
 }
 
 /*
@@ -83,7 +109,7 @@ void arch_vtime_task_switch(struct task_struct *prev)
 	struct thread_info *pi = task_thread_info(prev);
 	struct thread_info *ni = task_thread_info(current);
 
-	pi->ac_stamp = ni->ac_stamp;
+	ni->ac_stamp = pi->ac_stamp;
 	ni->ac_stime = ni->ac_utime = 0;
 }
 
@@ -91,18 +117,15 @@ void arch_vtime_task_switch(struct task_struct *prev)
  * Account time for a transition between system, hard irq or soft irq state.
  * Note that this function is called with interrupts enabled.
  */
-static cputime_t vtime_delta(struct task_struct *tsk)
+static __u64 vtime_delta(struct task_struct *tsk)
 {
 	struct thread_info *ti = task_thread_info(tsk);
-	cputime_t delta_stime;
-	__u64 now;
+	__u64 now, delta_stime;
 
 	WARN_ON_ONCE(!irqs_disabled());
 
 	now = ia64_get_itc();
-
-	delta_stime = cycle_to_cputime(ti->ac_stime + (now - ti->ac_stamp));
-	ti->ac_stime = 0;
+	delta_stime = now - ti->ac_stamp;
 	ti->ac_stamp = now;
 
 	return delta_stime;
@@ -110,15 +133,25 @@ static cputime_t vtime_delta(struct task_struct *tsk)
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	cputime_t delta = vtime_delta(tsk);
-
-	account_system_time(tsk, 0, delta);
+	struct thread_info *ti = task_thread_info(tsk);
+	__u64 stime = vtime_delta(tsk);
+
+	if ((tsk->flags & PF_VCPU) && !irq_count())
+		ti->gtime += stime;
+	else if (hardirq_count())
+		ti->hardirq_time += stime;
+	else if (in_serving_softirq())
+		ti->softirq_time += stime;
+	else
+		ti->stime += stime;
 }
 EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
-	account_idle_time(vtime_delta(tsk));
+	struct thread_info *ti = task_thread_info(tsk);
+
+	ti->idle_time += vtime_delta(tsk);
 }
 
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index 860e440611c9..652100b64a71 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -1,6 +1,5 @@
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += kvm_para.h
diff --git a/arch/m68k/68000/m68328.c b/arch/m68k/68000/m68328.c
index e53caf4c3bfb..419751b15ec8 100644
--- a/arch/m68k/68000/m68328.c
+++ b/arch/m68k/68000/m68328.c
@@ -45,9 +45,9 @@ void m68328_reset (void)
 
 void __init config_BSP(char *command, int len)
 {
-  printk(KERN_INFO "\n68328 support D. Jeff Dionne <jeff@uclinux.org>\n");
-  printk(KERN_INFO "68328 support Kenneth Albanowski <kjahds@kjshds.com>\n");
-  printk(KERN_INFO "68328/Pilot support Bernhard Kuhn <kuhn@lpr.e-technik.tu-muenchen.de>\n");
+  pr_info("68328 support D. Jeff Dionne <jeff@uclinux.org>\n");
+  pr_info("68328 support Kenneth Albanowski <kjahds@kjshds.com>\n");
+  pr_info("68328/Pilot support Bernhard Kuhn <kuhn@lpr.e-technik.tu-muenchen.de>\n");
 
   mach_hwclk = m68328_hwclk;
   mach_reset = m68328_reset;
diff --git a/arch/m68k/68000/m68EZ328.c b/arch/m68k/68000/m68EZ328.c
index e6ab321f93f8..6a309a3cfbfc 100644
--- a/arch/m68k/68000/m68EZ328.c
+++ b/arch/m68k/68000/m68EZ328.c
@@ -57,12 +57,12 @@ void __init config_BSP(char *command, int len)
 {
   unsigned char *p;
 
-  printk(KERN_INFO "\n68EZ328 DragonBallEZ support (C) 1999 Rt-Control, Inc\n");
+  pr_info("68EZ328 DragonBallEZ support (C) 1999 Rt-Control, Inc\n");
 
 #ifdef CONFIG_UCSIMM
-  printk(KERN_INFO "uCsimm serial string [%s]\n",getserialnum());
+  pr_info("uCsimm serial string [%s]\n", getserialnum());
   p = cs8900a_hwaddr = gethwaddr(0);
-  printk(KERN_INFO "uCsimm hwaddr %pM\n", p);
+  pr_info("uCsimm hwaddr %pM\n", p);
 
   p = getbenv("APPEND");
   if (p) strcpy(p,command);
diff --git a/arch/m68k/68000/m68VZ328.c b/arch/m68k/68000/m68VZ328.c
index 1154bdb220a0..81b5491685a4 100644
--- a/arch/m68k/68000/m68VZ328.c
+++ b/arch/m68k/68000/m68VZ328.c
@@ -150,9 +150,9 @@ static void __init init_hardware(char *command, int size)
 {
 	char *p;
 
-	printk(KERN_INFO "uCdimm serial string [%s]\n", getserialnum());
+	pr_info("uCdimm serial string [%s]\n", getserialnum());
 	p = cs8900a_hwaddr = gethwaddr(0);
-	printk(KERN_INFO "uCdimm hwaddr %pM\n", p);
+	pr_info("uCdimm hwaddr %pM\n", p);
 	p = getbenv("APPEND");
 	if (p)
 		strcpy(p, command);
@@ -177,7 +177,7 @@ static void __init init_hardware(char *command, int size)
 
 void __init config_BSP(char *command, int size)
 {
-	printk(KERN_INFO "68VZ328 DragonBallVZ support (c) 2001 Lineo, Inc.\n");
+	pr_info("68VZ328 DragonBallVZ support (c) 2001 Lineo, Inc.\n");
 
 	init_hardware(command, size);
 
diff --git a/arch/m68k/atari/atakeyb.c b/arch/m68k/atari/atakeyb.c
index 264db1126803..37091898adb3 100644
--- a/arch/m68k/atari/atakeyb.c
+++ b/arch/m68k/atari/atakeyb.c
@@ -149,7 +149,7 @@ repeat:
 	if (acia_stat & ACIA_OVRN) {
 		/* a very fast typist or a slow system, give a warning */
 		/* ...happens often if interrupts were disabled for too long */
-		printk(KERN_DEBUG "Keyboard overrun\n");
+		pr_debug("Keyboard overrun\n");
 		scancode = acia.key_data;
 		if (ikbd_self_test)
 			/* During self test, don't do resyncing, just process the code */
@@ -228,14 +228,14 @@ repeat:
 					keytyp = KTYP(keyval) - 0xf0;
 					keyval = KVAL(keyval);
 
-					printk(KERN_WARNING "Key with scancode %d ", scancode);
+					pr_warn("Key with scancode %d ", scancode);
 					if (keytyp == KT_LATIN || keytyp == KT_LETTER) {
 						if (keyval < ' ')
-							printk("('^%c') ", keyval + '@');
+							pr_cont("('^%c') ", keyval + '@');
 						else
-							printk("('%c') ", keyval);
+							pr_cont("('%c') ", keyval);
 					}
-					printk("is broken -- will be ignored.\n");
+					pr_cont("is broken -- will be ignored.\n");
 					break;
 				} else if (test_bit(scancode, broken_keys))
 					break;
@@ -299,7 +299,7 @@ repeat:
 #endif
 
 	if (acia_stat & (ACIA_FE | ACIA_PE)) {
-		printk("Error in keyboard communication\n");
+		pr_err("Error in keyboard communication\n");
 	}
 
 	/* handle_scancode() can take a lot of time, so check again if
@@ -553,7 +553,7 @@ int atari_keyb_init(void)
 		barrier();
 	/* if not incremented: no 0xf1 received */
 	if (ikbd_self_test == 1)
-		printk(KERN_ERR "WARNING: keyboard self test failed!\n");
+		pr_err("Keyboard self test failed!\n");
 	ikbd_self_test = 0;
 
 	ikbd_mouse_disable();
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index e328eaf816e3..565c6f06ab0b 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -234,44 +234,44 @@ void __init config_atari(void)
 	 * Determine hardware present
 	 */
 
-	printk("Atari hardware found: ");
+	pr_info("Atari hardware found:");
 	if (MACH_IS_MEDUSA) {
 		/* There's no Atari video hardware on the Medusa, but all the
 		 * addresses below generate a DTACK so no bus error occurs! */
 	} else if (hwreg_present(f030_xreg)) {
 		ATARIHW_SET(VIDEL_SHIFTER);
-		printk("VIDEL ");
+		pr_cont(" VIDEL");
 		/* This is a temporary hack: If there is Falcon video
 		 * hardware, we assume that the ST-DMA serves SCSI instead of
 		 * ACSI. In the future, there should be a better method for
 		 * this...
 		 */
 		ATARIHW_SET(ST_SCSI);
-		printk("STDMA-SCSI ");
+		pr_cont(" STDMA-SCSI");
 	} else if (hwreg_present(tt_palette)) {
 		ATARIHW_SET(TT_SHIFTER);
-		printk("TT_SHIFTER ");
+		pr_cont(" TT_SHIFTER");
 	} else if (hwreg_present(&shifter.bas_hi)) {
 		if (hwreg_present(&shifter.bas_lo) &&
 		    (shifter.bas_lo = 0x0aau, shifter.bas_lo == 0x0aau)) {
 			ATARIHW_SET(EXTD_SHIFTER);
-			printk("EXTD_SHIFTER ");
+			pr_cont(" EXTD_SHIFTER");
 		} else {
 			ATARIHW_SET(STND_SHIFTER);
-			printk("STND_SHIFTER ");
+			pr_cont(" STND_SHIFTER");
 		}
 	}
 	if (hwreg_present(&st_mfp.par_dt_reg)) {
 		ATARIHW_SET(ST_MFP);
-		printk("ST_MFP ");
+		pr_cont(" ST_MFP");
 	}
 	if (hwreg_present(&tt_mfp.par_dt_reg)) {
 		ATARIHW_SET(TT_MFP);
-		printk("TT_MFP ");
+		pr_cont(" TT_MFP");
 	}
 	if (hwreg_present(&tt_scsi_dma.dma_addr_hi)) {
 		ATARIHW_SET(SCSI_DMA);
-		printk("TT_SCSI_DMA ");
+		pr_cont(" TT_SCSI_DMA");
 	}
 	/*
 	 * The ST-DMA address registers aren't readable
@@ -284,27 +284,27 @@ void __init config_atari(void)
 	     (st_dma.dma_vhi = 0xaa) && (st_dma.dma_hi = 0x55) &&
 	     st_dma.dma_vhi == 0xaa && st_dma.dma_hi == 0x55)) {
 		ATARIHW_SET(EXTD_DMA);
-		printk("EXTD_DMA ");
+		pr_cont(" EXTD_DMA");
 	}
 	if (hwreg_present(&tt_scsi.scsi_data)) {
 		ATARIHW_SET(TT_SCSI);
-		printk("TT_SCSI ");
+		pr_cont(" TT_SCSI");
 	}
 	if (hwreg_present(&sound_ym.rd_data_reg_sel)) {
 		ATARIHW_SET(YM_2149);
-		printk("YM2149 ");
+		pr_cont(" YM2149");
 	}
 	if (!MACH_IS_MEDUSA && hwreg_present(&tt_dmasnd.ctrl)) {
 		ATARIHW_SET(PCM_8BIT);
-		printk("PCM ");
+		pr_cont(" PCM");
 	}
 	if (hwreg_present(&falcon_codec.unused5)) {
 		ATARIHW_SET(CODEC);
-		printk("CODEC ");
+		pr_cont(" CODEC");
 	}
 	if (hwreg_present(&dsp56k_host_interface.icr)) {
 		ATARIHW_SET(DSP56K);
-		printk("DSP56K ");
+		pr_cont(" DSP56K");
 	}
 	if (hwreg_present(&tt_scc_dma.dma_ctrl) &&
 #if 0
@@ -316,33 +316,33 @@ void __init config_atari(void)
 #endif
 	    ) {
 		ATARIHW_SET(SCC_DMA);
-		printk("SCC_DMA ");
+		pr_cont(" SCC_DMA");
 	}
 	if (scc_test(&atari_scc.cha_a_ctrl)) {
 		ATARIHW_SET(SCC);
-		printk("SCC ");
+		pr_cont(" SCC");
 	}
 	if (scc_test(&st_escc.cha_b_ctrl)) {
 		ATARIHW_SET(ST_ESCC);
-		printk("ST_ESCC ");
+		pr_cont(" ST_ESCC");
 	}
 	if (hwreg_present(&tt_scu.sys_mask)) {
 		ATARIHW_SET(SCU);
 		/* Assume a VME bus if there's a SCU */
 		ATARIHW_SET(VME);
-		printk("VME SCU ");
+		pr_cont(" VME SCU");
 	}
 	if (hwreg_present((void *)(0xffff9210))) {
 		ATARIHW_SET(ANALOG_JOY);
-		printk("ANALOG_JOY ");
+		pr_cont(" ANALOG_JOY");
 	}
 	if (hwreg_present(blitter.halftone)) {
 		ATARIHW_SET(BLITTER);
-		printk("BLITTER ");
+		pr_cont(" BLITTER");
 	}
 	if (hwreg_present((void *)0xfff00039)) {
 		ATARIHW_SET(IDE);
-		printk("IDE ");
+		pr_cont(" IDE");
 	}
 #if 1 /* This maybe wrong */
 	if (!MACH_IS_MEDUSA && hwreg_present(&tt_microwire.data) &&
@@ -355,31 +355,31 @@ void __init config_atari(void)
 		ATARIHW_SET(MICROWIRE);
 		while (tt_microwire.mask != 0x7ff)
 			;
-		printk("MICROWIRE ");
+		pr_cont(" MICROWIRE");
 	}
 #endif
 	if (hwreg_present(&tt_rtc.regsel)) {
 		ATARIHW_SET(TT_CLK);
-		printk("TT_CLK ");
+		pr_cont(" TT_CLK");
 		mach_hwclk = atari_tt_hwclk;
 		mach_set_clock_mmss = atari_tt_set_clock_mmss;
 	}
 	if (hwreg_present(&mste_rtc.sec_ones)) {
 		ATARIHW_SET(MSTE_CLK);
-		printk("MSTE_CLK ");
+		pr_cont(" MSTE_CLK");
 		mach_hwclk = atari_mste_hwclk;
 		mach_set_clock_mmss = atari_mste_set_clock_mmss;
 	}
 	if (!MACH_IS_MEDUSA && hwreg_present(&dma_wd.fdc_speed) &&
 	    hwreg_write(&dma_wd.fdc_speed, 0)) {
 		ATARIHW_SET(FDCSPEED);
-		printk("FDC_SPEED ");
+		pr_cont(" FDC_SPEED");
 	}
 	if (!ATARIHW_PRESENT(ST_SCSI)) {
 		ATARIHW_SET(ACSI);
-		printk("ACSI ");
+		pr_cont(" ACSI");
 	}
-	printk("\n");
+	pr_cont("\n");
 
 	if (CPU_IS_040_OR_060)
 		/* Now it seems to be safe to turn of the tt0 transparent
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 611d4d9ea2bd..2cfff4765040 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -63,8 +63,8 @@ void bvme6000_reset(void)
 {
 	volatile PitRegsPtr pit = (PitRegsPtr)BVME_PIT_BASE;
 
-	printk ("\r\n\nCalled bvme6000_reset\r\n"
-			"\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r");
+	pr_info("\r\n\nCalled bvme6000_reset\r\n"
+		"\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r");
 	/* The string of returns is to delay the reset until the whole
 	 * message is output. */
 	/* Enable the watchdog, via PIT port C bit 4 */
@@ -117,8 +117,8 @@ void __init config_bvme6000(void)
     mach_reset		 = bvme6000_reset;
     mach_get_model       = bvme6000_get_model;
 
-    printk ("Board is %sconfigured as a System Controller\n",
-		*config_reg_ptr & BVME_CONFIG_SW1 ? "" : "not ");
+    pr_info("Board is %sconfigured as a System Controller\n",
+	    *config_reg_ptr & BVME_CONFIG_SW1 ? "" : "not ");
 
     /* Now do the PIT configuration */
 
diff --git a/arch/m68k/bvme6000/rtc.c b/arch/m68k/bvme6000/rtc.c
index d53c9b301f84..e4f1faffe32b 100644
--- a/arch/m68k/bvme6000/rtc.c
+++ b/arch/m68k/bvme6000/rtc.c
@@ -168,7 +168,7 @@ static int __init rtc_DP8570A_init(void)
 	if (!MACH_IS_BVME6000)
 		return -ENODEV;
 
-	printk(KERN_INFO "DP8570A Real Time Clock Driver v%s\n", RTC_VERSION);
+	pr_info("DP8570A Real Time Clock Driver v%s\n", RTC_VERSION);
 	return misc_register(&rtc_dev);
 }
 module_init(rtc_DP8570A_init);
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index b98acd15ca22..048bf076f7df 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -66,6 +66,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -76,10 +77,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -95,6 +96,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -105,11 +107,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -176,6 +180,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -184,8 +189,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -212,8 +219,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -294,6 +303,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
 CONFIG_PARPORT_AMIGA=m
@@ -369,6 +379,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_A2065=y
 CONFIG_ARIADNE=y
@@ -390,6 +401,7 @@ CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
@@ -421,7 +433,6 @@ CONFIG_INPUT_MISC=y
 CONFIG_INPUT_M68K_BEEP=m
 # CONFIG_SERIO is not set
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_PRINTER=m
 # CONFIG_HW_RANDOM is not set
 CONFIG_NTP_PPS=y
@@ -569,6 +580,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index f80dc57e6374..d4de24963f5f 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -64,6 +64,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -74,10 +75,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -93,6 +94,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -103,11 +105,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -174,6 +178,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -182,8 +187,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -210,8 +217,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -292,6 +301,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_CRYPTOLOOP=m
@@ -350,6 +360,7 @@ CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
@@ -365,6 +376,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
@@ -391,7 +403,6 @@ CONFIG_MOUSE_SERIAL=m
 CONFIG_SERIO=m
 CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
@@ -528,6 +539,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 4e16b1821fbb..fc0fd3f871f3 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -64,6 +64,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -74,10 +75,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -93,6 +94,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -103,11 +105,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -174,6 +178,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -182,8 +187,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -210,8 +217,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -292,6 +301,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
 CONFIG_PARPORT_ATARI=m
@@ -359,6 +369,7 @@ CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
@@ -375,6 +386,7 @@ CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 CONFIG_SMC91X=y
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
@@ -404,7 +416,6 @@ CONFIG_INPUT_MISC=y
 CONFIG_INPUT_M68K_BEEP=m
 # CONFIG_SERIO is not set
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_PRINTER=m
 # CONFIG_HW_RANDOM is not set
 CONFIG_NTP_PPS=y
@@ -549,6 +560,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 2767bbf5ad61..52e984a0aa69 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -62,6 +62,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -72,10 +73,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -91,6 +92,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -101,11 +103,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -172,6 +176,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -180,8 +185,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -208,8 +215,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -290,6 +299,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_CRYPTOLOOP=m
@@ -349,6 +359,7 @@ CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
@@ -364,6 +375,7 @@ CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
@@ -389,7 +401,6 @@ CONFIG_INPUT_EVDEV=m
 # CONFIG_SERIO is not set
 CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
@@ -520,6 +531,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index d13ba309265e..aaeed4422cc9 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -64,6 +64,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -74,10 +75,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -93,6 +94,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -103,11 +105,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -174,6 +178,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -182,8 +187,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -210,8 +217,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -292,6 +301,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_CRYPTOLOOP=m
@@ -350,6 +360,7 @@ CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
@@ -366,6 +377,7 @@ CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
@@ -394,7 +406,6 @@ CONFIG_HP_SDC_RTC=m
 CONFIG_SERIO_SERPORT=m
 CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
@@ -530,6 +541,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 78b5101c1aa6..3bbc9b2f0dac 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -63,6 +63,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -73,10 +74,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -92,6 +93,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -102,11 +104,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -173,6 +177,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -181,8 +186,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -209,8 +216,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -294,6 +303,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_SWIM=m
 CONFIG_BLK_DEV_LOOP=y
@@ -366,6 +376,7 @@ CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_ARC is not set
@@ -384,6 +395,7 @@ CONFIG_MAC8390=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
@@ -413,7 +425,6 @@ CONFIG_INPUT_M68K_BEEP=m
 CONFIG_SERIO=m
 CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_PMACZILOG=y
 CONFIG_SERIAL_PMACZILOG_TTYS=y
 CONFIG_SERIAL_PMACZILOG_CONSOLE=y
@@ -552,6 +563,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 38e5bcbd0d62..8f2c0decb2f8 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -73,6 +73,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -83,10 +84,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -102,6 +103,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -112,11 +114,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -183,6 +187,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -191,8 +196,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -219,8 +226,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -304,6 +313,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
 CONFIG_PARPORT_PC=m
@@ -400,6 +410,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_A2065=y
 CONFIG_ARIADNE=y
@@ -430,6 +441,7 @@ CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 CONFIG_SMC91X=y
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
@@ -468,7 +480,6 @@ CONFIG_HP_SDC_RTC=m
 CONFIG_SERIO_Q40KBD=y
 CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_PMACZILOG=y
 CONFIG_SERIAL_PMACZILOG_TTYS=y
 CONFIG_SERIAL_PMACZILOG_CONSOLE=y
@@ -632,6 +643,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 28687192b68e..c743dd22e96f 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -61,6 +61,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -71,10 +72,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -90,6 +91,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -100,11 +102,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -171,6 +175,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -179,8 +184,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -207,8 +214,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -289,6 +298,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_CRYPTOLOOP=m
@@ -348,6 +358,7 @@ CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_ARC is not set
@@ -364,6 +375,7 @@ CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
@@ -389,7 +401,6 @@ CONFIG_INPUT_EVDEV=m
 # CONFIG_SERIO is not set
 CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
@@ -520,6 +531,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 5a5f109ab3cd..2ccaca858f05 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -62,6 +62,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -72,10 +73,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -91,6 +92,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -101,11 +103,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -172,6 +176,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -180,8 +185,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -208,8 +215,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -290,6 +299,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_CRYPTOLOOP=m
@@ -349,6 +359,7 @@ CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_ARC is not set
 # CONFIG_NET_CADENCE is not set
@@ -364,6 +375,7 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
@@ -389,7 +401,6 @@ CONFIG_INPUT_EVDEV=m
 # CONFIG_SERIO is not set
 CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
@@ -520,6 +531,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index e557c9de3fbc..5599f3fd5fcd 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -62,6 +62,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -72,10 +73,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -91,6 +92,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -101,11 +103,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -172,6 +176,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -180,8 +185,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -208,8 +215,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -290,6 +299,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_PARPORT=m
 CONFIG_PARPORT_PC=m
@@ -356,6 +366,7 @@ CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
 # CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_ARC is not set
@@ -374,6 +385,7 @@ CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
@@ -404,7 +416,6 @@ CONFIG_INPUT_M68K_BEEP=m
 CONFIG_SERIO_Q40KBD=y
 CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_PRINTER=m
 # CONFIG_HW_RANDOM is not set
 CONFIG_NTP_PPS=y
@@ -543,6 +554,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index c6a748a36daf..313bf0a562ad 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -59,6 +59,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -69,10 +70,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -88,6 +89,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -98,11 +100,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -169,6 +173,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -177,8 +182,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -205,8 +212,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -287,6 +296,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_CRYPTOLOOP=m
@@ -346,6 +356,7 @@ CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
@@ -361,6 +372,7 @@ CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SUN is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
@@ -388,7 +400,6 @@ CONFIG_KEYBOARD_SUNKBD=y
 CONFIG_MOUSE_SERIAL=m
 CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
@@ -521,6 +532,7 @@ CONFIG_TEST_BPF=m
 CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 10d60857b9a6..38b61365f769 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -59,6 +59,7 @@ CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
 CONFIG_INET_DIAG=m
 CONFIG_INET_UDP_DIAG=m
+CONFIG_INET_RAW_DIAG=m
 CONFIG_IPV6=m
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
@@ -69,10 +70,10 @@ CONFIG_IPV6_VTI=m
 CONFIG_IPV6_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NF_CONNTRACK=m
+CONFIG_NF_LOG_NETDEV=m
 CONFIG_NF_CONNTRACK_ZONES=y
 # CONFIG_NF_CONNTRACK_PROCFS is not set
 # CONFIG_NF_CT_PROTO_DCCP is not set
-CONFIG_NF_CT_PROTO_UDPLITE=m
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
@@ -88,6 +89,7 @@ CONFIG_NF_TABLES_INET=m
 CONFIG_NF_TABLES_NETDEV=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
+CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_SET_RBTREE=m
@@ -98,11 +100,13 @@ CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
 CONFIG_NFT_REDIR=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_OBJREF=m
 CONFIG_NFT_QUEUE=m
 CONFIG_NFT_QUOTA=m
 CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
+CONFIG_NFT_FIB_INET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NETFILTER_XT_SET=m
@@ -169,6 +173,7 @@ CONFIG_IP_SET_HASH_IPMARK=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_IPMAC=m
 CONFIG_IP_SET_HASH_MAC=m
 CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
@@ -177,8 +182,10 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
+CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
+CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=m
 CONFIG_NF_LOG_ARP=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
@@ -205,8 +212,10 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
+CONFIG_NFT_FIB_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
 CONFIG_NFT_REDIR_IPV6=m
@@ -287,6 +296,7 @@ CONFIG_NET_DEVLINK=m
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_FIRMWARE_IN_KERNEL is not set
+CONFIG_TEST_ASYNC_DRIVER_PROBE=m
 CONFIG_CONNECTOR=m
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_CRYPTOLOOP=m
@@ -346,6 +356,7 @@ CONFIG_MACSEC=m
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_VETH=m
+# CONFIG_NET_VENDOR_ALACRITECH is not set
 # CONFIG_NET_VENDOR_AMAZON is not set
 CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_ARC is not set
@@ -362,6 +373,7 @@ CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_ROCKER is not set
 # CONFIG_NET_VENDOR_SAMSUNG is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
@@ -388,7 +400,6 @@ CONFIG_KEYBOARD_SUNKBD=y
 CONFIG_MOUSE_SERIAL=m
 CONFIG_USERIO=m
 # CONFIG_LEGACY_PTYS is not set
-# CONFIG_DEVKMEM is not set
 # CONFIG_HW_RANDOM is not set
 CONFIG_NTP_PPS=y
 CONFIG_PPS_CLIENT_LDISC=m
@@ -522,6 +533,7 @@ CONFIG_TEST_FIRMWARE=m
 CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_EARLY_PRINTK=y
+CONFIG_ENCRYPTED_KEYS=m
 CONFIG_CRYPTO_RSA=m
 CONFIG_CRYPTO_DH=m
 CONFIG_CRYPTO_ECDH=m
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 1f2e5d31cb24..6c76d6c24b3d 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,7 +1,6 @@
 generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += device.h
 generic-y += emergency-restart.h
 generic-y += errno.h
diff --git a/arch/m68k/include/asm/bug.h b/arch/m68k/include/asm/bug.h
index ef9a2e47352f..5bc8d91d68d4 100644
--- a/arch/m68k/include/asm/bug.h
+++ b/arch/m68k/include/asm/bug.h
@@ -6,12 +6,12 @@
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 #ifndef CONFIG_SUN3
 #define BUG() do { \
-	printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
+	pr_crit("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
 	__builtin_trap(); \
 } while (0)
 #else
 #define BUG() do { \
-	printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
+	pr_crit("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
 	panic("BUG!"); \
 } while (0)
 #endif
diff --git a/arch/m68k/include/asm/floppy.h b/arch/m68k/include/asm/floppy.h
index 47365b1ccbec..c3b9ad6732fc 100644
--- a/arch/m68k/include/asm/floppy.h
+++ b/arch/m68k/include/asm/floppy.h
@@ -234,9 +234,9 @@ asmlinkage irqreturn_t floppy_hardint(int irq, void *dev_id)
 		virtual_dma_residue += virtual_dma_count;
 		virtual_dma_count=0;
 #ifdef TRACE_FLPY_INT
-		printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
-		       virtual_dma_count, virtual_dma_residue, calls, bytes,
-		       dma_wait);
+		pr_info("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
+			virtual_dma_count, virtual_dma_residue, calls, bytes,
+			dma_wait);
 		calls = 0;
 		dma_wait=0;
 #endif
diff --git a/arch/m68k/include/asm/macints.h b/arch/m68k/include/asm/macints.h
index 92aa8a4c2d03..cddb2d3ea49b 100644
--- a/arch/m68k/include/asm/macints.h
+++ b/arch/m68k/include/asm/macints.h
@@ -14,22 +14,6 @@
 
 #include <asm/irq.h>
 
-/* Setting this prints debugging info for unclaimed interrupts */
-
-#define DEBUG_SPURIOUS
-
-/* Setting this prints debugging info on each autovector interrupt */
-
-/* #define DEBUG_IRQS */
-
-/* Setting this prints debugging info on each Nubus interrupt */
-
-/* #define DEBUG_NUBUS_INT */
-
-/* Setting this prints debugging info on irqs as they enabled and disabled. */
-
-/* #define DEBUG_IRQUSE */
-
 /*
  * Base IRQ number for all Mac68K interrupt sources. Each source
  * has eight indexes (base -> base+7).
diff --git a/arch/m68k/include/asm/math-emu.h b/arch/m68k/include/asm/math-emu.h
index 5e9249b0014c..b062696d5a0d 100644
--- a/arch/m68k/include/asm/math-emu.h
+++ b/arch/m68k/include/asm/math-emu.h
@@ -105,21 +105,21 @@ struct fp_data {
 #ifdef FPU_EMU_DEBUG
 extern unsigned int fp_debugprint;
 
-#define dprint(bit, fmt, args...) ({			\
+#define dprint(bit, fmt, ...) ({			\
 	if (fp_debugprint & (1 << (bit)))		\
-		printk(fmt, ## args);			\
+		pr_info(fmt, ##__VA_ARGS__);		\
 })
 #else
-#define dprint(bit, fmt, args...)
+#define dprint(bit, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
 #define uprint(str) ({					\
 	static int __count = 3;				\
 							\
 	if (__count > 0) {				\
-		printk("You just hit an unimplemented "	\
+		pr_err("You just hit an unimplemented "	\
 		       "fpu instruction (%s)\n", str);	\
-		printk("Please report this to ....\n");	\
+		pr_err("Please report this to ....\n");	\
 		__count--;				\
 	}						\
 })
diff --git a/arch/m68k/include/asm/sun3_pgtable.h b/arch/m68k/include/asm/sun3_pgtable.h
index 48657f9fdece..d5104a7b5388 100644
--- a/arch/m68k/include/asm/sun3_pgtable.h
+++ b/arch/m68k/include/asm/sun3_pgtable.h
@@ -151,11 +151,11 @@ static inline void pgd_clear (pgd_t *pgdp) {}
 
 
 #define pte_ERROR(e) \
-	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+	pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
 #define pmd_ERROR(e) \
-	printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+	pr_err("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
 #define pgd_ERROR(e) \
-	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
 
 /*
diff --git a/arch/m68k/include/asm/sun3xflop.h b/arch/m68k/include/asm/sun3xflop.h
index a02ea3a7bb20..159269b7f2e8 100644
--- a/arch/m68k/include/asm/sun3xflop.h
+++ b/arch/m68k/include/asm/sun3xflop.h
@@ -48,7 +48,7 @@ static unsigned char sun3x_82072_fd_inb(int port)
 //	udelay(5);
 	switch(port & 7) {
 	default:
-		printk("floppy: Asked to read unknown port %d\n", port);
+		pr_crit("floppy: Asked to read unknown port %d\n", port);
 		panic("floppy: Port bolixed.");
 	case 4: /* FD_STATUS */
 		return (*sun3x_fdc.status_r) & ~STATUS_DMA;
@@ -70,7 +70,7 @@ static void sun3x_82072_fd_outb(unsigned char value, int port)
 //	udelay(5);
 	switch(port & 7) {
 	default:
-		printk("floppy: Asked to write to unknown port %d\n", port);
+		pr_crit("floppy: Asked to write to unknown port %d\n", port);
 		panic("floppy: Port bolixed.");
 	case 2: /* FD_DOR */
 		/* Oh geese, 82072 on the Sun has no DOR register,
@@ -127,7 +127,7 @@ asmlinkage irqreturn_t sun3xflop_hardint(int irq, void *dev_id)
 		return IRQ_HANDLED;
 	}
 
-//	printk("doing pdma\n");// st %x\n", sun_fdc->status_82072);
+//	pr_info("doing pdma\n");// st %x\n", sun_fdc->status_82072);
 
 #ifdef TRACE_FLPY_INT
 	if(!calls)
@@ -171,7 +171,7 @@ asmlinkage irqreturn_t sun3xflop_hardint(int irq, void *dev_id)
 #ifdef TRACE_FLPY_INT
 	calls++;
 #endif
-//	printk("st=%02x\n", st);
+//	pr_info("st=%02x\n", st);
 	if(st == 0x20)
 		return IRQ_HANDLED;
 	if(!(st & 0x20)) {
@@ -180,9 +180,9 @@ asmlinkage irqreturn_t sun3xflop_hardint(int irq, void *dev_id)
 		doing_pdma = 0;
 
 #ifdef TRACE_FLPY_INT
-		printk("count=%x, residue=%x calls=%d bytes=%x dma_wait=%d\n",
-		       virtual_dma_count, virtual_dma_residue, calls, bytes,
-		       dma_wait);
+		pr_info("count=%x, residue=%x calls=%d bytes=%x dma_wait=%d\n",
+			virtual_dma_count, virtual_dma_residue, calls, bytes,
+			dma_wait);
 		calls = 0;
 		dma_wait=0;
 #endif
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index 07070065a425..1e4f386ba31e 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -110,8 +110,8 @@ static void m68k_dma_sync_single_for_device(struct device *dev,
 		cache_clear(handle, size);
 		break;
 	default:
-		if (printk_ratelimit())
-			printk("dma_sync_single_for_device: unsupported dir %u\n", dir);
+		pr_err_ratelimited("dma_sync_single_for_device: unsupported dir %u\n",
+				   dir);
 		break;
 	}
 }
diff --git a/arch/m68k/kernel/module.c b/arch/m68k/kernel/module.c
index eb46fd6038ca..aaac2da318ff 100644
--- a/arch/m68k/kernel/module.c
+++ b/arch/m68k/kernel/module.c
@@ -12,9 +12,9 @@
 #include <linux/kernel.h>
 
 #if 0
-#define DEBUGP printk
+#define DEBUGP(fmt, ...) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 #else
-#define DEBUGP(fmt...)
+#define DEBUGP(fmt, ...) no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 #endif
 
 #ifdef CONFIG_MODULES
@@ -51,8 +51,8 @@ int apply_relocate(Elf32_Shdr *sechdrs,
 			*location += sym->st_value - (uint32_t)location;
 			break;
 		default:
-			printk(KERN_ERR "module %s: Unknown relocation: %u\n",
-			       me->name, ELF32_R_TYPE(rel[i].r_info));
+			pr_err("module %s: Unknown relocation: %u\n", me->name,
+			       ELF32_R_TYPE(rel[i].r_info));
 			return -ENOEXEC;
 		}
 	}
@@ -91,8 +91,8 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			*location = rel[i].r_addend + sym->st_value - (uint32_t)location;
 			break;
 		default:
-			printk(KERN_ERR "module %s: Unknown relocation: %u\n",
-			       me->name, ELF32_R_TYPE(rel[i].r_info));
+			pr_err("module %s: Unknown relocation: %u\n", me->name,
+			       ELF32_R_TYPE(rel[i].r_info));
 			return -ENOEXEC;
 		}
 	}
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index aaf28f8e342d..f0a8e9b332cd 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -87,17 +87,17 @@ EXPORT_SYMBOL(pm_power_off);
 
 void show_regs(struct pt_regs * regs)
 {
-	printk("\n");
-	printk("Format %02x  Vector: %04x  PC: %08lx  Status: %04x    %s\n",
-	       regs->format, regs->vector, regs->pc, regs->sr, print_tainted());
-	printk("ORIG_D0: %08lx  D0: %08lx  A2: %08lx  A1: %08lx\n",
-	       regs->orig_d0, regs->d0, regs->a2, regs->a1);
-	printk("A0: %08lx  D5: %08lx  D4: %08lx\n",
-	       regs->a0, regs->d5, regs->d4);
-	printk("D3: %08lx  D2: %08lx  D1: %08lx\n",
-	       regs->d3, regs->d2, regs->d1);
+	pr_info("Format %02x  Vector: %04x  PC: %08lx  Status: %04x    %s\n",
+		regs->format, regs->vector, regs->pc, regs->sr,
+		print_tainted());
+	pr_info("ORIG_D0: %08lx  D0: %08lx  A2: %08lx  A1: %08lx\n",
+		regs->orig_d0, regs->d0, regs->a2, regs->a1);
+	pr_info("A0: %08lx  D5: %08lx  D4: %08lx\n", regs->a0, regs->d5,
+		regs->d4);
+	pr_info("D3: %08lx  D2: %08lx  D1: %08lx\n", regs->d3, regs->d2,
+		regs->d1);
 	if (!(regs->sr & PS_S))
-		printk("USP: %08lx\n", rdusp());
+		pr_info("USP: %08lx\n", rdusp());
 }
 
 void flush_thread(void)
diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c
index 8ead291a902a..093b7c42fb85 100644
--- a/arch/m68k/kernel/signal.c
+++ b/arch/m68k/kernel/signal.c
@@ -598,9 +598,7 @@ static int mangle_kernel_stack(struct pt_regs *regs, int formatvec,
 		/*
 		 * user process trying to return with weird frame format
 		 */
-#ifdef DEBUG
-		printk("user process returning with weird frame format\n");
-#endif
+		pr_debug("user process returning with weird frame format\n");
 		return 1;
 	}
 	if (!fsize) {
@@ -846,10 +844,8 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 	int err = 0, sig = ksig->sig;
 
 	if (fsize < 0) {
-#ifdef DEBUG
-		printk ("setup_frame: Unknown frame format %#x\n",
-			regs->format);
-#endif
+		pr_debug("setup_frame: Unknown frame format %#x\n",
+			 regs->format);
 		return -EFAULT;
 	}
 
@@ -905,9 +901,7 @@ static int setup_frame(struct ksignal *ksig, sigset_t *set,
 	if (regs->stkadj) {
 		struct pt_regs *tregs =
 			(struct pt_regs *)((ulong)regs + regs->stkadj);
-#ifdef DEBUG
-		printk("Performing stackadjust=%04x\n", regs->stkadj);
-#endif
+		pr_debug("Performing stackadjust=%04lx\n", regs->stkadj);
 		/* This must be copied with decreasing addresses to
                    handle overlaps.  */
 		tregs->vector = 0;
@@ -926,10 +920,8 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	int err = 0, sig = ksig->sig;
 
 	if (fsize < 0) {
-#ifdef DEBUG
-		printk ("setup_frame: Unknown frame format %#x\n",
-			regs->format);
-#endif
+		pr_debug("setup_frame: Unknown frame format %#x\n",
+			 regs->format);
 		return -EFAULT;
 	}
 
@@ -993,9 +985,7 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set,
 	if (regs->stkadj) {
 		struct pt_regs *tregs =
 			(struct pt_regs *)((ulong)regs + regs->stkadj);
-#ifdef DEBUG
-		printk("Performing stackadjust=%04x\n", regs->stkadj);
-#endif
+		pr_debug("Performing stackadjust=%04lx\n", regs->stkadj);
 		/* This must be copied with decreasing addresses to
                    handle overlaps.  */
 		tregs->vector = 0;
diff --git a/arch/m68k/kernel/sys_m68k.c b/arch/m68k/kernel/sys_m68k.c
index 98a2daaae30c..933e4815dac8 100644
--- a/arch/m68k/kernel/sys_m68k.c
+++ b/arch/m68k/kernel/sys_m68k.c
@@ -398,7 +398,6 @@ sys_cacheflush (unsigned long addr, int scope, int cache, unsigned long len)
 		 * Verify that the specified address region actually belongs
 		 * to this process.
 		 */
-		ret = -EINVAL;
 		down_read(&current->mm->mmap_sem);
 		vma = find_vma(current->mm, addr);
 		if (!vma || addr < vma->vm_start || addr + len > vma->vm_end)
diff --git a/arch/m68k/kernel/uboot.c b/arch/m68k/kernel/uboot.c
index b3536a82a262..b29c3b241e1b 100644
--- a/arch/m68k/kernel/uboot.c
+++ b/arch/m68k/kernel/uboot.c
@@ -83,8 +83,7 @@ static void __init parse_uboot_commandline(char *commandp, int size)
 		initrd_start = uboot_initrd_start;
 		initrd_end = uboot_initrd_end;
 		ROOT_DEV = Root_RAM0;
-		printk(KERN_INFO "initrd at 0x%lx:0x%lx\n",
-			initrd_start, initrd_end);
+		pr_info("initrd at 0x%lx:0x%lx\n", initrd_start, initrd_end);
 	}
 #endif /* if defined(CONFIG_BLK_DEV_INITRD) */
 }
diff --git a/arch/m68k/mac/baboon.c b/arch/m68k/mac/baboon.c
index f6f7d42713ec..514acde3cd40 100644
--- a/arch/m68k/mac/baboon.c
+++ b/arch/m68k/mac/baboon.c
@@ -14,8 +14,6 @@
 #include <asm/macints.h>
 #include <asm/mac_baboon.h>
 
-/* #define DEBUG_IRQS */
-
 int baboon_present;
 static volatile struct baboon *baboon;
 
@@ -50,12 +48,6 @@ static void baboon_irq(struct irq_desc *desc)
 	int irq_bit, irq_num;
 	unsigned char events;
 
-#ifdef DEBUG_IRQS
-	printk("baboon_irq: mb_control %02X mb_ifr %02X mb_status %02X\n",
-		(uint) baboon->mb_control, (uint) baboon->mb_ifr,
-		(uint) baboon->mb_status);
-#endif
-
 	events = baboon->mb_ifr & 0x07;
 	if (!events)
 		return;
@@ -97,18 +89,10 @@ void __init baboon_register_interrupts(void)
 
 void baboon_irq_enable(int irq)
 {
-#ifdef DEBUG_IRQUSE
-	printk("baboon_irq_enable(%d)\n", irq);
-#endif
-
 	mac_irq_enable(irq_get_irq_data(IRQ_NUBUS_C));
 }
 
 void baboon_irq_disable(int irq)
 {
-#ifdef DEBUG_IRQUSE
-	printk("baboon_irq_disable(%d)\n", irq);
-#endif
-
 	mac_irq_disable(irq_get_irq_data(IRQ_NUBUS_C));
 }
diff --git a/arch/m68k/mac/macints.c b/arch/m68k/mac/macints.c
index 9f98c0871901..b5cd06df71fd 100644
--- a/arch/m68k/mac/macints.c
+++ b/arch/m68k/mac/macints.c
@@ -125,16 +125,9 @@
 #include <asm/hwtest.h>
 #include <asm/irq_regs.h>
 
-#define SHUTUP_SONIC
-
-/*
- * console_loglevel determines NMI handler function
- */
+extern void show_registers(struct pt_regs *);
 
 irqreturn_t mac_nmi_handler(int, void *);
-irqreturn_t mac_debug_handler(int, void *);
-
-/* #define DEBUG_MACINTS */
 
 static unsigned int mac_irq_startup(struct irq_data *);
 static void mac_irq_shutdown(struct irq_data *);
@@ -149,21 +142,8 @@ static struct irq_chip mac_irq_chip = {
 
 void __init mac_init_IRQ(void)
 {
-#ifdef DEBUG_MACINTS
-	printk("mac_init_IRQ(): Setting things up...\n");
-#endif
 	m68k_setup_irq_controller(&mac_irq_chip, handle_simple_irq, IRQ_USER,
 				  NUM_MAC_SOURCES - IRQ_USER);
-	/* Make sure the SONIC interrupt is cleared or things get ugly */
-#ifdef SHUTUP_SONIC
-	printk("Killing onboard sonic... ");
-	/* This address should hopefully be mapped already */
-	if (hwreg_present((void*)(0x50f0a000))) {
-		*(long *)(0x50f0a014) = 0x7fffL;
-		*(long *)(0x50f0a010) = 0L;
-	}
-	printk("Done.\n");
-#endif /* SHUTUP_SONIC */
 
 	/*
 	 * Now register the handlers for the master IRQ handlers
@@ -182,9 +162,6 @@ void __init mac_init_IRQ(void)
 	if (request_irq(IRQ_AUTO_7, mac_nmi_handler, 0, "NMI",
 			mac_nmi_handler))
 		pr_err("Couldn't register NMI\n");
-#ifdef DEBUG_MACINTS
-	printk("mac_init_IRQ(): Done!\n");
-#endif
 }
 
 /*
@@ -276,65 +253,17 @@ static void mac_irq_shutdown(struct irq_data *data)
 		mac_irq_disable(data);
 }
 
-static int num_debug[8];
-
-irqreturn_t mac_debug_handler(int irq, void *dev_id)
-{
-	if (num_debug[irq] < 10) {
-		printk("DEBUG: Unexpected IRQ %d\n", irq);
-		num_debug[irq]++;
-	}
-	return IRQ_HANDLED;
-}
-
-static int in_nmi;
-static volatile int nmi_hold;
+static volatile int in_nmi;
 
 irqreturn_t mac_nmi_handler(int irq, void *dev_id)
 {
-	int i;
-	/*
-	 * generate debug output on NMI switch if 'debug' kernel option given
-	 * (only works with Penguin!)
-	 */
+	if (in_nmi)
+		return IRQ_HANDLED;
+	in_nmi = 1;
 
-	in_nmi++;
-	for (i=0; i<100; i++)
-		udelay(1000);
-
-	if (in_nmi == 1) {
-		nmi_hold = 1;
-		printk("... pausing, press NMI to resume ...");
-	} else {
-		printk(" ok!\n");
-		nmi_hold = 0;
-	}
+	pr_info("Non-Maskable Interrupt\n");
+	show_registers(get_irq_regs());
 
-	barrier();
-
-	while (nmi_hold == 1)
-		udelay(1000);
-
-	if (console_loglevel >= 8) {
-#if 0
-		struct pt_regs *fp = get_irq_regs();
-		show_state();
-		printk("PC: %08lx\nSR: %04x  SP: %p\n", fp->pc, fp->sr, fp);
-		printk("d0: %08lx    d1: %08lx    d2: %08lx    d3: %08lx\n",
-		       fp->d0, fp->d1, fp->d2, fp->d3);
-		printk("d4: %08lx    d5: %08lx    a0: %08lx    a1: %08lx\n",
-		       fp->d4, fp->d5, fp->a0, fp->a1);
-
-		if (STACK_MAGIC != *(unsigned long *)current->kernel_stack_page)
-			printk("Corrupted stack page\n");
-		printk("Process %s (pid: %d, stackpage=%08lx)\n",
-			current->comm, current->pid, current->kernel_stack_page);
-		if (intr_count == 1)
-			dump_stack((struct frame *)fp);
-#else
-		/* printk("NMI "); */
-#endif
-	}
-	in_nmi--;
+	in_nmi = 0;
 	return IRQ_HANDLED;
 }
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index c6d351f5bd79..3b1f7a6159f8 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -4,7 +4,6 @@
 
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <linux/miscdevice.h>
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
diff --git a/arch/m68k/mac/oss.c b/arch/m68k/mac/oss.c
index 55d6592783f5..ca84dcf41fc9 100644
--- a/arch/m68k/mac/oss.c
+++ b/arch/m68k/mac/oss.c
@@ -68,15 +68,6 @@ static void oss_irq(struct irq_desc *desc)
 	int events = oss->irq_pending &
 		(OSS_IP_IOPSCC | OSS_IP_SCSI | OSS_IP_IOPISM);
 
-#ifdef DEBUG_IRQS
-	if ((console_loglevel == 10) && !(events & OSS_IP_SCSI)) {
-		unsigned int irq = irq_desc_get_irq(desc);
-
-		printk("oss_irq: irq %u events = 0x%04X\n", irq,
-			(int) oss->irq_pending);
-	}
-#endif
-
 	if (events & OSS_IP_IOPSCC) {
 		oss->irq_pending &= ~OSS_IP_IOPSCC;
 		generic_handle_irq(IRQ_MAC_SCC);
@@ -107,11 +98,6 @@ static void oss_nubus_irq(struct irq_desc *desc)
 	if (!events)
 		return;
 
-#ifdef DEBUG_NUBUS_INT
-	if (console_loglevel > 7) {
-		printk("oss_nubus_irq: events = 0x%04X\n", events);
-	}
-#endif
 	/* There are only six slots on the OSS, not seven */
 
 	i = 6;
@@ -163,9 +149,6 @@ void __init oss_register_interrupts(void)
  */
 
 void oss_irq_enable(int irq) {
-#ifdef DEBUG_IRQUSE
-	printk("oss_irq_enable(%d)\n", irq);
-#endif
 	switch(irq) {
 		case IRQ_MAC_SCC:
 			oss->irq_level[OSS_IOPSCC] = OSS_IRQLEV_IOPSCC;
@@ -199,9 +182,6 @@ void oss_irq_enable(int irq) {
  */
 
 void oss_irq_disable(int irq) {
-#ifdef DEBUG_IRQUSE
-	printk("oss_irq_disable(%d)\n", irq);
-#endif
 	switch(irq) {
 		case IRQ_MAC_SCC:
 			oss->irq_level[OSS_IOPSCC] = 0;
diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c
index cb2b1a3a2b62..439a2a2e5874 100644
--- a/arch/m68k/mac/psc.c
+++ b/arch/m68k/mac/psc.c
@@ -122,11 +122,6 @@ static void psc_irq(struct irq_desc *desc)
 	int irq_num;
 	unsigned char irq_bit, events;
 
-#ifdef DEBUG_IRQS
-	printk("psc_irq: irq %u pIFR = 0x%02X pIER = 0x%02X\n",
-		irq, (int) psc_read_byte(pIFR), (int) psc_read_byte(pIER));
-#endif
-
 	events = psc_read_byte(pIFR) & psc_read_byte(pIER) & 0xF;
 	if (!events)
 		return;
@@ -160,9 +155,6 @@ void psc_irq_enable(int irq) {
 	int irq_idx	= IRQ_IDX(irq);
 	int pIER	= pIERbase + (irq_src << 4);
 
-#ifdef DEBUG_IRQUSE
-	printk("psc_irq_enable(%d)\n", irq);
-#endif
 	psc_write_byte(pIER, (1 << irq_idx) | 0x80);
 }
 
@@ -171,8 +163,5 @@ void psc_irq_disable(int irq) {
 	int irq_idx	= IRQ_IDX(irq);
 	int pIER	= pIERbase + (irq_src << 4);
 
-#ifdef DEBUG_IRQUSE
-	printk("psc_irq_disable(%d)\n", irq);
-#endif
 	psc_write_byte(pIER, 1 << irq_idx);
 }
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index 920ff63d4a81..16629e91feba 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -550,10 +550,6 @@ void via_irq_enable(int irq) {
 	int irq_src	= IRQ_SRC(irq);
 	int irq_idx	= IRQ_IDX(irq);
 
-#ifdef DEBUG_IRQUSE
-	printk(KERN_DEBUG "via_irq_enable(%d)\n", irq);
-#endif
-
 	if (irq_src == 1) {
 		via1[vIER] = IER_SET_BIT(irq_idx);
 	} else if (irq_src == 2) {
@@ -582,10 +578,6 @@ void via_irq_disable(int irq) {
 	int irq_src	= IRQ_SRC(irq);
 	int irq_idx	= IRQ_IDX(irq);
 
-#ifdef DEBUG_IRQUSE
-	printk(KERN_DEBUG "via_irq_disable(%d)\n", irq);
-#endif
-
 	if (irq_src == 1) {
 		via1[vIER] = IER_CLR_BIT(irq_idx);
 	} else if (irq_src == 2) {
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 9c1e656b1f8f..a6ffead9bef5 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -66,7 +66,7 @@ void __init m68k_setup_node(int node)
 	end = (unsigned long)phys_to_virt(info->addr + info->size - 1) >> __virt_to_node_shift();
 	for (; i <= end; i++) {
 		if (pg_data_table[i])
-			printk("overlap at %u for chunk %u\n", i, node);
+			pr_warn("overlap at %u for chunk %u\n", i, node);
 		pg_data_table[i] = pg_data_map + node;
 	}
 #endif
diff --git a/arch/m68k/mm/memory.c b/arch/m68k/mm/memory.c
index 51bc9d258ede..4902b681a9fc 100644
--- a/arch/m68k/mm/memory.c
+++ b/arch/m68k/mm/memory.c
@@ -47,9 +47,7 @@ void __init init_pointer_table(unsigned long ptable)
 	}
 
 	PD_MARKBITS(dp) &= ~mask;
-#ifdef DEBUG
-	printk("init_pointer_table: %lx, %x\n", ptable, PD_MARKBITS(dp));
-#endif
+	pr_debug("init_pointer_table: %lx, %x\n", ptable, PD_MARKBITS(dp));
 
 	/* unreserve the page so it's possible to free that page */
 	PD_PAGE(dp)->flags &= ~(1 << PG_reserved);
diff --git a/arch/m68k/mm/sun3kmap.c b/arch/m68k/mm/sun3kmap.c
index 3dc41158c05e..ae03555449b8 100644
--- a/arch/m68k/mm/sun3kmap.c
+++ b/arch/m68k/mm/sun3kmap.c
@@ -40,6 +40,7 @@ static inline void do_page_mapin(unsigned long phys, unsigned long virt,
 	sun3_put_pte(virt, pte);
 
 #ifdef SUN3_KMAP_DEBUG
+	pr_info("mapin:");
 	print_pte_vaddr(virt);
 #endif
 
@@ -80,8 +81,8 @@ void __iomem *sun3_ioremap(unsigned long phys, unsigned long size,
 		return NULL;
 
 #ifdef SUN3_KMAP_DEBUG
-	printk("ioremap: got virt %p size %lx(%lx)\n",
-	       area->addr, size, area->size);
+	pr_info("ioremap: got virt %p size %lx(%lx)\n", area->addr, size,
+		area->size);
 #endif
 
 	pages = size / PAGE_SIZE;
diff --git a/arch/m68k/mm/sun3mmu.c b/arch/m68k/mm/sun3mmu.c
index b5b7d53f7283..177d776de1a0 100644
--- a/arch/m68k/mm/sun3mmu.c
+++ b/arch/m68k/mm/sun3mmu.c
@@ -44,9 +44,6 @@ void __init paging_init(void)
 	unsigned long zones_size[MAX_NR_ZONES] = { 0, };
 	unsigned long size;
 
-#ifdef TEST_VERIFY_AREA
-	wp_works_ok = 0;
-#endif
 	empty_zero_page = alloc_bootmem_pages(PAGE_SIZE);
 
 	address = PAGE_OFFSET;
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index c11d38dfad08..8778612d1f31 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -63,7 +63,7 @@ int __init mvme147_parse_bootinfo(const struct bi_record *bi)
 
 void mvme147_reset(void)
 {
-	printk ("\r\n\nCalled mvme147_reset\r\n");
+	pr_info("\r\n\nCalled mvme147_reset\r\n");
 	m147_pcc->watchdog = 0x0a;	/* Clear timer */
 	m147_pcc->watchdog = 0xa5;	/* Enable watchdog - 100ms to reset */
 	while (1)
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 58e240939d26..6fa06d4d16bf 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -72,8 +72,8 @@ int __init mvme16x_parse_bootinfo(const struct bi_record *bi)
 
 void mvme16x_reset(void)
 {
-	printk ("\r\n\nCalled mvme16x_reset\r\n"
-			"\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r");
+	pr_info("\r\n\nCalled mvme16x_reset\r\n"
+		"\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r\r");
 	/* The string of returns is to delay the reset until the whole
 	 * message is output.  Assert reset bit in GCSR */
 	*(volatile char *)0xfff40107 = 0x80;
@@ -289,7 +289,7 @@ void __init config_mvme16x(void)
 
     if (strncmp("BDID", p->bdid, 4))
     {
-	printk ("\n\nBug call .BRD_ID returned garbage - giving up\n\n");
+	pr_crit("Bug call .BRD_ID returned garbage - giving up\n");
 	while (1)
 		;
     }
@@ -298,25 +298,25 @@ void __init config_mvme16x(void)
 	vme_brdtype = brdno;
 
     mvme16x_get_model(id);
-    printk ("\nBRD_ID: %s   BUG %x.%x %02x/%02x/%02x\n", id, p->rev>>4,
-					p->rev&0xf, p->yr, p->mth, p->day);
+    pr_info("BRD_ID: %s   BUG %x.%x %02x/%02x/%02x\n", id, p->rev >> 4,
+	    p->rev & 0xf, p->yr, p->mth, p->day);
     if (brdno == 0x0162 || brdno == 0x172)
     {
 	unsigned char rev = *(unsigned char *)MVME162_VERSION_REG;
 
 	mvme16x_config = rev | MVME16x_CONFIG_GOT_SCCA;
 
-	printk ("MVME%x Hardware status:\n", brdno);
-	printk ("    CPU Type           68%s040\n",
-			rev & MVME16x_CONFIG_GOT_FPU ? "" : "LC");
-	printk ("    CPU clock          %dMHz\n",
-			rev & MVME16x_CONFIG_SPEED_32 ? 32 : 25);
-	printk ("    VMEchip2           %spresent\n",
-			rev & MVME16x_CONFIG_NO_VMECHIP2 ? "NOT " : "");
-	printk ("    SCSI interface     %spresent\n",
-			rev & MVME16x_CONFIG_NO_SCSICHIP ? "NOT " : "");
-	printk ("    Ethernet interface %spresent\n",
-			rev & MVME16x_CONFIG_NO_ETHERNET ? "NOT " : "");
+	pr_info("MVME%x Hardware status:\n", brdno);
+	pr_info("    CPU Type           68%s040\n",
+		rev & MVME16x_CONFIG_GOT_FPU ? "" : "LC");
+	pr_info("    CPU clock          %dMHz\n",
+		rev & MVME16x_CONFIG_SPEED_32 ? 32 : 25);
+	pr_info("    VMEchip2           %spresent\n",
+		rev & MVME16x_CONFIG_NO_VMECHIP2 ? "NOT " : "");
+	pr_info("    SCSI interface     %spresent\n",
+		rev & MVME16x_CONFIG_NO_SCSICHIP ? "NOT " : "");
+	pr_info("    Ethernet interface %spresent\n",
+		rev & MVME16x_CONFIG_NO_ETHERNET ? "NOT " : "");
     }
     else
     {
diff --git a/arch/m68k/mvme16x/rtc.c b/arch/m68k/mvme16x/rtc.c
index 8f00847a0e4b..7b24577a7bd0 100644
--- a/arch/m68k/mvme16x/rtc.c
+++ b/arch/m68k/mvme16x/rtc.c
@@ -158,7 +158,7 @@ static int __init rtc_MK48T08_init(void)
 	if (!MACH_IS_MVME16x)
 		return -ENODEV;
 
-	printk(KERN_INFO "MK48T08 Real Time Clock Driver v%s\n", RTC_VERSION);
+	pr_info("MK48T08 Real Time Clock Driver v%s\n", RTC_VERSION);
 	return misc_register(&rtc_dev);
 }
 device_initcall(rtc_MK48T08_init);
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index ea89a24f4600..71c0867ecf20 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -84,7 +84,7 @@ static int __init q40_debug_setup(char *arg)
 {
 	/* useful for early debugging stages - writes kernel messages into SRAM */
 	if (MACH_IS_Q40 && !strncmp(arg, "mem", 3)) {
-		/*printk("using NVRAM debug, q40_mem_cptr=%p\n",q40_mem_cptr);*/
+		/*pr_info("using NVRAM debug, q40_mem_cptr=%p\n",q40_mem_cptr);*/
 		_cpleft = 2000 - ((long)q40_mem_cptr-0xff020000) / 4;
 		register_console(&q40_console_driver);
 	}
@@ -124,8 +124,8 @@ static void q40_heartbeat(int on)
 
 static void q40_reset(void)
 {
-        halted = 1;
-        printk("\n\n*******************************************\n"
+	halted = 1;
+	pr_info("*******************************************\n"
 		"Called q40_reset : press the RESET button!!\n"
 		"*******************************************\n");
 	Q40_LED_ON();
@@ -135,10 +135,10 @@ static void q40_reset(void)
 
 static void q40_halt(void)
 {
-        halted = 1;
-        printk("\n\n*******************\n"
-		   "  Called q40_halt\n"
-		   "*******************\n");
+	halted = 1;
+	pr_info("*******************\n"
+		"  Called q40_halt\n"
+		"*******************\n");
 	Q40_LED_ON();
 	while (1)
 		;
diff --git a/arch/m68k/q40/q40ints.c b/arch/m68k/q40/q40ints.c
index 513f9bb17b9c..3e7603202977 100644
--- a/arch/m68k/q40/q40ints.c
+++ b/arch/m68k/q40/q40ints.c
@@ -48,7 +48,8 @@ static unsigned int q40_irq_startup(struct irq_data *data)
 	switch (irq) {
 	case 1: case 2: case 8: case 9:
 	case 11: case 12: case 13:
-		printk("%s: ISA IRQ %d not implemented by HW\n", __func__, irq);
+		pr_warn("%s: ISA IRQ %d not implemented by HW\n", __func__,
+			irq);
 		/* FIXME return -ENXIO; */
 	}
 	return 0;
@@ -250,7 +251,7 @@ static void q40_irq_handler(unsigned int irq, struct pt_regs *fp)
 					disable_irq(irq);
 					disabled = 1;
 #else
-					/*printk("IRQ_INPROGRESS detected for irq %d, disabling - %s disabled\n",
+					/*pr_warn("IRQ_INPROGRESS detected for irq %d, disabling - %s disabled\n",
 						irq, disabled ? "already" : "not yet"); */
 					fp->sr = (((fp->sr) & (~0x700))+0x200);
 					disabled = 1;
@@ -273,7 +274,7 @@ static void q40_irq_handler(unsigned int irq, struct pt_regs *fp)
 					}
 #else
 					disabled = 0;
-					/*printk("reenabling irq %d\n", irq); */
+					/*pr_info("reenabling irq %d\n", irq); */
 #endif
 				}
 // used to do 'goto repeat;' here, this delayed bh processing too long
@@ -281,7 +282,8 @@ static void q40_irq_handler(unsigned int irq, struct pt_regs *fp)
 			}
 		}
 		if (mer && ccleirq > 0 && !aliased_irq) {
-			printk("ISA interrupt from unknown source? EIRQ_REG = %x\n",mer);
+			pr_warn("ISA interrupt from unknown source? EIRQ_REG = %x\n",
+				mer);
 			ccleirq--;
 		}
 	}
@@ -301,7 +303,7 @@ void q40_irq_enable(struct irq_data *data)
 	if (irq >= 5 && irq <= 15) {
 		mext_disabled--;
 		if (mext_disabled > 0)
-			printk("q40_irq_enable : nested disable/enable\n");
+			pr_warn("q40_irq_enable : nested disable/enable\n");
 		if (mext_disabled == 0)
 			master_outb(1, EXT_ENABLE_REG);
 	}
@@ -321,6 +323,7 @@ void q40_irq_disable(struct irq_data *data)
 		master_outb(0, EXT_ENABLE_REG);
 		mext_disabled++;
 		if (mext_disabled > 1)
-			printk("disable_irq nesting count %d\n",mext_disabled);
+			pr_info("disable_irq nesting count %d\n",
+				mext_disabled);
 	}
 }
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index 3af34fa3a344..1d28d380e8cc 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -134,7 +134,7 @@ void __init config_sun3(void)
 {
 	unsigned long memory_start, memory_end;
 
-	printk("ARCH: SUN3\n");
+	pr_info("ARCH: SUN3\n");
 	idprom_init();
 
 	/* Subtract kernel memory from available memory */
diff --git a/arch/m68k/sun3/dvma.c b/arch/m68k/sun3/dvma.c
index d95506e06c2a..ca02ee25894c 100644
--- a/arch/m68k/sun3/dvma.c
+++ b/arch/m68k/sun3/dvma.c
@@ -31,8 +31,7 @@ static unsigned long dvma_page(unsigned long kaddr, unsigned long vaddr)
 
 	ptep = pfn_pte(virt_to_pfn(kaddr), PAGE_KERNEL);
 	pte = pte_val(ptep);
-//		printk("dvma_remap: addr %lx -> %lx pte %08lx len %x\n",
-//		       kaddr, vaddr, pte, len);
+//	pr_info("dvma_remap: addr %lx -> %lx pte %08lx\n", kaddr, vaddr, pte);
 	if(ptelist[(vaddr & 0xff000) >> PAGE_SHIFT] != pte) {
 		sun3_put_pte(vaddr, pte);
 		ptelist[(vaddr & 0xff000) >> PAGE_SHIFT] = pte;
diff --git a/arch/m68k/sun3/idprom.c b/arch/m68k/sun3/idprom.c
index cfe9aa422343..9c23f506d60d 100644
--- a/arch/m68k/sun3/idprom.c
+++ b/arch/m68k/sun3/idprom.c
@@ -64,12 +64,14 @@ static void __init display_system_type(unsigned char machtype)
 	for (i = 0; i < NUM_SUN_MACHINES; i++) {
 		if(Sun_Machines[i].id_machtype == machtype) {
 			if (machtype != (SM_SUN4M_OBP | 0x00))
-				printk("TYPE: %s\n", Sun_Machines[i].name);
+				pr_info("TYPE: %s\n", Sun_Machines[i].name);
 			else {
 #if 0
+				char sysname[128];
+
 				prom_getproperty(prom_root_node, "banner-name",
 						 sysname, sizeof(sysname));
-				printk("TYPE: %s\n", sysname);
+				pr_info("TYPE: %s\n", sysname);
 #endif
 			}
 			return;
@@ -125,5 +127,5 @@ void __init idprom_init(void)
 
 	display_system_type(idprom->id_machtype);
 
-	printk("Ethernet address: %pM\n", idprom->id_ethaddr);
+	pr_info("Ethernet address: %pM\n", idprom->id_ethaddr);
 }
diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c
index 0f95134e9b85..e9d7fbe4d5ae 100644
--- a/arch/m68k/sun3/mmu_emu.c
+++ b/arch/m68k/sun3/mmu_emu.c
@@ -72,21 +72,21 @@ void print_pte (pte_t pte)
 #if 0
 	/* Verbose version. */
 	unsigned long val = pte_val (pte);
-	printk (" pte=%lx [addr=%lx",
+	pr_cont(" pte=%lx [addr=%lx",
 		val, (val & SUN3_PAGE_PGNUM_MASK) << PAGE_SHIFT);
-	if (val & SUN3_PAGE_VALID)	printk (" valid");
-	if (val & SUN3_PAGE_WRITEABLE)	printk (" write");
-	if (val & SUN3_PAGE_SYSTEM)	printk (" sys");
-	if (val & SUN3_PAGE_NOCACHE)	printk (" nocache");
-	if (val & SUN3_PAGE_ACCESSED)	printk (" accessed");
-	if (val & SUN3_PAGE_MODIFIED)	printk (" modified");
+	if (val & SUN3_PAGE_VALID)	pr_cont(" valid");
+	if (val & SUN3_PAGE_WRITEABLE)	pr_cont(" write");
+	if (val & SUN3_PAGE_SYSTEM)	pr_cont(" sys");
+	if (val & SUN3_PAGE_NOCACHE)	pr_cont(" nocache");
+	if (val & SUN3_PAGE_ACCESSED)	pr_cont(" accessed");
+	if (val & SUN3_PAGE_MODIFIED)	pr_cont(" modified");
 	switch (val & SUN3_PAGE_TYPE_MASK) {
-		case SUN3_PAGE_TYPE_MEMORY: printk (" memory"); break;
-		case SUN3_PAGE_TYPE_IO:     printk (" io");     break;
-		case SUN3_PAGE_TYPE_VME16:  printk (" vme16");  break;
-		case SUN3_PAGE_TYPE_VME32:  printk (" vme32");  break;
+		case SUN3_PAGE_TYPE_MEMORY: pr_cont(" memory"); break;
+		case SUN3_PAGE_TYPE_IO:     pr_cont(" io");     break;
+		case SUN3_PAGE_TYPE_VME16:  pr_cont(" vme16");  break;
+		case SUN3_PAGE_TYPE_VME32:  pr_cont(" vme32");  break;
 	}
-	printk ("]\n");
+	pr_cont("]\n");
 #else
 	/* Terse version. More likely to fit on a line. */
 	unsigned long val = pte_val (pte);
@@ -108,7 +108,7 @@ void print_pte (pte_t pte)
 		default: type = "unknown?"; break;
 	}
 
-	printk (" pte=%08lx [%07lx %s %s]\n",
+	pr_cont(" pte=%08lx [%07lx %s %s]\n",
 		val, (val & SUN3_PAGE_PGNUM_MASK) << PAGE_SHIFT, flags, type);
 #endif
 }
@@ -116,7 +116,7 @@ void print_pte (pte_t pte)
 /* Print the PTE value for a given virtual address. For debugging. */
 void print_pte_vaddr (unsigned long vaddr)
 {
-	printk (" vaddr=%lx [%02lx]", vaddr, sun3_get_segmap (vaddr));
+	pr_cont(" vaddr=%lx [%02lx]", vaddr, sun3_get_segmap (vaddr));
 	print_pte (__pte (sun3_get_pte (vaddr)));
 }
 
@@ -153,7 +153,7 @@ void __init mmu_emu_init(unsigned long bootmem_end)
 
 		if(!pmeg_alloc[i]) {
 #ifdef DEBUG_MMU_EMU
-			printk("freed: ");
+			pr_info("freed:");
 			print_pte_vaddr (seg);
 #endif
 			sun3_put_segmap(seg, SUN3_INVALID_PMEG);
@@ -165,7 +165,7 @@ void __init mmu_emu_init(unsigned long bootmem_end)
 		if (sun3_get_segmap (seg) != SUN3_INVALID_PMEG) {
 #ifdef DEBUG_PROM_MAPS
 			for(i = 0; i < 16; i++) {
-				printk ("mapped:");
+				pr_info("mapped:");
 				print_pte_vaddr (seg + (i*PAGE_SIZE));
 				break;
 			}
@@ -293,8 +293,8 @@ inline void mmu_emu_map_pmeg (int context, int vaddr)
 
 
 #ifdef DEBUG_MMU_EMU
-printk("mmu_emu_map_pmeg: pmeg %x to context %d vaddr %x\n",
-       curr_pmeg, context, vaddr);
+	pr_info("mmu_emu_map_pmeg: pmeg %x to context %d vaddr %x\n",
+		curr_pmeg, context, vaddr);
 #endif
 
 	/* Invalidate old mapping for the pmeg, if any */
@@ -370,7 +370,7 @@ int mmu_emu_handle_fault (unsigned long vaddr, int read_flag, int kernel_fault)
 	}
 
 #ifdef DEBUG_MMU_EMU
-	printk ("mmu_emu_handle_fault: vaddr=%lx type=%s crp=%p\n",
+	pr_info("mmu_emu_handle_fault: vaddr=%lx type=%s crp=%p\n",
 		vaddr, read_flag ? "read" : "write", crp);
 #endif
 
@@ -378,14 +378,15 @@ int mmu_emu_handle_fault (unsigned long vaddr, int read_flag, int kernel_fault)
 	offset  = (vaddr >> SUN3_PTE_SIZE_BITS) & 0xF;
 
 #ifdef DEBUG_MMU_EMU
-	printk ("mmu_emu_handle_fault: segment=%lx offset=%lx\n", segment, offset);
+	pr_info("mmu_emu_handle_fault: segment=%lx offset=%lx\n", segment,
+		offset);
 #endif
 
 	pte = (pte_t *) pgd_val (*(crp + segment));
 
 //todo: next line should check for valid pmd properly.
 	if (!pte) {
-//                printk ("mmu_emu_handle_fault: invalid pmd\n");
+//                pr_info("mmu_emu_handle_fault: invalid pmd\n");
                 return 0;
         }
 
@@ -417,9 +418,9 @@ int mmu_emu_handle_fault (unsigned long vaddr, int read_flag, int kernel_fault)
 		pte_val (*pte) |= SUN3_PAGE_ACCESSED;
 
 #ifdef DEBUG_MMU_EMU
-	printk ("seg:%d crp:%p ->", get_fs().seg, crp);
+	pr_info("seg:%ld crp:%p ->", get_fs().seg, crp);
 	print_pte_vaddr (vaddr);
-	printk ("\n");
+	pr_cont("\n");
 #endif
 
 	return 1;
diff --git a/arch/m68k/sun3/prom/printf.c b/arch/m68k/sun3/prom/printf.c
index df85018f487a..5b82bea03493 100644
--- a/arch/m68k/sun3/prom/printf.c
+++ b/arch/m68k/sun3/prom/printf.c
@@ -39,7 +39,7 @@ prom_printf(char *fmt, ...)
 
 #ifdef CONFIG_KGDB
 	if (kgdb_initialized) {
-		printk("kgdb_initialized = %d\n", kgdb_initialized);
+		pr_info("kgdb_initialized = %d\n", kgdb_initialized);
 		putpacket(bptr, 1);
 	} else
 #else
diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c
index b37521a5259d..d36bd15f9fdc 100644
--- a/arch/m68k/sun3/sun3dvma.c
+++ b/arch/m68k/sun3/sun3dvma.c
@@ -62,7 +62,7 @@ static void print_use(void)
 	int i;
 	int j = 0;
 
-	printk("dvma entry usage:\n");
+	pr_info("dvma entry usage:\n");
 
 	for(i = 0; i < IOMMU_TOTAL_ENTRIES; i++) {
 		if(!iommu_use[i])
@@ -70,16 +70,15 @@ static void print_use(void)
 
 		j++;
 
-		printk("dvma entry: %08lx len %08lx\n",
-		       ( i << DVMA_PAGE_SHIFT) + DVMA_START,
-		       iommu_use[i]);
+		pr_info("dvma entry: %08x len %08lx\n",
+			(i << DVMA_PAGE_SHIFT) + DVMA_START, iommu_use[i]);
 	}
 
-	printk("%d entries in use total\n", j);
+	pr_info("%d entries in use total\n", j);
 
-	printk("allocation/free calls: %lu/%lu\n", dvma_allocs, dvma_frees);
-	printk("allocation/free bytes: %Lx/%Lx\n", dvma_alloc_bytes,
-	       dvma_free_bytes);
+	pr_info("allocation/free calls: %lu/%lu\n", dvma_allocs, dvma_frees);
+	pr_info("allocation/free bytes: %Lx/%Lx\n", dvma_alloc_bytes,
+		dvma_free_bytes);
 }
 
 static void print_holes(struct list_head *holes)
@@ -88,18 +87,18 @@ static void print_holes(struct list_head *holes)
 	struct list_head *cur;
 	struct hole *hole;
 
-	printk("listing dvma holes\n");
+	pr_info("listing dvma holes\n");
 	list_for_each(cur, holes) {
 		hole = list_entry(cur, struct hole, list);
 
 		if((hole->start == 0) && (hole->end == 0) && (hole->size == 0))
 			continue;
 
-		printk("hole: start %08lx end %08lx size %08lx\n", hole->start, hole->end, hole->size);
+		pr_info("hole: start %08lx end %08lx size %08lx\n",
+			hole->start, hole->end, hole->size);
 	}
 
-	printk("end of hole listing...\n");
-
+	pr_info("end of hole listing...\n");
 }
 #endif /* DVMA_DEBUG */
 
@@ -137,7 +136,7 @@ static inline struct hole *rmcache(void)
 
 	if(list_empty(&hole_cache)) {
 		if(!refill()) {
-			printk("out of dvma hole cache!\n");
+			pr_crit("out of dvma hole cache!\n");
 			BUG();
 		}
 	}
@@ -157,7 +156,7 @@ static inline unsigned long get_baddr(int len, unsigned long align)
 
 	if(list_empty(&hole_list)) {
 #ifdef DVMA_DEBUG
-		printk("out of dvma holes! (printing hole cache)\n");
+		pr_crit("out of dvma holes! (printing hole cache)\n");
 		print_holes(&hole_cache);
 		print_use();
 #endif
@@ -195,7 +194,7 @@ static inline unsigned long get_baddr(int len, unsigned long align)
 
 	}
 
-	printk("unable to find dvma hole!\n");
+	pr_crit("unable to find dvma hole!\n");
 	BUG();
 	return 0;
 }
@@ -287,15 +286,12 @@ unsigned long dvma_map_align(unsigned long kaddr, int len, int align)
 		len = 0x800;
 
 	if(!kaddr || !len) {
-//		printk("error: kaddr %lx len %x\n", kaddr, len);
+//		pr_err("error: kaddr %lx len %x\n", kaddr, len);
 //		*(int *)4 = 0;
 		return 0;
 	}
 
-#ifdef DEBUG
-	printk("dvma_map request %08lx bytes from %08lx\n",
-	       len, kaddr);
-#endif
+	pr_debug("dvma_map request %08x bytes from %08lx\n", len, kaddr);
 	off = kaddr & ~DVMA_PAGE_MASK;
 	kaddr &= PAGE_MASK;
 	len += off;
@@ -307,12 +303,13 @@ unsigned long dvma_map_align(unsigned long kaddr, int len, int align)
 		align = ((align + (DVMA_PAGE_SIZE-1)) & DVMA_PAGE_MASK);
 
 	baddr = get_baddr(len, align);
-//	printk("using baddr %lx\n", baddr);
+//	pr_info("using baddr %lx\n", baddr);
 
 	if(!dvma_map_iommu(kaddr, baddr, len))
 		return (baddr + off);
 
-	printk("dvma_map failed kaddr %lx baddr %lx len %x\n", kaddr, baddr, len);
+	pr_crit("dvma_map failed kaddr %lx baddr %lx len %x\n", kaddr, baddr,
+	len);
 	BUG();
 	return 0;
 }
@@ -343,9 +340,7 @@ void *dvma_malloc_align(unsigned long len, unsigned long align)
 	if(!len)
 		return NULL;
 
-#ifdef DEBUG
-	printk("dvma_malloc request %lx bytes\n", len);
-#endif
+	pr_debug("dvma_malloc request %lx bytes\n", len);
 	len = ((len + (DVMA_PAGE_SIZE-1)) & DVMA_PAGE_MASK);
 
         if((kaddr = __get_free_pages(GFP_ATOMIC, get_order(len))) == 0)
@@ -364,10 +359,8 @@ void *dvma_malloc_align(unsigned long len, unsigned long align)
 		return NULL;
 	}
 
-#ifdef DEBUG
-	printk("mapped %08lx bytes %08lx kern -> %08lx bus\n",
-	       len, kaddr, baddr);
-#endif
+	pr_debug("mapped %08lx bytes %08lx kern -> %08lx bus\n", len, kaddr,
+		 baddr);
 
 	return (void *)vaddr;
 
diff --git a/arch/m68k/sun3x/dvma.c b/arch/m68k/sun3x/dvma.c
index d5ddcdaa2347..9413c8724b0d 100644
--- a/arch/m68k/sun3x/dvma.c
+++ b/arch/m68k/sun3x/dvma.c
@@ -58,21 +58,17 @@ static volatile unsigned long *iommu_pte = (unsigned long *)SUN3X_IOMMU;
 					 ((addr & 0x03c00000) >>     \
 						(DVMA_PAGE_SHIFT+4)))
 
-#undef DEBUG
-
 #ifdef DEBUG
 /* code to print out a dvma mapping for debugging purposes */
 void dvma_print (unsigned long dvma_addr)
 {
 
-        unsigned long index;
-
-        index = dvma_addr >> DVMA_PAGE_SHIFT;
-
-        printk("idx %lx dvma_addr %08lx paddr %08lx\n", index, dvma_addr,
-               dvma_entry_paddr(index));
+	unsigned long index;
 
+	index = dvma_addr >> DVMA_PAGE_SHIFT;
 
+	pr_info("idx %lx dvma_addr %08lx paddr %08lx\n", index, dvma_addr,
+		dvma_entry_paddr(index));
 }
 #endif
 
@@ -91,10 +87,7 @@ inline int dvma_map_cpu(unsigned long kaddr,
 
 	end = PAGE_ALIGN(vaddr + len);
 
-#ifdef DEBUG
-	printk("dvma: mapping kern %08lx to virt %08lx\n",
-	       kaddr, vaddr);
-#endif
+	pr_debug("dvma: mapping kern %08lx to virt %08lx\n", kaddr, vaddr);
 	pgd = pgd_offset_k(vaddr);
 
 	do {
@@ -126,10 +119,8 @@ inline int dvma_map_cpu(unsigned long kaddr,
 				end3 = end2;
 
 			do {
-#ifdef DEBUG
-				printk("mapping %08lx phys to %08lx\n",
-				       __pa(kaddr), vaddr);
-#endif
+				pr_debug("mapping %08lx phys to %08lx\n",
+					 __pa(kaddr), vaddr);
 				set_pte(pte, pfn_pte(virt_to_pfn(kaddr),
 						     PAGE_KERNEL));
 				pte++;
@@ -162,7 +153,8 @@ inline int dvma_map_iommu(unsigned long kaddr, unsigned long baddr,
 	for(; index < end ; index++) {
 //		if(dvma_entry_use(index))
 //			BUG();
-//		printk("mapping pa %lx to ba %lx\n", __pa(kaddr), index << DVMA_PAGE_SHIFT);
+//		pr_info("mapping pa %lx to ba %lx\n", __pa(kaddr),
+//			index << DVMA_PAGE_SHIFT);
 
 		dvma_entry_set(index, __pa(kaddr));
 
@@ -190,13 +182,12 @@ void dvma_unmap_iommu(unsigned long baddr, int len)
 	end = (DVMA_PAGE_ALIGN(baddr+len) >> DVMA_PAGE_SHIFT);
 
 	for(; index < end ; index++) {
-#ifdef DEBUG
-		printk("freeing bus mapping %08x\n", index << DVMA_PAGE_SHIFT);
-#endif
+		pr_debug("freeing bus mapping %08x\n",
+			 index << DVMA_PAGE_SHIFT);
 #if 0
 		if(!dvma_entry_use(index))
-			printk("dvma_unmap freeing unused entry %04x\n",
-			       index);
+			pr_info("dvma_unmap freeing unused entry %04x\n",
+				index);
 		else
 			dvma_entry_dec(index);
 #endif
diff --git a/arch/m68k/sun3x/prom.c b/arch/m68k/sun3x/prom.c
index 0898c3f81508..5d60e65c1ee5 100644
--- a/arch/m68k/sun3x/prom.c
+++ b/arch/m68k/sun3x/prom.c
@@ -106,9 +106,9 @@ void __init sun3x_prom_init(void)
 	idprom_init();
 
 	if (!((idprom->id_machtype & SM_ARCH_MASK) == SM_SUN3X)) {
-		printk("Warning: machine reports strange type %02x\n",
+		pr_warn("Machine reports strange type %02x\n",
 			idprom->id_machtype);
-		printk("Pretending it's a 3/80, but very afraid...\n");
+		pr_warn("Pretending it's a 3/80, but very afraid...\n");
 		idprom->id_machtype = SM_SUN3X | SM_3_80;
 	}
 
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index 167150c701d1..d3731f0db73b 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -2,7 +2,6 @@ generic-y += auxvec.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += dma.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index b0ae88c9fed9..6275eb051801 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -1,7 +1,6 @@
 
 generic-y += barrier.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += device.h
 generic-y += exec.h
 generic-y += irq_work.h
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index b3c5bde43d34..e137eedb90d2 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1703,6 +1703,8 @@ config CPU_BMIPS
 	select WEAK_ORDERING
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_HAS_PREFETCH
+	select CPU_SUPPORTS_CPUFREQ
+	select MIPS_EXTERNAL_TIMER
 	help
 	  Support for BMIPS32/3300/4350/4380 and BMIPS5000 processors.
 
diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c
index d3c087f59f1a..a5504f57cb00 100644
--- a/arch/mips/alchemy/devboards/db1300.c
+++ b/arch/mips/alchemy/devboards/db1300.c
@@ -13,6 +13,7 @@
 #include <linux/i2c.h>
 #include <linux/io.h>
 #include <linux/leds.h>
+#include <linux/interrupt.h>
 #include <linux/ata_platform.h>
 #include <linux/mmc/host.h>
 #include <linux/module.h>
diff --git a/arch/mips/configs/bmips_stb_defconfig b/arch/mips/configs/bmips_stb_defconfig
index 4eb5d6e9cf8f..3cefa6bc01dd 100644
--- a/arch/mips/configs/bmips_stb_defconfig
+++ b/arch/mips/configs/bmips_stb_defconfig
@@ -9,13 +9,20 @@ CONFIG_MIPS_O32_FP64_SUPPORT=y
 # CONFIG_SWAP is not set
 CONFIG_NO_HZ=y
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_RD_GZIP=y
 CONFIG_EXPERT=y
 # CONFIG_VM_EVENT_COUNTERS is not set
 # CONFIG_SLUB_DEBUG is not set
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+CONFIG_CPU_FREQ=y
+CONFIG_CPU_FREQ_STAT=y
+CONFIG_CPU_FREQ_GOV_POWERSAVE=y
+CONFIG_CPU_FREQ_GOV_USERSPACE=y
+CONFIG_CPU_FREQ_GOV_ONDEMAND=y
+CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y
+CONFIG_CPU_FREQ_GOV_SCHEDUTIL=y
+CONFIG_BMIPS_CPUFREQ=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_PACKET_DIAG=y
@@ -24,7 +31,6 @@ CONFIG_INET=y
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 # CONFIG_INET_XFRM_MODE_BEET is not set
-# CONFIG_INET_LRO is not set
 # CONFIG_INET_DIAG is not set
 CONFIG_CFG80211=y
 CONFIG_NL80211_TESTMODE=y
@@ -34,8 +40,6 @@ CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-CONFIG_PRINTK_TIME=y
-CONFIG_BRCMSTB_GISB_ARB=y
 CONFIG_MTD=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_CFI_INTELEXT=y
@@ -51,16 +55,15 @@ CONFIG_USB_USBNET=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
-# CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
 # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
-CONFIG_POWER_SUPPLY=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_BRCMSTB=y
 CONFIG_POWER_RESET_SYSCON=y
+CONFIG_POWER_SUPPLY=y
 # CONFIG_HWMON is not set
 CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
@@ -82,6 +85,7 @@ CONFIG_CIFS=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
+CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_FS=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_CMDLINE_BOOL=y
diff --git a/arch/mips/configs/lemote2f_defconfig b/arch/mips/configs/lemote2f_defconfig
index 5da76e0e120f..bed745596d86 100644
--- a/arch/mips/configs/lemote2f_defconfig
+++ b/arch/mips/configs/lemote2f_defconfig
@@ -40,7 +40,6 @@ CONFIG_PM_STD_PARTITION="/dev/hda3"
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_DEBUG=y
 CONFIG_CPU_FREQ_STAT=m
-CONFIG_CPU_FREQ_STAT_DETAILS=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=m
 CONFIG_CPU_FREQ_GOV_USERSPACE=m
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 3269b742a75e..994b1c4392be 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -1,7 +1,6 @@
 # MIPS headers
 generic-(CONFIG_GENERIC_CSUM) += checksum.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += dma-contiguous.h
 generic-y += emergency-restart.h
diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c
index 9c7f3e136d50..4a2ff3953b99 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -99,15 +99,7 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value)
 #undef TASK_SIZE
 #define TASK_SIZE TASK_SIZE32
 
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-static __inline__ void
-cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value)
-{
-	unsigned long jiffies = cputime_to_jiffies(cputime);
-
-	value->tv_usec = (jiffies % HZ) * (1000000L / HZ);
-	value->tv_sec = jiffies / HZ;
-}
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
 
 #include "../../../fs/binfmt_elf.c"
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 1ab34322dd97..3916404e7fd1 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -102,15 +102,7 @@ jiffies_to_compat_timeval(unsigned long jiffies, struct compat_timeval *value)
 #undef TASK_SIZE
 #define TASK_SIZE TASK_SIZE32
 
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-static __inline__ void
-cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value)
-{
-	unsigned long jiffies = cputime_to_jiffies(cputime);
-
-	value->tv_usec = (jiffies % HZ) * (1000000L / HZ);
-	value->tv_sec = jiffies / HZ;
-}
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
 
 #include "../../../fs/binfmt_elf.c"
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 1c8dd0f5cd5d..97f64c723a0c 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -1,7 +1,6 @@
 
 generic-y += barrier.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
diff --git a/arch/mn10300/include/asm/switch_to.h b/arch/mn10300/include/asm/switch_to.h
index 393d311735c8..67e333aa7629 100644
--- a/arch/mn10300/include/asm/switch_to.h
+++ b/arch/mn10300/include/asm/switch_to.h
@@ -16,7 +16,7 @@
 struct task_struct;
 struct thread_struct;
 
-#if !defined(CONFIG_LAZY_SAVE_FPU)
+#if defined(CONFIG_FPU) && !defined(CONFIG_LAZY_SAVE_FPU)
 struct fpu_state_struct;
 extern asmlinkage void fpu_save(struct fpu_state_struct *);
 #define switch_fpu(prev, next)						\
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index d63330e88379..35b0e883761a 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -6,7 +6,6 @@ generic-y += bitsperlong.h
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 2832f031fb11..ef8d1ccc3e45 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -12,7 +12,6 @@ generic-y += checksum.h
 generic-y += clkdev.h
 generic-y += cmpxchg-local.h
 generic-y += cmpxchg.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 91f53c07f410..4e179d770d69 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -2,7 +2,6 @@
 generic-y += auxvec.h
 generic-y += barrier.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h
index 3f9406d9b9d6..da87943328a5 100644
--- a/arch/parisc/include/asm/bitops.h
+++ b/arch/parisc/include/asm/bitops.h
@@ -6,7 +6,7 @@
 #endif
 
 #include <linux/compiler.h>
-#include <asm/types.h>		/* for BITS_PER_LONG/SHIFT_PER_LONG */
+#include <asm/types.h>
 #include <asm/byteorder.h>
 #include <asm/barrier.h>
 #include <linux/atomic.h>
@@ -17,6 +17,12 @@
  * to include/asm-i386/bitops.h or kerneldoc
  */
 
+#if __BITS_PER_LONG == 64
+#define SHIFT_PER_LONG 6
+#else
+#define SHIFT_PER_LONG 5
+#endif
+
 #define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))
 
 
diff --git a/arch/parisc/include/uapi/asm/bitsperlong.h b/arch/parisc/include/uapi/asm/bitsperlong.h
index e0a23c7bdd43..07fa7e50bdc0 100644
--- a/arch/parisc/include/uapi/asm/bitsperlong.h
+++ b/arch/parisc/include/uapi/asm/bitsperlong.h
@@ -3,10 +3,8 @@
 
 #if defined(__LP64__)
 #define __BITS_PER_LONG 64
-#define SHIFT_PER_LONG 6
 #else
 #define __BITS_PER_LONG 32
-#define SHIFT_PER_LONG 5
 #endif
 
 #include <asm-generic/bitsperlong.h>
diff --git a/arch/parisc/include/uapi/asm/swab.h b/arch/parisc/include/uapi/asm/swab.h
index e78403b129ef..928e1bbac98f 100644
--- a/arch/parisc/include/uapi/asm/swab.h
+++ b/arch/parisc/include/uapi/asm/swab.h
@@ -1,6 +1,7 @@
 #ifndef _PARISC_SWAB_H
 #define _PARISC_SWAB_H
 
+#include <asm/bitsperlong.h>
 #include <linux/types.h>
 #include <linux/compiler.h>
 
@@ -38,7 +39,7 @@ static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 }
 #define __arch_swab32 __arch_swab32
 
-#if BITS_PER_LONG > 32
+#if __BITS_PER_LONG > 32
 /*
 ** From "PA-RISC 2.0 Architecture", HP Professional Books.
 ** See Appendix I page 8 , "Endian Byte Swapping".
@@ -61,6 +62,6 @@ static inline __attribute_const__ __u64 __arch_swab64(__u64 x)
 	return x;
 }
 #define __arch_swab64 __arch_swab64
-#endif /* BITS_PER_LONG > 32 */
+#endif /* __BITS_PER_LONG > 32 */
 
 #endif /* _PARISC_SWAB_H */
diff --git a/arch/parisc/kernel/binfmt_elf32.c b/arch/parisc/kernel/binfmt_elf32.c
index 00dc66f9c2ba..f2adcf33f8f2 100644
--- a/arch/parisc/kernel/binfmt_elf32.c
+++ b/arch/parisc/kernel/binfmt_elf32.c
@@ -91,14 +91,7 @@ struct elf_prpsinfo32
 	current->thread.map_base = DEFAULT_MAP_BASE32; \
 	current->thread.task_size = DEFAULT_TASK_SIZE32 \
 
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-static __inline__ void
-cputime_to_compat_timeval(const cputime_t cputime, struct compat_timeval *value)
-{
-	unsigned long jiffies = cputime_to_jiffies(cputime);
-	value->tv_usec = (jiffies % HZ) * (1000000L / HZ);
-	value->tv_sec = jiffies / HZ;
-}
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
 
 #include "../../../fs/binfmt_elf.c"
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 2e66a887788e..068ed3607bac 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -36,6 +36,7 @@
 #undef PCI_DEBUG
 #include <linux/proc_fs.h>
 #include <linux/export.h>
+#include <linux/sched.h>
 
 #include <asm/processor.h>
 #include <asm/sections.h>
@@ -176,6 +177,7 @@ void __init setup_arch(char **cmdline_p)
 	conswitchp = &dummy_con;	/* we use do_take_over_console() later ! */
 #endif
 
+	clear_sched_clock_stable();
 }
 
 /*
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a8ee573fe610..281f4f1fcd1f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -164,7 +164,6 @@ config PPC
 	select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
 	select HAVE_ARCH_HARDENED_USERCOPY
 	select HAVE_KERNEL_GZIP
-	select HAVE_CC_STACKPROTECTOR
 
 config GENERIC_CSUM
 	def_bool CPU_LITTLE_ENDIAN
@@ -484,6 +483,7 @@ config RELOCATABLE
 	bool "Build a relocatable kernel"
 	depends on (PPC64 && !COMPILE_TEST) || (FLATMEM && (44x || FSL_BOOKE))
 	select NONSTATIC_KERNEL
+	select MODULE_REL_CRCS if MODVERSIONS
 	help
 	  This builds a kernel image that is capable of running at the
 	  location the kernel is loaded at. For ppc32, there is no any
diff --git a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
index c744569a20e1..a97296c64eb2 100644
--- a/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
+++ b/arch/powerpc/boot/dts/fsl/t2081si-post.dtsi
@@ -678,5 +678,6 @@
 		compatible = "fsl,t2080-l2-cache-controller";
 		reg = <0xc20000 0x40000>;
 		next-level-cache = <&cpc>;
+		interrupts = <16 2 1 9>;
 	};
 };
diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig
index 3ce91a3df27f..1d2d69dd6409 100644
--- a/arch/powerpc/configs/ppc6xx_defconfig
+++ b/arch/powerpc/configs/ppc6xx_defconfig
@@ -62,7 +62,6 @@ CONFIG_MPC8610_HPCD=y
 CONFIG_GEF_SBC610=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_STAT=m
-CONFIG_CPU_FREQ_STAT_DETAILS=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y
 CONFIG_CPU_FREQ_GOV_PERFORMANCE=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=m
diff --git a/arch/powerpc/include/asm/accounting.h b/arch/powerpc/include/asm/accounting.h
index c133246df467..3abcf98ed2e0 100644
--- a/arch/powerpc/include/asm/accounting.h
+++ b/arch/powerpc/include/asm/accounting.h
@@ -12,9 +12,17 @@
 
 /* Stuff for accurate time accounting */
 struct cpu_accounting_data {
-	unsigned long user_time;	/* accumulated usermode TB ticks */
-	unsigned long system_time;	/* accumulated system TB ticks */
-	unsigned long user_time_scaled;	/* accumulated usermode SPURR ticks */
+	/* Accumulated cputime values to flush on ticks*/
+	unsigned long utime;
+	unsigned long stime;
+	unsigned long utime_scaled;
+	unsigned long stime_scaled;
+	unsigned long gtime;
+	unsigned long hardirq_time;
+	unsigned long softirq_time;
+	unsigned long steal_time;
+	unsigned long idle_time;
+	/* Internal counters */
 	unsigned long starttime;	/* TB value snapshot */
 	unsigned long starttime_user;	/* TB value on exit to usermode */
 	unsigned long startspurr;	/* SPURR value snapshot */
diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h
index b312b152461b..6e834caa3720 100644
--- a/arch/powerpc/include/asm/cpu_has_feature.h
+++ b/arch/powerpc/include/asm/cpu_has_feature.h
@@ -23,7 +23,9 @@ static __always_inline bool cpu_has_feature(unsigned long feature)
 {
 	int i;
 
+#ifndef __clang__ /* clang can't cope with this */
 	BUILD_BUG_ON(!__builtin_constant_p(feature));
+#endif
 
 #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
 	if (!static_key_initialized) {
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index aa2e6a34b872..99b541865d8d 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -16,12 +16,7 @@
 #ifndef __POWERPC_CPUTIME_H
 #define __POWERPC_CPUTIME_H
 
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-#include <asm-generic/cputime.h>
-#ifdef __KERNEL__
-static inline void setup_cputime_one_jiffy(void) { }
-#endif
-#else
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 
 #include <linux/types.h>
 #include <linux/time.h>
@@ -36,65 +31,6 @@ typedef u64 __nocast cputime64_t;
 #define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
 
 #ifdef __KERNEL__
-
-/*
- * One jiffy in timebase units computed during initialization
- */
-extern cputime_t cputime_one_jiffy;
-
-/*
- * Convert cputime <-> jiffies
- */
-extern u64 __cputime_jiffies_factor;
-
-static inline unsigned long cputime_to_jiffies(const cputime_t ct)
-{
-	return mulhdu((__force u64) ct, __cputime_jiffies_factor);
-}
-
-static inline cputime_t jiffies_to_cputime(const unsigned long jif)
-{
-	u64 ct;
-	unsigned long sec;
-
-	/* have to be a little careful about overflow */
-	ct = jif % HZ;
-	sec = jif / HZ;
-	if (ct) {
-		ct *= tb_ticks_per_sec;
-		do_div(ct, HZ);
-	}
-	if (sec)
-		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return (__force cputime_t) ct;
-}
-
-static inline void setup_cputime_one_jiffy(void)
-{
-	cputime_one_jiffy = jiffies_to_cputime(1);
-}
-
-static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
-{
-	u64 ct;
-	u64 sec = jif;
-
-	/* have to be a little careful about overflow */
-	ct = do_div(sec, HZ);
-	if (ct) {
-		ct *= tb_ticks_per_sec;
-		do_div(ct, HZ);
-	}
-	if (sec)
-		ct += (u64) sec * tb_ticks_per_sec;
-	return (__force cputime64_t) ct;
-}
-
-static inline u64 cputime64_to_jiffies64(const cputime_t ct)
-{
-	return mulhdu((__force u64) ct, __cputime_jiffies_factor);
-}
-
 /*
  * Convert cputime <-> microseconds
  */
@@ -105,117 +41,6 @@ static inline unsigned long cputime_to_usecs(const cputime_t ct)
 	return mulhdu((__force u64) ct, __cputime_usec_factor);
 }
 
-static inline cputime_t usecs_to_cputime(const unsigned long us)
-{
-	u64 ct;
-	unsigned long sec;
-
-	/* have to be a little careful about overflow */
-	ct = us % 1000000;
-	sec = us / 1000000;
-	if (ct) {
-		ct *= tb_ticks_per_sec;
-		do_div(ct, 1000000);
-	}
-	if (sec)
-		ct += (cputime_t) sec * tb_ticks_per_sec;
-	return (__force cputime_t) ct;
-}
-
-#define usecs_to_cputime64(us)		usecs_to_cputime(us)
-
-/*
- * Convert cputime <-> seconds
- */
-extern u64 __cputime_sec_factor;
-
-static inline unsigned long cputime_to_secs(const cputime_t ct)
-{
-	return mulhdu((__force u64) ct, __cputime_sec_factor);
-}
-
-static inline cputime_t secs_to_cputime(const unsigned long sec)
-{
-	return (__force cputime_t)((u64) sec * tb_ticks_per_sec);
-}
-
-/*
- * Convert cputime <-> timespec
- */
-static inline void cputime_to_timespec(const cputime_t ct, struct timespec *p)
-{
-	u64 x = (__force u64) ct;
-	unsigned int frac;
-
-	frac = do_div(x, tb_ticks_per_sec);
-	p->tv_sec = x;
-	x = (u64) frac * 1000000000;
-	do_div(x, tb_ticks_per_sec);
-	p->tv_nsec = x;
-}
-
-static inline cputime_t timespec_to_cputime(const struct timespec *p)
-{
-	u64 ct;
-
-	ct = (u64) p->tv_nsec * tb_ticks_per_sec;
-	do_div(ct, 1000000000);
-	return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
-}
-
-/*
- * Convert cputime <-> timeval
- */
-static inline void cputime_to_timeval(const cputime_t ct, struct timeval *p)
-{
-	u64 x = (__force u64) ct;
-	unsigned int frac;
-
-	frac = do_div(x, tb_ticks_per_sec);
-	p->tv_sec = x;
-	x = (u64) frac * 1000000;
-	do_div(x, tb_ticks_per_sec);
-	p->tv_usec = x;
-}
-
-static inline cputime_t timeval_to_cputime(const struct timeval *p)
-{
-	u64 ct;
-
-	ct = (u64) p->tv_usec * tb_ticks_per_sec;
-	do_div(ct, 1000000);
-	return (__force cputime_t)(ct + (u64) p->tv_sec * tb_ticks_per_sec);
-}
-
-/*
- * Convert cputime <-> clock_t (units of 1/USER_HZ seconds)
- */
-extern u64 __cputime_clockt_factor;
-
-static inline unsigned long cputime_to_clock_t(const cputime_t ct)
-{
-	return mulhdu((__force u64) ct, __cputime_clockt_factor);
-}
-
-static inline cputime_t clock_t_to_cputime(const unsigned long clk)
-{
-	u64 ct;
-	unsigned long sec;
-
-	/* have to be a little careful about overflow */
-	ct = clk % USER_HZ;
-	sec = clk / USER_HZ;
-	if (ct) {
-		ct *= tb_ticks_per_sec;
-		do_div(ct, USER_HZ);
-	}
-	if (sec)
-		ct += (u64) sec * tb_ticks_per_sec;
-	return (__force cputime_t) ct;
-}
-
-#define cputime64_to_clock_t(ct)	cputime_to_clock_t((cputime_t)(ct))
-
 /*
  * PPC64 uses PACA which is task independent for storing accounting data while
  * PPC32 uses struct thread_info, therefore at task switch the accounting data
diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h
index a402f7f94896..47a03b9b528b 100644
--- a/arch/powerpc/include/asm/livepatch.h
+++ b/arch/powerpc/include/asm/livepatch.h
@@ -28,13 +28,6 @@ static inline int klp_check_compiler_support(void)
 	return 0;
 }
 
-static inline int klp_write_module_reloc(struct module *mod, unsigned long
-		type, unsigned long loc, unsigned long value)
-{
-	/* This requires infrastructure changes; we need the loadinfos. */
-	return -ENOSYS;
-}
-
 static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 {
 	regs->nip = ip;
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index a34c764ca8dd..233a7e8cc8e3 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -160,7 +160,9 @@ static __always_inline bool mmu_has_feature(unsigned long feature)
 {
 	int i;
 
+#ifndef __clang__ /* clang can't cope with this */
 	BUILD_BUG_ON(!__builtin_constant_p(feature));
+#endif
 
 #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
 	if (!static_key_initialized) {
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index cc12c61ef315..53885512b8d3 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -90,9 +90,5 @@ static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sec
 }
 #endif
 
-#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64)
-#define ARCH_RELOCATES_KCRCTAB
-#define reloc_start PHYSICAL_START
-#endif
 #endif /* __KERNEL__ */
 #endif	/* _ASM_POWERPC_MODULE_H */
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 6a6792bb39fb..708c3e592eeb 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -187,7 +187,6 @@ struct paca_struct {
 
 	/* Stuff for accurate time accounting */
 	struct cpu_accounting_data accounting;
-	u64 stolen_time;		/* TB ticks taken by hypervisor */
 	u64 dtl_ridx;			/* read index in dispatch log */
 	struct dtl_entry *dtl_curr;	/* pointer corresponding to dtl_ridx */
 
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 0d4531aa2052..dff79798903d 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -649,9 +649,10 @@
 #define   SRR1_ISI_N_OR_G	0x10000000 /* ISI: Access is no-exec or G */
 #define   SRR1_ISI_PROT		0x08000000 /* ISI: Other protection fault */
 #define   SRR1_WAKEMASK		0x00380000 /* reason for wakeup */
-#define   SRR1_WAKEMASK_P8	0x003c0000 /* reason for wakeup on POWER8 */
+#define   SRR1_WAKEMASK_P8	0x003c0000 /* reason for wakeup on POWER8 and 9 */
 #define   SRR1_WAKESYSERR	0x00300000 /* System error */
 #define   SRR1_WAKEEE		0x00200000 /* External interrupt */
+#define   SRR1_WAKEHVI		0x00240000 /* Hypervisor Virtualization Interrupt (P9) */
 #define   SRR1_WAKEMT		0x00280000 /* mtctrl */
 #define	  SRR1_WAKEHMI		0x00280000 /* Hypervisor maintenance */
 #define   SRR1_WAKEDEC		0x00180000 /* Decrementer interrupt */
diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h
deleted file mode 100644
index 6720190eabec..000000000000
--- a/arch/powerpc/include/asm/stackprotector.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- * GCC stack protector support.
- *
- * Stack protector works by putting predefined pattern at the start of
- * the stack frame and verifying that it hasn't been overwritten when
- * returning from the function.  The pattern is called stack canary
- * and gcc expects it to be defined by a global variable called
- * "__stack_chk_guard" on PPC.  This unfortunately means that on SMP
- * we cannot have a different canary value per task.
- */
-
-#ifndef _ASM_STACKPROTECTOR_H
-#define _ASM_STACKPROTECTOR_H
-
-#include <linux/random.h>
-#include <linux/version.h>
-#include <asm/reg.h>
-
-extern unsigned long __stack_chk_guard;
-
-/*
- * Initialize the stackprotector canary value.
- *
- * NOTE: this must only be called from functions that never return,
- * and it must always be inlined.
- */
-static __always_inline void boot_init_stack_canary(void)
-{
-	unsigned long canary;
-
-	/* Try to get a semi random initial value. */
-	get_random_bytes(&canary, sizeof(canary));
-	canary ^= mftb();
-	canary ^= LINUX_VERSION_CODE;
-
-	current->stack_canary = canary;
-	__stack_chk_guard = current->stack_canary;
-}
-
-#endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h
index f0b238516e9b..e0b9e576905a 100644
--- a/arch/powerpc/include/asm/xics.h
+++ b/arch/powerpc/include/asm/xics.h
@@ -44,6 +44,7 @@ static inline int icp_hv_init(void) { return -ENODEV; }
 
 #ifdef CONFIG_PPC_POWERNV
 extern int icp_opal_init(void);
+extern void icp_opal_flush_interrupt(void);
 #else
 static inline int icp_opal_init(void) { return -ENODEV; }
 #endif
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 23f8082d7bfa..f4c2b52e58b3 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -19,10 +19,6 @@ CFLAGS_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
 
-# -fstack-protector triggers protection checks in this code,
-# but it is being used too early to link to meaningful stack_chk logic.
-CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector)
-
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace early boot code
 CFLAGS_REMOVE_cputable.o = -mno-sched-epilog $(CC_FLAGS_FTRACE)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0601e6a7297c..9e8e771f8acb 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -91,9 +91,6 @@ int main(void)
 	DEFINE(TI_livepatch_sp, offsetof(struct thread_info, livepatch_sp));
 #endif
 
-#ifdef CONFIG_CC_STACKPROTECTOR
-	DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary));
-#endif
 	DEFINE(KSP, offsetof(struct thread_struct, ksp));
 	DEFINE(PT_REGS, offsetof(struct thread_struct, regs));
 #ifdef CONFIG_BOOKE
@@ -252,9 +249,9 @@ int main(void)
 	DEFINE(ACCOUNT_STARTTIME_USER,
 	       offsetof(struct paca_struct, accounting.starttime_user));
 	DEFINE(ACCOUNT_USER_TIME,
-	       offsetof(struct paca_struct, accounting.user_time));
+	       offsetof(struct paca_struct, accounting.utime));
 	DEFINE(ACCOUNT_SYSTEM_TIME,
-	       offsetof(struct paca_struct, accounting.system_time));
+	       offsetof(struct paca_struct, accounting.stime));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
 	DEFINE(PACA_NAPSTATELOST, offsetof(struct paca_struct, nap_state_lost));
 	DEFINE(PACA_SPRG_VDSO, offsetof(struct paca_struct, sprg_vdso));
@@ -265,9 +262,9 @@ int main(void)
 	DEFINE(ACCOUNT_STARTTIME_USER,
 	       offsetof(struct thread_info, accounting.starttime_user));
 	DEFINE(ACCOUNT_USER_TIME,
-	       offsetof(struct thread_info, accounting.user_time));
+	       offsetof(struct thread_info, accounting.utime));
 	DEFINE(ACCOUNT_SYSTEM_TIME,
-	       offsetof(struct thread_info, accounting.system_time));
+	       offsetof(struct thread_info, accounting.stime));
 #endif
 #endif /* CONFIG_PPC64 */
 
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index d88573bdd090..b94887165a10 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -545,7 +545,7 @@ static void *eeh_pe_detach_dev(void *data, void *userdata)
 static void *__eeh_clear_pe_frozen_state(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
-	bool *clear_sw_state = flag;
+	bool clear_sw_state = *(bool *)flag;
 	int i, rc = 1;
 
 	for (i = 0; rc && i < 3; i++)
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 5742dbdbee46..3841d749a430 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -674,11 +674,7 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_SPEFSCR,r0		/* restore SPEFSCR reg */
 END_FTR_SECTION_IFSET(CPU_FTR_SPE)
 #endif /* CONFIG_SPE */
-#if defined(CONFIG_CC_STACKPROTECTOR) && !defined(CONFIG_SMP)
-	lwz	r0,TSK_STACK_CANARY(r2)
-	lis	r4,__stack_chk_guard@ha
-	stw	r0,__stack_chk_guard@l(r4)
-#endif
+
 	lwz	r0,_CCR(r1)
 	mtcrf	0xFF,r0
 	/* r3-r12 are destroyed -- Cort */
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index bb1807184bad..0b0f89685b67 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -286,14 +286,6 @@ static void dedotify_versions(struct modversion_info *vers,
 	for (end = (void *)vers + size; vers < end; vers++)
 		if (vers->name[0] == '.') {
 			memmove(vers->name, vers->name+1, strlen(vers->name));
-#ifdef ARCH_RELOCATES_KCRCTAB
-			/* The TOC symbol has no CRC computed. To avoid CRC
-			 * check failing, we must force it to the expected
-			 * value (see CRC check in module.c).
-			 */
-			if (!strcmp(vers->name, "TOC."))
-				vers->crc = -(unsigned long)reloc_start;
-#endif
 		}
 }
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 04885cec24df..5dd056df0baa 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -64,12 +64,6 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 
-#ifdef CONFIG_CC_STACKPROTECTOR
-#include <linux/stackprotector.h>
-unsigned long __stack_chk_guard __read_mostly;
-EXPORT_SYMBOL(__stack_chk_guard);
-#endif
-
 /* Transactional Memory debug */
 #ifdef TM_DEBUG_SW
 #define TM_DEBUG(x...) printk(KERN_INFO x)
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index ec47a939cbdd..ac83eb04a8b8 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2834,6 +2834,9 @@ static void __init prom_find_boot_cpu(void)
 
 	cpu_pkg = call_prom("instance-to-package", 1, 1, prom_cpu);
 
+	if (!PHANDLE_VALID(cpu_pkg))
+		return;
+
 	prom_getprop(cpu_pkg, "reg", &rval, sizeof(rval));
 	prom.cpu = be32_to_cpu(rval);
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index bc2e08d415fa..14e485525e31 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -57,6 +57,7 @@
 #include <linux/clk-provider.h>
 #include <linux/suspend.h>
 #include <linux/rtc.h>
+#include <linux/cputime.h>
 #include <asm/trace.h>
 
 #include <asm/io.h>
@@ -72,7 +73,6 @@
 #include <asm/smp.h>
 #include <asm/vdso_datapage.h>
 #include <asm/firmware.h>
-#include <asm/cputime.h>
 #include <asm/asm-prototypes.h>
 
 /* powerpc clocksource/clockevent code */
@@ -152,20 +152,11 @@ EXPORT_SYMBOL_GPL(ppc_tb_freq);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 /*
- * Factors for converting from cputime_t (timebase ticks) to
- * jiffies, microseconds, seconds, and clock_t (1/USER_HZ seconds).
- * These are all stored as 0.64 fixed-point binary fractions.
+ * Factor for converting from cputime_t (timebase ticks) to
+ * microseconds. This is stored as 0.64 fixed-point binary fraction.
  */
-u64 __cputime_jiffies_factor;
-EXPORT_SYMBOL(__cputime_jiffies_factor);
 u64 __cputime_usec_factor;
 EXPORT_SYMBOL(__cputime_usec_factor);
-u64 __cputime_sec_factor;
-EXPORT_SYMBOL(__cputime_sec_factor);
-u64 __cputime_clockt_factor;
-EXPORT_SYMBOL(__cputime_clockt_factor);
-
-cputime_t cputime_one_jiffy;
 
 #ifdef CONFIG_PPC_SPLPAR
 void (*dtl_consumer)(struct dtl_entry *, u64);
@@ -181,14 +172,8 @@ static void calc_cputime_factors(void)
 {
 	struct div_result res;
 
-	div128_by_32(HZ, 0, tb_ticks_per_sec, &res);
-	__cputime_jiffies_factor = res.result_low;
 	div128_by_32(1000000, 0, tb_ticks_per_sec, &res);
 	__cputime_usec_factor = res.result_low;
-	div128_by_32(1, 0, tb_ticks_per_sec, &res);
-	__cputime_sec_factor = res.result_low;
-	div128_by_32(USER_HZ, 0, tb_ticks_per_sec, &res);
-	__cputime_clockt_factor = res.result_low;
 }
 
 /*
@@ -271,25 +256,19 @@ void accumulate_stolen_time(void)
 
 	sst = scan_dispatch_log(acct->starttime_user);
 	ust = scan_dispatch_log(acct->starttime);
-	acct->system_time -= sst;
-	acct->user_time -= ust;
-	local_paca->stolen_time += ust + sst;
+	acct->stime -= sst;
+	acct->utime -= ust;
+	acct->steal_time += ust + sst;
 
 	local_paca->soft_enabled = save_soft_enabled;
 }
 
 static inline u64 calculate_stolen_time(u64 stop_tb)
 {
-	u64 stolen = 0;
+	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx))
+		return scan_dispatch_log(stop_tb);
 
-	if (get_paca()->dtl_ridx != be64_to_cpu(get_lppaca()->dtl_idx)) {
-		stolen = scan_dispatch_log(stop_tb);
-		get_paca()->accounting.system_time -= stolen;
-	}
-
-	stolen += get_paca()->stolen_time;
-	get_paca()->stolen_time = 0;
-	return stolen;
+	return 0;
 }
 
 #else /* CONFIG_PPC_SPLPAR */
@@ -305,28 +284,27 @@ static inline u64 calculate_stolen_time(u64 stop_tb)
  * or soft irq state.
  */
 static unsigned long vtime_delta(struct task_struct *tsk,
-				 unsigned long *sys_scaled,
-				 unsigned long *stolen)
+				 unsigned long *stime_scaled,
+				 unsigned long *steal_time)
 {
 	unsigned long now, nowscaled, deltascaled;
-	unsigned long udelta, delta, user_scaled;
+	unsigned long stime;
+	unsigned long utime, utime_scaled;
 	struct cpu_accounting_data *acct = get_accounting(tsk);
 
 	WARN_ON_ONCE(!irqs_disabled());
 
 	now = mftb();
 	nowscaled = read_spurr(now);
-	acct->system_time += now - acct->starttime;
+	stime = now - acct->starttime;
 	acct->starttime = now;
 	deltascaled = nowscaled - acct->startspurr;
 	acct->startspurr = nowscaled;
 
-	*stolen = calculate_stolen_time(now);
+	*steal_time = calculate_stolen_time(now);
 
-	delta = acct->system_time;
-	acct->system_time = 0;
-	udelta = acct->user_time - acct->utime_sspurr;
-	acct->utime_sspurr = acct->user_time;
+	utime = acct->utime - acct->utime_sspurr;
+	acct->utime_sspurr = acct->utime;
 
 	/*
 	 * Because we don't read the SPURR on every kernel entry/exit,
@@ -338,62 +316,105 @@ static unsigned long vtime_delta(struct task_struct *tsk,
 	 * the user ticks get saved up in paca->user_time_scaled to be
 	 * used by account_process_tick.
 	 */
-	*sys_scaled = delta;
-	user_scaled = udelta;
-	if (deltascaled != delta + udelta) {
-		if (udelta) {
-			*sys_scaled = deltascaled * delta / (delta + udelta);
-			user_scaled = deltascaled - *sys_scaled;
+	*stime_scaled = stime;
+	utime_scaled = utime;
+	if (deltascaled != stime + utime) {
+		if (utime) {
+			*stime_scaled = deltascaled * stime / (stime + utime);
+			utime_scaled = deltascaled - *stime_scaled;
 		} else {
-			*sys_scaled = deltascaled;
+			*stime_scaled = deltascaled;
 		}
 	}
-	acct->user_time_scaled += user_scaled;
+	acct->utime_scaled += utime_scaled;
 
-	return delta;
+	return stime;
 }
 
 void vtime_account_system(struct task_struct *tsk)
 {
-	unsigned long delta, sys_scaled, stolen;
+	unsigned long stime, stime_scaled, steal_time;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
+
+	stime = vtime_delta(tsk, &stime_scaled, &steal_time);
 
-	delta = vtime_delta(tsk, &sys_scaled, &stolen);
-	account_system_time(tsk, 0, delta);
-	tsk->stimescaled += sys_scaled;
-	if (stolen)
-		account_steal_time(stolen);
+	stime -= min(stime, steal_time);
+	acct->steal_time += steal_time;
+
+	if ((tsk->flags & PF_VCPU) && !irq_count()) {
+		acct->gtime += stime;
+		acct->utime_scaled += stime_scaled;
+	} else {
+		if (hardirq_count())
+			acct->hardirq_time += stime;
+		else if (in_serving_softirq())
+			acct->softirq_time += stime;
+		else
+			acct->stime += stime;
+
+		acct->stime_scaled += stime_scaled;
+	}
 }
 EXPORT_SYMBOL_GPL(vtime_account_system);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
-	unsigned long delta, sys_scaled, stolen;
+	unsigned long stime, stime_scaled, steal_time;
+	struct cpu_accounting_data *acct = get_accounting(tsk);
 
-	delta = vtime_delta(tsk, &sys_scaled, &stolen);
-	account_idle_time(delta + stolen);
+	stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+	acct->idle_time += stime + steal_time;
 }
 
 /*
- * Transfer the user time accumulated in the paca
- * by the exception entry and exit code to the generic
- * process user time records.
+ * Account the whole cputime accumulated in the paca
  * Must be called with interrupts disabled.
  * Assumes that vtime_account_system/idle() has been called
  * recently (i.e. since the last entry from usermode) so that
  * get_paca()->user_time_scaled is up to date.
  */
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
 {
-	cputime_t utime, utimescaled;
 	struct cpu_accounting_data *acct = get_accounting(tsk);
 
-	utime = acct->user_time;
-	utimescaled = acct->user_time_scaled;
-	acct->user_time = 0;
-	acct->user_time_scaled = 0;
+	if (acct->utime)
+		account_user_time(tsk, cputime_to_nsecs(acct->utime));
+
+	if (acct->utime_scaled)
+		tsk->utimescaled += cputime_to_nsecs(acct->utime_scaled);
+
+	if (acct->gtime)
+		account_guest_time(tsk, cputime_to_nsecs(acct->gtime));
+
+	if (acct->steal_time)
+		account_steal_time(cputime_to_nsecs(acct->steal_time));
+
+	if (acct->idle_time)
+		account_idle_time(cputime_to_nsecs(acct->idle_time));
+
+	if (acct->stime)
+		account_system_index_time(tsk, cputime_to_nsecs(acct->stime),
+					  CPUTIME_SYSTEM);
+	if (acct->stime_scaled)
+		tsk->stimescaled += cputime_to_nsecs(acct->stime_scaled);
+
+	if (acct->hardirq_time)
+		account_system_index_time(tsk, cputime_to_nsecs(acct->hardirq_time),
+					  CPUTIME_IRQ);
+	if (acct->softirq_time)
+		account_system_index_time(tsk, cputime_to_nsecs(acct->softirq_time),
+					  CPUTIME_SOFTIRQ);
+
+	acct->utime = 0;
+	acct->utime_scaled = 0;
 	acct->utime_sspurr = 0;
-	account_user_time(tsk, utime);
-	tsk->utimescaled += utimescaled;
+	acct->gtime = 0;
+	acct->steal_time = 0;
+	acct->idle_time = 0;
+	acct->stime = 0;
+	acct->stime_scaled = 0;
+	acct->hardirq_time = 0;
+	acct->softirq_time = 0;
 }
 
 #ifdef CONFIG_PPC32
@@ -407,8 +428,7 @@ void arch_vtime_task_switch(struct task_struct *prev)
 	struct cpu_accounting_data *acct = get_accounting(current);
 
 	acct->starttime = get_accounting(prev)->starttime;
-	acct->system_time = 0;
-	acct->user_time = 0;
+	acct->startspurr = get_accounting(prev)->startspurr;
 }
 #endif /* CONFIG_PPC32 */
 
@@ -1018,7 +1038,6 @@ void __init time_init(void)
 	tb_ticks_per_sec = ppc_tb_freq;
 	tb_ticks_per_usec = ppc_tb_freq / 1000000;
 	calc_cputime_factors();
-	setup_cputime_one_jiffy();
 
 	/*
 	 * Compute scale factor for sched_clock.
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 6fd30ac7d14a..62a50d6d1053 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -253,8 +253,11 @@ int do_page_fault(struct pt_regs *regs, unsigned long address,
 	if (unlikely(debugger_fault_handler(regs)))
 		goto bail;
 
-	/* On a kernel SLB miss we can only check for a valid exception entry */
-	if (!user_mode(regs) && (address >= TASK_SIZE)) {
+	/*
+	 * The kernel should never take an execute fault nor should it
+	 * take a page fault to a kernel address.
+	 */
+	if (!user_mode(regs) && (is_exec || (address >= TASK_SIZE))) {
 		rc = SIGSEGV;
 		goto bail;
 	}
@@ -391,20 +394,6 @@ good_area:
 
 	if (is_exec) {
 		/*
-		 * An execution fault + no execute ?
-		 *
-		 * On CPUs that don't have CPU_FTR_COHERENT_ICACHE we
-		 * deliberately create NX mappings, and use the fault to do the
-		 * cache flush. This is usually handled in hash_page_do_lazy_icache()
-		 * but we could end up here if that races with a concurrent PTE
-		 * update. In that case we need to fall through here to the VMA
-		 * check below.
-		 */
-		if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE) &&
-			(regs->msr & SRR1_ISI_N_OR_G))
-			goto bad_area;
-
-		/*
 		 * Allow execution from readable areas if the MMU does not
 		 * provide separate controls over reading and executing.
 		 *
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 93abf8a9813d..8e1588021d1c 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -347,7 +347,8 @@ early_param("disable_radix", parse_disable_radix);
 void __init mmu_early_init_devtree(void)
 {
 	/* Disable radix mode based on kernel command line. */
-	if (disable_radix)
+	/* We don't yet have the machinery to do radix as a guest. */
+	if (disable_radix || !(mfmsr() & MSR_HV))
 		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
 
 	if (early_radix_enabled())
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index cfa53ccc8baf..34f1a0dbc898 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -65,7 +65,7 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa,
 		if (!pmdp)
 			return -ENOMEM;
 		if (map_page_size == PMD_SIZE) {
-			ptep = (pte_t *)pudp;
+			ptep = pmdp_ptep(pmdp);
 			goto set_the_pte;
 		}
 		ptep = pte_alloc_kernel(pmdp, ea);
@@ -90,7 +90,7 @@ int radix__map_kernel_page(unsigned long ea, unsigned long pa,
 		}
 		pmdp = pmd_offset(pudp, ea);
 		if (map_page_size == PMD_SIZE) {
-			ptep = (pte_t *)pudp;
+			ptep = pmdp_ptep(pmdp);
 			goto set_the_pte;
 		}
 		if (!pmd_present(*pmdp)) {
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 61b79119065f..952713d6cf04 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -50,9 +50,7 @@ static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
 	for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
 		__tlbiel_pid(pid, set, ric);
 	}
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
-	return;
+	asm volatile(PPC_INVALIDATE_ERAT "; isync" : : :"memory");
 }
 
 static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
@@ -85,8 +83,6 @@ static inline void _tlbiel_va(unsigned long va, unsigned long pid,
 	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
 	asm volatile("ptesync": : :"memory");
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
 }
 
 static inline void _tlbie_va(unsigned long va, unsigned long pid,
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index c789258ae1e1..eec0e8d0454d 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -155,8 +155,10 @@ static void pnv_smp_cpu_kill_self(void)
 		wmask = SRR1_WAKEMASK_P8;
 
 	idle_states = pnv_get_supported_cpuidle_states();
+
 	/* We don't want to take decrementer interrupts while we are offline,
-	 * so clear LPCR:PECE1. We keep PECE2 enabled.
+	 * so clear LPCR:PECE1. We keep PECE2 (and LPCR_PECE_HVEE on P9)
+	 * enabled as to let IPIs in.
 	 */
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 
@@ -206,8 +208,12 @@ static void pnv_smp_cpu_kill_self(void)
 		 * contains 0.
 		 */
 		if (((srr1 & wmask) == SRR1_WAKEEE) ||
+		    ((srr1 & wmask) == SRR1_WAKEHVI) ||
 		    (local_paca->irq_happened & PACA_IRQ_EE)) {
-			icp_native_flush_interrupt();
+			if (cpu_has_feature(CPU_FTR_ARCH_300))
+				icp_opal_flush_interrupt();
+			else
+				icp_native_flush_interrupt();
 		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
 			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
@@ -221,6 +227,8 @@ static void pnv_smp_cpu_kill_self(void)
 		if (srr1 && !generic_check_cpu_restart(cpu))
 			DBG("CPU%d Unexpected exit while offline !\n", cpu);
 	}
+
+	/* Re-enable decrementer interrupts */
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1);
 	DBG("CPU%d coming online...\n", cpu);
 }
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index 60c57657c772..f9670eabfcfa 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -120,18 +120,49 @@ static void icp_opal_cause_ipi(int cpu, unsigned long data)
 {
 	int hw_cpu = get_hard_smp_processor_id(cpu);
 
+	kvmppc_set_host_ipi(cpu, 1);
 	opal_int_set_mfrr(hw_cpu, IPI_PRIORITY);
 }
 
 static irqreturn_t icp_opal_ipi_action(int irq, void *dev_id)
 {
-	int hw_cpu = hard_smp_processor_id();
+	int cpu = smp_processor_id();
 
-	opal_int_set_mfrr(hw_cpu, 0xff);
+	kvmppc_set_host_ipi(cpu, 0);
+	opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff);
 
 	return smp_ipi_demux();
 }
 
+/*
+ * Called when an interrupt is received on an off-line CPU to
+ * clear the interrupt, so that the CPU can go back to nap mode.
+ */
+void icp_opal_flush_interrupt(void)
+{
+	unsigned int xirr;
+	unsigned int vec;
+
+	do {
+		xirr = icp_opal_get_xirr();
+		vec = xirr & 0x00ffffff;
+		if (vec == XICS_IRQ_SPURIOUS)
+			break;
+		if (vec == XICS_IPI) {
+			/* Clear pending IPI */
+			int cpu = smp_processor_id();
+			kvmppc_set_host_ipi(cpu, 0);
+			opal_int_set_mfrr(get_hard_smp_processor_id(cpu), 0xff);
+		} else {
+			pr_err("XICS: hw interrupt 0x%x to offline cpu, "
+			       "disabling\n", vec);
+			xics_mask_unknown_vec(vec);
+		}
+
+		/* EOI the interrupt */
+	} while (opal_int_eoi(xirr) > 0);
+}
+
 #endif /* CONFIG_SMP */
 
 static const struct icp_ops icp_opal_ops = {
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 9c0e17cf6886..3f864c36d847 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2287,14 +2287,14 @@ static void dump_one_paca(int cpu)
 	DUMP(p, subcore_sibling_mask, "x");
 #endif
 
-	DUMP(p, accounting.user_time, "llx");
-	DUMP(p, accounting.system_time, "llx");
-	DUMP(p, accounting.user_time_scaled, "llx");
+	DUMP(p, accounting.utime, "llx");
+	DUMP(p, accounting.stime, "llx");
+	DUMP(p, accounting.utime_scaled, "llx");
 	DUMP(p, accounting.starttime, "llx");
 	DUMP(p, accounting.starttime_user, "llx");
 	DUMP(p, accounting.startspurr, "llx");
 	DUMP(p, accounting.utime_sspurr, "llx");
-	DUMP(p, stolen_time, "llx");
+	DUMP(p, accounting.steal_time, "llx");
 #undef DUMP
 
 	catch_memory_errors = 0;
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index 69b23b25ac34..08b9e942a262 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -113,21 +113,21 @@ static void appldata_get_os_data(void *data)
 	j = 0;
 	for_each_online_cpu(i) {
 		os_data->os_cpu[j].per_cpu_user =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
 		os_data->os_cpu[j].per_cpu_nice =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
 		os_data->os_cpu[j].per_cpu_system =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
 		os_data->os_cpu[j].per_cpu_idle =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
 		os_data->os_cpu[j].per_cpu_irq =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
 		os_data->os_cpu[j].per_cpu_softirq =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
 		os_data->os_cpu[j].per_cpu_iowait =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
 		os_data->os_cpu[j].per_cpu_steal =
-			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
+			nsecs_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
 		os_data->os_cpu[j].cpu_id = i;
 		j++;
 	}
diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h
index 221b454c734a..d1c407ddf703 100644
--- a/arch/s390/include/asm/cputime.h
+++ b/arch/s390/include/asm/cputime.h
@@ -25,33 +25,6 @@ static inline unsigned long __div(unsigned long long n, unsigned long base)
 	return n / base;
 }
 
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-
-/*
- * Convert cputime to jiffies and back.
- */
-static inline unsigned long cputime_to_jiffies(const cputime_t cputime)
-{
-	return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / HZ);
-}
-
-static inline cputime_t jiffies_to_cputime(const unsigned int jif)
-{
-	return (__force cputime_t)(jif * (CPUTIME_PER_SEC / HZ));
-}
-
-static inline u64 cputime64_to_jiffies64(cputime64_t cputime)
-{
-	unsigned long long jif = (__force unsigned long long) cputime;
-	do_div(jif, CPUTIME_PER_SEC / HZ);
-	return jif;
-}
-
-static inline cputime64_t jiffies64_to_cputime64(const u64 jif)
-{
-	return (__force cputime64_t)(jif * (CPUTIME_PER_SEC / HZ));
-}
-
 /*
  * Convert cputime to microseconds and back.
  */
@@ -60,88 +33,8 @@ static inline unsigned int cputime_to_usecs(const cputime_t cputime)
 	return (__force unsigned long long) cputime >> 12;
 }
 
-static inline cputime_t usecs_to_cputime(const unsigned int m)
-{
-	return (__force cputime_t)(m * CPUTIME_PER_USEC);
-}
-
-#define usecs_to_cputime64(m)		usecs_to_cputime(m)
-
-/*
- * Convert cputime to milliseconds and back.
- */
-static inline unsigned int cputime_to_secs(const cputime_t cputime)
-{
-	return __div((__force unsigned long long) cputime, CPUTIME_PER_SEC / 2) >> 1;
-}
-
-static inline cputime_t secs_to_cputime(const unsigned int s)
-{
-	return (__force cputime_t)(s * CPUTIME_PER_SEC);
-}
-
-/*
- * Convert cputime to timespec and back.
- */
-static inline cputime_t timespec_to_cputime(const struct timespec *value)
-{
-	unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC;
-	return (__force cputime_t)(ret + __div(value->tv_nsec * CPUTIME_PER_USEC, NSEC_PER_USEC));
-}
-
-static inline void cputime_to_timespec(const cputime_t cputime,
-				       struct timespec *value)
-{
-	unsigned long long __cputime = (__force unsigned long long) cputime;
-	value->tv_nsec = (__cputime % CPUTIME_PER_SEC) * NSEC_PER_USEC / CPUTIME_PER_USEC;
-	value->tv_sec = __cputime / CPUTIME_PER_SEC;
-}
-
-/*
- * Convert cputime to timeval and back.
- * Since cputime and timeval have the same resolution (microseconds)
- * this is easy.
- */
-static inline cputime_t timeval_to_cputime(const struct timeval *value)
-{
-	unsigned long long ret = value->tv_sec * CPUTIME_PER_SEC;
-	return (__force cputime_t)(ret + value->tv_usec * CPUTIME_PER_USEC);
-}
-
-static inline void cputime_to_timeval(const cputime_t cputime,
-				      struct timeval *value)
-{
-	unsigned long long __cputime = (__force unsigned long long) cputime;
-	value->tv_usec = (__cputime % CPUTIME_PER_SEC) / CPUTIME_PER_USEC;
-	value->tv_sec = __cputime / CPUTIME_PER_SEC;
-}
-
-/*
- * Convert cputime to clock and back.
- */
-static inline clock_t cputime_to_clock_t(cputime_t cputime)
-{
-	unsigned long long clock = (__force unsigned long long) cputime;
-	do_div(clock, CPUTIME_PER_SEC / USER_HZ);
-	return clock;
-}
-
-static inline cputime_t clock_t_to_cputime(unsigned long x)
-{
-	return (__force cputime_t)(x * (CPUTIME_PER_SEC / USER_HZ));
-}
-
-/*
- * Convert cputime64 to clock.
- */
-static inline clock_t cputime64_to_clock_t(cputime64_t cputime)
-{
-	unsigned long long clock = (__force unsigned long long) cputime;
-	do_div(clock, CPUTIME_PER_SEC / USER_HZ);
-	return clock;
-}
 
-cputime64_t arch_cpu_idle_time(int cpu);
+u64 arch_cpu_idle_time(int cpu);
 
 #define arch_idle_time(cpu) arch_cpu_idle_time(cpu)
 
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 9bfad2ad6312..61261e0e95c0 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -85,53 +85,56 @@ struct lowcore {
 	__u64	mcck_enter_timer;		/* 0x02c0 */
 	__u64	exit_timer;			/* 0x02c8 */
 	__u64	user_timer;			/* 0x02d0 */
-	__u64	system_timer;			/* 0x02d8 */
-	__u64	steal_timer;			/* 0x02e0 */
-	__u64	last_update_timer;		/* 0x02e8 */
-	__u64	last_update_clock;		/* 0x02f0 */
-	__u64	int_clock;			/* 0x02f8 */
-	__u64	mcck_clock;			/* 0x0300 */
-	__u64	clock_comparator;		/* 0x0308 */
+	__u64	guest_timer;			/* 0x02d8 */
+	__u64	system_timer;			/* 0x02e0 */
+	__u64	hardirq_timer;			/* 0x02e8 */
+	__u64	softirq_timer;			/* 0x02f0 */
+	__u64	steal_timer;			/* 0x02f8 */
+	__u64	last_update_timer;		/* 0x0300 */
+	__u64	last_update_clock;		/* 0x0308 */
+	__u64	int_clock;			/* 0x0310 */
+	__u64	mcck_clock;			/* 0x0318 */
+	__u64	clock_comparator;		/* 0x0320 */
 
 	/* Current process. */
-	__u64	current_task;			/* 0x0310 */
-	__u8	pad_0x318[0x320-0x318];		/* 0x0318 */
-	__u64	kernel_stack;			/* 0x0320 */
+	__u64	current_task;			/* 0x0328 */
+	__u8	pad_0x318[0x320-0x318];		/* 0x0330 */
+	__u64	kernel_stack;			/* 0x0338 */
 
 	/* Interrupt, panic and restart stack. */
-	__u64	async_stack;			/* 0x0328 */
-	__u64	panic_stack;			/* 0x0330 */
-	__u64	restart_stack;			/* 0x0338 */
+	__u64	async_stack;			/* 0x0340 */
+	__u64	panic_stack;			/* 0x0348 */
+	__u64	restart_stack;			/* 0x0350 */
 
 	/* Restart function and parameter. */
-	__u64	restart_fn;			/* 0x0340 */
-	__u64	restart_data;			/* 0x0348 */
-	__u64	restart_source;			/* 0x0350 */
+	__u64	restart_fn;			/* 0x0358 */
+	__u64	restart_data;			/* 0x0360 */
+	__u64	restart_source;			/* 0x0368 */
 
 	/* Address space pointer. */
-	__u64	kernel_asce;			/* 0x0358 */
-	__u64	user_asce;			/* 0x0360 */
+	__u64	kernel_asce;			/* 0x0370 */
+	__u64	user_asce;			/* 0x0378 */
 
 	/*
 	 * The lpp and current_pid fields form a
 	 * 64-bit value that is set as program
 	 * parameter with the LPP instruction.
 	 */
-	__u32	lpp;				/* 0x0368 */
-	__u32	current_pid;			/* 0x036c */
+	__u32	lpp;				/* 0x0380 */
+	__u32	current_pid;			/* 0x0384 */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x0370 */
-	__u32	softirq_pending;		/* 0x0374 */
-	__u64	percpu_offset;			/* 0x0378 */
-	__u64	vdso_per_cpu_data;		/* 0x0380 */
-	__u64	machine_flags;			/* 0x0388 */
-	__u32	preempt_count;			/* 0x0390 */
-	__u8	pad_0x0394[0x0398-0x0394];	/* 0x0394 */
-	__u64	gmap;				/* 0x0398 */
-	__u32	spinlock_lockval;		/* 0x03a0 */
-	__u32	fpu_flags;			/* 0x03a4 */
-	__u8	pad_0x03a8[0x0400-0x03a8];	/* 0x03a8 */
+	__u32	cpu_nr;				/* 0x0388 */
+	__u32	softirq_pending;		/* 0x038c */
+	__u64	percpu_offset;			/* 0x0390 */
+	__u64	vdso_per_cpu_data;		/* 0x0398 */
+	__u64	machine_flags;			/* 0x03a0 */
+	__u32	preempt_count;			/* 0x03a8 */
+	__u8	pad_0x03ac[0x03b0-0x03ac];	/* 0x03ac */
+	__u64	gmap;				/* 0x03b0 */
+	__u32	spinlock_lockval;		/* 0x03b8 */
+	__u32	fpu_flags;			/* 0x03bc */
+	__u8	pad_0x03c0[0x0400-0x03c0];	/* 0x03c0 */
 
 	/* Per cpu primary space access list */
 	__u32	paste[16];			/* 0x0400 */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 6bca916a5ba0..977a5b6501b8 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -111,7 +111,10 @@ struct thread_struct {
 	unsigned int  acrs[NUM_ACRS];
         unsigned long ksp;              /* kernel stack pointer             */
 	unsigned long user_timer;	/* task cputime in user space */
+	unsigned long guest_timer;	/* task cputime in kvm guest */
 	unsigned long system_timer;	/* task cputime in kernel space */
+	unsigned long hardirq_timer;	/* task cputime in hardirq context */
+	unsigned long softirq_timer;	/* task cputime in softirq context */
 	unsigned long sys_call_table;	/* system call table address */
 	mm_segment_t mm_segment;
 	unsigned long gmap_addr;	/* address of last gmap fault. */
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index 7a55c29b0b33..d3bf69ef42cf 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -12,7 +12,7 @@
 #include <linux/notifier.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
-#include <asm/cputime.h>
+#include <linux/cputime.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
 #include "entry.h"
@@ -43,7 +43,7 @@ void enabled_wait(void)
 	idle->clock_idle_enter = idle->clock_idle_exit = 0ULL;
 	idle->idle_time += idle_time;
 	idle->idle_count++;
-	account_idle_time(idle_time);
+	account_idle_time(cputime_to_nsecs(idle_time));
 	write_seqcount_end(&idle->seqcount);
 }
 NOKPROBE_SYMBOL(enabled_wait);
@@ -84,7 +84,7 @@ static ssize_t show_idle_time(struct device *dev,
 }
 DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 
-cputime64_t arch_cpu_idle_time(int cpu)
+u64 arch_cpu_idle_time(int cpu)
 {
 	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
 	unsigned long long now, idle_enter, idle_exit;
@@ -96,7 +96,8 @@ cputime64_t arch_cpu_idle_time(int cpu)
 		idle_enter = ACCESS_ONCE(idle->clock_idle_enter);
 		idle_exit = ACCESS_ONCE(idle->clock_idle_exit);
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-	return idle_enter ? ((idle_exit ?: now) - idle_enter) : 0;
+
+	return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0);
 }
 
 void arch_cpu_idle_enter(void)
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 7447ba509c30..12020b55887b 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -963,6 +963,11 @@ static int s390_fpregs_set(struct task_struct *target,
 	if (target == current)
 		save_fpu_regs();
 
+	if (MACHINE_HAS_VX)
+		convert_vx_to_fp(fprs, target->thread.fpu.vxrs);
+	else
+		memcpy(&fprs, target->thread.fpu.fprs, sizeof(fprs));
+
 	/* If setting FPC, must validate it first. */
 	if (count > 0 && pos < offsetof(s390_fp_regs, fprs)) {
 		u32 ufpc[2] = { target->thread.fpu.fpc, 0 };
@@ -1067,6 +1072,9 @@ static int s390_vxrs_low_set(struct task_struct *target,
 	if (target == current)
 		save_fpu_regs();
 
+	for (i = 0; i < __NUM_VXRS_LOW; i++)
+		vxrs[i] = *((__u64 *)(target->thread.fpu.vxrs + i) + 1);
+
 	rc = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vxrs, 0, -1);
 	if (rc == 0)
 		for (i = 0; i < __NUM_VXRS_LOW; i++)
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 1b5c5ee9fc1b..b4a3e9e06ef2 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -6,13 +6,13 @@
  */
 
 #include <linux/kernel_stat.h>
+#include <linux/cputime.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/timex.h>
 #include <linux/types.h>
 #include <linux/time.h>
 
-#include <asm/cputime.h>
 #include <asm/vtimer.h>
 #include <asm/vtime.h>
 #include <asm/cpu_mf.h>
@@ -90,14 +90,41 @@ static void update_mt_scaling(void)
 	__this_cpu_write(mt_scaling_jiffies, jiffies_64);
 }
 
+static inline u64 update_tsk_timer(unsigned long *tsk_vtime, u64 new)
+{
+	u64 delta;
+
+	delta = new - *tsk_vtime;
+	*tsk_vtime = new;
+	return delta;
+}
+
+
+static inline u64 scale_vtime(u64 vtime)
+{
+	u64 mult = __this_cpu_read(mt_scaling_mult);
+	u64 div = __this_cpu_read(mt_scaling_div);
+
+	if (smp_cpu_mtid)
+		return vtime * mult / div;
+	return vtime;
+}
+
+static void account_system_index_scaled(struct task_struct *p,
+					cputime_t cputime, cputime_t scaled,
+					enum cpu_usage_stat index)
+{
+	p->stimescaled += cputime_to_nsecs(scaled);
+	account_system_index_time(p, cputime_to_nsecs(cputime), index);
+}
+
 /*
  * Update process times based on virtual cpu times stored by entry.S
  * to the lowcore fields user_timer, system_timer & steal_clock.
  */
 static int do_account_vtime(struct task_struct *tsk)
 {
-	u64 timer, clock, user, system, steal;
-	u64 user_scaled, system_scaled;
+	u64 timer, clock, user, guest, system, hardirq, softirq, steal;
 
 	timer = S390_lowcore.last_update_timer;
 	clock = S390_lowcore.last_update_clock;
@@ -110,53 +137,76 @@ static int do_account_vtime(struct task_struct *tsk)
 #endif
 		: "=m" (S390_lowcore.last_update_timer),
 		  "=m" (S390_lowcore.last_update_clock));
-	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
-	S390_lowcore.steal_timer += S390_lowcore.last_update_clock - clock;
+	clock = S390_lowcore.last_update_clock - clock;
+	timer -= S390_lowcore.last_update_timer;
+
+	if (hardirq_count())
+		S390_lowcore.hardirq_timer += timer;
+	else
+		S390_lowcore.system_timer += timer;
 
 	/* Update MT utilization calculation */
 	if (smp_cpu_mtid &&
 	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
 		update_mt_scaling();
 
-	user = S390_lowcore.user_timer - tsk->thread.user_timer;
-	S390_lowcore.steal_timer -= user;
-	tsk->thread.user_timer = S390_lowcore.user_timer;
-
-	system = S390_lowcore.system_timer - tsk->thread.system_timer;
-	S390_lowcore.steal_timer -= system;
-	tsk->thread.system_timer = S390_lowcore.system_timer;
-
-	user_scaled = user;
-	system_scaled = system;
-	/* Do MT utilization scaling */
-	if (smp_cpu_mtid) {
-		u64 mult = __this_cpu_read(mt_scaling_mult);
-		u64 div = __this_cpu_read(mt_scaling_div);
+	/* Calculate cputime delta */
+	user = update_tsk_timer(&tsk->thread.user_timer,
+				READ_ONCE(S390_lowcore.user_timer));
+	guest = update_tsk_timer(&tsk->thread.guest_timer,
+				 READ_ONCE(S390_lowcore.guest_timer));
+	system = update_tsk_timer(&tsk->thread.system_timer,
+				  READ_ONCE(S390_lowcore.system_timer));
+	hardirq = update_tsk_timer(&tsk->thread.hardirq_timer,
+				   READ_ONCE(S390_lowcore.hardirq_timer));
+	softirq = update_tsk_timer(&tsk->thread.softirq_timer,
+				   READ_ONCE(S390_lowcore.softirq_timer));
+	S390_lowcore.steal_timer +=
+		clock - user - guest - system - hardirq - softirq;
+
+	/* Push account value */
+	if (user) {
+		account_user_time(tsk, cputime_to_nsecs(user));
+		tsk->utimescaled += cputime_to_nsecs(scale_vtime(user));
+	}
 
-		user_scaled = (user_scaled * mult) / div;
-		system_scaled = (system_scaled * mult) / div;
+	if (guest) {
+		account_guest_time(tsk, cputime_to_nsecs(guest));
+		tsk->utimescaled += cputime_to_nsecs(scale_vtime(guest));
 	}
-	account_user_time(tsk, user);
-	tsk->utimescaled += user_scaled;
-	account_system_time(tsk, 0, system);
-	tsk->stimescaled += system_scaled;
+
+	if (system)
+		account_system_index_scaled(tsk, system, scale_vtime(system),
+					    CPUTIME_SYSTEM);
+	if (hardirq)
+		account_system_index_scaled(tsk, hardirq, scale_vtime(hardirq),
+					    CPUTIME_IRQ);
+	if (softirq)
+		account_system_index_scaled(tsk, softirq, scale_vtime(softirq),
+					    CPUTIME_SOFTIRQ);
 
 	steal = S390_lowcore.steal_timer;
 	if ((s64) steal > 0) {
 		S390_lowcore.steal_timer = 0;
-		account_steal_time(steal);
+		account_steal_time(cputime_to_nsecs(steal));
 	}
 
-	return virt_timer_forward(user + system);
+	return virt_timer_forward(user + guest + system + hardirq + softirq);
 }
 
 void vtime_task_switch(struct task_struct *prev)
 {
 	do_account_vtime(prev);
 	prev->thread.user_timer = S390_lowcore.user_timer;
+	prev->thread.guest_timer = S390_lowcore.guest_timer;
 	prev->thread.system_timer = S390_lowcore.system_timer;
+	prev->thread.hardirq_timer = S390_lowcore.hardirq_timer;
+	prev->thread.softirq_timer = S390_lowcore.softirq_timer;
 	S390_lowcore.user_timer = current->thread.user_timer;
+	S390_lowcore.guest_timer = current->thread.guest_timer;
 	S390_lowcore.system_timer = current->thread.system_timer;
+	S390_lowcore.hardirq_timer = current->thread.hardirq_timer;
+	S390_lowcore.softirq_timer = current->thread.softirq_timer;
 }
 
 /*
@@ -164,7 +214,7 @@ void vtime_task_switch(struct task_struct *prev)
  * accounting system time in order to correctly compute
  * the stolen time accounting.
  */
-void vtime_account_user(struct task_struct *tsk)
+void vtime_flush(struct task_struct *tsk)
 {
 	if (do_account_vtime(tsk))
 		virt_timer_expire();
@@ -176,32 +226,22 @@ void vtime_account_user(struct task_struct *tsk)
  */
 void vtime_account_irq_enter(struct task_struct *tsk)
 {
-	u64 timer, system, system_scaled;
+	u64 timer;
 
 	timer = S390_lowcore.last_update_timer;
 	S390_lowcore.last_update_timer = get_vtimer();
-	S390_lowcore.system_timer += timer - S390_lowcore.last_update_timer;
-
-	/* Update MT utilization calculation */
-	if (smp_cpu_mtid &&
-	    time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies)))
-		update_mt_scaling();
-
-	system = S390_lowcore.system_timer - tsk->thread.system_timer;
-	S390_lowcore.steal_timer -= system;
-	tsk->thread.system_timer = S390_lowcore.system_timer;
-	system_scaled = system;
-	/* Do MT utilization scaling */
-	if (smp_cpu_mtid) {
-		u64 mult = __this_cpu_read(mt_scaling_mult);
-		u64 div = __this_cpu_read(mt_scaling_div);
-
-		system_scaled = (system_scaled * mult) / div;
-	}
-	account_system_time(tsk, 0, system);
-	tsk->stimescaled += system_scaled;
-
-	virt_timer_forward(system);
+	timer -= S390_lowcore.last_update_timer;
+
+	if ((tsk->flags & PF_VCPU) && (irq_count() == 0))
+		S390_lowcore.guest_timer += timer;
+	else if (hardirq_count())
+		S390_lowcore.hardirq_timer += timer;
+	else if (in_serving_softirq())
+		S390_lowcore.softirq_timer += timer;
+	else
+		S390_lowcore.system_timer += timer;
+
+	virt_timer_forward(timer);
 }
 EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 7a1897c51c54..d56ef26d4681 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -202,7 +202,7 @@ static inline pgste_t ptep_xchg_start(struct mm_struct *mm,
 	return pgste;
 }
 
-static inline void ptep_xchg_commit(struct mm_struct *mm,
+static inline pte_t ptep_xchg_commit(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep,
 				    pgste_t pgste, pte_t old, pte_t new)
 {
@@ -220,6 +220,7 @@ static inline void ptep_xchg_commit(struct mm_struct *mm,
 	} else {
 		*ptep = new;
 	}
+	return old;
 }
 
 pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr,
@@ -231,7 +232,7 @@ pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr,
 	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
 	old = ptep_flush_direct(mm, addr, ptep);
-	ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+	old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
 	preempt_enable();
 	return old;
 }
@@ -246,7 +247,7 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr,
 	preempt_disable();
 	pgste = ptep_xchg_start(mm, addr, ptep);
 	old = ptep_flush_lazy(mm, addr, ptep);
-	ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
+	old = ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
 	preempt_enable();
 	return old;
 }
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index a05218ff3fe4..51970bb6c4fe 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -4,7 +4,6 @@ header-y +=
 
 generic-y += barrier.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
diff --git a/arch/sh/boot/romimage/mmcif-sh7724.c b/arch/sh/boot/romimage/mmcif-sh7724.c
index 16b122510c84..6595b6b45bf1 100644
--- a/arch/sh/boot/romimage/mmcif-sh7724.c
+++ b/arch/sh/boot/romimage/mmcif-sh7724.c
@@ -9,7 +9,6 @@
  */
 
 #include <linux/mmc/sh_mmcif.h>
-#include <linux/mmc/boot.h>
 #include <mach/romimage.h>
 
 #define MMCIF_BASE      (void __iomem *)0xa4ca0000
@@ -22,6 +21,13 @@
 #define HIZCRC		0xa405015c
 #define DRVCRA		0xa405018a
 
+enum {
+	MMCIF_PROGRESS_ENTER,
+	MMCIF_PROGRESS_INIT,
+	MMCIF_PROGRESS_LOAD,
+	MMCIF_PROGRESS_DONE
+};
+
 /* SH7724 specific MMCIF loader
  *
  * loads the romImage from an MMC card starting from block 512
@@ -30,7 +36,7 @@
  */
 asmlinkage void mmcif_loader(unsigned char *buf, unsigned long no_bytes)
 {
-	mmcif_update_progress(MMC_PROGRESS_ENTER);
+	mmcif_update_progress(MMCIF_PROGRESS_ENTER);
 
 	/* enable clock to the MMCIF hardware block */
 	__raw_writel(__raw_readl(MSTPCR2) & ~0x20000000, MSTPCR2);
@@ -53,12 +59,12 @@ asmlinkage void mmcif_loader(unsigned char *buf, unsigned long no_bytes)
 	/* high drive capability for MMC pins */
 	__raw_writew(__raw_readw(DRVCRA) | 0x3000, DRVCRA);
 
-	mmcif_update_progress(MMC_PROGRESS_INIT);
+	mmcif_update_progress(MMCIF_PROGRESS_INIT);
 
 	/* setup MMCIF hardware */
 	sh_mmcif_boot_init(MMCIF_BASE);
 
-	mmcif_update_progress(MMC_PROGRESS_LOAD);
+	mmcif_update_progress(MMCIF_PROGRESS_LOAD);
 
 	/* load kernel via MMCIF interface */
 	sh_mmcif_boot_do_read(MMCIF_BASE, 512,
@@ -68,5 +74,5 @@ asmlinkage void mmcif_loader(unsigned char *buf, unsigned long no_bytes)
 	/* disable clock to the MMCIF hardware block */
 	__raw_writel(__raw_readl(MSTPCR2) | 0x20000000, MSTPCR2);
 
-	mmcif_update_progress(MMC_PROGRESS_DONE);
+	mmcif_update_progress(MMCIF_PROGRESS_DONE);
 }
diff --git a/arch/sh/configs/sh7785lcr_32bit_defconfig b/arch/sh/configs/sh7785lcr_32bit_defconfig
index 9bdcf72ec06a..2fce54d9c388 100644
--- a/arch/sh/configs/sh7785lcr_32bit_defconfig
+++ b/arch/sh/configs/sh7785lcr_32bit_defconfig
@@ -25,7 +25,7 @@ CONFIG_SH_SH7785LCR=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_CPU_FREQ=y
-CONFIG_CPU_FREQ_STAT_DETAILS=y
+CONFIG_CPU_FREQ_STAT=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_SH_CPU_FREQ=y
 CONFIG_HEARTBEAT=y
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 751c3373a92c..cf2a75063b53 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -1,7 +1,6 @@
 
 generic-y += bitsperlong.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 0569bfac4afb..e9e837bc3158 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -2,7 +2,6 @@
 
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += exec.h
diff --git a/arch/sparc/include/asm/mmu_context_64.h b/arch/sparc/include/asm/mmu_context_64.h
index b84be675e507..d0317993e947 100644
--- a/arch/sparc/include/asm/mmu_context_64.h
+++ b/arch/sparc/include/asm/mmu_context_64.h
@@ -35,15 +35,15 @@ void __tsb_context_switch(unsigned long pgd_pa,
 static inline void tsb_context_switch(struct mm_struct *mm)
 {
 	__tsb_context_switch(__pa(mm->pgd),
-			     &mm->context.tsb_block[0],
+			     &mm->context.tsb_block[MM_TSB_BASE],
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-			     (mm->context.tsb_block[1].tsb ?
-			      &mm->context.tsb_block[1] :
+			     (mm->context.tsb_block[MM_TSB_HUGE].tsb ?
+			      &mm->context.tsb_block[MM_TSB_HUGE] :
 			      NULL)
 #else
 			     NULL
 #endif
-			     , __pa(&mm->context.tsb_descr[0]));
+			     , __pa(&mm->context.tsb_descr[MM_TSB_BASE]));
 }
 
 void tsb_grow(struct mm_struct *mm,
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 3bebf395252c..4d0248aa0928 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -1021,7 +1021,7 @@ static void __init alloc_one_queue(unsigned long *pa_ptr, unsigned long qmask)
 	unsigned long order = get_order(size);
 	unsigned long p;
 
-	p = __get_free_pages(GFP_KERNEL, order);
+	p = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
 	if (!p) {
 		prom_printf("SUN4V: Error, cannot allocate queue.\n");
 		prom_halt();
diff --git a/arch/sparc/kernel/sstate.c b/arch/sparc/kernel/sstate.c
index c59af546f522..3caed4023589 100644
--- a/arch/sparc/kernel/sstate.c
+++ b/arch/sparc/kernel/sstate.c
@@ -43,8 +43,8 @@ static const char poweroff_msg[32] __attribute__((aligned(32))) =
 	"Linux powering off";
 static const char rebooting_msg[32] __attribute__((aligned(32))) =
 	"Linux rebooting";
-static const char panicing_msg[32] __attribute__((aligned(32))) =
-	"Linux panicing";
+static const char panicking_msg[32] __attribute__((aligned(32))) =
+	"Linux panicking";
 
 static int sstate_reboot_call(struct notifier_block *np, unsigned long type, void *_unused)
 {
@@ -76,7 +76,7 @@ static struct notifier_block sstate_reboot_notifier = {
 
 static int sstate_panic_event(struct notifier_block *n, unsigned long event, void *ptr)
 {
-	do_set_sstate(HV_SOFT_STATE_TRANSITION, panicing_msg);
+	do_set_sstate(HV_SOFT_STATE_TRANSITION, panicking_msg);
 
 	return NOTIFY_DONE;
 }
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 4bc10e44d1ca..dfc97a47c9a0 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2051,6 +2051,73 @@ void sun4v_resum_overflow(struct pt_regs *regs)
 	atomic_inc(&sun4v_resum_oflow_cnt);
 }
 
+/* Given a set of registers, get the virtual addressi that was being accessed
+ * by the faulting instructions at tpc.
+ */
+static unsigned long sun4v_get_vaddr(struct pt_regs *regs)
+{
+	unsigned int insn;
+
+	if (!copy_from_user(&insn, (void __user *)regs->tpc, 4)) {
+		return compute_effective_address(regs, insn,
+						 (insn >> 25) & 0x1f);
+	}
+	return 0;
+}
+
+/* Attempt to handle non-resumable errors generated from userspace.
+ * Returns true if the signal was handled, false otherwise.
+ */
+bool sun4v_nonresum_error_user_handled(struct pt_regs *regs,
+				  struct sun4v_error_entry *ent) {
+
+	unsigned int attrs = ent->err_attrs;
+
+	if (attrs & SUN4V_ERR_ATTRS_MEMORY) {
+		unsigned long addr = ent->err_raddr;
+		siginfo_t info;
+
+		if (addr == ~(u64)0) {
+			/* This seems highly unlikely to ever occur */
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory error detected in unknown location!\n");
+		} else {
+			unsigned long page_cnt = DIV_ROUND_UP(ent->err_size,
+							      PAGE_SIZE);
+
+			/* Break the unfortunate news. */
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR: Memory failed at %016lX\n",
+				 addr);
+			pr_emerg("SUN4V NON-RECOVERABLE ERROR:   Claiming %lu ages.\n",
+				 page_cnt);
+
+			while (page_cnt-- > 0) {
+				if (pfn_valid(addr >> PAGE_SHIFT))
+					get_page(pfn_to_page(addr >> PAGE_SHIFT));
+				addr += PAGE_SIZE;
+			}
+		}
+		info.si_signo = SIGKILL;
+		info.si_errno = 0;
+		info.si_trapno = 0;
+		force_sig_info(info.si_signo, &info, current);
+
+		return true;
+	}
+	if (attrs & SUN4V_ERR_ATTRS_PIO) {
+		siginfo_t info;
+
+		info.si_signo = SIGBUS;
+		info.si_code = BUS_ADRERR;
+		info.si_addr = (void __user *)sun4v_get_vaddr(regs);
+		force_sig_info(info.si_signo, &info, current);
+
+		return true;
+	}
+
+	/* Default to doing nothing */
+	return false;
+}
+
 /* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate.
  * Log the event, clear the first word of the entry, and die.
  */
@@ -2075,6 +2142,12 @@ void sun4v_nonresum_error(struct pt_regs *regs, unsigned long offset)
 
 	put_cpu();
 
+	if (!(regs->tstate & TSTATE_PRIV) &&
+	    sun4v_nonresum_error_user_handled(regs, &local_copy)) {
+		/* DON'T PANIC: This userspace error was handled. */
+		return;
+	}
+
 #ifdef CONFIG_PCI
 	/* Check for the special PCI poke sequence. */
 	if (pci_poke_in_progress && pci_poke_cpu == cpu) {
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 2d1f5638974c..aa48b6eaff2d 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -4,8 +4,6 @@ header-y += ../arch/
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
-generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
diff --git a/arch/tile/include/asm/div64.h b/arch/tile/include/asm/div64.h
new file mode 100644
index 000000000000..9f765cdf09a5
--- /dev/null
+++ b/arch/tile/include/asm/div64.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_TILE_DIV64_H
+#define _ASM_TILE_DIV64_H
+
+#include <linux/types.h>
+
+#ifdef __tilegx__
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+	return __insn_mul_lu_lu(a, b);
+}
+#define mul_u32_u32 mul_u32_u32
+#endif
+
+#include <asm-generic/div64.h>
+
+#endif /* _ASM_TILE_DIV64_H */
diff --git a/arch/tile/kernel/ptrace.c b/arch/tile/kernel/ptrace.c
index d89b7011667c..e279572824b1 100644
--- a/arch/tile/kernel/ptrace.c
+++ b/arch/tile/kernel/ptrace.c
@@ -111,7 +111,7 @@ static int tile_gpr_set(struct task_struct *target,
 			  const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	struct pt_regs regs;
+	struct pt_regs regs = *task_pt_regs(target);
 
 	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &regs, 0,
 				 sizeof(regs));
diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
index 05523f14d7b2..57f03050c850 100644
--- a/arch/um/drivers/random.c
+++ b/arch/um/drivers/random.c
@@ -76,7 +76,7 @@ static ssize_t rng_dev_read (struct file *filp, char __user *buf, size_t size,
 			add_sigio_fd(random_fd);
 
 			add_wait_queue(&host_read_wait, &wait);
-			set_task_state(current, TASK_INTERRUPTIBLE);
+			set_current_state(TASK_INTERRUPTIBLE);
 
 			schedule();
 			remove_wait_queue(&host_read_wait, &wait);
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 052f7f6d0551..90c281cd7e1d 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,7 +1,6 @@
 generic-y += barrier.h
 generic-y += bug.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += device.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 256c45b3ae34..5d51ade89f4c 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -4,7 +4,6 @@ generic-y += auxvec.h
 generic-y += bitsperlong.h
 generic-y += bugs.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e487493bbd47..f8fbfc5a98ba 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1070,7 +1070,7 @@ config X86_MCE_THRESHOLD
 	def_bool y
 
 config X86_MCE_INJECT
-	depends on X86_MCE
+	depends on X86_MCE && X86_LOCAL_APIC
 	tristate "Machine check injector support"
 	---help---
 	  Provide support for injecting machine checks for testing purposes.
@@ -1994,10 +1994,6 @@ config RANDOMIZE_BASE
 	  theoretically possible, but the implementations are further
 	  limited due to memory layouts.
 
-	  If CONFIG_HIBERNATE is also enabled, KASLR is disabled at boot
-	  time. To enable it, boot with "kaslr" on the kernel command
-	  line (which will also disable hibernation).
-
 	  If unsure, say N.
 
 # Relocation on x86 needs some additional build support
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 67eec55093a5..783099f2ac72 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -120,14 +120,6 @@ config DEBUG_SET_MODULE_RONX
 	  against certain classes of kernel exploits.
 	  If in doubt, say "N".
 
-config DEBUG_NX_TEST
-	tristate "Testcase for the NX non-executable stack feature"
-	depends on DEBUG_KERNEL && m
-	---help---
-	  This option enables a testcase for the CPU NX capability
-	  and the software setup of this feature.
-	  If in doubt, say "N"
-
 config DOUBLEFAULT
 	default y
 	bool "Enable doublefault exception handler" if EXPERT
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index e5612f3e3b57..9b42b6d1e902 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -333,6 +333,7 @@ size_t strnlen(const char *s, size_t maxlen);
 unsigned int atou(const char *s);
 unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base);
 size_t strlen(const char *s);
+char *strchr(const char *s, int c);
 
 /* tty.c */
 void puts(const char *);
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index ff01c8fc76f7..801c7a158e55 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -32,160 +32,13 @@ static void setup_boot_services##bits(struct efi_config *c)		\
 									\
 	table = (typeof(table))sys_table;				\
 									\
+	c->runtime_services = table->runtime;				\
 	c->boot_services = table->boottime;				\
 	c->text_output = table->con_out;				\
 }
 BOOT_SERVICES(32);
 BOOT_SERVICES(64);
 
-void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
-
-static efi_status_t
-__file_size32(void *__fh, efi_char16_t *filename_16,
-	      void **handle, u64 *file_sz)
-{
-	efi_file_handle_32_t *h, *fh = __fh;
-	efi_file_info_t *info;
-	efi_status_t status;
-	efi_guid_t info_guid = EFI_FILE_INFO_ID;
-	u32 info_sz;
-
-	status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
-				 EFI_FILE_MODE_READ, (u64)0);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to open file: ");
-		efi_char16_printk(sys_table, filename_16);
-		efi_printk(sys_table, "\n");
-		return status;
-	}
-
-	*handle = h;
-
-	info_sz = 0;
-	status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
-				 &info_sz, NULL);
-	if (status != EFI_BUFFER_TOO_SMALL) {
-		efi_printk(sys_table, "Failed to get file info size\n");
-		return status;
-	}
-
-grow:
-	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
-				info_sz, (void **)&info);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for file info\n");
-		return status;
-	}
-
-	status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
-				 &info_sz, info);
-	if (status == EFI_BUFFER_TOO_SMALL) {
-		efi_call_early(free_pool, info);
-		goto grow;
-	}
-
-	*file_sz = info->file_size;
-	efi_call_early(free_pool, info);
-
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table, "Failed to get initrd info\n");
-
-	return status;
-}
-
-static efi_status_t
-__file_size64(void *__fh, efi_char16_t *filename_16,
-	      void **handle, u64 *file_sz)
-{
-	efi_file_handle_64_t *h, *fh = __fh;
-	efi_file_info_t *info;
-	efi_status_t status;
-	efi_guid_t info_guid = EFI_FILE_INFO_ID;
-	u64 info_sz;
-
-	status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
-				 EFI_FILE_MODE_READ, (u64)0);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to open file: ");
-		efi_char16_printk(sys_table, filename_16);
-		efi_printk(sys_table, "\n");
-		return status;
-	}
-
-	*handle = h;
-
-	info_sz = 0;
-	status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
-				 &info_sz, NULL);
-	if (status != EFI_BUFFER_TOO_SMALL) {
-		efi_printk(sys_table, "Failed to get file info size\n");
-		return status;
-	}
-
-grow:
-	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
-				info_sz, (void **)&info);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for file info\n");
-		return status;
-	}
-
-	status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
-				 &info_sz, info);
-	if (status == EFI_BUFFER_TOO_SMALL) {
-		efi_call_early(free_pool, info);
-		goto grow;
-	}
-
-	*file_sz = info->file_size;
-	efi_call_early(free_pool, info);
-
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table, "Failed to get initrd info\n");
-
-	return status;
-}
-efi_status_t
-efi_file_size(efi_system_table_t *sys_table, void *__fh,
-	      efi_char16_t *filename_16, void **handle, u64 *file_sz)
-{
-	if (efi_early->is64)
-		return __file_size64(__fh, filename_16, handle, file_sz);
-
-	return __file_size32(__fh, filename_16, handle, file_sz);
-}
-
-efi_status_t
-efi_file_read(void *handle, unsigned long *size, void *addr)
-{
-	unsigned long func;
-
-	if (efi_early->is64) {
-		efi_file_handle_64_t *fh = handle;
-
-		func = (unsigned long)fh->read;
-		return efi_early->call(func, handle, size, addr);
-	} else {
-		efi_file_handle_32_t *fh = handle;
-
-		func = (unsigned long)fh->read;
-		return efi_early->call(func, handle, size, addr);
-	}
-}
-
-efi_status_t efi_file_close(void *handle)
-{
-	if (efi_early->is64) {
-		efi_file_handle_64_t *fh = handle;
-
-		return efi_early->call((unsigned long)fh->close, handle);
-	} else {
-		efi_file_handle_32_t *fh = handle;
-
-		return efi_early->call((unsigned long)fh->close, handle);
-	}
-}
-
 static inline efi_status_t __open_volume32(void *__image, void **__fh)
 {
 	efi_file_io_interface_t *io;
@@ -249,30 +102,8 @@ efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
 
 void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 {
-	unsigned long output_string;
-	size_t offset;
-
-	if (efi_early->is64) {
-		struct efi_simple_text_output_protocol_64 *out;
-		u64 *func;
-
-		offset = offsetof(typeof(*out), output_string);
-		output_string = efi_early->text_output + offset;
-		out = (typeof(out))(unsigned long)efi_early->text_output;
-		func = (u64 *)output_string;
-
-		efi_early->call(*func, out, str);
-	} else {
-		struct efi_simple_text_output_protocol_32 *out;
-		u32 *func;
-
-		offset = offsetof(typeof(*out), output_string);
-		output_string = efi_early->text_output + offset;
-		out = (typeof(out))(unsigned long)efi_early->text_output;
-		func = (u32 *)output_string;
-
-		efi_early->call(*func, out, str);
-	}
+	efi_call_proto(efi_simple_text_output_protocol, output_string,
+		       efi_early->text_output, str);
 }
 
 static efi_status_t
@@ -1157,6 +988,13 @@ struct boot_params *efi_main(struct efi_config *c,
 	else
 		setup_boot_services32(efi_early);
 
+	/*
+	 * If the boot loader gave us a value for secure_boot then we use that,
+	 * otherwise we ask the BIOS.
+	 */
+	if (boot_params->secure_boot == efi_secureboot_mode_unset)
+		boot_params->secure_boot = efi_get_secureboot(sys_table);
+
 	setup_graphics(boot_params);
 
 	setup_efi_pci(boot_params);
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index fd0b6a272dd5..d85b9625e836 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -82,7 +82,7 @@ ENTRY(efi_pe_entry)
 
 	/* Relocate efi_config->call() */
 	leal	efi32_config(%esi), %eax
-	add	%esi, 32(%eax)
+	add	%esi, 40(%eax)
 	pushl	%eax
 
 	call	make_boot_params
@@ -108,7 +108,7 @@ ENTRY(efi32_stub_entry)
 
 	/* Relocate efi_config->call() */
 	leal	efi32_config(%esi), %eax
-	add	%esi, 32(%eax)
+	add	%esi, 40(%eax)
 	pushl	%eax
 2:
 	call	efi_main
@@ -264,7 +264,7 @@ relocated:
 #ifdef CONFIG_EFI_STUB
 	.data
 efi32_config:
-	.fill 4,8,0
+	.fill 5,8,0
 	.long efi_call_phys
 	.long 0
 	.byte 0
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 4d85e600db78..d2ae1f821e0c 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -264,7 +264,7 @@ ENTRY(efi_pe_entry)
 	/*
 	 * Relocate efi_config->call().
 	 */
-	addq	%rbp, efi64_config+32(%rip)
+	addq	%rbp, efi64_config+40(%rip)
 
 	movq	%rax, %rdi
 	call	make_boot_params
@@ -284,7 +284,7 @@ handover_entry:
 	 * Relocate efi_config->call().
 	 */
 	movq	efi_config(%rip), %rax
-	addq	%rbp, 32(%rax)
+	addq	%rbp, 40(%rax)
 2:
 	movq	efi_config(%rip), %rdi
 	call	efi_main
@@ -456,14 +456,14 @@ efi_config:
 #ifdef CONFIG_EFI_MIXED
 	.global efi32_config
 efi32_config:
-	.fill	4,8,0
+	.fill	5,8,0
 	.quad	efi64_thunk
 	.byte	0
 #endif
 
 	.global efi64_config
 efi64_config:
-	.fill	4,8,0
+	.fill	5,8,0
 	.quad	efi_call
 	.byte	1
 #endif /* CONFIG_EFI_STUB */
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index a66854d99ee1..8b7c9e75edcb 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -11,6 +11,7 @@
  */
 #include "misc.h"
 #include "error.h"
+#include "../boot.h"
 
 #include <generated/compile.h>
 #include <linux/module.h>
@@ -52,15 +53,22 @@ static unsigned long get_boot_seed(void)
 #include "../../lib/kaslr.c"
 
 struct mem_vector {
-	unsigned long start;
-	unsigned long size;
+	unsigned long long start;
+	unsigned long long size;
 };
 
+/* Only supporting at most 4 unusable memmap regions with kaslr */
+#define MAX_MEMMAP_REGIONS	4
+
+static bool memmap_too_large;
+
 enum mem_avoid_index {
 	MEM_AVOID_ZO_RANGE = 0,
 	MEM_AVOID_INITRD,
 	MEM_AVOID_CMDLINE,
 	MEM_AVOID_BOOTPARAMS,
+	MEM_AVOID_MEMMAP_BEGIN,
+	MEM_AVOID_MEMMAP_END = MEM_AVOID_MEMMAP_BEGIN + MAX_MEMMAP_REGIONS - 1,
 	MEM_AVOID_MAX,
 };
 
@@ -77,6 +85,123 @@ static bool mem_overlaps(struct mem_vector *one, struct mem_vector *two)
 	return true;
 }
 
+/**
+ *	_memparse - Parse a string with mem suffixes into a number
+ *	@ptr: Where parse begins
+ *	@retptr: (output) Optional pointer to next char after parse completes
+ *
+ *	Parses a string into a number.  The number stored at @ptr is
+ *	potentially suffixed with K, M, G, T, P, E.
+ */
+static unsigned long long _memparse(const char *ptr, char **retptr)
+{
+	char *endptr;	/* Local pointer to end of parsed string */
+
+	unsigned long long ret = simple_strtoull(ptr, &endptr, 0);
+
+	switch (*endptr) {
+	case 'E':
+	case 'e':
+		ret <<= 10;
+	case 'P':
+	case 'p':
+		ret <<= 10;
+	case 'T':
+	case 't':
+		ret <<= 10;
+	case 'G':
+	case 'g':
+		ret <<= 10;
+	case 'M':
+	case 'm':
+		ret <<= 10;
+	case 'K':
+	case 'k':
+		ret <<= 10;
+		endptr++;
+	default:
+		break;
+	}
+
+	if (retptr)
+		*retptr = endptr;
+
+	return ret;
+}
+
+static int
+parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
+{
+	char *oldp;
+
+	if (!p)
+		return -EINVAL;
+
+	/* We don't care about this option here */
+	if (!strncmp(p, "exactmap", 8))
+		return -EINVAL;
+
+	oldp = p;
+	*size = _memparse(p, &p);
+	if (p == oldp)
+		return -EINVAL;
+
+	switch (*p) {
+	case '@':
+		/* Skip this region, usable */
+		*start = 0;
+		*size = 0;
+		return 0;
+	case '#':
+	case '$':
+	case '!':
+		*start = _memparse(p + 1, &p);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static void mem_avoid_memmap(void)
+{
+	char arg[128];
+	int rc;
+	int i;
+	char *str;
+
+	/* See if we have any memmap areas */
+	rc = cmdline_find_option("memmap", arg, sizeof(arg));
+	if (rc <= 0)
+		return;
+
+	i = 0;
+	str = arg;
+	while (str && (i < MAX_MEMMAP_REGIONS)) {
+		int rc;
+		unsigned long long start, size;
+		char *k = strchr(str, ',');
+
+		if (k)
+			*k++ = 0;
+
+		rc = parse_memmap(str, &start, &size);
+		if (rc < 0)
+			break;
+		str = k;
+		/* A usable region that should not be skipped */
+		if (size == 0)
+			continue;
+
+		mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].start = start;
+		mem_avoid[MEM_AVOID_MEMMAP_BEGIN + i].size = size;
+		i++;
+	}
+
+	/* More than 4 memmaps, fail kaslr */
+	if ((i >= MAX_MEMMAP_REGIONS) && str)
+		memmap_too_large = true;
+}
+
 /*
  * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T).
  * The mem_avoid array is used to store the ranges that need to be avoided
@@ -197,6 +322,9 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 
 	/* We don't need to set a mapping for setup_data. */
 
+	/* Mark the memmap regions we need to avoid */
+	mem_avoid_memmap();
+
 #ifdef CONFIG_X86_VERBOSE_BOOTUP
 	/* Make sure video RAM can be used. */
 	add_identity_map(0, PMD_SIZE);
@@ -379,6 +507,12 @@ static unsigned long find_random_phys_addr(unsigned long minimum,
 	int i;
 	unsigned long addr;
 
+	/* Check if we had too many memmaps. */
+	if (memmap_too_large) {
+		debug_putstr("Aborted e820 scan (more than 4 memmap= args)!\n");
+		return 0;
+	}
+
 	/* Make sure minimum is aligned. */
 	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
 
@@ -456,7 +590,7 @@ void choose_random_location(unsigned long input,
 	/* Walk e820 and find a random address. */
 	random_addr = find_random_phys_addr(min_addr, output_size);
 	if (!random_addr) {
-		warn("KASLR disabled: could not find suitable E820 region!");
+		warn("Physical KASLR disabled: no suitable memory region!");
 	} else {
 		/* Update the new physical address location. */
 		if (*output != random_addr) {
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 9e240fcba784..5457b02fc050 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -156,3 +156,16 @@ char *strstr(const char *s1, const char *s2)
 	}
 	return NULL;
 }
+
+/**
+ * strchr - Find the first occurrence of the character c in the string s.
+ * @s: the string to be searched
+ * @c: the character to search for
+ */
+char *strchr(const char *s, int c)
+{
+	while (*s != (char)c)
+		if (*s++ == '\0')
+			return NULL;
+	return (char *)s;
+}
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 6ef688a1ef3e..7ff1b0c86a8e 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1085,9 +1085,9 @@ static void aesni_free_simds(void)
 		    aesni_simd_skciphers[i]; i++)
 		simd_skcipher_free(aesni_simd_skciphers[i]);
 
-	for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2) &&
-		    aesni_simd_skciphers2[i].simd; i++)
-		simd_skcipher_free(aesni_simd_skciphers2[i].simd);
+	for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers2); i++)
+		if (aesni_simd_skciphers2[i].simd)
+			simd_skcipher_free(aesni_simd_skciphers2[i].simd);
 }
 
 static int __init aesni_init(void)
@@ -1168,7 +1168,7 @@ static int __init aesni_init(void)
 		simd = simd_skcipher_create_compat(algname, drvname, basename);
 		err = PTR_ERR(simd);
 		if (IS_ERR(simd))
-			goto unregister_simds;
+			continue;
 
 		aesni_simd_skciphers2[i].simd = simd;
 	}
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 1d392c39fe56..b8ccdb5c9244 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,11 +1,4 @@
-obj-y			+= core.o
-
-obj-$(CONFIG_CPU_SUP_AMD)               += amd/core.o amd/uncore.o
-obj-$(CONFIG_PERF_EVENTS_AMD_POWER)	+= amd/power.o
-obj-$(CONFIG_X86_LOCAL_APIC)            += amd/ibs.o msr.o
-ifdef CONFIG_AMD_IOMMU
-obj-$(CONFIG_CPU_SUP_AMD)               += amd/iommu.o
-endif
-
-obj-$(CONFIG_CPU_SUP_INTEL)		+= msr.o
+obj-y					+= core.o
+obj-y					+= amd/
+obj-$(CONFIG_X86_LOCAL_APIC)            += msr.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/
diff --git a/arch/x86/events/amd/Makefile b/arch/x86/events/amd/Makefile
new file mode 100644
index 000000000000..b1da46f396e0
--- /dev/null
+++ b/arch/x86/events/amd/Makefile
@@ -0,0 +1,7 @@
+obj-$(CONFIG_CPU_SUP_AMD)		+= core.o uncore.o
+obj-$(CONFIG_PERF_EVENTS_AMD_POWER)	+= power.o
+obj-$(CONFIG_X86_LOCAL_APIC)		+= ibs.o
+ifdef CONFIG_AMD_IOMMU
+obj-$(CONFIG_CPU_SUP_AMD)		+= iommu.o
+endif
+
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index a0b1bdb3ad42..4d1f7f2d9aff 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -22,13 +22,17 @@
 
 #define NUM_COUNTERS_NB		4
 #define NUM_COUNTERS_L2		4
-#define MAX_COUNTERS		NUM_COUNTERS_NB
+#define NUM_COUNTERS_L3		6
+#define MAX_COUNTERS		6
 
 #define RDPMC_BASE_NB		6
-#define RDPMC_BASE_L2		10
+#define RDPMC_BASE_LLC		10
 
 #define COUNTER_SHIFT		16
 
+static int num_counters_llc;
+static int num_counters_nb;
+
 static HLIST_HEAD(uncore_unused_list);
 
 struct amd_uncore {
@@ -45,30 +49,30 @@ struct amd_uncore {
 };
 
 static struct amd_uncore * __percpu *amd_uncore_nb;
-static struct amd_uncore * __percpu *amd_uncore_l2;
+static struct amd_uncore * __percpu *amd_uncore_llc;
 
 static struct pmu amd_nb_pmu;
-static struct pmu amd_l2_pmu;
+static struct pmu amd_llc_pmu;
 
 static cpumask_t amd_nb_active_mask;
-static cpumask_t amd_l2_active_mask;
+static cpumask_t amd_llc_active_mask;
 
 static bool is_nb_event(struct perf_event *event)
 {
 	return event->pmu->type == amd_nb_pmu.type;
 }
 
-static bool is_l2_event(struct perf_event *event)
+static bool is_llc_event(struct perf_event *event)
 {
-	return event->pmu->type == amd_l2_pmu.type;
+	return event->pmu->type == amd_llc_pmu.type;
 }
 
 static struct amd_uncore *event_to_amd_uncore(struct perf_event *event)
 {
 	if (is_nb_event(event) && amd_uncore_nb)
 		return *per_cpu_ptr(amd_uncore_nb, event->cpu);
-	else if (is_l2_event(event) && amd_uncore_l2)
-		return *per_cpu_ptr(amd_uncore_l2, event->cpu);
+	else if (is_llc_event(event) && amd_uncore_llc)
+		return *per_cpu_ptr(amd_uncore_llc, event->cpu);
 
 	return NULL;
 }
@@ -183,16 +187,16 @@ static int amd_uncore_event_init(struct perf_event *event)
 		return -ENOENT;
 
 	/*
-	 * NB and L2 counters (MSRs) are shared across all cores that share the
-	 * same NB / L2 cache. Interrupts can be directed to a single target
-	 * core, however, event counts generated by processes running on other
-	 * cores cannot be masked out. So we do not support sampling and
-	 * per-thread events.
+	 * NB and Last level cache counters (MSRs) are shared across all cores
+	 * that share the same NB / Last level cache. Interrupts can be directed
+	 * to a single target core, however, event counts generated by processes
+	 * running on other cores cannot be masked out. So we do not support
+	 * sampling and per-thread events.
 	 */
 	if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK)
 		return -EINVAL;
 
-	/* NB and L2 counters do not have usr/os/guest/host bits */
+	/* NB and Last level cache counters do not have usr/os/guest/host bits */
 	if (event->attr.exclude_user || event->attr.exclude_kernel ||
 	    event->attr.exclude_host || event->attr.exclude_guest)
 		return -EINVAL;
@@ -226,8 +230,8 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
 
 	if (pmu->type == amd_nb_pmu.type)
 		active_mask = &amd_nb_active_mask;
-	else if (pmu->type == amd_l2_pmu.type)
-		active_mask = &amd_l2_active_mask;
+	else if (pmu->type == amd_llc_pmu.type)
+		active_mask = &amd_llc_active_mask;
 	else
 		return 0;
 
@@ -244,30 +248,47 @@ static struct attribute_group amd_uncore_attr_group = {
 	.attrs = amd_uncore_attrs,
 };
 
-PMU_FORMAT_ATTR(event, "config:0-7,32-35");
-PMU_FORMAT_ATTR(umask, "config:8-15");
-
-static struct attribute *amd_uncore_format_attr[] = {
-	&format_attr_event.attr,
-	&format_attr_umask.attr,
-	NULL,
-};
-
-static struct attribute_group amd_uncore_format_group = {
-	.name = "format",
-	.attrs = amd_uncore_format_attr,
+/*
+ * Similar to PMU_FORMAT_ATTR but allowing for format_attr to be assigned based
+ * on family
+ */
+#define AMD_FORMAT_ATTR(_dev, _name, _format)				     \
+static ssize_t								     \
+_dev##_show##_name(struct device *dev,					     \
+		struct device_attribute *attr,				     \
+		char *page)						     \
+{									     \
+	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);			     \
+	return sprintf(page, _format "\n");				     \
+}									     \
+static struct device_attribute format_attr_##_dev##_name = __ATTR_RO(_dev);
+
+/* Used for each uncore counter type */
+#define AMD_ATTRIBUTE(_name)						     \
+static struct attribute *amd_uncore_format_attr_##_name[] = {		     \
+	&format_attr_event_##_name.attr,				     \
+	&format_attr_umask.attr,					     \
+	NULL,								     \
+};									     \
+static struct attribute_group amd_uncore_format_group_##_name = {	     \
+	.name = "format",						     \
+	.attrs = amd_uncore_format_attr_##_name,			     \
+};									     \
+static const struct attribute_group *amd_uncore_attr_groups_##_name[] = {    \
+	&amd_uncore_attr_group,						     \
+	&amd_uncore_format_group_##_name,				     \
+	NULL,								     \
 };
 
-static const struct attribute_group *amd_uncore_attr_groups[] = {
-	&amd_uncore_attr_group,
-	&amd_uncore_format_group,
-	NULL,
-};
+AMD_FORMAT_ATTR(event, , "config:0-7,32-35");
+AMD_FORMAT_ATTR(umask, , "config:8-15");
+AMD_FORMAT_ATTR(event, _df, "config:0-7,32-35,59-60");
+AMD_FORMAT_ATTR(event, _l3, "config:0-7");
+AMD_ATTRIBUTE(df);
+AMD_ATTRIBUTE(l3);
 
 static struct pmu amd_nb_pmu = {
 	.task_ctx_nr	= perf_invalid_context,
-	.attr_groups	= amd_uncore_attr_groups,
-	.name		= "amd_nb",
 	.event_init	= amd_uncore_event_init,
 	.add		= amd_uncore_add,
 	.del		= amd_uncore_del,
@@ -276,10 +297,8 @@ static struct pmu amd_nb_pmu = {
 	.read		= amd_uncore_read,
 };
 
-static struct pmu amd_l2_pmu = {
+static struct pmu amd_llc_pmu = {
 	.task_ctx_nr	= perf_invalid_context,
-	.attr_groups	= amd_uncore_attr_groups,
-	.name		= "amd_l2",
 	.event_init	= amd_uncore_event_init,
 	.add		= amd_uncore_add,
 	.del		= amd_uncore_del,
@@ -296,14 +315,14 @@ static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
 
 static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 {
-	struct amd_uncore *uncore_nb = NULL, *uncore_l2;
+	struct amd_uncore *uncore_nb = NULL, *uncore_llc;
 
 	if (amd_uncore_nb) {
 		uncore_nb = amd_uncore_alloc(cpu);
 		if (!uncore_nb)
 			goto fail;
 		uncore_nb->cpu = cpu;
-		uncore_nb->num_counters = NUM_COUNTERS_NB;
+		uncore_nb->num_counters = num_counters_nb;
 		uncore_nb->rdpmc_base = RDPMC_BASE_NB;
 		uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
 		uncore_nb->active_mask = &amd_nb_active_mask;
@@ -312,18 +331,18 @@ static int amd_uncore_cpu_up_prepare(unsigned int cpu)
 		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
 	}
 
-	if (amd_uncore_l2) {
-		uncore_l2 = amd_uncore_alloc(cpu);
-		if (!uncore_l2)
+	if (amd_uncore_llc) {
+		uncore_llc = amd_uncore_alloc(cpu);
+		if (!uncore_llc)
 			goto fail;
-		uncore_l2->cpu = cpu;
-		uncore_l2->num_counters = NUM_COUNTERS_L2;
-		uncore_l2->rdpmc_base = RDPMC_BASE_L2;
-		uncore_l2->msr_base = MSR_F16H_L2I_PERF_CTL;
-		uncore_l2->active_mask = &amd_l2_active_mask;
-		uncore_l2->pmu = &amd_l2_pmu;
-		uncore_l2->id = -1;
-		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore_l2;
+		uncore_llc->cpu = cpu;
+		uncore_llc->num_counters = num_counters_llc;
+		uncore_llc->rdpmc_base = RDPMC_BASE_LLC;
+		uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL;
+		uncore_llc->active_mask = &amd_llc_active_mask;
+		uncore_llc->pmu = &amd_llc_pmu;
+		uncore_llc->id = -1;
+		*per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc;
 	}
 
 	return 0;
@@ -376,17 +395,17 @@ static int amd_uncore_cpu_starting(unsigned int cpu)
 		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
 	}
 
-	if (amd_uncore_l2) {
+	if (amd_uncore_llc) {
 		unsigned int apicid = cpu_data(cpu).apicid;
 		unsigned int nshared;
 
-		uncore = *per_cpu_ptr(amd_uncore_l2, cpu);
+		uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
 		cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx);
 		nshared = ((eax >> 14) & 0xfff) + 1;
 		uncore->id = apicid - (apicid % nshared);
 
-		uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2);
-		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
+		uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
+		*per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
 	}
 
 	return 0;
@@ -419,8 +438,8 @@ static int amd_uncore_cpu_online(unsigned int cpu)
 	if (amd_uncore_nb)
 		uncore_online(cpu, amd_uncore_nb);
 
-	if (amd_uncore_l2)
-		uncore_online(cpu, amd_uncore_l2);
+	if (amd_uncore_llc)
+		uncore_online(cpu, amd_uncore_llc);
 
 	return 0;
 }
@@ -456,8 +475,8 @@ static int amd_uncore_cpu_down_prepare(unsigned int cpu)
 	if (amd_uncore_nb)
 		uncore_down_prepare(cpu, amd_uncore_nb);
 
-	if (amd_uncore_l2)
-		uncore_down_prepare(cpu, amd_uncore_l2);
+	if (amd_uncore_llc)
+		uncore_down_prepare(cpu, amd_uncore_llc);
 
 	return 0;
 }
@@ -479,8 +498,8 @@ static int amd_uncore_cpu_dead(unsigned int cpu)
 	if (amd_uncore_nb)
 		uncore_dead(cpu, amd_uncore_nb);
 
-	if (amd_uncore_l2)
-		uncore_dead(cpu, amd_uncore_l2);
+	if (amd_uncore_llc)
+		uncore_dead(cpu, amd_uncore_llc);
 
 	return 0;
 }
@@ -492,6 +511,47 @@ static int __init amd_uncore_init(void)
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
 		goto fail_nodev;
 
+	switch(boot_cpu_data.x86) {
+		case 23:
+			/* Family 17h: */
+			num_counters_nb = NUM_COUNTERS_NB;
+			num_counters_llc = NUM_COUNTERS_L3;
+			/*
+			 * For Family17h, the NorthBridge counters are
+			 * re-purposed as Data Fabric counters. Also, support is
+			 * added for L3 counters. The pmus are exported based on
+			 * family as either L2 or L3 and NB or DF.
+			 */
+			amd_nb_pmu.name = "amd_df";
+			amd_llc_pmu.name = "amd_l3";
+			format_attr_event_df.show = &event_show_df;
+			format_attr_event_l3.show = &event_show_l3;
+			break;
+		case 22:
+			/* Family 16h - may change: */
+			num_counters_nb = NUM_COUNTERS_NB;
+			num_counters_llc = NUM_COUNTERS_L2;
+			amd_nb_pmu.name = "amd_nb";
+			amd_llc_pmu.name = "amd_l2";
+			format_attr_event_df = format_attr_event;
+			format_attr_event_l3 = format_attr_event;
+			break;
+		default:
+			/*
+			 * All prior families have the same number of
+			 * NorthBridge and Last Level Cache counters
+			 */
+			num_counters_nb = NUM_COUNTERS_NB;
+			num_counters_llc = NUM_COUNTERS_L2;
+			amd_nb_pmu.name = "amd_nb";
+			amd_llc_pmu.name = "amd_l2";
+			format_attr_event_df = format_attr_event;
+			format_attr_event_l3 = format_attr_event;
+			break;
+	}
+	amd_nb_pmu.attr_groups = amd_uncore_attr_groups_df;
+	amd_llc_pmu.attr_groups = amd_uncore_attr_groups_l3;
+
 	if (!boot_cpu_has(X86_FEATURE_TOPOEXT))
 		goto fail_nodev;
 
@@ -510,16 +570,16 @@ static int __init amd_uncore_init(void)
 	}
 
 	if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) {
-		amd_uncore_l2 = alloc_percpu(struct amd_uncore *);
-		if (!amd_uncore_l2) {
+		amd_uncore_llc = alloc_percpu(struct amd_uncore *);
+		if (!amd_uncore_llc) {
 			ret = -ENOMEM;
-			goto fail_l2;
+			goto fail_llc;
 		}
-		ret = perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1);
+		ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1);
 		if (ret)
-			goto fail_l2;
+			goto fail_llc;
 
-		pr_info("perf: AMD L2I counters detected\n");
+		pr_info("perf: AMD LLC counters detected\n");
 		ret = 0;
 	}
 
@@ -529,7 +589,7 @@ static int __init amd_uncore_init(void)
 	if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
 			      "perf/x86/amd/uncore:prepare",
 			      amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
-		goto fail_l2;
+		goto fail_llc;
 
 	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 			      "perf/x86/amd/uncore:starting",
@@ -546,11 +606,11 @@ fail_start:
 	cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
 fail_prep:
 	cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
-fail_l2:
+fail_llc:
 	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
 		perf_pmu_unregister(&amd_nb_pmu);
-	if (amd_uncore_l2)
-		free_percpu(amd_uncore_l2);
+	if (amd_uncore_llc)
+		free_percpu(amd_uncore_llc);
 fail_nb:
 	if (amd_uncore_nb)
 		free_percpu(amd_uncore_nb);
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 1076c9a77292..aff4b5b69d40 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -541,6 +541,9 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
 
+	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNM, knl_cstates),
 	{ },
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 1c1b9fe705c8..5900471ee508 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -99,18 +99,24 @@ static struct attribute_group pt_cap_group = {
 };
 
 PMU_FORMAT_ATTR(cyc,		"config:1"	);
+PMU_FORMAT_ATTR(pwr_evt,	"config:4"	);
+PMU_FORMAT_ATTR(fup_on_ptw,	"config:5"	);
 PMU_FORMAT_ATTR(mtc,		"config:9"	);
 PMU_FORMAT_ATTR(tsc,		"config:10"	);
 PMU_FORMAT_ATTR(noretcomp,	"config:11"	);
+PMU_FORMAT_ATTR(ptw,		"config:12"	);
 PMU_FORMAT_ATTR(mtc_period,	"config:14-17"	);
 PMU_FORMAT_ATTR(cyc_thresh,	"config:19-22"	);
 PMU_FORMAT_ATTR(psb_period,	"config:24-27"	);
 
 static struct attribute *pt_formats_attr[] = {
 	&format_attr_cyc.attr,
+	&format_attr_pwr_evt.attr,
+	&format_attr_fup_on_ptw.attr,
 	&format_attr_mtc.attr,
 	&format_attr_tsc.attr,
 	&format_attr_noretcomp.attr,
+	&format_attr_ptw.attr,
 	&format_attr_mtc_period.attr,
 	&format_attr_cyc_thresh.attr,
 	&format_attr_psb_period.attr,
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 17c3564d087a..22054ca49026 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -161,7 +161,13 @@ static u64 rapl_timer_ms;
 
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
-	return rapl_pmus->pmus[topology_logical_package_id(cpu)];
+	unsigned int pkgid = topology_logical_package_id(cpu);
+
+	/*
+	 * The unsigned check also catches the '-1' return value for non
+	 * existent mappings in the topology map.
+	 */
+	return pkgid < rapl_pmus->maxpkg ? rapl_pmus->pmus[pkgid] : NULL;
 }
 
 static inline u64 rapl_read_counter(struct perf_event *event)
@@ -402,6 +408,8 @@ static int rapl_pmu_event_init(struct perf_event *event)
 
 	/* must be done before validate_group */
 	pmu = cpu_to_rapl_pmu(event->cpu);
+	if (!pmu)
+		return -EINVAL;
 	event->cpu = pmu->cpu;
 	event->pmu_private = pmu;
 	event->hw.event_base = msr;
@@ -585,6 +593,20 @@ static int rapl_cpu_online(unsigned int cpu)
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 	int target;
 
+	if (!pmu) {
+		pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+		if (!pmu)
+			return -ENOMEM;
+
+		raw_spin_lock_init(&pmu->lock);
+		INIT_LIST_HEAD(&pmu->active_list);
+		pmu->pmu = &rapl_pmus->pmu;
+		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+		rapl_hrtimer_init(pmu);
+
+		rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
+	}
+
 	/*
 	 * Check if there is an online cpu in the package which collects rapl
 	 * events already.
@@ -598,27 +620,6 @@ static int rapl_cpu_online(unsigned int cpu)
 	return 0;
 }
 
-static int rapl_cpu_prepare(unsigned int cpu)
-{
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-
-	if (pmu)
-		return 0;
-
-	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
-	if (!pmu)
-		return -ENOMEM;
-
-	raw_spin_lock_init(&pmu->lock);
-	INIT_LIST_HEAD(&pmu->active_list);
-	pmu->pmu = &rapl_pmus->pmu;
-	pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
-	pmu->cpu = -1;
-	rapl_hrtimer_init(pmu);
-	rapl_pmus->pmus[topology_logical_package_id(cpu)] = pmu;
-	return 0;
-}
-
 static int rapl_check_hw_unit(bool apply_quirk)
 {
 	u64 msr_rapl_power_unit_bits;
@@ -770,6 +771,9 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP, skl_rapl_init),
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,	 hsx_rapl_init),
 
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE,  skl_rapl_init),
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_rapl_init),
+
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT, hsw_rapl_init),
 	{},
 };
@@ -803,29 +807,21 @@ static int __init rapl_pmu_init(void)
 	/*
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
-
-	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "perf/x86/rapl:prepare",
-				rapl_cpu_prepare, NULL);
-	if (ret)
-		goto out;
-
 	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
 				"perf/x86/rapl:online",
 				rapl_cpu_online, rapl_cpu_offline);
 	if (ret)
-		goto out1;
+		goto out;
 
 	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
 	if (ret)
-		goto out2;
+		goto out1;
 
 	rapl_advertise();
 	return 0;
 
-out2:
-	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out1:
-	cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP);
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out:
 	pr_warn("Initialization failed (%d), disabled\n", ret);
 	cleanup_rapl_pmus();
@@ -836,7 +832,6 @@ module_init(rapl_pmu_init);
 static void __exit intel_rapl_exit(void)
 {
 	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP);
 	perf_pmu_unregister(&rapl_pmus->pmu);
 	cleanup_rapl_pmus();
 }
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 8c4ccdc3a3f3..758c1aa5009d 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -100,7 +100,13 @@ ssize_t uncore_event_show(struct kobject *kobj,
 
 struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
 {
-	return pmu->boxes[topology_logical_package_id(cpu)];
+	unsigned int pkgid = topology_logical_package_id(cpu);
+
+	/*
+	 * The unsigned check also catches the '-1' return value for non
+	 * existent mappings in the topology map.
+	 */
+	return pkgid < max_packages ? pmu->boxes[pkgid] : NULL;
 }
 
 u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
@@ -764,30 +770,6 @@ static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu)
 	pmu->registered = false;
 }
 
-static void __uncore_exit_boxes(struct intel_uncore_type *type, int cpu)
-{
-	struct intel_uncore_pmu *pmu = type->pmus;
-	struct intel_uncore_box *box;
-	int i, pkg;
-
-	if (pmu) {
-		pkg = topology_physical_package_id(cpu);
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
-			if (box)
-				uncore_box_exit(box);
-		}
-	}
-}
-
-static void uncore_exit_boxes(void *dummy)
-{
-	struct intel_uncore_type **types;
-
-	for (types = uncore_msr_uncores; *types; types++)
-		__uncore_exit_boxes(*types++, smp_processor_id());
-}
-
 static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
 {
 	int pkg;
@@ -1058,86 +1040,6 @@ static void uncore_pci_exit(void)
 	}
 }
 
-static int uncore_cpu_dying(unsigned int cpu)
-{
-	struct intel_uncore_type *type, **types = uncore_msr_uncores;
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	int i, pkg;
-
-	pkg = topology_logical_package_id(cpu);
-	for (; *types; types++) {
-		type = *types;
-		pmu = type->pmus;
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
-			if (box && atomic_dec_return(&box->refcnt) == 0)
-				uncore_box_exit(box);
-		}
-	}
-	return 0;
-}
-
-static int first_init;
-
-static int uncore_cpu_starting(unsigned int cpu)
-{
-	struct intel_uncore_type *type, **types = uncore_msr_uncores;
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	int i, pkg, ncpus = 1;
-
-	if (first_init) {
-		/*
-		 * On init we get the number of online cpus in the package
-		 * and set refcount for all of them.
-		 */
-		ncpus = cpumask_weight(topology_core_cpumask(cpu));
-	}
-
-	pkg = topology_logical_package_id(cpu);
-	for (; *types; types++) {
-		type = *types;
-		pmu = type->pmus;
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			box = pmu->boxes[pkg];
-			if (!box)
-				continue;
-			/* The first cpu on a package activates the box */
-			if (atomic_add_return(ncpus, &box->refcnt) == ncpus)
-				uncore_box_init(box);
-		}
-	}
-
-	return 0;
-}
-
-static int uncore_cpu_prepare(unsigned int cpu)
-{
-	struct intel_uncore_type *type, **types = uncore_msr_uncores;
-	struct intel_uncore_pmu *pmu;
-	struct intel_uncore_box *box;
-	int i, pkg;
-
-	pkg = topology_logical_package_id(cpu);
-	for (; *types; types++) {
-		type = *types;
-		pmu = type->pmus;
-		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			if (pmu->boxes[pkg])
-				continue;
-			/* First cpu of a package allocates the box */
-			box = uncore_alloc_box(type, cpu_to_node(cpu));
-			if (!box)
-				return -ENOMEM;
-			box->pmu = pmu;
-			box->pkgid = pkg;
-			pmu->boxes[pkg] = box;
-		}
-	}
-	return 0;
-}
-
 static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
 				   int new_cpu)
 {
@@ -1177,12 +1079,14 @@ static void uncore_change_context(struct intel_uncore_type **uncores,
 
 static int uncore_event_cpu_offline(unsigned int cpu)
 {
-	int target;
+	struct intel_uncore_type *type, **types = uncore_msr_uncores;
+	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_box *box;
+	int i, pkg, target;
 
 	/* Check if exiting cpu is used for collecting uncore events */
 	if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
-		return 0;
-
+		goto unref;
 	/* Find a new cpu to collect uncore events */
 	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
 
@@ -1194,12 +1098,82 @@ static int uncore_event_cpu_offline(unsigned int cpu)
 
 	uncore_change_context(uncore_msr_uncores, cpu, target);
 	uncore_change_context(uncore_pci_uncores, cpu, target);
+
+unref:
+	/* Clear the references */
+	pkg = topology_logical_package_id(cpu);
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			box = pmu->boxes[pkg];
+			if (box && atomic_dec_return(&box->refcnt) == 0)
+				uncore_box_exit(box);
+		}
+	}
 	return 0;
 }
 
+static int allocate_boxes(struct intel_uncore_type **types,
+			 unsigned int pkg, unsigned int cpu)
+{
+	struct intel_uncore_box *box, *tmp;
+	struct intel_uncore_type *type;
+	struct intel_uncore_pmu *pmu;
+	LIST_HEAD(allocated);
+	int i;
+
+	/* Try to allocate all required boxes */
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			if (pmu->boxes[pkg])
+				continue;
+			box = uncore_alloc_box(type, cpu_to_node(cpu));
+			if (!box)
+				goto cleanup;
+			box->pmu = pmu;
+			box->pkgid = pkg;
+			list_add(&box->active_list, &allocated);
+		}
+	}
+	/* Install them in the pmus */
+	list_for_each_entry_safe(box, tmp, &allocated, active_list) {
+		list_del_init(&box->active_list);
+		box->pmu->boxes[pkg] = box;
+	}
+	return 0;
+
+cleanup:
+	list_for_each_entry_safe(box, tmp, &allocated, active_list) {
+		list_del_init(&box->active_list);
+		kfree(box);
+	}
+	return -ENOMEM;
+}
+
 static int uncore_event_cpu_online(unsigned int cpu)
 {
-	int target;
+	struct intel_uncore_type *type, **types = uncore_msr_uncores;
+	struct intel_uncore_pmu *pmu;
+	struct intel_uncore_box *box;
+	int i, ret, pkg, target;
+
+	pkg = topology_logical_package_id(cpu);
+	ret = allocate_boxes(types, pkg, cpu);
+	if (ret)
+		return ret;
+
+	for (; *types; types++) {
+		type = *types;
+		pmu = type->pmus;
+		for (i = 0; i < type->num_boxes; i++, pmu++) {
+			box = pmu->boxes[pkg];
+			if (!box && atomic_inc_return(&box->refcnt) == 1)
+				uncore_box_init(box);
+		}
+	}
 
 	/*
 	 * Check if there is an online cpu in the package
@@ -1354,6 +1328,8 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_DESKTOP,skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_MOBILE, skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,      skx_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
 	{},
 };
 
@@ -1389,38 +1365,16 @@ static int __init intel_uncore_init(void)
 	if (cret && pret)
 		return -ENODEV;
 
-	/*
-	 * Install callbacks. Core will call them for each online cpu.
-	 *
-	 * The first online cpu of each package allocates and takes
-	 * the refcounts for all other online cpus in that package.
-	 * If msrs are not enabled no allocation is required and
-	 * uncore_cpu_prepare() is not called for each online cpu.
-	 */
-	if (!cret) {
-	       ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
-				       "perf/x86/intel/uncore:prepare",
-				       uncore_cpu_prepare, NULL);
-		if (ret)
-			goto err;
-	} else {
-		cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
-					  "perf/x86/intel/uncore:prepare",
-					  uncore_cpu_prepare, NULL);
-	}
-	first_init = 1;
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
-			  "perf/x86/uncore:starting",
-			  uncore_cpu_starting, uncore_cpu_dying);
-	first_init = 0;
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
-			  "perf/x86/uncore:online",
-			  uncore_event_cpu_online, uncore_event_cpu_offline);
+	/* Install hotplug callbacks to setup the targets for each package */
+	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
+				"perf/x86/intel/uncore:online",
+				uncore_event_cpu_online,
+				uncore_event_cpu_offline);
+	if (ret)
+		goto err;
 	return 0;
 
 err:
-	/* Undo box->init_box() */
-	on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1);
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_pci_exit();
 	return ret;
@@ -1429,9 +1383,7 @@ module_init(intel_uncore_init);
 
 static void __exit intel_uncore_exit(void)
 {
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING);
-	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP);
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_pci_exit();
 }
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 2b892e2313a9..5d6a53fd7521 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -7,7 +7,6 @@ generated-y += unistd_64_x32.h
 generated-y += xen-hypercalls.h
 
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 0c5fbc68e82d..eff8e36aaf72 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -195,7 +195,7 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
 
 static inline void native_apic_msr_eoi_write(u32 reg, u32 v)
 {
-	wrmsr_notrace(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+	__wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
 }
 
 static inline u32 native_apic_msr_read(u32 reg)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index eafee3161d1c..4e7772387c6e 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -100,7 +100,7 @@
 #define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
 #define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
-/* free, was #define X86_FEATURE_CLFLUSH_MONITOR ( 3*32+25) * "" clflush reqd with monitor */
+#define X86_FEATURE_CPUID	( 3*32+25) /* CPU has CPUID instruction itself */
 #define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
@@ -186,7 +186,7 @@
  *
  * Reuse free bits when adding new feature flags!
  */
-
+#define X86_FEATURE_RING3MWAIT	( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
 #define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
@@ -288,6 +288,7 @@
 #define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
 #define X86_FEATURE_RDPID	(16*32+ 22) /* RDPID instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
@@ -320,5 +321,4 @@
 #define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
 #define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
 #define X86_BUG_AMD_E400	X86_BUG(13) /* CPU is among the affected by Erratum 400 */
-
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
index ced283ac79df..af95c47d5c9e 100644
--- a/arch/x86/include/asm/div64.h
+++ b/arch/x86/include/asm/div64.h
@@ -59,6 +59,17 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
 }
 #define div_u64_rem	div_u64_rem
 
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+	u32 high, low;
+
+	asm ("mull %[b]" : "=a" (low), "=d" (high)
+			 : [a] "a" (a), [b] "rm" (b) );
+
+	return low | ((u64)high) << 32;
+}
+#define mul_u32_u32 mul_u32_u32
+
 #else
 # include <asm-generic/div64.h>
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index ec23d8e1297c..67313f3a9874 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -30,8 +30,6 @@ extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
 			     int checktype);
 extern void update_e820(void);
 extern void e820_setup_gap(void);
-extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
-			unsigned long start_addr, unsigned long long end_addr);
 struct setup_data;
 extern void parse_e820_ext(u64 phys_addr, u32 data_len);
 
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index e99675b9c861..2f77bcefe6b4 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -191,6 +191,7 @@ static inline efi_status_t efi_thunk_set_virtual_address_map(
 struct efi_config {
 	u64 image_handle;
 	u64 table;
+	u64 runtime_services;
 	u64 boot_services;
 	u64 text_output;
 	efi_status_t (*call)(unsigned long, ...);
@@ -226,6 +227,10 @@ static inline bool efi_is_64bit(void)
 #define __efi_call_early(f, ...)					\
 	__efi_early()->call((unsigned long)f, __VA_ARGS__);
 
+#define efi_call_runtime(f, ...)					\
+	__efi_early()->call(efi_table_attr(efi_runtime_services, f,	\
+		__efi_early()->runtime_services), __VA_ARGS__)
+
 extern bool efi_reboot_required(void);
 
 #else
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index e7f155c3045e..9d49c18b5ea9 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -258,6 +258,15 @@ extern int force_personality32;
 
 #define ELF_HWCAP		(boot_cpu_data.x86_capability[CPUID_1_EDX])
 
+extern u32 elf_hwcap2;
+
+/*
+ * HWCAP2 supplies mask with kernel enabled CPU features, so that
+ * the application can discover that it can safely use them.
+ * The bits are defined in uapi/asm/hwcap2.h.
+ */
+#define ELF_HWCAP2		(elf_hwcap2)
+
 /* This yields a string that ld.so will use to load implementation
    specific libraries for optimization.  This is more specific in
    intent than poking at uname or /proc/cpuinfo.
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index d4a684997497..255645f60ca2 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -87,6 +87,16 @@ extern void fpstate_init_soft(struct swregs_state *soft);
 #else
 static inline void fpstate_init_soft(struct swregs_state *soft) {}
 #endif
+
+static inline void fpstate_init_xstate(struct xregs_state *xsave)
+{
+	/*
+	 * XRSTORS requires these bits set in xcomp_bv, or it will
+	 * trigger #GP:
+	 */
+	xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xfeatures_mask;
+}
+
 static inline void fpstate_init_fxstate(struct fxregs_state *fx)
 {
 	fx->cwd = 0x37f;
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index 49da9f497b90..fe04491130ae 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -27,7 +27,6 @@ extern void intel_mid_pwr_power_off(void);
 extern int intel_mid_pwr_get_lss_id(struct pci_dev *pdev);
 
 extern int get_gpio_by_name(const char *name);
-extern void intel_scu_device_register(struct platform_device *pdev);
 extern int __init sfi_parse_mrtc(struct sfi_table_header *table);
 extern int __init sfi_parse_mtmr(struct sfi_table_header *table);
 extern int sfi_mrtc_num;
@@ -42,10 +41,8 @@ struct devs_id {
 	char name[SFI_NAME_LEN + 1];
 	u8 type;
 	u8 delay;
+	u8 msic;
 	void *(*get_platform_data)(void *info);
-	/* Custom handler for devices */
-	void (*device_handler)(struct sfi_device_table_entry *pentry,
-			       struct devs_id *dev);
 };
 
 #define sfi_device(i)								\
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index d34bd370074b..7afb0e2f07f4 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -164,6 +164,17 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
 #define virt_to_bus virt_to_phys
 #define bus_to_virt phys_to_virt
 
+/*
+ * The default ioremap() behavior is non-cached; if you need something
+ * else, you probably want one of the following.
+ */
+extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
+#define ioremap_uc ioremap_uc
+
+extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, unsigned long prot_val);
+
 /**
  * ioremap     -   map bus memory into CPU space
  * @offset:    bus address of the memory
@@ -178,17 +189,6 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
  * If the area you are trying to map is a PCI BAR you should have a
  * look at pci_iomap().
  */
-extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size);
-#define ioremap_uc ioremap_uc
-
-extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
-				unsigned long prot_val);
-
-/*
- * The default ioremap() behavior is non-cached:
- */
 static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
 {
 	return ioremap_nocache(offset, size);
@@ -207,18 +207,42 @@ extern void set_iounmap_nonlazy(void);
  */
 #define xlate_dev_kmem_ptr(p)	p
 
+/**
+ * memset_io	Set a range of I/O memory to a constant value
+ * @addr:	The beginning of the I/O-memory range to set
+ * @val:	The value to set the memory to
+ * @count:	The number of bytes to set
+ *
+ * Set a range of I/O memory to a given value.
+ */
 static inline void
 memset_io(volatile void __iomem *addr, unsigned char val, size_t count)
 {
 	memset((void __force *)addr, val, count);
 }
 
+/**
+ * memcpy_fromio	Copy a block of data from I/O memory
+ * @dst:		The (RAM) destination for the copy
+ * @src:		The (I/O memory) source for the data
+ * @count:		The number of bytes to copy
+ *
+ * Copy a block of data from I/O memory.
+ */
 static inline void
 memcpy_fromio(void *dst, const volatile void __iomem *src, size_t count)
 {
 	memcpy(dst, (const void __force *)src, count);
 }
 
+/**
+ * memcpy_toio		Copy a block of data into I/O memory
+ * @dst:		The (I/O memory) destination for the copy
+ * @src:		The (RAM) source for the data
+ * @count:		The number of bytes to copy
+ *
+ * Copy a block of data to I/O memory.
+ */
 static inline void
 memcpy_toio(volatile void __iomem *dst, const void *src, size_t count)
 {
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 5132f2a6c0a2..e63873683d4a 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -97,10 +97,6 @@
 
 #define MCE_OVERFLOW 0		/* bit 0 in flags means overflow */
 
-/* Software defined banks */
-#define MCE_EXTENDED_BANK	128
-#define MCE_THERMAL_BANK	(MCE_EXTENDED_BANK + 0)
-
 #define MCE_LOG_LEN 32
 #define MCE_LOG_SIGNATURE	"MACHINECHECK"
 
@@ -193,6 +189,15 @@ extern struct mce_vendor_flags mce_flags;
 
 extern struct mca_config mca_cfg;
 extern struct mca_msr_regs msr_ops;
+
+enum mce_notifier_prios {
+	MCE_PRIO_SRAO		= INT_MAX,
+	MCE_PRIO_EXTLOG		= INT_MAX - 1,
+	MCE_PRIO_NFIT		= INT_MAX - 2,
+	MCE_PRIO_EDAC		= INT_MAX - 3,
+	MCE_PRIO_LOWEST		= 0,
+};
+
 extern void mce_register_decode_chain(struct notifier_block *nb);
 extern void mce_unregister_decode_chain(struct notifier_block *nb);
 
@@ -306,8 +311,6 @@ extern void (*deferred_error_int_vector)(void);
 
 void intel_init_thermal(struct cpuinfo_x86 *c);
 
-void mce_log_therm_throt_event(__u64 status);
-
 /* Interrupt Handler for core thermal thresholds */
 extern int (*platform_thermal_notify)(__u64 msr_val);
 
@@ -362,12 +365,13 @@ struct smca_hwid {
 	unsigned int bank_type;	/* Use with smca_bank_types for easy indexing. */
 	u32 hwid_mcatype;	/* (hwid,mcatype) tuple */
 	u32 xec_bitmap;		/* Bitmap of valid ExtErrorCodes; current max is 21. */
+	u8 count;		/* Number of instances. */
 };
 
 struct smca_bank {
 	struct smca_hwid *hwid;
-	/* Instance ID */
-	u32 id;
+	u32 id;			/* Value of MCA_IPID[InstanceId]. */
+	u8 sysfs_id;		/* Value used for sysfs name. */
 };
 
 extern struct smca_bank smca_banks[MAX_NR_BANKS];
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 38711df3bcb5..daadeeea00b1 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -7,18 +7,17 @@
 
 #define native_rdmsr(msr, val1, val2)			\
 do {							\
-	u64 __val = native_read_msr((msr));		\
+	u64 __val = __rdmsr((msr));			\
 	(void)((val1) = (u32)__val);			\
 	(void)((val2) = (u32)(__val >> 32));		\
 } while (0)
 
 #define native_wrmsr(msr, low, high)			\
-	native_write_msr(msr, low, high)
+	__wrmsr(msr, low, high)
 
 #define native_wrmsrl(msr, val)				\
-	native_write_msr((msr),				\
-			 (u32)((u64)(val)),		\
-			 (u32)((u64)(val) >> 32))
+	__wrmsr((msr), (u32)((u64)(val)),		\
+		       (u32)((u64)(val) >> 32))
 
 struct ucode_patch {
 	struct list_head plist;
@@ -140,6 +139,7 @@ extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
 void reload_early_microcode(void);
 extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
+extern bool initrd_gone;
 #else
 static inline int __init microcode_init(void)			{ return 0; };
 static inline void __init load_ucode_bsp(void)			{ }
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index 3e3e20be829a..3d57009e168b 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -54,6 +54,4 @@ static inline int __init
 save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
 void reload_ucode_amd(void) {}
 #endif
-
-extern bool check_current_patch_level(u32 *rev, bool early);
 #endif /* _ASM_X86_MICROCODE_AMD_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 710273c617b8..00293a94ffaf 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -543,6 +543,11 @@
 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT	39
 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
 
+/* MISC_FEATURE_ENABLES non-architectural features */
+#define MSR_MISC_FEATURE_ENABLES	0x00000140
+
+#define MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT		1
+
 #define MSR_IA32_TSC_DEADLINE		0x000006E0
 
 /* P4/Xeon+ specific */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index db0b90c3b03e..898dba2e2e2c 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -80,7 +80,14 @@ static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {}
 static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
 #endif
 
-static inline unsigned long long native_read_msr(unsigned int msr)
+/*
+ * __rdmsr() and __wrmsr() are the two primitives which are the bare minimum MSR
+ * accessors and should not have any tracing or other functionality piggybacking
+ * on them - those are *purely* for accessing MSRs and nothing more. So don't even
+ * think of extending them - you will be slapped with a stinking trout or a frozen
+ * shark will reach you, wherever you are! You've been warned.
+ */
+static inline unsigned long long notrace __rdmsr(unsigned int msr)
 {
 	DECLARE_ARGS(val, low, high);
 
@@ -88,11 +95,30 @@ static inline unsigned long long native_read_msr(unsigned int msr)
 		     "2:\n"
 		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe)
 		     : EAX_EDX_RET(val, low, high) : "c" (msr));
-	if (msr_tracepoint_active(__tracepoint_read_msr))
-		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0);
+
 	return EAX_EDX_VAL(val, low, high);
 }
 
+static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high)
+{
+	asm volatile("1: wrmsr\n"
+		     "2:\n"
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
+		     : : "c" (msr), "a"(low), "d" (high) : "memory");
+}
+
+static inline unsigned long long native_read_msr(unsigned int msr)
+{
+	unsigned long long val;
+
+	val = __rdmsr(msr);
+
+	if (msr_tracepoint_active(__tracepoint_read_msr))
+		do_trace_read_msr(msr, val, 0);
+
+	return val;
+}
+
 static inline unsigned long long native_read_msr_safe(unsigned int msr,
 						      int *err)
 {
@@ -116,29 +142,14 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 
 /* Can be uninlined because referenced by paravirt */
 static inline void notrace
-__native_write_msr_notrace(unsigned int msr, u32 low, u32 high)
-{
-	asm volatile("1: wrmsr\n"
-		     "2:\n"
-		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
-		     : : "c" (msr), "a"(low), "d" (high) : "memory");
-}
-
-/* Can be uninlined because referenced by paravirt */
-static inline void notrace
 native_write_msr(unsigned int msr, u32 low, u32 high)
 {
-	__native_write_msr_notrace(msr, low, high);
+	__wrmsr(msr, low, high);
+
 	if (msr_tracepoint_active(__tracepoint_write_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
 }
 
-static inline void
-wrmsr_notrace(unsigned int msr, u32 low, u32 high)
-{
-	__native_write_msr_notrace(msr, low, high);
-}
-
 /* Can be uninlined because referenced by paravirt */
 static inline int notrace
 native_write_msr_safe(unsigned int msr, u32 low, u32 high)
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index b6c0b404898a..fbc73360aea0 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -27,6 +27,7 @@ struct vm_area_struct;
 
 extern pgd_t swapper_pg_dir[1024];
 extern pgd_t initial_page_table[1024];
+extern pmd_t initial_pg_pmd[];
 
 static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
@@ -75,4 +76,35 @@ do {						\
 #define kern_addr_valid(kaddr)	(0)
 #endif
 
+/*
+ * This is how much memory in addition to the memory covered up to
+ * and including _end we need mapped initially.
+ * We need:
+ *     (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE)
+ *     (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE)
+ *
+ * Modulo rounding, each megabyte assigned here requires a kilobyte of
+ * memory, which is currently unreclaimed.
+ *
+ * This should be a multiple of a page.
+ *
+ * KERNEL_IMAGE_SIZE should be greater than pa(_end)
+ * and small than max_low_pfn, otherwise will waste some page table entries
+ */
+#if PTRS_PER_PMD > 1
+#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
+#else
+#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
+#endif
+
+/*
+ * Number of possible pages in the lowmem region.
+ *
+ * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
+ * gas warning about overflowing shift count when gas has been compiled
+ * with only a host target support using a 32-bit type for internal
+ * representation.
+ */
+#define LOWMEM_PAGES ((((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT))
+
 #endif /* _ASM_X86_PGTABLE_32_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 1be64da0384e..e6cfe7ba2d65 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -104,6 +104,7 @@ struct cpuinfo_x86 {
 	__u8			x86_phys_bits;
 	/* CPUID returned core id bits: */
 	__u8			x86_coreid_bits;
+	__u8			cu_id;
 	/* Max extended CPUID function supported: */
 	__u32			extended_cpuid_level;
 	/* Maximum supported CPUID level, -1=no CPUID: */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 921bea7a2708..6d391909e864 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -23,9 +23,6 @@
 /* How long a lock should spin before we consider blocking */
 #define SPIN_THRESHOLD	(1 << 15)
 
-extern struct static_key paravirt_ticketlocks_enabled;
-static __always_inline bool static_key_false(struct static_key *key);
-
 #include <asm/qspinlock.h>
 
 /*
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index 062921ef34e9..6686820feae9 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -10,6 +10,7 @@ struct mm_struct;
 
 extern enum uv_system_type get_uv_system_type(void);
 extern int is_uv_system(void);
+extern int is_uv_hubless(void);
 extern void uv_cpu_init(void);
 extern void uv_nmi_init(void);
 extern void uv_system_init(void);
@@ -23,6 +24,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 
 static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
 static inline int is_uv_system(void)	{ return 0; }
+static inline int is_uv_hubless(void)	{ return 0; }
 static inline void uv_cpu_init(void)	{ }
 static inline void uv_system_init(void)	{ }
 static inline const struct cpumask *
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 097b80c989c4..72e8300b1e8a 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -772,6 +772,7 @@ static inline int uv_num_possible_blades(void)
 
 /* Per Hub NMI support */
 extern void uv_nmi_setup(void);
+extern void uv_nmi_setup_hubless(void);
 
 /* BMC sets a bit this MMR non-zero before sending an NMI */
 #define UVH_NMI_MMR		UVH_SCRATCH5
@@ -799,6 +800,8 @@ struct uv_hub_nmi_s {
 	atomic_t	read_mmr_count;	/* count of MMR reads */
 	atomic_t	nmi_count;	/* count of true UV NMIs */
 	unsigned long	nmi_value;	/* last value read from NMI MMR */
+	bool		hub_present;	/* false means UV hubless system */
+	bool		pch_owner;	/* indicates this hub owns PCH */
 };
 
 struct uv_cpu_nmi_s {
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index b10bf319ed20..5138dacf8bb8 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -135,7 +135,8 @@ struct boot_params {
 	__u8  eddbuf_entries;				/* 0x1e9 */
 	__u8  edd_mbr_sig_buf_entries;			/* 0x1ea */
 	__u8  kbd_status;				/* 0x1eb */
-	__u8  _pad5[3];					/* 0x1ec */
+	__u8  secure_boot;				/* 0x1ec */
+	__u8  _pad5[2];					/* 0x1ed */
 	/*
 	 * The sentinel is set to a nonzero value (0xff) in header.S.
 	 *
diff --git a/arch/x86/include/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h
new file mode 100644
index 000000000000..0bd2be5c7617
--- /dev/null
+++ b/arch/x86/include/uapi/asm/hwcap2.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_X86_HWCAP2_H
+#define _ASM_X86_HWCAP2_H
+
+/* MONITOR/MWAIT enabled in Ring 3 */
+#define HWCAP2_RING3MWAIT		(1 << 0)
+
+#endif
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 581386c7e429..bdcdb3b3a219 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -101,7 +101,6 @@ obj-$(CONFIG_APB_TIMER)		+= apb_timer.o
 
 obj-$(CONFIG_AMD_NB)		+= amd_nb.o
 obj-$(CONFIG_DEBUG_RODATA_TEST)	+= test_rodata.o
-obj-$(CONFIG_DEBUG_NX_TEST)	+= test_nx.o
 obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
 
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvmclock.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 64422f850e95..ae32838cac5f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -35,6 +35,7 @@
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
 #include <linux/pci.h>
+#include <linux/efi-bgrt.h>
 
 #include <asm/irqdomain.h>
 #include <asm/pci_x86.h>
@@ -723,11 +724,12 @@ int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
 	return 0;
 }
 
-int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu)
+int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id,
+		 int *pcpu)
 {
 	int cpu;
 
-	cpu = acpi_register_lapic(physid, U32_MAX, ACPI_MADT_ENABLED);
+	cpu = acpi_register_lapic(physid, acpi_id, ACPI_MADT_ENABLED);
 	if (cpu < 0) {
 		pr_info(PREFIX "Unable to map lapic to logical cpu number\n");
 		return cpu;
@@ -1557,6 +1559,12 @@ int __init early_acpi_boot_init(void)
 	return 0;
 }
 
+static int __init acpi_parse_bgrt(struct acpi_table_header *table)
+{
+	efi_bgrt_init(table);
+	return 0;
+}
+
 int __init acpi_boot_init(void)
 {
 	/* those are executed after early-quirks are executed */
@@ -1581,6 +1589,8 @@ int __init acpi_boot_init(void)
 	acpi_process_madt();
 
 	acpi_table_parse(ACPI_SIG_HPET, acpi_parse_hpet);
+	if (IS_ENABLED(CONFIG_ACPI_BGRT))
+		acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
 
 	if (!acpi_noirq)
 		x86_init.pci.init = pci_acpi_init;
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index af15f4444330..8233a630280f 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -12,7 +12,6 @@
 #include <linux/sched.h>
 
 #include <acpi/processor.h>
-#include <asm/acpi.h>
 #include <asm/mwait.h>
 #include <asm/special_insns.h>
 
@@ -89,7 +88,8 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
 	retval = 0;
 	/* If the HW does not support any sub-states in this C-state */
 	if (num_cstate_subtype == 0) {
-		pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n", cx->address, edx_part);
+		pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n",
+				cx->address, edx_part);
 		retval = -1;
 		goto out;
 	}
@@ -104,8 +104,8 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
 	if (!mwait_supported[cstate_type]) {
 		mwait_supported[cstate_type] = 1;
 		printk(KERN_DEBUG
-			"Monitor-Mwait will be used to enter C-%d "
-			"state\n", cx->type);
+			"Monitor-Mwait will be used to enter C-%d state\n",
+			cx->type);
 	}
 	snprintf(cx->desc,
 			ACPI_CX_DESC_LEN, "ACPI FFH INTEL MWAIT 0x%x",
@@ -166,6 +166,7 @@ EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_enter);
 static int __init ffh_cstate_init(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
+
 	if (c->x86_vendor != X86_VENDOR_INTEL)
 		return -1;
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 5b7e43eff139..8567c851172c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -529,18 +529,19 @@ static void lapic_timer_broadcast(const struct cpumask *mask)
  * The local apic timer can be used for any function which is CPU local.
  */
 static struct clock_event_device lapic_clockevent = {
-	.name			= "lapic",
-	.features		= CLOCK_EVT_FEAT_PERIODIC |
-				  CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP
-				  | CLOCK_EVT_FEAT_DUMMY,
-	.shift			= 32,
-	.set_state_shutdown	= lapic_timer_shutdown,
-	.set_state_periodic	= lapic_timer_set_periodic,
-	.set_state_oneshot	= lapic_timer_set_oneshot,
-	.set_next_event		= lapic_next_event,
-	.broadcast		= lapic_timer_broadcast,
-	.rating			= 100,
-	.irq			= -1,
+	.name				= "lapic",
+	.features			= CLOCK_EVT_FEAT_PERIODIC |
+					  CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP
+					  | CLOCK_EVT_FEAT_DUMMY,
+	.shift				= 32,
+	.set_state_shutdown		= lapic_timer_shutdown,
+	.set_state_periodic		= lapic_timer_set_periodic,
+	.set_state_oneshot		= lapic_timer_set_oneshot,
+	.set_state_oneshot_stopped	= lapic_timer_shutdown,
+	.set_next_event			= lapic_next_event,
+	.broadcast			= lapic_timer_broadcast,
+	.rating				= 100,
+	.irq				= -1,
 };
 static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
 
@@ -1245,7 +1246,7 @@ static void lapic_setup_esr(void)
 /**
  * setup_local_APIC - setup the local APIC
  *
- * Used to setup local APIC while initializing BSP or bringin up APs.
+ * Used to setup local APIC while initializing BSP or bringing up APs.
  * Always called with preemption disabled.
  */
 void setup_local_APIC(void)
@@ -2028,8 +2029,8 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 /*
  * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated
  * contiguously, it equals to current allocated max logical CPU ID plus 1.
- * All allocated CPU ID should be in [0, nr_logical_cpuidi), so the maximum of
- * nr_logical_cpuids is nr_cpu_ids.
+ * All allocated CPU IDs should be in the [0, nr_logical_cpuids) range,
+ * so the maximum of nr_logical_cpuids is nr_cpu_ids.
  *
  * NOTE: Reserve 0 for BSP.
  */
@@ -2094,7 +2095,7 @@ int __generic_processor_info(int apicid, int version, bool enabled)
 	 * Since fixing handling of boot_cpu_physical_apicid requires
 	 * another discussion and tests on each platform, we leave it
 	 * for now and here we use read_apic_id() directly in this
-	 * function, generic_processor_info().
+	 * function, __generic_processor_info().
 	 */
 	if (disabled_cpu_apicid != BAD_APICID &&
 	    disabled_cpu_apicid != read_apic_id() &&
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 1e35dd06b090..347bb9f65737 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1107,12 +1107,12 @@ int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, struct irq_alloc_info *info)
 
 	ioapic = mp_find_ioapic(gsi);
 	if (ioapic < 0)
-		return -1;
+		return -ENODEV;
 
 	pin = mp_find_ioapic_pin(ioapic, gsi);
 	idx = find_irq_entry(ioapic, pin, mp_INT);
 	if ((flags & IOAPIC_MAP_CHECK) && idx < 0)
-		return -1;
+		return -ENODEV;
 
 	return mp_map_pin_to_irq(gsi, idx, ioapic, pin, flags, info);
 }
@@ -2117,6 +2117,7 @@ static inline void __init check_timer(void)
 			if (idx != -1 && irq_trigger(idx))
 				unmask_ioapic_irq(irq_get_chip_data(0));
 		}
+		irq_domain_deactivate_irq(irq_data);
 		irq_domain_activate_irq(irq_data);
 		if (timer_irq_works()) {
 			if (disable_timer_pin_1 > 0)
@@ -2138,6 +2139,7 @@ static inline void __init check_timer(void)
 		 * legacy devices should be connected to IO APIC #0
 		 */
 		replace_pin_at_irq_node(data, node, apic1, pin1, apic2, pin2);
+		irq_domain_deactivate_irq(irq_data);
 		irq_domain_activate_irq(irq_data);
 		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 35690a168cf7..e9f8f8cdd570 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -41,40 +41,44 @@
 
 DEFINE_PER_CPU(int, x2apic_extra_bits);
 
-#define PR_DEVEL(fmt, args...)	pr_devel("%s: " fmt, __func__, args)
-
-static enum uv_system_type uv_system_type;
-static u64 gru_start_paddr, gru_end_paddr;
-static u64 gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr;
-static u64 gru_dist_lmask, gru_dist_umask;
-static union uvh_apicid uvh_apicid;
-
-/* info derived from CPUID */
+static enum uv_system_type	uv_system_type;
+static bool			uv_hubless_system;
+static u64			gru_start_paddr, gru_end_paddr;
+static u64			gru_dist_base, gru_first_node_paddr = -1LL, gru_last_node_paddr;
+static u64			gru_dist_lmask, gru_dist_umask;
+static union uvh_apicid		uvh_apicid;
+
+/* Information derived from CPUID: */
 static struct {
 	unsigned int apicid_shift;
 	unsigned int apicid_mask;
 	unsigned int socketid_shift;	/* aka pnode_shift for UV1/2/3 */
 	unsigned int pnode_mask;
 	unsigned int gpa_shift;
+	unsigned int gnode_shift;
 } uv_cpuid;
 
 int uv_min_hub_revision_id;
 EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
+
 unsigned int uv_apicid_hibits;
 EXPORT_SYMBOL_GPL(uv_apicid_hibits);
 
 static struct apic apic_x2apic_uv_x;
 static struct uv_hub_info_s uv_hub_info_node0;
 
-/* Set this to use hardware error handler instead of kernel panic */
+/* Set this to use hardware error handler instead of kernel panic: */
 static int disable_uv_undefined_panic = 1;
+
 unsigned long uv_undefined(char *str)
 {
 	if (likely(!disable_uv_undefined_panic))
 		panic("UV: error: undefined MMR: %s\n", str);
 	else
 		pr_crit("UV: error: undefined MMR: %s\n", str);
-	return ~0ul;	/* cause a machine fault  */
+
+	/* Cause a machine fault: */
+	return ~0ul;
 }
 EXPORT_SYMBOL(uv_undefined);
 
@@ -85,18 +89,19 @@ static unsigned long __init uv_early_read_mmr(unsigned long addr)
 	mmr = early_ioremap(UV_LOCAL_MMR_BASE | addr, sizeof(*mmr));
 	val = *mmr;
 	early_iounmap(mmr, sizeof(*mmr));
+
 	return val;
 }
 
 static inline bool is_GRU_range(u64 start, u64 end)
 {
 	if (gru_dist_base) {
-		u64 su = start & gru_dist_umask; /* upper (incl pnode) bits */
-		u64 sl = start & gru_dist_lmask; /* base offset bits */
+		u64 su = start & gru_dist_umask; /* Upper (incl pnode) bits */
+		u64 sl = start & gru_dist_lmask; /* Base offset bits */
 		u64 eu = end & gru_dist_umask;
 		u64 el = end & gru_dist_lmask;
 
-		/* Must reside completely within a single GRU range */
+		/* Must reside completely within a single GRU range: */
 		return (sl == gru_dist_base && el == gru_dist_base &&
 			su >= gru_first_node_paddr &&
 			su <= gru_last_node_paddr &&
@@ -133,13 +138,14 @@ static int __init early_get_pnodeid(void)
 		break;
 	case UV4_HUB_PART_NUMBER:
 		uv_min_hub_revision_id += UV4_HUB_REVISION_BASE - 1;
+		uv_cpuid.gnode_shift = 2; /* min partition is 4 sockets */
 		break;
 	}
 
 	uv_hub_info->hub_revision = uv_min_hub_revision_id;
 	uv_cpuid.pnode_mask = (1 << m_n_config.s.n_skt) - 1;
 	pnode = (node_id.s.node_id >> 1) & uv_cpuid.pnode_mask;
-	uv_cpuid.gpa_shift = 46;	/* default unless changed */
+	uv_cpuid.gpa_shift = 46;	/* Default unless changed */
 
 	pr_info("UV: rev:%d part#:%x nodeid:%04x n_skt:%d pnmsk:%x pn:%x\n",
 		node_id.s.revision, node_id.s.part_number, node_id.s.node_id,
@@ -147,11 +153,12 @@ static int __init early_get_pnodeid(void)
 	return pnode;
 }
 
-/* [copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */
-#define SMT_LEVEL	0	/* leaf 0xb SMT level */
-#define INVALID_TYPE	0	/* leaf 0xb sub-leaf types */
-#define SMT_TYPE	1
-#define CORE_TYPE	2
+/* [Copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */
+
+#define SMT_LEVEL			0	/* Leaf 0xb SMT level */
+#define INVALID_TYPE			0	/* Leaf 0xb sub-leaf types */
+#define SMT_TYPE			1
+#define CORE_TYPE			2
 #define LEAFB_SUBTYPE(ecx)		(((ecx) >> 8) & 0xff)
 #define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
 
@@ -165,11 +172,13 @@ static void set_x2apic_bits(void)
 		pr_info("UV: CPU does not have CPUID.11\n");
 		return;
 	}
+
 	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
 	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) {
 		pr_info("UV: CPUID.11 not implemented\n");
 		return;
 	}
+
 	sid_shift = BITS_SHIFT_NEXT_LEVEL(eax);
 	sub_index = 1;
 	do {
@@ -180,8 +189,9 @@ static void set_x2apic_bits(void)
 		}
 		sub_index++;
 	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
-	uv_cpuid.apicid_shift = 0;
-	uv_cpuid.apicid_mask = (~(-1 << sid_shift));
+
+	uv_cpuid.apicid_shift	= 0;
+	uv_cpuid.apicid_mask	= (~(-1 << sid_shift));
 	uv_cpuid.socketid_shift = sid_shift;
 }
 
@@ -192,10 +202,8 @@ static void __init early_get_apic_socketid_shift(void)
 
 	set_x2apic_bits();
 
-	pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n",
-		uv_cpuid.apicid_shift, uv_cpuid.apicid_mask);
-	pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n",
-		uv_cpuid.socketid_shift, uv_cpuid.pnode_mask);
+	pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n", uv_cpuid.apicid_shift, uv_cpuid.apicid_mask);
+	pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n", uv_cpuid.socketid_shift, uv_cpuid.pnode_mask);
 }
 
 /*
@@ -208,10 +216,8 @@ static void __init uv_set_apicid_hibit(void)
 	union uv1h_lb_target_physical_apic_id_mask_u apicid_mask;
 
 	if (is_uv1_hub()) {
-		apicid_mask.v =
-			uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK);
-		uv_apicid_hibits =
-			apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK;
+		apicid_mask.v = uv_early_read_mmr(UV1H_LB_TARGET_PHYSICAL_APIC_ID_MASK);
+		uv_apicid_hibits = apicid_mask.s1.bit_enables & UV_APICID_HIBIT_MASK;
 	}
 }
 
@@ -220,20 +226,26 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	int pnodeid;
 	int uv_apic;
 
-	if (strncmp(oem_id, "SGI", 3) != 0)
+	if (strncmp(oem_id, "SGI", 3) != 0) {
+		if (strncmp(oem_id, "NSGI", 4) == 0) {
+			uv_hubless_system = true;
+			pr_info("UV: OEM IDs %s/%s, HUBLESS\n",
+				oem_id, oem_table_id);
+		}
 		return 0;
+	}
 
 	if (numa_off) {
 		pr_err("UV: NUMA is off, disabling UV support\n");
 		return 0;
 	}
 
-	/* Setup early hub type field in uv_hub_info for Node 0 */
+	/* Set up early hub type field in uv_hub_info for Node 0 */
 	uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0;
 
 	/*
 	 * Determine UV arch type.
-	 *   SGI: UV100/1000
+	 *   SGI:  UV100/1000
 	 *   SGI2: UV2000/3000
 	 *   SGI3: UV300 (truncated to 4 chars because of different varieties)
 	 *   SGI4: UV400 (truncated to 4 chars because of different varieties)
@@ -249,31 +261,32 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 
 	pnodeid = early_get_pnodeid();
 	early_get_apic_socketid_shift();
-	x86_platform.is_untracked_pat_range =  uv_is_untracked_pat_range;
+
+	x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range;
 	x86_platform.nmi_init = uv_nmi_init;
 
-	if (!strcmp(oem_table_id, "UVX")) {		/* most common */
+	if (!strcmp(oem_table_id, "UVX")) {
+		/* This is the most common hardware variant: */
 		uv_system_type = UV_X2APIC;
 		uv_apic = 0;
 
-	} else if (!strcmp(oem_table_id, "UVH")) {	/* only UV1 systems */
+	} else if (!strcmp(oem_table_id, "UVH")) {
+		/* Only UV1 systems: */
 		uv_system_type = UV_NON_UNIQUE_APIC;
-		__this_cpu_write(x2apic_extra_bits,
-			pnodeid << uvh_apicid.s.pnode_shift);
+		__this_cpu_write(x2apic_extra_bits, pnodeid << uvh_apicid.s.pnode_shift);
 		uv_set_apicid_hibit();
 		uv_apic = 1;
 
-	} else	if (!strcmp(oem_table_id, "UVL")) {	/* only used for */
-		uv_system_type = UV_LEGACY_APIC;	/* very small systems */
+	} else if (!strcmp(oem_table_id, "UVL")) {
+		/* Only used for very small systems:  */
+		uv_system_type = UV_LEGACY_APIC;
 		uv_apic = 0;
 
 	} else {
 		goto badbios;
 	}
 
-	pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n",
-		oem_id, oem_table_id, uv_system_type,
-		uv_min_hub_revision_id, uv_apic);
+	pr_info("UV: OEM IDs %s/%s, System/HUB Types %d/%d, uv_apic %d\n", oem_id, oem_table_id, uv_system_type, uv_min_hub_revision_id, uv_apic);
 
 	return uv_apic;
 
@@ -294,6 +307,12 @@ int is_uv_system(void)
 }
 EXPORT_SYMBOL_GPL(is_uv_system);
 
+int is_uv_hubless(void)
+{
+	return uv_hubless_system;
+}
+EXPORT_SYMBOL_GPL(is_uv_hubless);
+
 void **__uv_hub_info_list;
 EXPORT_SYMBOL_GPL(__uv_hub_info_list);
 
@@ -306,16 +325,18 @@ EXPORT_SYMBOL_GPL(uv_possible_blades);
 unsigned long sn_rtc_cycles_per_second;
 EXPORT_SYMBOL(sn_rtc_cycles_per_second);
 
-/* the following values are used for the per node hub info struct */
-static __initdata unsigned short *_node_to_pnode;
-static __initdata unsigned short _min_socket, _max_socket;
-static __initdata unsigned short _min_pnode, _max_pnode, _gr_table_len;
-static __initdata struct uv_gam_range_entry *uv_gre_table;
-static __initdata struct uv_gam_parameters *uv_gp_table;
-static __initdata unsigned short *_socket_to_node;
-static __initdata unsigned short *_socket_to_pnode;
-static __initdata unsigned short *_pnode_to_socket;
-static __initdata struct uv_gam_range_s *_gr_table;
+/* The following values are used for the per node hub info struct */
+static __initdata unsigned short		*_node_to_pnode;
+static __initdata unsigned short		_min_socket, _max_socket;
+static __initdata unsigned short		_min_pnode, _max_pnode, _gr_table_len;
+static __initdata struct uv_gam_range_entry	*uv_gre_table;
+static __initdata struct uv_gam_parameters	*uv_gp_table;
+static __initdata unsigned short		*_socket_to_node;
+static __initdata unsigned short		*_socket_to_pnode;
+static __initdata unsigned short		*_pnode_to_socket;
+
+static __initdata struct uv_gam_range_s		*_gr_table;
+
 #define	SOCK_EMPTY	((unsigned short)~0)
 
 extern int uv_hub_info_version(void)
@@ -324,7 +345,7 @@ extern int uv_hub_info_version(void)
 }
 EXPORT_SYMBOL(uv_hub_info_version);
 
-/* Build GAM range lookup table */
+/* Build GAM range lookup table: */
 static __init void build_uv_gr_table(void)
 {
 	struct uv_gam_range_entry *gre = uv_gre_table;
@@ -342,25 +363,24 @@ static __init void build_uv_gr_table(void)
 
 	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
 		if (gre->type == UV_GAM_RANGE_TYPE_HOLE) {
-			if (!ram_limit) {   /* mark hole between ram/non-ram */
+			if (!ram_limit) {
+				/* Mark hole between RAM/non-RAM: */
 				ram_limit = last_limit;
 				last_limit = gre->limit;
 				lsid++;
 				continue;
 			}
 			last_limit = gre->limit;
-			pr_info("UV: extra hole in GAM RE table @%d\n",
-				(int)(gre - uv_gre_table));
+			pr_info("UV: extra hole in GAM RE table @%d\n", (int)(gre - uv_gre_table));
 			continue;
 		}
 		if (_max_socket < gre->sockid) {
-			pr_err("UV: GAM table sockid(%d) too large(>%d) @%d\n",
-				gre->sockid, _max_socket,
-				(int)(gre - uv_gre_table));
+			pr_err("UV: GAM table sockid(%d) too large(>%d) @%d\n", gre->sockid, _max_socket, (int)(gre - uv_gre_table));
 			continue;
 		}
 		sid = gre->sockid - _min_socket;
-		if (lsid < sid) {		/* new range */
+		if (lsid < sid) {
+			/* New range: */
 			grt = &_gr_table[indx];
 			grt->base = lindx;
 			grt->nasid = gre->nasid;
@@ -369,27 +389,32 @@ static __init void build_uv_gr_table(void)
 			lindx = indx++;
 			continue;
 		}
-		if (lsid == sid && !ram_limit) {	/* update range */
-			if (grt->limit == last_limit) {	/* .. if contiguous */
+		/* Update range: */
+		if (lsid == sid && !ram_limit) {
+			/* .. if contiguous: */
+			if (grt->limit == last_limit) {
 				grt->limit = last_limit = gre->limit;
 				continue;
 			}
 		}
-		if (!ram_limit) {		/* non-contiguous ram range */
+		/* Non-contiguous RAM range: */
+		if (!ram_limit) {
 			grt++;
 			grt->base = lindx;
 			grt->nasid = gre->nasid;
 			grt->limit = last_limit = gre->limit;
 			continue;
 		}
-		grt++;				/* non-contiguous/non-ram */
-		grt->base = grt - _gr_table;	/* base is this entry */
+		/* Non-contiguous/non-RAM: */
+		grt++;
+		/* base is this entry */
+		grt->base = grt - _gr_table;
 		grt->nasid = gre->nasid;
 		grt->limit = last_limit = gre->limit;
 		lsid++;
 	}
 
-	/* shorten table if possible */
+	/* Shorten table if possible */
 	grt++;
 	i = grt - _gr_table;
 	if (i < _gr_table_len) {
@@ -403,16 +428,15 @@ static __init void build_uv_gr_table(void)
 		}
 	}
 
-	/* display resultant gam range table */
+	/* Display resultant GAM range table: */
 	for (i = 0, grt = _gr_table; i < _gr_table_len; i++, grt++) {
+		unsigned long start, end;
 		int gb = grt->base;
-		unsigned long start = gb < 0 ?  0 :
-			(unsigned long)_gr_table[gb].limit << UV_GAM_RANGE_SHFT;
-		unsigned long end =
-			(unsigned long)grt->limit << UV_GAM_RANGE_SHFT;
 
-		pr_info("UV: GAM Range %2d %04x 0x%013lx-0x%013lx (%d)\n",
-			i, grt->nasid, start, end, gb);
+		start = gb < 0 ?  0 : (unsigned long)_gr_table[gb].limit << UV_GAM_RANGE_SHFT;
+		end = (unsigned long)grt->limit << UV_GAM_RANGE_SHFT;
+
+		pr_info("UV: GAM Range %2d %04x 0x%013lx-0x%013lx (%d)\n", i, grt->nasid, start, end, gb);
 	}
 }
 
@@ -423,16 +447,19 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 
 	pnode = uv_apicid_to_pnode(phys_apicid);
 	phys_apicid |= uv_apicid_hibits;
+
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	    (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
 	    ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
 	    APIC_DM_INIT;
+
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	    (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
 	    ((start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
 	    APIC_DM_STARTUP;
+
 	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 
 	return 0;
@@ -566,7 +593,7 @@ static struct apic apic_x2apic_uv_x __ro_after_init = {
 	.apic_id_registered		= uv_apic_id_registered,
 
 	.irq_delivery_mode		= dest_Fixed,
-	.irq_dest_mode			= 0, /* physical */
+	.irq_dest_mode			= 0, /* Physical */
 
 	.target_cpus			= online_target_cpus,
 	.disable_esr			= 0,
@@ -627,23 +654,22 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 		switch (i) {
 		case 0:
 			m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR;
-			m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR;
+			m_overlay  = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR;
 			break;
 		case 1:
 			m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR;
-			m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR;
+			m_overlay  = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR;
 			break;
 		case 2:
 			m_redirect = UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR;
-			m_overlay = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR;
+			m_overlay  = UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR;
 			break;
 		}
 		alias.v = uv_read_local_mmr(m_overlay);
 		if (alias.s.enable && alias.s.base == 0) {
 			*size = (1UL << alias.s.m_alias);
 			redirect.v = uv_read_local_mmr(m_redirect);
-			*base = (unsigned long)redirect.s.dest_base
-							<< DEST_SHIFT;
+			*base = (unsigned long)redirect.s.dest_base << DEST_SHIFT;
 			return;
 		}
 	}
@@ -652,8 +678,7 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 
 enum map_type {map_wb, map_uc};
 
-static __init void map_high(char *id, unsigned long base, int pshift,
-			int bshift, int max_pnode, enum map_type map_type)
+static __init void map_high(char *id, unsigned long base, int pshift, int bshift, int max_pnode, enum map_type map_type)
 {
 	unsigned long bytes, paddr;
 
@@ -678,16 +703,19 @@ static __init void map_gru_distributed(unsigned long c)
 	int nid;
 
 	gru.v = c;
-	/* only base bits 42:28 relevant in dist mode */
+
+	/* Only base bits 42:28 relevant in dist mode */
 	gru_dist_base = gru.v & 0x000007fff0000000UL;
 	if (!gru_dist_base) {
 		pr_info("UV: Map GRU_DIST base address NULL\n");
 		return;
 	}
+
 	bytes = 1UL << UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT;
 	gru_dist_lmask = ((1UL << uv_hub_info->m_val) - 1) & ~(bytes - 1);
 	gru_dist_umask = ~((1UL << uv_hub_info->m_val) - 1);
 	gru_dist_base &= gru_dist_lmask; /* Clear bits above M */
+
 	for_each_online_node(nid) {
 		paddr = ((u64)uv_node_to_pnode(nid) << uv_hub_info->m_val) |
 				gru_dist_base;
@@ -695,11 +723,12 @@ static __init void map_gru_distributed(unsigned long c)
 		gru_first_node_paddr = min(paddr, gru_first_node_paddr);
 		gru_last_node_paddr = max(paddr, gru_last_node_paddr);
 	}
+
 	/* Save upper (63:M) bits of address only for is_GRU_range */
 	gru_first_node_paddr &= gru_dist_umask;
 	gru_last_node_paddr &= gru_dist_umask;
-	pr_debug("UV: Map GRU_DIST base 0x%016llx  0x%016llx - 0x%016llx\n",
-		gru_dist_base, gru_first_node_paddr, gru_last_node_paddr);
+
+	pr_debug("UV: Map GRU_DIST base 0x%016llx  0x%016llx - 0x%016llx\n", gru_dist_base, gru_first_node_paddr, gru_last_node_paddr);
 }
 
 static __init void map_gru_high(int max_pnode)
@@ -719,6 +748,7 @@ static __init void map_gru_high(int max_pnode)
 		map_gru_distributed(gru.v);
 		return;
 	}
+
 	base = (gru.v & mask) >> shift;
 	map_high("GRU", base, shift, shift, max_pnode, map_wb);
 	gru_start_paddr = ((u64)base << shift);
@@ -772,8 +802,8 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
 
 	id = mmiohs[index].id;
 	overlay.v = uv_read_local_mmr(mmiohs[index].overlay);
-	pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n",
-		id, overlay.v, overlay.s3.base, overlay.s3.m_io);
+
+	pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", id, overlay.v, overlay.s3.base, overlay.s3.m_io);
 	if (!overlay.s3.enable) {
 		pr_info("UV: %s disabled\n", id);
 		return;
@@ -784,7 +814,8 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
 	m_io = overlay.s3.m_io;
 	mmr = mmiohs[index].redirect;
 	n = UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH;
-	min_pnode *= 2;				/* convert to NASID */
+	/* Convert to NASID: */
+	min_pnode *= 2;
 	max_pnode *= 2;
 	max_io = lnasid = fi = li = -1;
 
@@ -793,16 +824,18 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
 
 		redirect.v = uv_read_local_mmr(mmr + i * 8);
 		nasid = redirect.s3.nasid;
+		/* Invalid NASID: */
 		if (nasid < min_pnode || max_pnode < nasid)
-			nasid = -1;		/* invalid NASID */
+			nasid = -1;
 
 		if (nasid == lnasid) {
 			li = i;
-			if (i != n-1)		/* last entry check */
+			/* Last entry check: */
+			if (i != n-1)
 				continue;
 		}
 
-		/* check if we have a cached (or last) redirect to print */
+		/* Check if we have a cached (or last) redirect to print: */
 		if (lnasid != -1 || (i == n-1 && nasid != -1))  {
 			unsigned long addr1, addr2;
 			int f, l;
@@ -814,12 +847,9 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
 				f = fi;
 				l = li;
 			}
-			addr1 = (base << shift) +
-				f * (1ULL << m_io);
-			addr2 = (base << shift) +
-				(l + 1) * (1ULL << m_io);
-			pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n",
-				id, fi, li, lnasid, addr1, addr2);
+			addr1 = (base << shift) + f * (1ULL << m_io);
+			addr2 = (base << shift) + (l + 1) * (1ULL << m_io);
+			pr_info("UV: %s[%03d..%03d] NASID 0x%04x ADDR 0x%016lx - 0x%016lx\n", id, fi, li, lnasid, addr1, addr2);
 			if (max_io < l)
 				max_io = l;
 		}
@@ -827,8 +857,7 @@ static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
 		lnasid = nasid;
 	}
 
-	pr_info("UV: %s base:0x%lx shift:%d M_IO:%d MAX_IO:%d\n",
-		id, base, shift, m_io, max_io);
+	pr_info("UV: %s base:0x%lx shift:%d M_IO:%d MAX_IO:%d\n", id, base, shift, m_io, max_io);
 
 	if (max_io >= 0)
 		map_high(id, base, shift, m_io, max_io, map_uc);
@@ -841,36 +870,35 @@ static __init void map_mmioh_high(int min_pnode, int max_pnode)
 	int shift, enable, m_io, n_io;
 
 	if (is_uv3_hub() || is_uv4_hub()) {
-		/* Map both MMIOH Regions */
+		/* Map both MMIOH regions: */
 		map_mmioh_high_uv3(0, min_pnode, max_pnode);
 		map_mmioh_high_uv3(1, min_pnode, max_pnode);
 		return;
 	}
 
 	if (is_uv1_hub()) {
-		mmr = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR;
-		shift = UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
-		mmioh.v = uv_read_local_mmr(mmr);
-		enable = !!mmioh.s1.enable;
-		base = mmioh.s1.base;
-		m_io = mmioh.s1.m_io;
-		n_io = mmioh.s1.n_io;
+		mmr	= UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR;
+		shift	= UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+		mmioh.v	= uv_read_local_mmr(mmr);
+		enable	= !!mmioh.s1.enable;
+		base	= mmioh.s1.base;
+		m_io	= mmioh.s1.m_io;
+		n_io	= mmioh.s1.n_io;
 	} else if (is_uv2_hub()) {
-		mmr = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR;
-		shift = UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
-		mmioh.v = uv_read_local_mmr(mmr);
-		enable = !!mmioh.s2.enable;
-		base = mmioh.s2.base;
-		m_io = mmioh.s2.m_io;
-		n_io = mmioh.s2.n_io;
-	} else
+		mmr	= UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR;
+		shift	= UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT;
+		mmioh.v	= uv_read_local_mmr(mmr);
+		enable	= !!mmioh.s2.enable;
+		base	= mmioh.s2.base;
+		m_io	= mmioh.s2.m_io;
+		n_io	= mmioh.s2.n_io;
+	} else {
 		return;
+	}
 
 	if (enable) {
 		max_pnode &= (1 << n_io) - 1;
-		pr_info(
-		    "UV: base:0x%lx shift:%d N_IO:%d M_IO:%d max_pnode:0x%x\n",
-			base, shift, m_io, n_io, max_pnode);
+		pr_info("UV: base:0x%lx shift:%d N_IO:%d M_IO:%d max_pnode:0x%x\n", base, shift, m_io, n_io, max_pnode);
 		map_high("MMIOH", base, shift, m_io, max_pnode, map_uc);
 	} else {
 		pr_info("UV: MMIOH disabled\n");
@@ -888,16 +916,16 @@ static __init void uv_rtc_init(void)
 	long status;
 	u64 ticks_per_sec;
 
-	status = uv_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK,
-					&ticks_per_sec);
+	status = uv_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK, &ticks_per_sec);
+
 	if (status != BIOS_STATUS_SUCCESS || ticks_per_sec < 100000) {
-		printk(KERN_WARNING
-			"unable to determine platform RTC clock frequency, "
-			"guessing.\n");
-		/* BIOS gives wrong value for clock freq. so guess */
+		pr_warn("UV: unable to determine platform RTC clock frequency, guessing.\n");
+
+		/* BIOS gives wrong value for clock frequency, so guess: */
 		sn_rtc_cycles_per_second = 1000000000000UL / 30000UL;
-	} else
+	} else {
 		sn_rtc_cycles_per_second = ticks_per_sec;
+	}
 }
 
 /*
@@ -908,19 +936,19 @@ static void uv_heartbeat(unsigned long ignored)
 	struct timer_list *timer = &uv_scir_info->timer;
 	unsigned char bits = uv_scir_info->state;
 
-	/* flip heartbeat bit */
+	/* Flip heartbeat bit: */
 	bits ^= SCIR_CPU_HEARTBEAT;
 
-	/* is this cpu idle? */
+	/* Is this CPU idle? */
 	if (idle_cpu(raw_smp_processor_id()))
 		bits &= ~SCIR_CPU_ACTIVITY;
 	else
 		bits |= SCIR_CPU_ACTIVITY;
 
-	/* update system controller interface reg */
+	/* Update system controller interface reg: */
 	uv_set_scir_bits(bits);
 
-	/* enable next timer period */
+	/* Enable next timer period: */
 	mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL);
 }
 
@@ -935,7 +963,7 @@ static int uv_heartbeat_enable(unsigned int cpu)
 		add_timer_on(timer, cpu);
 		uv_cpu_scir_info(cpu)->enabled = 1;
 
-		/* also ensure that boot cpu is enabled */
+		/* Also ensure that boot CPU is enabled: */
 		cpu = 0;
 	}
 	return 0;
@@ -968,9 +996,11 @@ static __init int uv_init_heartbeat(void)
 {
 	int cpu;
 
-	if (is_uv_system())
+	if (is_uv_system()) {
 		for_each_online_cpu(cpu)
 			uv_heartbeat_enable(cpu);
+	}
+
 	return 0;
 }
 
@@ -979,14 +1009,10 @@ late_initcall(uv_init_heartbeat);
 #endif /* !CONFIG_HOTPLUG_CPU */
 
 /* Direct Legacy VGA I/O traffic to designated IOH */
-int uv_set_vga_state(struct pci_dev *pdev, bool decode,
-		      unsigned int command_bits, u32 flags)
+int uv_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags)
 {
 	int domain, bus, rc;
 
-	PR_DEVEL("devfn %x decode %d cmd %x flags %d\n",
-			pdev->devfn, decode, command_bits, flags);
-
 	if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE))
 		return 0;
 
@@ -997,13 +1023,12 @@ int uv_set_vga_state(struct pci_dev *pdev, bool decode,
 	bus = pdev->bus->number;
 
 	rc = uv_bios_set_legacy_vga_target(decode, domain, bus);
-	PR_DEVEL("vga decode %d %x:%x, rc: %d\n", decode, domain, bus, rc);
 
 	return rc;
 }
 
 /*
- * Called on each cpu to initialize the per_cpu UV data area.
+ * Called on each CPU to initialize the per_cpu UV data area.
  * FIXME: hotplug not supported yet
  */
 void uv_cpu_init(void)
@@ -1030,90 +1055,79 @@ static void get_mn(struct mn *mnp)
 	union uvh_rh_gam_config_mmr_u m_n_config;
 	union uv3h_gr0_gam_gr_config_u m_gr_config;
 
-	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR);
-	mnp->n_val = m_n_config.s.n_skt;
+	/* Make sure the whole structure is well initialized: */
+	memset(mnp, 0, sizeof(*mnp));
+
+	m_n_config.v	= uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR);
+	mnp->n_val	= m_n_config.s.n_skt;
+
 	if (is_uv4_hub()) {
-		mnp->m_val = 0;
-		mnp->n_lshift = 0;
+		mnp->m_val	= 0;
+		mnp->n_lshift	= 0;
 	} else if (is_uv3_hub()) {
-		mnp->m_val = m_n_config.s3.m_skt;
-		m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG);
-		mnp->n_lshift = m_gr_config.s3.m_skt;
+		mnp->m_val	= m_n_config.s3.m_skt;
+		m_gr_config.v	= uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG);
+		mnp->n_lshift	= m_gr_config.s3.m_skt;
 	} else if (is_uv2_hub()) {
-		mnp->m_val = m_n_config.s2.m_skt;
-		mnp->n_lshift = mnp->m_val == 40 ? 40 : 39;
+		mnp->m_val	= m_n_config.s2.m_skt;
+		mnp->n_lshift	= mnp->m_val == 40 ? 40 : 39;
 	} else if (is_uv1_hub()) {
-		mnp->m_val = m_n_config.s1.m_skt;
-		mnp->n_lshift = mnp->m_val;
+		mnp->m_val	= m_n_config.s1.m_skt;
+		mnp->n_lshift	= mnp->m_val;
 	}
 	mnp->m_shift = mnp->m_val ? 64 - mnp->m_val : 0;
 }
 
-void __init uv_init_hub_info(struct uv_hub_info_s *hub_info)
+void __init uv_init_hub_info(struct uv_hub_info_s *hi)
 {
-	struct mn mn = {0};	/* avoid unitialized warnings */
 	union uvh_node_id_u node_id;
+	struct mn mn;
 
 	get_mn(&mn);
-	hub_info->m_val = mn.m_val;
-	hub_info->n_val = mn.n_val;
-	hub_info->m_shift = mn.m_shift;
-	hub_info->n_lshift = mn.n_lshift ? mn.n_lshift : 0;
-
-	hub_info->hub_revision = uv_hub_info->hub_revision;
-	hub_info->pnode_mask = uv_cpuid.pnode_mask;
-	hub_info->min_pnode = _min_pnode;
-	hub_info->min_socket = _min_socket;
-	hub_info->pnode_to_socket = _pnode_to_socket;
-	hub_info->socket_to_node = _socket_to_node;
-	hub_info->socket_to_pnode = _socket_to_pnode;
-	hub_info->gr_table_len = _gr_table_len;
-	hub_info->gr_table = _gr_table;
-	hub_info->gpa_mask = mn.m_val ?
+	hi->gpa_mask = mn.m_val ?
 		(1UL << (mn.m_val + mn.n_val)) - 1 :
 		(1UL << uv_cpuid.gpa_shift) - 1;
 
-	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
-	hub_info->gnode_extra =
-		(node_id.s.node_id & ~((1 << mn.n_val) - 1)) >> 1;
-
-	hub_info->gnode_upper =
-		((unsigned long)hub_info->gnode_extra << mn.m_val);
+	hi->m_val		= mn.m_val;
+	hi->n_val		= mn.n_val;
+	hi->m_shift		= mn.m_shift;
+	hi->n_lshift		= mn.n_lshift ? mn.n_lshift : 0;
+	hi->hub_revision	= uv_hub_info->hub_revision;
+	hi->pnode_mask		= uv_cpuid.pnode_mask;
+	hi->min_pnode		= _min_pnode;
+	hi->min_socket		= _min_socket;
+	hi->pnode_to_socket	= _pnode_to_socket;
+	hi->socket_to_node	= _socket_to_node;
+	hi->socket_to_pnode	= _socket_to_pnode;
+	hi->gr_table_len	= _gr_table_len;
+	hi->gr_table		= _gr_table;
+
+	node_id.v		= uv_read_local_mmr(UVH_NODE_ID);
+	uv_cpuid.gnode_shift	= max_t(unsigned int, uv_cpuid.gnode_shift, mn.n_val);
+	hi->gnode_extra		= (node_id.s.node_id & ~((1 << uv_cpuid.gnode_shift) - 1)) >> 1;
+	hi->gnode_upper		= (unsigned long)hi->gnode_extra << mn.m_val;
 
 	if (uv_gp_table) {
-		hub_info->global_mmr_base = uv_gp_table->mmr_base;
-		hub_info->global_mmr_shift = uv_gp_table->mmr_shift;
-		hub_info->global_gru_base = uv_gp_table->gru_base;
-		hub_info->global_gru_shift = uv_gp_table->gru_shift;
-		hub_info->gpa_shift = uv_gp_table->gpa_shift;
-		hub_info->gpa_mask = (1UL << hub_info->gpa_shift) - 1;
+		hi->global_mmr_base	= uv_gp_table->mmr_base;
+		hi->global_mmr_shift	= uv_gp_table->mmr_shift;
+		hi->global_gru_base	= uv_gp_table->gru_base;
+		hi->global_gru_shift	= uv_gp_table->gru_shift;
+		hi->gpa_shift		= uv_gp_table->gpa_shift;
+		hi->gpa_mask		= (1UL << hi->gpa_shift) - 1;
 	} else {
-		hub_info->global_mmr_base =
-			uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
-					~UV_MMR_ENABLE;
-		hub_info->global_mmr_shift = _UV_GLOBAL_MMR64_PNODE_SHIFT;
+		hi->global_mmr_base	= uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE;
+		hi->global_mmr_shift	= _UV_GLOBAL_MMR64_PNODE_SHIFT;
 	}
 
-	get_lowmem_redirect(
-		&hub_info->lowmem_remap_base, &hub_info->lowmem_remap_top);
-
-	hub_info->apic_pnode_shift = uv_cpuid.socketid_shift;
-
-	/* show system specific info */
-	pr_info("UV: N:%d M:%d m_shift:%d n_lshift:%d\n",
-		hub_info->n_val, hub_info->m_val,
-		hub_info->m_shift, hub_info->n_lshift);
-
-	pr_info("UV: gpa_mask/shift:0x%lx/%d pnode_mask:0x%x apic_pns:%d\n",
-		hub_info->gpa_mask, hub_info->gpa_shift,
-		hub_info->pnode_mask, hub_info->apic_pnode_shift);
+	get_lowmem_redirect(&hi->lowmem_remap_base, &hi->lowmem_remap_top);
 
-	pr_info("UV: mmr_base/shift:0x%lx/%ld gru_base/shift:0x%lx/%ld\n",
-		hub_info->global_mmr_base, hub_info->global_mmr_shift,
-		hub_info->global_gru_base, hub_info->global_gru_shift);
+	hi->apic_pnode_shift = uv_cpuid.socketid_shift;
 
-	pr_info("UV: gnode_upper:0x%lx gnode_extra:0x%x\n",
-		hub_info->gnode_upper, hub_info->gnode_extra);
+	/* Show system specific info: */
+	pr_info("UV: N:%d M:%d m_shift:%d n_lshift:%d\n", hi->n_val, hi->m_val, hi->m_shift, hi->n_lshift);
+	pr_info("UV: gpa_mask/shift:0x%lx/%d pnode_mask:0x%x apic_pns:%d\n", hi->gpa_mask, hi->gpa_shift, hi->pnode_mask, hi->apic_pnode_shift);
+	pr_info("UV: mmr_base/shift:0x%lx/%ld gru_base/shift:0x%lx/%ld\n", hi->global_mmr_base, hi->global_mmr_shift, hi->global_gru_base, hi->global_gru_shift);
+	pr_info("UV: gnode_upper:0x%lx gnode_extra:0x%x\n", hi->gnode_upper, hi->gnode_extra);
 }
 
 static void __init decode_gam_params(unsigned long ptr)
@@ -1139,12 +1153,9 @@ static void __init decode_gam_rng_tbl(unsigned long ptr)
 	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
 		if (!index) {
 			pr_info("UV: GAM Range Table...\n");
-			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s\n",
-				"Range", "", "Size", "Type", "NASID",
-				"SID", "PN");
+			pr_info("UV:  # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", "SID", "PN");
 		}
-		pr_info(
-		"UV: %2d: 0x%014lx-0x%014lx %5luG %3d   %04x  %02x %02x\n",
+		pr_info("UV: %2d: 0x%014lx-0x%014lx %5luG %3d   %04x  %02x %02x\n",
 			index++,
 			(unsigned long)lgre << UV_GAM_RANGE_SHFT,
 			(unsigned long)gre->limit << UV_GAM_RANGE_SHFT,
@@ -1162,29 +1173,32 @@ static void __init decode_gam_rng_tbl(unsigned long ptr)
 		if (pnode_max < gre->pnode)
 			pnode_max = gre->pnode;
 	}
-	_min_socket = sock_min;
-	_max_socket = sock_max;
-	_min_pnode = pnode_min;
-	_max_pnode = pnode_max;
-	_gr_table_len = index;
-	pr_info(
-	"UV: GRT: %d entries, sockets(min:%x,max:%x) pnodes(min:%x,max:%x)\n",
-		index, _min_socket, _max_socket, _min_pnode, _max_pnode);
+	_min_socket	= sock_min;
+	_max_socket	= sock_max;
+	_min_pnode	= pnode_min;
+	_max_pnode	= pnode_max;
+	_gr_table_len	= index;
+
+	pr_info("UV: GRT: %d entries, sockets(min:%x,max:%x) pnodes(min:%x,max:%x)\n", index, _min_socket, _max_socket, _min_pnode, _max_pnode);
 }
 
-static void __init decode_uv_systab(void)
+static int __init decode_uv_systab(void)
 {
 	struct uv_systab *st;
 	int i;
 
+	if (uv_hub_info->hub_revision < UV4_HUB_REVISION_BASE)
+		return 0;	/* No extended UVsystab required */
+
 	st = uv_systab;
-	if ((!st || st->revision < UV_SYSTAB_VERSION_UV4) && !is_uv4_hub())
-		return;
-	if (st->revision != UV_SYSTAB_VERSION_UV4_LATEST) {
-		pr_crit(
-		"UV: BIOS UVsystab version(%x) mismatch, expecting(%x)\n",
-			st->revision, UV_SYSTAB_VERSION_UV4_LATEST);
-		BUG();
+	if ((!st) || (st->revision < UV_SYSTAB_VERSION_UV4_LATEST)) {
+		int rev = st ? st->revision : 0;
+
+		pr_err("UV: BIOS UVsystab version(%x) mismatch, expecting(%x)\n", rev, UV_SYSTAB_VERSION_UV4_LATEST);
+		pr_err("UV: Cannot support UV operations, switching to generic PC\n");
+		uv_system_type = UV_NONE;
+
+		return -EINVAL;
 	}
 
 	for (i = 0; st->entry[i].type != UV_SYSTAB_TYPE_UNUSED; i++) {
@@ -1205,10 +1219,11 @@ static void __init decode_uv_systab(void)
 			break;
 		}
 	}
+	return 0;
 }
 
 /*
- * Setup physical blade translations from UVH_NODE_PRESENT_TABLE
+ * Set up physical blade translations from UVH_NODE_PRESENT_TABLE
  * .. NB: UVH_NODE_PRESENT_TABLE is going away,
  * .. being replaced by GAM Range Table
  */
@@ -1244,14 +1259,13 @@ static void __init build_socket_tables(void)
 	if (!gre) {
 		if (is_uv1_hub() || is_uv2_hub() || is_uv3_hub()) {
 			pr_info("UV: No UVsystab socket table, ignoring\n");
-			return;		/* not required */
+			return;
 		}
-		pr_crit(
-		"UV: Error: UVsystab address translations not available!\n");
+		pr_crit("UV: Error: UVsystab address translations not available!\n");
 		BUG();
 	}
 
-	/* build socket id -> node id, pnode */
+	/* Build socket id -> node id, pnode */
 	num = maxsock - minsock + 1;
 	bytes = num * sizeof(_socket_to_node[0]);
 	_socket_to_node = kmalloc(bytes, GFP_KERNEL);
@@ -1268,27 +1282,27 @@ static void __init build_socket_tables(void)
 	for (i = 0; i < nump; i++)
 		_pnode_to_socket[i] = SOCK_EMPTY;
 
-	/* fill in pnode/node/addr conversion list values */
+	/* Fill in pnode/node/addr conversion list values: */
 	pr_info("UV: GAM Building socket/pnode conversion tables\n");
 	for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) {
 		if (gre->type == UV_GAM_RANGE_TYPE_HOLE)
 			continue;
 		i = gre->sockid - minsock;
+		/* Duplicate: */
 		if (_socket_to_pnode[i] != SOCK_EMPTY)
-			continue;	/* duplicate */
+			continue;
 		_socket_to_pnode[i] = gre->pnode;
 
 		i = gre->pnode - minpnode;
 		_pnode_to_socket[i] = gre->sockid;
 
-		pr_info(
-		"UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n",
+		pr_info("UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n",
 			gre->sockid, gre->type, gre->nasid,
 			_socket_to_pnode[gre->sockid - minsock],
 			_pnode_to_socket[gre->pnode - minpnode]);
 	}
 
-	/* Set socket -> node values */
+	/* Set socket -> node values: */
 	lnid = -1;
 	for_each_present_cpu(cpu) {
 		int nid = cpu_to_node(cpu);
@@ -1304,7 +1318,7 @@ static void __init build_socket_tables(void)
 			sockid, apicid, nid);
 	}
 
-	/* Setup physical blade to pnode translation from GAM Range Table */
+	/* Set up physical blade to pnode translation from GAM Range Table: */
 	bytes = num_possible_nodes() * sizeof(_node_to_pnode[0]);
 	_node_to_pnode = kmalloc(bytes, GFP_KERNEL);
 	BUG_ON(!_node_to_pnode);
@@ -1314,8 +1328,7 @@ static void __init build_socket_tables(void)
 
 		for (sockid = minsock; sockid <= maxsock; sockid++) {
 			if (lnid == _socket_to_node[sockid - minsock]) {
-				_node_to_pnode[lnid] =
-					_socket_to_pnode[sockid - minsock];
+				_node_to_pnode[lnid] = _socket_to_pnode[sockid - minsock];
 				break;
 			}
 		}
@@ -1332,8 +1345,7 @@ static void __init build_socket_tables(void)
 	pr_info("UV: Checking socket->node/pnode for identity maps\n");
 	if (minsock == 0) {
 		for (i = 0; i < num; i++)
-			if (_socket_to_node[i] == SOCK_EMPTY ||
-				i != _socket_to_node[i])
+			if (_socket_to_node[i] == SOCK_EMPTY || i != _socket_to_node[i])
 				break;
 		if (i >= num) {
 			kfree(_socket_to_node);
@@ -1354,7 +1366,7 @@ static void __init build_socket_tables(void)
 	}
 }
 
-void __init uv_system_init(void)
+static void __init uv_system_init_hub(void)
 {
 	struct uv_hub_info_s hub_info = {0};
 	int bytes, cpu, nodeid;
@@ -1372,8 +1384,13 @@ void __init uv_system_init(void)
 
 	map_low_mmrs();
 
-	uv_bios_init();			/* get uv_systab for decoding */
-	decode_uv_systab();
+	/* Get uv_systab for decoding: */
+	uv_bios_init();
+
+	/* If there's an UVsystab problem then abort UV init: */
+	if (decode_uv_systab() < 0)
+		return;
+
 	build_socket_tables();
 	build_uv_gr_table();
 	uv_init_hub_info(&hub_info);
@@ -1381,14 +1398,10 @@ void __init uv_system_init(void)
 	if (!_node_to_pnode)
 		boot_init_possible_blades(&hub_info);
 
-	/* uv_num_possible_blades() is really the hub count */
-	pr_info("UV: Found %d hubs, %d nodes, %d cpus\n",
-			uv_num_possible_blades(),
-			num_possible_nodes(),
-			num_possible_cpus());
+	/* uv_num_possible_blades() is really the hub count: */
+	pr_info("UV: Found %d hubs, %d nodes, %d CPUs\n", uv_num_possible_blades(), num_possible_nodes(), num_possible_cpus());
 
-	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id, &sn_coherency_id,
-			    &sn_region_size, &system_serial_number);
+	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id, &sn_coherency_id, &sn_region_size, &system_serial_number);
 	hub_info.coherency_domain_number = sn_coherency_id;
 	uv_rtc_init();
 
@@ -1401,33 +1414,31 @@ void __init uv_system_init(void)
 		struct uv_hub_info_s *new_hub;
 
 		if (__uv_hub_info_list[nodeid]) {
-			pr_err("UV: Node %d UV HUB already initialized!?\n",
-				nodeid);
+			pr_err("UV: Node %d UV HUB already initialized!?\n", nodeid);
 			BUG();
 		}
 
 		/* Allocate new per hub info list */
-		new_hub = (nodeid == 0) ?
-			&uv_hub_info_node0 :
-			kzalloc_node(bytes, GFP_KERNEL, nodeid);
+		new_hub = (nodeid == 0) ?  &uv_hub_info_node0 : kzalloc_node(bytes, GFP_KERNEL, nodeid);
 		BUG_ON(!new_hub);
 		__uv_hub_info_list[nodeid] = new_hub;
 		new_hub = uv_hub_info_list(nodeid);
 		BUG_ON(!new_hub);
 		*new_hub = hub_info;
 
-		/* Use information from GAM table if available */
+		/* Use information from GAM table if available: */
 		if (_node_to_pnode)
 			new_hub->pnode = _node_to_pnode[nodeid];
-		else	/* Fill in during cpu loop */
+		else /* Or fill in during CPU loop: */
 			new_hub->pnode = 0xffff;
+
 		new_hub->numa_blade_id = uv_node_to_blade_id(nodeid);
 		new_hub->memory_nid = -1;
 		new_hub->nr_possible_cpus = 0;
 		new_hub->nr_online_cpus = 0;
 	}
 
-	/* Initialize per cpu info */
+	/* Initialize per CPU info: */
 	for_each_possible_cpu(cpu) {
 		int apicid = per_cpu(x86_cpu_to_apicid, cpu);
 		int numa_node_id;
@@ -1438,22 +1449,24 @@ void __init uv_system_init(void)
 		pnode = uv_apicid_to_pnode(apicid);
 
 		uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid);
-		uv_cpu_info_per(cpu)->blade_cpu_id =
-			uv_cpu_hub_info(cpu)->nr_possible_cpus++;
+		uv_cpu_info_per(cpu)->blade_cpu_id = uv_cpu_hub_info(cpu)->nr_possible_cpus++;
 		if (uv_cpu_hub_info(cpu)->memory_nid == -1)
 			uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu);
-		if (nodeid != numa_node_id &&	/* init memoryless node */
+
+		/* Init memoryless node: */
+		if (nodeid != numa_node_id &&
 		    uv_hub_info_list(numa_node_id)->pnode == 0xffff)
 			uv_hub_info_list(numa_node_id)->pnode = pnode;
 		else if (uv_cpu_hub_info(cpu)->pnode == 0xffff)
 			uv_cpu_hub_info(cpu)->pnode = pnode;
+
 		uv_cpu_scir_info(cpu)->offset = uv_scir_offset(apicid);
 	}
 
 	for_each_node(nodeid) {
 		unsigned short pnode = uv_hub_info_list(nodeid)->pnode;
 
-		/* Add pnode info for pre-GAM list nodes without cpus */
+		/* Add pnode info for pre-GAM list nodes without CPUs: */
 		if (pnode == 0xffff) {
 			unsigned long paddr;
 
@@ -1479,15 +1492,30 @@ void __init uv_system_init(void)
 	uv_scir_register_cpu_notifier();
 	proc_mkdir("sgi_uv", NULL);
 
-	/* register Legacy VGA I/O redirection handler */
+	/* Register Legacy VGA I/O redirection handler: */
 	pci_register_set_vga_state(uv_set_vga_state);
 
 	/*
 	 * For a kdump kernel the reset must be BOOT_ACPI, not BOOT_EFI, as
-	 * EFI is not enabled in the kdump kernel.
+	 * EFI is not enabled in the kdump kernel:
 	 */
 	if (is_kdump_kernel())
 		reboot_type = BOOT_ACPI;
 }
 
+/*
+ * There is a small amount of UV specific code needed to initialize a
+ * UV system that does not have a "UV HUB" (referred to as "hubless").
+ */
+void __init uv_system_init(void)
+{
+	if (likely(!is_uv_system() && !is_uv_hubless()))
+		return;
+
+	if (is_uv_system())
+		uv_system_init_hub();
+	else
+		uv_nmi_setup_hubless();
+}
+
 apic_driver(apic_x2apic_uv_x);
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 45d44c173cf9..4a7080c84a5a 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -905,8 +905,8 @@ static int apm_cpu_idle(struct cpuidle_device *dev,
 {
 	static int use_apm_idle; /* = 0 */
 	static unsigned int last_jiffies; /* = 0 */
-	static unsigned int last_stime; /* = 0 */
-	cputime_t stime, utime;
+	static u64 last_stime; /* = 0 */
+	u64 stime, utime;
 
 	int apm_idle_done = 0;
 	unsigned int jiffies_since_last_check = jiffies - last_jiffies;
@@ -919,7 +919,7 @@ recalc:
 	} else if (jiffies_since_last_check > idle_period) {
 		unsigned int idle_percentage;
 
-		idle_percentage = cputime_to_jiffies(stime - last_stime);
+		idle_percentage = nsecs_to_jiffies(stime - last_stime);
 		idle_percentage *= 100;
 		idle_percentage /= jiffies_since_last_check;
 		use_apm_idle = (idle_percentage > idle_threshold);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index c62e015b126c..de827d6ac8c2 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -81,6 +81,7 @@ void common(void) {
 
 	BLANK();
 	OFFSET(BP_scratch, boot_params, scratch);
+	OFFSET(BP_secure_boot, boot_params, secure_boot);
 	OFFSET(BP_loadflags, boot_params, hdr.loadflags);
 	OFFSET(BP_hardware_subarch, boot_params, hdr.hardware_subarch);
 	OFFSET(BP_version, boot_params, hdr.version);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1d3167269a67..4e95b2e0d95f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -309,8 +309,22 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 	/* get information required for multi-node processors */
 	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		u32 eax, ebx, ecx, edx;
 
-		node_id = cpuid_ecx(0x8000001e) & 7;
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+
+		node_id  = ecx & 0xff;
+		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
+
+		if (c->x86 == 0x15)
+			c->cu_id = ebx & 0xff;
+
+		if (c->x86 >= 0x17) {
+			c->cpu_core_id = ebx & 0xff;
+
+			if (smp_num_siblings > 1)
+				c->x86_max_cores /= smp_num_siblings;
+		}
 
 		/*
 		 * We may have multiple LLCs if L3 caches exist, so check if we
@@ -541,8 +555,10 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		if (!check_tsc_unstable())
-			set_sched_clock_stable();
+		if (check_tsc_unstable())
+			clear_sched_clock_stable();
+	} else {
+		clear_sched_clock_stable();
 	}
 
 	/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 1661d8ec9280..2c234a6d94c4 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -1,5 +1,5 @@
-#include <linux/bitops.h>
-#include <linux/kernel.h>
+
+#include <linux/sched.h>
 
 #include <asm/cpufeature.h>
 #include <asm/e820.h>
@@ -104,6 +104,8 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 #endif
+
+	clear_sched_clock_stable();
 }
 
 static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9bab7a8a4293..f07005e6f461 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -35,6 +35,7 @@
 #include <asm/desc.h>
 #include <asm/fpu/internal.h>
 #include <asm/mtrr.h>
+#include <asm/hwcap2.h>
 #include <linux/numa.h>
 #include <asm/asm.h>
 #include <asm/bugs.h>
@@ -51,6 +52,8 @@
 
 #include "cpu.h"
 
+u32 elf_hwcap2 __read_mostly;
+
 /* all of these masks are initialized in setup_cpu_local_masks() */
 cpumask_var_t cpu_initialized_mask;
 cpumask_var_t cpu_callout_mask;
@@ -83,6 +86,7 @@ static void default_init(struct cpuinfo_x86 *c)
 			strcpy(c->x86_model_id, "386");
 	}
 #endif
+	clear_sched_clock_stable();
 }
 
 static const struct cpu_dev default_cpu = {
@@ -655,6 +659,16 @@ void cpu_detect(struct cpuinfo_x86 *c)
 	}
 }
 
+static void apply_forced_caps(struct cpuinfo_x86 *c)
+{
+	int i;
+
+	for (i = 0; i < NCAPINTS; i++) {
+		c->x86_capability[i] &= ~cpu_caps_cleared[i];
+		c->x86_capability[i] |= cpu_caps_set[i];
+	}
+}
+
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
@@ -748,6 +762,13 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a);
 
 	init_scattered_cpuid_features(c);
+
+	/*
+	 * Clear/Set all flags overridden by options, after probe.
+	 * This needs to happen each time we re-probe, which may happen
+	 * several times during CPU initialization.
+	 */
+	apply_forced_caps(c);
 }
 
 static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
@@ -801,14 +822,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	memset(&c->x86_capability, 0, sizeof c->x86_capability);
 	c->extended_cpuid_level = 0;
 
-	if (!have_cpuid_p())
-		identify_cpu_without_cpuid(c);
-
 	/* cyrix could have cpuid enabled via c_identify()*/
 	if (have_cpuid_p()) {
 		cpu_detect(c);
 		get_cpu_vendor(c);
 		get_cpu_cap(c);
+		setup_force_cpu_cap(X86_FEATURE_CPUID);
 
 		if (this_cpu->c_early_init)
 			this_cpu->c_early_init(c);
@@ -818,6 +837,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 		if (this_cpu->c_bsp_init)
 			this_cpu->c_bsp_init(c);
+	} else {
+		identify_cpu_without_cpuid(c);
+		setup_clear_cpu_cap(X86_FEATURE_CPUID);
 	}
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
@@ -1015,6 +1037,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	c->x86_model_id[0] = '\0';  /* Unset */
 	c->x86_max_cores = 1;
 	c->x86_coreid_bits = 0;
+	c->cu_id = 0xff;
 #ifdef CONFIG_X86_64
 	c->x86_clflush_size = 64;
 	c->x86_phys_bits = 36;
@@ -1034,10 +1057,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 		this_cpu->c_identify(c);
 
 	/* Clear/Set all flags overridden by options, after probe */
-	for (i = 0; i < NCAPINTS; i++) {
-		c->x86_capability[i] &= ~cpu_caps_cleared[i];
-		c->x86_capability[i] |= cpu_caps_set[i];
-	}
+	apply_forced_caps(c);
 
 #ifdef CONFIG_X86_64
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
@@ -1055,6 +1075,8 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	if (this_cpu->c_init)
 		this_cpu->c_init(c);
+	else
+		clear_sched_clock_stable();
 
 	/* Disable the PN if appropriate */
 	squash_the_stupid_serial_number(c);
@@ -1096,10 +1118,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	 * Clear/Set all flags overridden by options, need do it
 	 * before following smp all cpus cap AND.
 	 */
-	for (i = 0; i < NCAPINTS; i++) {
-		c->x86_capability[i] &= ~cpu_caps_cleared[i];
-		c->x86_capability[i] |= cpu_caps_set[i];
-	}
+	apply_forced_caps(c);
 
 	/*
 	 * On SMP, boot_cpu_data holds the common feature set between
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index bd9dcd6b712d..47416f959a48 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -9,6 +9,7 @@
 #include <asm/pci-direct.h>
 #include <asm/tsc.h>
 #include <asm/cpufeature.h>
+#include <linux/sched.h>
 
 #include "cpu.h"
 
@@ -183,6 +184,7 @@ static void early_init_cyrix(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
 		break;
 	}
+	clear_sched_clock_stable();
 }
 
 static void init_cyrix(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 203f860d2ab3..017ecd3bb553 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -15,6 +15,8 @@
 #include <asm/cpu.h>
 #include <asm/intel-family.h>
 #include <asm/microcode_intel.h>
+#include <asm/hwcap2.h>
+#include <asm/elf.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -62,6 +64,46 @@ void check_mpx_erratum(struct cpuinfo_x86 *c)
 	}
 }
 
+static bool ring3mwait_disabled __read_mostly;
+
+static int __init ring3mwait_disable(char *__unused)
+{
+	ring3mwait_disabled = true;
+	return 0;
+}
+__setup("ring3mwait=disable", ring3mwait_disable);
+
+static void probe_xeon_phi_r3mwait(struct cpuinfo_x86 *c)
+{
+	/*
+	 * Ring 3 MONITOR/MWAIT feature cannot be detected without
+	 * cpu model and family comparison.
+	 */
+	if (c->x86 != 6)
+		return;
+	switch (c->x86_model) {
+	case INTEL_FAM6_XEON_PHI_KNL:
+	case INTEL_FAM6_XEON_PHI_KNM:
+		break;
+	default:
+		return;
+	}
+
+	if (ring3mwait_disabled) {
+		msr_clear_bit(MSR_MISC_FEATURE_ENABLES,
+			      MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
+		return;
+	}
+
+	msr_set_bit(MSR_MISC_FEATURE_ENABLES,
+		    MSR_MISC_FEATURE_ENABLES_RING3MWAIT_BIT);
+
+	set_cpu_cap(c, X86_FEATURE_RING3MWAIT);
+
+	if (c == &boot_cpu_data)
+		ELF_HWCAP2 |= HWCAP2_RING3MWAIT;
+}
+
 static void early_init_intel(struct cpuinfo_x86 *c)
 {
 	u64 misc_enable;
@@ -119,8 +161,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		if (!check_tsc_unstable())
-			set_sched_clock_stable();
+		if (check_tsc_unstable())
+			clear_sched_clock_stable();
+	} else {
+		clear_sched_clock_stable();
 	}
 
 	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
@@ -560,6 +604,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 		detect_vmx_virtcap(c);
 
 	init_intel_energy_perf(c);
+
+	probe_xeon_phi_r3mwait(c);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 83f1a98d37db..2eee85379689 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -52,8 +52,11 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 
 	if (severity >= GHES_SEV_RECOVERABLE)
 		m.status |= MCI_STATUS_UC;
-	if (severity >= GHES_SEV_PANIC)
+
+	if (severity >= GHES_SEV_PANIC) {
 		m.status |= MCI_STATUS_PCC;
+		m.tsc = rdtsc();
+	}
 
 	m.addr = mem_err->physical_addr;
 	mce_log(&m);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 93d824ec3120..1e5a50c11d3c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -72,7 +72,7 @@ struct llist_node *mce_gen_pool_prepare_records(void)
 	return new_head.first;
 }
 
-void mce_gen_pool_process(void)
+void mce_gen_pool_process(struct work_struct *__unused)
 {
 	struct llist_node *head;
 	struct mce_evt_llist *node, *tmp;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 517619ea6498..99165b206df3 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -152,7 +152,6 @@ static void raise_mce(struct mce *m)
 	if (context == MCJ_CTX_RANDOM)
 		return;
 
-#ifdef CONFIG_X86_LOCAL_APIC
 	if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) {
 		unsigned long start;
 		int cpu;
@@ -192,9 +191,7 @@ static void raise_mce(struct mce *m)
 		raise_local();
 		put_cpu();
 		put_online_cpus();
-	} else
-#endif
-	{
+	} else {
 		preempt_disable();
 		raise_local();
 		preempt_enable();
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index cd74a3f00aea..903043e6a62b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -31,7 +31,7 @@ struct mce_evt_llist {
 	struct mce mce;
 };
 
-void mce_gen_pool_process(void);
+void mce_gen_pool_process(struct work_struct *__unused);
 bool mce_gen_pool_empty(void);
 int mce_gen_pool_add(struct mce *mce);
 int mce_gen_pool_init(void);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 00ef43233e03..8e9725c607ea 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -128,7 +128,6 @@ void mce_setup(struct mce *m)
 {
 	memset(m, 0, sizeof(struct mce));
 	m->cpu = m->extcpu = smp_processor_id();
-	m->tsc = rdtsc();
 	/* We hope get_seconds stays lockless */
 	m->time = get_seconds();
 	m->cpuvendor = boot_cpu_data.x86_vendor;
@@ -217,9 +216,7 @@ void mce_register_decode_chain(struct notifier_block *nb)
 {
 	atomic_inc(&num_notifiers);
 
-	/* Ensure SRAO notifier has the highest priority in the decode chain. */
-	if (nb != &mce_srao_nb && nb->priority == INT_MAX)
-		nb->priority -= 1;
+	WARN_ON(nb->priority > MCE_PRIO_LOWEST && nb->priority < MCE_PRIO_EDAC);
 
 	atomic_notifier_chain_register(&x86_mce_decoder_chain, nb);
 }
@@ -583,7 +580,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val,
 }
 static struct notifier_block mce_srao_nb = {
 	.notifier_call	= srao_decode_notifier,
-	.priority = INT_MAX,
+	.priority	= MCE_PRIO_SRAO,
 };
 
 static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
@@ -609,7 +606,7 @@ static int mce_default_notifier(struct notifier_block *nb, unsigned long val,
 static struct notifier_block mce_default_nb = {
 	.notifier_call	= mce_default_notifier,
 	/* lowest prio, we want it to run last. */
-	.priority	= 0,
+	.priority	= MCE_PRIO_LOWEST,
 };
 
 /*
@@ -710,14 +707,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 
 	mce_gather_info(&m, NULL);
 
-	/*
-	 * m.tsc was set in mce_setup(). Clear it if not requested.
-	 *
-	 * FIXME: Propagate @flags to mce_gather_info/mce_setup() to avoid
-	 *	  that dance.
-	 */
-	if (!(flags & MCP_TIMESTAMP))
-		m.tsc = 0;
+	if (flags & MCP_TIMESTAMP)
+		m.tsc = rdtsc();
 
 	for (i = 0; i < mca_cfg.banks; i++) {
 		if (!mce_banks[i].ctl || !test_bit(i, *b))
@@ -1156,6 +1147,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		goto out;
 
 	mce_gather_info(&m, regs);
+	m.tsc = rdtsc();
 
 	final = this_cpu_ptr(&mces_seen);
 	*final = m;
@@ -1322,41 +1314,6 @@ int memory_failure(unsigned long pfn, int vector, int flags)
 #endif
 
 /*
- * Action optional processing happens here (picking up
- * from the list of faulting pages that do_machine_check()
- * placed into the genpool).
- */
-static void mce_process_work(struct work_struct *dummy)
-{
-	mce_gen_pool_process();
-}
-
-#ifdef CONFIG_X86_MCE_INTEL
-/***
- * mce_log_therm_throt_event - Logs the thermal throttling event to mcelog
- * @cpu: The CPU on which the event occurred.
- * @status: Event status information
- *
- * This function should be called by the thermal interrupt after the
- * event has been processed and the decision was made to log the event
- * further.
- *
- * The status parameter will be saved to the 'status' field of 'struct mce'
- * and historically has been the register value of the
- * MSR_IA32_THERMAL_STATUS (Intel) msr.
- */
-void mce_log_therm_throt_event(__u64 status)
-{
-	struct mce m;
-
-	mce_setup(&m);
-	m.bank = MCE_THERMAL_BANK;
-	m.status = status;
-	mce_log(&m);
-}
-#endif /* CONFIG_X86_MCE_INTEL */
-
-/*
  * Periodic polling timer for "silent" machine check errors.  If the
  * poller finds an MCE, poll 2x faster.  When the poller finds no more
  * errors, poll 2x slower (up to check_interval seconds).
@@ -1373,20 +1330,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval)
 
 static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
 
-static void __restart_timer(struct timer_list *t, unsigned long interval)
+static void __start_timer(struct timer_list *t, unsigned long interval)
 {
 	unsigned long when = jiffies + interval;
 	unsigned long flags;
 
 	local_irq_save(flags);
 
-	if (timer_pending(t)) {
-		if (time_before(when, t->expires))
-			mod_timer(t, when);
-	} else {
-		t->expires = round_jiffies(when);
-		add_timer_on(t, smp_processor_id());
-	}
+	if (!timer_pending(t) || time_before(when, t->expires))
+		mod_timer(t, round_jiffies(when));
 
 	local_irq_restore(flags);
 }
@@ -1421,7 +1373,7 @@ static void mce_timer_fn(unsigned long data)
 
 done:
 	__this_cpu_write(mce_next_interval, iv);
-	__restart_timer(t, iv);
+	__start_timer(t, iv);
 }
 
 /*
@@ -1432,7 +1384,7 @@ void mce_timer_kick(unsigned long interval)
 	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	unsigned long iv = __this_cpu_read(mce_next_interval);
 
-	__restart_timer(t, interval);
+	__start_timer(t, interval);
 
 	if (interval < iv)
 		__this_cpu_write(mce_next_interval, interval);
@@ -1779,17 +1731,15 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
 	}
 }
 
-static void mce_start_timer(unsigned int cpu, struct timer_list *t)
+static void mce_start_timer(struct timer_list *t)
 {
 	unsigned long iv = check_interval * HZ;
 
 	if (mca_cfg.ignore_ce || !iv)
 		return;
 
-	per_cpu(mce_next_interval, cpu) = iv;
-
-	t->expires = round_jiffies(jiffies + iv);
-	add_timer_on(t, cpu);
+	this_cpu_write(mce_next_interval, iv);
+	__start_timer(t, iv);
 }
 
 static void __mcheck_cpu_setup_timer(void)
@@ -1806,7 +1756,7 @@ static void __mcheck_cpu_init_timer(void)
 	unsigned int cpu = smp_processor_id();
 
 	setup_pinned_timer(t, mce_timer_fn, cpu);
-	mce_start_timer(cpu, t);
+	mce_start_timer(t);
 }
 
 /* Handle unconfigured int18 (should never happen) */
@@ -2196,7 +2146,7 @@ int __init mcheck_init(void)
 	mce_register_decode_chain(&mce_default_nb);
 	mcheck_vendor_init_severity();
 
-	INIT_WORK(&mce_work, mce_process_work);
+	INIT_WORK(&mce_work, mce_gen_pool_process);
 	init_irq_work(&mce_irq_work, mce_irq_work_cb);
 
 	return 0;
@@ -2566,7 +2516,7 @@ static int mce_cpu_dead(unsigned int cpu)
 
 static int mce_cpu_online(unsigned int cpu)
 {
-	struct timer_list *t = &per_cpu(mce_timer, cpu);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 	int ret;
 
 	mce_device_create(cpu);
@@ -2577,13 +2527,13 @@ static int mce_cpu_online(unsigned int cpu)
 		return ret;
 	}
 	mce_reenable_cpu();
-	mce_start_timer(cpu, t);
+	mce_start_timer(t);
 	return 0;
 }
 
 static int mce_cpu_pre_down(unsigned int cpu)
 {
-	struct timer_list *t = &per_cpu(mce_timer, cpu);
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
 
 	mce_disable_cpu();
 	del_timer_sync(t);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index a5fd137417a2..9e5427df3243 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -192,6 +192,7 @@ static void get_smca_bank_info(unsigned int bank)
 
 			smca_banks[bank].hwid = s_hwid;
 			smca_banks[bank].id = instance_id;
+			smca_banks[bank].sysfs_id = s_hwid->count++;
 			break;
 		}
 	}
@@ -777,7 +778,8 @@ __log_error(unsigned int bank, bool deferred_err, bool threshold_err, u64 misc)
 	mce_setup(&m);
 
 	m.status = status;
-	m.bank = bank;
+	m.bank   = bank;
+	m.tsc	 = rdtsc();
 
 	if (threshold_err)
 		m.misc = misc;
@@ -1064,9 +1066,12 @@ static const char *get_name(unsigned int bank, struct threshold_block *b)
 		return NULL;
 	}
 
+	if (smca_banks[bank].hwid->count == 1)
+		return smca_get_name(bank_type);
+
 	snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN,
 		 "%s_%x", smca_get_name(bank_type),
-			  smca_banks[bank].id);
+			  smca_banks[bank].sysfs_id);
 	return buf_mcatype;
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 465aca8be009..85469f84c921 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -6,7 +6,7 @@
  *
  * Maintains a counter in /sys that keeps track of the number of thermal
  * events, such that the user knows how bad the thermal problem might be
- * (since the logging to syslog and mcelog is rate limited).
+ * (since the logging to syslog is rate limited).
  *
  * Author: Dmitriy Zavin (dmitriyz@google.com)
  *
@@ -141,13 +141,8 @@ static struct attribute_group thermal_attr_group = {
  * IRQ has been acknowledged.
  *
  * It will take care of rate limiting and printing messages to the syslog.
- *
- * Returns: 0 : Event should NOT be further logged, i.e. still in
- *              "timeout" from previous log message.
- *          1 : Event should be logged further, and a message has been
- *              printed to the syslog.
  */
-static int therm_throt_process(bool new_event, int event, int level)
+static void therm_throt_process(bool new_event, int event, int level)
 {
 	struct _thermal_state *state;
 	unsigned int this_cpu = smp_processor_id();
@@ -162,16 +157,16 @@ static int therm_throt_process(bool new_event, int event, int level)
 		else if (event == POWER_LIMIT_EVENT)
 			state = &pstate->core_power_limit;
 		else
-			 return 0;
+			return;
 	} else if (level == PACKAGE_LEVEL) {
 		if (event == THERMAL_THROTTLING_EVENT)
 			state = &pstate->package_throttle;
 		else if (event == POWER_LIMIT_EVENT)
 			state = &pstate->package_power_limit;
 		else
-			return 0;
+			return;
 	} else
-		return 0;
+		return;
 
 	old_event = state->new_event;
 	state->new_event = new_event;
@@ -181,7 +176,7 @@ static int therm_throt_process(bool new_event, int event, int level)
 
 	if (time_before64(now, state->next_check) &&
 			state->count != state->last_count)
-		return 0;
+		return;
 
 	state->next_check = now + CHECK_INTERVAL;
 	state->last_count = state->count;
@@ -193,16 +188,14 @@ static int therm_throt_process(bool new_event, int event, int level)
 				this_cpu,
 				level == CORE_LEVEL ? "Core" : "Package",
 				state->count);
-		return 1;
+		return;
 	}
 	if (old_event) {
 		if (event == THERMAL_THROTTLING_EVENT)
 			pr_info("CPU%d: %s temperature/speed normal\n", this_cpu,
 				level == CORE_LEVEL ? "Core" : "Package");
-		return 1;
+		return;
 	}
-
-	return 0;
 }
 
 static int thresh_event_valid(int level, int event)
@@ -365,10 +358,9 @@ static void intel_thermal_interrupt(void)
 	/* Check for violation of core thermal thresholds*/
 	notify_thresholds(msr_val);
 
-	if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
-				THERMAL_THROTTLING_EVENT,
-				CORE_LEVEL) != 0)
-		mce_log_therm_throt_event(msr_val);
+	therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
+			    THERMAL_THROTTLING_EVENT,
+			    CORE_LEVEL);
 
 	if (this_cpu_has(X86_FEATURE_PLN) && int_pln_enable)
 		therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 6a31e2691f3a..7889ae492af0 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -42,16 +42,19 @@ static struct equiv_cpu_entry *equiv_cpu_table;
 
 /*
  * This points to the current valid container of microcode patches which we will
- * save from the initrd/builtin before jettisoning its contents.
+ * save from the initrd/builtin before jettisoning its contents. @mc is the
+ * microcode patch we found to match.
  */
-struct container {
-	u8 *data;
-	size_t size;
-} cont;
+struct cont_desc {
+	struct microcode_amd *mc;
+	u32		     cpuid_1_eax;
+	u32		     psize;
+	u8		     *data;
+	size_t		     size;
+};
 
 static u32 ucode_new_rev;
 static u8 amd_ucode_patch[PATCH_MAX_SIZE];
-static u16 this_equiv_id;
 
 /*
  * Microcode patch container file is prepended to the initrd in cpio
@@ -60,57 +63,13 @@ static u16 this_equiv_id;
 static const char
 ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
 
-static size_t compute_container_size(u8 *data, u32 total_size)
+static u16 find_equiv_id(struct equiv_cpu_entry *equiv_table, u32 sig)
 {
-	size_t size = 0;
-	u32 *header = (u32 *)data;
-
-	if (header[0] != UCODE_MAGIC ||
-	    header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
-	    header[2] == 0)                            /* size */
-		return size;
-
-	size = header[2] + CONTAINER_HDR_SZ;
-	total_size -= size;
-	data += size;
-
-	while (total_size) {
-		u16 patch_size;
-
-		header = (u32 *)data;
-
-		if (header[0] != UCODE_UCODE_TYPE)
-			break;
-
-		/*
-		 * Sanity-check patch size.
-		 */
-		patch_size = header[1];
-		if (patch_size > PATCH_MAX_SIZE)
-			break;
-
-		size	   += patch_size + SECTION_HDR_SIZE;
-		data	   += patch_size + SECTION_HDR_SIZE;
-		total_size -= patch_size + SECTION_HDR_SIZE;
+	for (; equiv_table && equiv_table->installed_cpu; equiv_table++) {
+		if (sig == equiv_table->installed_cpu)
+			return equiv_table->equiv_cpu;
 	}
 
-	return size;
-}
-
-static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
-				unsigned int sig)
-{
-	int i = 0;
-
-	if (!equiv_cpu_table)
-		return 0;
-
-	while (equiv_cpu_table[i].installed_cpu != 0) {
-		if (sig == equiv_cpu_table[i].installed_cpu)
-			return equiv_cpu_table[i].equiv_cpu;
-
-		i++;
-	}
 	return 0;
 }
 
@@ -118,91 +77,109 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
  * This scans the ucode blob for the proper container as we can have multiple
  * containers glued together. Returns the equivalence ID from the equivalence
  * table or 0 if none found.
+ * Returns the amount of bytes consumed while scanning. @desc contains all the
+ * data we're going to use in later stages of the application.
  */
-static u16
-find_proper_container(u8 *ucode, size_t size, struct container *ret_cont)
+static ssize_t parse_container(u8 *ucode, ssize_t size, struct cont_desc *desc)
 {
-	struct container ret = { NULL, 0 };
-	u32 eax, ebx, ecx, edx;
 	struct equiv_cpu_entry *eq;
-	int offset, left;
-	u16 eq_id = 0;
-	u32 *header;
-	u8 *data;
+	ssize_t orig_size = size;
+	u32 *hdr = (u32 *)ucode;
+	u16 eq_id;
+	u8 *buf;
 
-	data   = ucode;
-	left   = size;
-	header = (u32 *)data;
+	/* Am I looking at an equivalence table header? */
+	if (hdr[0] != UCODE_MAGIC ||
+	    hdr[1] != UCODE_EQUIV_CPU_TABLE_TYPE ||
+	    hdr[2] == 0)
+		return CONTAINER_HDR_SZ;
 
+	buf = ucode;
 
-	/* find equiv cpu table */
-	if (header[0] != UCODE_MAGIC ||
-	    header[1] != UCODE_EQUIV_CPU_TABLE_TYPE || /* type */
-	    header[2] == 0)                            /* size */
-		return eq_id;
+	eq = (struct equiv_cpu_entry *)(buf + CONTAINER_HDR_SZ);
 
-	eax = 0x00000001;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
+	/* Find the equivalence ID of our CPU in this table: */
+	eq_id = find_equiv_id(eq, desc->cpuid_1_eax);
 
-	while (left > 0) {
-		eq = (struct equiv_cpu_entry *)(data + CONTAINER_HDR_SZ);
+	buf  += hdr[2] + CONTAINER_HDR_SZ;
+	size -= hdr[2] + CONTAINER_HDR_SZ;
+
+	/*
+	 * Scan through the rest of the container to find where it ends. We do
+	 * some basic sanity-checking too.
+	 */
+	while (size > 0) {
+		struct microcode_amd *mc;
+		u32 patch_size;
 
-		ret.data = data;
+		hdr = (u32 *)buf;
 
-		/* Advance past the container header */
-		offset = header[2] + CONTAINER_HDR_SZ;
-		data  += offset;
-		left  -= offset;
+		if (hdr[0] != UCODE_UCODE_TYPE)
+			break;
 
-		eq_id = find_equiv_id(eq, eax);
-		if (eq_id) {
-			ret.size = compute_container_size(ret.data, left + offset);
+		/* Sanity-check patch size. */
+		patch_size = hdr[1];
+		if (patch_size > PATCH_MAX_SIZE)
+			break;
 
-			/*
-			 * truncate how much we need to iterate over in the
-			 * ucode update loop below
-			 */
-			left = ret.size - offset;
+		/* Skip patch section header: */
+		buf  += SECTION_HDR_SIZE;
+		size -= SECTION_HDR_SIZE;
 
-			*ret_cont = ret;
-			return eq_id;
+		mc = (struct microcode_amd *)buf;
+		if (eq_id == mc->hdr.processor_rev_id) {
+			desc->psize = patch_size;
+			desc->mc = mc;
 		}
 
-		/*
-		 * support multiple container files appended together. if this
-		 * one does not have a matching equivalent cpu entry, we fast
-		 * forward to the next container file.
-		 */
-		while (left > 0) {
-			header = (u32 *)data;
-
-			if (header[0] == UCODE_MAGIC &&
-			    header[1] == UCODE_EQUIV_CPU_TABLE_TYPE)
-				break;
-
-			offset = header[1] + SECTION_HDR_SIZE;
-			data  += offset;
-			left  -= offset;
-		}
+		buf  += patch_size;
+		size -= patch_size;
+	}
 
-		/* mark where the next microcode container file starts */
-		offset    = data - (u8 *)ucode;
-		ucode     = data;
+	/*
+	 * If we have found a patch (desc->mc), it means we're looking at the
+	 * container which has a patch for this CPU so return 0 to mean, @ucode
+	 * already points to the proper container. Otherwise, we return the size
+	 * we scanned so that we can advance to the next container in the
+	 * buffer.
+	 */
+	if (desc->mc) {
+		desc->data = ucode;
+		desc->size = orig_size - size;
+
+		return 0;
 	}
 
-	return eq_id;
+	return orig_size - size;
 }
 
-static int __apply_microcode_amd(struct microcode_amd *mc_amd)
+/*
+ * Scan the ucode blob for the proper container as we can have multiple
+ * containers glued together.
+ */
+static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc)
+{
+	ssize_t rem = size;
+
+	while (rem >= 0) {
+		ssize_t s = parse_container(ucode, rem, desc);
+		if (!s)
+			return;
+
+		ucode += s;
+		rem   -= s;
+	}
+}
+
+static int __apply_microcode_amd(struct microcode_amd *mc)
 {
 	u32 rev, dummy;
 
-	native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc_amd->hdr.data_code);
+	native_wrmsrl(MSR_AMD64_PATCH_LOADER, (u64)(long)&mc->hdr.data_code);
 
 	/* verify patch application was successful */
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-	if (rev != mc_amd->hdr.patch_id)
+	if (rev != mc->hdr.patch_id)
 		return -1;
 
 	return 0;
@@ -217,17 +194,16 @@ static int __apply_microcode_amd(struct microcode_amd *mc_amd)
  * load_microcode_amd() to save equivalent cpu table and microcode patches in
  * kernel heap memory.
  *
- * Returns true if container found (sets @ret_cont), false otherwise.
+ * Returns true if container found (sets @desc), false otherwise.
  */
-static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch,
-				      struct container *ret_cont)
+static bool
+apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_patch)
 {
+	struct cont_desc desc = { 0 };
 	u8 (*patch)[PATCH_MAX_SIZE];
-	u32 rev, *header, *new_rev;
-	struct container ret;
-	int offset, left;
-	u16 eq_id = 0;
-	u8  *data;
+	struct microcode_amd *mc;
+	u32 rev, dummy, *new_rev;
+	bool ret = false;
 
 #ifdef CONFIG_X86_32
 	new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
@@ -237,50 +213,27 @@ static bool apply_microcode_early_amd(void *ucode, size_t size, bool save_patch,
 	patch	= &amd_ucode_patch;
 #endif
 
-	if (check_current_patch_level(&rev, true))
-		return false;
-
-	eq_id = find_proper_container(ucode, size, &ret);
-	if (!eq_id)
-		return false;
-
-	this_equiv_id = eq_id;
-	header = (u32 *)ret.data;
-
-	/* We're pointing to an equiv table, skip over it. */
-	data = ret.data +  header[2] + CONTAINER_HDR_SZ;
-	left = ret.size - (header[2] + CONTAINER_HDR_SZ);
-
-	while (left > 0) {
-		struct microcode_amd *mc;
-
-		header = (u32 *)data;
-		if (header[0] != UCODE_UCODE_TYPE || /* type */
-		    header[1] == 0)                  /* size */
-			break;
+	desc.cpuid_1_eax = cpuid_1_eax;
 
-		mc = (struct microcode_amd *)(data + SECTION_HDR_SIZE);
+	scan_containers(ucode, size, &desc);
 
-		if (eq_id == mc->hdr.processor_rev_id && rev < mc->hdr.patch_id) {
+	mc = desc.mc;
+	if (!mc)
+		return ret;
 
-			if (!__apply_microcode_amd(mc)) {
-				rev = mc->hdr.patch_id;
-				*new_rev = rev;
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+	if (rev >= mc->hdr.patch_id)
+		return ret;
 
-				if (save_patch)
-					memcpy(patch, mc, min_t(u32, header[1], PATCH_MAX_SIZE));
-			}
-		}
+	if (!__apply_microcode_amd(mc)) {
+		*new_rev = mc->hdr.patch_id;
+		ret      = true;
 
-		offset  = header[1] + SECTION_HDR_SIZE;
-		data   += offset;
-		left   -= offset;
+		if (save_patch)
+			memcpy(patch, mc, min_t(u32, desc.psize, PATCH_MAX_SIZE));
 	}
 
-	if (ret_cont)
-		*ret_cont = ret;
-
-	return true;
+	return ret;
 }
 
 static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
@@ -298,10 +251,9 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family)
 #endif
 }
 
-void __init load_ucode_amd_bsp(unsigned int family)
+void __load_ucode_amd(unsigned int cpuid_1_eax, struct cpio_data *ret)
 {
 	struct ucode_cpu_info *uci;
-	u32 eax, ebx, ecx, edx;
 	struct cpio_data cp;
 	const char *path;
 	bool use_pa;
@@ -316,183 +268,95 @@ void __init load_ucode_amd_bsp(unsigned int family)
 		use_pa	= false;
 	}
 
-	if (!get_builtin_microcode(&cp, family))
+	if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax)))
 		cp = find_microcode_in_initrd(path, use_pa);
 
-	if (!(cp.data && cp.size))
-		return;
-
-	/* Get BSP's CPUID.EAX(1), needed in load_microcode_amd() */
-	eax = 1;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-	uci->cpu_sig.sig = eax;
+	/* Needed in load_microcode_amd() */
+	uci->cpu_sig.sig = cpuid_1_eax;
 
-	apply_microcode_early_amd(cp.data, cp.size, true, NULL);
+	*ret = cp;
 }
 
-#ifdef CONFIG_X86_32
-/*
- * On 32-bit, since AP's early load occurs before paging is turned on, we
- * cannot traverse cpu_equiv_table and microcode_cache in kernel heap memory.
- * So during cold boot, AP will apply_ucode_in_initrd() just like the BSP.
- * In save_microcode_in_initrd_amd() BSP's patch is copied to amd_ucode_patch,
- * which is used upon resume from suspend.
- */
-void load_ucode_amd_ap(unsigned int family)
+void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax)
 {
-	struct microcode_amd *mc;
-	struct cpio_data cp;
-
-	mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch);
-	if (mc->hdr.patch_id && mc->hdr.processor_rev_id) {
-		__apply_microcode_amd(mc);
-		return;
-	}
-
-	if (!get_builtin_microcode(&cp, family))
-		cp = find_microcode_in_initrd((const char *)__pa_nodebug(ucode_path), true);
+	struct cpio_data cp = { };
 
+	__load_ucode_amd(cpuid_1_eax, &cp);
 	if (!(cp.data && cp.size))
 		return;
 
-	/*
-	 * This would set amd_ucode_patch above so that the following APs can
-	 * use it directly instead of going down this path again.
-	 */
-	apply_microcode_early_amd(cp.data, cp.size, true, NULL);
+	apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, true);
 }
-#else
-void load_ucode_amd_ap(unsigned int family)
+
+void load_ucode_amd_ap(unsigned int cpuid_1_eax)
 {
-	struct equiv_cpu_entry *eq;
 	struct microcode_amd *mc;
-	u32 rev, eax;
-	u16 eq_id;
-
-	/* 64-bit runs with paging enabled, thus early==false. */
-	if (check_current_patch_level(&rev, false))
-		return;
-
-	/* First AP hasn't cached it yet, go through the blob. */
-	if (!cont.data) {
-		struct cpio_data cp = { NULL, 0, "" };
+	struct cpio_data cp;
+	u32 *new_rev, rev, dummy;
 
-		if (cont.size == -1)
-			return;
+	if (IS_ENABLED(CONFIG_X86_32)) {
+		mc	= (struct microcode_amd *)__pa_nodebug(amd_ucode_patch);
+		new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
+	} else {
+		mc	= (struct microcode_amd *)amd_ucode_patch;
+		new_rev = &ucode_new_rev;
+	}
 
-reget:
-		if (!get_builtin_microcode(&cp, family)) {
-#ifdef CONFIG_BLK_DEV_INITRD
-			cp = find_cpio_data(ucode_path, (void *)initrd_start,
-					    initrd_end - initrd_start, NULL);
-#endif
-			if (!(cp.data && cp.size)) {
-				/*
-				 * Mark it so that other APs do not scan again
-				 * for no real reason and slow down boot
-				 * needlessly.
-				 */
-				cont.size = -1;
-				return;
-			}
-		}
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 
-		if (!apply_microcode_early_amd(cp.data, cp.size, false, &cont)) {
-			cont.size = -1;
+	/* Check whether we have saved a new patch already: */
+	if (*new_rev && rev < mc->hdr.patch_id) {
+		if (!__apply_microcode_amd(mc)) {
+			*new_rev = mc->hdr.patch_id;
 			return;
 		}
 	}
 
-	eax = cpuid_eax(0x00000001);
-	eq  = (struct equiv_cpu_entry *)(cont.data + CONTAINER_HDR_SZ);
-
-	eq_id = find_equiv_id(eq, eax);
-	if (!eq_id)
+	__load_ucode_amd(cpuid_1_eax, &cp);
+	if (!(cp.data && cp.size))
 		return;
 
-	if (eq_id == this_equiv_id) {
-		mc = (struct microcode_amd *)amd_ucode_patch;
-
-		if (mc && rev < mc->hdr.patch_id) {
-			if (!__apply_microcode_amd(mc))
-				ucode_new_rev = mc->hdr.patch_id;
-		}
-
-	} else {
-
-		/*
-		 * AP has a different equivalence ID than BSP, looks like
-		 * mixed-steppings silicon so go through the ucode blob anew.
-		 */
-		goto reget;
-	}
+	apply_microcode_early_amd(cpuid_1_eax, cp.data, cp.size, false);
 }
-#endif /* CONFIG_X86_32 */
 
 static enum ucode_state
 load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
 
-int __init save_microcode_in_initrd_amd(unsigned int fam)
+int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 {
+	struct cont_desc desc = { 0 };
 	enum ucode_state ret;
-	int retval = 0;
-	u16 eq_id;
-
-	if (!cont.data) {
-		if (IS_ENABLED(CONFIG_X86_32) && (cont.size != -1)) {
-			struct cpio_data cp = { NULL, 0, "" };
-
-#ifdef CONFIG_BLK_DEV_INITRD
-			cp = find_cpio_data(ucode_path, (void *)initrd_start,
-					    initrd_end - initrd_start, NULL);
-#endif
+	struct cpio_data cp;
 
-			if (!(cp.data && cp.size)) {
-				cont.size = -1;
-				return -EINVAL;
-			}
+	cp = find_microcode_in_initrd(ucode_path, false);
+	if (!(cp.data && cp.size))
+		return -EINVAL;
 
-			eq_id = find_proper_container(cp.data, cp.size, &cont);
-			if (!eq_id) {
-				cont.size = -1;
-				return -EINVAL;
-			}
+	desc.cpuid_1_eax = cpuid_1_eax;
 
-		} else
-			return -EINVAL;
-	}
+	scan_containers(cp.data, cp.size, &desc);
+	if (!desc.mc)
+		return -EINVAL;
 
-	ret = load_microcode_amd(smp_processor_id(), fam, cont.data, cont.size);
+	ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax),
+				 desc.data, desc.size);
 	if (ret != UCODE_OK)
-		retval = -EINVAL;
-
-	/*
-	 * This will be freed any msec now, stash patches for the current
-	 * family and switch to patch cache for cpu hotplug, etc later.
-	 */
-	cont.data = NULL;
-	cont.size = 0;
+		return -EINVAL;
 
-	return retval;
+	return 0;
 }
 
 void reload_ucode_amd(void)
 {
 	struct microcode_amd *mc;
-	u32 rev;
-
-	/*
-	 * early==false because this is a syscore ->resume path and by
-	 * that time paging is long enabled.
-	 */
-	if (check_current_patch_level(&rev, false))
-		return;
+	u32 rev, dummy;
 
 	mc = (struct microcode_amd *)amd_ucode_patch;
 	if (!mc)
 		return;
 
+	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+
 	if (rev < mc->hdr.patch_id) {
 		if (!__apply_microcode_amd(mc)) {
 			ucode_new_rev = mc->hdr.patch_id;
@@ -630,60 +494,13 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 	return patch_size;
 }
 
-/*
- * Those patch levels cannot be updated to newer ones and thus should be final.
- */
-static u32 final_levels[] = {
-	0x01000098,
-	0x0100009f,
-	0x010000af,
-	0, /* T-101 terminator */
-};
-
-/*
- * Check the current patch level on this CPU.
- *
- * @rev: Use it to return the patch level. It is set to 0 in the case of
- * error.
- *
- * Returns:
- *  - true: if update should stop
- *  - false: otherwise
- */
-bool check_current_patch_level(u32 *rev, bool early)
-{
-	u32 lvl, dummy, i;
-	bool ret = false;
-	u32 *levels;
-
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
-
-	if (IS_ENABLED(CONFIG_X86_32) && early)
-		levels = (u32 *)__pa_nodebug(&final_levels);
-	else
-		levels = final_levels;
-
-	for (i = 0; levels[i]; i++) {
-		if (lvl == levels[i]) {
-			lvl = 0;
-			ret = true;
-			break;
-		}
-	}
-
-	if (rev)
-		*rev = lvl;
-
-	return ret;
-}
-
 static int apply_microcode_amd(int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct microcode_amd *mc_amd;
 	struct ucode_cpu_info *uci;
 	struct ucode_patch *p;
-	u32 rev;
+	u32 rev, dummy;
 
 	BUG_ON(raw_smp_processor_id() != cpu);
 
@@ -696,8 +513,7 @@ static int apply_microcode_amd(int cpu)
 	mc_amd  = p->data;
 	uci->mc = p->data;
 
-	if (check_current_patch_level(&rev, false))
-		return -1;
+	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 
 	/* need to apply patch? */
 	if (rev >= mc_amd->hdr.patch_id) {
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 2af69d27da62..b4a4cd39b358 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -46,6 +46,8 @@
 static struct microcode_ops	*microcode_ops;
 static bool dis_ucode_ldr = true;
 
+bool initrd_gone;
+
 LIST_HEAD(microcode_cache);
 
 /*
@@ -64,19 +66,50 @@ static DEFINE_MUTEX(microcode_mutex);
 
 struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 
-/*
- * Operations that are run on a target cpu:
- */
-
 struct cpu_info_ctx {
 	struct cpu_signature	*cpu_sig;
 	int			err;
 };
 
+/*
+ * Those patch levels cannot be updated to newer ones and thus should be final.
+ */
+static u32 final_levels[] = {
+	0x01000098,
+	0x0100009f,
+	0x010000af,
+	0, /* T-101 terminator */
+};
+
+/*
+ * Check the current patch level on this CPU.
+ *
+ * Returns:
+ *  - true: if update should stop
+ *  - false: otherwise
+ */
+static bool amd_check_current_patch_level(void)
+{
+	u32 lvl, dummy, i;
+	u32 *levels;
+
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy);
+
+	if (IS_ENABLED(CONFIG_X86_32))
+		levels = (u32 *)__pa_nodebug(&final_levels);
+	else
+		levels = final_levels;
+
+	for (i = 0; levels[i]; i++) {
+		if (lvl == levels[i])
+			return true;
+	}
+	return false;
+}
+
 static bool __init check_loader_disabled_bsp(void)
 {
 	static const char *__dis_opt_str = "dis_ucode_ldr";
-	u32 a, b, c, d;
 
 #ifdef CONFIG_X86_32
 	const char *cmdline = (const char *)__pa_nodebug(boot_command_line);
@@ -92,18 +125,19 @@ static bool __init check_loader_disabled_bsp(void)
 	if (!have_cpuid_p())
 		return *res;
 
-	a = 1;
-	c = 0;
-	native_cpuid(&a, &b, &c, &d);
-
 	/*
 	 * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not
 	 * completely accurate as xen pv guests don't see that CPUID bit set but
 	 * that's good enough as they don't land on the BSP path anyway.
 	 */
-	if (c & BIT(31))
+	if (native_cpuid_ecx(1) & BIT(31))
 		return *res;
 
+	if (x86_cpuid_vendor() == X86_VENDOR_AMD) {
+		if (amd_check_current_patch_level())
+			return *res;
+	}
+
 	if (cmdline_find_option_bool(cmdline, option) <= 0)
 		*res = false;
 
@@ -131,23 +165,21 @@ bool get_builtin_firmware(struct cpio_data *cd, const char *name)
 
 void __init load_ucode_bsp(void)
 {
-	int vendor;
-	unsigned int family;
+	unsigned int cpuid_1_eax;
 
 	if (check_loader_disabled_bsp())
 		return;
 
-	vendor = x86_cpuid_vendor();
-	family = x86_cpuid_family();
+	cpuid_1_eax = native_cpuid_eax(1);
 
-	switch (vendor) {
+	switch (x86_cpuid_vendor()) {
 	case X86_VENDOR_INTEL:
-		if (family >= 6)
+		if (x86_family(cpuid_1_eax) >= 6)
 			load_ucode_intel_bsp();
 		break;
 	case X86_VENDOR_AMD:
-		if (family >= 0x10)
-			load_ucode_amd_bsp(family);
+		if (x86_family(cpuid_1_eax) >= 0x10)
+			load_ucode_amd_bsp(cpuid_1_eax);
 		break;
 	default:
 		break;
@@ -165,22 +197,21 @@ static bool check_loader_disabled_ap(void)
 
 void load_ucode_ap(void)
 {
-	int vendor, family;
+	unsigned int cpuid_1_eax;
 
 	if (check_loader_disabled_ap())
 		return;
 
-	vendor = x86_cpuid_vendor();
-	family = x86_cpuid_family();
+	cpuid_1_eax = native_cpuid_eax(1);
 
-	switch (vendor) {
+	switch (x86_cpuid_vendor()) {
 	case X86_VENDOR_INTEL:
-		if (family >= 6)
+		if (x86_family(cpuid_1_eax) >= 6)
 			load_ucode_intel_ap();
 		break;
 	case X86_VENDOR_AMD:
-		if (family >= 0x10)
-			load_ucode_amd_ap(family);
+		if (x86_family(cpuid_1_eax) >= 0x10)
+			load_ucode_amd_ap(cpuid_1_eax);
 		break;
 	default:
 		break;
@@ -190,21 +221,24 @@ void load_ucode_ap(void)
 static int __init save_microcode_in_initrd(void)
 {
 	struct cpuinfo_x86 *c = &boot_cpu_data;
+	int ret = -EINVAL;
 
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
 		if (c->x86 >= 6)
-			return save_microcode_in_initrd_intel();
+			ret = save_microcode_in_initrd_intel();
 		break;
 	case X86_VENDOR_AMD:
 		if (c->x86 >= 0x10)
-			return save_microcode_in_initrd_amd(c->x86);
+			return save_microcode_in_initrd_amd(cpuid_eax(1));
 		break;
 	default:
 		break;
 	}
 
-	return -EINVAL;
+	initrd_gone = true;
+
+	return ret;
 }
 
 struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
@@ -247,9 +281,16 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa)
 	 * has the virtual address of the beginning of the initrd. It also
 	 * possibly relocates the ramdisk. In either case, initrd_start contains
 	 * the updated address so use that instead.
+	 *
+	 * initrd_gone is for the hotplug case where we've thrown out initrd
+	 * already.
 	 */
-	if (!use_pa && initrd_start)
-		start = initrd_start;
+	if (!use_pa) {
+		if (initrd_gone)
+			return (struct cpio_data){ NULL, 0, "" };
+		if (initrd_start)
+			start = initrd_start;
+	}
 
 	return find_cpio_data(path, (void *)start, size, NULL);
 #else /* !CONFIG_BLK_DEV_INITRD */
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 3f329b74e040..8325d8a09ab0 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -41,7 +41,7 @@
 
 static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin";
 
-/* Current microcode patch used in early patching */
+/* Current microcode patch used in early patching on the APs. */
 struct microcode_intel *intel_ucode_patch;
 
 static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1,
@@ -607,12 +607,6 @@ int __init save_microcode_in_initrd_intel(void)
 	struct ucode_cpu_info uci;
 	struct cpio_data cp;
 
-	/*
-	 * AP loading didn't find any microcode patch, no need to save anything.
-	 */
-	if (!intel_ucode_patch || IS_ERR(intel_ucode_patch))
-		return 0;
-
 	if (!load_builtin_intel_microcode(&cp))
 		cp = find_microcode_in_initrd(ucode_path, false);
 
@@ -628,7 +622,6 @@ int __init save_microcode_in_initrd_intel(void)
 	return 0;
 }
 
-
 /*
  * @res_patch, output: a pointer to the patch we found.
  */
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 34178564be2a..c1ea5b999839 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -1,4 +1,5 @@
 #include <linux/kernel.h>
+#include <linux/sched.h>
 #include <linux/mm.h>
 #include <asm/cpufeature.h>
 #include <asm/msr.h>
@@ -14,6 +15,8 @@ static void early_init_transmeta(struct cpuinfo_x86 *c)
 		if (xlvl >= 0x80860001)
 			c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
 	}
+
+	clear_sched_clock_stable();
 }
 
 static void init_transmeta(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 90e8dde3ec26..b2bbad6ebe4d 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -580,24 +580,19 @@ static void __init update_e820_saved(void)
 }
 #define MAX_GAP_END 0x100000000ull
 /*
- * Search for a gap in the e820 memory space from start_addr to end_addr.
+ * Search for a gap in the e820 memory space from 0 to MAX_GAP_END.
  */
-__init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
-		unsigned long start_addr, unsigned long long end_addr)
+static int __init e820_search_gap(unsigned long *gapstart,
+		unsigned long *gapsize)
 {
-	unsigned long long last;
+	unsigned long long last = MAX_GAP_END;
 	int i = e820->nr_map;
 	int found = 0;
 
-	last = (end_addr && end_addr < MAX_GAP_END) ? end_addr : MAX_GAP_END;
-
 	while (--i >= 0) {
 		unsigned long long start = e820->map[i].addr;
 		unsigned long long end = start + e820->map[i].size;
 
-		if (end < start_addr)
-			continue;
-
 		/*
 		 * Since "last" is at most 4GB, we know we'll
 		 * fit in 32 bits if this condition is true
@@ -628,18 +623,19 @@ __init void e820_setup_gap(void)
 	unsigned long gapstart, gapsize;
 	int found;
 
-	gapstart = 0x10000000;
 	gapsize = 0x400000;
-	found  = e820_search_gap(&gapstart, &gapsize, 0, MAX_GAP_END);
+	found  = e820_search_gap(&gapstart, &gapsize);
 
-#ifdef CONFIG_X86_64
 	if (!found) {
+#ifdef CONFIG_X86_64
 		gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
 		printk(KERN_ERR
 	"e820: cannot find a gap in the 32bit address range\n"
 	"e820: PCI devices with unassigned 32bit BARs may break!\n");
-	}
+#else
+		gapstart = 0x10000000;
 #endif
+	}
 
 	/*
 	 * e820_reserve_resources_late protect stolen RAM already
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index e4e97a5355ce..e1114f070c2d 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -178,13 +178,8 @@ void fpstate_init(union fpregs_state *state)
 
 	memset(state, 0, fpu_kernel_xstate_size);
 
-	/*
-	 * XRSTORS requires that this bit is set in xcomp_bv, or
-	 * it will #GP. Make sure it is replaced after the memset().
-	 */
 	if (static_cpu_has(X86_FEATURE_XSAVES))
-		state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT;
-
+		fpstate_init_xstate(&state->xsave);
 	if (static_cpu_has(X86_FEATURE_FXSR))
 		fpstate_init_fxstate(&state->fxsave);
 	else
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 60dece392b3a..19bdd1bf8160 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -48,13 +48,7 @@ void fpu__init_cpu(void)
 	fpu__init_cpu_xstate();
 }
 
-/*
- * The earliest FPU detection code.
- *
- * Set the X86_FEATURE_FPU CPU-capability bit based on
- * trying to execute an actual sequence of FPU instructions:
- */
-static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+static bool fpu__probe_without_cpuid(void)
 {
 	unsigned long cr0;
 	u16 fsw, fcw;
@@ -65,18 +59,25 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
 	cr0 &= ~(X86_CR0_TS | X86_CR0_EM);
 	write_cr0(cr0);
 
-	if (!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
-		asm volatile("fninit ; fnstsw %0 ; fnstcw %1"
-			     : "+m" (fsw), "+m" (fcw));
+	asm volatile("fninit ; fnstsw %0 ; fnstcw %1" : "+m" (fsw), "+m" (fcw));
+
+	pr_info("x86/fpu: Probing for FPU: FSW=0x%04hx FCW=0x%04hx\n", fsw, fcw);
 
-		if (fsw == 0 && (fcw & 0x103f) == 0x003f)
-			set_cpu_cap(c, X86_FEATURE_FPU);
+	return fsw == 0 && (fcw & 0x103f) == 0x003f;
+}
+
+static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+{
+	if (!boot_cpu_has(X86_FEATURE_CPUID) &&
+	    !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
+		if (fpu__probe_without_cpuid())
+			setup_force_cpu_cap(X86_FEATURE_FPU);
 		else
-			clear_cpu_cap(c, X86_FEATURE_FPU);
+			setup_clear_cpu_cap(X86_FEATURE_FPU);
 	}
 
 #ifndef CONFIG_MATH_EMULATION
-	if (!boot_cpu_has(X86_FEATURE_FPU)) {
+	if (!test_cpu_cap(&boot_cpu_data, X86_FEATURE_FPU)) {
 		pr_emerg("x86/fpu: Giving up, no FPU found and no math emulation present\n");
 		for (;;)
 			asm volatile("hlt");
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 1d7770447b3e..c24ac1efb12d 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -78,6 +78,7 @@ void fpu__xstate_clear_all_cpu_caps(void)
 	setup_clear_cpu_cap(X86_FEATURE_PKU);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW);
 	setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512_VPOPCNTDQ);
 }
 
 /*
@@ -705,8 +706,14 @@ void __init fpu__init_system_xstate(void)
 	WARN_ON_FPU(!on_boot_cpu);
 	on_boot_cpu = 0;
 
+	if (!boot_cpu_has(X86_FEATURE_FPU)) {
+		pr_info("x86/fpu: No FPU detected\n");
+		return;
+	}
+
 	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
-		pr_info("x86/fpu: Legacy x87 FPU detected.\n");
+		pr_info("x86/fpu: x87 FPU will use %s\n",
+			boot_cpu_has(X86_FEATURE_FXSR) ? "FXSAVE" : "FSAVE");
 		return;
 	}
 
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index f16c55bfc090..e5fb436a6548 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -49,3 +49,65 @@ asmlinkage __visible void __init i386_start_kernel(void)
 
 	start_kernel();
 }
+
+/*
+ * Initialize page tables.  This creates a PDE and a set of page
+ * tables, which are located immediately beyond __brk_base.  The variable
+ * _brk_end is set up to point to the first "safe" location.
+ * Mappings are created both at virtual address 0 (identity mapping)
+ * and PAGE_OFFSET for up to _end.
+ *
+ * In PAE mode initial_page_table is statically defined to contain
+ * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
+ * entries). The identity mapping is handled by pointing two PGD entries
+ * to the first kernel PMD. Note the upper half of each PMD or PTE are
+ * always zero at this stage.
+ */
+void __init mk_early_pgtbl_32(void)
+{
+#ifdef __pa
+#undef __pa
+#endif
+#define __pa(x)  ((unsigned long)(x) - PAGE_OFFSET)
+	pte_t pte, *ptep;
+	int i;
+	unsigned long *ptr;
+	/* Enough space to fit pagetables for the low memory linear map */
+	const unsigned long limit = __pa(_end) +
+		(PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT);
+#ifdef CONFIG_X86_PAE
+	pmd_t pl2, *pl2p = (pmd_t *)__pa(initial_pg_pmd);
+#define SET_PL2(pl2, val)    { (pl2).pmd = (val); }
+#else
+	pgd_t pl2, *pl2p = (pgd_t *)__pa(initial_page_table);
+#define SET_PL2(pl2, val)   { (pl2).pgd = (val); }
+#endif
+
+	ptep = (pte_t *)__pa(__brk_base);
+	pte.pte = PTE_IDENT_ATTR;
+
+	while ((pte.pte & PTE_PFN_MASK) < limit) {
+
+		SET_PL2(pl2, (unsigned long)ptep | PDE_IDENT_ATTR);
+		*pl2p = pl2;
+#ifndef CONFIG_X86_PAE
+		/* Kernel PDE entry */
+		*(pl2p +  ((PAGE_OFFSET >> PGDIR_SHIFT))) = pl2;
+#endif
+		for (i = 0; i < PTRS_PER_PTE; i++) {
+			*ptep = pte;
+			pte.pte += PAGE_SIZE;
+			ptep++;
+		}
+
+		pl2p++;
+	}
+
+	ptr = (unsigned long *)__pa(&max_pfn_mapped);
+	/* Can't use pte_pfn() since it's a call with CONFIG_PARAVIRT */
+	*ptr = (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+
+	ptr = (unsigned long *)__pa(&_brk_end);
+	*ptr = (unsigned long)ptep + PAGE_OFFSET;
+}
+
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 4e8577d03372..1f85ee8f9439 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -24,6 +24,7 @@
 #include <asm/nops.h>
 #include <asm/bootparam.h>
 #include <asm/export.h>
+#include <asm/pgtable_32.h>
 
 /* Physical address */
 #define pa(X) ((X) - __PAGE_OFFSET)
@@ -41,44 +42,10 @@
 #define X86_CAPABILITY	new_cpu_data+CPUINFO_x86_capability
 #define X86_VENDOR_ID	new_cpu_data+CPUINFO_x86_vendor_id
 
-/*
- * This is how much memory in addition to the memory covered up to
- * and including _end we need mapped initially.
- * We need:
- *     (KERNEL_IMAGE_SIZE/4096) / 1024 pages (worst case, non PAE)
- *     (KERNEL_IMAGE_SIZE/4096) / 512 + 4 pages (worst case for PAE)
- *
- * Modulo rounding, each megabyte assigned here requires a kilobyte of
- * memory, which is currently unreclaimed.
- *
- * This should be a multiple of a page.
- *
- * KERNEL_IMAGE_SIZE should be greater than pa(_end)
- * and small than max_low_pfn, otherwise will waste some page table entries
- */
-
-#if PTRS_PER_PMD > 1
-#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
-#else
-#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
-#endif
 
 #define SIZEOF_PTREGS 17*4
 
 /*
- * Number of possible pages in the lowmem region.
- *
- * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a
- * gas warning about overflowing shift count when gas has been compiled
- * with only a host target support using a 32-bit type for internal
- * representation.
- */
-LOWMEM_PAGES = (((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)
-
-/* Enough space to fit pagetables for the low memory linear map */
-MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
-
-/*
  * Worst-case size of the kernel mapping we need to make:
  * a relocatable kernel can live anywhere in lowmem, so we need to be able
  * to map all of lowmem.
@@ -160,90 +127,15 @@ ENTRY(startup_32)
 	call load_ucode_bsp
 #endif
 
-/*
- * Initialize page tables.  This creates a PDE and a set of page
- * tables, which are located immediately beyond __brk_base.  The variable
- * _brk_end is set up to point to the first "safe" location.
- * Mappings are created both at virtual address 0 (identity mapping)
- * and PAGE_OFFSET for up to _end.
- */
-#ifdef CONFIG_X86_PAE
-
-	/*
-	 * In PAE mode initial_page_table is statically defined to contain
-	 * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
-	 * entries). The identity mapping is handled by pointing two PGD entries
-	 * to the first kernel PMD.
-	 *
-	 * Note the upper half of each PMD or PTE are always zero at this stage.
-	 */
-
-#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
-
-	xorl %ebx,%ebx				/* %ebx is kept at zero */
-
-	movl $pa(__brk_base), %edi
-	movl $pa(initial_pg_pmd), %edx
-	movl $PTE_IDENT_ATTR, %eax
-10:
-	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PMD entry */
-	movl %ecx,(%edx)			/* Store PMD entry */
-						/* Upper half already zero */
-	addl $8,%edx
-	movl $512,%ecx
-11:
-	stosl
-	xchgl %eax,%ebx
-	stosl
-	xchgl %eax,%ebx
-	addl $0x1000,%eax
-	loop 11b
-
-	/*
-	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
-	 */
-	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
-	cmpl %ebp,%eax
-	jb 10b
-1:
-	addl $__PAGE_OFFSET, %edi
-	movl %edi, pa(_brk_end)
-	shrl $12, %eax
-	movl %eax, pa(max_pfn_mapped)
+	/* Create early pagetables. */
+	call  mk_early_pgtbl_32
 
 	/* Do early initialization of the fixmap area */
 	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+#ifdef  CONFIG_X86_PAE
+#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
 	movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8)
-#else	/* Not PAE */
-
-page_pde_offset = (__PAGE_OFFSET >> 20);
-
-	movl $pa(__brk_base), %edi
-	movl $pa(initial_page_table), %edx
-	movl $PTE_IDENT_ATTR, %eax
-10:
-	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PDE entry */
-	movl %ecx,(%edx)			/* Store identity PDE entry */
-	movl %ecx,page_pde_offset(%edx)		/* Store kernel PDE entry */
-	addl $4,%edx
-	movl $1024, %ecx
-11:
-	stosl
-	addl $0x1000,%eax
-	loop 11b
-	/*
-	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
-	 */
-	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
-	cmpl %ebp,%eax
-	jb 10b
-	addl $__PAGE_OFFSET, %edi
-	movl %edi, pa(_brk_end)
-	shrl $12, %eax
-	movl %eax, pa(max_pfn_mapped)
-
-	/* Do early initialization of the fixmap area */
-	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+#else
 	movl %eax,pa(initial_page_table+0xffc)
 #endif
 
@@ -666,6 +558,7 @@ ENTRY(setup_once_ref)
 __PAGE_ALIGNED_BSS
 	.align PAGE_SIZE
 #ifdef CONFIG_X86_PAE
+.globl initial_pg_pmd
 initial_pg_pmd:
 	.fill 1024*KPMDS,4,0
 #else
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 85e87b46c318..dc6ba5bda9fc 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -352,6 +352,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
 	} else {
 		struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
 
+		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
 		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
 		disable_irq(hdev->irq);
 		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index cb9c1ed1d391..f73f475d0573 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -132,10 +132,8 @@ int sched_set_itmt_support(void)
 
 	sysctl_sched_itmt_enabled = 1;
 
-	if (sysctl_sched_itmt_enabled) {
-		x86_topology_update = true;
-		rebuild_sched_domains();
-	}
+	x86_topology_update = true;
+	rebuild_sched_domains();
 
 	mutex_unlock(&itmt_update_mutex);
 
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index fc25f698d792..c37bd0f39c70 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -32,8 +32,7 @@ static void bug_at(unsigned char *ip, int line)
 	 * Something went wrong. Crash the box, as something could be
 	 * corrupting the kernel.
 	 */
-	pr_warning("Unexpected op at %pS [%p] (%02x %02x %02x %02x %02x) %s:%d\n",
-	       ip, ip, ip[0], ip[1], ip[2], ip[3], ip[4], __FILE__, line);
+	pr_crit("jump_label: Fatal kernel bug, unexpected op at %pS [%p] (%5ph) %d\n", ip, ip, ip, line);
 	BUG();
 }
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index eb3509338ae0..520b8dfe1640 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -745,7 +745,7 @@ __visible __used void *trampoline_handler(struct pt_regs *regs)
 	 *	 will be the real return address, and all the rest will
 	 *	 point to kretprobe_trampoline.
 	 */
-	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
+	hlist_for_each_entry(ri, head, hlist) {
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 36bc66416021..099fcba4981d 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -620,18 +620,4 @@ void __init kvm_spinlock_init(void)
 	}
 }
 
-static __init int kvm_spinlock_init_jump(void)
-{
-	if (!kvm_para_available())
-		return 0;
-	if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
-		return 0;
-
-	static_key_slow_inc(&paravirt_ticketlocks_enabled);
-	printk(KERN_INFO "KVM setup paravirtual spinlock\n");
-
-	return 0;
-}
-early_initcall(kvm_spinlock_init_jump);
-
 #endif	/* CONFIG_PARAVIRT_SPINLOCKS */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2a5cafdf8808..542710b99f52 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -107,12 +107,12 @@ static inline void kvm_sched_clock_init(bool stable)
 {
 	if (!stable) {
 		pv_time_ops.sched_clock = kvm_clock_read;
+		clear_sched_clock_stable();
 		return;
 	}
 
 	kvm_sched_clock_offset = kvm_clock_read();
 	pv_time_ops.sched_clock = kvm_sched_clock_read;
-	set_sched_clock_stable();
 
 	printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
 			kvm_sched_clock_offset);
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 6d4bf812af45..6259327f3454 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -42,6 +42,3 @@ struct pv_lock_ops pv_lock_ops = {
 #endif /* SMP */
 };
 EXPORT_SYMBOL(pv_lock_ops);
-
-struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE;
-EXPORT_SYMBOL(paravirt_ticketlocks_enabled);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 5d400ba1349d..d47517941bbc 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -296,7 +296,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 
 	/* were we called with bad_dma_address? */
 	badend = DMA_ERROR_CODE + (EMERGENCY_PAGES * PAGE_SIZE);
-	if (unlikely((dma_addr >= DMA_ERROR_CODE) && (dma_addr < badend))) {
+	if (unlikely(dma_addr < badend)) {
 		WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA "
 		       "address 0x%Lx\n", dma_addr);
 		return;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 4cfba947d774..69780edf0dde 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1176,6 +1176,20 @@ void __init setup_arch(char **cmdline_p)
 	/* Allocate bigger log buffer */
 	setup_log_buf(1);
 
+	if (efi_enabled(EFI_BOOT)) {
+		switch (boot_params.secure_boot) {
+		case efi_secureboot_mode_disabled:
+			pr_info("Secure boot disabled\n");
+			break;
+		case efi_secureboot_mode_enabled:
+			pr_info("Secure boot enabled\n");
+			break;
+		default:
+			pr_info("Secure boot could not be determined\n");
+			break;
+		}
+	}
+
 	reserve_initrd();
 
 	acpi_table_upgrade();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 46732dc3b73c..a0d38685f7df 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -433,9 +433,15 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
-		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
-		    c->cpu_core_id == o->cpu_core_id)
-			return topology_sane(c, o, "smt");
+		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
+			if (c->cpu_core_id == o->cpu_core_id)
+				return topology_sane(c, o, "smt");
+
+			if ((c->cu_id != 0xff) &&
+			    (o->cu_id != 0xff) &&
+			    (c->cu_id == o->cu_id))
+				return topology_sane(c, o, "smt");
+		}
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
 		   c->cpu_core_id == o->cpu_core_id) {
@@ -1341,8 +1347,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	pr_info("CPU0: ");
 	print_cpu_info(&cpu_data(0));
 
-	if (is_uv_system())
-		uv_system_init();
+	uv_system_init();
 
 	set_mtrr_aps_delayed_init();
 
diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c
deleted file mode 100644
index a3b875c9e6af..000000000000
--- a/arch/x86/kernel/test_nx.c
+++ /dev/null
@@ -1,173 +0,0 @@
-/*
- * test_nx.c: functional test for NX functionality
- *
- * (C) Copyright 2008 Intel Corporation
- * Author: Arjan van de Ven <arjan@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-#include <linux/module.h>
-#include <linux/sort.h>
-#include <linux/slab.h>
-
-#include <linux/uaccess.h>
-#include <asm/asm.h>
-
-extern int rodata_test_data;
-
-/*
- * This file checks 4 things:
- * 1) Check if the stack is not executable
- * 2) Check if kmalloc memory is not executable
- * 3) Check if the .rodata section is not executable
- * 4) Check if the .data section of a module is not executable
- *
- * To do this, the test code tries to execute memory in stack/kmalloc/etc,
- * and then checks if the expected trap happens.
- *
- * Sadly, this implies having a dynamic exception handling table entry.
- * ... which can be done (and will make Rusty cry)... but it can only
- * be done in a stand-alone module with only 1 entry total.
- * (otherwise we'd have to sort and that's just too messy)
- */
-
-
-
-/*
- * We want to set up an exception handling point on our stack,
- * which means a variable value. This function is rather dirty
- * and walks the exception table of the module, looking for a magic
- * marker and replaces it with a specific function.
- */
-static void fudze_exception_table(void *marker, void *new)
-{
-	struct module *mod = THIS_MODULE;
-	struct exception_table_entry *extable;
-
-	/*
-	 * Note: This module has only 1 exception table entry,
-	 * so searching and sorting is not needed. If that changes,
-	 * this would be the place to search and re-sort the exception
-	 * table.
-	 */
-	if (mod->num_exentries > 1) {
-		printk(KERN_ERR "test_nx: too many exception table entries!\n");
-		printk(KERN_ERR "test_nx: test results are not reliable.\n");
-		return;
-	}
-	extable = (struct exception_table_entry *)mod->extable;
-	extable[0].insn = (unsigned long)new;
-}
-
-
-/*
- * exception tables get their symbols translated so we need
- * to use a fake function to put in there, which we can then
- * replace at runtime.
- */
-void foo_label(void);
-
-/*
- * returns 0 for not-executable, negative for executable
- *
- * Note: we cannot allow this function to be inlined, because
- * that would give us more than 1 exception table entry.
- * This in turn would break the assumptions above.
- */
-static noinline int test_address(void *address)
-{
-	unsigned long result;
-
-	/* Set up an exception table entry for our address */
-	fudze_exception_table(&foo_label, address);
-	result = 1;
-	asm volatile(
-		"foo_label:\n"
-		"0:	call *%[fake_code]\n"
-		"1:\n"
-		".section .fixup,\"ax\"\n"
-		"2:	mov %[zero], %[rslt]\n"
-		"	ret\n"
-		".previous\n"
-		_ASM_EXTABLE(0b,2b)
-		: [rslt] "=r" (result)
-		: [fake_code] "r" (address), [zero] "r" (0UL), "0" (result)
-	);
-	/* change the exception table back for the next round */
-	fudze_exception_table(address, &foo_label);
-
-	if (result)
-		return -ENODEV;
-	return 0;
-}
-
-static unsigned char test_data = 0xC3; /* 0xC3 is the opcode for "ret" */
-
-static int test_NX(void)
-{
-	int ret = 0;
-	/* 0xC3 is the opcode for "ret" */
-	char stackcode[] = {0xC3, 0x90, 0 };
-	char *heap;
-
-	test_data = 0xC3;
-
-	printk(KERN_INFO "Testing NX protection\n");
-
-	/* Test 1: check if the stack is not executable */
-	if (test_address(&stackcode)) {
-		printk(KERN_ERR "test_nx: stack was executable\n");
-		ret = -ENODEV;
-	}
-
-
-	/* Test 2: Check if the heap is executable */
-	heap = kmalloc(64, GFP_KERNEL);
-	if (!heap)
-		return -ENOMEM;
-	heap[0] = 0xC3; /* opcode for "ret" */
-
-	if (test_address(heap)) {
-		printk(KERN_ERR "test_nx: heap was executable\n");
-		ret = -ENODEV;
-	}
-	kfree(heap);
-
-	/*
-	 * The following 2 tests currently fail, this needs to get fixed
-	 * Until then, don't run them to avoid too many people getting scared
-	 * by the error message
-	 */
-
-	/* Test 3: Check if the .rodata section is executable */
-	if (rodata_test_data != 0xC3) {
-		printk(KERN_ERR "test_nx: .rodata marker has invalid value\n");
-		ret = -ENODEV;
-	} else if (test_address(&rodata_test_data)) {
-		printk(KERN_ERR "test_nx: .rodata section is executable\n");
-		ret = -ENODEV;
-	}
-
-#if 0
-	/* Test 4: Check if the .data section of a module is executable */
-	if (test_address(&test_data)) {
-		printk(KERN_ERR "test_nx: .data section is executable\n");
-		ret = -ENODEV;
-	}
-
-#endif
-	return ret;
-}
-
-static void test_exit(void)
-{
-}
-
-module_init(test_NX);
-module_exit(test_exit);
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Testcase for the NX infrastructure");
-MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index bf0c6d049080..1dc86ee60a03 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -563,11 +563,9 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
 	 * as we may switch to the interrupt stack.
 	 */
 	debug_stack_usage_inc();
-	preempt_disable();
 	cond_local_irq_enable(regs);
 	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
 	cond_local_irq_disable(regs);
-	preempt_enable_no_resched();
 	debug_stack_usage_dec();
 exit:
 	ist_exit(regs);
@@ -742,14 +740,12 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	debug_stack_usage_inc();
 
 	/* It's safe to allow irq's after DR6 has been saved */
-	preempt_disable();
 	cond_local_irq_enable(regs);
 
 	if (v8086_mode(regs)) {
 		handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
 					X86_TRAP_DB);
 		cond_local_irq_disable(regs);
-		preempt_enable_no_resched();
 		debug_stack_usage_dec();
 		goto exit;
 	}
@@ -769,7 +765,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
 		send_sigtrap(tsk, regs, error_code, si_code);
 	cond_local_irq_disable(regs);
-	preempt_enable_no_resched();
 	debug_stack_usage_dec();
 
 exit:
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e41af597aed8..2724dc82f992 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1107,6 +1107,16 @@ static u64 read_tsc(struct clocksource *cs)
 	return (u64)rdtsc_ordered();
 }
 
+static void tsc_cs_mark_unstable(struct clocksource *cs)
+{
+	if (tsc_unstable)
+		return;
+	tsc_unstable = 1;
+	clear_sched_clock_stable();
+	disable_sched_clock_irqtime();
+	pr_info("Marking TSC unstable due to clocksource watchdog\n");
+}
+
 /*
  * .mask MUST be CLOCKSOURCE_MASK(64). See comment above read_tsc()
  */
@@ -1119,6 +1129,7 @@ static struct clocksource clocksource_tsc = {
 				  CLOCK_SOURCE_MUST_VERIFY,
 	.archdata               = { .vclock_mode = VCLOCK_TSC },
 	.resume			= tsc_resume,
+	.mark_unstable		= tsc_cs_mark_unstable,
 };
 
 void mark_tsc_unstable(char *reason)
@@ -1356,6 +1367,9 @@ void __init tsc_init(void)
 		(unsigned long)cpu_khz / 1000,
 		(unsigned long)cpu_khz % 1000);
 
+	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
+	tsc_store_and_check_tsc_adjust(true);
+
 	/*
 	 * Secondary CPUs do not run through tsc_init(), so set up
 	 * all the scale factors for all CPUs, assuming the same
@@ -1386,8 +1400,6 @@ void __init tsc_init(void)
 
 	if (unsynchronized_tsc())
 		mark_tsc_unstable("TSCs unsynchronized");
-	else
-		tsc_store_and_check_tsc_adjust(true);
 
 	check_system_tsc_reliable();
 
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index d0db011051a5..728f75378475 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -286,13 +286,6 @@ void check_tsc_sync_source(int cpu)
 	if (unsynchronized_tsc())
 		return;
 
-	if (tsc_clocksource_reliable) {
-		if (cpu == (nr_cpu_ids-1) || system_state != SYSTEM_BOOTING)
-			pr_info(
-			"Skipped synchronization checks as TSC is reliable.\n");
-		return;
-	}
-
 	/*
 	 * Set the maximum number of test runs to
 	 *  1 if the CPU does not provide the TSC_ADJUST MSR
@@ -380,14 +373,19 @@ void check_tsc_sync_target(void)
 	int cpus = 2;
 
 	/* Also aborts if there is no TSC. */
-	if (unsynchronized_tsc() || tsc_clocksource_reliable)
+	if (unsynchronized_tsc())
 		return;
 
 	/*
 	 * Store, verify and sanitize the TSC adjust register. If
 	 * successful skip the test.
+	 *
+	 * The test is also skipped when the TSC is marked reliable. This
+	 * is true for SoCs which have no fallback clocksource. On these
+	 * SoCs the TSC is frequency synchronized, but still the TSC ADJUST
+	 * register might have been wreckaged by the BIOS..
 	 */
-	if (tsc_store_and_check_tsc_adjust(false)) {
+	if (tsc_store_and_check_tsc_adjust(false) || tsc_clocksource_reliable) {
 		atomic_inc(&skip_test);
 		return;
 	}
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index ec5d7545e6dc..0442d98367ae 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -160,11 +160,12 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 
 static void mark_screen_rdonly(struct mm_struct *mm)
 {
+	struct vm_area_struct *vma;
+	spinlock_t *ptl;
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
-	spinlock_t *ptl;
 	int i;
 
 	down_write(&mm->mmap_sem);
@@ -177,7 +178,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
 	pmd = pmd_offset(pud, 0xA0000);
 
 	if (pmd_trans_huge(*pmd)) {
-		struct vm_area_struct *vma = find_vma(mm, 0xA0000);
+		vma = find_vma(mm, 0xA0000);
 		split_huge_pmd(vma, pmd, 0xA0000);
 	}
 	if (pmd_none_or_clear_bad(pmd))
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 1572c35b4f1a..2ecd7dab4631 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -964,10 +964,11 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
 /* Calculate cpu time spent by current task in 100ns units */
 static u64 current_task_runtime_100ns(void)
 {
-	cputime_t utime, stime;
+	u64 utime, stime;
 
 	task_cputime_adjusted(current, &utime, &stime);
-	return div_u64(cputime_to_nsecs(utime + stime), 100);
+
+	return div_u64(utime + stime, 100);
 }
 
 static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d153be8929a6..e52c9088660f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3182,6 +3182,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
 	memcpy(dest, xsave, XSAVE_HDR_OFFSET);
 
 	/* Set XSTATE_BV */
+	xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
 	*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
 
 	/*
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 073d1f1a620b..a8e91ae89fb3 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -156,13 +156,13 @@ EXPORT_SYMBOL(__delay);
 
 inline void __const_udelay(unsigned long xloops)
 {
+	unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy;
 	int d0;
 
 	xloops *= 4;
 	asm("mull %%edx"
 		:"=d" (xloops), "=&a" (d0)
-		:"1" (xloops), "0"
-		(this_cpu_read(cpu_info.loops_per_jiffy) * (HZ/4)));
+		:"1" (xloops), "0" (lpj * (HZ / 4)));
 
 	__delay(++xloops);
 }
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ea9c49adaa1f..58b5bee7ea27 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -15,8 +15,10 @@
 #include <linux/debugfs.h>
 #include <linux/mm.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/seq_file.h>
 
+#include <asm/kasan.h>
 #include <asm/pgtable.h>
 
 /*
@@ -50,6 +52,10 @@ enum address_markers_idx {
 	LOW_KERNEL_NR,
 	VMALLOC_START_NR,
 	VMEMMAP_START_NR,
+#ifdef CONFIG_KASAN
+	KASAN_SHADOW_START_NR,
+	KASAN_SHADOW_END_NR,
+#endif
 # ifdef CONFIG_X86_ESPFIX64
 	ESPFIX_START_NR,
 # endif
@@ -75,6 +81,10 @@ static struct addr_marker address_markers[] = {
 	{ 0/* PAGE_OFFSET */,   "Low Kernel Mapping" },
 	{ 0/* VMALLOC_START */, "vmalloc() Area" },
 	{ 0/* VMEMMAP_START */, "Vmemmap" },
+#ifdef CONFIG_KASAN
+	{ KASAN_SHADOW_START,	"KASAN shadow" },
+	{ KASAN_SHADOW_END,	"KASAN shadow end" },
+#endif
 # ifdef CONFIG_X86_ESPFIX64
 	{ ESPFIX_BASE_ADDR,	"ESPfix Area", 16 },
 # endif
@@ -326,18 +336,31 @@ static void walk_pmd_level(struct seq_file *m, struct pg_state *st, pud_t addr,
 
 #if PTRS_PER_PUD > 1
 
+/*
+ * This is an optimization for CONFIG_DEBUG_WX=y + CONFIG_KASAN=y
+ * KASAN fills page tables with the same values. Since there is no
+ * point in checking page table more than once we just skip repeated
+ * entries. This saves us dozens of seconds during boot.
+ */
+static bool pud_already_checked(pud_t *prev_pud, pud_t *pud, bool checkwx)
+{
+	return checkwx && prev_pud && (pud_val(*prev_pud) == pud_val(*pud));
+}
+
 static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 							unsigned long P)
 {
 	int i;
 	pud_t *start;
 	pgprotval_t prot;
+	pud_t *prev_pud = NULL;
 
 	start = (pud_t *) pgd_page_vaddr(addr);
 
 	for (i = 0; i < PTRS_PER_PUD; i++) {
 		st->current_address = normalize_addr(P + i * PUD_LEVEL_MULT);
-		if (!pud_none(*start)) {
+		if (!pud_none(*start) &&
+		    !pud_already_checked(prev_pud, start, st->check_wx)) {
 			if (pud_large(*start) || !pud_present(*start)) {
 				prot = pud_flags(*start);
 				note_page(m, st, __pgprot(prot), 2);
@@ -348,6 +371,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 		} else
 			note_page(m, st, __pgprot(0), 2);
 
+		prev_pud = start;
 		start++;
 	}
 }
@@ -406,6 +430,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 		} else
 			note_page(m, &st, __pgprot(0), 1);
 
+		cond_resched();
 		start++;
 	}
 
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 5a287e523eab..28d42130243c 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -214,7 +214,20 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache,
 			    int in_flags, struct page **pages)
 {
 	unsigned int i, level;
+#ifdef CONFIG_PREEMPT
+	/*
+	 * Avoid wbinvd() because it causes latencies on all CPUs,
+	 * regardless of any CPU isolation that may be in effect.
+	 *
+	 * This should be extended for CAT enabled systems independent of
+	 * PREEMPT because wbinvd() does not respect the CAT partitions and
+	 * this is exposed to unpriviledged users through the graphics
+	 * subsystem.
+	 */
+	unsigned long do_wbinvd = 0;
+#else
 	unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
+#endif
 
 	BUG_ON(irqs_disabled());
 
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 159b52ccd600..d76485b22824 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -47,7 +47,7 @@ static u64 get_subtree_max_end(struct rb_node *node)
 {
 	u64 ret = 0;
 	if (node) {
-		struct memtype *data = container_of(node, struct memtype, rb);
+		struct memtype *data = rb_entry(node, struct memtype, rb);
 		ret = data->subtree_max_end;
 	}
 	return ret;
@@ -79,7 +79,7 @@ static struct memtype *memtype_rb_lowest_match(struct rb_root *root,
 	struct memtype *last_lower = NULL;
 
 	while (node) {
-		struct memtype *data = container_of(node, struct memtype, rb);
+		struct memtype *data = rb_entry(node, struct memtype, rb);
 
 		if (get_subtree_max_end(node->rb_left) > start) {
 			/* Lowest overlap if any must be on left side */
@@ -121,7 +121,7 @@ static struct memtype *memtype_rb_match(struct rb_root *root,
 
 		node = rb_next(&match->rb);
 		if (node)
-			match = container_of(node, struct memtype, rb);
+			match = rb_entry(node, struct memtype, rb);
 		else
 			match = NULL;
 	}
@@ -150,7 +150,7 @@ static int memtype_rb_check_conflict(struct rb_root *root,
 
 	node = rb_next(&match->rb);
 	while (node) {
-		match = container_of(node, struct memtype, rb);
+		match = rb_entry(node, struct memtype, rb);
 
 		if (match->start >= end) /* Checked all possible matches */
 			goto success;
@@ -181,7 +181,7 @@ static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
 	struct rb_node *parent = NULL;
 
 	while (*node) {
-		struct memtype *data = container_of(*node, struct memtype, rb);
+		struct memtype *data = rb_entry(*node, struct memtype, rb);
 
 		parent = *node;
 		if (data->subtree_max_end < newdata->end)
@@ -270,7 +270,7 @@ int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos)
 	}
 
 	if (node) { /* pos == i */
-		struct memtype *this = container_of(node, struct memtype, rb);
+		struct memtype *this = rb_entry(node, struct memtype, rb);
 		*out = *this;
 		return 0;
 	} else {
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index 6aad870e8962..04ca8764f0c0 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -19,8 +19,7 @@
 #include <linux/efi.h>
 #include <linux/efi-bgrt.h>
 
-struct acpi_table_bgrt *bgrt_tab;
-void *__initdata bgrt_image;
+struct acpi_table_bgrt bgrt_tab;
 size_t __initdata bgrt_image_size;
 
 struct bmp_header {
@@ -28,66 +27,58 @@ struct bmp_header {
 	u32 size;
 } __packed;
 
-void __init efi_bgrt_init(void)
+void __init efi_bgrt_init(struct acpi_table_header *table)
 {
-	acpi_status status;
 	void *image;
 	struct bmp_header bmp_header;
+	struct acpi_table_bgrt *bgrt = &bgrt_tab;
 
 	if (acpi_disabled)
 		return;
 
-	status = acpi_get_table("BGRT", 0,
-	                        (struct acpi_table_header **)&bgrt_tab);
-	if (ACPI_FAILURE(status))
-		return;
-
-	if (bgrt_tab->header.length < sizeof(*bgrt_tab)) {
+	if (table->length < sizeof(bgrt_tab)) {
 		pr_notice("Ignoring BGRT: invalid length %u (expected %zu)\n",
-		       bgrt_tab->header.length, sizeof(*bgrt_tab));
+		       table->length, sizeof(bgrt_tab));
 		return;
 	}
-	if (bgrt_tab->version != 1) {
+	*bgrt = *(struct acpi_table_bgrt *)table;
+	if (bgrt->version != 1) {
 		pr_notice("Ignoring BGRT: invalid version %u (expected 1)\n",
-		       bgrt_tab->version);
-		return;
+		       bgrt->version);
+		goto out;
 	}
-	if (bgrt_tab->status & 0xfe) {
+	if (bgrt->status & 0xfe) {
 		pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n",
-		       bgrt_tab->status);
-		return;
+		       bgrt->status);
+		goto out;
 	}
-	if (bgrt_tab->image_type != 0) {
+	if (bgrt->image_type != 0) {
 		pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n",
-		       bgrt_tab->image_type);
-		return;
+		       bgrt->image_type);
+		goto out;
 	}
-	if (!bgrt_tab->image_address) {
+	if (!bgrt->image_address) {
 		pr_notice("Ignoring BGRT: null image address\n");
-		return;
+		goto out;
 	}
 
-	image = memremap(bgrt_tab->image_address, sizeof(bmp_header), MEMREMAP_WB);
+	image = early_memremap(bgrt->image_address, sizeof(bmp_header));
 	if (!image) {
 		pr_notice("Ignoring BGRT: failed to map image header memory\n");
-		return;
+		goto out;
 	}
 
 	memcpy(&bmp_header, image, sizeof(bmp_header));
-	memunmap(image);
+	early_memunmap(image, sizeof(bmp_header));
 	if (bmp_header.id != 0x4d42) {
 		pr_notice("Ignoring BGRT: Incorrect BMP magic number 0x%x (expected 0x4d42)\n",
 			bmp_header.id);
-		return;
+		goto out;
 	}
 	bgrt_image_size = bmp_header.size;
+	efi_mem_reserve(bgrt->image_address, bgrt_image_size);
 
-	bgrt_image = memremap(bgrt_tab->image_address, bmp_header.size, MEMREMAP_WB);
-	if (!bgrt_image) {
-		pr_notice("Ignoring BGRT: failed to map image memory\n");
-		bgrt_image = NULL;
-		return;
-	}
-
-	efi_mem_reserve(bgrt_tab->image_address, bgrt_image_size);
+	return;
+out:
+	memset(bgrt, 0, sizeof(bgrt_tab));
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 274dfc481849..565dff3c9a12 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -542,11 +542,6 @@ void __init efi_init(void)
 		efi_print_memmap();
 }
 
-void __init efi_late_init(void)
-{
-	efi_bgrt_init();
-}
-
 void __init efi_set_executable(efi_memory_desc_t *md, bool executable)
 {
 	u64 addr, npages;
@@ -960,6 +955,11 @@ static void __init __efi_enter_virtual_mode(void)
 		return;
 	}
 
+	if (efi_enabled(EFI_DBG)) {
+		pr_info("EFI runtime memory map:\n");
+		efi_print_memmap();
+	}
+
 	BUG_ON(!efi.systab);
 
 	if (efi_setup_page_tables(pa, 1 << pg_shift)) {
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 319148bd4b05..a4695da42d77 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -269,6 +269,22 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 	efi_scratch.use_pgd = true;
 
 	/*
+	 * Certain firmware versions are way too sentimential and still believe
+	 * they are exclusive and unquestionable owners of the first physical page,
+	 * even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY
+	 * (but then write-access it later during SetVirtualAddressMap()).
+	 *
+	 * Create a 1:1 mapping for this page, to avoid triple faults during early
+	 * boot with such firmware. We are free to hand this page to the BIOS,
+	 * as trim_bios_range() will reserve the first page and isolate it away
+	 * from memory allocators anyway.
+	 */
+	if (kernel_map_pages_in_pgd(pgd, 0x0, 0x0, 1, _PAGE_RW)) {
+		pr_err("Failed to create 1:1 mapping for the first page!\n");
+		return 1;
+	}
+
+	/*
 	 * When making calls to the firmware everything needs to be 1:1
 	 * mapped and addressable with 32-bit pointers. Map the kernel
 	 * text and allocate a new stack because we can't rely on the
@@ -398,10 +414,44 @@ void __init parse_efi_setup(u64 phys_addr, u32 data_len)
 	efi_setup = phys_addr + sizeof(struct setup_data);
 }
 
-void __init efi_runtime_update_mappings(void)
+static int __init efi_update_mappings(efi_memory_desc_t *md, unsigned long pf)
 {
 	unsigned long pfn;
 	pgd_t *pgd = efi_pgd;
+	int err1, err2;
+
+	/* Update the 1:1 mapping */
+	pfn = md->phys_addr >> PAGE_SHIFT;
+	err1 = kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf);
+	if (err1) {
+		pr_err("Error while updating 1:1 mapping PA 0x%llx -> VA 0x%llx!\n",
+			   md->phys_addr, md->virt_addr);
+	}
+
+	err2 = kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf);
+	if (err2) {
+		pr_err("Error while updating VA mapping PA 0x%llx -> VA 0x%llx!\n",
+			   md->phys_addr, md->virt_addr);
+	}
+
+	return err1 || err2;
+}
+
+static int __init efi_update_mem_attr(struct mm_struct *mm, efi_memory_desc_t *md)
+{
+	unsigned long pf = 0;
+
+	if (md->attribute & EFI_MEMORY_XP)
+		pf |= _PAGE_NX;
+
+	if (!(md->attribute & EFI_MEMORY_RO))
+		pf |= _PAGE_RW;
+
+	return efi_update_mappings(md, pf);
+}
+
+void __init efi_runtime_update_mappings(void)
+{
 	efi_memory_desc_t *md;
 
 	if (efi_enabled(EFI_OLD_MEMMAP)) {
@@ -410,6 +460,24 @@ void __init efi_runtime_update_mappings(void)
 		return;
 	}
 
+	/*
+	 * Use the EFI Memory Attribute Table for mapping permissions if it
+	 * exists, since it is intended to supersede EFI_PROPERTIES_TABLE.
+	 */
+	if (efi_enabled(EFI_MEM_ATTR)) {
+		efi_memattr_apply_permissions(NULL, efi_update_mem_attr);
+		return;
+	}
+
+	/*
+	 * EFI_MEMORY_ATTRIBUTES_TABLE is intended to replace
+	 * EFI_PROPERTIES_TABLE. So, use EFI_PROPERTIES_TABLE to update
+	 * permissions only if EFI_MEMORY_ATTRIBUTES_TABLE is not
+	 * published by the firmware. Even if we find a buggy implementation of
+	 * EFI_MEMORY_ATTRIBUTES_TABLE, don't fall back to
+	 * EFI_PROPERTIES_TABLE, because of the same reason.
+	 */
+
 	if (!efi_enabled(EFI_NX_PE_DATA))
 		return;
 
@@ -430,15 +498,7 @@ void __init efi_runtime_update_mappings(void)
 			(md->type != EFI_RUNTIME_SERVICES_CODE))
 			pf |= _PAGE_RW;
 
-		/* Update the 1:1 mapping */
-		pfn = md->phys_addr >> PAGE_SHIFT;
-		if (kernel_map_pages_in_pgd(pgd, pfn, md->phys_addr, md->num_pages, pf))
-			pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
-				   md->phys_addr, md->virt_addr);
-
-		if (kernel_map_pages_in_pgd(pgd, pfn, md->virt_addr, md->num_pages, pf))
-			pr_warn("Error mapping PA 0x%llx -> VA 0x%llx!\n",
-				   md->phys_addr, md->virt_addr);
+		efi_update_mappings(md, pf);
 	}
 }
 
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
index 90e4f2a6625b..a7dbec4dce27 100644
--- a/arch/x86/platform/intel-mid/device_libs/Makefile
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -5,14 +5,12 @@ obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI)) += platform_mrfld_sd.o
 # WiFi
 obj-$(subst m,y,$(CONFIG_BRCMFMAC_SDIO)) += platform_bcm43xx.o
 # IPC Devices
-obj-y += platform_ipc.o
 obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic.o
 obj-$(subst m,y,$(CONFIG_SND_MFLD_MACHINE)) += platform_msic_audio.o
 obj-$(subst m,y,$(CONFIG_GPIO_MSIC)) += platform_msic_gpio.o
 obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_ocd.o
 obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_battery.o
 obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_msic_power_btn.o
-obj-$(subst m,y,$(CONFIG_GPIO_INTEL_PMIC)) += platform_pmic_gpio.o
 obj-$(subst m,y,$(CONFIG_INTEL_MFLD_THERMAL)) += platform_msic_thermal.o
 # SPI Devices
 obj-$(subst m,y,$(CONFIG_SPI_SPIDEV)) += platform_mrfld_spidev.o
@@ -28,4 +26,5 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o
 obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
 # MISC Devices
 obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
+obj-$(subst m,y,$(CONFIG_RTC_DRV_CMOS)) += platform_mrfld_rtc.o
 obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
index 52534ec29765..74283875c7e8 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
@@ -32,6 +32,9 @@ static struct gpio_keys_button gpio_button[] = {
 	{SW_LID,		-1, 1, "lid_switch",	EV_SW,  0, 20},
 	{KEY_VOLUMEUP,		-1, 1, "vol_up",	EV_KEY, 0, 20},
 	{KEY_VOLUMEDOWN,	-1, 1, "vol_down",	EV_KEY, 0, 20},
+	{KEY_MUTE,		-1, 1, "mute_enable",	EV_KEY, 0, 20},
+	{KEY_VOLUMEUP,		-1, 1, "volume_up",	EV_KEY, 0, 20},
+	{KEY_VOLUMEDOWN,	-1, 1, "volume_down",	EV_KEY, 0, 20},
 	{KEY_CAMERA,		-1, 1, "camera_full",	EV_KEY, 0, 20},
 	{KEY_CAMERA_FOCUS,	-1, 1, "camera_half",	EV_KEY, 0, 20},
 	{SW_KEYPAD_SLIDE,	-1, 1, "MagSw1",	EV_SW,  0, 20},
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.c b/arch/x86/platform/intel-mid/device_libs/platform_ipc.c
deleted file mode 100644
index a84b73d6c4a0..000000000000
--- a/arch/x86/platform/intel-mid/device_libs/platform_ipc.c
+++ /dev/null
@@ -1,68 +0,0 @@
-/*
- * platform_ipc.c: IPC platform library file
- *
- * (C) Copyright 2013 Intel Corporation
- * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/sfi.h>
-#include <linux/gpio.h>
-#include <asm/intel-mid.h>
-#include "platform_ipc.h"
-
-void __init ipc_device_handler(struct sfi_device_table_entry *pentry,
-				struct devs_id *dev)
-{
-	struct platform_device *pdev;
-	void *pdata = NULL;
-	static struct resource res __initdata = {
-		.name = "IRQ",
-		.flags = IORESOURCE_IRQ,
-	};
-
-	pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n",
-		pentry->name, pentry->irq);
-
-	/*
-	 * We need to call platform init of IPC devices to fill misc_pdata
-	 * structure. It will be used in msic_init for initialization.
-	 */
-	if (dev != NULL)
-		pdata = dev->get_platform_data(pentry);
-
-	/*
-	 * On Medfield the platform device creation is handled by the MSIC
-	 * MFD driver so we don't need to do it here.
-	 */
-	if (intel_mid_has_msic())
-		return;
-
-	pdev = platform_device_alloc(pentry->name, 0);
-	if (pdev == NULL) {
-		pr_err("out of memory for SFI platform device '%s'.\n",
-			pentry->name);
-		return;
-	}
-	res.start = pentry->irq;
-	platform_device_add_resources(pdev, &res, 1);
-
-	pdev->dev.platform_data = pdata;
-	intel_scu_device_register(pdev);
-}
-
-static const struct devs_id pmic_audio_dev_id __initconst = {
-	.name = "pmic_audio",
-	.type = SFI_DEV_TYPE_IPC,
-	.delay = 1,
-	.device_handler = &ipc_device_handler,
-};
-
-sfi_device(pmic_audio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.h b/arch/x86/platform/intel-mid/device_libs/platform_ipc.h
deleted file mode 100644
index 79bb09d4f718..000000000000
--- a/arch/x86/platform/intel-mid/device_libs/platform_ipc.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * platform_ipc.h: IPC platform library header file
- *
- * (C) Copyright 2013 Intel Corporation
- * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-#ifndef _PLATFORM_IPC_H_
-#define _PLATFORM_IPC_H_
-
-void __init
-ipc_device_handler(struct sfi_device_table_entry *pentry, struct devs_id *dev);
-
-#endif
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c
new file mode 100644
index 000000000000..3135416df037
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_rtc.c
@@ -0,0 +1,48 @@
+/*
+ * Intel Merrifield legacy RTC initialization file
+ *
+ * (C) Copyright 2017 Intel Corporation
+ *
+ * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#include <linux/init.h>
+
+#include <asm/hw_irq.h>
+#include <asm/intel-mid.h>
+#include <asm/io_apic.h>
+#include <asm/time.h>
+#include <asm/x86_init.h>
+
+static int __init mrfld_legacy_rtc_alloc_irq(void)
+{
+	struct irq_alloc_info info;
+	int ret;
+
+	if (!x86_platform.legacy.rtc)
+		return -ENODEV;
+
+	ioapic_set_alloc_attr(&info, NUMA_NO_NODE, 1, 0);
+	ret = mp_map_gsi_to_irq(RTC_IRQ, IOAPIC_MAP_ALLOC, &info);
+	if (ret < 0) {
+		pr_info("Failed to allocate RTC interrupt. Disabling RTC\n");
+		x86_platform.legacy.rtc = 0;
+		return ret;
+	}
+
+	return 0;
+}
+
+static int __init mrfld_legacy_rtc_init(void)
+{
+	if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+		return -ENODEV;
+
+	return mrfld_legacy_rtc_alloc_irq();
+}
+arch_initcall(mrfld_legacy_rtc_init);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index 3f1f1c77d090..86edd1e941eb 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -28,9 +28,9 @@ static struct platform_device wdt_dev = {
 
 static int tangier_probe(struct platform_device *pdev)
 {
-	int gsi;
 	struct irq_alloc_info info;
 	struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data;
+	int gsi, irq;
 
 	if (!pdata)
 		return -EINVAL;
@@ -38,10 +38,10 @@ static int tangier_probe(struct platform_device *pdev)
 	/* IOAPIC builds identity mapping between GSI and IRQ on MID */
 	gsi = pdata->irq;
 	ioapic_set_alloc_attr(&info, cpu_to_node(0), 1, 0);
-	if (mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info) <= 0) {
-		dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n",
-			 gsi);
-		return -EINVAL;
+	irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC, &info);
+	if (irq < 0) {
+		dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n", gsi);
+		return irq;
 	}
 
 	return 0;
@@ -82,4 +82,4 @@ static int __init register_mid_wdt(void)
 
 	return 0;
 }
-rootfs_initcall(register_mid_wdt);
+arch_initcall(register_mid_wdt);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
index cb3490ecb341..d4dc744dd5a5 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
@@ -20,7 +20,6 @@
 #include <asm/intel-mid.h>
 
 #include "platform_msic.h"
-#include "platform_ipc.h"
 
 static void *msic_audio_platform_data(void *info)
 {
@@ -40,8 +39,8 @@ static const struct devs_id msic_audio_dev_id __initconst = {
 	.name = "msic_audio",
 	.type = SFI_DEV_TYPE_IPC,
 	.delay = 1,
+	.msic = 1,
 	.get_platform_data = &msic_audio_platform_data,
-	.device_handler = &ipc_device_handler,
 };
 
 sfi_device(msic_audio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
index 4f72193939a6..5c3e9919633f 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
@@ -19,7 +19,6 @@
 #include <asm/intel-mid.h>
 
 #include "platform_msic.h"
-#include "platform_ipc.h"
 
 static void __init *msic_battery_platform_data(void *info)
 {
@@ -30,8 +29,8 @@ static const struct devs_id msic_battery_dev_id __initconst = {
 	.name = "msic_battery",
 	.type = SFI_DEV_TYPE_IPC,
 	.delay = 1,
+	.msic = 1,
 	.get_platform_data = &msic_battery_platform_data,
-	.device_handler = &ipc_device_handler,
 };
 
 sfi_device(msic_battery_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
index 70de5b531ba0..9fdb88d460d7 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
@@ -20,7 +20,6 @@
 #include <asm/intel-mid.h>
 
 #include "platform_msic.h"
-#include "platform_ipc.h"
 
 static void __init *msic_gpio_platform_data(void *info)
 {
@@ -41,8 +40,8 @@ static const struct devs_id msic_gpio_dev_id __initconst = {
 	.name = "msic_gpio",
 	.type = SFI_DEV_TYPE_IPC,
 	.delay = 1,
+	.msic = 1,
 	.get_platform_data = &msic_gpio_platform_data,
-	.device_handler = &ipc_device_handler,
 };
 
 sfi_device(msic_gpio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
index 3d7c2011b6cf..7ae37cdbf256 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
@@ -20,7 +20,6 @@
 #include <asm/intel-mid.h>
 
 #include "platform_msic.h"
-#include "platform_ipc.h"
 
 static void __init *msic_ocd_platform_data(void *info)
 {
@@ -42,8 +41,8 @@ static const struct devs_id msic_ocd_dev_id __initconst = {
 	.name = "msic_ocd",
 	.type = SFI_DEV_TYPE_IPC,
 	.delay = 1,
+	.msic = 1,
 	.get_platform_data = &msic_ocd_platform_data,
-	.device_handler = &ipc_device_handler,
 };
 
 sfi_device(msic_ocd_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
index 038f618fbc52..96809b98cf69 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
@@ -18,7 +18,6 @@
 #include <asm/intel-mid.h>
 
 #include "platform_msic.h"
-#include "platform_ipc.h"
 
 static void __init *msic_power_btn_platform_data(void *info)
 {
@@ -29,8 +28,8 @@ static const struct devs_id msic_power_btn_dev_id __initconst = {
 	.name = "msic_power_btn",
 	.type = SFI_DEV_TYPE_IPC,
 	.delay = 1,
+	.msic = 1,
 	.get_platform_data = &msic_power_btn_platform_data,
-	.device_handler = &ipc_device_handler,
 };
 
 sfi_device(msic_power_btn_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
index 114a5755b1e4..3e4167d246cd 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
@@ -19,7 +19,6 @@
 #include <asm/intel-mid.h>
 
 #include "platform_msic.h"
-#include "platform_ipc.h"
 
 static void __init *msic_thermal_platform_data(void *info)
 {
@@ -30,8 +29,8 @@ static const struct devs_id msic_thermal_dev_id __initconst = {
 	.name = "msic_thermal",
 	.type = SFI_DEV_TYPE_IPC,
 	.delay = 1,
+	.msic = 1,
 	.get_platform_data = &msic_thermal_platform_data,
-	.device_handler = &ipc_device_handler,
 };
 
 sfi_device(msic_thermal_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
deleted file mode 100644
index e30cb62e3300..000000000000
--- a/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * platform_pmic_gpio.c: PMIC GPIO platform data initialization file
- *
- * (C) Copyright 2013 Intel Corporation
- * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/scatterlist.h>
-#include <linux/gpio.h>
-#include <linux/init.h>
-#include <linux/sfi.h>
-#include <linux/intel_pmic_gpio.h>
-#include <asm/intel-mid.h>
-
-#include "platform_ipc.h"
-
-static void __init *pmic_gpio_platform_data(void *info)
-{
-	static struct intel_pmic_gpio_platform_data pmic_gpio_pdata;
-	int gpio_base = get_gpio_by_name("pmic_gpio_base");
-
-	if (gpio_base < 0)
-		gpio_base = 64;
-	pmic_gpio_pdata.gpio_base = gpio_base;
-	pmic_gpio_pdata.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
-	pmic_gpio_pdata.gpiointr = 0xffffeff8;
-
-	return &pmic_gpio_pdata;
-}
-
-static const struct devs_id pmic_gpio_spi_dev_id __initconst = {
-	.name = "pmic_gpio",
-	.type = SFI_DEV_TYPE_SPI,
-	.delay = 1,
-	.get_platform_data = &pmic_gpio_platform_data,
-};
-
-static const struct devs_id pmic_gpio_ipc_dev_id __initconst = {
-	.name = "pmic_gpio",
-	.type = SFI_DEV_TYPE_IPC,
-	.delay = 1,
-	.get_platform_data = &pmic_gpio_platform_data,
-	.device_handler = &ipc_device_handler
-};
-
-sfi_device(pmic_gpio_spi_dev_id);
-sfi_device(pmic_gpio_ipc_dev_id);
diff --git a/arch/x86/platform/intel-mid/mrfld.c b/arch/x86/platform/intel-mid/mrfld.c
index e0607c77a1bd..ae7bdeb0e507 100644
--- a/arch/x86/platform/intel-mid/mrfld.c
+++ b/arch/x86/platform/intel-mid/mrfld.c
@@ -91,6 +91,7 @@ static unsigned long __init tangier_calibrate_tsc(void)
 static void __init tangier_arch_setup(void)
 {
 	x86_platform.calibrate_tsc = tangier_calibrate_tsc;
+	x86_platform.legacy.rtc = 1;
 }
 
 /* tangier arch ops */
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 051d264fce2e..19b43e3a9f0f 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -15,7 +15,6 @@
 #include <linux/interrupt.h>
 #include <linux/scatterlist.h>
 #include <linux/sfi.h>
-#include <linux/intel_pmic_gpio.h>
 #include <linux/spi/spi.h>
 #include <linux/i2c.h>
 #include <linux/skbuff.h>
@@ -226,7 +225,7 @@ int get_gpio_by_name(const char *name)
 	return -EINVAL;
 }
 
-void __init intel_scu_device_register(struct platform_device *pdev)
+static void __init intel_scu_ipc_device_register(struct platform_device *pdev)
 {
 	if (ipc_next_dev == MAX_IPCDEVS)
 		pr_err("too many SCU IPC devices");
@@ -335,10 +334,22 @@ static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *pentry,
 
 	pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n",
 		pentry->name, pentry->irq);
+
+	/*
+	 * We need to call platform init of IPC devices to fill misc_pdata
+	 * structure. It will be used in msic_init for initialization.
+	 */
 	pdata = intel_mid_sfi_get_pdata(dev, pentry);
 	if (IS_ERR(pdata))
 		return;
 
+	/*
+	 * On Medfield the platform device creation is handled by the MSIC
+	 * MFD driver so we don't need to do it here.
+	 */
+	if (dev->msic && intel_mid_has_msic())
+		return;
+
 	pdev = platform_device_alloc(pentry->name, 0);
 	if (pdev == NULL) {
 		pr_err("out of memory for SFI platform device '%s'.\n",
@@ -348,7 +359,10 @@ static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *pentry,
 	install_irq_resource(pdev, pentry->irq);
 
 	pdev->dev.platform_data = pdata;
-	platform_device_add(pdev);
+	if (dev->delay)
+		intel_scu_ipc_device_register(pdev);
+	else
+		platform_device_add(pdev);
 }
 
 static void __init sfi_handle_spi_dev(struct sfi_device_table_entry *pentry,
@@ -503,27 +517,23 @@ static int __init sfi_parse_devs(struct sfi_table_header *table)
 		if (!dev)
 			continue;
 
-		if (dev->device_handler) {
-			dev->device_handler(pentry, dev);
-		} else {
-			switch (pentry->type) {
-			case SFI_DEV_TYPE_IPC:
-				sfi_handle_ipc_dev(pentry, dev);
-				break;
-			case SFI_DEV_TYPE_SPI:
-				sfi_handle_spi_dev(pentry, dev);
-				break;
-			case SFI_DEV_TYPE_I2C:
-				sfi_handle_i2c_dev(pentry, dev);
-				break;
-			case SFI_DEV_TYPE_SD:
-				sfi_handle_sd_dev(pentry, dev);
-				break;
-			case SFI_DEV_TYPE_UART:
-			case SFI_DEV_TYPE_HSI:
-			default:
-				break;
-			}
+		switch (pentry->type) {
+		case SFI_DEV_TYPE_IPC:
+			sfi_handle_ipc_dev(pentry, dev);
+			break;
+		case SFI_DEV_TYPE_SPI:
+			sfi_handle_spi_dev(pentry, dev);
+			break;
+		case SFI_DEV_TYPE_I2C:
+			sfi_handle_i2c_dev(pentry, dev);
+			break;
+		case SFI_DEV_TYPE_SD:
+			sfi_handle_sd_dev(pentry, dev);
+			break;
+		case SFI_DEV_TYPE_UART:
+		case SFI_DEV_TYPE_HSI:
+		default:
+			break;
 		}
 	}
 	return 0;
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index 8410e7d0a5b5..9743d0ccfec6 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -45,8 +45,8 @@
  *
  * Handle system-wide NMI events generated by the global 'power nmi' command.
  *
- * Basic operation is to field the NMI interrupt on each cpu and wait
- * until all cpus have arrived into the nmi handler.  If some cpus do not
+ * Basic operation is to field the NMI interrupt on each CPU and wait
+ * until all CPU's have arrived into the nmi handler.  If some CPU's do not
  * make it into the handler, try and force them in with the IPI(NMI) signal.
  *
  * We also have to lessen UV Hub MMR accesses as much as possible as this
@@ -56,7 +56,7 @@
  * To do this we register our primary NMI notifier on the NMI_UNKNOWN
  * chain.  This reduces the number of false NMI calls when the perf
  * tools are running which generate an enormous number of NMIs per
- * second (~4M/s for 1024 cpu threads).  Our secondary NMI handler is
+ * second (~4M/s for 1024 CPU threads).  Our secondary NMI handler is
  * very short as it only checks that if it has been "pinged" with the
  * IPI(NMI) signal as mentioned above, and does not read the UV Hub's MMR.
  *
@@ -65,8 +65,20 @@
 static struct uv_hub_nmi_s **uv_hub_nmi_list;
 
 DEFINE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
-EXPORT_PER_CPU_SYMBOL_GPL(uv_cpu_nmi);
 
+/* UV hubless values */
+#define NMI_CONTROL_PORT	0x70
+#define NMI_DUMMY_PORT		0x71
+#define PAD_OWN_GPP_D_0		0x2c
+#define GPI_NMI_STS_GPP_D_0	0x164
+#define GPI_NMI_ENA_GPP_D_0	0x174
+#define STS_GPP_D_0_MASK	0x1
+#define PAD_CFG_DW0_GPP_D_0	0x4c0
+#define GPIROUTNMI		(1ul << 17)
+#define PCH_PCR_GPIO_1_BASE	0xfdae0000ul
+#define PCH_PCR_GPIO_ADDRESS(offset) (int *)((u64)(pch_base) | (u64)(offset))
+
+static u64 *pch_base;
 static unsigned long nmi_mmr;
 static unsigned long nmi_mmr_clear;
 static unsigned long nmi_mmr_pending;
@@ -100,7 +112,7 @@ static int param_get_local64(char *buffer, const struct kernel_param *kp)
 
 static int param_set_local64(const char *val, const struct kernel_param *kp)
 {
-	/* clear on any write */
+	/* Clear on any write */
 	local64_set((local64_t *)kp->arg, 0);
 	return 0;
 }
@@ -144,16 +156,80 @@ module_param_named(wait_count, uv_nmi_wait_count, int, 0644);
 static int uv_nmi_retry_count = 500;
 module_param_named(retry_count, uv_nmi_retry_count, int, 0644);
 
-/*
- * Valid NMI Actions:
- *  "dump"	- dump process stack for each cpu
- *  "ips"	- dump IP info for each cpu
- *  "kdump"	- do crash dump
- *  "kdb"	- enter KDB (default)
- *  "kgdb"	- enter KGDB
- */
-static char uv_nmi_action[8] = "kdb";
-module_param_string(action, uv_nmi_action, sizeof(uv_nmi_action), 0644);
+static bool uv_pch_intr_enable = true;
+static bool uv_pch_intr_now_enabled;
+module_param_named(pch_intr_enable, uv_pch_intr_enable, bool, 0644);
+
+static bool uv_pch_init_enable = true;
+module_param_named(pch_init_enable, uv_pch_init_enable, bool, 0644);
+
+static int uv_nmi_debug;
+module_param_named(debug, uv_nmi_debug, int, 0644);
+
+#define nmi_debug(fmt, ...)				\
+	do {						\
+		if (uv_nmi_debug)			\
+			pr_info(fmt, ##__VA_ARGS__);	\
+	} while (0)
+
+/* Valid NMI Actions */
+#define	ACTION_LEN	16
+static struct nmi_action {
+	char	*action;
+	char	*desc;
+} valid_acts[] = {
+	{	"kdump",	"do kernel crash dump"			},
+	{	"dump",		"dump process stack for each cpu"	},
+	{	"ips",		"dump Inst Ptr info for each cpu"	},
+	{	"kdb",		"enter KDB (needs kgdboc= assignment)"	},
+	{	"kgdb",		"enter KGDB (needs gdb target remote)"	},
+	{	"health",	"check if CPUs respond to NMI"		},
+};
+typedef char action_t[ACTION_LEN];
+static action_t uv_nmi_action = { "dump" };
+
+static int param_get_action(char *buffer, const struct kernel_param *kp)
+{
+	return sprintf(buffer, "%s\n", uv_nmi_action);
+}
+
+static int param_set_action(const char *val, const struct kernel_param *kp)
+{
+	int i;
+	int n = ARRAY_SIZE(valid_acts);
+	char arg[ACTION_LEN], *p;
+
+	/* (remove possible '\n') */
+	strncpy(arg, val, ACTION_LEN - 1);
+	arg[ACTION_LEN - 1] = '\0';
+	p = strchr(arg, '\n');
+	if (p)
+		*p = '\0';
+
+	for (i = 0; i < n; i++)
+		if (!strcmp(arg, valid_acts[i].action))
+			break;
+
+	if (i < n) {
+		strcpy(uv_nmi_action, arg);
+		pr_info("UV: New NMI action:%s\n", uv_nmi_action);
+		return 0;
+	}
+
+	pr_err("UV: Invalid NMI action:%s, valid actions are:\n", arg);
+	for (i = 0; i < n; i++)
+		pr_err("UV: %-8s - %s\n",
+			valid_acts[i].action, valid_acts[i].desc);
+	return -EINVAL;
+}
+
+static const struct kernel_param_ops param_ops_action = {
+	.get = param_get_action,
+	.set = param_set_action,
+};
+#define param_check_action(name, p) __param_check(name, p, action_t)
+
+module_param_named(action, uv_nmi_action, action, 0644);
 
 static inline bool uv_nmi_action_is(const char *action)
 {
@@ -192,8 +268,200 @@ static inline void uv_local_mmr_clear_nmi(void)
 }
 
 /*
- * If first cpu in on this hub, set hub_nmi "in_nmi" and "owner" values and
- * return true.  If first cpu in on the system, set global "in_nmi" flag.
+ * UV hubless NMI handler functions
+ */
+static inline void uv_reassert_nmi(void)
+{
+	/* (from arch/x86/include/asm/mach_traps.h) */
+	outb(0x8f, NMI_CONTROL_PORT);
+	inb(NMI_DUMMY_PORT);		/* dummy read */
+	outb(0x0f, NMI_CONTROL_PORT);
+	inb(NMI_DUMMY_PORT);		/* dummy read */
+}
+
+static void uv_init_hubless_pch_io(int offset, int mask, int data)
+{
+	int *addr = PCH_PCR_GPIO_ADDRESS(offset);
+	int readd = readl(addr);
+
+	if (mask) {			/* OR in new data */
+		int writed = (readd & ~mask) | data;
+
+		nmi_debug("UV:PCH: %p = %x & %x | %x (%x)\n",
+			addr, readd, ~mask, data, writed);
+		writel(writed, addr);
+	} else if (readd & data) {	/* clear status bit */
+		nmi_debug("UV:PCH: %p = %x\n", addr, data);
+		writel(data, addr);
+	}
+
+	(void)readl(addr);		/* flush write data */
+}
+
+static void uv_nmi_setup_hubless_intr(void)
+{
+	uv_pch_intr_now_enabled = uv_pch_intr_enable;
+
+	uv_init_hubless_pch_io(
+		PAD_CFG_DW0_GPP_D_0, GPIROUTNMI,
+		uv_pch_intr_now_enabled ? GPIROUTNMI : 0);
+
+	nmi_debug("UV:NMI: GPP_D_0 interrupt %s\n",
+		uv_pch_intr_now_enabled ? "enabled" : "disabled");
+}
+
+static struct init_nmi {
+	unsigned int	offset;
+	unsigned int	mask;
+	unsigned int	data;
+} init_nmi[] = {
+	{	/* HOSTSW_OWN_GPP_D_0 */
+	.offset = 0x84,
+	.mask = 0x1,
+	.data = 0x0,	/* ACPI Mode */
+	},
+
+/* Clear status: */
+	{	/* GPI_INT_STS_GPP_D_0 */
+	.offset = 0x104,
+	.mask = 0x0,
+	.data = 0x1,	/* Clear Status */
+	},
+	{	/* GPI_GPE_STS_GPP_D_0 */
+	.offset = 0x124,
+	.mask = 0x0,
+	.data = 0x1,	/* Clear Status */
+	},
+	{	/* GPI_SMI_STS_GPP_D_0 */
+	.offset = 0x144,
+	.mask = 0x0,
+	.data = 0x1,	/* Clear Status */
+	},
+	{	/* GPI_NMI_STS_GPP_D_0 */
+	.offset = 0x164,
+	.mask = 0x0,
+	.data = 0x1,	/* Clear Status */
+	},
+
+/* Disable interrupts: */
+	{	/* GPI_INT_EN_GPP_D_0 */
+	.offset = 0x114,
+	.mask = 0x1,
+	.data = 0x0,	/* Disable interrupt generation */
+	},
+	{	/* GPI_GPE_EN_GPP_D_0 */
+	.offset = 0x134,
+	.mask = 0x1,
+	.data = 0x0,	/* Disable interrupt generation */
+	},
+	{	/* GPI_SMI_EN_GPP_D_0 */
+	.offset = 0x154,
+	.mask = 0x1,
+	.data = 0x0,	/* Disable interrupt generation */
+	},
+	{	/* GPI_NMI_EN_GPP_D_0 */
+	.offset = 0x174,
+	.mask = 0x1,
+	.data = 0x0,	/* Disable interrupt generation */
+	},
+
+/* Setup GPP_D_0 Pad Config: */
+	{	/* PAD_CFG_DW0_GPP_D_0 */
+	.offset = 0x4c0,
+	.mask = 0xffffffff,
+	.data = 0x82020100,
+/*
+ *  31:30 Pad Reset Config (PADRSTCFG): = 2h  # PLTRST# (default)
+ *
+ *  29    RX Pad State Select (RXPADSTSEL): = 0 # Raw RX pad state directly
+ *                                                from RX buffer (default)
+ *
+ *  28    RX Raw Override to '1' (RXRAW1): = 0 # No Override
+ *
+ *  26:25 RX Level/Edge Configuration (RXEVCFG):
+ *      = 0h # Level
+ *      = 1h # Edge
+ *
+ *  23    RX Invert (RXINV): = 0 # No Inversion (signal active high)
+ *
+ *  20    GPIO Input Route IOxAPIC (GPIROUTIOXAPIC):
+ * = 0 # Routing does not cause peripheral IRQ...
+ *     # (we want an NMI not an IRQ)
+ *
+ *  19    GPIO Input Route SCI (GPIROUTSCI): = 0 # Routing does not cause SCI.
+ *  18    GPIO Input Route SMI (GPIROUTSMI): = 0 # Routing does not cause SMI.
+ *  17    GPIO Input Route NMI (GPIROUTNMI): = 1 # Routing can cause NMI.
+ *
+ *  11:10 Pad Mode (PMODE1/0): = 0h = GPIO control the Pad.
+ *   9    GPIO RX Disable (GPIORXDIS):
+ * = 0 # Enable the input buffer (active low enable)
+ *
+ *   8    GPIO TX Disable (GPIOTXDIS):
+ * = 1 # Disable the output buffer; i.e. Hi-Z
+ *
+ *   1 GPIO RX State (GPIORXSTATE): This is the current internal RX pad state..
+ *   0 GPIO TX State (GPIOTXSTATE):
+ * = 0 # (Leave at default)
+ */
+	},
+
+/* Pad Config DW1 */
+	{	/* PAD_CFG_DW1_GPP_D_0 */
+	.offset = 0x4c4,
+	.mask = 0x3c00,
+	.data = 0,	/* Termination = none (default) */
+	},
+};
+
+static void uv_init_hubless_pch_d0(void)
+{
+	int i, read;
+
+	read = *PCH_PCR_GPIO_ADDRESS(PAD_OWN_GPP_D_0);
+	if (read != 0) {
+		pr_info("UV: Hubless NMI already configured\n");
+		return;
+	}
+
+	nmi_debug("UV: Initializing UV Hubless NMI on PCH\n");
+	for (i = 0; i < ARRAY_SIZE(init_nmi); i++) {
+		uv_init_hubless_pch_io(init_nmi[i].offset,
+					init_nmi[i].mask,
+					init_nmi[i].data);
+	}
+}
+
+static int uv_nmi_test_hubless(struct uv_hub_nmi_s *hub_nmi)
+{
+	int *pstat = PCH_PCR_GPIO_ADDRESS(GPI_NMI_STS_GPP_D_0);
+	int status = *pstat;
+
+	hub_nmi->nmi_value = status;
+	atomic_inc(&hub_nmi->read_mmr_count);
+
+	if (!(status & STS_GPP_D_0_MASK))	/* Not a UV external NMI */
+		return 0;
+
+	*pstat = STS_GPP_D_0_MASK;	/* Is a UV NMI: clear GPP_D_0 status */
+	(void)*pstat;			/* Flush write */
+
+	return 1;
+}
+
+static int uv_test_nmi(struct uv_hub_nmi_s *hub_nmi)
+{
+	if (hub_nmi->hub_present)
+		return uv_nmi_test_mmr(hub_nmi);
+
+	if (hub_nmi->pch_owner)		/* Only PCH owner can check status */
+		return uv_nmi_test_hubless(hub_nmi);
+
+	return -1;
+}
+
+/*
+ * If first CPU in on this hub, set hub_nmi "in_nmi" and "owner" values and
+ * return true.  If first CPU in on the system, set global "in_nmi" flag.
  */
 static int uv_set_in_nmi(int cpu, struct uv_hub_nmi_s *hub_nmi)
 {
@@ -214,6 +482,7 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi)
 {
 	int cpu = smp_processor_id();
 	int nmi = 0;
+	int nmi_detected = 0;
 
 	local64_inc(&uv_nmi_count);
 	this_cpu_inc(uv_cpu_nmi.queries);
@@ -224,35 +493,48 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi)
 			break;
 
 		if (raw_spin_trylock(&hub_nmi->nmi_lock)) {
+			nmi_detected = uv_test_nmi(hub_nmi);
 
-			/* check hub MMR NMI flag */
-			if (uv_nmi_test_mmr(hub_nmi)) {
+			/* Check flag for UV external NMI */
+			if (nmi_detected > 0) {
 				uv_set_in_nmi(cpu, hub_nmi);
 				nmi = 1;
 				break;
 			}
 
-			/* MMR NMI flag is clear */
+			/* A non-PCH node in a hubless system waits for NMI */
+			else if (nmi_detected < 0)
+				goto slave_wait;
+
+			/* MMR/PCH NMI flag is clear */
 			raw_spin_unlock(&hub_nmi->nmi_lock);
 
 		} else {
-			/* wait a moment for the hub nmi locker to set flag */
-			cpu_relax();
+
+			/* Wait a moment for the HUB NMI locker to set flag */
+slave_wait:		cpu_relax();
 			udelay(uv_nmi_slave_delay);
 
-			/* re-check hub in_nmi flag */
+			/* Re-check hub in_nmi flag */
 			nmi = atomic_read(&hub_nmi->in_nmi);
 			if (nmi)
 				break;
 		}
 
-		/* check if this BMC missed setting the MMR NMI flag */
+		/*
+		 * Check if this BMC missed setting the MMR NMI flag (or)
+		 * UV hubless system where only PCH owner can check flag
+		 */
 		if (!nmi) {
 			nmi = atomic_read(&uv_in_nmi);
 			if (nmi)
 				uv_set_in_nmi(cpu, hub_nmi);
 		}
 
+		/* If we're holding the hub lock, release it now */
+		if (nmi_detected < 0)
+			raw_spin_unlock(&hub_nmi->nmi_lock);
+
 	} while (0);
 
 	if (!nmi)
@@ -269,12 +551,15 @@ static inline void uv_clear_nmi(int cpu)
 	if (cpu == atomic_read(&hub_nmi->cpu_owner)) {
 		atomic_set(&hub_nmi->cpu_owner, -1);
 		atomic_set(&hub_nmi->in_nmi, 0);
-		uv_local_mmr_clear_nmi();
+		if (hub_nmi->hub_present)
+			uv_local_mmr_clear_nmi();
+		else
+			uv_reassert_nmi();
 		raw_spin_unlock(&hub_nmi->nmi_lock);
 	}
 }
 
-/* Ping non-responding cpus attemping to force them into the NMI handler */
+/* Ping non-responding CPU's attemping to force them into the NMI handler */
 static void uv_nmi_nr_cpus_ping(void)
 {
 	int cpu;
@@ -285,7 +570,7 @@ static void uv_nmi_nr_cpus_ping(void)
 	apic->send_IPI_mask(uv_nmi_cpu_mask, APIC_DM_NMI);
 }
 
-/* Clean up flags for cpus that ignored both NMI and ping */
+/* Clean up flags for CPU's that ignored both NMI and ping */
 static void uv_nmi_cleanup_mask(void)
 {
 	int cpu;
@@ -297,11 +582,12 @@ static void uv_nmi_cleanup_mask(void)
 	}
 }
 
-/* Loop waiting as cpus enter nmi handler */
+/* Loop waiting as CPU's enter NMI handler */
 static int uv_nmi_wait_cpus(int first)
 {
 	int i, j, k, n = num_online_cpus();
 	int last_k = 0, waiting = 0;
+	int cpu = smp_processor_id();
 
 	if (first) {
 		cpumask_copy(uv_nmi_cpu_mask, cpu_online_mask);
@@ -310,6 +596,12 @@ static int uv_nmi_wait_cpus(int first)
 		k = n - cpumask_weight(uv_nmi_cpu_mask);
 	}
 
+	/* PCH NMI causes only one CPU to respond */
+	if (first && uv_pch_intr_now_enabled) {
+		cpumask_clear_cpu(cpu, uv_nmi_cpu_mask);
+		return n - k - 1;
+	}
+
 	udelay(uv_nmi_initial_delay);
 	for (i = 0; i < uv_nmi_retry_count; i++) {
 		int loop_delay = uv_nmi_loop_delay;
@@ -325,13 +617,13 @@ static int uv_nmi_wait_cpus(int first)
 			k = n;
 			break;
 		}
-		if (last_k != k) {	/* abort if no new cpus coming in */
+		if (last_k != k) {	/* abort if no new CPU's coming in */
 			last_k = k;
 			waiting = 0;
 		} else if (++waiting > uv_nmi_wait_count)
 			break;
 
-		/* extend delay if waiting only for cpu 0 */
+		/* Extend delay if waiting only for CPU 0: */
 		if (waiting && (n - k) == 1 &&
 		    cpumask_test_cpu(0, uv_nmi_cpu_mask))
 			loop_delay *= 100;
@@ -342,29 +634,29 @@ static int uv_nmi_wait_cpus(int first)
 	return n - k;
 }
 
-/* Wait until all slave cpus have entered UV NMI handler */
+/* Wait until all slave CPU's have entered UV NMI handler */
 static void uv_nmi_wait(int master)
 {
-	/* indicate this cpu is in */
+	/* Indicate this CPU is in: */
 	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_IN);
 
-	/* if not the first cpu in (the master), then we are a slave cpu */
+	/* If not the first CPU in (the master), then we are a slave CPU */
 	if (!master)
 		return;
 
 	do {
-		/* wait for all other cpus to gather here */
+		/* Wait for all other CPU's to gather here */
 		if (!uv_nmi_wait_cpus(1))
 			break;
 
-		/* if not all made it in, send IPI NMI to them */
-		pr_alert("UV: Sending NMI IPI to %d non-responding CPUs: %*pbl\n",
+		/* If not all made it in, send IPI NMI to them */
+		pr_alert("UV: Sending NMI IPI to %d CPUs: %*pbl\n",
 			 cpumask_weight(uv_nmi_cpu_mask),
 			 cpumask_pr_args(uv_nmi_cpu_mask));
 
 		uv_nmi_nr_cpus_ping();
 
-		/* if all cpus are in, then done */
+		/* If all CPU's are in, then done */
 		if (!uv_nmi_wait_cpus(0))
 			break;
 
@@ -416,7 +708,7 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs)
 	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
 }
 
-/* Trigger a slave cpu to dump it's state */
+/* Trigger a slave CPU to dump it's state */
 static void uv_nmi_trigger_dump(int cpu)
 {
 	int retry = uv_nmi_trigger_delay;
@@ -437,7 +729,7 @@ static void uv_nmi_trigger_dump(int cpu)
 	uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP_DONE;
 }
 
-/* Wait until all cpus ready to exit */
+/* Wait until all CPU's ready to exit */
 static void uv_nmi_sync_exit(int master)
 {
 	atomic_dec(&uv_nmi_cpus_in_nmi);
@@ -451,7 +743,23 @@ static void uv_nmi_sync_exit(int master)
 	}
 }
 
-/* Walk through cpu list and dump state of each */
+/* Current "health" check is to check which CPU's are responsive */
+static void uv_nmi_action_health(int cpu, struct pt_regs *regs, int master)
+{
+	if (master) {
+		int in = atomic_read(&uv_nmi_cpus_in_nmi);
+		int out = num_online_cpus() - in;
+
+		pr_alert("UV: NMI CPU health check (non-responding:%d)\n", out);
+		atomic_set(&uv_nmi_slave_continue, SLAVE_EXIT);
+	} else {
+		while (!atomic_read(&uv_nmi_slave_continue))
+			cpu_relax();
+	}
+	uv_nmi_sync_exit(master);
+}
+
+/* Walk through CPU list and dump state of each */
 static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master)
 {
 	if (master) {
@@ -538,7 +846,7 @@ static inline int uv_nmi_kdb_reason(void)
 #else /* !CONFIG_KGDB_KDB */
 static inline int uv_nmi_kdb_reason(void)
 {
-	/* Insure user is expecting to attach gdb remote */
+	/* Ensure user is expecting to attach gdb remote */
 	if (uv_nmi_action_is("kgdb"))
 		return 0;
 
@@ -563,7 +871,7 @@ static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master)
 		if (reason < 0)
 			return;
 
-		/* call KGDB NMI handler as MASTER */
+		/* Call KGDB NMI handler as MASTER */
 		ret = kgdb_nmicallin(cpu, X86_TRAP_NMI, regs, reason,
 				&uv_nmi_slave_continue);
 		if (ret) {
@@ -571,7 +879,7 @@ static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master)
 			atomic_set(&uv_nmi_slave_continue, SLAVE_EXIT);
 		}
 	} else {
-		/* wait for KGDB signal that it's ready for slaves to enter */
+		/* Wait for KGDB signal that it's ready for slaves to enter */
 		int sig;
 
 		do {
@@ -579,7 +887,7 @@ static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master)
 			sig = atomic_read(&uv_nmi_slave_continue);
 		} while (!sig);
 
-		/* call KGDB as slave */
+		/* Call KGDB as slave */
 		if (sig == SLAVE_CONTINUE)
 			kgdb_nmicallback(cpu, regs);
 	}
@@ -623,18 +931,23 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 			strncpy(uv_nmi_action, "dump", strlen(uv_nmi_action));
 	}
 
-	/* Pause as all cpus enter the NMI handler */
+	/* Pause as all CPU's enter the NMI handler */
 	uv_nmi_wait(master);
 
-	/* Dump state of each cpu */
-	if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump"))
+	/* Process actions other than "kdump": */
+	if (uv_nmi_action_is("health")) {
+		uv_nmi_action_health(cpu, regs, master);
+	} else if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump")) {
 		uv_nmi_dump_state(cpu, regs, master);
-
-	/* Call KGDB/KDB if enabled */
-	else if (uv_nmi_action_is("kdb") || uv_nmi_action_is("kgdb"))
+	} else if (uv_nmi_action_is("kdb") || uv_nmi_action_is("kgdb")) {
 		uv_call_kgdb_kdb(cpu, regs, master);
+	} else {
+		if (master)
+			pr_alert("UV: unknown NMI action: %s\n", uv_nmi_action);
+		uv_nmi_sync_exit(master);
+	}
 
-	/* Clear per_cpu "in nmi" flag */
+	/* Clear per_cpu "in_nmi" flag */
 	this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_OUT);
 
 	/* Clear MMR NMI flag on each hub */
@@ -648,6 +961,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 		atomic_set(&uv_nmi_cpu, -1);
 		atomic_set(&uv_in_nmi, 0);
 		atomic_set(&uv_nmi_kexec_failed, 0);
+		atomic_set(&uv_nmi_slave_continue, SLAVE_CLEAR);
 	}
 
 	uv_nmi_touch_watchdogs();
@@ -657,7 +971,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 }
 
 /*
- * NMI handler for pulling in CPUs when perf events are grabbing our NMI
+ * NMI handler for pulling in CPU's when perf events are grabbing our NMI
  */
 static int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs)
 {
@@ -690,35 +1004,62 @@ void uv_nmi_init(void)
 	unsigned int value;
 
 	/*
-	 * Unmask NMI on all cpus
+	 * Unmask NMI on all CPU's
 	 */
 	value = apic_read(APIC_LVT1) | APIC_DM_NMI;
 	value &= ~APIC_LVT_MASKED;
 	apic_write(APIC_LVT1, value);
 }
 
-void uv_nmi_setup(void)
+/* Setup HUB NMI info */
+void __init uv_nmi_setup_common(bool hubbed)
 {
 	int size = sizeof(void *) * (1 << NODES_SHIFT);
-	int cpu, nid;
+	int cpu;
 
-	/* Setup hub nmi info */
-	uv_nmi_setup_mmrs();
 	uv_hub_nmi_list = kzalloc(size, GFP_KERNEL);
-	pr_info("UV: NMI hub list @ 0x%p (%d)\n", uv_hub_nmi_list, size);
+	nmi_debug("UV: NMI hub list @ 0x%p (%d)\n", uv_hub_nmi_list, size);
 	BUG_ON(!uv_hub_nmi_list);
 	size = sizeof(struct uv_hub_nmi_s);
 	for_each_present_cpu(cpu) {
-		nid = cpu_to_node(cpu);
+		int nid = cpu_to_node(cpu);
 		if (uv_hub_nmi_list[nid] == NULL) {
 			uv_hub_nmi_list[nid] = kzalloc_node(size,
 							    GFP_KERNEL, nid);
 			BUG_ON(!uv_hub_nmi_list[nid]);
 			raw_spin_lock_init(&(uv_hub_nmi_list[nid]->nmi_lock));
 			atomic_set(&uv_hub_nmi_list[nid]->cpu_owner, -1);
+			uv_hub_nmi_list[nid]->hub_present = hubbed;
+			uv_hub_nmi_list[nid]->pch_owner = (nid == 0);
 		}
 		uv_hub_nmi_per(cpu) = uv_hub_nmi_list[nid];
 	}
 	BUG_ON(!alloc_cpumask_var(&uv_nmi_cpu_mask, GFP_KERNEL));
+}
+
+/* Setup for UV Hub systems */
+void __init uv_nmi_setup(void)
+{
+	uv_nmi_setup_mmrs();
+	uv_nmi_setup_common(true);
+	uv_register_nmi_notifier();
+	pr_info("UV: Hub NMI enabled\n");
+}
+
+/* Setup for UV Hubless systems */
+void __init uv_nmi_setup_hubless(void)
+{
+	uv_nmi_setup_common(false);
+	pch_base = xlate_dev_mem_ptr(PCH_PCR_GPIO_1_BASE);
+	nmi_debug("UV: PCH base:%p from 0x%lx, GPP_D_0\n",
+		pch_base, PCH_PCR_GPIO_1_BASE);
+	if (uv_pch_init_enable)
+		uv_init_hubless_pch_d0();
+	uv_init_hubless_pch_io(GPI_NMI_ENA_GPP_D_0,
+				STS_GPP_D_0_MASK, STS_GPP_D_0_MASK);
+	uv_nmi_setup_hubless_intr();
+	/* Ensure NMI enabled in Processor Interface Reg: */
+	uv_reassert_nmi();
 	uv_register_nmi_notifier();
+	pr_info("UV: Hubless NMI enabled\n");
 }
diff --git a/arch/x86/ras/Kconfig b/arch/x86/ras/Kconfig
index d957d5f21a86..0bc60a308730 100644
--- a/arch/x86/ras/Kconfig
+++ b/arch/x86/ras/Kconfig
@@ -1,6 +1,6 @@
 config MCE_AMD_INJ
 	tristate "Simple MCE injection interface for AMD processors"
-	depends on RAS && EDAC_DECODE_MCE && DEBUG_FS && AMD_NB
+	depends on RAS && X86_MCE && DEBUG_FS && AMD_NB
 	default n
 	help
 	  This is a simple debugfs interface to inject MCEs and test different
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index e8a9ea7d7a21..25a7c4302ce7 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -141,25 +141,6 @@ void __init xen_init_spinlocks(void)
 	pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
 }
 
-/*
- * While the jump_label init code needs to happend _after_ the jump labels are
- * enabled and before SMP is started. Hence we use pre-SMP initcall level
- * init. We cannot do it in xen_init_spinlocks as that is done before
- * jump labels are activated.
- */
-static __init int xen_init_spinlocks_jump(void)
-{
-	if (!xen_pvspin)
-		return 0;
-
-	if (!xen_domain())
-		return 0;
-
-	static_key_slow_inc(&paravirt_ticketlocks_enabled);
-	return 0;
-}
-early_initcall(xen_init_spinlocks_jump);
-
 static __init int xen_parse_nopvspin(char *arg)
 {
 	xen_pvspin = false;
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index b7fbaa56b51a..9e9760b20be5 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -1,7 +1,6 @@
 generic-y += bitsperlong.h
 generic-y += bug.h
 generic-y += clkdev.h
-generic-y += cputime.h
 generic-y += div64.h
 generic-y += dma-contiguous.h
 generic-y += emergency-restart.h
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 848e8568fb3c..8fd4be610607 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -419,7 +419,7 @@ subsys_initcall(topology_init);
 
 void cpu_reset(void)
 {
-#if XCHAL_HAVE_PTP_MMU
+#if XCHAL_HAVE_PTP_MMU && IS_ENABLED(CONFIG_MMU)
 	local_irq_disable();
 	/*
 	 * We have full MMU: all autoload ways, ways 7, 8 and 9 of DTLB must
diff --git a/block/Kconfig b/block/Kconfig
index 8bf114a3858a..a2a92e57a87d 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -49,9 +49,13 @@ config LBDAF
 
 	  If unsure, say Y.
 
+config BLK_SCSI_REQUEST
+	bool
+
 config BLK_DEV_BSG
 	bool "Block layer SG support v4"
 	default y
+	select BLK_SCSI_REQUEST
 	help
 	  Saying Y here will enable generic SG (SCSI generic) v4 support
 	  for any block device.
@@ -71,6 +75,7 @@ config BLK_DEV_BSGLIB
 	bool "Block layer SG support v4 helper lib"
 	default n
 	select BLK_DEV_BSG
+	select BLK_SCSI_REQUEST
 	help
 	  Subsystems will normally enable this if needed. Users will not
 	  normally need to manually enable this.
@@ -147,6 +152,25 @@ config BLK_WBT_MQ
 	Multiqueue currently doesn't have support for IO scheduling,
 	enabling this option is recommended.
 
+config BLK_DEBUG_FS
+	bool "Block layer debugging information in debugfs"
+	default y
+	depends on DEBUG_FS
+	---help---
+	Include block layer debugging information in debugfs. This information
+	is mostly useful for kernel developers, but it doesn't incur any cost
+	at runtime.
+
+	Unless you are building a kernel for a tiny system, you should
+	say Y here.
+
+config BLK_SED_OPAL
+	bool "Logic for interfacing with Opal enabled SEDs"
+	---help---
+	Builds Logic for interfacing with Opal enabled controllers.
+	Enabling this option enables users to setup/unlock/lock
+	Locking ranges for SED devices using the Opal protocol.
+
 menu "Partition Types"
 
 source "block/partitions/Kconfig"
diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched
index 421bef9c4c48..0715ce93daef 100644
--- a/block/Kconfig.iosched
+++ b/block/Kconfig.iosched
@@ -63,6 +63,56 @@ config DEFAULT_IOSCHED
 	default "cfq" if DEFAULT_CFQ
 	default "noop" if DEFAULT_NOOP
 
+config MQ_IOSCHED_DEADLINE
+	tristate "MQ deadline I/O scheduler"
+	default y
+	---help---
+	  MQ version of the deadline IO scheduler.
+
+config MQ_IOSCHED_NONE
+	bool
+	default y
+
+choice
+	prompt "Default single-queue blk-mq I/O scheduler"
+	default DEFAULT_SQ_NONE
+	help
+	  Select the I/O scheduler which will be used by default for blk-mq
+	  managed block devices with a single queue.
+
+	config DEFAULT_SQ_DEADLINE
+		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
+
+	config DEFAULT_SQ_NONE
+		bool "None"
+
+endchoice
+
+config DEFAULT_SQ_IOSCHED
+	string
+	default "mq-deadline" if DEFAULT_SQ_DEADLINE
+	default "none" if DEFAULT_SQ_NONE
+
+choice
+	prompt "Default multi-queue blk-mq I/O scheduler"
+	default DEFAULT_MQ_NONE
+	help
+	  Select the I/O scheduler which will be used by default for blk-mq
+	  managed block devices with multiple queues.
+
+	config DEFAULT_MQ_DEADLINE
+		bool "MQ Deadline" if MQ_IOSCHED_DEADLINE=y
+
+	config DEFAULT_MQ_NONE
+		bool "None"
+
+endchoice
+
+config DEFAULT_MQ_IOSCHED
+	string
+	default "mq-deadline" if DEFAULT_MQ_DEADLINE
+	default "none" if DEFAULT_MQ_NONE
+
 endmenu
 
 endif
diff --git a/block/Makefile b/block/Makefile
index a827f988c4e6..2ad7c304e3f5 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -6,11 +6,12 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
-			blk-mq-sysfs.o blk-mq-cpumap.o ioctl.o \
-			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
+			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
+			genhd.o partition-generic.o ioprio.o \
 			badblocks.o partitions/
 
-obj-$(CONFIG_BOUNCE)	+= bounce.o
+obj-$(CONFIG_BOUNCE)		+= bounce.o
+obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
@@ -18,6 +19,7 @@ obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
+obj-$(CONFIG_MQ_IOSCHED_DEADLINE)	+= mq-deadline.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
@@ -25,3 +27,5 @@ obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
+obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
+obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
diff --git a/block/bio.c b/block/bio.c
index 2b375020fc49..4b564d0c3e29 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1227,9 +1227,6 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 	if (!bio)
 		goto out_bmd;
 
-	if (iter->type & WRITE)
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
 	ret = 0;
 
 	if (map_data) {
@@ -1394,16 +1391,10 @@ struct bio *bio_map_user_iov(struct request_queue *q,
 
 	kfree(pages);
 
-	/*
-	 * set data direction, and check if mapped pages need bouncing
-	 */
-	if (iter->type & WRITE)
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-
 	bio_set_flag(bio, BIO_USER_MAPPED);
 
 	/*
-	 * subtle -- if __bio_map_user() ended up bouncing a bio,
+	 * subtle -- if bio_map_user_iov() ended up bouncing a bio,
 	 * it would normally disappear when its bi_end_io is run.
 	 * however, we need it for the unmap, so grab an extra
 	 * reference to it
@@ -1445,8 +1436,8 @@ static void __bio_unmap_user(struct bio *bio)
  *	bio_unmap_user	-	unmap a bio
  *	@bio:		the bio being unmapped
  *
- *	Unmap a bio previously mapped by bio_map_user(). Must be called with
- *	a process context.
+ *	Unmap a bio previously mapped by bio_map_user_iov(). Must be called from
+ *	process context.
  *
  *	bio_unmap_user() may sleep.
  */
@@ -1590,7 +1581,6 @@ struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
 		bio->bi_private = data;
 	} else {
 		bio->bi_end_io = bio_copy_kern_endio;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	}
 
 	return bio;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 8ba0af780e88..295e98c2c8cc 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -184,7 +184,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg,
 		goto err_free_blkg;
 	}
 
-	wb_congested = wb_congested_get_create(&q->backing_dev_info,
+	wb_congested = wb_congested_get_create(q->backing_dev_info,
 					       blkcg->css.id,
 					       GFP_NOWAIT | __GFP_NOWARN);
 	if (!wb_congested) {
@@ -469,8 +469,8 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 const char *blkg_dev_name(struct blkcg_gq *blkg)
 {
 	/* some drivers (floppy) instantiate a queue w/o disk registered */
-	if (blkg->q->backing_dev_info.dev)
-		return dev_name(blkg->q->backing_dev_info.dev);
+	if (blkg->q->backing_dev_info->dev)
+		return dev_name(blkg->q->backing_dev_info->dev);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(blkg_dev_name);
@@ -1079,10 +1079,8 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	if (IS_ERR(blkg)) {
-		blkg_free(new_blkg);
+	if (IS_ERR(blkg))
 		return PTR_ERR(blkg);
-	}
 
 	q->root_blkg = blkg;
 	q->root_rl.blkg = blkg;
@@ -1223,7 +1221,10 @@ int blkcg_activate_policy(struct request_queue *q,
 	if (blkcg_policy_enabled(q, pol))
 		return 0;
 
-	blk_queue_bypass_start(q);
+	if (q->mq_ops)
+		blk_mq_freeze_queue(q);
+	else
+		blk_queue_bypass_start(q);
 pd_prealloc:
 	if (!pd_prealloc) {
 		pd_prealloc = pol->pd_alloc_fn(GFP_KERNEL, q->node);
@@ -1261,7 +1262,10 @@ pd_prealloc:
 
 	spin_unlock_irq(q->queue_lock);
 out_bypass_end:
-	blk_queue_bypass_end(q);
+	if (q->mq_ops)
+		blk_mq_unfreeze_queue(q);
+	else
+		blk_queue_bypass_end(q);
 	if (pd_prealloc)
 		pol->pd_free_fn(pd_prealloc);
 	return ret;
@@ -1284,7 +1288,11 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	if (!blkcg_policy_enabled(q, pol))
 		return;
 
-	blk_queue_bypass_start(q);
+	if (q->mq_ops)
+		blk_mq_freeze_queue(q);
+	else
+		blk_queue_bypass_start(q);
+
 	spin_lock_irq(q->queue_lock);
 
 	__clear_bit(pol->plid, q->blkcg_pols);
@@ -1304,7 +1312,11 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	}
 
 	spin_unlock_irq(q->queue_lock);
-	blk_queue_bypass_end(q);
+
+	if (q->mq_ops)
+		blk_mq_unfreeze_queue(q);
+	else
+		blk_queue_bypass_end(q);
 }
 EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 61ba08c58b64..b9e857f4afe8 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -33,14 +33,20 @@
 #include <linux/ratelimit.h>
 #include <linux/pm_runtime.h>
 #include <linux/blk-cgroup.h>
+#include <linux/debugfs.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/block.h>
 
 #include "blk.h"
 #include "blk-mq.h"
+#include "blk-mq-sched.h"
 #include "blk-wbt.h"
 
+#ifdef CONFIG_DEBUG_FS
+struct dentry *blk_debugfs_root;
+#endif
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
@@ -74,7 +80,7 @@ static void blk_clear_congested(struct request_list *rl, int sync)
 	 * flip its congestion state for events on other blkcgs.
 	 */
 	if (rl == &rl->q->root_rl)
-		clear_wb_congested(rl->q->backing_dev_info.wb.congested, sync);
+		clear_wb_congested(rl->q->backing_dev_info->wb.congested, sync);
 #endif
 }
 
@@ -85,7 +91,7 @@ static void blk_set_congested(struct request_list *rl, int sync)
 #else
 	/* see blk_clear_congested() */
 	if (rl == &rl->q->root_rl)
-		set_wb_congested(rl->q->backing_dev_info.wb.congested, sync);
+		set_wb_congested(rl->q->backing_dev_info->wb.congested, sync);
 #endif
 }
 
@@ -104,22 +110,6 @@ void blk_queue_congestion_threshold(struct request_queue *q)
 	q->nr_congestion_off = nr;
 }
 
-/**
- * blk_get_backing_dev_info - get the address of a queue's backing_dev_info
- * @bdev:	device
- *
- * Locates the passed device's request queue and returns the address of its
- * backing_dev_info.  This function can only be called if @bdev is opened
- * and the return value is never NULL.
- */
-struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	return &q->backing_dev_info;
-}
-EXPORT_SYMBOL(blk_get_backing_dev_info);
-
 void blk_rq_init(struct request_queue *q, struct request *rq)
 {
 	memset(rq, 0, sizeof(*rq));
@@ -131,9 +121,8 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 	rq->__sector = (sector_t) -1;
 	INIT_HLIST_NODE(&rq->hash);
 	RB_CLEAR_NODE(&rq->rb_node);
-	rq->cmd = rq->__cmd;
-	rq->cmd_len = BLK_MAX_CDB;
 	rq->tag = -1;
+	rq->internal_tag = -1;
 	rq->start_time = jiffies;
 	set_start_time_ns(rq);
 	rq->part = NULL;
@@ -158,10 +147,8 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 
 void blk_dump_rq_flags(struct request *rq, char *msg)
 {
-	int bit;
-
-	printk(KERN_INFO "%s: dev %s: type=%x, flags=%llx\n", msg,
-		rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
+	printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg,
+		rq->rq_disk ? rq->rq_disk->disk_name : "?",
 		(unsigned long long) rq->cmd_flags);
 
 	printk(KERN_INFO "  sector %llu, nr/cnr %u/%u\n",
@@ -169,13 +156,6 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 	       blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
 	printk(KERN_INFO "  bio %p, biotail %p, len %u\n",
 	       rq->bio, rq->biotail, blk_rq_bytes(rq));
-
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
-		printk(KERN_INFO "  cdb: ");
-		for (bit = 0; bit < BLK_MAX_CDB; bit++)
-			printk("%02x ", rq->cmd[bit]);
-		printk("\n");
-	}
 }
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
@@ -525,12 +505,14 @@ void blk_set_queue_dying(struct request_queue *q)
 	else {
 		struct request_list *rl;
 
+		spin_lock_irq(q->queue_lock);
 		blk_queue_for_each_rl(rl, q) {
 			if (rl->rq_pool) {
 				wake_up(&rl->wait[BLK_RW_SYNC]);
 				wake_up(&rl->wait[BLK_RW_ASYNC]);
 			}
 		}
+		spin_unlock_irq(q->queue_lock);
 	}
 }
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
@@ -584,7 +566,7 @@ void blk_cleanup_queue(struct request_queue *q)
 	blk_flush_integrity();
 
 	/* @q won't process any more request, flush async actions */
-	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
+	del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer);
 	blk_sync_queue(q);
 
 	if (q->mq_ops)
@@ -596,7 +578,8 @@ void blk_cleanup_queue(struct request_queue *q)
 		q->queue_lock = &q->__queue_lock;
 	spin_unlock_irq(lock);
 
-	bdi_unregister(&q->backing_dev_info);
+	bdi_unregister(q->backing_dev_info);
+	put_disk_devt(q->disk_devt);
 
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
@@ -604,17 +587,41 @@ void blk_cleanup_queue(struct request_queue *q)
 EXPORT_SYMBOL(blk_cleanup_queue);
 
 /* Allocate memory local to the request queue */
-static void *alloc_request_struct(gfp_t gfp_mask, void *data)
+static void *alloc_request_simple(gfp_t gfp_mask, void *data)
 {
-	int nid = (int)(long)data;
-	return kmem_cache_alloc_node(request_cachep, gfp_mask, nid);
+	struct request_queue *q = data;
+
+	return kmem_cache_alloc_node(request_cachep, gfp_mask, q->node);
 }
 
-static void free_request_struct(void *element, void *unused)
+static void free_request_simple(void *element, void *data)
 {
 	kmem_cache_free(request_cachep, element);
 }
 
+static void *alloc_request_size(gfp_t gfp_mask, void *data)
+{
+	struct request_queue *q = data;
+	struct request *rq;
+
+	rq = kmalloc_node(sizeof(struct request) + q->cmd_size, gfp_mask,
+			q->node);
+	if (rq && q->init_rq_fn && q->init_rq_fn(q, rq, gfp_mask) < 0) {
+		kfree(rq);
+		rq = NULL;
+	}
+	return rq;
+}
+
+static void free_request_size(void *element, void *data)
+{
+	struct request_queue *q = data;
+
+	if (q->exit_rq_fn)
+		q->exit_rq_fn(q, element);
+	kfree(element);
+}
+
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask)
 {
@@ -627,10 +634,15 @@ int blk_init_rl(struct request_list *rl, struct request_queue *q,
 	init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
 	init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
 
-	rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, alloc_request_struct,
-					  free_request_struct,
-					  (void *)(long)q->node, gfp_mask,
-					  q->node);
+	if (q->cmd_size) {
+		rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ,
+				alloc_request_size, free_request_size,
+				q, gfp_mask, q->node);
+	} else {
+		rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ,
+				alloc_request_simple, free_request_simple,
+				q, gfp_mask, q->node);
+	}
 	if (!rl->rq_pool)
 		return -ENOMEM;
 
@@ -693,7 +705,6 @@ static void blk_rq_timed_out_timer(unsigned long data)
 struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 {
 	struct request_queue *q;
-	int err;
 
 	q = kmem_cache_alloc_node(blk_requestq_cachep,
 				gfp_mask | __GFP_ZERO, node_id);
@@ -708,17 +719,17 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (!q->bio_split)
 		goto fail_id;
 
-	q->backing_dev_info.ra_pages =
+	q->backing_dev_info = bdi_alloc_node(gfp_mask, node_id);
+	if (!q->backing_dev_info)
+		goto fail_split;
+
+	q->backing_dev_info->ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
-	q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK;
-	q->backing_dev_info.name = "block";
+	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
+	q->backing_dev_info->name = "block";
 	q->node = node_id;
 
-	err = bdi_init(&q->backing_dev_info);
-	if (err)
-		goto fail_split;
-
-	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
+	setup_timer(&q->backing_dev_info->laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->queue_head);
@@ -768,7 +779,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 fail_ref:
 	percpu_ref_exit(&q->q_usage_counter);
 fail_bdi:
-	bdi_destroy(&q->backing_dev_info);
+	bdi_put(q->backing_dev_info);
 fail_split:
 	bioset_free(q->bio_split);
 fail_id:
@@ -821,15 +832,19 @@ EXPORT_SYMBOL(blk_init_queue);
 struct request_queue *
 blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 {
-	struct request_queue *uninit_q, *q;
+	struct request_queue *q;
 
-	uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id);
-	if (!uninit_q)
+	q = blk_alloc_queue_node(GFP_KERNEL, node_id);
+	if (!q)
 		return NULL;
 
-	q = blk_init_allocated_queue(uninit_q, rfn, lock);
-	if (!q)
-		blk_cleanup_queue(uninit_q);
+	q->request_fn = rfn;
+	if (lock)
+		q->queue_lock = lock;
+	if (blk_init_allocated_queue(q) < 0) {
+		blk_cleanup_queue(q);
+		return NULL;
+	}
 
 	return q;
 }
@@ -837,30 +852,22 @@ EXPORT_SYMBOL(blk_init_queue_node);
 
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio);
 
-struct request_queue *
-blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
-			 spinlock_t *lock)
-{
-	if (!q)
-		return NULL;
 
-	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, 0);
+int blk_init_allocated_queue(struct request_queue *q)
+{
+	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size);
 	if (!q->fq)
-		return NULL;
+		return -ENOMEM;
+
+	if (q->init_rq_fn && q->init_rq_fn(q, q->fq->flush_rq, GFP_KERNEL))
+		goto out_free_flush_queue;
 
 	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
-		goto fail;
+		goto out_exit_flush_rq;
 
 	INIT_WORK(&q->timeout_work, blk_timeout_work);
-	q->request_fn		= rfn;
-	q->prep_rq_fn		= NULL;
-	q->unprep_rq_fn		= NULL;
 	q->queue_flags		|= QUEUE_FLAG_DEFAULT;
 
-	/* Override internal queue lock with supplied lock pointer */
-	if (lock)
-		q->queue_lock		= lock;
-
 	/*
 	 * This also sets hw/phys segments, boundary and size
 	 */
@@ -874,17 +881,19 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	/* init elevator */
 	if (elevator_init(q, NULL)) {
 		mutex_unlock(&q->sysfs_lock);
-		goto fail;
+		goto out_exit_flush_rq;
 	}
 
 	mutex_unlock(&q->sysfs_lock);
+	return 0;
 
-	return q;
-
-fail:
+out_exit_flush_rq:
+	if (q->exit_rq_fn)
+		q->exit_rq_fn(q, q->fq->flush_rq);
+out_free_flush_queue:
 	blk_free_flush_queue(q->fq);
 	wbt_exit(q);
-	return NULL;
+	return -ENOMEM;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
 
@@ -1020,41 +1029,6 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
 	return 0;
 }
 
-/*
- * Determine if elevator data should be initialized when allocating the
- * request associated with @bio.
- */
-static bool blk_rq_should_init_elevator(struct bio *bio)
-{
-	if (!bio)
-		return true;
-
-	/*
-	 * Flush requests do not use the elevator so skip initialization.
-	 * This allows a request to share the flush and elevator data.
-	 */
-	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA))
-		return false;
-
-	return true;
-}
-
-/**
- * rq_ioc - determine io_context for request allocation
- * @bio: request being allocated is for this bio (can be %NULL)
- *
- * Determine io_context to use for request allocation for @bio.  May return
- * %NULL if %current->io_context doesn't exist.
- */
-static struct io_context *rq_ioc(struct bio *bio)
-{
-#ifdef CONFIG_BLK_CGROUP
-	if (bio && bio->bi_ioc)
-		return bio->bi_ioc;
-#endif
-	return current->io_context;
-}
-
 /**
  * __get_request - get a free request
  * @rl: request list to allocate from
@@ -1133,10 +1107,13 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 	 * request is freed.  This guarantees icq's won't be destroyed and
 	 * makes creating new ones safe.
 	 *
+	 * Flush requests do not use the elevator so skip initialization.
+	 * This allows a request to share the flush and elevator data.
+	 *
 	 * Also, lookup icq while holding queue_lock.  If it doesn't exist,
 	 * it will be created after releasing queue_lock.
 	 */
-	if (blk_rq_should_init_elevator(bio) && !blk_queue_bypass(q)) {
+	if (!op_is_flush(op) && !blk_queue_bypass(q)) {
 		rq_flags |= RQF_ELVPRIV;
 		q->nr_rqs_elvpriv++;
 		if (et->icq_cache && ioc)
@@ -1196,7 +1173,7 @@ fail_elvpriv:
 	 * disturb iosched and blkcg but weird is bettern than dead.
 	 */
 	printk_ratelimited(KERN_WARNING "%s: dev %s: request aux data allocation failed, iosched may be disturbed\n",
-			   __func__, dev_name(q->backing_dev_info.dev));
+			   __func__, dev_name(q->backing_dev_info->dev));
 
 	rq->rq_flags &= ~RQF_ELVPRIV;
 	rq->elv.icq = NULL;
@@ -1290,8 +1267,6 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 {
 	struct request *rq;
 
-	BUG_ON(rw != READ && rw != WRITE);
-
 	/* create ioc upfront */
 	create_io_context(gfp_mask, q->node);
 
@@ -1321,18 +1296,6 @@ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
 EXPORT_SYMBOL(blk_get_request);
 
 /**
- * blk_rq_set_block_pc - initialize a request to type BLOCK_PC
- * @rq:		request to be initialized
- *
- */
-void blk_rq_set_block_pc(struct request *rq)
-{
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	memset(rq->__cmd, 0, sizeof(rq->__cmd));
-}
-EXPORT_SYMBOL(blk_rq_set_block_pc);
-
-/**
  * blk_requeue_request - put a request back on queue
  * @q:		request queue where request should be inserted
  * @rq:		request to be inserted
@@ -1522,6 +1485,30 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 	return true;
 }
 
+bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
+		struct bio *bio)
+{
+	unsigned short segments = blk_rq_nr_discard_segments(req);
+
+	if (segments >= queue_max_discard_segments(q))
+		goto no_merge;
+	if (blk_rq_sectors(req) + bio_sectors(bio) >
+	    blk_rq_get_max_sectors(req, blk_rq_pos(req)))
+		goto no_merge;
+
+	req->biotail->bi_next = bio;
+	req->biotail = bio;
+	req->__data_len += bio->bi_iter.bi_size;
+	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
+	req->nr_phys_segments = segments + 1;
+
+	blk_account_io_start(req, false);
+	return true;
+no_merge:
+	req_set_nomerge(q, req);
+	return false;
+}
+
 /**
  * blk_attempt_plug_merge - try to merge with %current's plugged list
  * @q: request_queue new bio is being queued at
@@ -1550,12 +1537,11 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 {
 	struct blk_plug *plug;
 	struct request *rq;
-	bool ret = false;
 	struct list_head *plug_list;
 
 	plug = current->plug;
 	if (!plug)
-		goto out;
+		return false;
 	*request_count = 0;
 
 	if (q->mq_ops)
@@ -1564,7 +1550,7 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		plug_list = &plug->list;
 
 	list_for_each_entry_reverse(rq, plug_list, queuelist) {
-		int el_ret;
+		bool merged = false;
 
 		if (rq->q == q) {
 			(*request_count)++;
@@ -1580,19 +1566,25 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		if (rq->q != q || !blk_rq_merge_ok(rq, bio))
 			continue;
 
-		el_ret = blk_try_merge(rq, bio);
-		if (el_ret == ELEVATOR_BACK_MERGE) {
-			ret = bio_attempt_back_merge(q, rq, bio);
-			if (ret)
-				break;
-		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-			ret = bio_attempt_front_merge(q, rq, bio);
-			if (ret)
-				break;
+		switch (blk_try_merge(rq, bio)) {
+		case ELEVATOR_BACK_MERGE:
+			merged = bio_attempt_back_merge(q, rq, bio);
+			break;
+		case ELEVATOR_FRONT_MERGE:
+			merged = bio_attempt_front_merge(q, rq, bio);
+			break;
+		case ELEVATOR_DISCARD_MERGE:
+			merged = bio_attempt_discard_merge(q, rq, bio);
+			break;
+		default:
+			break;
 		}
+
+		if (merged)
+			return true;
 	}
-out:
-	return ret;
+
+	return false;
 }
 
 unsigned int blk_plug_queued_count(struct request_queue *q)
@@ -1621,7 +1613,6 @@ out:
 
 void init_request_from_bio(struct request *req, struct bio *bio)
 {
-	req->cmd_type = REQ_TYPE_FS;
 	if (bio->bi_opf & REQ_RAHEAD)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
@@ -1635,8 +1626,8 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
 	struct blk_plug *plug;
-	int el_ret, where = ELEVATOR_INSERT_SORT;
-	struct request *req;
+	int where = ELEVATOR_INSERT_SORT;
+	struct request *req, *free;
 	unsigned int request_count = 0;
 	unsigned int wb_acct;
 
@@ -1655,7 +1646,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
-	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) {
+	if (op_is_flush(bio->bi_opf)) {
 		spin_lock_irq(q->queue_lock);
 		where = ELEVATOR_INSERT_FLUSH;
 		goto get_rq;
@@ -1673,21 +1664,29 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	el_ret = elv_merge(q, &req, bio);
-	if (el_ret == ELEVATOR_BACK_MERGE) {
-		if (bio_attempt_back_merge(q, req, bio)) {
-			elv_bio_merged(q, req, bio);
-			if (!attempt_back_merge(q, req))
-				elv_merged_request(q, req, el_ret);
-			goto out_unlock;
-		}
-	} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-		if (bio_attempt_front_merge(q, req, bio)) {
-			elv_bio_merged(q, req, bio);
-			if (!attempt_front_merge(q, req))
-				elv_merged_request(q, req, el_ret);
-			goto out_unlock;
-		}
+	switch (elv_merge(q, &req, bio)) {
+	case ELEVATOR_BACK_MERGE:
+		if (!bio_attempt_back_merge(q, req, bio))
+			break;
+		elv_bio_merged(q, req, bio);
+		free = attempt_back_merge(q, req);
+		if (free)
+			__blk_put_request(q, free);
+		else
+			elv_merged_request(q, req, ELEVATOR_BACK_MERGE);
+		goto out_unlock;
+	case ELEVATOR_FRONT_MERGE:
+		if (!bio_attempt_front_merge(q, req, bio))
+			break;
+		elv_bio_merged(q, req, bio);
+		free = attempt_front_merge(q, req);
+		if (free)
+			__blk_put_request(q, free);
+		else
+			elv_merged_request(q, req, ELEVATOR_FRONT_MERGE);
+		goto out_unlock;
+	default:
+		break;
 	}
 
 get_rq:
@@ -1894,7 +1893,7 @@ generic_make_request_checks(struct bio *bio)
 	 * drivers without flush support don't have to worry
 	 * about them.
 	 */
-	if ((bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) &&
+	if (op_is_flush(bio->bi_opf) &&
 	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
 		bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
 		if (!nr_sectors) {
@@ -2143,7 +2142,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
-		blk_mq_insert_request(rq, false, true, false);
+		blk_mq_sched_insert_request(rq, false, true, false, false);
 		return 0;
 	}
 
@@ -2159,7 +2158,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
+	if (op_is_flush(rq->cmd_flags))
 		where = ELEVATOR_INSERT_FLUSH;
 
 	add_acct_request(q, rq, where);
@@ -2464,14 +2463,6 @@ void blk_start_request(struct request *req)
 		wbt_issue(req->q->rq_wb, &req->issue_stat);
 	}
 
-	/*
-	 * We are now handing the request to the hardware, initialize
-	 * resid_len to full count and add the timeout handler.
-	 */
-	req->resid_len = blk_rq_bytes(req);
-	if (unlikely(blk_bidi_rq(req)))
-		req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
-
 	BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
 	blk_add_timer(req);
 }
@@ -2542,10 +2533,10 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	 * TODO: tj: This is too subtle.  It would be better to let
 	 * low level drivers do what they see fit.
 	 */
-	if (req->cmd_type == REQ_TYPE_FS)
+	if (!blk_rq_is_passthrough(req))
 		req->errors = 0;
 
-	if (error && req->cmd_type == REQ_TYPE_FS &&
+	if (error && !blk_rq_is_passthrough(req) &&
 	    !(req->rq_flags & RQF_QUIET)) {
 		char *error_type;
 
@@ -2617,7 +2608,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	req->__data_len -= total_bytes;
 
 	/* update sector only for requests with clear definition of sector */
-	if (req->cmd_type == REQ_TYPE_FS)
+	if (!blk_rq_is_passthrough(req))
 		req->__sector += total_bytes >> 9;
 
 	/* mixed attributes always follow the first bio */
@@ -2695,8 +2686,8 @@ void blk_finish_request(struct request *req, int error)
 
 	BUG_ON(blk_queued_rq(req));
 
-	if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS)
-		laptop_io_completion(&req->q->backing_dev_info);
+	if (unlikely(laptop_mode) && !blk_rq_is_passthrough(req))
+		laptop_io_completion(req->q->backing_dev_info);
 
 	blk_delete_timer(req);
 
@@ -3019,8 +3010,6 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
 static void __blk_rq_prep_clone(struct request *dst, struct request *src)
 {
 	dst->cpu = src->cpu;
-	dst->cmd_flags = src->cmd_flags | REQ_NOMERGE;
-	dst->cmd_type = src->cmd_type;
 	dst->__sector = blk_rq_pos(src);
 	dst->__data_len = blk_rq_bytes(src);
 	dst->nr_phys_segments = src->nr_phys_segments;
@@ -3270,7 +3259,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		/*
 		 * rq is already accounted, so use raw insert
 		 */
-		if (rq->cmd_flags & (REQ_PREFLUSH | REQ_FUA))
+		if (op_is_flush(rq->cmd_flags))
 			__elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH);
 		else
 			__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
@@ -3496,5 +3485,9 @@ int __init blk_dev_init(void)
 	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
 
+#ifdef CONFIG_DEBUG_FS
+	blk_debugfs_root = debugfs_create_dir("block", NULL);
+#endif
+
 	return 0;
 }
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 3ecb00a6cf45..8cd0e9bc8dc8 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -9,11 +9,7 @@
 #include <linux/sched/sysctl.h>
 
 #include "blk.h"
-
-/*
- * for max sense size
- */
-#include <scsi/scsi_cmnd.h>
+#include "blk-mq-sched.h"
 
 /**
  * blk_end_sync_rq - executes a completion event on a request
@@ -55,7 +51,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK;
 
 	WARN_ON(irqs_disabled());
-	WARN_ON(rq->cmd_type == REQ_TYPE_FS);
+	WARN_ON(!blk_rq_is_passthrough(rq));
 
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
@@ -65,7 +61,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be reused after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_insert_request(rq, at_head, true, false);
+		blk_mq_sched_insert_request(rq, at_head, true, false, false);
 		return;
 	}
 
@@ -100,16 +96,9 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 		   struct request *rq, int at_head)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
-	char sense[SCSI_SENSE_BUFFERSIZE];
 	int err = 0;
 	unsigned long hang_check;
 
-	if (!rq->sense) {
-		memset(sense, 0, sizeof(sense));
-		rq->sense = sense;
-		rq->sense_len = 0;
-	}
-
 	rq->end_io_data = &wait;
 	blk_execute_rq_nowait(q, bd_disk, rq, at_head, blk_end_sync_rq);
 
@@ -123,11 +112,6 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 	if (rq->errors)
 		err = -EIO;
 
-	if (rq->sense == sense)	{
-		rq->sense = NULL;
-		rq->sense_len = 0;
-	}
-
 	return err;
 }
 EXPORT_SYMBOL(blk_execute_rq);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 20b7c7a02f1c..0d5a9c1da1fc 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -74,6 +74,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
 
 /* FLUSH/FUA sequences */
 enum {
@@ -296,8 +297,14 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending))
 		return false;
 
-	/* C2 and C3 */
+	/* C2 and C3
+	 *
+	 * For blk-mq + scheduling, we can risk having all driver tags
+	 * assigned to empty flushes, and we deadlock if we are expecting
+	 * other requests to make progress. Don't defer for that case.
+	 */
 	if (!list_empty(&fq->flush_data_in_flight) &&
+	    !(q->mq_ops && q->elevator) &&
 	    time_before(jiffies,
 			fq->flush_pending_since + FLUSH_PENDING_TIMEOUT))
 		return false;
@@ -326,7 +333,6 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 		blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq);
 	}
 
-	flush_rq->cmd_type = REQ_TYPE_FS;
 	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;
 	flush_rq->rq_flags |= RQF_FLUSH_SEQ;
 	flush_rq->rq_disk = first_rq->rq_disk;
@@ -391,9 +397,10 @@ static void mq_flush_data_end_io(struct request *rq, int error)
 	 * the comment in flush_end_io().
 	 */
 	spin_lock_irqsave(&fq->mq_flush_lock, flags);
-	if (blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error))
-		blk_mq_run_hw_queue(hctx, true);
+	blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error);
 	spin_unlock_irqrestore(&fq->mq_flush_lock, flags);
+
+	blk_mq_run_hw_queue(hctx, true);
 }
 
 /**
@@ -453,9 +460,9 @@ void blk_insert_flush(struct request *rq)
 	 */
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
-		if (q->mq_ops) {
-			blk_mq_insert_request(rq, false, true, false);
-		} else
+		if (q->mq_ops)
+			blk_mq_sched_insert_request(rq, false, true, false, false);
+		else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
 	}
@@ -545,11 +552,10 @@ struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
 	if (!fq)
 		goto fail;
 
-	if (q->mq_ops) {
+	if (q->mq_ops)
 		spin_lock_init(&fq->mq_flush_lock);
-		rq_sz = round_up(rq_sz + cmd_size, cache_line_size());
-	}
 
+	rq_sz = round_up(rq_sz + cmd_size, cache_line_size());
 	fq->flush_rq = kzalloc_node(rq_sz, GFP_KERNEL, node);
 	if (!fq->flush_rq)
 		goto fail_rq;
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index d69c5c79f98e..9f0ff5ba4f84 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -443,10 +443,10 @@ void blk_integrity_revalidate(struct gendisk *disk)
 		return;
 
 	if (bi->profile)
-		disk->queue->backing_dev_info.capabilities |=
+		disk->queue->backing_dev_info->capabilities |=
 			BDI_CAP_STABLE_WRITES;
 	else
-		disk->queue->backing_dev_info.capabilities &=
+		disk->queue->backing_dev_info->capabilities &=
 			~BDI_CAP_STABLE_WRITES;
 }
 
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 381cb50a673c..b12f9c87b4c3 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -35,7 +35,10 @@ static void icq_free_icq_rcu(struct rcu_head *head)
 	kmem_cache_free(icq->__rcu_icq_cache, icq);
 }
 
-/* Exit an icq. Called with both ioc and q locked. */
+/*
+ * Exit an icq. Called with both ioc and q locked for sq, only ioc locked for
+ * mq.
+ */
 static void ioc_exit_icq(struct io_cq *icq)
 {
 	struct elevator_type *et = icq->q->elevator->type;
@@ -43,8 +46,10 @@ static void ioc_exit_icq(struct io_cq *icq)
 	if (icq->flags & ICQ_EXITED)
 		return;
 
-	if (et->ops.elevator_exit_icq_fn)
-		et->ops.elevator_exit_icq_fn(icq);
+	if (et->uses_mq && et->ops.mq.exit_icq)
+		et->ops.mq.exit_icq(icq);
+	else if (!et->uses_mq && et->ops.sq.elevator_exit_icq_fn)
+		et->ops.sq.elevator_exit_icq_fn(icq);
 
 	icq->flags |= ICQ_EXITED;
 }
@@ -164,6 +169,7 @@ EXPORT_SYMBOL(put_io_context);
  */
 void put_io_context_active(struct io_context *ioc)
 {
+	struct elevator_type *et;
 	unsigned long flags;
 	struct io_cq *icq;
 
@@ -182,13 +188,19 @@ retry:
 	hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) {
 		if (icq->flags & ICQ_EXITED)
 			continue;
-		if (spin_trylock(icq->q->queue_lock)) {
+
+		et = icq->q->elevator->type;
+		if (et->uses_mq) {
 			ioc_exit_icq(icq);
-			spin_unlock(icq->q->queue_lock);
 		} else {
-			spin_unlock_irqrestore(&ioc->lock, flags);
-			cpu_relax();
-			goto retry;
+			if (spin_trylock(icq->q->queue_lock)) {
+				ioc_exit_icq(icq);
+				spin_unlock(icq->q->queue_lock);
+			} else {
+				spin_unlock_irqrestore(&ioc->lock, flags);
+				cpu_relax();
+				goto retry;
+			}
 		}
 	}
 	spin_unlock_irqrestore(&ioc->lock, flags);
@@ -383,8 +395,10 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
 	if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) {
 		hlist_add_head(&icq->ioc_node, &ioc->icq_list);
 		list_add(&icq->q_node, &q->icq_list);
-		if (et->ops.elevator_init_icq_fn)
-			et->ops.elevator_init_icq_fn(icq);
+		if (et->uses_mq && et->ops.mq.init_icq)
+			et->ops.mq.init_icq(icq);
+		else if (!et->uses_mq && et->ops.sq.elevator_init_icq_fn)
+			et->ops.sq.elevator_init_icq_fn(icq);
 	} else {
 		kmem_cache_free(et->icq_cache, icq);
 		icq = ioc_lookup_icq(ioc, q);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index f8c82a9b4012..ed1e78e24db0 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -306,11 +306,6 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 	if (ret == 0 || (ret && ret != -EOPNOTSUPP))
 		goto out;
 
-	ret = __blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
-			ZERO_PAGE(0), biop);
-	if (ret == 0 || (ret && ret != -EOPNOTSUPP))
-		goto out;
-
 	ret = 0;
 	while (nr_sects != 0) {
 		bio = next_bio(bio, min(nr_sects, (sector_t)BIO_MAX_PAGES),
@@ -369,6 +364,10 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			return 0;
 	}
 
+	if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
+			ZERO_PAGE(0)))
+		return 0;
+
 	blk_start_plug(&plug);
 	ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
 			&bio, discard);
diff --git a/block/blk-map.c b/block/blk-map.c
index 0acb6640ead7..2f18c2a0be1b 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -16,8 +16,6 @@
 int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
 	if (!rq->bio) {
-		rq->cmd_flags &= REQ_OP_MASK;
-		rq->cmd_flags |= (bio->bi_opf & REQ_OP_MASK);
 		blk_rq_bio_prep(rq->q, rq, bio);
 	} else {
 		if (!ll_back_merge_fn(rq->q, rq, bio))
@@ -62,6 +60,9 @@ static int __blk_rq_map_user_iov(struct request *rq,
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
+	bio->bi_opf &= ~REQ_OP_MASK;
+	bio->bi_opf |= req_op(rq);
+
 	if (map_data && map_data->null_mapped)
 		bio_set_flag(bio, BIO_NULL_MAPPED);
 
@@ -90,7 +91,7 @@ static int __blk_rq_map_user_iov(struct request *rq,
 }
 
 /**
- * blk_rq_map_user_iov - map user data to a request, for REQ_TYPE_BLOCK_PC usage
+ * blk_rq_map_user_iov - map user data to a request, for passthrough requests
  * @q:		request queue where request should be inserted
  * @rq:		request to map data to
  * @map_data:   pointer to the rq_map_data holding pages (if necessary)
@@ -199,7 +200,7 @@ int blk_rq_unmap_user(struct bio *bio)
 EXPORT_SYMBOL(blk_rq_unmap_user);
 
 /**
- * blk_rq_map_kern - map kernel data to a request, for REQ_TYPE_BLOCK_PC usage
+ * blk_rq_map_kern - map kernel data to a request, for passthrough requests
  * @q:		request queue where request should be inserted
  * @rq:		request to fill
  * @kbuf:	the kernel buffer
@@ -234,8 +235,8 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	if (!reading)
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+	bio->bi_opf &= ~REQ_OP_MASK;
+	bio->bi_opf |= req_op(rq);
 
 	if (do_copy)
 		rq->rq_flags |= RQF_COPY_USER;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 182398cb1524..2afa262425d1 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -482,13 +482,6 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(blk_rq_map_sg);
 
-static void req_set_nomerge(struct request_queue *q, struct request *req)
-{
-	req->cmd_flags |= REQ_NOMERGE;
-	if (req == q->last_merge)
-		q->last_merge = NULL;
-}
-
 static inline int ll_new_hw_segment(struct request_queue *q,
 				    struct request *req,
 				    struct bio *bio)
@@ -659,31 +652,32 @@ static void blk_account_io_merge(struct request *req)
 }
 
 /*
- * Has to be called with the request spinlock acquired
+ * For non-mq, this has to be called with the request spinlock acquired.
+ * For mq with scheduling, the appropriate queue wide lock should be held.
  */
-static int attempt_merge(struct request_queue *q, struct request *req,
-			  struct request *next)
+static struct request *attempt_merge(struct request_queue *q,
+				     struct request *req, struct request *next)
 {
 	if (!rq_mergeable(req) || !rq_mergeable(next))
-		return 0;
+		return NULL;
 
 	if (req_op(req) != req_op(next))
-		return 0;
+		return NULL;
 
 	/*
 	 * not contiguous
 	 */
 	if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next))
-		return 0;
+		return NULL;
 
 	if (rq_data_dir(req) != rq_data_dir(next)
 	    || req->rq_disk != next->rq_disk
 	    || req_no_special_merge(next))
-		return 0;
+		return NULL;
 
 	if (req_op(req) == REQ_OP_WRITE_SAME &&
 	    !blk_write_same_mergeable(req->bio, next->bio))
-		return 0;
+		return NULL;
 
 	/*
 	 * If we are allowed to merge, then append bio list
@@ -692,7 +686,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	 * counts here.
 	 */
 	if (!ll_merge_requests_fn(q, req, next))
-		return 0;
+		return NULL;
 
 	/*
 	 * If failfast settings disagree or any of the two is already
@@ -732,42 +726,51 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (blk_rq_cpu_valid(next))
 		req->cpu = next->cpu;
 
-	/* owner-ship of bio passed from next to req */
+	/*
+	 * ownership of bio passed from next to req, return 'next' for
+	 * the caller to free
+	 */
 	next->bio = NULL;
-	__blk_put_request(q, next);
-	return 1;
+	return next;
 }
 
-int attempt_back_merge(struct request_queue *q, struct request *rq)
+struct request *attempt_back_merge(struct request_queue *q, struct request *rq)
 {
 	struct request *next = elv_latter_request(q, rq);
 
 	if (next)
 		return attempt_merge(q, rq, next);
 
-	return 0;
+	return NULL;
 }
 
-int attempt_front_merge(struct request_queue *q, struct request *rq)
+struct request *attempt_front_merge(struct request_queue *q, struct request *rq)
 {
 	struct request *prev = elv_former_request(q, rq);
 
 	if (prev)
 		return attempt_merge(q, prev, rq);
 
-	return 0;
+	return NULL;
 }
 
 int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 			  struct request *next)
 {
 	struct elevator_queue *e = q->elevator;
+	struct request *free;
 
-	if (e->type->ops.elevator_allow_rq_merge_fn)
-		if (!e->type->ops.elevator_allow_rq_merge_fn(q, rq, next))
+	if (!e->uses_mq && e->type->ops.sq.elevator_allow_rq_merge_fn)
+		if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next))
 			return 0;
 
-	return attempt_merge(q, rq, next);
+	free = attempt_merge(q, rq, next);
+	if (free) {
+		__blk_put_request(q, free);
+		return 1;
+	}
+
+	return 0;
 }
 
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
@@ -798,9 +801,12 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	return true;
 }
 
-int blk_try_merge(struct request *rq, struct bio *bio)
+enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
 {
-	if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
+	if (req_op(rq) == REQ_OP_DISCARD &&
+	    queue_max_discard_segments(rq->q) > 1)
+		return ELEVATOR_DISCARD_MERGE;
+	else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
 		return ELEVATOR_BACK_MERGE;
 	else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
 		return ELEVATOR_FRONT_MERGE;
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
new file mode 100644
index 000000000000..f6d917977b33
--- /dev/null
+++ b/block/blk-mq-debugfs.c
@@ -0,0 +1,772 @@
+/*
+ * Copyright (C) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/debugfs.h>
+
+#include <linux/blk-mq.h>
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+
+struct blk_mq_debugfs_attr {
+	const char *name;
+	umode_t mode;
+	const struct file_operations *fops;
+};
+
+static int blk_mq_debugfs_seq_open(struct inode *inode, struct file *file,
+				   const struct seq_operations *ops)
+{
+	struct seq_file *m;
+	int ret;
+
+	ret = seq_open(file, ops);
+	if (!ret) {
+		m = file->private_data;
+		m->private = inode->i_private;
+	}
+	return ret;
+}
+
+static int hctx_state_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "0x%lx\n", hctx->state);
+	return 0;
+}
+
+static int hctx_state_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_state_show, inode->i_private);
+}
+
+static const struct file_operations hctx_state_fops = {
+	.open		= hctx_state_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_flags_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "0x%lx\n", hctx->flags);
+	return 0;
+}
+
+static int hctx_flags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_flags_show, inode->i_private);
+}
+
+static const struct file_operations hctx_flags_fops = {
+	.open		= hctx_flags_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
+{
+	struct request *rq = list_entry_rq(v);
+
+	seq_printf(m, "%p {.cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n",
+		   rq, rq->cmd_flags, (__force unsigned int)rq->rq_flags,
+		   rq->tag, rq->internal_tag);
+	return 0;
+}
+
+static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
+	__acquires(&hctx->lock)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	spin_lock(&hctx->lock);
+	return seq_list_start(&hctx->dispatch, *pos);
+}
+
+static void *hctx_dispatch_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	return seq_list_next(v, &hctx->dispatch, pos);
+}
+
+static void hctx_dispatch_stop(struct seq_file *m, void *v)
+	__releases(&hctx->lock)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	spin_unlock(&hctx->lock);
+}
+
+static const struct seq_operations hctx_dispatch_seq_ops = {
+	.start	= hctx_dispatch_start,
+	.next	= hctx_dispatch_next,
+	.stop	= hctx_dispatch_stop,
+	.show	= blk_mq_debugfs_rq_show,
+};
+
+static int hctx_dispatch_open(struct inode *inode, struct file *file)
+{
+	return blk_mq_debugfs_seq_open(inode, file, &hctx_dispatch_seq_ops);
+}
+
+static const struct file_operations hctx_dispatch_fops = {
+	.open		= hctx_dispatch_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int hctx_ctx_map_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	sbitmap_bitmap_show(&hctx->ctx_map, m);
+	return 0;
+}
+
+static int hctx_ctx_map_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_ctx_map_show, inode->i_private);
+}
+
+static const struct file_operations hctx_ctx_map_fops = {
+	.open		= hctx_ctx_map_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void blk_mq_debugfs_tags_show(struct seq_file *m,
+				     struct blk_mq_tags *tags)
+{
+	seq_printf(m, "nr_tags=%u\n", tags->nr_tags);
+	seq_printf(m, "nr_reserved_tags=%u\n", tags->nr_reserved_tags);
+	seq_printf(m, "active_queues=%d\n",
+		   atomic_read(&tags->active_queues));
+
+	seq_puts(m, "\nbitmap_tags:\n");
+	sbitmap_queue_show(&tags->bitmap_tags, m);
+
+	if (tags->nr_reserved_tags) {
+		seq_puts(m, "\nbreserved_tags:\n");
+		sbitmap_queue_show(&tags->breserved_tags, m);
+	}
+}
+
+static int hctx_tags_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct request_queue *q = hctx->queue;
+	int res;
+
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
+	if (hctx->tags)
+		blk_mq_debugfs_tags_show(m, hctx->tags);
+	mutex_unlock(&q->sysfs_lock);
+
+out:
+	return res;
+}
+
+static int hctx_tags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_tags_show, inode->i_private);
+}
+
+static const struct file_operations hctx_tags_fops = {
+	.open		= hctx_tags_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_tags_bitmap_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct request_queue *q = hctx->queue;
+	int res;
+
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
+	if (hctx->tags)
+		sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m);
+	mutex_unlock(&q->sysfs_lock);
+
+out:
+	return res;
+}
+
+static int hctx_tags_bitmap_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_tags_bitmap_show, inode->i_private);
+}
+
+static const struct file_operations hctx_tags_bitmap_fops = {
+	.open		= hctx_tags_bitmap_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_sched_tags_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct request_queue *q = hctx->queue;
+	int res;
+
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
+	if (hctx->sched_tags)
+		blk_mq_debugfs_tags_show(m, hctx->sched_tags);
+	mutex_unlock(&q->sysfs_lock);
+
+out:
+	return res;
+}
+
+static int hctx_sched_tags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_sched_tags_show, inode->i_private);
+}
+
+static const struct file_operations hctx_sched_tags_fops = {
+	.open		= hctx_sched_tags_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_sched_tags_bitmap_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct request_queue *q = hctx->queue;
+	int res;
+
+	res = mutex_lock_interruptible(&q->sysfs_lock);
+	if (res)
+		goto out;
+	if (hctx->sched_tags)
+		sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m);
+	mutex_unlock(&q->sysfs_lock);
+
+out:
+	return res;
+}
+
+static int hctx_sched_tags_bitmap_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_sched_tags_bitmap_show, inode->i_private);
+}
+
+static const struct file_operations hctx_sched_tags_bitmap_fops = {
+	.open		= hctx_sched_tags_bitmap_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_io_poll_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "considered=%lu\n", hctx->poll_considered);
+	seq_printf(m, "invoked=%lu\n", hctx->poll_invoked);
+	seq_printf(m, "success=%lu\n", hctx->poll_success);
+	return 0;
+}
+
+static int hctx_io_poll_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_io_poll_show, inode->i_private);
+}
+
+static ssize_t hctx_io_poll_write(struct file *file, const char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	hctx->poll_considered = hctx->poll_invoked = hctx->poll_success = 0;
+	return count;
+}
+
+static const struct file_operations hctx_io_poll_fops = {
+	.open		= hctx_io_poll_open,
+	.read		= seq_read,
+	.write		= hctx_io_poll_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
+{
+	seq_printf(m, "samples=%d, mean=%lld, min=%llu, max=%llu",
+		   stat->nr_samples, stat->mean, stat->min, stat->max);
+}
+
+static int hctx_stats_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_rq_stat stat[2];
+
+	blk_stat_init(&stat[BLK_STAT_READ]);
+	blk_stat_init(&stat[BLK_STAT_WRITE]);
+
+	blk_hctx_stat_get(hctx, stat);
+
+	seq_puts(m, "read: ");
+	print_stat(m, &stat[BLK_STAT_READ]);
+	seq_puts(m, "\n");
+
+	seq_puts(m, "write: ");
+	print_stat(m, &stat[BLK_STAT_WRITE]);
+	seq_puts(m, "\n");
+	return 0;
+}
+
+static int hctx_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_stats_show, inode->i_private);
+}
+
+static ssize_t hctx_stats_write(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_hw_ctx *hctx = m->private;
+	struct blk_mq_ctx *ctx;
+	int i;
+
+	hctx_for_each_ctx(hctx, ctx, i) {
+		blk_stat_init(&ctx->stat[BLK_STAT_READ]);
+		blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
+	}
+	return count;
+}
+
+static const struct file_operations hctx_stats_fops = {
+	.open		= hctx_stats_open,
+	.read		= seq_read,
+	.write		= hctx_stats_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_dispatched_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+	int i;
+
+	seq_printf(m, "%8u\t%lu\n", 0U, hctx->dispatched[0]);
+
+	for (i = 1; i < BLK_MQ_MAX_DISPATCH_ORDER - 1; i++) {
+		unsigned int d = 1U << (i - 1);
+
+		seq_printf(m, "%8u\t%lu\n", d, hctx->dispatched[i]);
+	}
+
+	seq_printf(m, "%8u+\t%lu\n", 1U << (i - 1), hctx->dispatched[i]);
+	return 0;
+}
+
+static int hctx_dispatched_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_dispatched_show, inode->i_private);
+}
+
+static ssize_t hctx_dispatched_write(struct file *file, const char __user *buf,
+				     size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_hw_ctx *hctx = m->private;
+	int i;
+
+	for (i = 0; i < BLK_MQ_MAX_DISPATCH_ORDER; i++)
+		hctx->dispatched[i] = 0;
+	return count;
+}
+
+static const struct file_operations hctx_dispatched_fops = {
+	.open		= hctx_dispatched_open,
+	.read		= seq_read,
+	.write		= hctx_dispatched_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_queued_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "%lu\n", hctx->queued);
+	return 0;
+}
+
+static int hctx_queued_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_queued_show, inode->i_private);
+}
+
+static ssize_t hctx_queued_write(struct file *file, const char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	hctx->queued = 0;
+	return count;
+}
+
+static const struct file_operations hctx_queued_fops = {
+	.open		= hctx_queued_open,
+	.read		= seq_read,
+	.write		= hctx_queued_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_run_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "%lu\n", hctx->run);
+	return 0;
+}
+
+static int hctx_run_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_run_show, inode->i_private);
+}
+
+static ssize_t hctx_run_write(struct file *file, const char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	hctx->run = 0;
+	return count;
+}
+
+static const struct file_operations hctx_run_fops = {
+	.open		= hctx_run_open,
+	.read		= seq_read,
+	.write		= hctx_run_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int hctx_active_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_hw_ctx *hctx = m->private;
+
+	seq_printf(m, "%d\n", atomic_read(&hctx->nr_active));
+	return 0;
+}
+
+static int hctx_active_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hctx_active_show, inode->i_private);
+}
+
+static const struct file_operations hctx_active_fops = {
+	.open		= hctx_active_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos)
+	__acquires(&ctx->lock)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	spin_lock(&ctx->lock);
+	return seq_list_start(&ctx->rq_list, *pos);
+}
+
+static void *ctx_rq_list_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	return seq_list_next(v, &ctx->rq_list, pos);
+}
+
+static void ctx_rq_list_stop(struct seq_file *m, void *v)
+	__releases(&ctx->lock)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	spin_unlock(&ctx->lock);
+}
+
+static const struct seq_operations ctx_rq_list_seq_ops = {
+	.start	= ctx_rq_list_start,
+	.next	= ctx_rq_list_next,
+	.stop	= ctx_rq_list_stop,
+	.show	= blk_mq_debugfs_rq_show,
+};
+
+static int ctx_rq_list_open(struct inode *inode, struct file *file)
+{
+	return blk_mq_debugfs_seq_open(inode, file, &ctx_rq_list_seq_ops);
+}
+
+static const struct file_operations ctx_rq_list_fops = {
+	.open		= ctx_rq_list_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int ctx_dispatched_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	seq_printf(m, "%lu %lu\n", ctx->rq_dispatched[1], ctx->rq_dispatched[0]);
+	return 0;
+}
+
+static int ctx_dispatched_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ctx_dispatched_show, inode->i_private);
+}
+
+static ssize_t ctx_dispatched_write(struct file *file, const char __user *buf,
+				    size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_ctx *ctx = m->private;
+
+	ctx->rq_dispatched[0] = ctx->rq_dispatched[1] = 0;
+	return count;
+}
+
+static const struct file_operations ctx_dispatched_fops = {
+	.open		= ctx_dispatched_open,
+	.read		= seq_read,
+	.write		= ctx_dispatched_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int ctx_merged_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	seq_printf(m, "%lu\n", ctx->rq_merged);
+	return 0;
+}
+
+static int ctx_merged_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ctx_merged_show, inode->i_private);
+}
+
+static ssize_t ctx_merged_write(struct file *file, const char __user *buf,
+				    size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_ctx *ctx = m->private;
+
+	ctx->rq_merged = 0;
+	return count;
+}
+
+static const struct file_operations ctx_merged_fops = {
+	.open		= ctx_merged_open,
+	.read		= seq_read,
+	.write		= ctx_merged_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int ctx_completed_show(struct seq_file *m, void *v)
+{
+	struct blk_mq_ctx *ctx = m->private;
+
+	seq_printf(m, "%lu %lu\n", ctx->rq_completed[1], ctx->rq_completed[0]);
+	return 0;
+}
+
+static int ctx_completed_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ctx_completed_show, inode->i_private);
+}
+
+static ssize_t ctx_completed_write(struct file *file, const char __user *buf,
+				   size_t count, loff_t *ppos)
+{
+	struct seq_file *m = file->private_data;
+	struct blk_mq_ctx *ctx = m->private;
+
+	ctx->rq_completed[0] = ctx->rq_completed[1] = 0;
+	return count;
+}
+
+static const struct file_operations ctx_completed_fops = {
+	.open		= ctx_completed_open,
+	.read		= seq_read,
+	.write		= ctx_completed_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
+	{"state", 0400, &hctx_state_fops},
+	{"flags", 0400, &hctx_flags_fops},
+	{"dispatch", 0400, &hctx_dispatch_fops},
+	{"ctx_map", 0400, &hctx_ctx_map_fops},
+	{"tags", 0400, &hctx_tags_fops},
+	{"tags_bitmap", 0400, &hctx_tags_bitmap_fops},
+	{"sched_tags", 0400, &hctx_sched_tags_fops},
+	{"sched_tags_bitmap", 0400, &hctx_sched_tags_bitmap_fops},
+	{"io_poll", 0600, &hctx_io_poll_fops},
+	{"stats", 0600, &hctx_stats_fops},
+	{"dispatched", 0600, &hctx_dispatched_fops},
+	{"queued", 0600, &hctx_queued_fops},
+	{"run", 0600, &hctx_run_fops},
+	{"active", 0400, &hctx_active_fops},
+	{},
+};
+
+static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
+	{"rq_list", 0400, &ctx_rq_list_fops},
+	{"dispatched", 0600, &ctx_dispatched_fops},
+	{"merged", 0600, &ctx_merged_fops},
+	{"completed", 0600, &ctx_completed_fops},
+	{},
+};
+
+int blk_mq_debugfs_register(struct request_queue *q, const char *name)
+{
+	if (!blk_debugfs_root)
+		return -ENOENT;
+
+	q->debugfs_dir = debugfs_create_dir(name, blk_debugfs_root);
+	if (!q->debugfs_dir)
+		goto err;
+
+	if (blk_mq_debugfs_register_hctxs(q))
+		goto err;
+
+	return 0;
+
+err:
+	blk_mq_debugfs_unregister(q);
+	return -ENOMEM;
+}
+
+void blk_mq_debugfs_unregister(struct request_queue *q)
+{
+	debugfs_remove_recursive(q->debugfs_dir);
+	q->mq_debugfs_dir = NULL;
+	q->debugfs_dir = NULL;
+}
+
+static bool debugfs_create_files(struct dentry *parent, void *data,
+				const struct blk_mq_debugfs_attr *attr)
+{
+	for (; attr->name; attr++) {
+		if (!debugfs_create_file(attr->name, attr->mode, parent,
+					 data, attr->fops))
+			return false;
+	}
+	return true;
+}
+
+static int blk_mq_debugfs_register_ctx(struct request_queue *q,
+				       struct blk_mq_ctx *ctx,
+				       struct dentry *hctx_dir)
+{
+	struct dentry *ctx_dir;
+	char name[20];
+
+	snprintf(name, sizeof(name), "cpu%u", ctx->cpu);
+	ctx_dir = debugfs_create_dir(name, hctx_dir);
+	if (!ctx_dir)
+		return -ENOMEM;
+
+	if (!debugfs_create_files(ctx_dir, ctx, blk_mq_debugfs_ctx_attrs))
+		return -ENOMEM;
+
+	return 0;
+}
+
+static int blk_mq_debugfs_register_hctx(struct request_queue *q,
+					struct blk_mq_hw_ctx *hctx)
+{
+	struct blk_mq_ctx *ctx;
+	struct dentry *hctx_dir;
+	char name[20];
+	int i;
+
+	snprintf(name, sizeof(name), "%u", hctx->queue_num);
+	hctx_dir = debugfs_create_dir(name, q->mq_debugfs_dir);
+	if (!hctx_dir)
+		return -ENOMEM;
+
+	if (!debugfs_create_files(hctx_dir, hctx, blk_mq_debugfs_hctx_attrs))
+		return -ENOMEM;
+
+	hctx_for_each_ctx(hctx, ctx, i) {
+		if (blk_mq_debugfs_register_ctx(q, ctx, hctx_dir))
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	if (!q->debugfs_dir)
+		return -ENOENT;
+
+	q->mq_debugfs_dir = debugfs_create_dir("mq", q->debugfs_dir);
+	if (!q->mq_debugfs_dir)
+		goto err;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (blk_mq_debugfs_register_hctx(q, hctx))
+			goto err;
+	}
+
+	return 0;
+
+err:
+	blk_mq_debugfs_unregister_hctxs(q);
+	return -ENOMEM;
+}
+
+void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+{
+	debugfs_remove_recursive(q->mq_debugfs_dir);
+	q->mq_debugfs_dir = NULL;
+}
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
new file mode 100644
index 000000000000..9e8d6795a8c1
--- /dev/null
+++ b/block/blk-mq-sched.c
@@ -0,0 +1,515 @@
+/*
+ * blk-mq scheduling framework
+ *
+ * Copyright (C) 2016 Jens Axboe
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/blk-mq.h>
+
+#include <trace/events/block.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-sched.h"
+#include "blk-mq-tag.h"
+#include "blk-wbt.h"
+
+void blk_mq_sched_free_hctx_data(struct request_queue *q,
+				 void (*exit)(struct blk_mq_hw_ctx *))
+{
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (exit && hctx->sched_data)
+			exit(hctx);
+		kfree(hctx->sched_data);
+		hctx->sched_data = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
+
+int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
+				int (*init)(struct blk_mq_hw_ctx *),
+				void (*exit)(struct blk_mq_hw_ctx *))
+{
+	struct blk_mq_hw_ctx *hctx;
+	int ret;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		hctx->sched_data = kmalloc_node(size, GFP_KERNEL, hctx->numa_node);
+		if (!hctx->sched_data) {
+			ret = -ENOMEM;
+			goto error;
+		}
+
+		if (init) {
+			ret = init(hctx);
+			if (ret) {
+				/*
+				 * We don't want to give exit() a partially
+				 * initialized sched_data. init() must clean up
+				 * if it fails.
+				 */
+				kfree(hctx->sched_data);
+				hctx->sched_data = NULL;
+				goto error;
+			}
+		}
+	}
+
+	return 0;
+error:
+	blk_mq_sched_free_hctx_data(q, exit);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data);
+
+static void __blk_mq_sched_assign_ioc(struct request_queue *q,
+				      struct request *rq,
+				      struct bio *bio,
+				      struct io_context *ioc)
+{
+	struct io_cq *icq;
+
+	spin_lock_irq(q->queue_lock);
+	icq = ioc_lookup_icq(ioc, q);
+	spin_unlock_irq(q->queue_lock);
+
+	if (!icq) {
+		icq = ioc_create_icq(ioc, q, GFP_ATOMIC);
+		if (!icq)
+			return;
+	}
+
+	rq->elv.icq = icq;
+	if (!blk_mq_sched_get_rq_priv(q, rq, bio)) {
+		rq->rq_flags |= RQF_ELVPRIV;
+		get_io_context(icq->ioc);
+		return;
+	}
+
+	rq->elv.icq = NULL;
+}
+
+static void blk_mq_sched_assign_ioc(struct request_queue *q,
+				    struct request *rq, struct bio *bio)
+{
+	struct io_context *ioc;
+
+	ioc = rq_ioc(bio);
+	if (ioc)
+		__blk_mq_sched_assign_ioc(q, rq, bio, ioc);
+}
+
+struct request *blk_mq_sched_get_request(struct request_queue *q,
+					 struct bio *bio,
+					 unsigned int op,
+					 struct blk_mq_alloc_data *data)
+{
+	struct elevator_queue *e = q->elevator;
+	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_ctx *ctx;
+	struct request *rq;
+
+	blk_queue_enter_live(q);
+	ctx = blk_mq_get_ctx(q);
+	hctx = blk_mq_map_queue(q, ctx->cpu);
+
+	blk_mq_set_alloc_data(data, q, data->flags, ctx, hctx);
+
+	if (e) {
+		data->flags |= BLK_MQ_REQ_INTERNAL;
+
+		/*
+		 * Flush requests are special and go directly to the
+		 * dispatch list.
+		 */
+		if (!op_is_flush(op) && e->type->ops.mq.get_request) {
+			rq = e->type->ops.mq.get_request(q, op, data);
+			if (rq)
+				rq->rq_flags |= RQF_QUEUED;
+		} else
+			rq = __blk_mq_alloc_request(data, op);
+	} else {
+		rq = __blk_mq_alloc_request(data, op);
+		if (rq)
+			data->hctx->tags->rqs[rq->tag] = rq;
+	}
+
+	if (rq) {
+		if (!op_is_flush(op)) {
+			rq->elv.icq = NULL;
+			if (e && e->type->icq_cache)
+				blk_mq_sched_assign_ioc(q, rq, bio);
+		}
+		data->hctx->queued++;
+		return rq;
+	}
+
+	blk_queue_exit(q);
+	return NULL;
+}
+
+void blk_mq_sched_put_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+
+	if (rq->rq_flags & RQF_ELVPRIV) {
+		blk_mq_sched_put_rq_priv(rq->q, rq);
+		if (rq->elv.icq) {
+			put_io_context(rq->elv.icq->ioc);
+			rq->elv.icq = NULL;
+		}
+	}
+
+	if ((rq->rq_flags & RQF_QUEUED) && e && e->type->ops.mq.put_request)
+		e->type->ops.mq.put_request(rq);
+	else
+		blk_mq_finish_request(rq);
+}
+
+void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
+{
+	struct elevator_queue *e = hctx->queue->elevator;
+	const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
+	bool did_work = false;
+	LIST_HEAD(rq_list);
+
+	if (unlikely(blk_mq_hctx_stopped(hctx)))
+		return;
+
+	hctx->run++;
+
+	/*
+	 * If we have previous entries on our dispatch list, grab them first for
+	 * more fair dispatch.
+	 */
+	if (!list_empty_careful(&hctx->dispatch)) {
+		spin_lock(&hctx->lock);
+		if (!list_empty(&hctx->dispatch))
+			list_splice_init(&hctx->dispatch, &rq_list);
+		spin_unlock(&hctx->lock);
+	}
+
+	/*
+	 * Only ask the scheduler for requests, if we didn't have residual
+	 * requests from the dispatch list. This is to avoid the case where
+	 * we only ever dispatch a fraction of the requests available because
+	 * of low device queue depth. Once we pull requests out of the IO
+	 * scheduler, we can no longer merge or sort them. So it's best to
+	 * leave them there for as long as we can. Mark the hw queue as
+	 * needing a restart in that case.
+	 */
+	if (!list_empty(&rq_list)) {
+		blk_mq_sched_mark_restart(hctx);
+		did_work = blk_mq_dispatch_rq_list(hctx, &rq_list);
+	} else if (!has_sched_dispatch) {
+		blk_mq_flush_busy_ctxs(hctx, &rq_list);
+		blk_mq_dispatch_rq_list(hctx, &rq_list);
+	}
+
+	/*
+	 * We want to dispatch from the scheduler if we had no work left
+	 * on the dispatch list, OR if we did have work but weren't able
+	 * to make progress.
+	 */
+	if (!did_work && has_sched_dispatch) {
+		do {
+			struct request *rq;
+
+			rq = e->type->ops.mq.dispatch_request(hctx);
+			if (!rq)
+				break;
+			list_add(&rq->queuelist, &rq_list);
+		} while (blk_mq_dispatch_rq_list(hctx, &rq_list));
+	}
+}
+
+void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
+				   struct list_head *rq_list,
+				   struct request *(*get_rq)(struct blk_mq_hw_ctx *))
+{
+	do {
+		struct request *rq;
+
+		rq = get_rq(hctx);
+		if (!rq)
+			break;
+
+		list_add_tail(&rq->queuelist, rq_list);
+	} while (1);
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_move_to_dispatch);
+
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
+			    struct request **merged_request)
+{
+	struct request *rq;
+
+	switch (elv_merge(q, &rq, bio)) {
+	case ELEVATOR_BACK_MERGE:
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			return false;
+		if (!bio_attempt_back_merge(q, rq, bio))
+			return false;
+		*merged_request = attempt_back_merge(q, rq);
+		if (!*merged_request)
+			elv_merged_request(q, rq, ELEVATOR_BACK_MERGE);
+		return true;
+	case ELEVATOR_FRONT_MERGE:
+		if (!blk_mq_sched_allow_merge(q, rq, bio))
+			return false;
+		if (!bio_attempt_front_merge(q, rq, bio))
+			return false;
+		*merged_request = attempt_front_merge(q, rq);
+		if (!*merged_request)
+			elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE);
+		return true;
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
+
+bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e->type->ops.mq.bio_merge) {
+		struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
+		struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+
+		blk_mq_put_ctx(ctx);
+		return e->type->ops.mq.bio_merge(hctx, bio);
+	}
+
+	return false;
+}
+
+bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq)
+{
+	return rq_mergeable(rq) && elv_attempt_insert_merge(q, rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge);
+
+void blk_mq_sched_request_inserted(struct request *rq)
+{
+	trace_block_rq_insert(rq->q, rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
+
+static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
+				       struct request *rq)
+{
+	if (rq->tag == -1) {
+		rq->rq_flags |= RQF_SORTED;
+		return false;
+	}
+
+	/*
+	 * If we already have a real request tag, send directly to
+	 * the dispatch list.
+	 */
+	spin_lock(&hctx->lock);
+	list_add(&rq->queuelist, &hctx->dispatch);
+	spin_unlock(&hctx->lock);
+	return true;
+}
+
+static void blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+{
+	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
+		clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+		if (blk_mq_hctx_has_pending(hctx))
+			blk_mq_run_hw_queue(hctx, true);
+	}
+}
+
+void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx)
+{
+	unsigned int i;
+
+	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED))
+		blk_mq_sched_restart_hctx(hctx);
+	else {
+		struct request_queue *q = hctx->queue;
+
+		if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
+			return;
+
+		clear_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
+
+		queue_for_each_hw_ctx(q, hctx, i)
+			blk_mq_sched_restart_hctx(hctx);
+	}
+}
+
+/*
+ * Add flush/fua to the queue. If we fail getting a driver tag, then
+ * punt to the requeue list. Requeue will re-invoke us from a context
+ * that's safe to block from.
+ */
+static void blk_mq_sched_insert_flush(struct blk_mq_hw_ctx *hctx,
+				      struct request *rq, bool can_block)
+{
+	if (blk_mq_get_driver_tag(rq, &hctx, can_block)) {
+		blk_insert_flush(rq);
+		blk_mq_run_hw_queue(hctx, true);
+	} else
+		blk_mq_add_to_requeue_list(rq, false, true);
+}
+
+void blk_mq_sched_insert_request(struct request *rq, bool at_head,
+				 bool run_queue, bool async, bool can_block)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+
+	if (rq->tag == -1 && op_is_flush(rq->cmd_flags)) {
+		blk_mq_sched_insert_flush(hctx, rq, can_block);
+		return;
+	}
+
+	if (e && blk_mq_sched_bypass_insert(hctx, rq))
+		goto run;
+
+	if (e && e->type->ops.mq.insert_requests) {
+		LIST_HEAD(list);
+
+		list_add(&rq->queuelist, &list);
+		e->type->ops.mq.insert_requests(hctx, &list, at_head);
+	} else {
+		spin_lock(&ctx->lock);
+		__blk_mq_insert_request(hctx, rq, at_head);
+		spin_unlock(&ctx->lock);
+	}
+
+run:
+	if (run_queue)
+		blk_mq_run_hw_queue(hctx, async);
+}
+
+void blk_mq_sched_insert_requests(struct request_queue *q,
+				  struct blk_mq_ctx *ctx,
+				  struct list_head *list, bool run_queue_async)
+{
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (e) {
+		struct request *rq, *next;
+
+		/*
+		 * We bypass requests that already have a driver tag assigned,
+		 * which should only be flushes. Flushes are only ever inserted
+		 * as single requests, so we shouldn't ever hit the
+		 * WARN_ON_ONCE() below (but let's handle it just in case).
+		 */
+		list_for_each_entry_safe(rq, next, list, queuelist) {
+			if (WARN_ON_ONCE(rq->tag != -1)) {
+				list_del_init(&rq->queuelist);
+				blk_mq_sched_bypass_insert(hctx, rq);
+			}
+		}
+	}
+
+	if (e && e->type->ops.mq.insert_requests)
+		e->type->ops.mq.insert_requests(hctx, list, false);
+	else
+		blk_mq_insert_requests(hctx, ctx, list);
+
+	blk_mq_run_hw_queue(hctx, run_queue_async);
+}
+
+static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
+				   struct blk_mq_hw_ctx *hctx,
+				   unsigned int hctx_idx)
+{
+	if (hctx->sched_tags) {
+		blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx);
+		blk_mq_free_rq_map(hctx->sched_tags);
+		hctx->sched_tags = NULL;
+	}
+}
+
+int blk_mq_sched_setup(struct request_queue *q)
+{
+	struct blk_mq_tag_set *set = q->tag_set;
+	struct blk_mq_hw_ctx *hctx;
+	int ret, i;
+
+	/*
+	 * Default to 256, since we don't split into sync/async like the
+	 * old code did. Additionally, this is a per-hw queue depth.
+	 */
+	q->nr_requests = 2 * BLKDEV_MAX_RQ;
+
+	/*
+	 * We're switching to using an IO scheduler, so setup the hctx
+	 * scheduler tags and switch the request map from the regular
+	 * tags to scheduler tags. First allocate what we need, so we
+	 * can safely fail and fallback, if needed.
+	 */
+	ret = 0;
+	queue_for_each_hw_ctx(q, hctx, i) {
+		hctx->sched_tags = blk_mq_alloc_rq_map(set, i, q->nr_requests, 0);
+		if (!hctx->sched_tags) {
+			ret = -ENOMEM;
+			break;
+		}
+		ret = blk_mq_alloc_rqs(set, hctx->sched_tags, i, q->nr_requests);
+		if (ret)
+			break;
+	}
+
+	/*
+	 * If we failed, free what we did allocate
+	 */
+	if (ret) {
+		queue_for_each_hw_ctx(q, hctx, i) {
+			if (!hctx->sched_tags)
+				continue;
+			blk_mq_sched_free_tags(set, hctx, i);
+		}
+
+		return ret;
+	}
+
+	return 0;
+}
+
+void blk_mq_sched_teardown(struct request_queue *q)
+{
+	struct blk_mq_tag_set *set = q->tag_set;
+	struct blk_mq_hw_ctx *hctx;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i)
+		blk_mq_sched_free_tags(set, hctx, i);
+}
+
+int blk_mq_sched_init(struct request_queue *q)
+{
+	int ret;
+
+#if defined(CONFIG_DEFAULT_SQ_NONE)
+	if (q->nr_hw_queues == 1)
+		return 0;
+#endif
+#if defined(CONFIG_DEFAULT_MQ_NONE)
+	if (q->nr_hw_queues > 1)
+		return 0;
+#endif
+
+	mutex_lock(&q->sysfs_lock);
+	ret = elevator_init(q, NULL);
+	mutex_unlock(&q->sysfs_lock);
+
+	return ret;
+}
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
new file mode 100644
index 000000000000..7b5f3b95c78e
--- /dev/null
+++ b/block/blk-mq-sched.h
@@ -0,0 +1,143 @@
+#ifndef BLK_MQ_SCHED_H
+#define BLK_MQ_SCHED_H
+
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+
+int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
+				int (*init)(struct blk_mq_hw_ctx *),
+				void (*exit)(struct blk_mq_hw_ctx *));
+
+void blk_mq_sched_free_hctx_data(struct request_queue *q,
+				 void (*exit)(struct blk_mq_hw_ctx *));
+
+struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bio, unsigned int op, struct blk_mq_alloc_data *data);
+void blk_mq_sched_put_request(struct request *rq);
+
+void blk_mq_sched_request_inserted(struct request *rq);
+bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
+				struct request **merged_request);
+bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio);
+bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq);
+void blk_mq_sched_restart_queues(struct blk_mq_hw_ctx *hctx);
+
+void blk_mq_sched_insert_request(struct request *rq, bool at_head,
+				 bool run_queue, bool async, bool can_block);
+void blk_mq_sched_insert_requests(struct request_queue *q,
+				  struct blk_mq_ctx *ctx,
+				  struct list_head *list, bool run_queue_async);
+
+void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
+void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
+			struct list_head *rq_list,
+			struct request *(*get_rq)(struct blk_mq_hw_ctx *));
+
+int blk_mq_sched_setup(struct request_queue *q);
+void blk_mq_sched_teardown(struct request_queue *q);
+
+int blk_mq_sched_init(struct request_queue *q);
+
+static inline bool
+blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (!e || blk_queue_nomerges(q) || !bio_mergeable(bio))
+		return false;
+
+	return __blk_mq_sched_bio_merge(q, bio);
+}
+
+static inline int blk_mq_sched_get_rq_priv(struct request_queue *q,
+					   struct request *rq,
+					   struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.get_rq_priv)
+		return e->type->ops.mq.get_rq_priv(q, rq, bio);
+
+	return 0;
+}
+
+static inline void blk_mq_sched_put_rq_priv(struct request_queue *q,
+					    struct request *rq)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.put_rq_priv)
+		e->type->ops.mq.put_rq_priv(q, rq);
+}
+
+static inline bool
+blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
+			 struct bio *bio)
+{
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.allow_merge)
+		return e->type->ops.mq.allow_merge(q, rq, bio);
+
+	return true;
+}
+
+static inline void
+blk_mq_sched_completed_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
+{
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (e && e->type->ops.mq.completed_request)
+		e->type->ops.mq.completed_request(hctx, rq);
+
+	BUG_ON(rq->internal_tag == -1);
+
+	blk_mq_put_tag(hctx, hctx->sched_tags, rq->mq_ctx, rq->internal_tag);
+}
+
+static inline void blk_mq_sched_started_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.started_request)
+		e->type->ops.mq.started_request(rq);
+}
+
+static inline void blk_mq_sched_requeue_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+
+	if (e && e->type->ops.mq.requeue_request)
+		e->type->ops.mq.requeue_request(rq);
+}
+
+static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct elevator_queue *e = hctx->queue->elevator;
+
+	if (e && e->type->ops.mq.has_work)
+		return e->type->ops.mq.has_work(hctx);
+
+	return false;
+}
+
+static inline void blk_mq_sched_mark_restart(struct blk_mq_hw_ctx *hctx)
+{
+	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) {
+		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+		if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
+			struct request_queue *q = hctx->queue;
+
+			if (!test_bit(QUEUE_FLAG_RESTART, &q->queue_flags))
+				set_bit(QUEUE_FLAG_RESTART, &q->queue_flags);
+		}
+	}
+}
+
+static inline bool blk_mq_sched_needs_restart(struct blk_mq_hw_ctx *hctx)
+{
+	return test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+}
+
+#endif
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index eacd3af72099..295e69670c39 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -122,123 +122,16 @@ static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj,
 	return res;
 }
 
-static ssize_t blk_mq_sysfs_dispatched_show(struct blk_mq_ctx *ctx, char *page)
-{
-	return sprintf(page, "%lu %lu\n", ctx->rq_dispatched[1],
-				ctx->rq_dispatched[0]);
-}
-
-static ssize_t blk_mq_sysfs_merged_show(struct blk_mq_ctx *ctx, char *page)
-{
-	return sprintf(page, "%lu\n", ctx->rq_merged);
-}
-
-static ssize_t blk_mq_sysfs_completed_show(struct blk_mq_ctx *ctx, char *page)
-{
-	return sprintf(page, "%lu %lu\n", ctx->rq_completed[1],
-				ctx->rq_completed[0]);
-}
-
-static ssize_t sysfs_list_show(char *page, struct list_head *list, char *msg)
-{
-	struct request *rq;
-	int len = snprintf(page, PAGE_SIZE - 1, "%s:\n", msg);
-
-	list_for_each_entry(rq, list, queuelist) {
-		const int rq_len = 2 * sizeof(rq) + 2;
-
-		/* if the output will be truncated */
-		if (PAGE_SIZE - 1 < len + rq_len) {
-			/* backspacing if it can't hold '\t...\n' */
-			if (PAGE_SIZE - 1 < len + 5)
-				len -= rq_len;
-			len += snprintf(page + len, PAGE_SIZE - 1 - len,
-					"\t...\n");
-			break;
-		}
-		len += snprintf(page + len, PAGE_SIZE - 1 - len,
-				"\t%p\n", rq);
-	}
-
-	return len;
-}
-
-static ssize_t blk_mq_sysfs_rq_list_show(struct blk_mq_ctx *ctx, char *page)
-{
-	ssize_t ret;
-
-	spin_lock(&ctx->lock);
-	ret = sysfs_list_show(page, &ctx->rq_list, "CTX pending");
-	spin_unlock(&ctx->lock);
-
-	return ret;
-}
-
-static ssize_t blk_mq_hw_sysfs_poll_show(struct blk_mq_hw_ctx *hctx, char *page)
-{
-	return sprintf(page, "considered=%lu, invoked=%lu, success=%lu\n",
-		       hctx->poll_considered, hctx->poll_invoked,
-		       hctx->poll_success);
-}
-
-static ssize_t blk_mq_hw_sysfs_poll_store(struct blk_mq_hw_ctx *hctx,
-					  const char *page, size_t size)
-{
-	hctx->poll_considered = hctx->poll_invoked = hctx->poll_success = 0;
-
-	return size;
-}
-
-static ssize_t blk_mq_hw_sysfs_queued_show(struct blk_mq_hw_ctx *hctx,
-					   char *page)
-{
-	return sprintf(page, "%lu\n", hctx->queued);
-}
-
-static ssize_t blk_mq_hw_sysfs_run_show(struct blk_mq_hw_ctx *hctx, char *page)
-{
-	return sprintf(page, "%lu\n", hctx->run);
-}
-
-static ssize_t blk_mq_hw_sysfs_dispatched_show(struct blk_mq_hw_ctx *hctx,
-					       char *page)
-{
-	char *start_page = page;
-	int i;
-
-	page += sprintf(page, "%8u\t%lu\n", 0U, hctx->dispatched[0]);
-
-	for (i = 1; i < BLK_MQ_MAX_DISPATCH_ORDER - 1; i++) {
-		unsigned int d = 1U << (i - 1);
-
-		page += sprintf(page, "%8u\t%lu\n", d, hctx->dispatched[i]);
-	}
-
-	page += sprintf(page, "%8u+\t%lu\n", 1U << (i - 1),
-						hctx->dispatched[i]);
-	return page - start_page;
-}
-
-static ssize_t blk_mq_hw_sysfs_rq_list_show(struct blk_mq_hw_ctx *hctx,
+static ssize_t blk_mq_hw_sysfs_nr_tags_show(struct blk_mq_hw_ctx *hctx,
 					    char *page)
 {
-	ssize_t ret;
-
-	spin_lock(&hctx->lock);
-	ret = sysfs_list_show(page, &hctx->dispatch, "HCTX pending");
-	spin_unlock(&hctx->lock);
-
-	return ret;
+	return sprintf(page, "%u\n", hctx->tags->nr_tags);
 }
 
-static ssize_t blk_mq_hw_sysfs_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
+static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx,
+						     char *page)
 {
-	return blk_mq_tag_sysfs_show(hctx->tags, page);
-}
-
-static ssize_t blk_mq_hw_sysfs_active_show(struct blk_mq_hw_ctx *hctx, char *page)
-{
-	return sprintf(page, "%u\n", atomic_read(&hctx->nr_active));
+	return sprintf(page, "%u\n", hctx->tags->nr_reserved_tags);
 }
 
 static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
@@ -259,121 +152,27 @@ static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 	return ret;
 }
 
-static void blk_mq_stat_clear(struct blk_mq_hw_ctx *hctx)
-{
-	struct blk_mq_ctx *ctx;
-	unsigned int i;
-
-	hctx_for_each_ctx(hctx, ctx, i) {
-		blk_stat_init(&ctx->stat[BLK_STAT_READ]);
-		blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
-	}
-}
-
-static ssize_t blk_mq_hw_sysfs_stat_store(struct blk_mq_hw_ctx *hctx,
-					  const char *page, size_t count)
-{
-	blk_mq_stat_clear(hctx);
-	return count;
-}
-
-static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre)
-{
-	return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n",
-			pre, (long long) stat->nr_samples,
-			(long long) stat->mean, (long long) stat->min,
-			(long long) stat->max);
-}
-
-static ssize_t blk_mq_hw_sysfs_stat_show(struct blk_mq_hw_ctx *hctx, char *page)
-{
-	struct blk_rq_stat stat[2];
-	ssize_t ret;
-
-	blk_stat_init(&stat[BLK_STAT_READ]);
-	blk_stat_init(&stat[BLK_STAT_WRITE]);
-
-	blk_hctx_stat_get(hctx, stat);
-
-	ret = print_stat(page, &stat[BLK_STAT_READ], "read :");
-	ret += print_stat(page + ret, &stat[BLK_STAT_WRITE], "write:");
-	return ret;
-}
-
-static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_dispatched = {
-	.attr = {.name = "dispatched", .mode = S_IRUGO },
-	.show = blk_mq_sysfs_dispatched_show,
-};
-static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_merged = {
-	.attr = {.name = "merged", .mode = S_IRUGO },
-	.show = blk_mq_sysfs_merged_show,
-};
-static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_completed = {
-	.attr = {.name = "completed", .mode = S_IRUGO },
-	.show = blk_mq_sysfs_completed_show,
-};
-static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_rq_list = {
-	.attr = {.name = "rq_list", .mode = S_IRUGO },
-	.show = blk_mq_sysfs_rq_list_show,
-};
-
 static struct attribute *default_ctx_attrs[] = {
-	&blk_mq_sysfs_dispatched.attr,
-	&blk_mq_sysfs_merged.attr,
-	&blk_mq_sysfs_completed.attr,
-	&blk_mq_sysfs_rq_list.attr,
 	NULL,
 };
 
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_queued = {
-	.attr = {.name = "queued", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_queued_show,
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = {
+	.attr = {.name = "nr_tags", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_nr_tags_show,
 };
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_run = {
-	.attr = {.name = "run", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_run_show,
-};
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_dispatched = {
-	.attr = {.name = "dispatched", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_dispatched_show,
-};
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_active = {
-	.attr = {.name = "active", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_active_show,
-};
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_pending = {
-	.attr = {.name = "pending", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_rq_list_show,
-};
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_tags = {
-	.attr = {.name = "tags", .mode = S_IRUGO },
-	.show = blk_mq_hw_sysfs_tags_show,
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_reserved_tags = {
+	.attr = {.name = "nr_reserved_tags", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_nr_reserved_tags_show,
 };
 static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_cpus = {
 	.attr = {.name = "cpu_list", .mode = S_IRUGO },
 	.show = blk_mq_hw_sysfs_cpus_show,
 };
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_poll = {
-	.attr = {.name = "io_poll", .mode = S_IWUSR | S_IRUGO },
-	.show = blk_mq_hw_sysfs_poll_show,
-	.store = blk_mq_hw_sysfs_poll_store,
-};
-static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_stat = {
-	.attr = {.name = "stats", .mode = S_IRUGO | S_IWUSR },
-	.show = blk_mq_hw_sysfs_stat_show,
-	.store = blk_mq_hw_sysfs_stat_store,
-};
 
 static struct attribute *default_hw_ctx_attrs[] = {
-	&blk_mq_hw_sysfs_queued.attr,
-	&blk_mq_hw_sysfs_run.attr,
-	&blk_mq_hw_sysfs_dispatched.attr,
-	&blk_mq_hw_sysfs_pending.attr,
-	&blk_mq_hw_sysfs_tags.attr,
+	&blk_mq_hw_sysfs_nr_tags.attr,
+	&blk_mq_hw_sysfs_nr_reserved_tags.attr,
 	&blk_mq_hw_sysfs_cpus.attr,
-	&blk_mq_hw_sysfs_active.attr,
-	&blk_mq_hw_sysfs_poll.attr,
-	&blk_mq_hw_sysfs_stat.attr,
 	NULL,
 };
 
@@ -455,6 +254,8 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 		kobject_put(&hctx->kobj);
 	}
 
+	blk_mq_debugfs_unregister_hctxs(q);
+
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);
 	kobject_put(&q->mq_kobj);
@@ -504,6 +305,8 @@ int blk_mq_register_dev(struct device *dev, struct request_queue *q)
 
 	kobject_uevent(&q->mq_kobj, KOBJ_ADD);
 
+	blk_mq_debugfs_register(q, kobject_name(&dev->kobj));
+
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
@@ -529,6 +332,8 @@ void blk_mq_sysfs_unregister(struct request_queue *q)
 	if (!q->mq_sysfs_init_done)
 		return;
 
+	blk_mq_debugfs_unregister_hctxs(q);
+
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
 }
@@ -541,6 +346,8 @@ int blk_mq_sysfs_register(struct request_queue *q)
 	if (!q->mq_sysfs_init_done)
 		return ret;
 
+	blk_mq_debugfs_register_hctxs(q);
+
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index dcf5ce3ba4bf..54c84363c1b2 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -90,113 +90,97 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	return atomic_read(&hctx->nr_active) < depth;
 }
 
-static int __bt_get(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt)
+static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
+			    struct sbitmap_queue *bt)
 {
-	if (!hctx_may_queue(hctx, bt))
+	if (!(data->flags & BLK_MQ_REQ_INTERNAL) &&
+	    !hctx_may_queue(data->hctx, bt))
 		return -1;
 	return __sbitmap_queue_get(bt);
 }
 
-static int bt_get(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt,
-		  struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags)
+unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 {
+	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+	struct sbitmap_queue *bt;
 	struct sbq_wait_state *ws;
 	DEFINE_WAIT(wait);
+	unsigned int tag_offset;
+	bool drop_ctx;
 	int tag;
 
-	tag = __bt_get(hctx, bt);
+	if (data->flags & BLK_MQ_REQ_RESERVED) {
+		if (unlikely(!tags->nr_reserved_tags)) {
+			WARN_ON_ONCE(1);
+			return BLK_MQ_TAG_FAIL;
+		}
+		bt = &tags->breserved_tags;
+		tag_offset = 0;
+	} else {
+		bt = &tags->bitmap_tags;
+		tag_offset = tags->nr_reserved_tags;
+	}
+
+	tag = __blk_mq_get_tag(data, bt);
 	if (tag != -1)
-		return tag;
+		goto found_tag;
 
 	if (data->flags & BLK_MQ_REQ_NOWAIT)
-		return -1;
+		return BLK_MQ_TAG_FAIL;
 
-	ws = bt_wait_ptr(bt, hctx);
+	ws = bt_wait_ptr(bt, data->hctx);
+	drop_ctx = data->ctx == NULL;
 	do {
 		prepare_to_wait(&ws->wait, &wait, TASK_UNINTERRUPTIBLE);
 
-		tag = __bt_get(hctx, bt);
+		tag = __blk_mq_get_tag(data, bt);
 		if (tag != -1)
 			break;
 
 		/*
 		 * We're out of tags on this hardware queue, kick any
 		 * pending IO submits before going to sleep waiting for
-		 * some to complete. Note that hctx can be NULL here for
-		 * reserved tag allocation.
+		 * some to complete.
 		 */
-		if (hctx)
-			blk_mq_run_hw_queue(hctx, false);
+		blk_mq_run_hw_queue(data->hctx, false);
 
 		/*
 		 * Retry tag allocation after running the hardware queue,
 		 * as running the queue may also have found completions.
 		 */
-		tag = __bt_get(hctx, bt);
+		tag = __blk_mq_get_tag(data, bt);
 		if (tag != -1)
 			break;
 
-		blk_mq_put_ctx(data->ctx);
+		if (data->ctx)
+			blk_mq_put_ctx(data->ctx);
 
 		io_schedule();
 
 		data->ctx = blk_mq_get_ctx(data->q);
 		data->hctx = blk_mq_map_queue(data->q, data->ctx->cpu);
-		if (data->flags & BLK_MQ_REQ_RESERVED) {
-			bt = &data->hctx->tags->breserved_tags;
-		} else {
-			hctx = data->hctx;
-			bt = &hctx->tags->bitmap_tags;
-		}
+		tags = blk_mq_tags_from_data(data);
+		if (data->flags & BLK_MQ_REQ_RESERVED)
+			bt = &tags->breserved_tags;
+		else
+			bt = &tags->bitmap_tags;
+
 		finish_wait(&ws->wait, &wait);
-		ws = bt_wait_ptr(bt, hctx);
+		ws = bt_wait_ptr(bt, data->hctx);
 	} while (1);
 
-	finish_wait(&ws->wait, &wait);
-	return tag;
-}
-
-static unsigned int __blk_mq_get_tag(struct blk_mq_alloc_data *data)
-{
-	int tag;
-
-	tag = bt_get(data, &data->hctx->tags->bitmap_tags, data->hctx,
-		     data->hctx->tags);
-	if (tag >= 0)
-		return tag + data->hctx->tags->nr_reserved_tags;
-
-	return BLK_MQ_TAG_FAIL;
-}
-
-static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_alloc_data *data)
-{
-	int tag;
-
-	if (unlikely(!data->hctx->tags->nr_reserved_tags)) {
-		WARN_ON_ONCE(1);
-		return BLK_MQ_TAG_FAIL;
-	}
-
-	tag = bt_get(data, &data->hctx->tags->breserved_tags, NULL,
-		     data->hctx->tags);
-	if (tag < 0)
-		return BLK_MQ_TAG_FAIL;
+	if (drop_ctx && data->ctx)
+		blk_mq_put_ctx(data->ctx);
 
-	return tag;
-}
+	finish_wait(&ws->wait, &wait);
 
-unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
-{
-	if (data->flags & BLK_MQ_REQ_RESERVED)
-		return __blk_mq_get_reserved_tag(data);
-	return __blk_mq_get_tag(data);
+found_tag:
+	return tag + tag_offset;
 }
 
-void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
-		    unsigned int tag)
+void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
+		    struct blk_mq_ctx *ctx, unsigned int tag)
 {
-	struct blk_mq_tags *tags = hctx->tags;
-
 	if (tag >= tags->nr_reserved_tags) {
 		const int real_tag = tag - tags->nr_reserved_tags;
 
@@ -312,11 +296,11 @@ int blk_mq_reinit_tagset(struct blk_mq_tag_set *set)
 		struct blk_mq_tags *tags = set->tags[i];
 
 		for (j = 0; j < tags->nr_tags; j++) {
-			if (!tags->rqs[j])
+			if (!tags->static_rqs[j])
 				continue;
 
 			ret = set->ops->reinit_request(set->driver_data,
-						tags->rqs[j]);
+						tags->static_rqs[j]);
 			if (ret)
 				goto out;
 		}
@@ -351,11 +335,6 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 
 }
 
-static unsigned int bt_unused_tags(const struct sbitmap_queue *bt)
-{
-	return bt->sb.depth - sbitmap_weight(&bt->sb);
-}
-
 static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,
 		    bool round_robin, int node)
 {
@@ -411,19 +390,56 @@ void blk_mq_free_tags(struct blk_mq_tags *tags)
 	kfree(tags);
 }
 
-int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int tdepth)
+int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
+			    struct blk_mq_tags **tagsptr, unsigned int tdepth,
+			    bool can_grow)
 {
-	tdepth -= tags->nr_reserved_tags;
-	if (tdepth > tags->nr_tags)
+	struct blk_mq_tags *tags = *tagsptr;
+
+	if (tdepth <= tags->nr_reserved_tags)
 		return -EINVAL;
 
+	tdepth -= tags->nr_reserved_tags;
+
 	/*
-	 * Don't need (or can't) update reserved tags here, they remain
-	 * static and should never need resizing.
+	 * If we are allowed to grow beyond the original size, allocate
+	 * a new set of tags before freeing the old one.
 	 */
-	sbitmap_queue_resize(&tags->bitmap_tags, tdepth);
+	if (tdepth > tags->nr_tags) {
+		struct blk_mq_tag_set *set = hctx->queue->tag_set;
+		struct blk_mq_tags *new;
+		bool ret;
+
+		if (!can_grow)
+			return -EINVAL;
+
+		/*
+		 * We need some sort of upper limit, set it high enough that
+		 * no valid use cases should require more.
+		 */
+		if (tdepth > 16 * BLKDEV_MAX_RQ)
+			return -EINVAL;
+
+		new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, 0);
+		if (!new)
+			return -ENOMEM;
+		ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth);
+		if (ret) {
+			blk_mq_free_rq_map(new);
+			return -ENOMEM;
+		}
+
+		blk_mq_free_rqs(set, *tagsptr, hctx->queue_num);
+		blk_mq_free_rq_map(*tagsptr);
+		*tagsptr = new;
+	} else {
+		/*
+		 * Don't need (or can't) update reserved tags here, they
+		 * remain static and should never need resizing.
+		 */
+		sbitmap_queue_resize(&tags->bitmap_tags, tdepth);
+	}
 
-	blk_mq_tag_wakeup_all(tags, false);
 	return 0;
 }
 
@@ -454,25 +470,3 @@ u32 blk_mq_unique_tag(struct request *rq)
 		(rq->tag & BLK_MQ_UNIQUE_TAG_MASK);
 }
 EXPORT_SYMBOL(blk_mq_unique_tag);
-
-ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page)
-{
-	char *orig_page = page;
-	unsigned int free, res;
-
-	if (!tags)
-		return 0;
-
-	page += sprintf(page, "nr_tags=%u, reserved_tags=%u, "
-			"bits_per_word=%u\n",
-			tags->nr_tags, tags->nr_reserved_tags,
-			1U << tags->bitmap_tags.sb.shift);
-
-	free = bt_unused_tags(&tags->bitmap_tags);
-	res = bt_unused_tags(&tags->breserved_tags);
-
-	page += sprintf(page, "nr_free=%u, nr_reserved=%u\n", free, res);
-	page += sprintf(page, "active_queues=%u\n", atomic_read(&tags->active_queues));
-
-	return page - orig_page;
-}
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index d1662734dc53..63497423c5cd 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -16,6 +16,7 @@ struct blk_mq_tags {
 	struct sbitmap_queue breserved_tags;
 
 	struct request **rqs;
+	struct request **static_rqs;
 	struct list_head page_list;
 };
 
@@ -24,11 +25,12 @@ extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int r
 extern void blk_mq_free_tags(struct blk_mq_tags *tags);
 
 extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data);
-extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
-			   unsigned int tag);
+extern void blk_mq_put_tag(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags *tags,
+			   struct blk_mq_ctx *ctx, unsigned int tag);
 extern bool blk_mq_has_free_tags(struct blk_mq_tags *tags);
-extern ssize_t blk_mq_tag_sysfs_show(struct blk_mq_tags *tags, char *page);
-extern int blk_mq_tag_update_depth(struct blk_mq_tags *tags, unsigned int depth);
+extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
+					struct blk_mq_tags **tags,
+					unsigned int depth, bool can_grow);
 extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool);
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c3400b5444a7..b29e7dc7b309 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -32,6 +32,7 @@
 #include "blk-mq-tag.h"
 #include "blk-stat.h"
 #include "blk-wbt.h"
+#include "blk-mq-sched.h"
 
 static DEFINE_MUTEX(all_q_mutex);
 static LIST_HEAD(all_q_list);
@@ -39,9 +40,11 @@ static LIST_HEAD(all_q_list);
 /*
  * Check if any of the ctx's have pending work in this hardware queue
  */
-static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
+bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
 {
-	return sbitmap_any_bit_set(&hctx->ctx_map);
+	return sbitmap_any_bit_set(&hctx->ctx_map) ||
+			!list_empty_careful(&hctx->dispatch) ||
+			blk_mq_sched_has_work(hctx);
 }
 
 /*
@@ -167,8 +170,8 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 }
 EXPORT_SYMBOL(blk_mq_can_queue);
 
-static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			       struct request *rq, unsigned int op)
+void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
+			struct request *rq, unsigned int op)
 {
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* csd/requeue_work/fifo_time is initialized before use */
@@ -196,13 +199,7 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->special = NULL;
 	/* tag was already set */
 	rq->errors = 0;
-
-	rq->cmd = rq->__cmd;
-
 	rq->extra_len = 0;
-	rq->sense_len = 0;
-	rq->resid_len = 0;
-	rq->sense = NULL;
 
 	INIT_LIST_HEAD(&rq->timeout_list);
 	rq->timeout = 0;
@@ -213,53 +210,58 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 
 	ctx->rq_dispatched[op_is_sync(op)]++;
 }
+EXPORT_SYMBOL_GPL(blk_mq_rq_ctx_init);
 
-static struct request *
-__blk_mq_alloc_request(struct blk_mq_alloc_data *data, unsigned int op)
+struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
+				       unsigned int op)
 {
 	struct request *rq;
 	unsigned int tag;
 
 	tag = blk_mq_get_tag(data);
 	if (tag != BLK_MQ_TAG_FAIL) {
-		rq = data->hctx->tags->rqs[tag];
+		struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
 
-		if (blk_mq_tag_busy(data->hctx)) {
-			rq->rq_flags = RQF_MQ_INFLIGHT;
-			atomic_inc(&data->hctx->nr_active);
+		rq = tags->static_rqs[tag];
+
+		if (data->flags & BLK_MQ_REQ_INTERNAL) {
+			rq->tag = -1;
+			rq->internal_tag = tag;
+		} else {
+			if (blk_mq_tag_busy(data->hctx)) {
+				rq->rq_flags = RQF_MQ_INFLIGHT;
+				atomic_inc(&data->hctx->nr_active);
+			}
+			rq->tag = tag;
+			rq->internal_tag = -1;
 		}
 
-		rq->tag = tag;
 		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op);
 		return rq;
 	}
 
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(__blk_mq_alloc_request);
 
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 		unsigned int flags)
 {
-	struct blk_mq_ctx *ctx;
-	struct blk_mq_hw_ctx *hctx;
+	struct blk_mq_alloc_data alloc_data = { .flags = flags };
 	struct request *rq;
-	struct blk_mq_alloc_data alloc_data;
 	int ret;
 
 	ret = blk_queue_enter(q, flags & BLK_MQ_REQ_NOWAIT);
 	if (ret)
 		return ERR_PTR(ret);
 
-	ctx = blk_mq_get_ctx(q);
-	hctx = blk_mq_map_queue(q, ctx->cpu);
-	blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx);
-	rq = __blk_mq_alloc_request(&alloc_data, rw);
-	blk_mq_put_ctx(ctx);
+	rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
 
-	if (!rq) {
-		blk_queue_exit(q);
+	blk_mq_put_ctx(alloc_data.ctx);
+	blk_queue_exit(q);
+
+	if (!rq)
 		return ERR_PTR(-EWOULDBLOCK);
-	}
 
 	rq->__data_len = 0;
 	rq->__sector = (sector_t) -1;
@@ -319,10 +321,10 @@ out_queue_exit:
 }
 EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
 
-static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
-				  struct blk_mq_ctx *ctx, struct request *rq)
+void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+			     struct request *rq)
 {
-	const int tag = rq->tag;
+	const int sched_tag = rq->internal_tag;
 	struct request_queue *q = rq->q;
 
 	if (rq->rq_flags & RQF_MQ_INFLIGHT)
@@ -333,23 +335,31 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
 	clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
-	blk_mq_put_tag(hctx, ctx, tag);
+	if (rq->tag != -1)
+		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
+	if (sched_tag != -1)
+		blk_mq_sched_completed_request(hctx, rq);
+	blk_mq_sched_restart_queues(hctx);
 	blk_queue_exit(q);
 }
 
-void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static void blk_mq_finish_hctx_request(struct blk_mq_hw_ctx *hctx,
+				     struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
 	ctx->rq_completed[rq_is_sync(rq)]++;
-	__blk_mq_free_request(hctx, ctx, rq);
+	__blk_mq_finish_request(hctx, ctx, rq);
+}
 
+void blk_mq_finish_request(struct request *rq)
+{
+	blk_mq_finish_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
 }
-EXPORT_SYMBOL_GPL(blk_mq_free_hctx_request);
 
 void blk_mq_free_request(struct request *rq)
 {
-	blk_mq_free_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
+	blk_mq_sched_put_request(rq);
 }
 EXPORT_SYMBOL_GPL(blk_mq_free_request);
 
@@ -467,11 +477,9 @@ void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
-	trace_block_rq_issue(q, rq);
+	blk_mq_sched_started_request(rq);
 
-	rq->resid_len = blk_rq_bytes(rq);
-	if (unlikely(blk_bidi_rq(rq)))
-		rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);
+	trace_block_rq_issue(q, rq);
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
 		blk_stat_set_issue_time(&rq->issue_stat);
@@ -515,6 +523,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 
 	trace_block_rq_requeue(q, rq);
 	wbt_requeue(q->rq_wb, &rq->issue_stat);
+	blk_mq_sched_requeue_request(rq);
 
 	if (test_and_clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) {
 		if (q->dma_drain_size && blk_rq_bytes(rq))
@@ -549,13 +558,13 @@ static void blk_mq_requeue_work(struct work_struct *work)
 
 		rq->rq_flags &= ~RQF_SOFTBARRIER;
 		list_del_init(&rq->queuelist);
-		blk_mq_insert_request(rq, true, false, false);
+		blk_mq_sched_insert_request(rq, true, false, false, true);
 	}
 
 	while (!list_empty(&rq_list)) {
 		rq = list_entry(rq_list.next, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		blk_mq_insert_request(rq, false, false, false);
+		blk_mq_sched_insert_request(rq, false, false, false, true);
 	}
 
 	blk_mq_run_hw_queues(q, false);
@@ -639,7 +648,7 @@ struct blk_mq_timeout_data {
 
 void blk_mq_rq_timed_out(struct request *req, bool reserved)
 {
-	struct blk_mq_ops *ops = req->q->mq_ops;
+	const struct blk_mq_ops *ops = req->q->mq_ops;
 	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;
 
 	/*
@@ -754,7 +763,7 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 	int checked = 8;
 
 	list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
-		int el_ret;
+		bool merged = false;
 
 		if (!checked--)
 			break;
@@ -762,20 +771,25 @@ static bool blk_mq_attempt_merge(struct request_queue *q,
 		if (!blk_rq_merge_ok(rq, bio))
 			continue;
 
-		el_ret = blk_try_merge(rq, bio);
-		if (el_ret == ELEVATOR_BACK_MERGE) {
-			if (bio_attempt_back_merge(q, rq, bio)) {
-				ctx->rq_merged++;
-				return true;
-			}
+		switch (blk_try_merge(rq, bio)) {
+		case ELEVATOR_BACK_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_back_merge(q, rq, bio);
 			break;
-		} else if (el_ret == ELEVATOR_FRONT_MERGE) {
-			if (bio_attempt_front_merge(q, rq, bio)) {
-				ctx->rq_merged++;
-				return true;
-			}
+		case ELEVATOR_FRONT_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_front_merge(q, rq, bio);
+			break;
+		case ELEVATOR_DISCARD_MERGE:
+			merged = bio_attempt_discard_merge(q, rq, bio);
 			break;
+		default:
+			continue;
 		}
+
+		if (merged)
+			ctx->rq_merged++;
+		return merged;
 	}
 
 	return false;
@@ -803,7 +817,7 @@ static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
  * Process software queues that have been marked busy, splicing them
  * to the for-dispatch
  */
-static void flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
+void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 {
 	struct flush_busy_ctx_data data = {
 		.hctx = hctx,
@@ -812,6 +826,7 @@ static void flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 
 	sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data);
 }
+EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs);
 
 static inline unsigned int queued_to_index(unsigned int queued)
 {
@@ -821,6 +836,74 @@ static inline unsigned int queued_to_index(unsigned int queued)
 	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
 }
 
+bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
+			   bool wait)
+{
+	struct blk_mq_alloc_data data = {
+		.q = rq->q,
+		.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
+		.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
+	};
+
+	if (rq->tag != -1) {
+done:
+		if (hctx)
+			*hctx = data.hctx;
+		return true;
+	}
+
+	rq->tag = blk_mq_get_tag(&data);
+	if (rq->tag >= 0) {
+		if (blk_mq_tag_busy(data.hctx)) {
+			rq->rq_flags |= RQF_MQ_INFLIGHT;
+			atomic_inc(&data.hctx->nr_active);
+		}
+		data.hctx->tags->rqs[rq->tag] = rq;
+		goto done;
+	}
+
+	return false;
+}
+
+static void blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
+				  struct request *rq)
+{
+	if (rq->tag == -1 || rq->internal_tag == -1)
+		return;
+
+	blk_mq_put_tag(hctx, hctx->tags, rq->mq_ctx, rq->tag);
+	rq->tag = -1;
+
+	if (rq->rq_flags & RQF_MQ_INFLIGHT) {
+		rq->rq_flags &= ~RQF_MQ_INFLIGHT;
+		atomic_dec(&hctx->nr_active);
+	}
+}
+
+/*
+ * If we fail getting a driver tag because all the driver tags are already
+ * assigned and on the dispatch list, BUT the first entry does not have a
+ * tag, then we could deadlock. For that case, move entries with assigned
+ * driver tags to the front, leaving the set of tagged requests in the
+ * same order, and the untagged set in the same order.
+ */
+static bool reorder_tags_to_front(struct list_head *list)
+{
+	struct request *rq, *tmp, *first = NULL;
+
+	list_for_each_entry_safe_reverse(rq, tmp, list, queuelist) {
+		if (rq == first)
+			break;
+		if (rq->tag != -1) {
+			list_move(&rq->queuelist, list);
+			if (!first)
+				first = rq;
+		}
+	}
+
+	return first != NULL;
+}
+
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 {
 	struct request_queue *q = hctx->queue;
@@ -843,6 +926,20 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 		struct blk_mq_queue_data bd;
 
 		rq = list_first_entry(list, struct request, queuelist);
+		if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
+			if (!queued && reorder_tags_to_front(list))
+				continue;
+
+			/*
+			 * We failed getting a driver tag. Mark the queue(s)
+			 * as needing a restart. Retry getting a tag again,
+			 * in case the needed IO completed right before we
+			 * marked the queue as needing a restart.
+			 */
+			blk_mq_sched_mark_restart(hctx);
+			if (!blk_mq_get_driver_tag(rq, &hctx, false))
+				break;
+		}
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
@@ -855,6 +952,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 			queued++;
 			break;
 		case BLK_MQ_RQ_QUEUE_BUSY:
+			blk_mq_put_driver_tag(hctx, rq);
 			list_add(&rq->queuelist, list);
 			__blk_mq_requeue_request(rq);
 			break;
@@ -885,7 +983,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 	 */
 	if (!list_empty(list)) {
 		spin_lock(&hctx->lock);
-		list_splice(list, &hctx->dispatch);
+		list_splice_init(list, &hctx->dispatch);
 		spin_unlock(&hctx->lock);
 
 		/*
@@ -896,45 +994,15 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list)
 		 * the requests in rq_list might get lost.
 		 *
 		 * blk_mq_run_hw_queue() already checks the STOPPED bit
-		 **/
-		blk_mq_run_hw_queue(hctx, true);
-	}
-
-	return ret != BLK_MQ_RQ_QUEUE_BUSY;
-}
-
-/*
- * Run this hardware queue, pulling any software queues mapped to it in.
- * Note that this function currently has various problems around ordering
- * of IO. In particular, we'd like FIFO behaviour on handling existing
- * items on the hctx->dispatch list. Ignore that for now.
- */
-static void blk_mq_process_rq_list(struct blk_mq_hw_ctx *hctx)
-{
-	LIST_HEAD(rq_list);
-
-	if (unlikely(blk_mq_hctx_stopped(hctx)))
-		return;
-
-	hctx->run++;
-
-	/*
-	 * Touch any software queue that has pending entries.
-	 */
-	flush_busy_ctxs(hctx, &rq_list);
-
-	/*
-	 * If we have previous entries on our dispatch list, grab them
-	 * and stuff them at the front for more fair dispatch.
-	 */
-	if (!list_empty_careful(&hctx->dispatch)) {
-		spin_lock(&hctx->lock);
-		if (!list_empty(&hctx->dispatch))
-			list_splice_init(&hctx->dispatch, &rq_list);
-		spin_unlock(&hctx->lock);
+		 *
+		 * If RESTART is set, then let completion restart the queue
+		 * instead of potentially looping here.
+		 */
+		if (!blk_mq_sched_needs_restart(hctx))
+			blk_mq_run_hw_queue(hctx, true);
 	}
 
-	blk_mq_dispatch_rq_list(hctx, &rq_list);
+	return queued != 0;
 }
 
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
@@ -946,11 +1014,11 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 
 	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
 		rcu_read_lock();
-		blk_mq_process_rq_list(hctx);
+		blk_mq_sched_dispatch_requests(hctx);
 		rcu_read_unlock();
 	} else {
 		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
-		blk_mq_process_rq_list(hctx);
+		blk_mq_sched_dispatch_requests(hctx);
 		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
 	}
 }
@@ -1006,8 +1074,7 @@ void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		if ((!blk_mq_hctx_has_pending(hctx) &&
-		    list_empty_careful(&hctx->dispatch)) ||
+		if (!blk_mq_hctx_has_pending(hctx) ||
 		    blk_mq_hctx_stopped(hctx))
 			continue;
 
@@ -1116,6 +1183,7 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 	if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
 		return;
 
+	blk_mq_stop_hw_queue(hctx);
 	kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
 			&hctx->delay_work, msecs_to_jiffies(msecs));
 }
@@ -1135,8 +1203,8 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
 		list_add_tail(&rq->queuelist, &ctx->rq_list);
 }
 
-static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
-				    struct request *rq, bool at_head)
+void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+			     bool at_head)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
@@ -1144,32 +1212,10 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
 
-void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
-			   bool async)
-{
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	spin_lock(&ctx->lock);
-	__blk_mq_insert_request(hctx, rq, at_head);
-	spin_unlock(&ctx->lock);
-
-	if (run_queue)
-		blk_mq_run_hw_queue(hctx, async);
-}
-
-static void blk_mq_insert_requests(struct request_queue *q,
-				     struct blk_mq_ctx *ctx,
-				     struct list_head *list,
-				     int depth,
-				     bool from_schedule)
+void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+			    struct list_head *list)
 
 {
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	trace_block_unplug(q, depth, !from_schedule);
-
 	/*
 	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
 	 * offline now
@@ -1185,8 +1231,6 @@ static void blk_mq_insert_requests(struct request_queue *q,
 	}
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
-
-	blk_mq_run_hw_queue(hctx, from_schedule);
 }
 
 static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b)
@@ -1222,9 +1266,10 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		BUG_ON(!rq->q);
 		if (rq->mq_ctx != this_ctx) {
 			if (this_ctx) {
-				blk_mq_insert_requests(this_q, this_ctx,
-							&ctx_list, depth,
-							from_schedule);
+				trace_block_unplug(this_q, depth, from_schedule);
+				blk_mq_sched_insert_requests(this_q, this_ctx,
+								&ctx_list,
+								from_schedule);
 			}
 
 			this_ctx = rq->mq_ctx;
@@ -1241,8 +1286,9 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	 * on 'ctx_list'. Do those.
 	 */
 	if (this_ctx) {
-		blk_mq_insert_requests(this_q, this_ctx, &ctx_list, depth,
-				       from_schedule);
+		trace_block_unplug(this_q, depth, from_schedule);
+		blk_mq_sched_insert_requests(this_q, this_ctx, &ctx_list,
+						from_schedule);
 	}
 }
 
@@ -1280,46 +1326,39 @@ insert_rq:
 		}
 
 		spin_unlock(&ctx->lock);
-		__blk_mq_free_request(hctx, ctx, rq);
+		__blk_mq_finish_request(hctx, ctx, rq);
 		return true;
 	}
 }
 
-static struct request *blk_mq_map_request(struct request_queue *q,
-					  struct bio *bio,
-					  struct blk_mq_alloc_data *data)
+static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
 {
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
-	struct request *rq;
+	if (rq->tag != -1)
+		return blk_tag_to_qc_t(rq->tag, hctx->queue_num, false);
 
-	blk_queue_enter_live(q);
-	ctx = blk_mq_get_ctx(q);
-	hctx = blk_mq_map_queue(q, ctx->cpu);
-
-	trace_block_getrq(q, bio, bio->bi_opf);
-	blk_mq_set_alloc_data(data, q, 0, ctx, hctx);
-	rq = __blk_mq_alloc_request(data, bio->bi_opf);
-
-	data->hctx->queued++;
-	return rq;
+	return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
 }
 
 static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
 {
-	int ret;
 	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu);
 	struct blk_mq_queue_data bd = {
 		.rq = rq,
 		.list = NULL,
 		.last = 1
 	};
-	blk_qc_t new_cookie = blk_tag_to_qc_t(rq->tag, hctx->queue_num);
+	struct blk_mq_hw_ctx *hctx;
+	blk_qc_t new_cookie;
+	int ret;
 
-	if (blk_mq_hctx_stopped(hctx))
+	if (q->elevator)
 		goto insert;
 
+	if (!blk_mq_get_driver_tag(rq, &hctx, false))
+		goto insert;
+
+	new_cookie = request_to_qc_t(hctx, rq);
+
 	/*
 	 * For OK queue, we are done. For error, kill it. Any other
 	 * error (busy), just add it to our list as we previously
@@ -1341,7 +1380,7 @@ static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie)
 	}
 
 insert:
-	blk_mq_insert_request(rq, false, true, true);
+	blk_mq_sched_insert_request(rq, false, true, true, false);
 }
 
 /*
@@ -1352,8 +1391,8 @@ insert:
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
-	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
-	struct blk_mq_alloc_data data;
+	const int is_flush_fua = op_is_flush(bio->bi_opf);
+	struct blk_mq_alloc_data data = { .flags = 0 };
 	struct request *rq;
 	unsigned int request_count = 0, srcu_idx;
 	struct blk_plug *plug;
@@ -1374,9 +1413,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	    blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq))
 		return BLK_QC_T_NONE;
 
+	if (blk_mq_sched_bio_merge(q, bio))
+		return BLK_QC_T_NONE;
+
 	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
 
-	rq = blk_mq_map_request(q, bio, &data);
+	trace_block_getrq(q, bio, bio->bi_opf);
+
+	rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
 		__wbt_done(q->rq_wb, wb_acct);
 		return BLK_QC_T_NONE;
@@ -1384,9 +1428,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	wbt_track(&rq->issue_stat, wb_acct);
 
-	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
+	cookie = request_to_qc_t(data.hctx, rq);
 
 	if (unlikely(is_flush_fua)) {
+		if (q->elevator)
+			goto elv_insert;
 		blk_mq_bio_to_request(rq, bio);
 		blk_insert_flush(rq);
 		goto run_queue;
@@ -1438,6 +1484,14 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		goto done;
 	}
 
+	if (q->elevator) {
+elv_insert:
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_sched_insert_request(rq, false, true,
+						!is_sync || is_flush_fua, true);
+		goto done;
+	}
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
 		/*
 		 * For a SYNC request, send it to the hardware immediately. For
@@ -1460,10 +1514,10 @@ done:
 static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
-	const int is_flush_fua = bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
+	const int is_flush_fua = op_is_flush(bio->bi_opf);
 	struct blk_plug *plug;
 	unsigned int request_count = 0;
-	struct blk_mq_alloc_data data;
+	struct blk_mq_alloc_data data = { .flags = 0 };
 	struct request *rq;
 	blk_qc_t cookie;
 	unsigned int wb_acct;
@@ -1483,9 +1537,14 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 	} else
 		request_count = blk_plug_queued_count(q);
 
+	if (blk_mq_sched_bio_merge(q, bio))
+		return BLK_QC_T_NONE;
+
 	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
 
-	rq = blk_mq_map_request(q, bio, &data);
+	trace_block_getrq(q, bio, bio->bi_opf);
+
+	rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
 		__wbt_done(q->rq_wb, wb_acct);
 		return BLK_QC_T_NONE;
@@ -1493,9 +1552,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 
 	wbt_track(&rq->issue_stat, wb_acct);
 
-	cookie = blk_tag_to_qc_t(rq->tag, data.hctx->queue_num);
+	cookie = request_to_qc_t(data.hctx, rq);
 
 	if (unlikely(is_flush_fua)) {
+		if (q->elevator)
+			goto elv_insert;
 		blk_mq_bio_to_request(rq, bio);
 		blk_insert_flush(rq);
 		goto run_queue;
@@ -1535,6 +1596,14 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		return cookie;
 	}
 
+	if (q->elevator) {
+elv_insert:
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_sched_insert_request(rq, false, true,
+						!is_sync || is_flush_fua, true);
+		goto done;
+	}
 	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
 		/*
 		 * For a SYNC request, send it to the hardware immediately. For
@@ -1547,11 +1616,12 @@ run_queue:
 	}
 
 	blk_mq_put_ctx(data.ctx);
+done:
 	return cookie;
 }
 
-static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
-		struct blk_mq_tags *tags, unsigned int hctx_idx)
+void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx)
 {
 	struct page *page;
 
@@ -1559,11 +1629,13 @@ static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
 		int i;
 
 		for (i = 0; i < tags->nr_tags; i++) {
-			if (!tags->rqs[i])
+			struct request *rq = tags->static_rqs[i];
+
+			if (!rq)
 				continue;
-			set->ops->exit_request(set->driver_data, tags->rqs[i],
+			set->ops->exit_request(set->driver_data, rq,
 						hctx_idx, i);
-			tags->rqs[i] = NULL;
+			tags->static_rqs[i] = NULL;
 		}
 	}
 
@@ -1577,33 +1649,32 @@ static void blk_mq_free_rq_map(struct blk_mq_tag_set *set,
 		kmemleak_free(page_address(page));
 		__free_pages(page, page->private);
 	}
+}
 
+void blk_mq_free_rq_map(struct blk_mq_tags *tags)
+{
 	kfree(tags->rqs);
+	tags->rqs = NULL;
+	kfree(tags->static_rqs);
+	tags->static_rqs = NULL;
 
 	blk_mq_free_tags(tags);
 }
 
-static size_t order_to_size(unsigned int order)
-{
-	return (size_t)PAGE_SIZE << order;
-}
-
-static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
-		unsigned int hctx_idx)
+struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
+					unsigned int hctx_idx,
+					unsigned int nr_tags,
+					unsigned int reserved_tags)
 {
 	struct blk_mq_tags *tags;
-	unsigned int i, j, entries_per_page, max_order = 4;
-	size_t rq_size, left;
 
-	tags = blk_mq_init_tags(set->queue_depth, set->reserved_tags,
+	tags = blk_mq_init_tags(nr_tags, reserved_tags,
 				set->numa_node,
 				BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags));
 	if (!tags)
 		return NULL;
 
-	INIT_LIST_HEAD(&tags->page_list);
-
-	tags->rqs = kzalloc_node(set->queue_depth * sizeof(struct request *),
+	tags->rqs = kzalloc_node(nr_tags * sizeof(struct request *),
 				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
 				 set->numa_node);
 	if (!tags->rqs) {
@@ -1611,15 +1682,40 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		return NULL;
 	}
 
+	tags->static_rqs = kzalloc_node(nr_tags * sizeof(struct request *),
+				 GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY,
+				 set->numa_node);
+	if (!tags->static_rqs) {
+		kfree(tags->rqs);
+		blk_mq_free_tags(tags);
+		return NULL;
+	}
+
+	return tags;
+}
+
+static size_t order_to_size(unsigned int order)
+{
+	return (size_t)PAGE_SIZE << order;
+}
+
+int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx, unsigned int depth)
+{
+	unsigned int i, j, entries_per_page, max_order = 4;
+	size_t rq_size, left;
+
+	INIT_LIST_HEAD(&tags->page_list);
+
 	/*
 	 * rq_size is the size of the request plus driver payload, rounded
 	 * to the cacheline size
 	 */
 	rq_size = round_up(sizeof(struct request) + set->cmd_size,
 				cache_line_size());
-	left = rq_size * set->queue_depth;
+	left = rq_size * depth;
 
-	for (i = 0; i < set->queue_depth; ) {
+	for (i = 0; i < depth; ) {
 		int this_order = max_order;
 		struct page *page;
 		int to_do;
@@ -1653,15 +1749,17 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 		 */
 		kmemleak_alloc(p, order_to_size(this_order), 1, GFP_NOIO);
 		entries_per_page = order_to_size(this_order) / rq_size;
-		to_do = min(entries_per_page, set->queue_depth - i);
+		to_do = min(entries_per_page, depth - i);
 		left -= to_do * rq_size;
 		for (j = 0; j < to_do; j++) {
-			tags->rqs[i] = p;
+			struct request *rq = p;
+
+			tags->static_rqs[i] = rq;
 			if (set->ops->init_request) {
 				if (set->ops->init_request(set->driver_data,
-						tags->rqs[i], hctx_idx, i,
+						rq, hctx_idx, i,
 						set->numa_node)) {
-					tags->rqs[i] = NULL;
+					tags->static_rqs[i] = NULL;
 					goto fail;
 				}
 			}
@@ -1670,11 +1768,11 @@ static struct blk_mq_tags *blk_mq_init_rq_map(struct blk_mq_tag_set *set,
 			i++;
 		}
 	}
-	return tags;
+	return 0;
 
 fail:
-	blk_mq_free_rq_map(set, tags, hctx_idx);
-	return NULL;
+	blk_mq_free_rqs(set, tags, hctx_idx);
+	return -ENOMEM;
 }
 
 /*
@@ -1866,6 +1964,35 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 	}
 }
 
+static bool __blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, int hctx_idx)
+{
+	int ret = 0;
+
+	set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx,
+					set->queue_depth, set->reserved_tags);
+	if (!set->tags[hctx_idx])
+		return false;
+
+	ret = blk_mq_alloc_rqs(set, set->tags[hctx_idx], hctx_idx,
+				set->queue_depth);
+	if (!ret)
+		return true;
+
+	blk_mq_free_rq_map(set->tags[hctx_idx]);
+	set->tags[hctx_idx] = NULL;
+	return false;
+}
+
+static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set,
+					 unsigned int hctx_idx)
+{
+	if (set->tags[hctx_idx]) {
+		blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx);
+		blk_mq_free_rq_map(set->tags[hctx_idx]);
+		set->tags[hctx_idx] = NULL;
+	}
+}
+
 static void blk_mq_map_swqueue(struct request_queue *q,
 			       const struct cpumask *online_mask)
 {
@@ -1894,17 +2021,15 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 
 		hctx_idx = q->mq_map[i];
 		/* unmapped hw queue can be remapped after CPU topo changed */
-		if (!set->tags[hctx_idx]) {
-			set->tags[hctx_idx] = blk_mq_init_rq_map(set, hctx_idx);
-
+		if (!set->tags[hctx_idx] &&
+		    !__blk_mq_alloc_rq_map(set, hctx_idx)) {
 			/*
 			 * If tags initialization fail for some hctx,
 			 * that hctx won't be brought online.  In this
 			 * case, remap the current ctx to hctx[0] which
 			 * is guaranteed to always have tags allocated
 			 */
-			if (!set->tags[hctx_idx])
-				q->mq_map[i] = 0;
+			q->mq_map[i] = 0;
 		}
 
 		ctx = per_cpu_ptr(q->queue_ctx, i);
@@ -1927,10 +2052,9 @@ static void blk_mq_map_swqueue(struct request_queue *q,
 			 * fallback in case of a new remap fails
 			 * allocation
 			 */
-			if (i && set->tags[i]) {
-				blk_mq_free_rq_map(set, set->tags[i], i);
-				set->tags[i] = NULL;
-			}
+			if (i && set->tags[i])
+				blk_mq_free_map_and_requests(set, i);
+
 			hctx->tags = NULL;
 			continue;
 		}
@@ -2023,6 +2147,8 @@ void blk_mq_release(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	unsigned int i;
 
+	blk_mq_sched_teardown(q);
+
 	/* hctx kobj stays in hctx */
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (!hctx)
@@ -2097,10 +2223,8 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 		struct blk_mq_hw_ctx *hctx = hctxs[j];
 
 		if (hctx) {
-			if (hctx->tags) {
-				blk_mq_free_rq_map(set, hctx->tags, j);
-				set->tags[j] = NULL;
-			}
+			if (hctx->tags)
+				blk_mq_free_map_and_requests(set, j);
 			blk_mq_exit_hctx(q, set, hctx, j);
 			free_cpumask_var(hctx->cpumask);
 			kobject_put(&hctx->kobj);
@@ -2181,6 +2305,14 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	mutex_unlock(&all_q_mutex);
 	put_online_cpus();
 
+	if (!(set->flags & BLK_MQ_F_NO_SCHED)) {
+		int ret;
+
+		ret = blk_mq_sched_init(q);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
 	return q;
 
 err_hctxs:
@@ -2279,10 +2411,10 @@ static int blk_mq_queue_reinit_dead(unsigned int cpu)
  * Now CPU1 is just onlined and a request is inserted into ctx1->rq_list
  * and set bit0 in pending bitmap as ctx1->index_hw is still zero.
  *
- * And then while running hw queue, flush_busy_ctxs() finds bit0 is set in
- * pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
- * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list
- * is ignored.
+ * And then while running hw queue, blk_mq_flush_busy_ctxs() finds bit0 is set
+ * in pending bitmap and tries to retrieve requests in hctx->ctxs[0]->rq_list.
+ * But htx->ctxs[0] is a pointer to ctx0, so the request in ctx1->rq_list is
+ * ignored.
  */
 static int blk_mq_queue_reinit_prepare(unsigned int cpu)
 {
@@ -2296,17 +2428,15 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 {
 	int i;
 
-	for (i = 0; i < set->nr_hw_queues; i++) {
-		set->tags[i] = blk_mq_init_rq_map(set, i);
-		if (!set->tags[i])
+	for (i = 0; i < set->nr_hw_queues; i++)
+		if (!__blk_mq_alloc_rq_map(set, i))
 			goto out_unwind;
-	}
 
 	return 0;
 
 out_unwind:
 	while (--i >= 0)
-		blk_mq_free_rq_map(set, set->tags[i], i);
+		blk_mq_free_rq_map(set->tags[i]);
 
 	return -ENOMEM;
 }
@@ -2430,10 +2560,8 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 {
 	int i;
 
-	for (i = 0; i < nr_cpu_ids; i++) {
-		if (set->tags[i])
-			blk_mq_free_rq_map(set, set->tags[i], i);
-	}
+	for (i = 0; i < nr_cpu_ids; i++)
+		blk_mq_free_map_and_requests(set, i);
 
 	kfree(set->mq_map);
 	set->mq_map = NULL;
@@ -2449,14 +2577,28 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	struct blk_mq_hw_ctx *hctx;
 	int i, ret;
 
-	if (!set || nr > set->queue_depth)
+	if (!set)
 		return -EINVAL;
 
+	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
+
 	ret = 0;
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (!hctx->tags)
 			continue;
-		ret = blk_mq_tag_update_depth(hctx->tags, nr);
+		/*
+		 * If we're using an MQ scheduler, just update the scheduler
+		 * queue depth. This is similar to what the old code would do.
+		 */
+		if (!hctx->sched_tags) {
+			ret = blk_mq_tag_update_depth(hctx, &hctx->tags,
+							min(nr, set->queue_depth),
+							false);
+		} else {
+			ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags,
+							nr, true);
+		}
 		if (ret)
 			break;
 	}
@@ -2464,6 +2606,9 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	if (!ret)
 		q->nr_requests = nr;
 
+	blk_mq_unfreeze_queue(q);
+	blk_mq_start_stopped_hw_queues(q, true);
+
 	return ret;
 }
 
@@ -2483,10 +2628,14 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
 
+		/*
+		 * Manually set the make_request_fn as blk_queue_make_request
+		 * resets a lot of the queue settings.
+		 */
 		if (q->nr_hw_queues > 1)
-			blk_queue_make_request(q, blk_mq_make_request);
+			q->make_request_fn = blk_mq_make_request;
 		else
-			blk_queue_make_request(q, blk_sq_make_request);
+			q->make_request_fn = blk_sq_make_request;
 
 		blk_mq_queue_reinit(q, cpu_online_mask);
 	}
@@ -2649,7 +2798,10 @@ bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie)
 		blk_flush_plug_list(plug, false);
 
 	hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)];
-	rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
+	if (!blk_qc_t_is_internal(cookie))
+		rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie));
+	else
+		rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie));
 
 	return __blk_mq_poll(hctx, rq);
 }
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 63e9116cddbd..24b2256186f3 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -32,8 +32,32 @@ void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *, struct list_head *);
+void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
+bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx);
+bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
+				bool wait);
 
 /*
+ * Internal helpers for allocating/freeing the request map
+ */
+void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx);
+void blk_mq_free_rq_map(struct blk_mq_tags *tags);
+struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set,
+					unsigned int hctx_idx,
+					unsigned int nr_tags,
+					unsigned int reserved_tags);
+int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
+		     unsigned int hctx_idx, unsigned int depth);
+
+/*
+ * Internal helpers for request insertion into sw queues
+ */
+void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+				bool at_head);
+void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+				struct list_head *list);
+/*
  * CPU hotplug helpers
  */
 void blk_mq_enable_hotplug(void);
@@ -57,6 +81,35 @@ extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
+/*
+ * debugfs helpers
+ */
+#ifdef CONFIG_BLK_DEBUG_FS
+int blk_mq_debugfs_register(struct request_queue *q, const char *name);
+void blk_mq_debugfs_unregister(struct request_queue *q);
+int blk_mq_debugfs_register_hctxs(struct request_queue *q);
+void blk_mq_debugfs_unregister_hctxs(struct request_queue *q);
+#else
+static inline int blk_mq_debugfs_register(struct request_queue *q,
+					  const char *name)
+{
+	return 0;
+}
+
+static inline void blk_mq_debugfs_unregister(struct request_queue *q)
+{
+}
+
+static inline int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+{
+	return 0;
+}
+
+static inline void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+{
+}
+#endif
+
 extern void blk_mq_rq_timed_out(struct request *req, bool reserved);
 
 void blk_mq_release(struct request_queue *q);
@@ -103,6 +156,25 @@ static inline void blk_mq_set_alloc_data(struct blk_mq_alloc_data *data,
 	data->hctx = hctx;
 }
 
+static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
+{
+	if (data->flags & BLK_MQ_REQ_INTERNAL)
+		return data->hctx->sched_tags;
+
+	return data->hctx->tags;
+}
+
+/*
+ * Internal helpers for request allocation/init/free
+ */
+void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
+			struct request *rq, unsigned int op);
+void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
+				struct request *rq);
+void blk_mq_finish_request(struct request *rq);
+struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
+					unsigned int op);
+
 static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
 {
 	return test_bit(BLK_MQ_S_STOPPED, &hctx->state);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 529e55f52a03..1e7174ffc9d4 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -88,6 +88,7 @@ EXPORT_SYMBOL_GPL(blk_queue_lld_busy);
 void blk_set_default_limits(struct queue_limits *lim)
 {
 	lim->max_segments = BLK_MAX_SEGMENTS;
+	lim->max_discard_segments = 1;
 	lim->max_integrity_segments = 0;
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->virt_boundary_mask = 0;
@@ -128,6 +129,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	/* Inherit limits from component devices */
 	lim->discard_zeroes_data = 1;
 	lim->max_segments = USHRT_MAX;
+	lim->max_discard_segments = 1;
 	lim->max_hw_sectors = UINT_MAX;
 	lim->max_segment_size = UINT_MAX;
 	lim->max_sectors = UINT_MAX;
@@ -253,7 +255,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 	max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
 	max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
 	limits->max_sectors = max_sectors;
-	q->backing_dev_info.io_pages = max_sectors >> (PAGE_SHIFT - 9);
+	q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9);
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
@@ -337,6 +339,22 @@ void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments
 EXPORT_SYMBOL(blk_queue_max_segments);
 
 /**
+ * blk_queue_max_discard_segments - set max segments for discard requests
+ * @q:  the request queue for the device
+ * @max_segments:  max number of segments
+ *
+ * Description:
+ *    Enables a low level driver to set an upper limit on the number of
+ *    segments in a discard request.
+ **/
+void blk_queue_max_discard_segments(struct request_queue *q,
+		unsigned short max_segments)
+{
+	q->limits.max_discard_segments = max_segments;
+}
+EXPORT_SYMBOL_GPL(blk_queue_max_discard_segments);
+
+/**
  * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
  * @q:  the request queue for the device
  * @max_size:  max size of segment in bytes
@@ -553,6 +571,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 					    b->virt_boundary_mask);
 
 	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
+	t->max_discard_segments = min_not_zero(t->max_discard_segments,
+					       b->max_discard_segments);
 	t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
 						 b->max_integrity_segments);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 1dbce057592d..002af836aa87 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -89,7 +89,7 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 
 static ssize_t queue_ra_show(struct request_queue *q, char *page)
 {
-	unsigned long ra_kb = q->backing_dev_info.ra_pages <<
+	unsigned long ra_kb = q->backing_dev_info->ra_pages <<
 					(PAGE_SHIFT - 10);
 
 	return queue_var_show(ra_kb, (page));
@@ -104,7 +104,7 @@ queue_ra_store(struct request_queue *q, const char *page, size_t count)
 	if (ret < 0)
 		return ret;
 
-	q->backing_dev_info.ra_pages = ra_kb >> (PAGE_SHIFT - 10);
+	q->backing_dev_info->ra_pages = ra_kb >> (PAGE_SHIFT - 10);
 
 	return ret;
 }
@@ -121,6 +121,12 @@ static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
 	return queue_var_show(queue_max_segments(q), (page));
 }
 
+static ssize_t queue_max_discard_segments_show(struct request_queue *q,
+		char *page)
+{
+	return queue_var_show(queue_max_discard_segments(q), (page));
+}
+
 static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page)
 {
 	return queue_var_show(q->limits.max_integrity_segments, (page));
@@ -236,7 +242,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 
 	spin_lock_irq(q->queue_lock);
 	q->limits.max_sectors = max_sectors_kb << 1;
-	q->backing_dev_info.io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
+	q->backing_dev_info->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
@@ -545,6 +551,11 @@ static struct queue_sysfs_entry queue_max_segments_entry = {
 	.show = queue_max_segments_show,
 };
 
+static struct queue_sysfs_entry queue_max_discard_segments_entry = {
+	.attr = {.name = "max_discard_segments", .mode = S_IRUGO },
+	.show = queue_max_discard_segments_show,
+};
+
 static struct queue_sysfs_entry queue_max_integrity_segments_entry = {
 	.attr = {.name = "max_integrity_segments", .mode = S_IRUGO },
 	.show = queue_max_integrity_segments_show,
@@ -697,6 +708,7 @@ static struct attribute *default_attrs[] = {
 	&queue_max_hw_sectors_entry.attr,
 	&queue_max_sectors_entry.attr,
 	&queue_max_segments_entry.attr,
+	&queue_max_discard_segments_entry.attr,
 	&queue_max_integrity_segments_entry.attr,
 	&queue_max_segment_size_entry.attr,
 	&queue_iosched_entry.attr,
@@ -799,7 +811,7 @@ static void blk_release_queue(struct kobject *kobj)
 		container_of(kobj, struct request_queue, kobj);
 
 	wbt_exit(q);
-	bdi_exit(&q->backing_dev_info);
+	bdi_put(q->backing_dev_info);
 	blkcg_exit_queue(q);
 
 	if (q->elevator) {
@@ -814,13 +826,19 @@ static void blk_release_queue(struct kobject *kobj)
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);
 
-	if (!q->mq_ops)
+	if (!q->mq_ops) {
+		if (q->exit_rq_fn)
+			q->exit_rq_fn(q, q->fq->flush_rq);
 		blk_free_flush_queue(q->fq);
-	else
+	} else {
 		blk_mq_release(q);
+	}
 
 	blk_trace_shutdown(q);
 
+	if (q->mq_ops)
+		blk_mq_debugfs_unregister(q);
+
 	if (q->bio_split)
 		bioset_free(q->bio_split);
 
@@ -884,32 +902,36 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret)
 		return ret;
 
+	if (q->mq_ops)
+		blk_mq_register_dev(dev, q);
+
+	/* Prevent changes through sysfs until registration is completed. */
+	mutex_lock(&q->sysfs_lock);
+
 	ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue");
 	if (ret < 0) {
 		blk_trace_remove_sysfs(dev);
-		return ret;
+		goto unlock;
 	}
 
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 
-	if (q->mq_ops)
-		blk_mq_register_dev(dev, q);
-
 	blk_wb_init(q);
 
-	if (!q->request_fn)
-		return 0;
-
-	ret = elv_register_queue(q);
-	if (ret) {
-		kobject_uevent(&q->kobj, KOBJ_REMOVE);
-		kobject_del(&q->kobj);
-		blk_trace_remove_sysfs(dev);
-		kobject_put(&dev->kobj);
-		return ret;
+	if (q->request_fn || (q->mq_ops && q->elevator)) {
+		ret = elv_register_queue(q);
+		if (ret) {
+			kobject_uevent(&q->kobj, KOBJ_REMOVE);
+			kobject_del(&q->kobj);
+			blk_trace_remove_sysfs(dev);
+			kobject_put(&dev->kobj);
+			goto unlock;
+		}
 	}
-
-	return 0;
+	ret = 0;
+unlock:
+	mutex_unlock(&q->sysfs_lock);
+	return ret;
 }
 
 void blk_unregister_queue(struct gendisk *disk)
@@ -922,7 +944,7 @@ void blk_unregister_queue(struct gendisk *disk)
 	if (q->mq_ops)
 		blk_mq_unregister_dev(disk_to_dev(disk), q);
 
-	if (q->request_fn)
+	if (q->request_fn || (q->mq_ops && q->elevator))
 		elv_unregister_queue(q);
 
 	kobject_uevent(&q->kobj, KOBJ_REMOVE);
diff --git a/block/blk-tag.c b/block/blk-tag.c
index bae1decb6ec3..07cc329fa4b0 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -272,6 +272,7 @@ void blk_queue_end_tag(struct request_queue *q, struct request *rq)
 	list_del_init(&rq->queuelist);
 	rq->rq_flags &= ~RQF_QUEUED;
 	rq->tag = -1;
+	rq->internal_tag = -1;
 
 	if (unlikely(bqt->tag_index[tag] == NULL))
 		printk(KERN_ERR "%s: tag %d is missing\n",
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index a6bb4fe326c3..82fd0cc394eb 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -866,10 +866,12 @@ static void tg_update_disptime(struct throtl_grp *tg)
 	unsigned long read_wait = -1, write_wait = -1, min_wait = -1, disptime;
 	struct bio *bio;
 
-	if ((bio = throtl_peek_queued(&sq->queued[READ])))
+	bio = throtl_peek_queued(&sq->queued[READ]);
+	if (bio)
 		tg_may_dispatch(tg, bio, &read_wait);
 
-	if ((bio = throtl_peek_queued(&sq->queued[WRITE])))
+	bio = throtl_peek_queued(&sq->queued[WRITE]);
+	if (bio)
 		tg_may_dispatch(tg, bio, &write_wait);
 
 	min_wait = min(read_wait, write_wait);
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index f0a9c07b4c7a..1aedb1f7ee0c 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -96,7 +96,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->queue->backing_dev_info.wb;
+	struct bdi_writeback *wb = &rwb->queue->backing_dev_info->wb;
 
 	return time_before(jiffies, wb->dirty_sleep + HZ);
 }
@@ -279,7 +279,7 @@ enum {
 
 static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 {
-	struct backing_dev_info *bdi = &rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
 	u64 thislat;
 
 	/*
@@ -339,7 +339,7 @@ static int latency_exceeded(struct rq_wb *rwb)
 
 static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
 {
-	struct backing_dev_info *bdi = &rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
 
 	trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec,
 			rwb->wb_background, rwb->wb_normal, rwb->wb_max);
@@ -423,7 +423,7 @@ static void wb_timer_fn(unsigned long data)
 
 	status = latency_exceeded(rwb);
 
-	trace_wbt_timer(&rwb->queue->backing_dev_info, status, rwb->scale_step,
+	trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
 			inflight);
 
 	/*
diff --git a/block/blk.h b/block/blk.h
index 041185e5f129..d1ea4bd9b9a3 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -14,6 +14,10 @@
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
 
+#ifdef CONFIG_DEBUG_FS
+extern struct dentry *blk_debugfs_root;
+#endif
+
 struct blk_flush_queue {
 	unsigned int		flush_queue_delayed:1;
 	unsigned int		flush_pending_idx:1;
@@ -96,6 +100,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 			     struct bio *bio);
 bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 			    struct bio *bio);
+bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
+		struct bio *bio);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 			    unsigned int *request_count,
 			    struct request **same_queue_rq);
@@ -167,7 +173,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			return NULL;
 		}
 		if (unlikely(blk_queue_bypass(q)) ||
-		    !q->elevator->type->ops.elevator_dispatch_fn(q, 0))
+		    !q->elevator->type->ops.sq.elevator_dispatch_fn(q, 0))
 			return NULL;
 	}
 }
@@ -176,16 +182,16 @@ static inline void elv_activate_rq(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_activate_req_fn)
-		e->type->ops.elevator_activate_req_fn(q, rq);
+	if (e->type->ops.sq.elevator_activate_req_fn)
+		e->type->ops.sq.elevator_activate_req_fn(q, rq);
 }
 
 static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_deactivate_req_fn)
-		e->type->ops.elevator_deactivate_req_fn(q, rq);
+	if (e->type->ops.sq.elevator_deactivate_req_fn)
+		e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
 }
 
 #ifdef CONFIG_FAIL_IO_TIMEOUT
@@ -204,14 +210,14 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 		     struct bio *bio);
 int ll_front_merge_fn(struct request_queue *q, struct request *req, 
 		      struct bio *bio);
-int attempt_back_merge(struct request_queue *q, struct request *rq);
-int attempt_front_merge(struct request_queue *q, struct request *rq);
+struct request *attempt_back_merge(struct request_queue *q, struct request *rq);
+struct request *attempt_front_merge(struct request_queue *q, struct request *rq);
 int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
 				struct request *next);
 void blk_recalc_rq_segments(struct request *rq);
 void blk_rq_set_mixed_merge(struct request *rq);
 bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
-int blk_try_merge(struct request *rq, struct bio *bio);
+enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
 
 void blk_queue_congestion_threshold(struct request_queue *q);
 
@@ -249,7 +255,14 @@ static inline int blk_do_io_stat(struct request *rq)
 {
 	return rq->rq_disk &&
 	       (rq->rq_flags & RQF_IO_STAT) &&
-		(rq->cmd_type == REQ_TYPE_FS);
+		!blk_rq_is_passthrough(rq);
+}
+
+static inline void req_set_nomerge(struct request_queue *q, struct request *req)
+{
+	req->cmd_flags |= REQ_NOMERGE;
+	if (req == q->last_merge)
+		q->last_merge = NULL;
 }
 
 /*
@@ -264,6 +277,22 @@ void ioc_clear_queue(struct request_queue *q);
 int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node);
 
 /**
+ * rq_ioc - determine io_context for request allocation
+ * @bio: request being allocated is for this bio (can be %NULL)
+ *
+ * Determine io_context to use for request allocation for @bio.  May return
+ * %NULL if %current->io_context doesn't exist.
+ */
+static inline struct io_context *rq_ioc(struct bio *bio)
+{
+#ifdef CONFIG_BLK_CGROUP
+	if (bio && bio->bi_ioc)
+		return bio->bi_ioc;
+#endif
+	return current->io_context;
+}
+
+/**
  * create_io_context - try to create task->io_context
  * @gfp_mask: allocation mask
  * @node: allocation node
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 9d652a992316..cd15f9dbb147 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -71,22 +71,24 @@ void bsg_job_done(struct bsg_job *job, int result,
 {
 	struct request *req = job->req;
 	struct request *rsp = req->next_rq;
+	struct scsi_request *rq = scsi_req(req);
 	int err;
 
 	err = job->req->errors = result;
 	if (err < 0)
 		/* we're only returning the result field in the reply */
-		job->req->sense_len = sizeof(u32);
+		rq->sense_len = sizeof(u32);
 	else
-		job->req->sense_len = job->reply_len;
+		rq->sense_len = job->reply_len;
 	/* we assume all request payload was transferred, residual == 0 */
-	req->resid_len = 0;
+	rq->resid_len = 0;
 
 	if (rsp) {
-		WARN_ON(reply_payload_rcv_len > rsp->resid_len);
+		WARN_ON(reply_payload_rcv_len > scsi_req(rsp)->resid_len);
 
 		/* set reply (bidi) residual */
-		rsp->resid_len -= min(reply_payload_rcv_len, rsp->resid_len);
+		scsi_req(rsp)->resid_len -=
+			min(reply_payload_rcv_len, scsi_req(rsp)->resid_len);
 	}
 	blk_complete_request(req);
 }
@@ -113,6 +115,7 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req)
 	if (!buf->sg_list)
 		return -ENOMEM;
 	sg_init_table(buf->sg_list, req->nr_phys_segments);
+	scsi_req(req)->resid_len = blk_rq_bytes(req);
 	buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list);
 	buf->payload_len = blk_rq_bytes(req);
 	return 0;
@@ -127,6 +130,7 @@ static int bsg_create_job(struct device *dev, struct request *req)
 {
 	struct request *rsp = req->next_rq;
 	struct request_queue *q = req->q;
+	struct scsi_request *rq = scsi_req(req);
 	struct bsg_job *job;
 	int ret;
 
@@ -140,9 +144,9 @@ static int bsg_create_job(struct device *dev, struct request *req)
 	job->req = req;
 	if (q->bsg_job_size)
 		job->dd_data = (void *)&job[1];
-	job->request = req->cmd;
-	job->request_len = req->cmd_len;
-	job->reply = req->sense;
+	job->request = rq->cmd;
+	job->request_len = rq->cmd_len;
+	job->reply = rq->sense;
 	job->reply_len = SCSI_SENSE_BUFFERSIZE;	/* Size of sense buffer
 						 * allocated */
 	if (req->bio) {
@@ -177,7 +181,7 @@ failjob_rls_job:
  *
  * Drivers/subsys should pass this to the queue init function.
  */
-void bsg_request_fn(struct request_queue *q)
+static void bsg_request_fn(struct request_queue *q)
 	__releases(q->queue_lock)
 	__acquires(q->queue_lock)
 {
@@ -214,24 +218,30 @@ void bsg_request_fn(struct request_queue *q)
 	put_device(dev);
 	spin_lock_irq(q->queue_lock);
 }
-EXPORT_SYMBOL_GPL(bsg_request_fn);
 
 /**
  * bsg_setup_queue - Create and add the bsg hooks so we can receive requests
  * @dev: device to attach bsg device to
- * @q: request queue setup by caller
  * @name: device to give bsg device
  * @job_fn: bsg job handler
  * @dd_job_size: size of LLD data needed for each job
- *
- * The caller should have setup the reuqest queue with bsg_request_fn
- * as the request_fn.
  */
-int bsg_setup_queue(struct device *dev, struct request_queue *q,
-		    char *name, bsg_job_fn *job_fn, int dd_job_size)
+struct request_queue *bsg_setup_queue(struct device *dev, char *name,
+		bsg_job_fn *job_fn, int dd_job_size)
 {
+	struct request_queue *q;
 	int ret;
 
+	q = blk_alloc_queue(GFP_KERNEL);
+	if (!q)
+		return ERR_PTR(-ENOMEM);
+	q->cmd_size = sizeof(struct scsi_request);
+	q->request_fn = bsg_request_fn;
+
+	ret = blk_init_allocated_queue(q);
+	if (ret)
+		goto out_cleanup_queue;
+
 	q->queuedata = dev;
 	q->bsg_job_size = dd_job_size;
 	q->bsg_job_fn = job_fn;
@@ -243,9 +253,12 @@ int bsg_setup_queue(struct device *dev, struct request_queue *q,
 	if (ret) {
 		printk(KERN_ERR "%s: bsg interface failed to "
 		       "initialize - register queue\n", dev->kobj.name);
-		return ret;
+		goto out_cleanup_queue;
 	}
 
-	return 0;
+	return q;
+out_cleanup_queue:
+	blk_cleanup_queue(q);
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(bsg_setup_queue);
diff --git a/block/bsg.c b/block/bsg.c
index a57046de2f07..a9a8b8e0446f 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -85,7 +85,6 @@ struct bsg_command {
 	struct bio *bidi_bio;
 	int err;
 	struct sg_io_v4 hdr;
-	char sense[SCSI_SENSE_BUFFERSIZE];
 };
 
 static void bsg_free_command(struct bsg_command *bc)
@@ -140,18 +139,20 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 				struct sg_io_v4 *hdr, struct bsg_device *bd,
 				fmode_t has_write_perm)
 {
+	struct scsi_request *req = scsi_req(rq);
+
 	if (hdr->request_len > BLK_MAX_CDB) {
-		rq->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
-		if (!rq->cmd)
+		req->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
+		if (!req->cmd)
 			return -ENOMEM;
 	}
 
-	if (copy_from_user(rq->cmd, (void __user *)(unsigned long)hdr->request,
+	if (copy_from_user(req->cmd, (void __user *)(unsigned long)hdr->request,
 			   hdr->request_len))
 		return -EFAULT;
 
 	if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) {
-		if (blk_verify_command(rq->cmd, has_write_perm))
+		if (blk_verify_command(req->cmd, has_write_perm))
 			return -EPERM;
 	} else if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
@@ -159,7 +160,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 	/*
 	 * fill in request structure
 	 */
-	rq->cmd_len = hdr->request_len;
+	req->cmd_len = hdr->request_len;
 
 	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
@@ -176,7 +177,7 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
  * Check if sg_io_v4 from user is allowed and valid
  */
 static int
-bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
+bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *op)
 {
 	int ret = 0;
 
@@ -197,7 +198,7 @@ bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
 		ret = -EINVAL;
 	}
 
-	*rw = hdr->dout_xfer_len ? WRITE : READ;
+	*op = hdr->dout_xfer_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN;
 	return ret;
 }
 
@@ -205,13 +206,12 @@ bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *rw)
  * map sg_io_v4 to a request.
  */
 static struct request *
-bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
-	    u8 *sense)
+bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
 {
 	struct request_queue *q = bd->queue;
 	struct request *rq, *next_rq = NULL;
-	int ret, rw;
-	unsigned int dxfer_len;
+	int ret;
+	unsigned int op, dxfer_len;
 	void __user *dxferp = NULL;
 	struct bsg_class_device *bcd = &q->bsg_dev;
 
@@ -226,36 +226,35 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 		hdr->dout_xfer_len, (unsigned long long) hdr->din_xferp,
 		hdr->din_xfer_len);
 
-	ret = bsg_validate_sgv4_hdr(hdr, &rw);
+	ret = bsg_validate_sgv4_hdr(hdr, &op);
 	if (ret)
 		return ERR_PTR(ret);
 
 	/*
 	 * map scatter-gather elements separately and string them to request
 	 */
-	rq = blk_get_request(q, rw, GFP_KERNEL);
+	rq = blk_get_request(q, op, GFP_KERNEL);
 	if (IS_ERR(rq))
 		return rq;
-	blk_rq_set_block_pc(rq);
+	scsi_req_init(rq);
 
 	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
 	if (ret)
 		goto out;
 
-	if (rw == WRITE && hdr->din_xfer_len) {
+	if (op == REQ_OP_SCSI_OUT && hdr->din_xfer_len) {
 		if (!test_bit(QUEUE_FLAG_BIDI, &q->queue_flags)) {
 			ret = -EOPNOTSUPP;
 			goto out;
 		}
 
-		next_rq = blk_get_request(q, READ, GFP_KERNEL);
+		next_rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
 		if (IS_ERR(next_rq)) {
 			ret = PTR_ERR(next_rq);
 			next_rq = NULL;
 			goto out;
 		}
 		rq->next_rq = next_rq;
-		next_rq->cmd_type = rq->cmd_type;
 
 		dxferp = (void __user *)(unsigned long)hdr->din_xferp;
 		ret =  blk_rq_map_user(q, next_rq, NULL, dxferp,
@@ -280,13 +279,9 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 			goto out;
 	}
 
-	rq->sense = sense;
-	rq->sense_len = 0;
-
 	return rq;
 out:
-	if (rq->cmd != rq->__cmd)
-		kfree(rq->cmd);
+	scsi_req_free_cmd(scsi_req(rq));
 	blk_put_request(rq);
 	if (next_rq) {
 		blk_rq_unmap_user(next_rq->bio);
@@ -393,6 +388,7 @@ static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd)
 static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 				    struct bio *bio, struct bio *bidi_bio)
 {
+	struct scsi_request *req = scsi_req(rq);
 	int ret = 0;
 
 	dprintk("rq %p bio %p 0x%x\n", rq, bio, rq->errors);
@@ -407,12 +403,12 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 		hdr->info |= SG_INFO_CHECK;
 	hdr->response_len = 0;
 
-	if (rq->sense_len && hdr->response) {
+	if (req->sense_len && hdr->response) {
 		int len = min_t(unsigned int, hdr->max_response_len,
-					rq->sense_len);
+					req->sense_len);
 
 		ret = copy_to_user((void __user *)(unsigned long)hdr->response,
-				   rq->sense, len);
+				   req->sense, len);
 		if (!ret)
 			hdr->response_len = len;
 		else
@@ -420,14 +416,14 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	}
 
 	if (rq->next_rq) {
-		hdr->dout_resid = rq->resid_len;
-		hdr->din_resid = rq->next_rq->resid_len;
+		hdr->dout_resid = req->resid_len;
+		hdr->din_resid = scsi_req(rq->next_rq)->resid_len;
 		blk_rq_unmap_user(bidi_bio);
 		blk_put_request(rq->next_rq);
 	} else if (rq_data_dir(rq) == READ)
-		hdr->din_resid = rq->resid_len;
+		hdr->din_resid = req->resid_len;
 	else
-		hdr->dout_resid = rq->resid_len;
+		hdr->dout_resid = req->resid_len;
 
 	/*
 	 * If the request generated a negative error number, return it
@@ -439,8 +435,7 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 		ret = rq->errors;
 
 	blk_rq_unmap_user(bio);
-	if (rq->cmd != rq->__cmd)
-		kfree(rq->cmd);
+	scsi_req_free_cmd(req);
 	blk_put_request(rq);
 
 	return ret;
@@ -625,7 +620,7 @@ static int __bsg_write(struct bsg_device *bd, const char __user *buf,
 		/*
 		 * get a request, fill in the blanks, and add to request queue
 		 */
-		rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm, bc->sense);
+		rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm);
 		if (IS_ERR(rq)) {
 			ret = PTR_ERR(rq);
 			rq = NULL;
@@ -911,12 +906,11 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		struct bio *bio, *bidi_bio = NULL;
 		struct sg_io_v4 hdr;
 		int at_head;
-		u8 sense[SCSI_SENSE_BUFFERSIZE];
 
 		if (copy_from_user(&hdr, uarg, sizeof(hdr)))
 			return -EFAULT;
 
-		rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE, sense);
+		rq = bsg_map_hdr(bd, &hdr, file->f_mode & FMODE_WRITE);
 		if (IS_ERR(rq))
 			return PTR_ERR(rq);
 
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index c73a6fcaeb9d..137944777859 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -2528,7 +2528,7 @@ static void cfq_remove_request(struct request *rq)
 	}
 }
 
-static int cfq_merge(struct request_queue *q, struct request **req,
+static enum elv_merge cfq_merge(struct request_queue *q, struct request **req,
 		     struct bio *bio)
 {
 	struct cfq_data *cfqd = q->elevator->elevator_data;
@@ -2544,7 +2544,7 @@ static int cfq_merge(struct request_queue *q, struct request **req,
 }
 
 static void cfq_merged_request(struct request_queue *q, struct request *req,
-			       int type)
+			       enum elv_merge type)
 {
 	if (type == ELEVATOR_FRONT_MERGE) {
 		struct cfq_queue *cfqq = RQ_CFQQ(req);
@@ -2749,9 +2749,11 @@ static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
 	if (!cfqg)
 		return NULL;
 
-	for_each_cfqg_st(cfqg, i, j, st)
-		if ((cfqq = cfq_rb_first(st)) != NULL)
+	for_each_cfqg_st(cfqg, i, j, st) {
+		cfqq = cfq_rb_first(st);
+		if (cfqq)
 			return cfqq;
+	}
 	return NULL;
 }
 
@@ -3758,7 +3760,7 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
-static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 {
 	struct cfq_data *cfqd = cic_to_cfqd(cic);
 	struct cfq_queue *cfqq;
@@ -3775,15 +3777,7 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	 * spuriously on a newly created cic but there's no harm.
 	 */
 	if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr))
-		return;
-
-	/*
-	 * If we have a non-root cgroup, we can depend on that to
-	 * do proper throttling of writes. Turn off wbt for that
-	 * case, if it was enabled by default.
-	 */
-	if (nonroot_cg)
-		wbt_disable_default(cfqd->queue);
+		return nonroot_cg;
 
 	/*
 	 * Drop reference to queues.  New queues will be assigned in new
@@ -3804,9 +3798,13 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	}
 
 	cic->blkcg_serial_nr = serial_nr;
+	return nonroot_cg;
 }
 #else
-static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) { }
+static inline bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+{
+	return false;
+}
 #endif  /* CONFIG_CFQ_GROUP_IOSCHED */
 
 static struct cfq_queue **
@@ -3864,6 +3862,8 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic,
 		goto out;
 	}
 
+	/* cfq_init_cfqq() assumes cfqq->ioprio_class is initialized. */
+	cfqq->ioprio_class = IOPRIO_CLASS_NONE;
 	cfq_init_cfqq(cfqd, cfqq, current->pid, is_sync);
 	cfq_init_prio_data(cfqq, cic);
 	cfq_link_cfqq_cfqg(cfqq, cfqg);
@@ -4448,11 +4448,12 @@ cfq_set_request(struct request_queue *q, struct request *rq, struct bio *bio,
 	const int rw = rq_data_dir(rq);
 	const bool is_sync = rq_is_sync(rq);
 	struct cfq_queue *cfqq;
+	bool disable_wbt;
 
 	spin_lock_irq(q->queue_lock);
 
 	check_ioprio_changed(cic, bio);
-	check_blkcg_changed(cic, bio);
+	disable_wbt = check_blkcg_changed(cic, bio);
 new_queue:
 	cfqq = cic_to_cfqq(cic, is_sync);
 	if (!cfqq || cfqq == &cfqd->oom_cfqq) {
@@ -4488,6 +4489,10 @@ new_queue:
 	rq->elv.priv[0] = cfqq;
 	rq->elv.priv[1] = cfqq->cfqg;
 	spin_unlock_irq(q->queue_lock);
+
+	if (disable_wbt)
+		wbt_disable_default(q);
+
 	return 0;
 }
 
@@ -4837,7 +4842,7 @@ static struct elv_fs_entry cfq_attrs[] = {
 };
 
 static struct elevator_type iosched_cfq = {
-	.ops = {
+	.ops.sq = {
 		.elevator_merge_fn = 		cfq_merge,
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 556826ac7cb4..570021a0dc1c 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -661,7 +661,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	struct block_device *bdev = inode->i_bdev;
 	struct gendisk *disk = bdev->bd_disk;
 	fmode_t mode = file->f_mode;
-	struct backing_dev_info *bdi;
 	loff_t size;
 	unsigned int max_sectors;
 
@@ -708,9 +707,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKFRAGET:
 		if (!arg)
 			return -EINVAL;
-		bdi = blk_get_backing_dev_info(bdev);
 		return compat_put_long(arg,
-				       (bdi->ra_pages * PAGE_SIZE) / 512);
+			       (bdev->bd_bdi->ra_pages * PAGE_SIZE) / 512);
 	case BLKROGET: /* compatible */
 		return compat_put_int(arg, bdev_read_only(bdev) != 0);
 	case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */
@@ -728,8 +726,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKFRASET:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
-		bdi = blk_get_backing_dev_info(bdev);
-		bdi->ra_pages = (arg * 512) / PAGE_SIZE;
+		bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE;
 		return 0;
 	case BLKGETSIZE:
 		size = i_size_read(bdev->bd_inode);
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index 55e0bb6d7da7..c68f6bbc0dcd 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -120,12 +120,11 @@ static void deadline_remove_request(struct request_queue *q, struct request *rq)
 	deadline_del_rq_rb(dd, rq);
 }
 
-static int
+static enum elv_merge
 deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct request *__rq;
-	int ret;
 
 	/*
 	 * check for front merge
@@ -138,20 +137,17 @@ deadline_merge(struct request_queue *q, struct request **req, struct bio *bio)
 			BUG_ON(sector != blk_rq_pos(__rq));
 
 			if (elv_bio_merge_ok(__rq, bio)) {
-				ret = ELEVATOR_FRONT_MERGE;
-				goto out;
+				*req = __rq;
+				return ELEVATOR_FRONT_MERGE;
 			}
 		}
 	}
 
 	return ELEVATOR_NO_MERGE;
-out:
-	*req = __rq;
-	return ret;
 }
 
 static void deadline_merged_request(struct request_queue *q,
-				    struct request *req, int type)
+				    struct request *req, enum elv_merge type)
 {
 	struct deadline_data *dd = q->elevator->elevator_data;
 
@@ -439,7 +435,7 @@ static struct elv_fs_entry deadline_attrs[] = {
 };
 
 static struct elevator_type iosched_deadline = {
-	.ops = {
+	.ops.sq = {
 		.elevator_merge_fn = 		deadline_merge,
 		.elevator_merged_fn =		deadline_merged_request,
 		.elevator_merge_req_fn =	deadline_merged_requests,
diff --git a/block/elevator.c b/block/elevator.c
index 40f0c04e5ad3..699d10f71a2c 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -40,6 +40,7 @@
 #include <trace/events/block.h>
 
 #include "blk.h"
+#include "blk-mq-sched.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
@@ -58,8 +59,10 @@ static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_allow_bio_merge_fn)
-		return e->type->ops.elevator_allow_bio_merge_fn(q, rq, bio);
+	if (e->uses_mq && e->type->ops.mq.allow_merge)
+		return e->type->ops.mq.allow_merge(q, rq, bio);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_allow_bio_merge_fn)
+		return e->type->ops.sq.elevator_allow_bio_merge_fn(q, rq, bio);
 
 	return 1;
 }
@@ -163,6 +166,7 @@ struct elevator_queue *elevator_alloc(struct request_queue *q,
 	kobject_init(&eq->kobj, &elv_ktype);
 	mutex_init(&eq->sysfs_lock);
 	hash_init(eq->hash);
+	eq->uses_mq = e->uses_mq;
 
 	return eq;
 }
@@ -203,11 +207,12 @@ int elevator_init(struct request_queue *q, char *name)
 	}
 
 	/*
-	 * Use the default elevator specified by config boot param or
-	 * config option.  Don't try to load modules as we could be running
-	 * off async and request_module() isn't allowed from async.
+	 * Use the default elevator specified by config boot param for
+	 * non-mq devices, or by config option. Don't try to load modules
+	 * as we could be running off async and request_module() isn't
+	 * allowed from async.
 	 */
-	if (!e && *chosen_elevator) {
+	if (!e && !q->mq_ops && *chosen_elevator) {
 		e = elevator_get(chosen_elevator, false);
 		if (!e)
 			printk(KERN_ERR "I/O scheduler %s not found\n",
@@ -215,18 +220,32 @@ int elevator_init(struct request_queue *q, char *name)
 	}
 
 	if (!e) {
-		e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
+		if (q->mq_ops && q->nr_hw_queues == 1)
+			e = elevator_get(CONFIG_DEFAULT_SQ_IOSCHED, false);
+		else if (q->mq_ops)
+			e = elevator_get(CONFIG_DEFAULT_MQ_IOSCHED, false);
+		else
+			e = elevator_get(CONFIG_DEFAULT_IOSCHED, false);
+
 		if (!e) {
 			printk(KERN_ERR
 				"Default I/O scheduler not found. " \
-				"Using noop.\n");
+				"Using noop/none.\n");
 			e = elevator_get("noop", false);
 		}
 	}
 
-	err = e->ops.elevator_init_fn(q, e);
-	if (err)
+	if (e->uses_mq) {
+		err = blk_mq_sched_setup(q);
+		if (!err)
+			err = e->ops.mq.init_sched(q, e);
+	} else
+		err = e->ops.sq.elevator_init_fn(q, e);
+	if (err) {
+		if (e->uses_mq)
+			blk_mq_sched_teardown(q);
 		elevator_put(e);
+	}
 	return err;
 }
 EXPORT_SYMBOL(elevator_init);
@@ -234,8 +253,10 @@ EXPORT_SYMBOL(elevator_init);
 void elevator_exit(struct elevator_queue *e)
 {
 	mutex_lock(&e->sysfs_lock);
-	if (e->type->ops.elevator_exit_fn)
-		e->type->ops.elevator_exit_fn(e);
+	if (e->uses_mq && e->type->ops.mq.exit_sched)
+		e->type->ops.mq.exit_sched(e);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn)
+		e->type->ops.sq.elevator_exit_fn(e);
 	mutex_unlock(&e->sysfs_lock);
 
 	kobject_put(&e->kobj);
@@ -253,6 +274,7 @@ void elv_rqhash_del(struct request_queue *q, struct request *rq)
 	if (ELV_ON_HASH(rq))
 		__elv_rqhash_del(rq);
 }
+EXPORT_SYMBOL_GPL(elv_rqhash_del);
 
 void elv_rqhash_add(struct request_queue *q, struct request *rq)
 {
@@ -262,6 +284,7 @@ void elv_rqhash_add(struct request_queue *q, struct request *rq)
 	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
 	rq->rq_flags |= RQF_HASHED;
 }
+EXPORT_SYMBOL_GPL(elv_rqhash_add);
 
 void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
 {
@@ -405,11 +428,11 @@ void elv_dispatch_add_tail(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL(elv_dispatch_add_tail);
 
-int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
+enum elv_merge elv_merge(struct request_queue *q, struct request **req,
+		struct bio *bio)
 {
 	struct elevator_queue *e = q->elevator;
 	struct request *__rq;
-	int ret;
 
 	/*
 	 * Levels of merges:
@@ -424,7 +447,8 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	 * First try one-hit cache.
 	 */
 	if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
-		ret = blk_try_merge(q->last_merge, bio);
+		enum elv_merge ret = blk_try_merge(q->last_merge, bio);
+
 		if (ret != ELEVATOR_NO_MERGE) {
 			*req = q->last_merge;
 			return ret;
@@ -443,8 +467,10 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		return ELEVATOR_BACK_MERGE;
 	}
 
-	if (e->type->ops.elevator_merge_fn)
-		return e->type->ops.elevator_merge_fn(q, req, bio);
+	if (e->uses_mq && e->type->ops.mq.request_merge)
+		return e->type->ops.mq.request_merge(q, req, bio);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_merge_fn)
+		return e->type->ops.sq.elevator_merge_fn(q, req, bio);
 
 	return ELEVATOR_NO_MERGE;
 }
@@ -456,8 +482,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
  *
  * Returns true if we merged, false otherwise
  */
-static bool elv_attempt_insert_merge(struct request_queue *q,
-				     struct request *rq)
+bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq)
 {
 	struct request *__rq;
 	bool ret;
@@ -491,12 +516,15 @@ static bool elv_attempt_insert_merge(struct request_queue *q,
 	return ret;
 }
 
-void elv_merged_request(struct request_queue *q, struct request *rq, int type)
+void elv_merged_request(struct request_queue *q, struct request *rq,
+		enum elv_merge type)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_merged_fn)
-		e->type->ops.elevator_merged_fn(q, rq, type);
+	if (e->uses_mq && e->type->ops.mq.request_merged)
+		e->type->ops.mq.request_merged(q, rq, type);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_merged_fn)
+		e->type->ops.sq.elevator_merged_fn(q, rq, type);
 
 	if (type == ELEVATOR_BACK_MERGE)
 		elv_rqhash_reposition(q, rq);
@@ -508,10 +536,15 @@ void elv_merge_requests(struct request_queue *q, struct request *rq,
 			     struct request *next)
 {
 	struct elevator_queue *e = q->elevator;
-	const int next_sorted = next->rq_flags & RQF_SORTED;
-
-	if (next_sorted && e->type->ops.elevator_merge_req_fn)
-		e->type->ops.elevator_merge_req_fn(q, rq, next);
+	bool next_sorted = false;
+
+	if (e->uses_mq && e->type->ops.mq.requests_merged)
+		e->type->ops.mq.requests_merged(q, rq, next);
+	else if (e->type->ops.sq.elevator_merge_req_fn) {
+		next_sorted = (__force bool)(next->rq_flags & RQF_SORTED);
+		if (next_sorted)
+			e->type->ops.sq.elevator_merge_req_fn(q, rq, next);
+	}
 
 	elv_rqhash_reposition(q, rq);
 
@@ -528,8 +561,11 @@ void elv_bio_merged(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_bio_merged_fn)
-		e->type->ops.elevator_bio_merged_fn(q, rq, bio);
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
+	if (e->type->ops.sq.elevator_bio_merged_fn)
+		e->type->ops.sq.elevator_bio_merged_fn(q, rq, bio);
 }
 
 #ifdef CONFIG_PM
@@ -574,11 +610,15 @@ void elv_requeue_request(struct request_queue *q, struct request *rq)
 
 void elv_drain_elevator(struct request_queue *q)
 {
+	struct elevator_queue *e = q->elevator;
 	static int printed;
 
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
 	lockdep_assert_held(q->queue_lock);
 
-	while (q->elevator->type->ops.elevator_dispatch_fn(q, 1))
+	while (e->type->ops.sq.elevator_dispatch_fn(q, 1))
 		;
 	if (q->nr_sorted && printed++ < 10) {
 		printk(KERN_ERR "%s: forced dispatching is broken "
@@ -597,7 +637,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 
 	if (rq->rq_flags & RQF_SOFTBARRIER) {
 		/* barriers are scheduling boundary, update end_sector */
-		if (rq->cmd_type == REQ_TYPE_FS) {
+		if (!blk_rq_is_passthrough(rq)) {
 			q->end_sector = rq_end_sector(rq);
 			q->boundary_rq = rq;
 		}
@@ -639,7 +679,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 		if (elv_attempt_insert_merge(q, rq))
 			break;
 	case ELEVATOR_INSERT_SORT:
-		BUG_ON(rq->cmd_type != REQ_TYPE_FS);
+		BUG_ON(blk_rq_is_passthrough(rq));
 		rq->rq_flags |= RQF_SORTED;
 		q->nr_sorted++;
 		if (rq_mergeable(rq)) {
@@ -653,7 +693,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 		 * rq cannot be accessed after calling
 		 * elevator_add_req_fn.
 		 */
-		q->elevator->type->ops.elevator_add_req_fn(q, rq);
+		q->elevator->type->ops.sq.elevator_add_req_fn(q, rq);
 		break;
 
 	case ELEVATOR_INSERT_FLUSH:
@@ -682,8 +722,11 @@ struct request *elv_latter_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_latter_req_fn)
-		return e->type->ops.elevator_latter_req_fn(q, rq);
+	if (e->uses_mq && e->type->ops.mq.next_request)
+		return e->type->ops.mq.next_request(q, rq);
+	else if (!e->uses_mq && e->type->ops.sq.elevator_latter_req_fn)
+		return e->type->ops.sq.elevator_latter_req_fn(q, rq);
+
 	return NULL;
 }
 
@@ -691,8 +734,10 @@ struct request *elv_former_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_former_req_fn)
-		return e->type->ops.elevator_former_req_fn(q, rq);
+	if (e->uses_mq && e->type->ops.mq.former_request)
+		return e->type->ops.mq.former_request(q, rq);
+	if (!e->uses_mq && e->type->ops.sq.elevator_former_req_fn)
+		return e->type->ops.sq.elevator_former_req_fn(q, rq);
 	return NULL;
 }
 
@@ -701,8 +746,11 @@ int elv_set_request(struct request_queue *q, struct request *rq,
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_set_req_fn)
-		return e->type->ops.elevator_set_req_fn(q, rq, bio, gfp_mask);
+	if (WARN_ON_ONCE(e->uses_mq))
+		return 0;
+
+	if (e->type->ops.sq.elevator_set_req_fn)
+		return e->type->ops.sq.elevator_set_req_fn(q, rq, bio, gfp_mask);
 	return 0;
 }
 
@@ -710,16 +758,22 @@ void elv_put_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_put_req_fn)
-		e->type->ops.elevator_put_req_fn(rq);
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
+	if (e->type->ops.sq.elevator_put_req_fn)
+		e->type->ops.sq.elevator_put_req_fn(rq);
 }
 
 int elv_may_queue(struct request_queue *q, unsigned int op)
 {
 	struct elevator_queue *e = q->elevator;
 
-	if (e->type->ops.elevator_may_queue_fn)
-		return e->type->ops.elevator_may_queue_fn(q, op);
+	if (WARN_ON_ONCE(e->uses_mq))
+		return 0;
+
+	if (e->type->ops.sq.elevator_may_queue_fn)
+		return e->type->ops.sq.elevator_may_queue_fn(q, op);
 
 	return ELV_MQUEUE_MAY;
 }
@@ -728,14 +782,17 @@ void elv_completed_request(struct request_queue *q, struct request *rq)
 {
 	struct elevator_queue *e = q->elevator;
 
+	if (WARN_ON_ONCE(e->uses_mq))
+		return;
+
 	/*
 	 * request is released from the driver, io must be done
 	 */
 	if (blk_account_rq(rq)) {
 		q->in_flight[rq_is_sync(rq)]--;
 		if ((rq->rq_flags & RQF_SORTED) &&
-		    e->type->ops.elevator_completed_req_fn)
-			e->type->ops.elevator_completed_req_fn(q, rq);
+		    e->type->ops.sq.elevator_completed_req_fn)
+			e->type->ops.sq.elevator_completed_req_fn(q, rq);
 	}
 }
 
@@ -803,8 +860,8 @@ int elv_register_queue(struct request_queue *q)
 		}
 		kobject_uevent(&e->kobj, KOBJ_ADD);
 		e->registered = 1;
-		if (e->type->ops.elevator_registered_fn)
-			e->type->ops.elevator_registered_fn(q);
+		if (!e->uses_mq && e->type->ops.sq.elevator_registered_fn)
+			e->type->ops.sq.elevator_registered_fn(q);
 	}
 	return error;
 }
@@ -891,9 +948,14 @@ EXPORT_SYMBOL_GPL(elv_unregister);
 static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 {
 	struct elevator_queue *old = q->elevator;
-	bool registered = old->registered;
+	bool old_registered = false;
 	int err;
 
+	if (q->mq_ops) {
+		blk_mq_freeze_queue(q);
+		blk_mq_quiesce_queue(q);
+	}
+
 	/*
 	 * Turn on BYPASS and drain all requests w/ elevator private data.
 	 * Block layer doesn't call into a quiesced elevator - all requests
@@ -901,42 +963,76 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 * using INSERT_BACK.  All requests have SOFTBARRIER set and no
 	 * merge happens either.
 	 */
-	blk_queue_bypass_start(q);
+	if (old) {
+		old_registered = old->registered;
+
+		if (old->uses_mq)
+			blk_mq_sched_teardown(q);
+
+		if (!q->mq_ops)
+			blk_queue_bypass_start(q);
 
-	/* unregister and clear all auxiliary data of the old elevator */
-	if (registered)
-		elv_unregister_queue(q);
+		/* unregister and clear all auxiliary data of the old elevator */
+		if (old_registered)
+			elv_unregister_queue(q);
 
-	spin_lock_irq(q->queue_lock);
-	ioc_clear_queue(q);
-	spin_unlock_irq(q->queue_lock);
+		spin_lock_irq(q->queue_lock);
+		ioc_clear_queue(q);
+		spin_unlock_irq(q->queue_lock);
+	}
 
 	/* allocate, init and register new elevator */
-	err = new_e->ops.elevator_init_fn(q, new_e);
-	if (err)
-		goto fail_init;
+	if (new_e) {
+		if (new_e->uses_mq) {
+			err = blk_mq_sched_setup(q);
+			if (!err)
+				err = new_e->ops.mq.init_sched(q, new_e);
+		} else
+			err = new_e->ops.sq.elevator_init_fn(q, new_e);
+		if (err)
+			goto fail_init;
 
-	if (registered) {
 		err = elv_register_queue(q);
 		if (err)
 			goto fail_register;
-	}
+	} else
+		q->elevator = NULL;
 
 	/* done, kill the old one and finish */
-	elevator_exit(old);
-	blk_queue_bypass_end(q);
+	if (old) {
+		elevator_exit(old);
+		if (!q->mq_ops)
+			blk_queue_bypass_end(q);
+	}
 
-	blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+	if (q->mq_ops) {
+		blk_mq_unfreeze_queue(q);
+		blk_mq_start_stopped_hw_queues(q, true);
+	}
+
+	if (new_e)
+		blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
+	else
+		blk_add_trace_msg(q, "elv switch: none");
 
 	return 0;
 
 fail_register:
+	if (q->mq_ops)
+		blk_mq_sched_teardown(q);
 	elevator_exit(q->elevator);
 fail_init:
 	/* switch failed, restore and re-register old elevator */
-	q->elevator = old;
-	elv_register_queue(q);
-	blk_queue_bypass_end(q);
+	if (old) {
+		q->elevator = old;
+		elv_register_queue(q);
+		if (!q->mq_ops)
+			blk_queue_bypass_end(q);
+	}
+	if (q->mq_ops) {
+		blk_mq_unfreeze_queue(q);
+		blk_mq_start_stopped_hw_queues(q, true);
+	}
 
 	return err;
 }
@@ -949,8 +1045,11 @@ static int __elevator_change(struct request_queue *q, const char *name)
 	char elevator_name[ELV_NAME_MAX];
 	struct elevator_type *e;
 
-	if (!q->elevator)
-		return -ENXIO;
+	/*
+	 * Special case for mq, turn off scheduling
+	 */
+	if (q->mq_ops && !strncmp(name, "none", 4))
+		return elevator_switch(q, NULL);
 
 	strlcpy(elevator_name, name, sizeof(elevator_name));
 	e = elevator_get(strstrip(elevator_name), true);
@@ -959,11 +1058,21 @@ static int __elevator_change(struct request_queue *q, const char *name)
 		return -EINVAL;
 	}
 
-	if (!strcmp(elevator_name, q->elevator->type->elevator_name)) {
+	if (q->elevator &&
+	    !strcmp(elevator_name, q->elevator->type->elevator_name)) {
 		elevator_put(e);
 		return 0;
 	}
 
+	if (!e->uses_mq && q->mq_ops) {
+		elevator_put(e);
+		return -EINVAL;
+	}
+	if (e->uses_mq && !q->mq_ops) {
+		elevator_put(e);
+		return -EINVAL;
+	}
+
 	return elevator_switch(q, e);
 }
 
@@ -985,7 +1094,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 {
 	int ret;
 
-	if (!q->elevator)
+	if (!(q->mq_ops || q->request_fn))
 		return count;
 
 	ret = __elevator_change(q, name);
@@ -999,24 +1108,34 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 ssize_t elv_iosched_show(struct request_queue *q, char *name)
 {
 	struct elevator_queue *e = q->elevator;
-	struct elevator_type *elv;
+	struct elevator_type *elv = NULL;
 	struct elevator_type *__e;
 	int len = 0;
 
-	if (!q->elevator || !blk_queue_stackable(q))
+	if (!blk_queue_stackable(q))
 		return sprintf(name, "none\n");
 
-	elv = e->type;
+	if (!q->elevator)
+		len += sprintf(name+len, "[none] ");
+	else
+		elv = e->type;
 
 	spin_lock(&elv_list_lock);
 	list_for_each_entry(__e, &elv_list, list) {
-		if (!strcmp(elv->elevator_name, __e->elevator_name))
+		if (elv && !strcmp(elv->elevator_name, __e->elevator_name)) {
 			len += sprintf(name+len, "[%s] ", elv->elevator_name);
-		else
+			continue;
+		}
+		if (__e->uses_mq && q->mq_ops)
+			len += sprintf(name+len, "%s ", __e->elevator_name);
+		else if (!__e->uses_mq && !q->mq_ops)
 			len += sprintf(name+len, "%s ", __e->elevator_name);
 	}
 	spin_unlock(&elv_list_lock);
 
+	if (q->mq_ops && q->elevator)
+		len += sprintf(name+len, "none");
+
 	len += sprintf(len+name, "\n");
 	return len;
 }
diff --git a/block/genhd.c b/block/genhd.c
index fcd6d4fae657..3631cd480295 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -572,6 +572,20 @@ exit:
 	disk_part_iter_exit(&piter);
 }
 
+void put_disk_devt(struct disk_devt *disk_devt)
+{
+	if (disk_devt && atomic_dec_and_test(&disk_devt->count))
+		disk_devt->release(disk_devt);
+}
+EXPORT_SYMBOL(put_disk_devt);
+
+void get_disk_devt(struct disk_devt *disk_devt)
+{
+	if (disk_devt)
+		atomic_inc(&disk_devt->count);
+}
+EXPORT_SYMBOL(get_disk_devt);
+
 /**
  * device_add_disk - add partitioning information to kernel list
  * @parent: parent device for the disk
@@ -612,8 +626,15 @@ void device_add_disk(struct device *parent, struct gendisk *disk)
 
 	disk_alloc_events(disk);
 
+	/*
+	 * Take a reference on the devt and assign it to queue since it
+	 * must not be reallocated while the bdi is registered
+	 */
+	disk->queue->disk_devt = disk->disk_devt;
+	get_disk_devt(disk->disk_devt);
+
 	/* Register BDI before referencing it from bdev */
-	bdi = &disk->queue->backing_dev_info;
+	bdi = disk->queue->backing_dev_info;
 	bdi_register_owner(bdi, disk_to_dev(disk));
 
 	blk_register_region(disk_devt(disk), disk->minors, NULL,
@@ -648,6 +669,8 @@ void del_gendisk(struct gendisk *disk)
 	disk_part_iter_init(&piter, disk,
 			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
 	while ((part = disk_part_iter_next(&piter))) {
+		bdev_unhash_inode(MKDEV(disk->major,
+					disk->first_minor + part->partno));
 		invalidate_partition(disk, part->partno);
 		delete_partition(disk, part->partno);
 	}
diff --git a/block/ioctl.c b/block/ioctl.c
index be7f4de3eb3c..7b88820b93d9 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -505,7 +505,6 @@ static int blkdev_bszset(struct block_device *bdev, fmode_t mode,
 int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 			unsigned long arg)
 {
-	struct backing_dev_info *bdi;
 	void __user *argp = (void __user *)arg;
 	loff_t size;
 	unsigned int max_sectors;
@@ -532,8 +531,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKFRAGET:
 		if (!arg)
 			return -EINVAL;
-		bdi = blk_get_backing_dev_info(bdev);
-		return put_long(arg, (bdi->ra_pages * PAGE_SIZE) / 512);
+		return put_long(arg, (bdev->bd_bdi->ra_pages*PAGE_SIZE) / 512);
 	case BLKROGET:
 		return put_int(arg, bdev_read_only(bdev) != 0);
 	case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */
@@ -560,8 +558,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKFRASET:
 		if(!capable(CAP_SYS_ADMIN))
 			return -EACCES;
-		bdi = blk_get_backing_dev_info(bdev);
-		bdi->ra_pages = (arg * 512) / PAGE_SIZE;
+		bdev->bd_bdi->ra_pages = (arg * 512) / PAGE_SIZE;
 		return 0;
 	case BLKBSZSET:
 		return blkdev_bszset(bdev, mode, argp);
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
new file mode 100644
index 000000000000..236121633ca0
--- /dev/null
+++ b/block/mq-deadline.c
@@ -0,0 +1,556 @@
+/*
+ *  MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler,
+ *  for the blk-mq scheduling framework
+ *
+ *  Copyright (C) 2016 Jens Axboe <axboe@kernel.dk>
+ */
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/elevator.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+#include <linux/sbitmap.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
+
+/*
+ * See Documentation/block/deadline-iosched.txt
+ */
+static const int read_expire = HZ / 2;  /* max time before a read is submitted. */
+static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
+static const int writes_starved = 2;    /* max times reads can starve a write */
+static const int fifo_batch = 16;       /* # of sequential requests treated as one
+				     by the above parameters. For throughput. */
+
+struct deadline_data {
+	/*
+	 * run time data
+	 */
+
+	/*
+	 * requests (deadline_rq s) are present on both sort_list and fifo_list
+	 */
+	struct rb_root sort_list[2];
+	struct list_head fifo_list[2];
+
+	/*
+	 * next in sort order. read, write or both are NULL
+	 */
+	struct request *next_rq[2];
+	unsigned int batching;		/* number of sequential requests made */
+	unsigned int starved;		/* times reads have starved writes */
+
+	/*
+	 * settings that change how the i/o scheduler behaves
+	 */
+	int fifo_expire[2];
+	int fifo_batch;
+	int writes_starved;
+	int front_merges;
+
+	spinlock_t lock;
+	struct list_head dispatch;
+};
+
+static inline struct rb_root *
+deadline_rb_root(struct deadline_data *dd, struct request *rq)
+{
+	return &dd->sort_list[rq_data_dir(rq)];
+}
+
+/*
+ * get the request after `rq' in sector-sorted order
+ */
+static inline struct request *
+deadline_latter_request(struct request *rq)
+{
+	struct rb_node *node = rb_next(&rq->rb_node);
+
+	if (node)
+		return rb_entry_rq(node);
+
+	return NULL;
+}
+
+static void
+deadline_add_rq_rb(struct deadline_data *dd, struct request *rq)
+{
+	struct rb_root *root = deadline_rb_root(dd, rq);
+
+	elv_rb_add(root, rq);
+}
+
+static inline void
+deadline_del_rq_rb(struct deadline_data *dd, struct request *rq)
+{
+	const int data_dir = rq_data_dir(rq);
+
+	if (dd->next_rq[data_dir] == rq)
+		dd->next_rq[data_dir] = deadline_latter_request(rq);
+
+	elv_rb_del(deadline_rb_root(dd, rq), rq);
+}
+
+/*
+ * remove rq from rbtree and fifo.
+ */
+static void deadline_remove_request(struct request_queue *q, struct request *rq)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	list_del_init(&rq->queuelist);
+
+	/*
+	 * We might not be on the rbtree, if we are doing an insert merge
+	 */
+	if (!RB_EMPTY_NODE(&rq->rb_node))
+		deadline_del_rq_rb(dd, rq);
+
+	elv_rqhash_del(q, rq);
+	if (q->last_merge == rq)
+		q->last_merge = NULL;
+}
+
+static void dd_request_merged(struct request_queue *q, struct request *req,
+			      enum elv_merge type)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	/*
+	 * if the merge was a front merge, we need to reposition request
+	 */
+	if (type == ELEVATOR_FRONT_MERGE) {
+		elv_rb_del(deadline_rb_root(dd, req), req);
+		deadline_add_rq_rb(dd, req);
+	}
+}
+
+static void dd_merged_requests(struct request_queue *q, struct request *req,
+			       struct request *next)
+{
+	/*
+	 * if next expires before rq, assign its expire time to rq
+	 * and move into next position (next will be deleted) in fifo
+	 */
+	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
+		if (time_before((unsigned long)next->fifo_time,
+				(unsigned long)req->fifo_time)) {
+			list_move(&req->queuelist, &next->queuelist);
+			req->fifo_time = next->fifo_time;
+		}
+	}
+
+	/*
+	 * kill knowledge of next, this one is a goner
+	 */
+	deadline_remove_request(q, next);
+}
+
+/*
+ * move an entry to dispatch queue
+ */
+static void
+deadline_move_request(struct deadline_data *dd, struct request *rq)
+{
+	const int data_dir = rq_data_dir(rq);
+
+	dd->next_rq[READ] = NULL;
+	dd->next_rq[WRITE] = NULL;
+	dd->next_rq[data_dir] = deadline_latter_request(rq);
+
+	/*
+	 * take it off the sort and fifo list
+	 */
+	deadline_remove_request(rq->q, rq);
+}
+
+/*
+ * deadline_check_fifo returns 0 if there are no expired requests on the fifo,
+ * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
+ */
+static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
+{
+	struct request *rq = rq_entry_fifo(dd->fifo_list[ddir].next);
+
+	/*
+	 * rq is expired!
+	 */
+	if (time_after_eq(jiffies, (unsigned long)rq->fifo_time))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * deadline_dispatch_requests selects the best request according to
+ * read/write expire, fifo_batch, etc
+ */
+static struct request *__dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+	struct request *rq;
+	bool reads, writes;
+	int data_dir;
+
+	if (!list_empty(&dd->dispatch)) {
+		rq = list_first_entry(&dd->dispatch, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		goto done;
+	}
+
+	reads = !list_empty(&dd->fifo_list[READ]);
+	writes = !list_empty(&dd->fifo_list[WRITE]);
+
+	/*
+	 * batches are currently reads XOR writes
+	 */
+	if (dd->next_rq[WRITE])
+		rq = dd->next_rq[WRITE];
+	else
+		rq = dd->next_rq[READ];
+
+	if (rq && dd->batching < dd->fifo_batch)
+		/* we have a next request are still entitled to batch */
+		goto dispatch_request;
+
+	/*
+	 * at this point we are not running a batch. select the appropriate
+	 * data direction (read / write)
+	 */
+
+	if (reads) {
+		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ]));
+
+		if (writes && (dd->starved++ >= dd->writes_starved))
+			goto dispatch_writes;
+
+		data_dir = READ;
+
+		goto dispatch_find_request;
+	}
+
+	/*
+	 * there are either no reads or writes have been starved
+	 */
+
+	if (writes) {
+dispatch_writes:
+		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[WRITE]));
+
+		dd->starved = 0;
+
+		data_dir = WRITE;
+
+		goto dispatch_find_request;
+	}
+
+	return NULL;
+
+dispatch_find_request:
+	/*
+	 * we are not running a batch, find best request for selected data_dir
+	 */
+	if (deadline_check_fifo(dd, data_dir) || !dd->next_rq[data_dir]) {
+		/*
+		 * A deadline has expired, the last request was in the other
+		 * direction, or we have run out of higher-sectored requests.
+		 * Start again from the request with the earliest expiry time.
+		 */
+		rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+	} else {
+		/*
+		 * The last req was the same dir and we have a next request in
+		 * sort order. No expired requests so continue on from here.
+		 */
+		rq = dd->next_rq[data_dir];
+	}
+
+	dd->batching = 0;
+
+dispatch_request:
+	/*
+	 * rq is the selected appropriate request.
+	 */
+	dd->batching++;
+	deadline_move_request(dd, rq);
+done:
+	rq->rq_flags |= RQF_STARTED;
+	return rq;
+}
+
+static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+	struct request *rq;
+
+	spin_lock(&dd->lock);
+	rq = __dd_dispatch_request(hctx);
+	spin_unlock(&dd->lock);
+
+	return rq;
+}
+
+static void dd_exit_queue(struct elevator_queue *e)
+{
+	struct deadline_data *dd = e->elevator_data;
+
+	BUG_ON(!list_empty(&dd->fifo_list[READ]));
+	BUG_ON(!list_empty(&dd->fifo_list[WRITE]));
+
+	kfree(dd);
+}
+
+/*
+ * initialize elevator private data (deadline_data).
+ */
+static int dd_init_queue(struct request_queue *q, struct elevator_type *e)
+{
+	struct deadline_data *dd;
+	struct elevator_queue *eq;
+
+	eq = elevator_alloc(q, e);
+	if (!eq)
+		return -ENOMEM;
+
+	dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
+	if (!dd) {
+		kobject_put(&eq->kobj);
+		return -ENOMEM;
+	}
+	eq->elevator_data = dd;
+
+	INIT_LIST_HEAD(&dd->fifo_list[READ]);
+	INIT_LIST_HEAD(&dd->fifo_list[WRITE]);
+	dd->sort_list[READ] = RB_ROOT;
+	dd->sort_list[WRITE] = RB_ROOT;
+	dd->fifo_expire[READ] = read_expire;
+	dd->fifo_expire[WRITE] = write_expire;
+	dd->writes_starved = writes_starved;
+	dd->front_merges = 1;
+	dd->fifo_batch = fifo_batch;
+	spin_lock_init(&dd->lock);
+	INIT_LIST_HEAD(&dd->dispatch);
+
+	q->elevator = eq;
+	return 0;
+}
+
+static int dd_request_merge(struct request_queue *q, struct request **rq,
+			    struct bio *bio)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+	sector_t sector = bio_end_sector(bio);
+	struct request *__rq;
+
+	if (!dd->front_merges)
+		return ELEVATOR_NO_MERGE;
+
+	__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
+	if (__rq) {
+		BUG_ON(sector != blk_rq_pos(__rq));
+
+		if (elv_bio_merge_ok(__rq, bio)) {
+			*rq = __rq;
+			return ELEVATOR_FRONT_MERGE;
+		}
+	}
+
+	return ELEVATOR_NO_MERGE;
+}
+
+static bool dd_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
+{
+	struct request_queue *q = hctx->queue;
+	struct deadline_data *dd = q->elevator->elevator_data;
+	struct request *free = NULL;
+	bool ret;
+
+	spin_lock(&dd->lock);
+	ret = blk_mq_sched_try_merge(q, bio, &free);
+	spin_unlock(&dd->lock);
+
+	if (free)
+		blk_mq_free_request(free);
+
+	return ret;
+}
+
+/*
+ * add rq to rbtree and fifo
+ */
+static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+			      bool at_head)
+{
+	struct request_queue *q = hctx->queue;
+	struct deadline_data *dd = q->elevator->elevator_data;
+	const int data_dir = rq_data_dir(rq);
+
+	if (blk_mq_sched_try_insert_merge(q, rq))
+		return;
+
+	blk_mq_sched_request_inserted(rq);
+
+	if (at_head || blk_rq_is_passthrough(rq)) {
+		if (at_head)
+			list_add(&rq->queuelist, &dd->dispatch);
+		else
+			list_add_tail(&rq->queuelist, &dd->dispatch);
+	} else {
+		deadline_add_rq_rb(dd, rq);
+
+		if (rq_mergeable(rq)) {
+			elv_rqhash_add(q, rq);
+			if (!q->last_merge)
+				q->last_merge = rq;
+		}
+
+		/*
+		 * set expire time and add to fifo list
+		 */
+		rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
+		list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]);
+	}
+}
+
+static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
+			       struct list_head *list, bool at_head)
+{
+	struct request_queue *q = hctx->queue;
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	spin_lock(&dd->lock);
+	while (!list_empty(list)) {
+		struct request *rq;
+
+		rq = list_first_entry(list, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		dd_insert_request(hctx, rq, at_head);
+	}
+	spin_unlock(&dd->lock);
+}
+
+static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+
+	return !list_empty_careful(&dd->dispatch) ||
+		!list_empty_careful(&dd->fifo_list[0]) ||
+		!list_empty_careful(&dd->fifo_list[1]);
+}
+
+/*
+ * sysfs parts below
+ */
+static ssize_t
+deadline_var_show(int var, char *page)
+{
+	return sprintf(page, "%d\n", var);
+}
+
+static ssize_t
+deadline_var_store(int *var, const char *page, size_t count)
+{
+	char *p = (char *) page;
+
+	*var = simple_strtol(p, &p, 10);
+	return count;
+}
+
+#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct deadline_data *dd = e->elevator_data;			\
+	int __data = __VAR;						\
+	if (__CONV)							\
+		__data = jiffies_to_msecs(__data);			\
+	return deadline_var_show(__data, (page));			\
+}
+SHOW_FUNCTION(deadline_read_expire_show, dd->fifo_expire[READ], 1);
+SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1);
+SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0);
+SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 0);
+SHOW_FUNCTION(deadline_fifo_batch_show, dd->fifo_batch, 0);
+#undef SHOW_FUNCTION
+
+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct deadline_data *dd = e->elevator_data;			\
+	int __data;							\
+	int ret = deadline_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	if (__CONV)							\
+		*(__PTR) = msecs_to_jiffies(__data);			\
+	else								\
+		*(__PTR) = __data;					\
+	return ret;							\
+}
+STORE_FUNCTION(deadline_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0);
+STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0);
+STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
+#undef STORE_FUNCTION
+
+#define DD_ATTR(name) \
+	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
+				      deadline_##name##_store)
+
+static struct elv_fs_entry deadline_attrs[] = {
+	DD_ATTR(read_expire),
+	DD_ATTR(write_expire),
+	DD_ATTR(writes_starved),
+	DD_ATTR(front_merges),
+	DD_ATTR(fifo_batch),
+	__ATTR_NULL
+};
+
+static struct elevator_type mq_deadline = {
+	.ops.mq = {
+		.insert_requests	= dd_insert_requests,
+		.dispatch_request	= dd_dispatch_request,
+		.next_request		= elv_rb_latter_request,
+		.former_request		= elv_rb_former_request,
+		.bio_merge		= dd_bio_merge,
+		.request_merge		= dd_request_merge,
+		.requests_merged	= dd_merged_requests,
+		.request_merged		= dd_request_merged,
+		.has_work		= dd_has_work,
+		.init_sched		= dd_init_queue,
+		.exit_sched		= dd_exit_queue,
+	},
+
+	.uses_mq	= true,
+	.elevator_attrs = deadline_attrs,
+	.elevator_name = "mq-deadline",
+	.elevator_owner = THIS_MODULE,
+};
+
+static int __init deadline_init(void)
+{
+	return elv_register(&mq_deadline);
+}
+
+static void __exit deadline_exit(void)
+{
+	elv_unregister(&mq_deadline);
+}
+
+module_init(deadline_init);
+module_exit(deadline_exit);
+
+MODULE_AUTHOR("Jens Axboe");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MQ deadline IO scheduler");
diff --git a/block/noop-iosched.c b/block/noop-iosched.c
index a163c487cf38..2d1b15d89b45 100644
--- a/block/noop-iosched.c
+++ b/block/noop-iosched.c
@@ -92,7 +92,7 @@ static void noop_exit_queue(struct elevator_queue *e)
 }
 
 static struct elevator_type elevator_noop = {
-	.ops = {
+	.ops.sq = {
 		.elevator_merge_req_fn		= noop_merged_requests,
 		.elevator_dispatch_fn		= noop_dispatch,
 		.elevator_add_req_fn		= noop_add_request,
diff --git a/block/opal_proto.h b/block/opal_proto.h
new file mode 100644
index 000000000000..f40c9acf8895
--- /dev/null
+++ b/block/opal_proto.h
@@ -0,0 +1,452 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Authors:
+ *    Rafael Antognolli <rafael.antognolli@intel.com>
+ *    Scott  Bauer      <scott.bauer@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#include <linux/types.h>
+
+#ifndef _OPAL_PROTO_H
+#define _OPAL_PROTO_H
+
+/*
+ * These constant values come from:
+ * SPC-4 section
+ * 6.30 SECURITY PROTOCOL IN command / table 265.
+ */
+enum {
+	TCG_SECP_00 = 0,
+	TCG_SECP_01,
+};
+
+/*
+ * Token defs derived from:
+ * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
+ * 3.2.2 Data Stream Encoding
+ */
+enum opal_response_token {
+	OPAL_DTA_TOKENID_BYTESTRING = 0xe0,
+	OPAL_DTA_TOKENID_SINT = 0xe1,
+	OPAL_DTA_TOKENID_UINT = 0xe2,
+	OPAL_DTA_TOKENID_TOKEN = 0xe3, /* actual token is returned */
+	OPAL_DTA_TOKENID_INVALID = 0X0
+};
+
+#define DTAERROR_NO_METHOD_STATUS 0x89
+#define GENERIC_HOST_SESSION_NUM 0x41
+
+#define TPER_SYNC_SUPPORTED 0x01
+
+#define TINY_ATOM_DATA_MASK 0x3F
+#define TINY_ATOM_SIGNED 0x40
+
+#define SHORT_ATOM_ID 0x80
+#define SHORT_ATOM_BYTESTRING 0x20
+#define SHORT_ATOM_SIGNED 0x10
+#define SHORT_ATOM_LEN_MASK 0xF
+
+#define MEDIUM_ATOM_ID 0xC0
+#define MEDIUM_ATOM_BYTESTRING 0x10
+#define MEDIUM_ATOM_SIGNED 0x8
+#define MEDIUM_ATOM_LEN_MASK 0x7
+
+#define LONG_ATOM_ID 0xe0
+#define LONG_ATOM_BYTESTRING 0x2
+#define LONG_ATOM_SIGNED 0x1
+
+/* Derived from TCG Core spec 2.01 Section:
+ * 3.2.2.1
+ * Data Type
+ */
+#define TINY_ATOM_BYTE   0x7F
+#define SHORT_ATOM_BYTE  0xBF
+#define MEDIUM_ATOM_BYTE 0xDF
+#define LONG_ATOM_BYTE   0xE3
+
+#define OPAL_INVAL_PARAM 12
+#define OPAL_MANUFACTURED_INACTIVE 0x08
+#define OPAL_DISCOVERY_COMID 0x0001
+
+#define LOCKING_RANGE_NON_GLOBAL 0x03
+/*
+ * User IDs used in the TCG storage SSCs
+ * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
+ * Section: 6.3 Assigned UIDs
+ */
+#define OPAL_UID_LENGTH 8
+#define OPAL_METHOD_LENGTH 8
+#define OPAL_MSID_KEYLEN 15
+#define OPAL_UID_LENGTH_HALF 4
+
+/* Enum to index OPALUID array */
+enum opal_uid {
+	/* users */
+	OPAL_SMUID_UID,
+	OPAL_THISSP_UID,
+	OPAL_ADMINSP_UID,
+	OPAL_LOCKINGSP_UID,
+	OPAL_ENTERPRISE_LOCKINGSP_UID,
+	OPAL_ANYBODY_UID,
+	OPAL_SID_UID,
+	OPAL_ADMIN1_UID,
+	OPAL_USER1_UID,
+	OPAL_USER2_UID,
+	OPAL_PSID_UID,
+	OPAL_ENTERPRISE_BANDMASTER0_UID,
+	OPAL_ENTERPRISE_ERASEMASTER_UID,
+	/* tables */
+	OPAL_LOCKINGRANGE_GLOBAL,
+	OPAL_LOCKINGRANGE_ACE_RDLOCKED,
+	OPAL_LOCKINGRANGE_ACE_WRLOCKED,
+	OPAL_MBRCONTROL,
+	OPAL_MBR,
+	OPAL_AUTHORITY_TABLE,
+	OPAL_C_PIN_TABLE,
+	OPAL_LOCKING_INFO_TABLE,
+	OPAL_ENTERPRISE_LOCKING_INFO_TABLE,
+	/* C_PIN_TABLE object ID's */
+	OPAL_C_PIN_MSID,
+	OPAL_C_PIN_SID,
+	OPAL_C_PIN_ADMIN1,
+	/* half UID's (only first 4 bytes used) */
+	OPAL_HALF_UID_AUTHORITY_OBJ_REF,
+	OPAL_HALF_UID_BOOLEAN_ACE,
+	/* omitted optional parameter */
+	OPAL_UID_HEXFF,
+};
+
+#define OPAL_METHOD_LENGTH 8
+
+/* Enum for indexing the OPALMETHOD array */
+enum opal_method {
+	OPAL_PROPERTIES,
+	OPAL_STARTSESSION,
+	OPAL_REVERT,
+	OPAL_ACTIVATE,
+	OPAL_EGET,
+	OPAL_ESET,
+	OPAL_NEXT,
+	OPAL_EAUTHENTICATE,
+	OPAL_GETACL,
+	OPAL_GENKEY,
+	OPAL_REVERTSP,
+	OPAL_GET,
+	OPAL_SET,
+	OPAL_AUTHENTICATE,
+	OPAL_RANDOM,
+	OPAL_ERASE,
+};
+
+enum opal_token {
+	/* Boolean */
+	OPAL_TRUE = 0x01,
+	OPAL_FALSE = 0x00,
+	OPAL_BOOLEAN_EXPR = 0x03,
+	/* cellblocks */
+	OPAL_TABLE = 0x00,
+	OPAL_STARTROW = 0x01,
+	OPAL_ENDROW = 0x02,
+	OPAL_STARTCOLUMN = 0x03,
+	OPAL_ENDCOLUMN = 0x04,
+	OPAL_VALUES = 0x01,
+	/* authority table */
+	OPAL_PIN = 0x03,
+	/* locking tokens */
+	OPAL_RANGESTART = 0x03,
+	OPAL_RANGELENGTH = 0x04,
+	OPAL_READLOCKENABLED = 0x05,
+	OPAL_WRITELOCKENABLED = 0x06,
+	OPAL_READLOCKED = 0x07,
+	OPAL_WRITELOCKED = 0x08,
+	OPAL_ACTIVEKEY = 0x0A,
+	/* locking info table */
+	OPAL_MAXRANGES = 0x04,
+	 /* mbr control */
+	OPAL_MBRENABLE = 0x01,
+	OPAL_MBRDONE = 0x02,
+	/* properties */
+	OPAL_HOSTPROPERTIES = 0x00,
+	/* atoms */
+	OPAL_STARTLIST = 0xf0,
+	OPAL_ENDLIST = 0xf1,
+	OPAL_STARTNAME = 0xf2,
+	OPAL_ENDNAME = 0xf3,
+	OPAL_CALL = 0xf8,
+	OPAL_ENDOFDATA = 0xf9,
+	OPAL_ENDOFSESSION = 0xfa,
+	OPAL_STARTTRANSACTON = 0xfb,
+	OPAL_ENDTRANSACTON = 0xfC,
+	OPAL_EMPTYATOM = 0xff,
+	OPAL_WHERE = 0x00,
+};
+
+/* Locking state for a locking range */
+enum opal_lockingstate {
+	OPAL_LOCKING_READWRITE = 0x01,
+	OPAL_LOCKING_READONLY = 0x02,
+	OPAL_LOCKING_LOCKED = 0x03,
+};
+
+/* Packets derived from:
+ * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
+ * Secion: 3.2.3 ComPackets, Packets & Subpackets
+ */
+
+/* Comm Packet (header) for transmissions. */
+struct opal_compacket {
+	__be32 reserved0;
+	u8 extendedComID[4];
+	__be32 outstandingData;
+	__be32 minTransfer;
+	__be32 length;
+};
+
+/* Packet structure. */
+struct opal_packet {
+	__be32 tsn;
+	__be32 hsn;
+	__be32 seq_number;
+	__be16 reserved0;
+	__be16 ack_type;
+	__be32 acknowledgment;
+	__be32 length;
+};
+
+/* Data sub packet header */
+struct opal_data_subpacket {
+	u8 reserved0[6];
+	__be16 kind;
+	__be32 length;
+};
+
+/* header of a response */
+struct opal_header {
+	struct opal_compacket cp;
+	struct opal_packet pkt;
+	struct opal_data_subpacket subpkt;
+};
+
+#define FC_TPER       0x0001
+#define FC_LOCKING    0x0002
+#define FC_GEOMETRY   0x0003
+#define FC_ENTERPRISE 0x0100
+#define FC_DATASTORE  0x0202
+#define FC_SINGLEUSER 0x0201
+#define FC_OPALV100   0x0200
+#define FC_OPALV200   0x0203
+
+/*
+ * The Discovery 0 Header. As defined in
+ * Opal SSC Documentation
+ * Section: 3.3.5 Capability Discovery
+ */
+struct d0_header {
+	__be32 length; /* the length of the header 48 in 2.00.100 */
+	__be32 revision; /**< revision of the header 1 in 2.00.100 */
+	__be32 reserved01;
+	__be32 reserved02;
+	/*
+	 * the remainder of the structure is vendor specific and will not be
+	 * addressed now
+	 */
+	u8 ignored[32];
+};
+
+/*
+ * TPer Feature Descriptor. Contains flags indicating support for the
+ * TPer features described in the OPAL specification. The names match the
+ * OPAL terminology
+ *
+ * code == 0x001 in 2.00.100
+ */
+struct d0_tper_features {
+	/*
+	 * supported_features bits:
+	 * bit 7: reserved
+	 * bit 6: com ID management
+	 * bit 5: reserved
+	 * bit 4: streaming support
+	 * bit 3: buffer management
+	 * bit 2: ACK/NACK
+	 * bit 1: async
+	 * bit 0: sync
+	 */
+	u8 supported_features;
+	/*
+	 * bytes 5 through 15 are reserved, but we represent the first 3 as
+	 * u8 to keep the other two 32bits integers aligned.
+	 */
+	u8 reserved01[3];
+	__be32 reserved02;
+	__be32 reserved03;
+};
+
+/*
+ * Locking Feature Descriptor. Contains flags indicating support for the
+ * locking features described in the OPAL specification. The names match the
+ * OPAL terminology
+ *
+ * code == 0x0002 in 2.00.100
+ */
+struct d0_locking_features {
+	/*
+	 * supported_features bits:
+	 * bits 6-7: reserved
+	 * bit 5: MBR done
+	 * bit 4: MBR enabled
+	 * bit 3: media encryption
+	 * bit 2: locked
+	 * bit 1: locking enabled
+	 * bit 0: locking supported
+	 */
+	u8 supported_features;
+	/*
+	 * bytes 5 through 15 are reserved, but we represent the first 3 as
+	 * u8 to keep the other two 32bits integers aligned.
+	 */
+	u8 reserved01[3];
+	__be32 reserved02;
+	__be32 reserved03;
+};
+
+/*
+ * Geometry Feature Descriptor. Contains flags indicating support for the
+ * geometry features described in the OPAL specification. The names match the
+ * OPAL terminology
+ *
+ * code == 0x0003 in 2.00.100
+ */
+struct d0_geometry_features {
+	/*
+	 * skip 32 bits from header, needed to align the struct to 64 bits.
+	 */
+	u8 header[4];
+	/*
+	 * reserved01:
+	 * bits 1-6: reserved
+	 * bit 0: align
+	 */
+	u8 reserved01;
+	u8 reserved02[7];
+	__be32 logical_block_size;
+	__be64 alignment_granularity;
+	__be64 lowest_aligned_lba;
+};
+
+/*
+ * Enterprise SSC Feature
+ *
+ * code == 0x0100
+ */
+struct d0_enterprise_ssc {
+	__be16 baseComID;
+	__be16 numComIDs;
+	/* range_crossing:
+	 * bits 1-6: reserved
+	 * bit 0: range crossing
+	 */
+	u8 range_crossing;
+	u8 reserved01;
+	__be16 reserved02;
+	__be32 reserved03;
+	__be32 reserved04;
+};
+
+/*
+ * Opal V1 feature
+ *
+ * code == 0x0200
+ */
+struct d0_opal_v100 {
+	__be16 baseComID;
+	__be16 numComIDs;
+};
+
+/*
+ * Single User Mode feature
+ *
+ * code == 0x0201
+ */
+struct d0_single_user_mode {
+	__be32 num_locking_objects;
+	/* reserved01:
+	 * bit 0: any
+	 * bit 1: all
+	 * bit 2: policy
+	 * bits 3-7: reserved
+	 */
+	u8 reserved01;
+	u8 reserved02;
+	__be16 reserved03;
+	__be32 reserved04;
+};
+
+/*
+ * Additonal Datastores feature
+ *
+ * code == 0x0202
+ */
+struct d0_datastore_table {
+	__be16 reserved01;
+	__be16 max_tables;
+	__be32 max_size_tables;
+	__be32 table_size_alignment;
+};
+
+/*
+ * OPAL 2.0 feature
+ *
+ * code == 0x0203
+ */
+struct d0_opal_v200 {
+	__be16 baseComID;
+	__be16 numComIDs;
+	/* range_crossing:
+	 * bits 1-6: reserved
+	 * bit 0: range crossing
+	 */
+	u8 range_crossing;
+	/* num_locking_admin_auth:
+	 * not aligned to 16 bits, so use two u8.
+	 * stored in big endian:
+	 * 0: MSB
+	 * 1: LSB
+	 */
+	u8 num_locking_admin_auth[2];
+	/* num_locking_user_auth:
+	 * not aligned to 16 bits, so use two u8.
+	 * stored in big endian:
+	 * 0: MSB
+	 * 1: LSB
+	 */
+	u8 num_locking_user_auth[2];
+	u8 initialPIN;
+	u8 revertedPIN;
+	u8 reserved01;
+	__be32 reserved02;
+};
+
+/* Union of features used to parse the discovery 0 response */
+struct d0_features {
+	__be16 code;
+	/*
+	 * r_version bits:
+	 * bits 4-7: version
+	 * bits 0-3: reserved
+	 */
+	u8 r_version;
+	u8 length;
+	u8 features[];
+};
+
+#endif /* _OPAL_PROTO_H */
diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index bcd86e5cd546..39f70d968754 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -293,7 +293,7 @@ static gpt_entry *alloc_read_gpt_entries(struct parsed_partitions *state,
 	if (!gpt)
 		return NULL;
 
-	count = le32_to_cpu(gpt->num_partition_entries) *
+	count = (size_t)le32_to_cpu(gpt->num_partition_entries) *
                 le32_to_cpu(gpt->sizeof_partition_entry);
 	if (!count)
 		return NULL;
@@ -352,7 +352,7 @@ static int is_gpt_valid(struct parsed_partitions *state, u64 lba,
 			gpt_header **gpt, gpt_entry **ptes)
 {
 	u32 crc, origcrc;
-	u64 lastlba;
+	u64 lastlba, pt_size;
 
 	if (!ptes)
 		return 0;
@@ -434,13 +434,20 @@ static int is_gpt_valid(struct parsed_partitions *state, u64 lba,
 		goto fail;
 	}
 
+	/* Sanity check partition table size */
+	pt_size = (u64)le32_to_cpu((*gpt)->num_partition_entries) *
+		le32_to_cpu((*gpt)->sizeof_partition_entry);
+	if (pt_size > KMALLOC_MAX_SIZE) {
+		pr_debug("GUID Partition Table is too large: %llu > %lu bytes\n",
+			 (unsigned long long)pt_size, KMALLOC_MAX_SIZE);
+		goto fail;
+	}
+
 	if (!(*ptes = alloc_read_gpt_entries(state, *gpt)))
 		goto fail;
 
 	/* Check the GUID Partition Entry Array CRC */
-	crc = efi_crc32((const unsigned char *) (*ptes),
-			le32_to_cpu((*gpt)->num_partition_entries) *
-			le32_to_cpu((*gpt)->sizeof_partition_entry));
+	crc = efi_crc32((const unsigned char *) (*ptes), pt_size);
 
 	if (crc != le32_to_cpu((*gpt)->partition_entry_array_crc32)) {
 		pr_debug("GUID Partition Entry Array CRC check failed.\n");
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index c2b64923ab66..2a2fc768b27a 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -230,15 +230,17 @@ EXPORT_SYMBOL(blk_verify_command);
 static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 			     struct sg_io_hdr *hdr, fmode_t mode)
 {
-	if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
+	struct scsi_request *req = scsi_req(rq);
+
+	if (copy_from_user(req->cmd, hdr->cmdp, hdr->cmd_len))
 		return -EFAULT;
-	if (blk_verify_command(rq->cmd, mode & FMODE_WRITE))
+	if (blk_verify_command(req->cmd, mode & FMODE_WRITE))
 		return -EPERM;
 
 	/*
 	 * fill in request structure
 	 */
-	rq->cmd_len = hdr->cmd_len;
+	req->cmd_len = hdr->cmd_len;
 
 	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
@@ -254,6 +256,7 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 				 struct bio *bio)
 {
+	struct scsi_request *req = scsi_req(rq);
 	int r, ret = 0;
 
 	/*
@@ -267,13 +270,13 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 	hdr->info = 0;
 	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
 		hdr->info |= SG_INFO_CHECK;
-	hdr->resid = rq->resid_len;
+	hdr->resid = req->resid_len;
 	hdr->sb_len_wr = 0;
 
-	if (rq->sense_len && hdr->sbp) {
-		int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len);
+	if (req->sense_len && hdr->sbp) {
+		int len = min((unsigned int) hdr->mx_sb_len, req->sense_len);
 
-		if (!copy_to_user(hdr->sbp, rq->sense, len))
+		if (!copy_to_user(hdr->sbp, req->sense, len))
 			hdr->sb_len_wr = len;
 		else
 			ret = -EFAULT;
@@ -294,7 +297,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	int writing = 0;
 	int at_head = 0;
 	struct request *rq;
-	char sense[SCSI_SENSE_BUFFERSIZE];
+	struct scsi_request *req;
 	struct bio *bio;
 
 	if (hdr->interface_id != 'S')
@@ -318,14 +321,16 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		at_head = 1;
 
 	ret = -ENOMEM;
-	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
+	rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
+			GFP_KERNEL);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
-	blk_rq_set_block_pc(rq);
+	req = scsi_req(rq);
+	scsi_req_init(rq);
 
 	if (hdr->cmd_len > BLK_MAX_CDB) {
-		rq->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
-		if (!rq->cmd)
+		req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
+		if (!req->cmd)
 			goto out_put_request;
 	}
 
@@ -357,9 +362,6 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		goto out_free_cdb;
 
 	bio = rq->bio;
-	memset(sense, 0, sizeof(sense));
-	rq->sense = sense;
-	rq->sense_len = 0;
 	rq->retries = 0;
 
 	start_time = jiffies;
@@ -375,8 +377,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	ret = blk_complete_sghdr_rq(rq, hdr, bio);
 
 out_free_cdb:
-	if (rq->cmd != rq->__cmd)
-		kfree(rq->cmd);
+	scsi_req_free_cmd(req);
 out_put_request:
 	blk_put_request(rq);
 	return ret;
@@ -420,9 +421,10 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		struct scsi_ioctl_command __user *sic)
 {
 	struct request *rq;
+	struct scsi_request *req;
 	int err;
 	unsigned int in_len, out_len, bytes, opcode, cmdlen;
-	char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE];
+	char *buffer = NULL;
 
 	if (!sic)
 		return -EINVAL;
@@ -447,12 +449,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	}
 
-	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_RECLAIM);
+	rq = blk_get_request(q, in_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
+			__GFP_RECLAIM);
 	if (IS_ERR(rq)) {
 		err = PTR_ERR(rq);
 		goto error_free_buffer;
 	}
-	blk_rq_set_block_pc(rq);
+	req = scsi_req(rq);
+	scsi_req_init(rq);
 
 	cmdlen = COMMAND_SIZE(opcode);
 
@@ -460,14 +464,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 	 * get command and data to send to device, if any
 	 */
 	err = -EFAULT;
-	rq->cmd_len = cmdlen;
-	if (copy_from_user(rq->cmd, sic->data, cmdlen))
+	req->cmd_len = cmdlen;
+	if (copy_from_user(req->cmd, sic->data, cmdlen))
 		goto error;
 
 	if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
 		goto error;
 
-	err = blk_verify_command(rq->cmd, mode & FMODE_WRITE);
+	err = blk_verify_command(req->cmd, mode & FMODE_WRITE);
 	if (err)
 		goto error;
 
@@ -503,18 +507,14 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		goto error;
 	}
 
-	memset(sense, 0, sizeof(sense));
-	rq->sense = sense;
-	rq->sense_len = 0;
-
 	blk_execute_rq(q, disk, rq, 0);
 
 	err = rq->errors & 0xff;	/* only 8 bit SCSI status */
 	if (err) {
-		if (rq->sense_len && rq->sense) {
-			bytes = (OMAX_SB_LEN > rq->sense_len) ?
-				rq->sense_len : OMAX_SB_LEN;
-			if (copy_to_user(sic->data, rq->sense, bytes))
+		if (req->sense_len && req->sense) {
+			bytes = (OMAX_SB_LEN > req->sense_len) ?
+				req->sense_len : OMAX_SB_LEN;
+			if (copy_to_user(sic->data, req->sense, bytes))
 				err = -EFAULT;
 		}
 	} else {
@@ -539,14 +539,14 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	struct request *rq;
 	int err;
 
-	rq = blk_get_request(q, WRITE, __GFP_RECLAIM);
+	rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
-	blk_rq_set_block_pc(rq);
+	scsi_req_init(rq);
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
-	rq->cmd[0] = cmd;
-	rq->cmd[4] = data;
-	rq->cmd_len = 6;
+	scsi_req(rq)->cmd[0] = cmd;
+	scsi_req(rq)->cmd[4] = data;
+	scsi_req(rq)->cmd_len = 6;
 	err = blk_execute_rq(q, bd_disk, rq, 0);
 	blk_put_request(rq);
 
@@ -743,6 +743,17 @@ int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode,
 }
 EXPORT_SYMBOL(scsi_cmd_blk_ioctl);
 
+void scsi_req_init(struct request *rq)
+{
+	struct scsi_request *req = scsi_req(rq);
+
+	memset(req->__cmd, 0, sizeof(req->__cmd));
+	req->cmd = req->__cmd;
+	req->cmd_len = BLK_MAX_CDB;
+	req->sense_len = 0;
+}
+EXPORT_SYMBOL(scsi_req_init);
+
 static int __init blk_scsi_ioctl_init(void)
 {
 	blk_set_cmd_filter_defaults(&blk_default_cmd_filter);
diff --git a/block/sed-opal.c b/block/sed-opal.c
new file mode 100644
index 000000000000..d1c52ba4d62d
--- /dev/null
+++ b/block/sed-opal.c
@@ -0,0 +1,2488 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Authors:
+ *    Scott  Bauer      <scott.bauer@intel.com>
+ *    Rafael Antognolli <rafael.antognolli@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ":OPAL: " fmt
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/genhd.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <uapi/linux/sed-opal.h>
+#include <linux/sed-opal.h>
+#include <linux/string.h>
+#include <linux/kdev_t.h>
+
+#include "opal_proto.h"
+
+#define IO_BUFFER_LENGTH 2048
+#define MAX_TOKS 64
+
+typedef int (*opal_step)(struct opal_dev *dev);
+
+enum opal_atom_width {
+	OPAL_WIDTH_TINY,
+	OPAL_WIDTH_SHORT,
+	OPAL_WIDTH_MEDIUM,
+	OPAL_WIDTH_LONG,
+	OPAL_WIDTH_TOKEN
+};
+
+/*
+ * On the parsed response, we don't store again the toks that are already
+ * stored in the response buffer. Instead, for each token, we just store a
+ * pointer to the position in the buffer where the token starts, and the size
+ * of the token in bytes.
+ */
+struct opal_resp_tok {
+	const u8 *pos;
+	size_t len;
+	enum opal_response_token type;
+	enum opal_atom_width width;
+	union {
+		u64 u;
+		s64 s;
+	} stored;
+};
+
+/*
+ * From the response header it's not possible to know how many tokens there are
+ * on the payload. So we hardcode that the maximum will be MAX_TOKS, and later
+ * if we start dealing with messages that have more than that, we can increase
+ * this number. This is done to avoid having to make two passes through the
+ * response, the first one counting how many tokens we have and the second one
+ * actually storing the positions.
+ */
+struct parsed_resp {
+	int num;
+	struct opal_resp_tok toks[MAX_TOKS];
+};
+
+struct opal_dev {
+	bool supported;
+
+	void *data;
+	sec_send_recv *send_recv;
+
+	const opal_step *funcs;
+	void **func_data;
+	int state;
+	struct mutex dev_lock;
+	u16 comid;
+	u32 hsn;
+	u32 tsn;
+	u64 align;
+	u64 lowest_lba;
+
+	size_t pos;
+	u8 cmd[IO_BUFFER_LENGTH];
+	u8 resp[IO_BUFFER_LENGTH];
+
+	struct parsed_resp parsed;
+	size_t prev_d_len;
+	void *prev_data;
+
+	struct list_head unlk_lst;
+};
+
+
+static const u8 opaluid[][OPAL_UID_LENGTH] = {
+	/* users */
+	[OPAL_SMUID_UID] =
+		{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff },
+	[OPAL_THISSP_UID] =
+		{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_ADMINSP_UID] =
+		{ 0x00, 0x00, 0x02, 0x05, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_LOCKINGSP_UID] =
+		{ 0x00, 0x00, 0x02, 0x05, 0x00, 0x00, 0x00, 0x02 },
+	[OPAL_ENTERPRISE_LOCKINGSP_UID] =
+		{ 0x00, 0x00, 0x02, 0x05, 0x00, 0x01, 0x00, 0x01 },
+	[OPAL_ANYBODY_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_SID_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x00, 0x06 },
+	[OPAL_ADMIN1_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x01, 0x00, 0x01 },
+	[OPAL_USER1_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x03, 0x00, 0x01 },
+	[OPAL_USER2_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x03, 0x00, 0x02 },
+	[OPAL_PSID_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x01, 0xff, 0x01 },
+	[OPAL_ENTERPRISE_BANDMASTER0_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x80, 0x01 },
+	[OPAL_ENTERPRISE_ERASEMASTER_UID] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x84, 0x01 },
+
+	/* tables */
+
+	[OPAL_LOCKINGRANGE_GLOBAL] =
+		{ 0x00, 0x00, 0x08, 0x02, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_LOCKINGRANGE_ACE_RDLOCKED] =
+		{ 0x00, 0x00, 0x00, 0x08, 0x00, 0x03, 0xE0, 0x01 },
+	[OPAL_LOCKINGRANGE_ACE_WRLOCKED] =
+		{ 0x00, 0x00, 0x00, 0x08, 0x00, 0x03, 0xE8, 0x01 },
+	[OPAL_MBRCONTROL] =
+		{ 0x00, 0x00, 0x08, 0x03, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_MBR] =
+		{ 0x00, 0x00, 0x08, 0x04, 0x00, 0x00, 0x00, 0x00 },
+	[OPAL_AUTHORITY_TABLE] =
+		{ 0x00, 0x00, 0x00, 0x09, 0x00, 0x00, 0x00, 0x00},
+	[OPAL_C_PIN_TABLE] =
+		{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x00, 0x00},
+	[OPAL_LOCKING_INFO_TABLE] =
+		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x01 },
+	[OPAL_ENTERPRISE_LOCKING_INFO_TABLE] =
+		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x00 },
+
+	/* C_PIN_TABLE object ID's */
+
+        [OPAL_C_PIN_MSID] =
+		{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x84, 0x02},
+	[OPAL_C_PIN_SID] =
+		{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x00, 0x00, 0x01},
+	[OPAL_C_PIN_ADMIN1] =
+		{ 0x00, 0x00, 0x00, 0x0B, 0x00, 0x01, 0x00, 0x01},
+
+	/* half UID's (only first 4 bytes used) */
+
+	[OPAL_HALF_UID_AUTHORITY_OBJ_REF] =
+		{ 0x00, 0x00, 0x0C, 0x05, 0xff, 0xff, 0xff, 0xff },
+	[OPAL_HALF_UID_BOOLEAN_ACE] =
+		{ 0x00, 0x00, 0x04, 0x0E, 0xff, 0xff, 0xff, 0xff },
+
+	/* special value for omitted optional parameter */
+	[OPAL_UID_HEXFF] =
+		{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff},
+};
+
+/*
+ * TCG Storage SSC Methods.
+ * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
+ * Section: 6.3 Assigned UIDs
+ */
+static const u8 opalmethod[][OPAL_UID_LENGTH] = {
+	[OPAL_PROPERTIES] =
+		{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x01 },
+	[OPAL_STARTSESSION] =
+		{ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x02 },
+	[OPAL_REVERT] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x02, 0x02 },
+	[OPAL_ACTIVATE] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x02, 0x03 },
+	[OPAL_EGET] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x06 },
+	[OPAL_ESET] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x07 },
+	[OPAL_NEXT] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x08 },
+	[OPAL_EAUTHENTICATE] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x0c },
+	[OPAL_GETACL] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x0d },
+	[OPAL_GENKEY] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x10 },
+	[OPAL_REVERTSP] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x11 },
+	[OPAL_GET] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x16 },
+	[OPAL_SET] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x17 },
+	[OPAL_AUTHENTICATE] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x00, 0x1c },
+	[OPAL_RANDOM] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x06, 0x01 },
+	[OPAL_ERASE] =
+		{ 0x00, 0x00, 0x00, 0x06, 0x00, 0x00, 0x08, 0x03 },
+};
+
+typedef int (cont_fn)(struct opal_dev *dev);
+
+static int end_opal_session_error(struct opal_dev *dev);
+
+struct opal_suspend_data {
+	struct opal_lock_unlock unlk;
+	u8 lr;
+	struct list_head node;
+};
+
+/*
+ * Derived from:
+ * TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
+ * Section: 5.1.5 Method Status Codes
+ */
+static const char * const opal_errors[] = {
+	"Success",
+	"Not Authorized",
+	"Unknown Error",
+	"SP Busy",
+	"SP Failed",
+	"SP Disabled",
+	"SP Frozen",
+	"No Sessions Available",
+	"Uniqueness Conflict",
+	"Insufficient Space",
+	"Insufficient Rows",
+	"Invalid Function",
+	"Invalid Parameter",
+	"Invalid Reference",
+	"Unknown Error",
+	"TPER Malfunction",
+	"Transaction Failure",
+	"Response Overflow",
+	"Authority Locked Out",
+};
+
+static const char *opal_error_to_human(int error)
+{
+	if (error == 0x3f)
+		return "Failed";
+
+	if (error >= ARRAY_SIZE(opal_errors) || error < 0)
+		return "Unknown Error";
+
+	return opal_errors[error];
+}
+
+static void print_buffer(const u8 *ptr, u32 length)
+{
+#ifdef DEBUG
+	print_hex_dump_bytes("OPAL: ", DUMP_PREFIX_OFFSET, ptr, length);
+	pr_debug("\n");
+#endif
+}
+
+static bool check_tper(const void *data)
+{
+	const struct d0_tper_features *tper = data;
+	u8 flags = tper->supported_features;
+
+	if (!(flags & TPER_SYNC_SUPPORTED)) {
+		pr_err("TPer sync not supported. flags = %d\n",
+		       tper->supported_features);
+		return false;
+	}
+
+	return true;
+}
+
+static bool check_sum(const void *data)
+{
+	const struct d0_single_user_mode *sum = data;
+	u32 nlo = be32_to_cpu(sum->num_locking_objects);
+
+	if (nlo == 0) {
+		pr_err("Need at least one locking object.\n");
+		return false;
+	}
+
+	pr_debug("Number of locking objects: %d\n", nlo);
+
+	return true;
+}
+
+static u16 get_comid_v100(const void *data)
+{
+	const struct d0_opal_v100 *v100 = data;
+
+	return be16_to_cpu(v100->baseComID);
+}
+
+static u16 get_comid_v200(const void *data)
+{
+	const struct d0_opal_v200 *v200 = data;
+
+	return be16_to_cpu(v200->baseComID);
+}
+
+static int opal_send_cmd(struct opal_dev *dev)
+{
+	return dev->send_recv(dev->data, dev->comid, TCG_SECP_01,
+			      dev->cmd, IO_BUFFER_LENGTH,
+			      true);
+}
+
+static int opal_recv_cmd(struct opal_dev *dev)
+{
+	return dev->send_recv(dev->data, dev->comid, TCG_SECP_01,
+			      dev->resp, IO_BUFFER_LENGTH,
+			      false);
+}
+
+static int opal_recv_check(struct opal_dev *dev)
+{
+	size_t buflen = IO_BUFFER_LENGTH;
+	void *buffer = dev->resp;
+	struct opal_header *hdr = buffer;
+	int ret;
+
+	do {
+		pr_debug("Sent OPAL command: outstanding=%d, minTransfer=%d\n",
+			 hdr->cp.outstandingData,
+			 hdr->cp.minTransfer);
+
+		if (hdr->cp.outstandingData == 0 ||
+		    hdr->cp.minTransfer != 0)
+			return 0;
+
+		memset(buffer, 0, buflen);
+		ret = opal_recv_cmd(dev);
+	} while (!ret);
+
+	return ret;
+}
+
+static int opal_send_recv(struct opal_dev *dev, cont_fn *cont)
+{
+	int ret;
+
+	ret = opal_send_cmd(dev);
+	if (ret)
+		return ret;
+	ret = opal_recv_cmd(dev);
+	if (ret)
+		return ret;
+	ret = opal_recv_check(dev);
+	if (ret)
+		return ret;
+	return cont(dev);
+}
+
+static void check_geometry(struct opal_dev *dev, const void *data)
+{
+	const struct d0_geometry_features *geo = data;
+
+	dev->align = geo->alignment_granularity;
+	dev->lowest_lba = geo->lowest_aligned_lba;
+}
+
+static int next(struct opal_dev *dev)
+{
+	opal_step func;
+	int error = 0;
+
+	do {
+		func = dev->funcs[dev->state];
+		if (!func)
+			break;
+
+		error = func(dev);
+		if (error) {
+			pr_err("Error on step function: %d with error %d: %s\n",
+			       dev->state, error,
+			       opal_error_to_human(error));
+
+			/* For each OPAL command we do a discovery0 then we
+			 * start some sort of session.
+			 * If we haven't passed state 1 then there was an error
+			 * on discovery0 or during the attempt to start a
+			 * session. Therefore we shouldn't attempt to terminate
+			 * a session, as one has not yet been created.
+			 */
+			if (dev->state > 1)
+				return end_opal_session_error(dev);
+		}
+		dev->state++;
+	} while (!error);
+
+	return error;
+}
+
+static int opal_discovery0_end(struct opal_dev *dev)
+{
+	bool found_com_id = false, supported = true, single_user = false;
+	const struct d0_header *hdr = (struct d0_header *)dev->resp;
+	const u8 *epos = dev->resp, *cpos = dev->resp;
+	u16 comid = 0;
+
+	print_buffer(dev->resp, be32_to_cpu(hdr->length));
+
+	epos += be32_to_cpu(hdr->length); /* end of buffer */
+	cpos += sizeof(*hdr); /* current position on buffer */
+
+	while (cpos < epos && supported) {
+		const struct d0_features *body =
+			(const struct d0_features *)cpos;
+
+		switch (be16_to_cpu(body->code)) {
+		case FC_TPER:
+			supported = check_tper(body->features);
+			break;
+		case FC_SINGLEUSER:
+			single_user = check_sum(body->features);
+			break;
+		case FC_GEOMETRY:
+			check_geometry(dev, body);
+			break;
+		case FC_LOCKING:
+		case FC_ENTERPRISE:
+		case FC_DATASTORE:
+			/* some ignored properties */
+			pr_debug("Found OPAL feature description: %d\n",
+				 be16_to_cpu(body->code));
+			break;
+		case FC_OPALV100:
+			comid = get_comid_v100(body->features);
+			found_com_id = true;
+			break;
+		case FC_OPALV200:
+			comid = get_comid_v200(body->features);
+			found_com_id = true;
+			break;
+		case 0xbfff ... 0xffff:
+			/* vendor specific, just ignore */
+			break;
+		default:
+			pr_debug("OPAL Unknown feature: %d\n",
+				 be16_to_cpu(body->code));
+
+		}
+		cpos += body->length + 4;
+	}
+
+	if (!supported) {
+		pr_debug("This device is not Opal enabled. Not Supported!\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (!single_user)
+		pr_debug("Device doesn't support single user mode\n");
+
+
+	if (!found_com_id) {
+		pr_debug("Could not find OPAL comid for device. Returning early\n");
+		return -EOPNOTSUPP;;
+	}
+
+	dev->comid = comid;
+
+	return 0;
+}
+
+static int opal_discovery0(struct opal_dev *dev)
+{
+	int ret;
+
+	memset(dev->resp, 0, IO_BUFFER_LENGTH);
+	dev->comid = OPAL_DISCOVERY_COMID;
+	ret = opal_recv_cmd(dev);
+	if (ret)
+		return ret;
+	return opal_discovery0_end(dev);
+}
+
+static void add_token_u8(int *err, struct opal_dev *cmd, u8 tok)
+{
+	if (*err)
+		return;
+	if (cmd->pos >= IO_BUFFER_LENGTH - 1) {
+		pr_err("Error adding u8: end of buffer.\n");
+		*err = -ERANGE;
+		return;
+	}
+	cmd->cmd[cmd->pos++] = tok;
+}
+
+static void add_short_atom_header(struct opal_dev *cmd, bool bytestring,
+				  bool has_sign, int len)
+{
+	u8 atom;
+	int err = 0;
+
+	atom = SHORT_ATOM_ID;
+	atom |= bytestring ? SHORT_ATOM_BYTESTRING : 0;
+	atom |= has_sign ? SHORT_ATOM_SIGNED : 0;
+	atom |= len & SHORT_ATOM_LEN_MASK;
+
+	add_token_u8(&err, cmd, atom);
+}
+
+static void add_medium_atom_header(struct opal_dev *cmd, bool bytestring,
+				   bool has_sign, int len)
+{
+	u8 header0;
+
+	header0 = MEDIUM_ATOM_ID;
+	header0 |= bytestring ? MEDIUM_ATOM_BYTESTRING : 0;
+	header0 |= has_sign ? MEDIUM_ATOM_SIGNED : 0;
+	header0 |= (len >> 8) & MEDIUM_ATOM_LEN_MASK;
+	cmd->cmd[cmd->pos++] = header0;
+	cmd->cmd[cmd->pos++] = len;
+}
+
+static void add_token_u64(int *err, struct opal_dev *cmd, u64 number)
+{
+
+	size_t len;
+	int msb;
+	u8 n;
+
+	if (!(number & ~TINY_ATOM_DATA_MASK)) {
+		add_token_u8(err, cmd, number);
+		return;
+	}
+
+	msb = fls(number);
+	len = DIV_ROUND_UP(msb, 4);
+
+	if (cmd->pos >= IO_BUFFER_LENGTH - len - 1) {
+		pr_err("Error adding u64: end of buffer.\n");
+		*err = -ERANGE;
+		return;
+	}
+	add_short_atom_header(cmd, false, false, len);
+	while (len--) {
+		n = number >> (len * 8);
+		add_token_u8(err, cmd, n);
+	}
+}
+
+static void add_token_bytestring(int *err, struct opal_dev *cmd,
+				 const u8 *bytestring, size_t len)
+{
+	size_t header_len = 1;
+	bool is_short_atom = true;
+
+	if (*err)
+		return;
+
+	if (len & ~SHORT_ATOM_LEN_MASK) {
+		header_len = 2;
+		is_short_atom = false;
+	}
+
+	if (len >= IO_BUFFER_LENGTH - cmd->pos - header_len) {
+		pr_err("Error adding bytestring: end of buffer.\n");
+		*err = -ERANGE;
+		return;
+	}
+
+	if (is_short_atom)
+		add_short_atom_header(cmd, true, false, len);
+	else
+		add_medium_atom_header(cmd, true, false, len);
+
+	memcpy(&cmd->cmd[cmd->pos], bytestring, len);
+	cmd->pos += len;
+
+}
+
+static int build_locking_range(u8 *buffer, size_t length, u8 lr)
+{
+	if (length > OPAL_UID_LENGTH) {
+		pr_err("Can't build locking range. Length OOB\n");
+		return -ERANGE;
+	}
+
+	memcpy(buffer, opaluid[OPAL_LOCKINGRANGE_GLOBAL], OPAL_UID_LENGTH);
+
+	if (lr == 0)
+		return 0;
+	buffer[5] = LOCKING_RANGE_NON_GLOBAL;
+	buffer[7] = lr;
+
+	return 0;
+}
+
+static int build_locking_user(u8 *buffer, size_t length, u8 lr)
+{
+	if (length > OPAL_UID_LENGTH) {
+		pr_err("Can't build locking range user, Length OOB\n");
+		return -ERANGE;
+	}
+
+	memcpy(buffer, opaluid[OPAL_USER1_UID], OPAL_UID_LENGTH);
+
+	buffer[7] = lr + 1;
+
+	return 0;
+}
+
+static void set_comid(struct opal_dev *cmd, u16 comid)
+{
+	struct opal_header *hdr = (struct opal_header *)cmd->cmd;
+
+	hdr->cp.extendedComID[0] = comid >> 8;
+	hdr->cp.extendedComID[1] = comid;
+	hdr->cp.extendedComID[2] = 0;
+	hdr->cp.extendedComID[3] = 0;
+}
+
+static int cmd_finalize(struct opal_dev *cmd, u32 hsn, u32 tsn)
+{
+	struct opal_header *hdr;
+	int err = 0;
+
+	add_token_u8(&err, cmd, OPAL_ENDOFDATA);
+	add_token_u8(&err, cmd, OPAL_STARTLIST);
+	add_token_u8(&err, cmd, 0);
+	add_token_u8(&err, cmd, 0);
+	add_token_u8(&err, cmd, 0);
+	add_token_u8(&err, cmd, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error finalizing command.\n");
+		return -EFAULT;
+	}
+
+	hdr = (struct opal_header *) cmd->cmd;
+
+	hdr->pkt.tsn = cpu_to_be32(tsn);
+	hdr->pkt.hsn = cpu_to_be32(hsn);
+
+	hdr->subpkt.length = cpu_to_be32(cmd->pos - sizeof(*hdr));
+	while (cmd->pos % 4) {
+		if (cmd->pos >= IO_BUFFER_LENGTH) {
+			pr_err("Error: Buffer overrun\n");
+			return -ERANGE;
+		}
+		cmd->cmd[cmd->pos++] = 0;
+	}
+	hdr->pkt.length = cpu_to_be32(cmd->pos - sizeof(hdr->cp) -
+				      sizeof(hdr->pkt));
+	hdr->cp.length = cpu_to_be32(cmd->pos - sizeof(hdr->cp));
+
+	return 0;
+}
+
+static enum opal_response_token token_type(const struct parsed_resp *resp,
+					   int n)
+{
+	const struct opal_resp_tok *tok;
+
+	if (n >= resp->num) {
+		pr_err("Token number doesn't exist: %d, resp: %d\n",
+		       n, resp->num);
+		return OPAL_DTA_TOKENID_INVALID;
+	}
+
+	tok = &resp->toks[n];
+	if (tok->len == 0) {
+		pr_err("Token length must be non-zero\n");
+		return OPAL_DTA_TOKENID_INVALID;
+	}
+
+	return tok->type;
+}
+
+/*
+ * This function returns 0 in case of invalid token. One should call
+ * token_type() first to find out if the token is valid or not.
+ */
+static enum opal_token response_get_token(const struct parsed_resp *resp,
+					  int n)
+{
+	const struct opal_resp_tok *tok;
+
+	if (n >= resp->num) {
+		pr_err("Token number doesn't exist: %d, resp: %d\n",
+		       n, resp->num);
+		return 0;
+	}
+
+	tok = &resp->toks[n];
+	if (tok->len == 0) {
+		pr_err("Token length must be non-zero\n");
+		return 0;
+	}
+
+	return tok->pos[0];
+}
+
+static size_t response_parse_tiny(struct opal_resp_tok *tok,
+				  const u8 *pos)
+{
+	tok->pos = pos;
+	tok->len = 1;
+	tok->width = OPAL_WIDTH_TINY;
+
+	if (pos[0] & TINY_ATOM_SIGNED) {
+		tok->type = OPAL_DTA_TOKENID_SINT;
+	} else {
+		tok->type = OPAL_DTA_TOKENID_UINT;
+		tok->stored.u = pos[0] & 0x3f;
+	}
+
+	return tok->len;
+}
+
+static size_t response_parse_short(struct opal_resp_tok *tok,
+				   const u8 *pos)
+{
+	tok->pos = pos;
+	tok->len = (pos[0] & SHORT_ATOM_LEN_MASK) + 1;
+	tok->width = OPAL_WIDTH_SHORT;
+
+	if (pos[0] & SHORT_ATOM_BYTESTRING) {
+		tok->type = OPAL_DTA_TOKENID_BYTESTRING;
+	} else if (pos[0] & SHORT_ATOM_SIGNED) {
+		tok->type = OPAL_DTA_TOKENID_SINT;
+	} else {
+		u64 u_integer = 0;
+		int i, b = 0;
+
+		tok->type = OPAL_DTA_TOKENID_UINT;
+		if (tok->len > 9) {
+			pr_warn("uint64 with more than 8 bytes\n");
+			return -EINVAL;
+		}
+		for (i = tok->len - 1; i > 0; i--) {
+			u_integer |= ((u64)pos[i] << (8 * b));
+			b++;
+		}
+		tok->stored.u = u_integer;
+	}
+
+	return tok->len;
+}
+
+static size_t response_parse_medium(struct opal_resp_tok *tok,
+				    const u8 *pos)
+{
+	tok->pos = pos;
+	tok->len = (((pos[0] & MEDIUM_ATOM_LEN_MASK) << 8) | pos[1]) + 2;
+	tok->width = OPAL_WIDTH_MEDIUM;
+
+	if (pos[0] & MEDIUM_ATOM_BYTESTRING)
+		tok->type = OPAL_DTA_TOKENID_BYTESTRING;
+	else if (pos[0] & MEDIUM_ATOM_SIGNED)
+		tok->type = OPAL_DTA_TOKENID_SINT;
+	else
+		tok->type = OPAL_DTA_TOKENID_UINT;
+
+	return tok->len;
+}
+
+static size_t response_parse_long(struct opal_resp_tok *tok,
+				  const u8 *pos)
+{
+	tok->pos = pos;
+	tok->len = ((pos[1] << 16) | (pos[2] << 8) | pos[3]) + 4;
+	tok->width = OPAL_WIDTH_LONG;
+
+	if (pos[0] & LONG_ATOM_BYTESTRING)
+		tok->type = OPAL_DTA_TOKENID_BYTESTRING;
+	else if (pos[0] & LONG_ATOM_SIGNED)
+		tok->type = OPAL_DTA_TOKENID_SINT;
+	else
+		tok->type = OPAL_DTA_TOKENID_UINT;
+
+	return tok->len;
+}
+
+static size_t response_parse_token(struct opal_resp_tok *tok,
+				   const u8 *pos)
+{
+	tok->pos = pos;
+	tok->len = 1;
+	tok->type = OPAL_DTA_TOKENID_TOKEN;
+	tok->width = OPAL_WIDTH_TOKEN;
+
+	return tok->len;
+}
+
+static int response_parse(const u8 *buf, size_t length,
+			  struct parsed_resp *resp)
+{
+	const struct opal_header *hdr;
+	struct opal_resp_tok *iter;
+	int num_entries = 0;
+	int total;
+	size_t token_length;
+	const u8 *pos;
+
+	if (!buf)
+		return -EFAULT;
+
+	if (!resp)
+		return -EFAULT;
+
+	hdr = (struct opal_header *)buf;
+	pos = buf;
+	pos += sizeof(*hdr);
+
+	pr_debug("Response size: cp: %d, pkt: %d, subpkt: %d\n",
+		 be32_to_cpu(hdr->cp.length),
+		 be32_to_cpu(hdr->pkt.length),
+		 be32_to_cpu(hdr->subpkt.length));
+
+	if (hdr->cp.length == 0 || hdr->pkt.length == 0 ||
+	    hdr->subpkt.length == 0) {
+		pr_err("Bad header length. cp: %d, pkt: %d, subpkt: %d\n",
+		       be32_to_cpu(hdr->cp.length),
+		       be32_to_cpu(hdr->pkt.length),
+		       be32_to_cpu(hdr->subpkt.length));
+		print_buffer(pos, sizeof(*hdr));
+		return -EINVAL;
+	}
+
+	if (pos > buf + length)
+		return -EFAULT;
+
+	iter = resp->toks;
+	total = be32_to_cpu(hdr->subpkt.length);
+	print_buffer(pos, total);
+	while (total > 0) {
+		if (pos[0] <= TINY_ATOM_BYTE) /* tiny atom */
+			token_length = response_parse_tiny(iter, pos);
+		else if (pos[0] <= SHORT_ATOM_BYTE) /* short atom */
+			token_length = response_parse_short(iter, pos);
+		else if (pos[0] <= MEDIUM_ATOM_BYTE) /* medium atom */
+			token_length = response_parse_medium(iter, pos);
+		else if (pos[0] <= LONG_ATOM_BYTE) /* long atom */
+			token_length = response_parse_long(iter, pos);
+		else /* TOKEN */
+			token_length = response_parse_token(iter, pos);
+
+		if (token_length == -EINVAL)
+			return -EINVAL;
+
+		pos += token_length;
+		total -= token_length;
+		iter++;
+		num_entries++;
+	}
+
+	if (num_entries == 0) {
+		pr_err("Couldn't parse response.\n");
+		return -EINVAL;
+	}
+	resp->num = num_entries;
+
+	return 0;
+}
+
+static size_t response_get_string(const struct parsed_resp *resp, int n,
+				  const char **store)
+{
+	*store = NULL;
+	if (!resp) {
+		pr_err("Response is NULL\n");
+		return 0;
+	}
+
+	if (n > resp->num) {
+		pr_err("Response has %d tokens. Can't access %d\n",
+		       resp->num, n);
+		return 0;
+	}
+
+	if (resp->toks[n].type != OPAL_DTA_TOKENID_BYTESTRING) {
+		pr_err("Token is not a byte string!\n");
+		return 0;
+	}
+
+	*store = resp->toks[n].pos + 1;
+	return resp->toks[n].len - 1;
+}
+
+static u64 response_get_u64(const struct parsed_resp *resp, int n)
+{
+	if (!resp) {
+		pr_err("Response is NULL\n");
+		return 0;
+	}
+
+	if (n > resp->num) {
+		pr_err("Response has %d tokens. Can't access %d\n",
+		       resp->num, n);
+		return 0;
+	}
+
+	if (resp->toks[n].type != OPAL_DTA_TOKENID_UINT) {
+		pr_err("Token is not unsigned it: %d\n",
+		       resp->toks[n].type);
+		return 0;
+	}
+
+	if (!(resp->toks[n].width == OPAL_WIDTH_TINY ||
+	      resp->toks[n].width == OPAL_WIDTH_SHORT)) {
+		pr_err("Atom is not short or tiny: %d\n",
+		       resp->toks[n].width);
+		return 0;
+	}
+
+	return resp->toks[n].stored.u;
+}
+
+static u8 response_status(const struct parsed_resp *resp)
+{
+	if (token_type(resp, 0) == OPAL_DTA_TOKENID_TOKEN &&
+	    response_get_token(resp, 0) == OPAL_ENDOFSESSION) {
+		return 0;
+	}
+
+	if (resp->num < 5)
+		return DTAERROR_NO_METHOD_STATUS;
+
+	if (token_type(resp, resp->num - 1) != OPAL_DTA_TOKENID_TOKEN ||
+	    token_type(resp, resp->num - 5) != OPAL_DTA_TOKENID_TOKEN ||
+	    response_get_token(resp, resp->num - 1) != OPAL_ENDLIST ||
+	    response_get_token(resp, resp->num - 5) != OPAL_STARTLIST)
+		return DTAERROR_NO_METHOD_STATUS;
+
+	return response_get_u64(resp, resp->num - 4);
+}
+
+/* Parses and checks for errors */
+static int parse_and_check_status(struct opal_dev *dev)
+{
+	int error;
+
+	print_buffer(dev->cmd, dev->pos);
+
+	error = response_parse(dev->resp, IO_BUFFER_LENGTH, &dev->parsed);
+	if (error) {
+		pr_err("Couldn't parse response.\n");
+		return error;
+	}
+
+	return response_status(&dev->parsed);
+}
+
+static void clear_opal_cmd(struct opal_dev *dev)
+{
+	dev->pos = sizeof(struct opal_header);
+	memset(dev->cmd, 0, IO_BUFFER_LENGTH);
+}
+
+static int start_opal_session_cont(struct opal_dev *dev)
+{
+	u32 hsn, tsn;
+	int error = 0;
+
+	error = parse_and_check_status(dev);
+	if (error)
+		return error;
+
+	hsn = response_get_u64(&dev->parsed, 4);
+	tsn = response_get_u64(&dev->parsed, 5);
+
+	if (hsn == 0 && tsn == 0) {
+		pr_err("Couldn't authenticate session\n");
+		return -EPERM;
+	}
+
+	dev->hsn = hsn;
+	dev->tsn = tsn;
+	return 0;
+}
+
+static void add_suspend_info(struct opal_dev *dev,
+			     struct opal_suspend_data *sus)
+{
+	struct opal_suspend_data *iter;
+
+	list_for_each_entry(iter, &dev->unlk_lst, node) {
+		if (iter->lr == sus->lr) {
+			list_del(&iter->node);
+			kfree(iter);
+			break;
+		}
+	}
+	list_add_tail(&sus->node, &dev->unlk_lst);
+}
+
+static int end_session_cont(struct opal_dev *dev)
+{
+	dev->hsn = 0;
+	dev->tsn = 0;
+	return parse_and_check_status(dev);
+}
+
+static int finalize_and_send(struct opal_dev *dev, cont_fn cont)
+{
+	int ret;
+
+	ret = cmd_finalize(dev, dev->hsn, dev->tsn);
+	if (ret) {
+		pr_err("Error finalizing command buffer: %d\n", ret);
+		return ret;
+	}
+
+	print_buffer(dev->cmd, dev->pos);
+
+	return opal_send_recv(dev, cont);
+}
+
+static int gen_key(struct opal_dev *dev)
+{
+	const u8 *method;
+	u8 uid[OPAL_UID_LENGTH];
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	memcpy(uid, dev->prev_data, min(sizeof(uid), dev->prev_d_len));
+	method = opalmethod[OPAL_GENKEY];
+	kfree(dev->prev_data);
+	dev->prev_data = NULL;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_GENKEY],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building gen key command\n");
+		return err;
+
+	}
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int get_active_key_cont(struct opal_dev *dev)
+{
+	const char *activekey;
+	size_t keylen;
+	int error = 0;
+
+	error = parse_and_check_status(dev);
+	if (error)
+		return error;
+	keylen = response_get_string(&dev->parsed, 4, &activekey);
+	if (!activekey) {
+		pr_err("%s: Couldn't extract the Activekey from the response\n",
+		       __func__);
+		return OPAL_INVAL_PARAM;
+	}
+	dev->prev_data = kmemdup(activekey, keylen, GFP_KERNEL);
+
+	if (!dev->prev_data)
+		return -ENOMEM;
+
+	dev->prev_d_len = keylen;
+
+	return 0;
+}
+
+static int get_active_key(struct opal_dev *dev)
+{
+	u8 uid[OPAL_UID_LENGTH];
+	int err = 0;
+	u8 *lr;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+	lr = dev->func_data[dev->state];
+
+	err = build_locking_range(uid, sizeof(uid), *lr);
+	if (err)
+		return err;
+
+	err = 0;
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3); /* startCloumn */
+	add_token_u8(&err, dev, 10); /* ActiveKey */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 4); /* endColumn */
+	add_token_u8(&err, dev, 10); /* ActiveKey */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	if (err) {
+		pr_err("Error building get active key command\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, get_active_key_cont);
+}
+
+static int generic_lr_enable_disable(struct opal_dev *dev,
+				     u8 *uid, bool rle, bool wle,
+				     bool rl, bool wl)
+{
+	int err = 0;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 5); /* ReadLockEnabled */
+	add_token_u8(&err, dev, rle);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 6); /* WriteLockEnabled */
+	add_token_u8(&err, dev, wle);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_READLOCKED);
+	add_token_u8(&err, dev, rl);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_WRITELOCKED);
+	add_token_u8(&err, dev, wl);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	return err;
+}
+
+static inline int enable_global_lr(struct opal_dev *dev, u8 *uid,
+				   struct opal_user_lr_setup *setup)
+{
+	int err;
+
+	err = generic_lr_enable_disable(dev, uid, !!setup->RLE, !!setup->WLE,
+					0, 0);
+	if (err)
+		pr_err("Failed to create enable global lr command\n");
+	return err;
+}
+
+static int setup_locking_range(struct opal_dev *dev)
+{
+	u8 uid[OPAL_UID_LENGTH];
+	struct opal_user_lr_setup *setup;
+	u8 lr;
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	setup = dev->func_data[dev->state];
+	lr = setup->session.opal_key.lr;
+	err = build_locking_range(uid, sizeof(uid), lr);
+	if (err)
+		return err;
+
+	if (lr == 0)
+		err = enable_global_lr(dev, uid, setup);
+	else {
+		add_token_u8(&err, dev, OPAL_CALL);
+		add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+		add_token_bytestring(&err, dev, opalmethod[OPAL_SET],
+				     OPAL_UID_LENGTH);
+
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_VALUES);
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 3); /* Ranges Start */
+		add_token_u64(&err, dev, setup->range_start);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 4); /* Ranges length */
+		add_token_u64(&err, dev, setup->range_length);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 5); /*ReadLockEnabled */
+		add_token_u64(&err, dev, !!setup->RLE);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 6); /*WriteLockEnabled*/
+		add_token_u64(&err, dev, !!setup->WLE);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	}
+	if (err) {
+		pr_err("Error building Setup Locking range command.\n");
+		return err;
+
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int start_generic_opal_session(struct opal_dev *dev,
+				      enum opal_uid auth,
+				      enum opal_uid sp_type,
+				      const char *key,
+				      u8 key_len)
+{
+	u32 hsn;
+	int err = 0;
+
+	if (key == NULL && auth != OPAL_ANYBODY_UID) {
+		pr_err("%s: Attempted to open ADMIN_SP Session without a Host" \
+		       "Challenge, and not as the Anybody UID\n", __func__);
+		return OPAL_INVAL_PARAM;
+	}
+
+	clear_opal_cmd(dev);
+
+	set_comid(dev, dev->comid);
+	hsn = GENERIC_HOST_SESSION_NUM;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_SMUID_UID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_STARTSESSION],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u64(&err, dev, hsn);
+	add_token_bytestring(&err, dev, opaluid[sp_type], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, 1);
+
+	switch (auth) {
+	case OPAL_ANYBODY_UID:
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+		break;
+	case OPAL_ADMIN1_UID:
+	case OPAL_SID_UID:
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 0); /* HostChallenge */
+		add_token_bytestring(&err, dev, key, key_len);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, 3); /* HostSignAuth */
+		add_token_bytestring(&err, dev, opaluid[auth],
+				     OPAL_UID_LENGTH);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+		break;
+	default:
+		pr_err("Cannot start Admin SP session with auth %d\n", auth);
+		return OPAL_INVAL_PARAM;
+	}
+
+	if (err) {
+		pr_err("Error building start adminsp session command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, start_opal_session_cont);
+}
+
+static int start_anybodyASP_opal_session(struct opal_dev *dev)
+{
+	return start_generic_opal_session(dev, OPAL_ANYBODY_UID,
+					  OPAL_ADMINSP_UID, NULL, 0);
+}
+
+static int start_SIDASP_opal_session(struct opal_dev *dev)
+{
+	int ret;
+	const u8 *key = dev->prev_data;
+	struct opal_key *okey;
+
+	if (!key) {
+		okey = dev->func_data[dev->state];
+		ret = start_generic_opal_session(dev, OPAL_SID_UID,
+						 OPAL_ADMINSP_UID,
+						 okey->key,
+						 okey->key_len);
+	} else {
+		ret = start_generic_opal_session(dev, OPAL_SID_UID,
+						 OPAL_ADMINSP_UID,
+						 key, dev->prev_d_len);
+		kfree(key);
+		dev->prev_data = NULL;
+	}
+	return ret;
+}
+
+static inline int start_admin1LSP_opal_session(struct opal_dev *dev)
+{
+	struct opal_key *key = dev->func_data[dev->state];
+
+	return start_generic_opal_session(dev, OPAL_ADMIN1_UID,
+					  OPAL_LOCKINGSP_UID,
+					  key->key, key->key_len);
+}
+
+static int start_auth_opal_session(struct opal_dev *dev)
+{
+	u8 lk_ul_user[OPAL_UID_LENGTH];
+	int err = 0;
+
+	struct opal_session_info *session = dev->func_data[dev->state];
+	size_t keylen = session->opal_key.key_len;
+	u8 *key = session->opal_key.key;
+	u32 hsn = GENERIC_HOST_SESSION_NUM;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	if (session->sum) {
+		err = build_locking_user(lk_ul_user, sizeof(lk_ul_user),
+					 session->opal_key.lr);
+		if (err)
+			return err;
+
+	} else if (session->who != OPAL_ADMIN1 && !session->sum) {
+		err = build_locking_user(lk_ul_user, sizeof(lk_ul_user),
+					 session->who - 1);
+		if (err)
+			return err;
+	} else
+		memcpy(lk_ul_user, opaluid[OPAL_ADMIN1_UID], OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_SMUID_UID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_STARTSESSION],
+			     OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u64(&err, dev, hsn);
+	add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, 1);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 0);
+	add_token_bytestring(&err, dev, key, keylen);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3);
+	add_token_bytestring(&err, dev, lk_ul_user, OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building STARTSESSION command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, start_opal_session_cont);
+}
+
+static int revert_tper(struct opal_dev *dev)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_ADMINSP_UID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_REVERT],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	if (err) {
+		pr_err("Error building REVERT TPER command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int internal_activate_user(struct opal_dev *dev)
+{
+	struct opal_session_info *session = dev->func_data[dev->state];
+	u8 uid[OPAL_UID_LENGTH];
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	memcpy(uid, opaluid[OPAL_USER1_UID], OPAL_UID_LENGTH);
+	uid[7] = session->who;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 5); /* Enabled */
+	add_token_u8(&err, dev, OPAL_TRUE);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building Activate UserN command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int erase_locking_range(struct opal_dev *dev)
+{
+	struct opal_session_info *session;
+	u8 uid[OPAL_UID_LENGTH];
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+	session = dev->func_data[dev->state];
+
+	if (build_locking_range(uid, sizeof(uid), session->opal_key.lr) < 0)
+		return -ERANGE;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_ERASE],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building Erase Locking Range Command.\n");
+		return err;
+	}
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int set_mbr_done(struct opal_dev *dev)
+{
+	u8 mbr_done_tf = *(u8 *)dev->func_data[dev->state];
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_MBRCONTROL],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 2); /* Done */
+	add_token_u8(&err, dev, mbr_done_tf); /* Done T or F */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error Building set MBR Done command\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int set_mbr_enable_disable(struct opal_dev *dev)
+{
+	u8 mbr_en_dis = *(u8 *)dev->func_data[dev->state];
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_MBRCONTROL],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 1);
+	add_token_u8(&err, dev, mbr_en_dis);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error Building set MBR done command\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int generic_pw_cmd(u8 *key, size_t key_len, u8 *cpin_uid,
+			  struct opal_dev *dev)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, cpin_uid, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET],
+			     OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3); /* PIN */
+	add_token_bytestring(&err, dev, key, key_len);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	return err;
+}
+
+static int set_new_pw(struct opal_dev *dev)
+{
+	u8 cpin_uid[OPAL_UID_LENGTH];
+	struct opal_session_info *usr = dev->func_data[dev->state];
+
+
+	memcpy(cpin_uid, opaluid[OPAL_C_PIN_ADMIN1], OPAL_UID_LENGTH);
+
+	if (usr->who != OPAL_ADMIN1) {
+		cpin_uid[5] = 0x03;
+		if (usr->sum)
+			cpin_uid[7] = usr->opal_key.lr + 1;
+		else
+			cpin_uid[7] = usr->who;
+	}
+
+	if (generic_pw_cmd(usr->opal_key.key, usr->opal_key.key_len,
+			   cpin_uid, dev)) {
+		pr_err("Error building set password command.\n");
+		return -ERANGE;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int set_sid_cpin_pin(struct opal_dev *dev)
+{
+	u8 cpin_uid[OPAL_UID_LENGTH];
+	struct opal_key *key = dev->func_data[dev->state];
+
+	memcpy(cpin_uid, opaluid[OPAL_C_PIN_SID], OPAL_UID_LENGTH);
+
+	if (generic_pw_cmd(key->key, key->key_len, cpin_uid, dev)) {
+		pr_err("Error building Set SID cpin\n");
+		return -ERANGE;
+	}
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int add_user_to_lr(struct opal_dev *dev)
+{
+	u8 lr_buffer[OPAL_UID_LENGTH];
+	u8 user_uid[OPAL_UID_LENGTH];
+	struct opal_lock_unlock *lkul;
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	lkul = dev->func_data[dev->state];
+
+	memcpy(lr_buffer, opaluid[OPAL_LOCKINGRANGE_ACE_RDLOCKED],
+	       OPAL_UID_LENGTH);
+
+	if (lkul->l_state == OPAL_RW)
+		memcpy(lr_buffer, opaluid[OPAL_LOCKINGRANGE_ACE_WRLOCKED],
+		       OPAL_UID_LENGTH);
+
+	lr_buffer[7] = lkul->session.opal_key.lr;
+
+	memcpy(user_uid, opaluid[OPAL_USER1_UID], OPAL_UID_LENGTH);
+
+	user_uid[7] = lkul->session.who;
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, lr_buffer, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET],
+			     OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_bytestring(&err, dev,
+			     opaluid[OPAL_HALF_UID_AUTHORITY_OBJ_REF],
+			     OPAL_UID_LENGTH/2);
+	add_token_bytestring(&err, dev, user_uid, OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_bytestring(&err, dev,
+			     opaluid[OPAL_HALF_UID_AUTHORITY_OBJ_REF],
+			     OPAL_UID_LENGTH/2);
+	add_token_bytestring(&err, dev, user_uid, OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_bytestring(&err, dev, opaluid[OPAL_HALF_UID_BOOLEAN_ACE],
+			     OPAL_UID_LENGTH/2);
+	add_token_u8(&err, dev, 1);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building add user to locking range command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int lock_unlock_locking_range(struct opal_dev *dev)
+{
+	u8 lr_buffer[OPAL_UID_LENGTH];
+	const u8 *method;
+	struct opal_lock_unlock *lkul;
+	u8 read_locked = 1, write_locked = 1;
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	method = opalmethod[OPAL_SET];
+	lkul = dev->func_data[dev->state];
+	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
+				lkul->session.opal_key.lr) < 0)
+		return -ERANGE;
+
+	switch (lkul->l_state) {
+	case OPAL_RO:
+		read_locked = 0;
+		write_locked = 1;
+		break;
+	case OPAL_RW:
+		read_locked = 0;
+		write_locked = 0;
+		break;
+	case OPAL_LK:
+		/* vars are initalized to locked */
+		break;
+	default:
+		pr_err("Tried to set an invalid locking state... returning to uland\n");
+		return OPAL_INVAL_PARAM;
+	}
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, lr_buffer, OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_SET], OPAL_UID_LENGTH);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_VALUES);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_READLOCKED);
+	add_token_u8(&err, dev, read_locked);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, OPAL_WRITELOCKED);
+	add_token_u8(&err, dev, write_locked);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building SET command.\n");
+		return err;
+	}
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+
+static int lock_unlock_locking_range_sum(struct opal_dev *dev)
+{
+	u8 lr_buffer[OPAL_UID_LENGTH];
+	u8 read_locked = 1, write_locked = 1;
+	const u8 *method;
+	struct opal_lock_unlock *lkul;
+	int ret;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	method = opalmethod[OPAL_SET];
+	lkul = dev->func_data[dev->state];
+	if (build_locking_range(lr_buffer, sizeof(lr_buffer),
+				lkul->session.opal_key.lr) < 0)
+		return -ERANGE;
+
+	switch (lkul->l_state) {
+	case OPAL_RO:
+		read_locked = 0;
+		write_locked = 1;
+		break;
+	case OPAL_RW:
+		read_locked = 0;
+		write_locked = 0;
+		break;
+	case OPAL_LK:
+		/* vars are initalized to locked */
+		break;
+	default:
+		pr_err("Tried to set an invalid locking state.\n");
+		return OPAL_INVAL_PARAM;
+	}
+	ret = generic_lr_enable_disable(dev, lr_buffer, 1, 1,
+					read_locked, write_locked);
+
+	if (ret < 0) {
+		pr_err("Error building SET command.\n");
+		return ret;
+	}
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int activate_lsp(struct opal_dev *dev)
+{
+	struct opal_lr_act *opal_act;
+	u8 user_lr[OPAL_UID_LENGTH];
+	u8 uint_3 = 0x83;
+	int err = 0, i;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	opal_act = dev->func_data[dev->state];
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_ACTIVATE],
+			     OPAL_UID_LENGTH);
+
+
+	if (opal_act->sum) {
+		err = build_locking_range(user_lr, sizeof(user_lr),
+					  opal_act->lr[0]);
+		if (err)
+			return err;
+
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, uint_3);
+		add_token_u8(&err, dev, 6);
+		add_token_u8(&err, dev, 0);
+		add_token_u8(&err, dev, 0);
+
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_bytestring(&err, dev, user_lr, OPAL_UID_LENGTH);
+		for (i = 1; i < opal_act->num_lrs; i++) {
+			user_lr[7] = opal_act->lr[i];
+			add_token_bytestring(&err, dev, user_lr, OPAL_UID_LENGTH);
+		}
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	} else {
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+	}
+
+	if (err) {
+		pr_err("Error building Activate LockingSP command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, parse_and_check_status);
+}
+
+static int get_lsp_lifecycle_cont(struct opal_dev *dev)
+{
+	u8 lc_status;
+	int error = 0;
+
+	error = parse_and_check_status(dev);
+	if (error)
+		return error;
+
+	lc_status = response_get_u64(&dev->parsed, 4);
+	/* 0x08 is Manufacured Inactive */
+	/* 0x09 is Manufactured */
+	if (lc_status != OPAL_MANUFACTURED_INACTIVE) {
+		pr_err("Couldn't determine the status of the Lifcycle state\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+/* Determine if we're in the Manufactured Inactive or Active state */
+static int get_lsp_lifecycle(struct opal_dev *dev)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_LOCKINGSP_UID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3); /* Start Column */
+	add_token_u8(&err, dev, 6); /* Lifecycle Column */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 4); /* End Column */
+	add_token_u8(&err, dev, 6); /* Lifecycle Column */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error Building GET Lifecycle Status command\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, get_lsp_lifecycle_cont);
+}
+
+static int get_msid_cpin_pin_cont(struct opal_dev *dev)
+{
+	const char *msid_pin;
+	size_t strlen;
+	int error = 0;
+
+	error = parse_and_check_status(dev);
+	if (error)
+		return error;
+
+	strlen = response_get_string(&dev->parsed, 4, &msid_pin);
+	if (!msid_pin) {
+		pr_err("%s: Couldn't extract PIN from response\n", __func__);
+		return OPAL_INVAL_PARAM;
+	}
+
+	dev->prev_data = kmemdup(msid_pin, strlen, GFP_KERNEL);
+	if (!dev->prev_data)
+		return -ENOMEM;
+
+	dev->prev_d_len = strlen;
+
+	return 0;
+}
+
+static int get_msid_cpin_pin(struct opal_dev *dev)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+	set_comid(dev, dev->comid);
+
+
+	add_token_u8(&err, dev, OPAL_CALL);
+	add_token_bytestring(&err, dev, opaluid[OPAL_C_PIN_MSID],
+			     OPAL_UID_LENGTH);
+	add_token_bytestring(&err, dev, opalmethod[OPAL_GET], OPAL_UID_LENGTH);
+
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+	add_token_u8(&err, dev, OPAL_STARTLIST);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 3); /* Start Column */
+	add_token_u8(&err, dev, 3); /* PIN */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_STARTNAME);
+	add_token_u8(&err, dev, 4); /* End Column */
+	add_token_u8(&err, dev, 3); /* Lifecycle Column */
+	add_token_u8(&err, dev, OPAL_ENDNAME);
+
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+	add_token_u8(&err, dev, OPAL_ENDLIST);
+
+	if (err) {
+		pr_err("Error building Get MSID CPIN PIN command.\n");
+		return err;
+	}
+
+	return finalize_and_send(dev, get_msid_cpin_pin_cont);
+}
+
+static int build_end_opal_session(struct opal_dev *dev)
+{
+	int err = 0;
+
+	clear_opal_cmd(dev);
+
+	set_comid(dev, dev->comid);
+	add_token_u8(&err, dev, OPAL_ENDOFSESSION);
+	return err;
+}
+
+static int end_opal_session(struct opal_dev *dev)
+{
+	int ret = build_end_opal_session(dev);
+
+	if (ret < 0)
+		return ret;
+	return finalize_and_send(dev, end_session_cont);
+}
+
+static int end_opal_session_error(struct opal_dev *dev)
+{
+	const opal_step error_end_session[] = {
+		end_opal_session,
+		NULL,
+	};
+	dev->funcs = error_end_session;
+	dev->state = 0;
+	return next(dev);
+}
+
+static inline void setup_opal_dev(struct opal_dev *dev,
+				  const opal_step *funcs)
+{
+	dev->state = 0;
+	dev->funcs = funcs;
+	dev->tsn = 0;
+	dev->hsn = 0;
+	dev->func_data = NULL;
+	dev->prev_data = NULL;
+}
+
+static int check_opal_support(struct opal_dev *dev)
+{
+	static const opal_step funcs[] = {
+		opal_discovery0,
+		NULL
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, funcs);
+	ret = next(dev);
+	dev->supported = !ret;
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+struct opal_dev *init_opal_dev(void *data, sec_send_recv *send_recv)
+{
+	struct opal_dev *dev;
+
+	dev = kmalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	INIT_LIST_HEAD(&dev->unlk_lst);
+	mutex_init(&dev->dev_lock);
+	dev->data = data;
+	dev->send_recv = send_recv;
+	if (check_opal_support(dev) != 0) {
+		pr_debug("Opal is not supported on this device\n");
+		kfree(dev);
+		return NULL;
+	}
+	return dev;
+}
+EXPORT_SYMBOL(init_opal_dev);
+
+static int opal_secure_erase_locking_range(struct opal_dev *dev,
+					   struct opal_session_info *opal_session)
+{
+	void *data[3] = { NULL };
+	static const opal_step erase_funcs[] = {
+		opal_discovery0,
+		start_auth_opal_session,
+		get_active_key,
+		gen_key,
+		end_opal_session,
+		NULL,
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, erase_funcs);
+
+	dev->func_data = data;
+	dev->func_data[1] = opal_session;
+	dev->func_data[2] = &opal_session->opal_key.lr;
+
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_erase_locking_range(struct opal_dev *dev,
+				    struct opal_session_info *opal_session)
+{
+	void *data[3] = { NULL };
+	static const opal_step erase_funcs[] = {
+		opal_discovery0,
+		start_auth_opal_session,
+		erase_locking_range,
+		end_opal_session,
+		NULL,
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, erase_funcs);
+
+	dev->func_data = data;
+	dev->func_data[1] = opal_session;
+	dev->func_data[2] = opal_session;
+
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_enable_disable_shadow_mbr(struct opal_dev *dev,
+					  struct opal_mbr_data *opal_mbr)
+{
+	void *func_data[6] = { NULL };
+	static const opal_step mbr_funcs[] = {
+		opal_discovery0,
+		start_admin1LSP_opal_session,
+		set_mbr_done,
+		end_opal_session,
+		start_admin1LSP_opal_session,
+		set_mbr_enable_disable,
+		end_opal_session,
+		NULL,
+	};
+	int ret;
+
+	if (opal_mbr->enable_disable != OPAL_MBR_ENABLE &&
+	    opal_mbr->enable_disable != OPAL_MBR_DISABLE)
+		return -EINVAL;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, mbr_funcs);
+	dev->func_data = func_data;
+	dev->func_data[1] = &opal_mbr->key;
+	dev->func_data[2] = &opal_mbr->enable_disable;
+	dev->func_data[4] = &opal_mbr->key;
+	dev->func_data[5] = &opal_mbr->enable_disable;
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_save(struct opal_dev *dev, struct opal_lock_unlock *lk_unlk)
+{
+	struct opal_suspend_data *suspend;
+
+	suspend = kzalloc(sizeof(*suspend), GFP_KERNEL);
+	if (!suspend)
+		return -ENOMEM;
+
+	suspend->unlk = *lk_unlk;
+	suspend->lr = lk_unlk->session.opal_key.lr;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, NULL);
+	add_suspend_info(dev, suspend);
+	mutex_unlock(&dev->dev_lock);
+	return 0;
+}
+
+static int opal_add_user_to_lr(struct opal_dev *dev,
+			       struct opal_lock_unlock *lk_unlk)
+{
+	void *func_data[3] = { NULL };
+	static const opal_step funcs[] = {
+		opal_discovery0,
+		start_admin1LSP_opal_session,
+		add_user_to_lr,
+		end_opal_session,
+		NULL
+	};
+	int ret;
+
+	if (lk_unlk->l_state != OPAL_RO &&
+	    lk_unlk->l_state != OPAL_RW) {
+		pr_err("Locking state was not RO or RW\n");
+		return -EINVAL;
+	}
+	if (lk_unlk->session.who < OPAL_USER1 &&
+	    lk_unlk->session.who > OPAL_USER9) {
+		pr_err("Authority was not within the range of users: %d\n",
+		       lk_unlk->session.who);
+		return -EINVAL;
+	}
+	if (lk_unlk->session.sum) {
+		pr_err("%s not supported in sum. Use setup locking range\n",
+		       __func__);
+		return -EINVAL;
+	}
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, funcs);
+	dev->func_data = func_data;
+	dev->func_data[1] = &lk_unlk->session.opal_key;
+	dev->func_data[2] = lk_unlk;
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_reverttper(struct opal_dev *dev, struct opal_key *opal)
+{
+	void *data[2] = { NULL };
+	static const opal_step revert_funcs[] = {
+		opal_discovery0,
+		start_SIDASP_opal_session,
+		revert_tper, /* controller will terminate session */
+		NULL,
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, revert_funcs);
+	dev->func_data = data;
+	dev->func_data[1] = opal;
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int __opal_lock_unlock_sum(struct opal_dev *dev)
+{
+	static const opal_step ulk_funcs_sum[] = {
+		opal_discovery0,
+		start_auth_opal_session,
+		lock_unlock_locking_range_sum,
+		end_opal_session,
+		NULL
+	};
+
+	dev->funcs = ulk_funcs_sum;
+	return next(dev);
+}
+
+static int __opal_lock_unlock(struct opal_dev *dev)
+{
+	static const opal_step _unlock_funcs[] = {
+		opal_discovery0,
+		start_auth_opal_session,
+		lock_unlock_locking_range,
+		end_opal_session,
+		NULL
+	};
+
+	dev->funcs = _unlock_funcs;
+	return next(dev);
+}
+
+static int opal_lock_unlock(struct opal_dev *dev, struct opal_lock_unlock *lk_unlk)
+{
+	void *func_data[3] = { NULL };
+	int ret;
+
+	if (lk_unlk->session.who < OPAL_ADMIN1 ||
+	    lk_unlk->session.who > OPAL_USER9)
+		return -EINVAL;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, NULL);
+	dev->func_data = func_data;
+	dev->func_data[1] = &lk_unlk->session;
+	dev->func_data[2] = lk_unlk;
+
+	if (lk_unlk->session.sum)
+		ret = __opal_lock_unlock_sum(dev);
+	else
+		ret = __opal_lock_unlock(dev);
+
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_take_ownership(struct opal_dev *dev, struct opal_key *opal)
+{
+	static const opal_step owner_funcs[] = {
+		opal_discovery0,
+		start_anybodyASP_opal_session,
+		get_msid_cpin_pin,
+		end_opal_session,
+		start_SIDASP_opal_session,
+		set_sid_cpin_pin,
+		end_opal_session,
+		NULL
+	};
+	void *data[6] = { NULL };
+	int ret;
+
+	if (!dev)
+		return -ENODEV;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, owner_funcs);
+	dev->func_data = data;
+	dev->func_data[4] = opal;
+	dev->func_data[5] = opal;
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_activate_lsp(struct opal_dev *dev, struct opal_lr_act *opal_lr_act)
+{
+	void *data[4] = { NULL };
+	static const opal_step active_funcs[] = {
+		opal_discovery0,
+		start_SIDASP_opal_session, /* Open session as SID auth */
+		get_lsp_lifecycle,
+		activate_lsp,
+		end_opal_session,
+		NULL
+	};
+	int ret;
+
+	if (!opal_lr_act->num_lrs || opal_lr_act->num_lrs > OPAL_MAX_LRS)
+		return -EINVAL;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, active_funcs);
+	dev->func_data = data;
+	dev->func_data[1] = &opal_lr_act->key;
+	dev->func_data[3] = opal_lr_act;
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_setup_locking_range(struct opal_dev *dev,
+				    struct opal_user_lr_setup *opal_lrs)
+{
+	void *data[3] = { NULL };
+	static const opal_step lr_funcs[] = {
+		opal_discovery0,
+		start_auth_opal_session,
+		setup_locking_range,
+		end_opal_session,
+		NULL,
+	};
+	int ret;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, lr_funcs);
+	dev->func_data = data;
+	dev->func_data[1] = &opal_lrs->session;
+	dev->func_data[2] = opal_lrs;
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_set_new_pw(struct opal_dev *dev, struct opal_new_pw *opal_pw)
+{
+	static const opal_step pw_funcs[] = {
+		opal_discovery0,
+		start_auth_opal_session,
+		set_new_pw,
+		end_opal_session,
+		NULL
+	};
+	void *data[3] = { NULL };
+	int ret;
+
+	if (opal_pw->session.who < OPAL_ADMIN1 ||
+	    opal_pw->session.who > OPAL_USER9  ||
+	    opal_pw->new_user_pw.who < OPAL_ADMIN1 ||
+	    opal_pw->new_user_pw.who > OPAL_USER9)
+		return -EINVAL;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, pw_funcs);
+	dev->func_data = data;
+	dev->func_data[1] = (void *) &opal_pw->session;
+	dev->func_data[2] = (void *) &opal_pw->new_user_pw;
+
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+static int opal_activate_user(struct opal_dev *dev,
+			      struct opal_session_info *opal_session)
+{
+	static const opal_step act_funcs[] = {
+		opal_discovery0,
+		start_admin1LSP_opal_session,
+		internal_activate_user,
+		end_opal_session,
+		NULL
+	};
+	void *data[3] = { NULL };
+	int ret;
+
+	/* We can't activate Admin1 it's active as manufactured */
+	if (opal_session->who < OPAL_USER1 &&
+	    opal_session->who > OPAL_USER9) {
+		pr_err("Who was not a valid user: %d\n", opal_session->who);
+		return -EINVAL;
+	}
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, act_funcs);
+	dev->func_data = data;
+	dev->func_data[1] = &opal_session->opal_key;
+	dev->func_data[2] = opal_session;
+	ret = next(dev);
+	mutex_unlock(&dev->dev_lock);
+	return ret;
+}
+
+bool opal_unlock_from_suspend(struct opal_dev *dev)
+{
+	struct opal_suspend_data *suspend;
+	void *func_data[3] = { NULL };
+	bool was_failure = false;
+	int ret = 0;
+
+	if (!dev)
+		return false;
+	if (!dev->supported)
+		return false;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev, NULL);
+	dev->func_data = func_data;
+
+	list_for_each_entry(suspend, &dev->unlk_lst, node) {
+		dev->state = 0;
+		dev->func_data[1] = &suspend->unlk.session;
+		dev->func_data[2] = &suspend->unlk;
+		dev->tsn = 0;
+		dev->hsn = 0;
+
+		if (suspend->unlk.session.sum)
+			ret = __opal_lock_unlock_sum(dev);
+		else
+			ret = __opal_lock_unlock(dev);
+		if (ret) {
+			pr_warn("Failed to unlock LR %hhu with sum %d\n",
+				suspend->unlk.session.opal_key.lr,
+				suspend->unlk.session.sum);
+			was_failure = true;
+		}
+	}
+	mutex_unlock(&dev->dev_lock);
+	return was_failure;
+}
+EXPORT_SYMBOL(opal_unlock_from_suspend);
+
+int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
+{
+	void *p;
+	int ret = -ENOTTY;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (!dev)
+		return -ENOTSUPP;
+	if (!dev->supported) {
+		pr_err("Not supported\n");
+		return -ENOTSUPP;
+	}
+
+	p = memdup_user(arg,  _IOC_SIZE(cmd));
+	if (IS_ERR(p))
+		return PTR_ERR(p);
+
+	switch (cmd) {
+	case IOC_OPAL_SAVE:
+		ret = opal_save(dev, p);
+		break;
+	case IOC_OPAL_LOCK_UNLOCK:
+		ret = opal_lock_unlock(dev, p);
+		break;
+	case IOC_OPAL_TAKE_OWNERSHIP:
+		ret = opal_take_ownership(dev, p);
+		break;
+	case IOC_OPAL_ACTIVATE_LSP:
+		ret = opal_activate_lsp(dev, p);
+		break;
+	case IOC_OPAL_SET_PW:
+		ret = opal_set_new_pw(dev, p);
+		break;
+	case IOC_OPAL_ACTIVATE_USR:
+		ret = opal_activate_user(dev, p);
+		break;
+	case IOC_OPAL_REVERT_TPR:
+		ret = opal_reverttper(dev, p);
+		break;
+	case IOC_OPAL_LR_SETUP:
+		ret = opal_setup_locking_range(dev, p);
+		break;
+	case IOC_OPAL_ADD_USR_TO_LR:
+		ret = opal_add_user_to_lr(dev, p);
+		break;
+	case IOC_OPAL_ENABLE_DISABLE_MBR:
+		ret = opal_enable_disable_shadow_mbr(dev, p);
+		break;
+	case IOC_OPAL_ERASE_LR:
+		ret = opal_erase_locking_range(dev, p);
+		break;
+	case IOC_OPAL_SECURE_ERASE_LR:
+		ret = opal_secure_erase_locking_range(dev, p);
+		break;
+	default:
+		pr_warn("No such Opal Ioctl %u\n", cmd);
+	}
+
+	kfree(p);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sed_ioctl);
diff --git a/crypto/algapi.c b/crypto/algapi.c
index df939b54b09f..1fad2a6b3bbb 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -356,6 +356,7 @@ int crypto_register_alg(struct crypto_alg *alg)
 	struct crypto_larval *larval;
 	int err;
 
+	alg->cra_flags &= ~CRYPTO_ALG_DEAD;
 	err = crypto_check_alg(alg);
 	if (err)
 		return err;
diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c
index f849311e9fd4..533265f110e0 100644
--- a/crypto/algif_aead.c
+++ b/crypto/algif_aead.c
@@ -661,9 +661,9 @@ static int aead_recvmsg_sync(struct socket *sock, struct msghdr *msg, int flags)
 unlock:
 	list_for_each_entry_safe(rsgl, tmp, &ctx->list, list) {
 		af_alg_free_sg(&rsgl->sgl);
+		list_del(&rsgl->list);
 		if (rsgl != &ctx->first_rsgl)
 			sock_kfree_s(sk, rsgl, sizeof(*rsgl));
-		list_del(&rsgl->list);
 	}
 	INIT_LIST_HEAD(&ctx->list);
 	aead_wmem_wakeup(sk);
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 9ed087853dee..a391bbc48105 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -55,7 +55,7 @@ acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
 acpi-$(CONFIG_ACPI_NUMA)	+= numa.o
 acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
 acpi-y				+= acpi_lpat.o
-acpi-$(CONFIG_ACPI_GENERIC_GSI) += gsi.o
+acpi-$(CONFIG_ACPI_GENERIC_GSI) += irq.o
 acpi-$(CONFIG_ACPI_WATCHDOG)	+= acpi_watchdog.o
 
 # These are (potentially) separate modules
diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index b3842ffc19ba..a15270a806fc 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -212,6 +212,7 @@ static bool __init extlog_get_l1addr(void)
 }
 static struct notifier_block extlog_mce_dec = {
 	.notifier_call	= extlog_print,
+	.priority	= MCE_PRIO_EXTLOG,
 };
 
 static int __init extlog_init(void)
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index 3de3b6b8f0f1..4467a8089ab8 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -165,7 +165,7 @@ static int acpi_processor_errata(void)
 
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 int __weak acpi_map_cpu(acpi_handle handle,
-		phys_cpuid_t physid, int *pcpu)
+		phys_cpuid_t physid, u32 acpi_id, int *pcpu)
 {
 	return -ENODEV;
 }
@@ -203,7 +203,7 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	cpu_maps_update_begin();
 	cpu_hotplug_begin();
 
-	ret = acpi_map_cpu(pr->handle, pr->phys_id, &pr->id);
+	ret = acpi_map_cpu(pr->handle, pr->phys_id, pr->acpi_id, &pr->id);
 	if (ret)
 		goto out;
 
diff --git a/drivers/acpi/acpica/acapps.h b/drivers/acpi/acpica/acapps.h
index 0bd6307e1f3c..b65f2731e9e2 100644
--- a/drivers/acpi/acpica/acapps.h
+++ b/drivers/acpi/acpica/acapps.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -51,26 +51,26 @@
 /* Common info for tool signons */
 
 #define ACPICA_NAME                 "Intel ACPI Component Architecture"
-#define ACPICA_COPYRIGHT            "Copyright (c) 2000 - 2016 Intel Corporation"
+#define ACPICA_COPYRIGHT            "Copyright (c) 2000 - 2017 Intel Corporation"
 
 #if ACPI_MACHINE_WIDTH == 64
-#define ACPI_WIDTH          "-64"
+#define ACPI_WIDTH          " (64-bit version)"
 
 #elif ACPI_MACHINE_WIDTH == 32
-#define ACPI_WIDTH          "-32"
+#define ACPI_WIDTH          " (32-bit version)"
 
 #else
 #error unknown ACPI_MACHINE_WIDTH
-#define ACPI_WIDTH          "-??"
+#define ACPI_WIDTH          " (unknown bit width, not 32 or 64)"
 
 #endif
 
 /* Macros for signons and file headers */
 
 #define ACPI_COMMON_SIGNON(utility_name) \
-	"\n%s\n%s version %8.8X%s\n%s\n\n", \
+	"\n%s\n%s version %8.8X\n%s\n\n", \
 	ACPICA_NAME, \
-	utility_name, ((u32) ACPI_CA_VERSION), ACPI_WIDTH, \
+	utility_name, ((u32) ACPI_CA_VERSION), \
 	ACPICA_COPYRIGHT
 
 #define ACPI_COMMON_HEADER(utility_name, prefix) \
diff --git a/drivers/acpi/acpica/accommon.h b/drivers/acpi/acpica/accommon.h
index 19d6ec815d12..49bf47ca5477 100644
--- a/drivers/acpi/acpica/accommon.h
+++ b/drivers/acpi/acpica/accommon.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acdebug.h b/drivers/acpi/acpica/acdebug.h
index 94737f8845ac..71743e5252f5 100644
--- a/drivers/acpi/acpica/acdebug.h
+++ b/drivers/acpi/acpica/acdebug.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acdispat.h b/drivers/acpi/acpica/acdispat.h
index dcd48bfedb4d..0d95c85cce06 100644
--- a/drivers/acpi/acpica/acdispat.h
+++ b/drivers/acpi/acpica/acdispat.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index 8a0049d5cdf3..a2adfd42f85c 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index edbb42e251a6..1d955fe216c4 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/achware.h b/drivers/acpi/acpica/achware.h
index 27addcf50c37..fd4f3cacb356 100644
--- a/drivers/acpi/acpica/achware.h
+++ b/drivers/acpi/acpica/achware.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acinterp.h b/drivers/acpi/acpica/acinterp.h
index 7ead235555cf..29a863c85318 100644
--- a/drivers/acpi/acpica/acinterp.h
+++ b/drivers/acpi/acpica/acinterp.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 792660054992..8fd495e8fdce 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -770,7 +770,7 @@ union acpi_parse_value {
 	char                            *operator_symbol;/* Used for C-style operator name strings */\
 	char                            aml_op_name[16])	/* Op name (debug only) */
 
-/* Flags for disasm_flags field above */
+/* Internal opcodes for disasm_opcode field above */
 
 #define ACPI_DASM_BUFFER                0x00	/* Buffer is a simple data buffer */
 #define ACPI_DASM_RESOURCE              0x01	/* Buffer is a Resource Descriptor */
@@ -783,7 +783,10 @@ union acpi_parse_value {
 #define ACPI_DASM_LNOT_PREFIX           0x08	/* Start of a Lnot_equal (etc.) pair of opcodes */
 #define ACPI_DASM_LNOT_SUFFIX           0x09	/* End  of a Lnot_equal (etc.) pair of opcodes */
 #define ACPI_DASM_HID_STRING            0x0A	/* String is a _HID or _CID */
-#define ACPI_DASM_IGNORE                0x0B	/* Not used at this time */
+#define ACPI_DASM_IGNORE_SINGLE         0x0B	/* Ignore the opcode but not it's children */
+#define ACPI_DASM_SWITCH_PREDICATE      0x0C	/* Object is a predicate for a Switch or Case block */
+#define ACPI_DASM_CASE                  0x0D	/* If/Else is a Case in a Switch/Case block */
+#define ACPI_DASM_DEFAULT               0x0E	/* Else is a Default in a Switch/Case block */
 
 /*
  * Generic operation (for example:  If, While, Store)
diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h
index a3b95431b7c5..c3337514e0ed 100644
--- a/drivers/acpi/acpica/acmacros.h
+++ b/drivers/acpi/acpica/acmacros.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -46,7 +46,7 @@
 
 /*
  * Extract data using a pointer. Any more than a byte and we
- * get into potential aligment issues -- see the STORE macros below.
+ * get into potential alignment issues -- see the STORE macros below.
  * Use with care.
  */
 #define ACPI_CAST8(ptr)                 ACPI_CAST_PTR (u8, (ptr))
@@ -63,7 +63,7 @@
 #define ACPI_SET64(ptr, val)            (*ACPI_CAST64 (ptr) = (u64) (val))
 
 /*
- * printf() format helper. This macros is a workaround for the difficulties
+ * printf() format helper. This macro is a workaround for the difficulties
  * with emitting 64-bit integers and 64-bit pointers with the same code
  * for both 32-bit and 64-bit hosts.
  */
@@ -260,8 +260,70 @@
 
 #define ACPI_IS_MISALIGNED(value)           (((acpi_size) value) & (sizeof(acpi_size)-1))
 
+/* Generic bit manipulation */
+
+#ifndef ACPI_USE_NATIVE_BIT_FINDER
+
+#define __ACPI_FIND_LAST_BIT_2(a, r)        ((((u8)  (a)) & 0x02) ? (r)+1 : (r))
+#define __ACPI_FIND_LAST_BIT_4(a, r)        ((((u8)  (a)) & 0x0C) ? \
+											 __ACPI_FIND_LAST_BIT_2  ((a)>>2,  (r)+2) : \
+											 __ACPI_FIND_LAST_BIT_2  ((a), (r)))
+#define __ACPI_FIND_LAST_BIT_8(a, r)        ((((u8)  (a)) & 0xF0) ? \
+											 __ACPI_FIND_LAST_BIT_4  ((a)>>4,  (r)+4) : \
+											 __ACPI_FIND_LAST_BIT_4  ((a), (r)))
+#define __ACPI_FIND_LAST_BIT_16(a, r)       ((((u16) (a)) & 0xFF00) ? \
+											 __ACPI_FIND_LAST_BIT_8  ((a)>>8,  (r)+8) : \
+											 __ACPI_FIND_LAST_BIT_8  ((a), (r)))
+#define __ACPI_FIND_LAST_BIT_32(a, r)       ((((u32) (a)) & 0xFFFF0000) ? \
+											 __ACPI_FIND_LAST_BIT_16 ((a)>>16, (r)+16) : \
+											 __ACPI_FIND_LAST_BIT_16 ((a), (r)))
+#define __ACPI_FIND_LAST_BIT_64(a, r)       ((((u64) (a)) & 0xFFFFFFFF00000000) ? \
+											 __ACPI_FIND_LAST_BIT_32 ((a)>>32, (r)+32) : \
+											 __ACPI_FIND_LAST_BIT_32 ((a), (r)))
+
+#define ACPI_FIND_LAST_BIT_8(a)             ((a) ? __ACPI_FIND_LAST_BIT_8 (a, 1) : 0)
+#define ACPI_FIND_LAST_BIT_16(a)            ((a) ? __ACPI_FIND_LAST_BIT_16 (a, 1) : 0)
+#define ACPI_FIND_LAST_BIT_32(a)            ((a) ? __ACPI_FIND_LAST_BIT_32 (a, 1) : 0)
+#define ACPI_FIND_LAST_BIT_64(a)            ((a) ? __ACPI_FIND_LAST_BIT_64 (a, 1) : 0)
+
+#define __ACPI_FIND_FIRST_BIT_2(a, r)       ((((u8) (a)) & 0x01) ? (r) : (r)+1)
+#define __ACPI_FIND_FIRST_BIT_4(a, r)       ((((u8) (a)) & 0x03) ? \
+											 __ACPI_FIND_FIRST_BIT_2  ((a), (r)) : \
+											 __ACPI_FIND_FIRST_BIT_2  ((a)>>2, (r)+2))
+#define __ACPI_FIND_FIRST_BIT_8(a, r)       ((((u8) (a)) & 0x0F) ? \
+											 __ACPI_FIND_FIRST_BIT_4  ((a), (r)) : \
+											 __ACPI_FIND_FIRST_BIT_4  ((a)>>4, (r)+4))
+#define __ACPI_FIND_FIRST_BIT_16(a, r)      ((((u16) (a)) & 0x00FF) ? \
+											 __ACPI_FIND_FIRST_BIT_8  ((a), (r)) : \
+											 __ACPI_FIND_FIRST_BIT_8  ((a)>>8, (r)+8))
+#define __ACPI_FIND_FIRST_BIT_32(a, r)      ((((u32) (a)) & 0x0000FFFF) ? \
+											 __ACPI_FIND_FIRST_BIT_16 ((a), (r)) : \
+											 __ACPI_FIND_FIRST_BIT_16 ((a)>>16, (r)+16))
+#define __ACPI_FIND_FIRST_BIT_64(a, r)      ((((u64) (a)) & 0x00000000FFFFFFFF) ? \
+											 __ACPI_FIND_FIRST_BIT_32 ((a), (r)) : \
+											 __ACPI_FIND_FIRST_BIT_32 ((a)>>32, (r)+32))
+
+#define ACPI_FIND_FIRST_BIT_8(a)            ((a) ? __ACPI_FIND_FIRST_BIT_8 (a, 1) : 0)
+#define ACPI_FIND_FIRST_BIT_16(a)           ((a) ? __ACPI_FIND_FIRST_BIT_16 (a, 1) : 0)
+#define ACPI_FIND_FIRST_BIT_32(a)           ((a) ? __ACPI_FIND_FIRST_BIT_32 (a, 1) : 0)
+#define ACPI_FIND_FIRST_BIT_64(a)           ((a) ? __ACPI_FIND_FIRST_BIT_64 (a, 1) : 0)
+
+#endif				/* ACPI_USE_NATIVE_BIT_FINDER */
+
 /* Generic (power-of-two) rounding */
 
+#define ACPI_ROUND_UP_POWER_OF_TWO_8(a)     ((u8) \
+											(((u16) 1) <<  ACPI_FIND_LAST_BIT_8  ((a)  - 1)))
+#define ACPI_ROUND_DOWN_POWER_OF_TWO_8(a)   ((u8) \
+											(((u16) 1) << (ACPI_FIND_LAST_BIT_8  ((a)) - 1)))
+#define ACPI_ROUND_UP_POWER_OF_TWO_16(a)    ((u16) \
+											(((u32) 1) <<  ACPI_FIND_LAST_BIT_16 ((a)  - 1)))
+#define ACPI_ROUND_DOWN_POWER_OF_TWO_16(a)  ((u16) \
+											(((u32) 1) << (ACPI_FIND_LAST_BIT_16 ((a)) - 1)))
+#define ACPI_ROUND_UP_POWER_OF_TWO_32(a)    ((u32) \
+											(((u64) 1) <<  ACPI_FIND_LAST_BIT_32 ((a)  - 1)))
+#define ACPI_ROUND_DOWN_POWER_OF_TWO_32(a)  ((u32) \
+											(((u64) 1) << (ACPI_FIND_LAST_BIT_32 ((a)) - 1)))
 #define ACPI_IS_ALIGNED(a, s)               (((a) & ((s) - 1)) == 0)
 #define ACPI_IS_POWER_OF_TWO(a)             ACPI_IS_ALIGNED(a, a)
 
@@ -270,8 +332,8 @@
  * Bit positions start at zero.
  * MASK_BITS_ABOVE creates a mask starting AT the position and above
  * MASK_BITS_BELOW creates a mask starting one bit BELOW the position
- * MASK_BITS_ABOVE/BELOW accpets a bit offset to create a mask
- * MASK_BITS_ABOVE/BELOW_32/64 accpets a bit width to create a mask
+ * MASK_BITS_ABOVE/BELOW accepts a bit offset to create a mask
+ * MASK_BITS_ABOVE/BELOW_32/64 accepts a bit width to create a mask
  * Note: The ACPI_INTEGER_BIT_SIZE check is used to bypass compiler
  * differences with the shift operator
  */
@@ -389,7 +451,7 @@
  */
 #ifndef ACPI_NO_ERROR_MESSAGES
 /*
- * Error reporting. Callers module and line number are inserted by AE_INFO,
+ * Error reporting. The callers module and line number are inserted by AE_INFO,
  * the plist contains a set of parens to allow variable-length lists.
  * These macros are used for both the debug and non-debug versions of the code.
  */
diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h
index 7affdcdfcc81..54a0c51b3e37 100644
--- a/drivers/acpi/acpica/acnamesp.h
+++ b/drivers/acpi/acpica/acnamesp.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acobject.h b/drivers/acpi/acpica/acobject.h
index 094b042678f7..27c3f982d810 100644
--- a/drivers/acpi/acpica/acobject.h
+++ b/drivers/acpi/acpica/acobject.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acopcode.h b/drivers/acpi/acpica/acopcode.h
index ca4bda1a60be..e758f098ff4b 100644
--- a/drivers/acpi/acpica/acopcode.h
+++ b/drivers/acpi/acpica/acopcode.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -92,7 +92,7 @@
 #define ARGP_BYTELIST_OP                ARGP_LIST1 (ARGP_NAMESTRING)
 #define ARGP_CONCAT_OP                  ARGP_LIST3 (ARGP_TERMARG,    ARGP_TERMARG,       ARGP_TARGET)
 #define ARGP_CONCAT_RES_OP              ARGP_LIST3 (ARGP_TERMARG,    ARGP_TERMARG,       ARGP_TARGET)
-#define ARGP_COND_REF_OF_OP             ARGP_LIST2 (ARGP_NAME_OR_REF,ARGP_TARGET)
+#define ARGP_COND_REF_OF_OP             ARGP_LIST2 (ARGP_SIMPLENAME, ARGP_TARGET)
 #define ARGP_CONNECTFIELD_OP            ARGP_LIST1 (ARGP_NAMESTRING)
 #define ARGP_CONTINUE_OP                ARG_NONE
 #define ARGP_COPY_OP                    ARGP_LIST2 (ARGP_TERMARG,    ARGP_SIMPLENAME)
@@ -105,7 +105,7 @@
 #define ARGP_DATA_REGION_OP             ARGP_LIST4 (ARGP_NAME,       ARGP_TERMARG,       ARGP_TERMARG,   ARGP_TERMARG)
 #define ARGP_DEBUG_OP                   ARG_NONE
 #define ARGP_DECREMENT_OP               ARGP_LIST1 (ARGP_SUPERNAME)
-#define ARGP_DEREF_OF_OP                ARGP_LIST1 (ARGP_TERMARG)
+#define ARGP_DEREF_OF_OP                ARGP_LIST1 (ARGP_SUPERNAME)
 #define ARGP_DEVICE_OP                  ARGP_LIST3 (ARGP_PKGLENGTH,  ARGP_NAME,          ARGP_OBJLIST)
 #define ARGP_DIVIDE_OP                  ARGP_LIST4 (ARGP_TERMARG,    ARGP_TERMARG,       ARGP_TARGET,    ARGP_TARGET)
 #define ARGP_DWORD_OP                   ARGP_LIST1 (ARGP_DWORDDATA)
@@ -152,14 +152,14 @@
 #define ARGP_NAMEPATH_OP                ARGP_LIST1 (ARGP_NAMESTRING)
 #define ARGP_NOOP_OP                    ARG_NONE
 #define ARGP_NOTIFY_OP                  ARGP_LIST2 (ARGP_SUPERNAME,  ARGP_TERMARG)
-#define ARGP_OBJECT_TYPE_OP             ARGP_LIST1 (ARGP_NAME_OR_REF)
+#define ARGP_OBJECT_TYPE_OP             ARGP_LIST1 (ARGP_SIMPLENAME)
 #define ARGP_ONE_OP                     ARG_NONE
 #define ARGP_ONES_OP                    ARG_NONE
 #define ARGP_PACKAGE_OP                 ARGP_LIST3 (ARGP_PKGLENGTH,  ARGP_BYTEDATA,      ARGP_DATAOBJLIST)
 #define ARGP_POWER_RES_OP               ARGP_LIST5 (ARGP_PKGLENGTH,  ARGP_NAME,          ARGP_BYTEDATA,  ARGP_WORDDATA,  ARGP_OBJLIST)
 #define ARGP_PROCESSOR_OP               ARGP_LIST6 (ARGP_PKGLENGTH,  ARGP_NAME,          ARGP_BYTEDATA,  ARGP_DWORDDATA, ARGP_BYTEDATA,  ARGP_OBJLIST)
 #define ARGP_QWORD_OP                   ARGP_LIST1 (ARGP_QWORDDATA)
-#define ARGP_REF_OF_OP                  ARGP_LIST1 (ARGP_NAME_OR_REF)
+#define ARGP_REF_OF_OP                  ARGP_LIST1 (ARGP_SIMPLENAME)
 #define ARGP_REGION_OP                  ARGP_LIST4 (ARGP_NAME,       ARGP_BYTEDATA,      ARGP_TERMARG,   ARGP_TERMARG)
 #define ARGP_RELEASE_OP                 ARGP_LIST1 (ARGP_SUPERNAME)
 #define ARGP_RESERVEDFIELD_OP           ARGP_LIST1 (ARGP_NAMESTRING)
@@ -249,7 +249,7 @@
 #define ARGI_FIELD_OP                   ARGI_INVALID_OPCODE
 #define ARGI_FIND_SET_LEFT_BIT_OP       ARGI_LIST2 (ARGI_INTEGER,    ARGI_TARGETREF)
 #define ARGI_FIND_SET_RIGHT_BIT_OP      ARGI_LIST2 (ARGI_INTEGER,    ARGI_TARGETREF)
-#define ARGI_FROM_BCD_OP                ARGI_LIST2 (ARGI_INTEGER,    ARGI_FIXED_TARGET)
+#define ARGI_FROM_BCD_OP                ARGI_LIST2 (ARGI_INTEGER,    ARGI_TARGETREF)
 #define ARGI_IF_OP                      ARGI_INVALID_OPCODE
 #define ARGI_INCREMENT_OP               ARGI_LIST1 (ARGI_TARGETREF)
 #define ARGI_INDEX_FIELD_OP             ARGI_INVALID_OPCODE
@@ -313,12 +313,12 @@
 #define ARGI_SUBTRACT_OP                ARGI_LIST3 (ARGI_INTEGER,    ARGI_INTEGER,       ARGI_TARGETREF)
 #define ARGI_THERMAL_ZONE_OP            ARGI_INVALID_OPCODE
 #define ARGI_TIMER_OP                   ARG_NONE
-#define ARGI_TO_BCD_OP                  ARGI_LIST2 (ARGI_INTEGER,    ARGI_FIXED_TARGET)
-#define ARGI_TO_BUFFER_OP               ARGI_LIST2 (ARGI_COMPUTEDATA,ARGI_FIXED_TARGET)
-#define ARGI_TO_DEC_STR_OP              ARGI_LIST2 (ARGI_COMPUTEDATA,ARGI_FIXED_TARGET)
-#define ARGI_TO_HEX_STR_OP              ARGI_LIST2 (ARGI_COMPUTEDATA,ARGI_FIXED_TARGET)
-#define ARGI_TO_INTEGER_OP              ARGI_LIST2 (ARGI_COMPUTEDATA,ARGI_FIXED_TARGET)
-#define ARGI_TO_STRING_OP               ARGI_LIST3 (ARGI_BUFFER,     ARGI_INTEGER,       ARGI_FIXED_TARGET)
+#define ARGI_TO_BCD_OP                  ARGI_LIST2 (ARGI_INTEGER,    ARGI_TARGETREF)
+#define ARGI_TO_BUFFER_OP               ARGI_LIST2 (ARGI_COMPUTEDATA,ARGI_TARGETREF)
+#define ARGI_TO_DEC_STR_OP              ARGI_LIST2 (ARGI_COMPUTEDATA,ARGI_TARGETREF)
+#define ARGI_TO_HEX_STR_OP              ARGI_LIST2 (ARGI_COMPUTEDATA,ARGI_TARGETREF)
+#define ARGI_TO_INTEGER_OP              ARGI_LIST2 (ARGI_COMPUTEDATA,ARGI_TARGETREF)
+#define ARGI_TO_STRING_OP               ARGI_LIST3 (ARGI_BUFFER,     ARGI_INTEGER,       ARGI_TARGETREF)
 #define ARGI_UNLOAD_OP                  ARGI_LIST1 (ARGI_DDBHANDLE)
 #define ARGI_VAR_PACKAGE_OP             ARGI_LIST1 (ARGI_INTEGER)
 #define ARGI_WAIT_OP                    ARGI_LIST2 (ARGI_EVENT,      ARGI_INTEGER)
diff --git a/drivers/acpi/acpica/acparser.h b/drivers/acpi/acpica/acparser.h
index 939d41113970..c23c47328060 100644
--- a/drivers/acpi/acpica/acparser.h
+++ b/drivers/acpi/acpica/acparser.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h
index 888440b2cf2e..dcfc05d40e36 100644
--- a/drivers/acpi/acpica/acpredef.h
+++ b/drivers/acpi/acpica/acpredef.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acresrc.h b/drivers/acpi/acpica/acresrc.h
index 63da1e37caba..b4d22f6e48e2 100644
--- a/drivers/acpi/acpica/acresrc.h
+++ b/drivers/acpi/acpica/acresrc.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acstruct.h b/drivers/acpi/acpica/acstruct.h
index 6235642e31d3..62134bdbeda6 100644
--- a/drivers/acpi/acpica/acstruct.h
+++ b/drivers/acpi/acpica/acstruct.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/actables.h b/drivers/acpi/acpica/actables.h
index 94be8a8e6c08..c8da453bd960 100644
--- a/drivers/acpi/acpica/actables.h
+++ b/drivers/acpi/acpica/actables.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/acutils.h b/drivers/acpi/acpica/acutils.h
index 845afb180a7e..6f28cfae2212 100644
--- a/drivers/acpi/acpica/acutils.h
+++ b/drivers/acpi/acpica/acutils.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/amlcode.h b/drivers/acpi/acpica/amlcode.h
index 6bd8d4bcff65..b536fd471292 100644
--- a/drivers/acpi/acpica/amlcode.h
+++ b/drivers/acpi/acpica/amlcode.h
@@ -7,7 +7,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -277,9 +277,23 @@
 #define ARGI_DEVICE_REF             0x0D
 #define ARGI_REFERENCE              0x0E
 #define ARGI_TARGETREF              0x0F	/* Target, subject to implicit conversion */
-#define ARGI_FIXED_TARGET           0x10	/* Target, no implicit conversion */
-#define ARGI_SIMPLE_TARGET          0x11	/* Name, Local, Arg -- no implicit conversion */
-#define ARGI_STORE_TARGET           0x12	/* Target for store is TARGETREF + package objects */
+#define ARGI_SIMPLE_TARGET          0x10	/* Name, Local, Arg -- no implicit conversion */
+#define ARGI_STORE_TARGET           0x11	/* Target for store is TARGETREF + package objects */
+/*
+ * #define ARGI_FIXED_TARGET           0x10     Target, no implicit conversion
+ *
+ * Removed 10/2016. ARGI_FIXED_TARGET was used for these operators:
+ *      from_BCD
+ *      to_BCD
+ *      to_decimal_string
+ *      to_hex_string
+ *      to_integer
+ *      to_buffer
+ * The purpose of this type was to disable "implicit result conversion",
+ * but this was incorrect per the ACPI spec and other ACPI implementations.
+ * These operators now have the target operand defined as a normal
+ * ARGI_TARGETREF.
+ */
 
 /* Multiple/complex types */
 
diff --git a/drivers/acpi/acpica/amlresrc.h b/drivers/acpi/acpica/amlresrc.h
index dee6c7ea4773..653a3d1ef5d5 100644
--- a/drivers/acpi/acpica/amlresrc.h
+++ b/drivers/acpi/acpica/amlresrc.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbcmds.c b/drivers/acpi/acpica/dbcmds.c
index 62bd446535f5..5984b90eb590 100644
--- a/drivers/acpi/acpica/dbcmds.c
+++ b/drivers/acpi/acpica/dbcmds.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbconvert.c b/drivers/acpi/acpica/dbconvert.c
index 147ce8894f76..251f9477a984 100644
--- a/drivers/acpi/acpica/dbconvert.c
+++ b/drivers/acpi/acpica/dbconvert.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbdisply.c b/drivers/acpi/acpica/dbdisply.c
index 502bb587f112..46bf270ac525 100644
--- a/drivers/acpi/acpica/dbdisply.c
+++ b/drivers/acpi/acpica/dbdisply.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbexec.c b/drivers/acpi/acpica/dbexec.c
index fe3da7c31bb7..b611cd92b5f5 100644
--- a/drivers/acpi/acpica/dbexec.c
+++ b/drivers/acpi/acpica/dbexec.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbfileio.c b/drivers/acpi/acpica/dbfileio.c
index 6f05b8c271a5..4d81ea291d93 100644
--- a/drivers/acpi/acpica/dbfileio.c
+++ b/drivers/acpi/acpica/dbfileio.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbhistry.c b/drivers/acpi/acpica/dbhistry.c
index 46bd65d38df9..7d08974c64c2 100644
--- a/drivers/acpi/acpica/dbhistry.c
+++ b/drivers/acpi/acpica/dbhistry.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbinput.c b/drivers/acpi/acpica/dbinput.c
index 068214f9cc9d..2626d79db064 100644
--- a/drivers/acpi/acpica/dbinput.c
+++ b/drivers/acpi/acpica/dbinput.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbmethod.c b/drivers/acpi/acpica/dbmethod.c
index 314b94cf086a..15c8237b8a80 100644
--- a/drivers/acpi/acpica/dbmethod.c
+++ b/drivers/acpi/acpica/dbmethod.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c
index 8667f14d535e..8c207c772517 100644
--- a/drivers/acpi/acpica/dbnames.c
+++ b/drivers/acpi/acpica/dbnames.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbobject.c b/drivers/acpi/acpica/dbobject.c
index 08eaaf350b24..f2252b1ac0b3 100644
--- a/drivers/acpi/acpica/dbobject.c
+++ b/drivers/acpi/acpica/dbobject.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbstats.c b/drivers/acpi/acpica/dbstats.c
index a414e1fa6f9d..99fb0160b8fb 100644
--- a/drivers/acpi/acpica/dbstats.c
+++ b/drivers/acpi/acpica/dbstats.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbtest.c b/drivers/acpi/acpica/dbtest.c
index 74aa38156cdc..c6bee6143266 100644
--- a/drivers/acpi/acpica/dbtest.c
+++ b/drivers/acpi/acpica/dbtest.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbutils.c b/drivers/acpi/acpica/dbutils.c
index ae80106d1000..bfa972b64171 100644
--- a/drivers/acpi/acpica/dbutils.c
+++ b/drivers/acpi/acpica/dbutils.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dbxface.c b/drivers/acpi/acpica/dbxface.c
index 124db237775d..205b8e0eded5 100644
--- a/drivers/acpi/acpica/dbxface.c
+++ b/drivers/acpi/acpica/dbxface.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -430,7 +430,7 @@ acpi_status acpi_initialize_debugger(void)
 
 		/* These were created with one unit, grab it */
 
-		status = acpi_os_initialize_command_signals();
+		status = acpi_os_initialize_debugger();
 		if (ACPI_FAILURE(status)) {
 			acpi_os_printf("Could not get debugger mutex\n");
 			return_ACPI_STATUS(status);
@@ -482,7 +482,7 @@ void acpi_terminate_debugger(void)
 			acpi_os_sleep(100);
 		}
 
-		acpi_os_terminate_command_signals();
+		acpi_os_terminate_debugger();
 	}
 
 	if (acpi_gbl_db_buffer) {
diff --git a/drivers/acpi/acpica/dsargs.c b/drivers/acpi/acpica/dsargs.c
index ad0413beeeae..287b3fd73cfc 100644
--- a/drivers/acpi/acpica/dsargs.c
+++ b/drivers/acpi/acpica/dsargs.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c
index 4ddcbf100234..d31b49feaa79 100644
--- a/drivers/acpi/acpica/dscontrol.c
+++ b/drivers/acpi/acpica/dscontrol.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsdebug.c b/drivers/acpi/acpica/dsdebug.c
index 56c3aadb4cba..4d885eb8eda9 100644
--- a/drivers/acpi/acpica/dsdebug.c
+++ b/drivers/acpi/acpica/dsdebug.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsfield.c b/drivers/acpi/acpica/dsfield.c
index 6a4b603d0e83..c5dccc54307d 100644
--- a/drivers/acpi/acpica/dsfield.c
+++ b/drivers/acpi/acpica/dsfield.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index 5de3f10cab03..b1842dd4edf7 100644
--- a/drivers/acpi/acpica/dsinit.c
+++ b/drivers/acpi/acpica/dsinit.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index 2b3210f42a46..31c9c7aec3d5 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsmthdat.c b/drivers/acpi/acpica/dsmthdat.c
index 45cbebaa32c0..adcc72cd53a7 100644
--- a/drivers/acpi/acpica/dsmthdat.c
+++ b/drivers/acpi/acpica/dsmthdat.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsobject.c b/drivers/acpi/acpica/dsobject.c
index a91de2b4603c..8deaa16493a0 100644
--- a/drivers/acpi/acpica/dsobject.c
+++ b/drivers/acpi/acpica/dsobject.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c
index 77fd7c84ec39..148523205d41 100644
--- a/drivers/acpi/acpica/dsopcode.c
+++ b/drivers/acpi/acpica/dsopcode.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dsutils.c b/drivers/acpi/acpica/dsutils.c
index 7d8ef52fb88d..049fbab4e5a6 100644
--- a/drivers/acpi/acpica/dsutils.c
+++ b/drivers/acpi/acpica/dsutils.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dswexec.c b/drivers/acpi/acpica/dswexec.c
index 438597cf6cc5..78f8e6a4f72f 100644
--- a/drivers/acpi/acpica/dswexec.c
+++ b/drivers/acpi/acpica/dswexec.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dswload.c b/drivers/acpi/acpica/dswload.c
index fd34040d4f44..cafb3ab567ab 100644
--- a/drivers/acpi/acpica/dswload.c
+++ b/drivers/acpi/acpica/dswload.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dswload2.c b/drivers/acpi/acpica/dswload2.c
index 651f35a66cc2..44d4553dfbdd 100644
--- a/drivers/acpi/acpica/dswload2.c
+++ b/drivers/acpi/acpica/dswload2.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dswscope.c b/drivers/acpi/acpica/dswscope.c
index 9f32e08a07d9..3e081983d2ee 100644
--- a/drivers/acpi/acpica/dswscope.c
+++ b/drivers/acpi/acpica/dswscope.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/dswstate.c b/drivers/acpi/acpica/dswstate.c
index e3338698e56b..da111a1f5bfb 100644
--- a/drivers/acpi/acpica/dswstate.c
+++ b/drivers/acpi/acpica/dswstate.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evevent.c b/drivers/acpi/acpica/evevent.c
index 80fc0b9b11e5..d3b6b314fa50 100644
--- a/drivers/acpi/acpica/evevent.c
+++ b/drivers/acpi/acpica/evevent.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evglock.c b/drivers/acpi/acpica/evglock.c
index 9f015782cdd3..0ce33b0f430c 100644
--- a/drivers/acpi/acpica/evglock.c
+++ b/drivers/acpi/acpica/evglock.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index bdb10bee13ce..229382035550 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index d54014cab01d..9c941947a063 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index 16ce4835e7d0..8649c6242478 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evgpeutil.c b/drivers/acpi/acpica/evgpeutil.c
index 3f150d567e64..c8adb400330a 100644
--- a/drivers/acpi/acpica/evgpeutil.c
+++ b/drivers/acpi/acpica/evgpeutil.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evhandler.c b/drivers/acpi/acpica/evhandler.c
index 24768ca03f19..2db61ef1b4a3 100644
--- a/drivers/acpi/acpica/evhandler.c
+++ b/drivers/acpi/acpica/evhandler.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evmisc.c b/drivers/acpi/acpica/evmisc.c
index f51d43adb7d1..4f6bb3f016ab 100644
--- a/drivers/acpi/acpica/evmisc.c
+++ b/drivers/acpi/acpica/evmisc.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 4c6f79514040..28b447ff92df 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evrgnini.c b/drivers/acpi/acpica/evrgnini.c
index a9092251ce80..93ec528bcd9a 100644
--- a/drivers/acpi/acpica/evrgnini.c
+++ b/drivers/acpi/acpica/evrgnini.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evsci.c b/drivers/acpi/acpica/evsci.c
index 3b7757c9c916..8ce73b962006 100644
--- a/drivers/acpi/acpica/evsci.c
+++ b/drivers/acpi/acpica/evsci.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index e4e9260cdc57..dd1b9dd64cef 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evxfevnt.c b/drivers/acpi/acpica/evxfevnt.c
index 9179e9abe3db..82e8971f23a4 100644
--- a/drivers/acpi/acpica/evxfevnt.c
+++ b/drivers/acpi/acpica/evxfevnt.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index d7a3b2775505..57718a3e029a 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c
index d2743067126a..beba9d56a0d8 100644
--- a/drivers/acpi/acpica/evxfregn.c
+++ b/drivers/acpi/acpica/evxfregn.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exconcat.c b/drivers/acpi/acpica/exconcat.c
index 5429c2a6bc41..76bfb7dcae2f 100644
--- a/drivers/acpi/acpica/exconcat.c
+++ b/drivers/acpi/acpica/exconcat.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c
index c32c7829878a..61813bd43f9e 100644
--- a/drivers/acpi/acpica/exconfig.c
+++ b/drivers/acpi/acpica/exconfig.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exconvrt.c b/drivers/acpi/acpica/exconvrt.c
index 588ad1409dbe..f71028e334ee 100644
--- a/drivers/acpi/acpica/exconvrt.c
+++ b/drivers/acpi/acpica/exconvrt.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -592,7 +592,6 @@ acpi_ex_convert_to_target_type(acpi_object_type destination_type,
 	 */
 	switch (GET_CURRENT_ARG_TYPE(walk_state->op_info->runtime_args)) {
 	case ARGI_SIMPLE_TARGET:
-	case ARGI_FIXED_TARGET:
 	case ARGI_INTEGER_REF:	/* Handles Increment, Decrement cases */
 
 		switch (destination_type) {
diff --git a/drivers/acpi/acpica/excreate.c b/drivers/acpi/acpica/excreate.c
index 613ba6eb08bb..d43d7da4c734 100644
--- a/drivers/acpi/acpica/excreate.c
+++ b/drivers/acpi/acpica/excreate.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exdebug.c b/drivers/acpi/acpica/exdebug.c
index 37a509d016da..ec614f5a3bcb 100644
--- a/drivers/acpi/acpica/exdebug.c
+++ b/drivers/acpi/acpica/exdebug.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index fce6b2e10209..970dc6c53994 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exfield.c b/drivers/acpi/acpica/exfield.c
index d7d3ee36338b..5fda981f6498 100644
--- a/drivers/acpi/acpica/exfield.c
+++ b/drivers/acpi/acpica/exfield.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c
index ee76d299b3d0..a656608dca84 100644
--- a/drivers/acpi/acpica/exfldio.c
+++ b/drivers/acpi/acpica/exfldio.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exmisc.c b/drivers/acpi/acpica/exmisc.c
index 37c88b424a02..1a6f59079ea5 100644
--- a/drivers/acpi/acpica/exmisc.c
+++ b/drivers/acpi/acpica/exmisc.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exmutex.c b/drivers/acpi/acpica/exmutex.c
index 26faa91e930c..ecd95b3f35f1 100644
--- a/drivers/acpi/acpica/exmutex.c
+++ b/drivers/acpi/acpica/exmutex.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c
index 3d6af93fe561..ee7b62a86661 100644
--- a/drivers/acpi/acpica/exnames.c
+++ b/drivers/acpi/acpica/exnames.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exoparg1.c b/drivers/acpi/acpica/exoparg1.c
index 007300433cde..af73fcde7e5c 100644
--- a/drivers/acpi/acpica/exoparg1.c
+++ b/drivers/acpi/acpica/exoparg1.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exoparg2.c b/drivers/acpi/acpica/exoparg2.c
index 79ef3b6811a9..44ecba50c0da 100644
--- a/drivers/acpi/acpica/exoparg2.c
+++ b/drivers/acpi/acpica/exoparg2.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exoparg3.c b/drivers/acpi/acpica/exoparg3.c
index 69e4e269ad2f..ce857addc8db 100644
--- a/drivers/acpi/acpica/exoparg3.c
+++ b/drivers/acpi/acpica/exoparg3.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exoparg6.c b/drivers/acpi/acpica/exoparg6.c
index 786d53b0bb37..31e4df97cbe1 100644
--- a/drivers/acpi/acpica/exoparg6.c
+++ b/drivers/acpi/acpica/exoparg6.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c
index aed8d3459220..8de060664204 100644
--- a/drivers/acpi/acpica/exprep.c
+++ b/drivers/acpi/acpica/exprep.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c
index 31b381cae94d..7bcc9d809b7e 100644
--- a/drivers/acpi/acpica/exregion.c
+++ b/drivers/acpi/acpica/exregion.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exresnte.c b/drivers/acpi/acpica/exresnte.c
index a183cb740d24..91c1de046442 100644
--- a/drivers/acpi/acpica/exresnte.c
+++ b/drivers/acpi/acpica/exresnte.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exresolv.c b/drivers/acpi/acpica/exresolv.c
index e1d3878be2c6..7fecefc2e1b4 100644
--- a/drivers/acpi/acpica/exresolv.c
+++ b/drivers/acpi/acpica/exresolv.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exresop.c b/drivers/acpi/acpica/exresop.c
index f29eba1dc5e9..c4852429e2ff 100644
--- a/drivers/acpi/acpica/exresop.c
+++ b/drivers/acpi/acpica/exresop.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -305,7 +305,6 @@ acpi_ex_resolve_operands(u16 opcode,
 		case ARGI_OBJECT_REF:
 		case ARGI_DEVICE_REF:
 		case ARGI_TARGETREF:	/* Allows implicit conversion rules before store */
-		case ARGI_FIXED_TARGET:	/* No implicit conversion before store to target */
 		case ARGI_SIMPLE_TARGET:	/* Name, Local, or arg - no implicit conversion  */
 		case ARGI_STORE_TARGET:
 
diff --git a/drivers/acpi/acpica/exstore.c b/drivers/acpi/acpica/exstore.c
index cd70cbcf6de6..a2f8001aeb86 100644
--- a/drivers/acpi/acpica/exstore.c
+++ b/drivers/acpi/acpica/exstore.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exstoren.c b/drivers/acpi/acpica/exstoren.c
index 13bbb2b241a3..85db4716a043 100644
--- a/drivers/acpi/acpica/exstoren.c
+++ b/drivers/acpi/acpica/exstoren.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exstorob.c b/drivers/acpi/acpica/exstorob.c
index 1dab82746d06..4ba7fcbf23b0 100644
--- a/drivers/acpi/acpica/exstorob.c
+++ b/drivers/acpi/acpica/exstorob.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c
index ac09c31cc70e..ad3b610057f3 100644
--- a/drivers/acpi/acpica/exsystem.c
+++ b/drivers/acpi/acpica/exsystem.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/extrace.c b/drivers/acpi/acpica/extrace.c
index c9ca82610d77..ae9df8672d9e 100644
--- a/drivers/acpi/acpica/extrace.c
+++ b/drivers/acpi/acpica/extrace.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/exutils.c b/drivers/acpi/acpica/exutils.c
index a8b857a7e9fb..34d608358eaf 100644
--- a/drivers/acpi/acpica/exutils.c
+++ b/drivers/acpi/acpica/exutils.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwacpi.c b/drivers/acpi/acpica/hwacpi.c
index 3ebbb09030b4..fad249e774b4 100644
--- a/drivers/acpi/acpica/hwacpi.c
+++ b/drivers/acpi/acpica/hwacpi.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwesleep.c b/drivers/acpi/acpica/hwesleep.c
index 3f2fb4b31fdc..12626d021a9b 100644
--- a/drivers/acpi/acpica/hwesleep.c
+++ b/drivers/acpi/acpica/hwesleep.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -43,7 +43,6 @@
  */
 
 #include <acpi/acpi.h>
-#include <linux/acpi.h>
 #include "accommon.h"
 
 #define _COMPONENT          ACPI_HARDWARE
@@ -103,7 +102,7 @@ void acpi_hw_execute_sleep_method(char *method_pathname, u32 integer_argument)
 acpi_status acpi_hw_extended_sleep(u8 sleep_state)
 {
 	acpi_status status;
-	u8 sleep_type_value;
+	u8 sleep_control;
 	u64 sleep_status;
 
 	ACPI_FUNCTION_TRACE(hw_extended_sleep);
@@ -125,18 +124,6 @@ acpi_status acpi_hw_extended_sleep(u8 sleep_state)
 
 	acpi_gbl_system_awake_and_running = FALSE;
 
-	/* Flush caches, as per ACPI specification */
-
-	ACPI_FLUSH_CPU_CACHE();
-
-	status = acpi_os_prepare_extended_sleep(sleep_state,
-						acpi_gbl_sleep_type_a,
-						acpi_gbl_sleep_type_b);
-	if (ACPI_SKIP(status))
-		return_ACPI_STATUS(AE_OK);
-	if (ACPI_FAILURE(status))
-		return_ACPI_STATUS(status);
-
 	/*
 	 * Set the SLP_TYP and SLP_EN bits.
 	 *
@@ -146,12 +133,22 @@ acpi_status acpi_hw_extended_sleep(u8 sleep_state)
 	ACPI_DEBUG_PRINT((ACPI_DB_INIT,
 			  "Entering sleep state [S%u]\n", sleep_state));
 
-	sleep_type_value =
-	    ((acpi_gbl_sleep_type_a << ACPI_X_SLEEP_TYPE_POSITION) &
-	     ACPI_X_SLEEP_TYPE_MASK);
+	sleep_control = ((acpi_gbl_sleep_type_a << ACPI_X_SLEEP_TYPE_POSITION) &
+			 ACPI_X_SLEEP_TYPE_MASK) | ACPI_X_SLEEP_ENABLE;
+
+	/* Flush caches, as per ACPI specification */
+
+	ACPI_FLUSH_CPU_CACHE();
+
+	status = acpi_os_enter_sleep(sleep_state, sleep_control, 0);
+	if (status == AE_CTRL_TERMINATE) {
+		return_ACPI_STATUS(AE_OK);
+	}
+	if (ACPI_FAILURE(status)) {
+		return_ACPI_STATUS(status);
+	}
 
-	status = acpi_write((u64)(sleep_type_value | ACPI_X_SLEEP_ENABLE),
-			    &acpi_gbl_FADT.sleep_control);
+	status = acpi_write((u64)sleep_control, &acpi_gbl_FADT.sleep_control);
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
 	}
diff --git a/drivers/acpi/acpica/hwgpe.c b/drivers/acpi/acpica/hwgpe.c
index 76b0e350f5bb..5eb11b30a79e 100644
--- a/drivers/acpi/acpica/hwgpe.c
+++ b/drivers/acpi/acpica/hwgpe.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwpci.c b/drivers/acpi/acpica/hwpci.c
index 3dd60c96aa07..283819930be6 100644
--- a/drivers/acpi/acpica/hwpci.c
+++ b/drivers/acpi/acpica/hwpci.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index 3b7fb99362b6..de74a4c25085 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -52,7 +52,8 @@ ACPI_MODULE_NAME("hwregs")
 #if (!ACPI_REDUCED_HARDWARE)
 /* Local Prototypes */
 static u8
-acpi_hw_get_access_bit_width(struct acpi_generic_address *reg,
+acpi_hw_get_access_bit_width(u64 address,
+			     struct acpi_generic_address *reg,
 			     u8 max_bit_width);
 
 static acpi_status
@@ -71,7 +72,8 @@ acpi_hw_write_multiple(u32 value,
  *
  * FUNCTION:    acpi_hw_get_access_bit_width
  *
- * PARAMETERS:  reg                 - GAS register structure
+ * PARAMETERS:  address             - GAS register address
+ *              reg                 - GAS register structure
  *              max_bit_width       - Max bit_width supported (32 or 64)
  *
  * RETURN:      Status
@@ -81,27 +83,59 @@ acpi_hw_write_multiple(u32 value,
  ******************************************************************************/
 
 static u8
-acpi_hw_get_access_bit_width(struct acpi_generic_address *reg, u8 max_bit_width)
+acpi_hw_get_access_bit_width(u64 address,
+			     struct acpi_generic_address *reg, u8 max_bit_width)
 {
-	if (!reg->access_width) {
-		if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
-			max_bit_width = 32;
-		}
+	u8 access_bit_width;
 
-		/*
-		 * Detect old register descriptors where only the bit_width field
-		 * makes senses.
-		 */
-		if (reg->bit_width < max_bit_width &&
-		    !reg->bit_offset && reg->bit_width &&
-		    ACPI_IS_POWER_OF_TWO(reg->bit_width) &&
-		    ACPI_IS_ALIGNED(reg->bit_width, 8)) {
-			return (reg->bit_width);
-		}
-		return (max_bit_width);
+	/*
+	 * GAS format "register", used by FADT:
+	 *  1. Detected if bit_offset is 0 and bit_width is 8/16/32/64;
+	 *  2. access_size field is ignored and bit_width field is used for
+	 *     determining the boundary of the IO accesses.
+	 * GAS format "region", used by APEI registers:
+	 *  1. Detected if bit_offset is not 0 or bit_width is not 8/16/32/64;
+	 *  2. access_size field is used for determining the boundary of the
+	 *     IO accesses;
+	 *  3. bit_offset/bit_width fields are used to describe the "region".
+	 *
+	 * Note: This algorithm assumes that the "Address" fields should always
+	 *       contain aligned values.
+	 */
+	if (!reg->bit_offset && reg->bit_width &&
+	    ACPI_IS_POWER_OF_TWO(reg->bit_width) &&
+	    ACPI_IS_ALIGNED(reg->bit_width, 8)) {
+		access_bit_width = reg->bit_width;
+	} else if (reg->access_width) {
+		access_bit_width = (1 << (reg->access_width + 2));
 	} else {
-		return (1 << (reg->access_width + 2));
+		access_bit_width =
+		    ACPI_ROUND_UP_POWER_OF_TWO_8(reg->bit_offset +
+						 reg->bit_width);
+		if (access_bit_width <= 8) {
+			access_bit_width = 8;
+		} else {
+			while (!ACPI_IS_ALIGNED(address, access_bit_width >> 3)) {
+				access_bit_width >>= 1;
+			}
+		}
 	}
+
+	/* Maximum IO port access bit width is 32 */
+
+	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_IO) {
+		max_bit_width = 32;
+	}
+
+	/*
+	 * Return access width according to the requested maximum access bit width,
+	 * as the caller should know the format of the register and may enforce
+	 * a 32-bit accesses.
+	 */
+	if (access_bit_width < max_bit_width) {
+		return (access_bit_width);
+	}
+	return (max_bit_width);
 }
 
 /******************************************************************************
@@ -163,7 +197,8 @@ acpi_hw_validate_register(struct acpi_generic_address *reg,
 
 	/* Validate the bit_width, convert access_width into number of bits */
 
-	access_width = acpi_hw_get_access_bit_width(reg, max_bit_width);
+	access_width =
+	    acpi_hw_get_access_bit_width(*address, reg, max_bit_width);
 	bit_width =
 	    ACPI_ROUND_UP(reg->bit_offset + reg->bit_width, access_width);
 	if (max_bit_width < bit_width) {
@@ -219,7 +254,7 @@ acpi_status acpi_hw_read(u32 *value, struct acpi_generic_address *reg)
 	 * into number of bits based
 	 */
 	*value = 0;
-	access_width = acpi_hw_get_access_bit_width(reg, 32);
+	access_width = acpi_hw_get_access_bit_width(address, reg, 32);
 	bit_width = reg->bit_offset + reg->bit_width;
 	bit_offset = reg->bit_offset;
 
@@ -252,20 +287,6 @@ acpi_status acpi_hw_read(u32 *value, struct acpi_generic_address *reg)
 							   &value32,
 							   access_width);
 			}
-
-			/*
-			 * Use offset style bit masks because:
-			 * bit_offset < access_width/bit_width < access_width, and
-			 * access_width is ensured to be less than 32-bits by
-			 * acpi_hw_validate_register().
-			 */
-			if (bit_offset) {
-				value32 &= ACPI_MASK_BITS_BELOW(bit_offset);
-				bit_offset = 0;
-			}
-			if (bit_width < access_width) {
-				value32 &= ACPI_MASK_BITS_ABOVE(bit_width);
-			}
 		}
 
 		/*
@@ -306,6 +327,12 @@ acpi_status acpi_hw_read(u32 *value, struct acpi_generic_address *reg)
 acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg)
 {
 	u64 address;
+	u8 access_width;
+	u32 bit_width;
+	u8 bit_offset;
+	u64 value64;
+	u32 value32;
+	u8 index;
 	acpi_status status;
 
 	ACPI_FUNCTION_NAME(hw_write);
@@ -317,23 +344,61 @@ acpi_status acpi_hw_write(u32 value, struct acpi_generic_address *reg)
 		return (status);
 	}
 
+	/* Convert access_width into number of bits based */
+
+	access_width = acpi_hw_get_access_bit_width(address, reg, 32);
+	bit_width = reg->bit_offset + reg->bit_width;
+	bit_offset = reg->bit_offset;
+
 	/*
 	 * Two address spaces supported: Memory or IO. PCI_Config is
 	 * not supported here because the GAS structure is insufficient
 	 */
-	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
-		status = acpi_os_write_memory((acpi_physical_address)
-					      address, (u64)value,
-					      reg->bit_width);
-	} else {		/* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
-
-		status = acpi_hw_write_port((acpi_io_address)
-					    address, value, reg->bit_width);
+	index = 0;
+	while (bit_width) {
+		/*
+		 * Use offset style bit reads because "Index * AccessWidth" is
+		 * ensured to be less than 32-bits by acpi_hw_validate_register().
+		 */
+		value32 = ACPI_GET_BITS(&value, index * access_width,
+					ACPI_MASK_BITS_ABOVE_32(access_width));
+
+		if (bit_offset >= access_width) {
+			bit_offset -= access_width;
+		} else {
+			if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
+				value64 = (u64)value32;
+				status =
+				    acpi_os_write_memory((acpi_physical_address)
+							 address +
+							 index *
+							 ACPI_DIV_8
+							 (access_width),
+							 value64, access_width);
+			} else {	/* ACPI_ADR_SPACE_SYSTEM_IO, validated earlier */
+
+				status = acpi_hw_write_port((acpi_io_address)
+							    address +
+							    index *
+							    ACPI_DIV_8
+							    (access_width),
+							    value32,
+							    access_width);
+			}
+		}
+
+		/*
+		 * Index * access_width is ensured to be less than 32-bits by
+		 * acpi_hw_validate_register().
+		 */
+		bit_width -=
+		    bit_width > access_width ? access_width : bit_width;
+		index++;
 	}
 
 	ACPI_DEBUG_PRINT((ACPI_DB_IO,
 			  "Wrote: %8.8X width %2d   to %8.8X%8.8X (%s)\n",
-			  value, reg->bit_width, ACPI_FORMAT_UINT64(address),
+			  value, access_width, ACPI_FORMAT_UINT64(address),
 			  acpi_ut_get_region_name(reg->space_id)));
 
 	return (status);
diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c
index d00c9810845b..1fe7387a00e6 100644
--- a/drivers/acpi/acpica/hwsleep.c
+++ b/drivers/acpi/acpica/hwsleep.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -43,7 +43,6 @@
  */
 
 #include <acpi/acpi.h>
-#include <linux/acpi.h>
 #include "accommon.h"
 
 #define _COMPONENT          ACPI_HARDWARE
@@ -152,12 +151,14 @@ acpi_status acpi_hw_legacy_sleep(u8 sleep_state)
 
 	ACPI_FLUSH_CPU_CACHE();
 
-	status = acpi_os_prepare_sleep(sleep_state, pm1a_control,
-				       pm1b_control);
-	if (ACPI_SKIP(status))
+	status = acpi_os_enter_sleep(sleep_state, pm1a_control, pm1b_control);
+	if (status == AE_CTRL_TERMINATE) {
 		return_ACPI_STATUS(AE_OK);
-	if (ACPI_FAILURE(status))
+	}
+	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
+	}
+
 	/* Write #2: Write both SLP_TYP + SLP_EN */
 
 	status = acpi_hw_write_pm1_control(pm1a_control, pm1b_control);
diff --git a/drivers/acpi/acpica/hwtimer.c b/drivers/acpi/acpica/hwtimer.c
index 04cc9406c7d8..b3c5d8c754bb 100644
--- a/drivers/acpi/acpica/hwtimer.c
+++ b/drivers/acpi/acpica/hwtimer.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c
index ad0a745712a9..531620abed80 100644
--- a/drivers/acpi/acpica/hwvalid.c
+++ b/drivers/acpi/acpica/hwvalid.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index 98c26ff39409..34684ae89981 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/hwxfsleep.c b/drivers/acpi/acpica/hwxfsleep.c
index f76e0eab32b8..5733b1167e46 100644
--- a/drivers/acpi/acpica/hwxfsleep.c
+++ b/drivers/acpi/acpica/hwxfsleep.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index 73f98d3fed25..498bb8f70e6b 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsalloc.c b/drivers/acpi/acpica/nsalloc.c
index c2cf73fd3918..8ba5b32c9f71 100644
--- a/drivers/acpi/acpica/nsalloc.c
+++ b/drivers/acpi/acpica/nsalloc.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsarguments.c b/drivers/acpi/acpica/nsarguments.c
index f45bff632692..9095d51f6b37 100644
--- a/drivers/acpi/acpica/nsarguments.c
+++ b/drivers/acpi/acpica/nsarguments.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsconvert.c b/drivers/acpi/acpica/nsconvert.c
index 2b85dee6d4c0..e4a7da8a11f0 100644
--- a/drivers/acpi/acpica/nsconvert.c
+++ b/drivers/acpi/acpica/nsconvert.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index 84f35dd27033..4123b5077a7d 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsdumpdv.c b/drivers/acpi/acpica/nsdumpdv.c
index 7060a5668989..5026594763ea 100644
--- a/drivers/acpi/acpica/nsdumpdv.c
+++ b/drivers/acpi/acpica/nsdumpdv.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nseval.c b/drivers/acpi/acpica/nseval.c
index 5d59cfcef6f4..d22167cbd0ca 100644
--- a/drivers/acpi/acpica/nseval.c
+++ b/drivers/acpi/acpica/nseval.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index 36643a8cf65a..ce33e7297ea7 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsload.c b/drivers/acpi/acpica/nsload.c
index d1f20143bb11..d2915e186ae1 100644
--- a/drivers/acpi/acpica/nsload.c
+++ b/drivers/acpi/acpica/nsload.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c
index 94d5d3339845..3db9ca25a620 100644
--- a/drivers/acpi/acpica/nsnames.c
+++ b/drivers/acpi/acpica/nsnames.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsobject.c b/drivers/acpi/acpica/nsobject.c
index cfa2bb7162d8..707b2aa501e1 100644
--- a/drivers/acpi/acpica/nsobject.c
+++ b/drivers/acpi/acpica/nsobject.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index 4f14e9205bff..2fc33a5203f4 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c
index 6d7844580b2a..3dbbecf22087 100644
--- a/drivers/acpi/acpica/nspredef.c
+++ b/drivers/acpi/acpica/nspredef.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsprepkg.c b/drivers/acpi/acpica/nsprepkg.c
index fbedc6e8ab36..4954cb6c9090 100644
--- a/drivers/acpi/acpica/nsprepkg.c
+++ b/drivers/acpi/acpica/nsprepkg.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index 9523d41c7ae9..38316266521e 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c
index d5336122486b..352265498e90 100644
--- a/drivers/acpi/acpica/nsrepair2.c
+++ b/drivers/acpi/acpica/nsrepair2.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nssearch.c b/drivers/acpi/acpica/nssearch.c
index 61036d210274..5de8957f5ef0 100644
--- a/drivers/acpi/acpica/nssearch.c
+++ b/drivers/acpi/acpica/nssearch.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index 691814dfed31..661676714f7b 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nswalk.c b/drivers/acpi/acpica/nswalk.c
index ebd731fe8e45..6b6e6f498cff 100644
--- a/drivers/acpi/acpica/nswalk.c
+++ b/drivers/acpi/acpica/nswalk.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c
index d2a9b4fd739f..8e365c0e766b 100644
--- a/drivers/acpi/acpica/nsxfeval.c
+++ b/drivers/acpi/acpica/nsxfeval.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index e525cbe7d83b..106966235805 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -6,7 +6,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/nsxfobj.c b/drivers/acpi/acpica/nsxfobj.c
index 32d372b85243..47f689ec3fcb 100644
--- a/drivers/acpi/acpica/nsxfobj.c
+++ b/drivers/acpi/acpica/nsxfobj.c
@@ -6,7 +6,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c
index c29c930ffa08..05b62ad44c3e 100644
--- a/drivers/acpi/acpica/psargs.c
+++ b/drivers/acpi/acpica/psargs.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -269,23 +269,27 @@ acpi_ps_get_next_namepath(struct acpi_walk_state *walk_state,
 	 */
 	if (ACPI_SUCCESS(status) &&
 	    possible_method_call && (node->type == ACPI_TYPE_METHOD)) {
-		if (walk_state->opcode == AML_UNLOAD_OP) {
+		if ((GET_CURRENT_ARG_TYPE(walk_state->arg_types) ==
+		     ARGP_SUPERNAME)
+		    || (GET_CURRENT_ARG_TYPE(walk_state->arg_types) ==
+			ARGP_TARGET)) {
 			/*
-			 * acpi_ps_get_next_namestring has increased the AML pointer,
-			 * so we need to restore the saved AML pointer for method call.
+			 * acpi_ps_get_next_namestring has increased the AML pointer past
+			 * the method invocation namestring, so we need to restore the
+			 * saved AML pointer back to the original method invocation
+			 * namestring.
 			 */
 			walk_state->parser_state.aml = start;
 			walk_state->arg_count = 1;
 			acpi_ps_init_op(arg, AML_INT_METHODCALL_OP);
-			return_ACPI_STATUS(AE_OK);
 		}
 
 		/* This name is actually a control method invocation */
 
 		method_desc = acpi_ns_get_attached_object(node);
 		ACPI_DEBUG_PRINT((ACPI_DB_PARSE,
-				  "Control Method - %p Desc %p Path=%p\n", node,
-				  method_desc, path));
+				  "Control Method invocation %4.4s - %p Desc %p Path=%p\n",
+				  node->name.ascii, node, method_desc, path));
 
 		name_op = acpi_ps_alloc_op(AML_INT_NAMEPATH_OP, start);
 		if (!name_op) {
@@ -719,6 +723,10 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 
 	ACPI_FUNCTION_TRACE_PTR(ps_get_next_arg, parser_state);
 
+	ACPI_DEBUG_PRINT((ACPI_DB_PARSE,
+			  "Expected argument type ARGP: %s (%2.2X)\n",
+			  acpi_ut_get_argument_type_name(arg_type), arg_type));
+
 	switch (arg_type) {
 	case ARGP_BYTEDATA:
 	case ARGP_WORDDATA:
@@ -796,11 +804,14 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 		}
 		break;
 
-	case ARGP_TARGET:
-	case ARGP_SUPERNAME:
 	case ARGP_SIMPLENAME:
 	case ARGP_NAME_OR_REF:
 
+		ACPI_DEBUG_PRINT((ACPI_DB_PARSE,
+				  "**** SimpleName/NameOrRef: %s (%2.2X)\n",
+				  acpi_ut_get_argument_type_name(arg_type),
+				  arg_type));
+
 		subop = acpi_ps_peek_opcode(parser_state);
 		if (subop == 0 ||
 		    acpi_ps_is_leading_char(subop) ||
@@ -816,28 +827,49 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 				return_ACPI_STATUS(AE_NO_MEMORY);
 			}
 
-			/* To support super_name arg of Unload */
-
-			if (walk_state->opcode == AML_UNLOAD_OP) {
-				status =
-				    acpi_ps_get_next_namepath(walk_state,
-							      parser_state, arg,
-							      ACPI_POSSIBLE_METHOD_CALL);
-
-				/*
-				 * If the super_name argument is a method call, we have
-				 * already restored the AML pointer, just free this Arg
-				 */
-				if (arg->common.aml_opcode ==
-				    AML_INT_METHODCALL_OP) {
-					acpi_ps_free_op(arg);
-					arg = NULL;
-				}
-			} else {
-				status =
-				    acpi_ps_get_next_namepath(walk_state,
-							      parser_state, arg,
-							      ACPI_NOT_METHOD_CALL);
+			status =
+			    acpi_ps_get_next_namepath(walk_state, parser_state,
+						      arg,
+						      ACPI_NOT_METHOD_CALL);
+		} else {
+			/* Single complex argument, nothing returned */
+
+			walk_state->arg_count = 1;
+		}
+		break;
+
+	case ARGP_TARGET:
+	case ARGP_SUPERNAME:
+
+		ACPI_DEBUG_PRINT((ACPI_DB_PARSE,
+				  "**** Target/Supername: %s (%2.2X)\n",
+				  acpi_ut_get_argument_type_name(arg_type),
+				  arg_type));
+
+		subop = acpi_ps_peek_opcode(parser_state);
+		if (subop == 0 ||
+		    acpi_ps_is_leading_char(subop) ||
+		    ACPI_IS_ROOT_PREFIX(subop) ||
+		    ACPI_IS_PARENT_PREFIX(subop)) {
+
+			/* NULL target (zero). Convert to a NULL namepath */
+
+			arg =
+			    acpi_ps_alloc_op(AML_INT_NAMEPATH_OP,
+					     parser_state->aml);
+			if (!arg) {
+				return_ACPI_STATUS(AE_NO_MEMORY);
+			}
+
+			status =
+			    acpi_ps_get_next_namepath(walk_state, parser_state,
+						      arg,
+						      ACPI_POSSIBLE_METHOD_CALL);
+
+			if (arg->common.aml_opcode == AML_INT_METHODCALL_OP) {
+				acpi_ps_free_op(arg);
+				arg = NULL;
+				walk_state->arg_count = 1;
 			}
 		} else {
 			/* Single complex argument, nothing returned */
@@ -849,6 +881,11 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state,
 	case ARGP_DATAOBJ:
 	case ARGP_TERMARG:
 
+		ACPI_DEBUG_PRINT((ACPI_DB_PARSE,
+				  "**** TermArg/DataObj: %s (%2.2X)\n",
+				  acpi_ut_get_argument_type_name(arg_type),
+				  arg_type));
+
 		/* Single complex argument, nothing returned */
 
 		walk_state->arg_count = 1;
diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c
index 6a9f5059f682..14d689606d2f 100644
--- a/drivers/acpi/acpica/psloop.c
+++ b/drivers/acpi/acpica/psloop.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -92,6 +92,10 @@ acpi_ps_get_arguments(struct acpi_walk_state *walk_state,
 
 	ACPI_FUNCTION_TRACE_PTR(ps_get_arguments, walk_state);
 
+	ACPI_DEBUG_PRINT((ACPI_DB_PARSE,
+			  "Get arguments for opcode [%s]\n",
+			  op->common.aml_op_name));
+
 	switch (op->common.aml_opcode) {
 	case AML_BYTE_OP:	/* AML_BYTEDATA_ARG */
 	case AML_WORD_OP:	/* AML_WORDDATA_ARG */
diff --git a/drivers/acpi/acpica/psobject.c b/drivers/acpi/acpica/psobject.c
index db0e90342e82..5c4aff0f4f26 100644
--- a/drivers/acpi/acpica/psobject.c
+++ b/drivers/acpi/acpica/psobject.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -348,7 +348,15 @@ acpi_ps_create_op(struct acpi_walk_state *walk_state,
 			    argument_count) {
 				op->common.flags |= ACPI_PARSEOP_TARGET;
 			}
-		} else if (parent_scope->common.aml_opcode == AML_INCREMENT_OP) {
+		}
+
+		/*
+		 * Special case for both Increment() and Decrement(), where
+		 * the lone argument is both a source and a target.
+		 */
+		else if ((parent_scope->common.aml_opcode == AML_INCREMENT_OP)
+			 || (parent_scope->common.aml_opcode ==
+			     AML_DECREMENT_OP)) {
 			op->common.flags |= ACPI_PARSEOP_TARGET;
 		}
 	}
diff --git a/drivers/acpi/acpica/psopcode.c b/drivers/acpi/acpica/psopcode.c
index 8e0c97dca01f..451b672915f1 100644
--- a/drivers/acpi/acpica/psopcode.c
+++ b/drivers/acpi/acpica/psopcode.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psopinfo.c b/drivers/acpi/acpica/psopinfo.c
index 177b05b239b7..89f95b7f26e9 100644
--- a/drivers/acpi/acpica/psopinfo.c
+++ b/drivers/acpi/acpica/psopinfo.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psparse.c b/drivers/acpi/acpica/psparse.c
index 1ce26d9f8ff6..a813bbbd5a8b 100644
--- a/drivers/acpi/acpica/psparse.c
+++ b/drivers/acpi/acpica/psparse.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psscope.c b/drivers/acpi/acpica/psscope.c
index 560c3684ef43..22d7f1d6849b 100644
--- a/drivers/acpi/acpica/psscope.c
+++ b/drivers/acpi/acpica/psscope.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/pstree.c b/drivers/acpi/acpica/pstree.c
index 0288cdbda88e..9677fff8fd47 100644
--- a/drivers/acpi/acpica/pstree.c
+++ b/drivers/acpi/acpica/pstree.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -129,10 +129,10 @@ acpi_ps_append_arg(union acpi_parse_object *op, union acpi_parse_object *arg)
 	union acpi_parse_object *prev_arg;
 	const struct acpi_opcode_info *op_info;
 
-	ACPI_FUNCTION_ENTRY();
+	ACPI_FUNCTION_TRACE(ps_append_arg);
 
 	if (!op) {
-		return;
+		return_VOID;
 	}
 
 	/* Get the info structure for this opcode */
@@ -144,7 +144,7 @@ acpi_ps_append_arg(union acpi_parse_object *op, union acpi_parse_object *arg)
 
 		ACPI_ERROR((AE_INFO, "Invalid AML Opcode: 0x%2.2X",
 			    op->common.aml_opcode));
-		return;
+		return_VOID;
 	}
 
 	/* Check if this opcode requires argument sub-objects */
@@ -153,7 +153,7 @@ acpi_ps_append_arg(union acpi_parse_object *op, union acpi_parse_object *arg)
 
 		/* Has no linked argument objects */
 
-		return;
+		return_VOID;
 	}
 
 	/* Append the argument to the linked argument list */
@@ -181,6 +181,8 @@ acpi_ps_append_arg(union acpi_parse_object *op, union acpi_parse_object *arg)
 
 		op->common.arg_list_length++;
 	}
+
+	return_VOID;
 }
 
 /*******************************************************************************
diff --git a/drivers/acpi/acpica/psutils.c b/drivers/acpi/acpica/psutils.c
index 89cb4bffcc7c..2fa38bb76a55 100644
--- a/drivers/acpi/acpica/psutils.c
+++ b/drivers/acpi/acpica/psutils.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/pswalk.c b/drivers/acpi/acpica/pswalk.c
index 04f98c0a7684..22a37c82af19 100644
--- a/drivers/acpi/acpica/pswalk.c
+++ b/drivers/acpi/acpica/pswalk.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/psxface.c b/drivers/acpi/acpica/psxface.c
index f3c87264bd1b..c88a681586bf 100644
--- a/drivers/acpi/acpica/psxface.c
+++ b/drivers/acpi/acpica/psxface.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsaddr.c b/drivers/acpi/acpica/rsaddr.c
index 492d5b011f33..a131a28bb09d 100644
--- a/drivers/acpi/acpica/rsaddr.c
+++ b/drivers/acpi/acpica/rsaddr.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rscalc.c b/drivers/acpi/acpica/rscalc.c
index f1e83addd5b4..74e47f829ccb 100644
--- a/drivers/acpi/acpica/rscalc.c
+++ b/drivers/acpi/acpica/rscalc.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rscreate.c b/drivers/acpi/acpica/rscreate.c
index 809b61c114fe..f72ff0b54a63 100644
--- a/drivers/acpi/acpica/rscreate.c
+++ b/drivers/acpi/acpica/rscreate.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsdump.c b/drivers/acpi/acpica/rsdump.c
index 5ffdb5602d8d..f4cdf8d832dc 100644
--- a/drivers/acpi/acpica/rsdump.c
+++ b/drivers/acpi/acpica/rsdump.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsdumpinfo.c b/drivers/acpi/acpica/rsdumpinfo.c
index 61e8f16c857d..8aacd28293fa 100644
--- a/drivers/acpi/acpica/rsdumpinfo.c
+++ b/drivers/acpi/acpica/rsdumpinfo.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsinfo.c b/drivers/acpi/acpica/rsinfo.c
index 8e067cb73973..475da9d6aed5 100644
--- a/drivers/acpi/acpica/rsinfo.c
+++ b/drivers/acpi/acpica/rsinfo.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsio.c b/drivers/acpi/acpica/rsio.c
index 07dfbed10d55..b7a47fbc519b 100644
--- a/drivers/acpi/acpica/rsio.c
+++ b/drivers/acpi/acpica/rsio.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsirq.c b/drivers/acpi/acpica/rsirq.c
index bc8f34590d95..092a733c42b8 100644
--- a/drivers/acpi/acpica/rsirq.c
+++ b/drivers/acpi/acpica/rsirq.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rslist.c b/drivers/acpi/acpica/rslist.c
index 8c42dd734559..36a6657dd34d 100644
--- a/drivers/acpi/acpica/rslist.c
+++ b/drivers/acpi/acpica/rslist.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsmemory.c b/drivers/acpi/acpica/rsmemory.c
index 88b53ef9105d..273eecb3001b 100644
--- a/drivers/acpi/acpica/rsmemory.c
+++ b/drivers/acpi/acpica/rsmemory.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsmisc.c b/drivers/acpi/acpica/rsmisc.c
index 25165ca42051..2ae79613f6b7 100644
--- a/drivers/acpi/acpica/rsmisc.c
+++ b/drivers/acpi/acpica/rsmisc.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsserial.c b/drivers/acpi/acpica/rsserial.c
index b82c061f205a..c20e6d07928d 100644
--- a/drivers/acpi/acpica/rsserial.c
+++ b/drivers/acpi/acpica/rsserial.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsutils.c b/drivers/acpi/acpica/rsutils.c
index fa491c64c040..b2aeca01204a 100644
--- a/drivers/acpi/acpica/rsutils.c
+++ b/drivers/acpi/acpica/rsutils.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/rsxface.c b/drivers/acpi/acpica/rsxface.c
index 465ed8137167..59a4f9ed06a7 100644
--- a/drivers/acpi/acpica/rsxface.c
+++ b/drivers/acpi/acpica/rsxface.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c
index 82b0b5710979..27c5c27d4818 100644
--- a/drivers/acpi/acpica/tbdata.c
+++ b/drivers/acpi/acpica/tbdata.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -852,23 +852,18 @@ acpi_tb_install_and_load_table(acpi_physical_address address,
 
 	ACPI_FUNCTION_TRACE(tb_install_and_load_table);
 
-	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
-
 	/* Install the table and load it into the namespace */
 
 	status = acpi_tb_install_standard_table(address, flags, TRUE,
 						override, &i);
 	if (ACPI_FAILURE(status)) {
-		goto unlock_and_exit;
+		goto exit;
 	}
 
-	(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
 	status = acpi_tb_load_table(i, acpi_gbl_root_node);
-	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
 
-unlock_and_exit:
+exit:
 	*table_index = i;
-	(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
 	return_ACPI_STATUS(status);
 }
 
diff --git a/drivers/acpi/acpica/tbfadt.c b/drivers/acpi/acpica/tbfadt.c
index 81473a4880ce..51860bfc111e 100644
--- a/drivers/acpi/acpica/tbfadt.c
+++ b/drivers/acpi/acpica/tbfadt.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c
index f6b9b4e4298b..fea89c8d305c 100644
--- a/drivers/acpi/acpica/tbfind.c
+++ b/drivers/acpi/acpica/tbfind.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index 5fdf251a9f97..4620f3c68c13 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -217,6 +217,10 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 		goto release_and_exit;
 	}
 
+	/* Acquire the table lock */
+
+	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
+
 	if (reload) {
 		/*
 		 * Validate the incoming table signature.
@@ -244,7 +248,7 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 					 new_table_desc.signature.integer));
 
 			status = AE_BAD_SIGNATURE;
-			goto release_and_exit;
+			goto unlock_and_exit;
 		}
 
 		/* Check if table is already registered */
@@ -279,7 +283,7 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 				/* Table is still loaded, this is an error */
 
 				status = AE_ALREADY_EXISTS;
-				goto release_and_exit;
+				goto unlock_and_exit;
 			} else {
 				/*
 				 * Table was unloaded, allow it to be reloaded.
@@ -290,6 +294,7 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 				 * indicate the re-installation.
 				 */
 				acpi_tb_uninstall_table(&new_table_desc);
+				(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
 				*table_index = i;
 				return_ACPI_STATUS(AE_OK);
 			}
@@ -303,11 +308,19 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 
 	/* Invoke table handler if present */
 
+	(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
 	if (acpi_gbl_table_handler) {
 		(void)acpi_gbl_table_handler(ACPI_TABLE_EVENT_INSTALL,
 					     new_table_desc.pointer,
 					     acpi_gbl_table_handler_context);
 	}
+	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
+
+unlock_and_exit:
+
+	/* Release the table lock */
+
+	(void)acpi_ut_release_mutex(ACPI_MTX_TABLES);
 
 release_and_exit:
 
diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c
index 26d61dbace0a..edfd7b10be19 100644
--- a/drivers/acpi/acpica/tbprint.c
+++ b/drivers/acpi/acpica/tbprint.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 86854e846800..5a968a78652b 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index 7684707b254b..010b1c43df92 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index 82019c01a0e5..b71ce3b817ea 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/tbxfroot.c b/drivers/acpi/acpica/tbxfroot.c
index 0adb1c78d863..f9f9a7da2cad 100644
--- a/drivers/acpi/acpica/tbxfroot.c
+++ b/drivers/acpi/acpica/tbxfroot.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c
index 433d822798b6..26a0633115be 100644
--- a/drivers/acpi/acpica/utaddress.c
+++ b/drivers/acpi/acpica/utaddress.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utalloc.c b/drivers/acpi/acpica/utalloc.c
index 13324a27b99b..a3401bd29413 100644
--- a/drivers/acpi/acpica/utalloc.c
+++ b/drivers/acpi/acpica/utalloc.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utascii.c b/drivers/acpi/acpica/utascii.c
index 706c1f346490..909bdb198651 100644
--- a/drivers/acpi/acpica/utascii.c
+++ b/drivers/acpi/acpica/utascii.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utbuffer.c b/drivers/acpi/acpica/utbuffer.c
index ff2981275b9a..f17eaa009dde 100644
--- a/drivers/acpi/acpica/utbuffer.c
+++ b/drivers/acpi/acpica/utbuffer.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utcache.c b/drivers/acpi/acpica/utcache.c
index 3b8d23ef351f..11c7f72f2d56 100644
--- a/drivers/acpi/acpica/utcache.c
+++ b/drivers/acpi/acpica/utcache.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utcopy.c b/drivers/acpi/acpica/utcopy.c
index 82f971402d85..e9382255d6c6 100644
--- a/drivers/acpi/acpica/utcopy.c
+++ b/drivers/acpi/acpica/utcopy.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c
index 044df9b0356e..bd5ea3101eb7 100644
--- a/drivers/acpi/acpica/utdebug.c
+++ b/drivers/acpi/acpica/utdebug.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index b3d8421cfb80..60868309e326 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -238,7 +238,7 @@ const char *acpi_ut_get_object_type_name(union acpi_operand_object *obj_desc)
 
 	if (!obj_desc) {
 		ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Null Object Descriptor\n"));
-		return_PTR("[NULL Object Descriptor]");
+		return_STR("[NULL Object Descriptor]");
 	}
 
 	/* These descriptor types share a common area */
@@ -251,7 +251,7 @@ const char *acpi_ut_get_object_type_name(union acpi_operand_object *obj_desc)
 				  acpi_ut_get_descriptor_name(obj_desc),
 				  obj_desc));
 
-		return_PTR("Invalid object");
+		return_STR("Invalid object");
 	}
 
 	return_STR(acpi_ut_get_type_name(obj_desc->common.type));
diff --git a/drivers/acpi/acpica/utdelete.c b/drivers/acpi/acpica/utdelete.c
index 529d6c38ea7c..c6eb9fae70f9 100644
--- a/drivers/acpi/acpica/utdelete.c
+++ b/drivers/acpi/acpica/utdelete.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -421,8 +421,10 @@ acpi_ut_update_ref_count(union acpi_operand_object *object, u32 action)
 		}
 
 		ACPI_DEBUG_PRINT((ACPI_DB_ALLOCATIONS,
-				  "Obj %p Type %.2X Refs %.2X [Incremented]\n",
-				  object, object->common.type, new_count));
+				  "Obj %p Type %.2X [%s] Refs %.2X [Incremented]\n",
+				  object, object->common.type,
+				  acpi_ut_get_object_type_name(object),
+				  new_count));
 		break;
 
 	case REF_DECREMENT:
diff --git a/drivers/acpi/acpica/uterror.c b/drivers/acpi/acpica/uterror.c
index 475932cecf1a..e3368186e1c1 100644
--- a/drivers/acpi/acpica/uterror.c
+++ b/drivers/acpi/acpica/uterror.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/uteval.c b/drivers/acpi/acpica/uteval.c
index 7bad13f2e518..3fce7519c690 100644
--- a/drivers/acpi/acpica/uteval.c
+++ b/drivers/acpi/acpica/uteval.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utexcep.c b/drivers/acpi/acpica/utexcep.c
index 695240338e00..eb6dcab33d2f 100644
--- a/drivers/acpi/acpica/utexcep.c
+++ b/drivers/acpi/acpica/utexcep.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utglobal.c b/drivers/acpi/acpica/utglobal.c
index dd3fd7f97f8e..230a50c82f22 100644
--- a/drivers/acpi/acpica/utglobal.c
+++ b/drivers/acpi/acpica/utglobal.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/uthex.c b/drivers/acpi/acpica/uthex.c
index 36d2fc789088..6600bc257516 100644
--- a/drivers/acpi/acpica/uthex.c
+++ b/drivers/acpi/acpica/uthex.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utids.c b/drivers/acpi/acpica/utids.c
index f7cd2d52643b..a6eb580ee21d 100644
--- a/drivers/acpi/acpica/utids.c
+++ b/drivers/acpi/acpica/utids.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utinit.c b/drivers/acpi/acpica/utinit.c
index 1711fdf41709..23e766d1691d 100644
--- a/drivers/acpi/acpica/utinit.c
+++ b/drivers/acpi/acpica/utinit.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utlock.c b/drivers/acpi/acpica/utlock.c
index 3cd0978925ef..db2d9910866e 100644
--- a/drivers/acpi/acpica/utlock.c
+++ b/drivers/acpi/acpica/utlock.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utmath.c b/drivers/acpi/acpica/utmath.c
index 2d6530ee7e51..aa0502d1d019 100644
--- a/drivers/acpi/acpica/utmath.c
+++ b/drivers/acpi/acpica/utmath.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utmisc.c b/drivers/acpi/acpica/utmisc.c
index 389de3bd1ff1..443ffad01209 100644
--- a/drivers/acpi/acpica/utmisc.c
+++ b/drivers/acpi/acpica/utmisc.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index 15073375bd00..586354788018 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utnonansi.c b/drivers/acpi/acpica/utnonansi.c
index 2514239282c2..792664982ea3 100644
--- a/drivers/acpi/acpica/utnonansi.c
+++ b/drivers/acpi/acpica/utnonansi.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utobject.c b/drivers/acpi/acpica/utobject.c
index 72b9a062bbab..64e6641bfe82 100644
--- a/drivers/acpi/acpica/utobject.c
+++ b/drivers/acpi/acpica/utobject.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c
index f0484b058c44..3175b133c0e4 100644
--- a/drivers/acpi/acpica/utosi.c
+++ b/drivers/acpi/acpica/utosi.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utownerid.c b/drivers/acpi/acpica/utownerid.c
index 3cd573c5f7f9..c82399f9b456 100644
--- a/drivers/acpi/acpica/utownerid.c
+++ b/drivers/acpi/acpica/utownerid.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c
index ce18346b6144..350709f23e4c 100644
--- a/drivers/acpi/acpica/utpredef.c
+++ b/drivers/acpi/acpica/utpredef.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utprint.c b/drivers/acpi/acpica/utprint.c
index 40eba804d49c..7e6e1ae6140f 100644
--- a/drivers/acpi/acpica/utprint.c
+++ b/drivers/acpi/acpica/utprint.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utresrc.c b/drivers/acpi/acpica/utresrc.c
index 1de3376da66a..c86bae7b1d0f 100644
--- a/drivers/acpi/acpica/utresrc.c
+++ b/drivers/acpi/acpica/utresrc.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -421,8 +421,10 @@ acpi_ut_walk_aml_resources(struct acpi_walk_state *walk_state,
 
 	ACPI_FUNCTION_TRACE(ut_walk_aml_resources);
 
-	/* The absolute minimum resource template is one end_tag descriptor */
-
+	/*
+	 * The absolute minimum resource template is one end_tag descriptor.
+	 * However, we will treat a lone end_tag as just a simple buffer.
+	 */
 	if (aml_length < sizeof(struct aml_resource_end_tag)) {
 		return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG);
 	}
@@ -454,9 +456,8 @@ acpi_ut_walk_aml_resources(struct acpi_walk_state *walk_state,
 		/* Invoke the user function */
 
 		if (user_function) {
-			status =
-			    user_function(aml, length, offset, resource_index,
-					  context);
+			status = user_function(aml, length, offset,
+					       resource_index, context);
 			if (ACPI_FAILURE(status)) {
 				return_ACPI_STATUS(status);
 			}
@@ -480,6 +481,12 @@ acpi_ut_walk_aml_resources(struct acpi_walk_state *walk_state,
 				*context = aml;
 			}
 
+			/* Check if buffer is defined to be longer than the resource length */
+
+			if (aml_length > (offset + length)) {
+				return_ACPI_STATUS(AE_AML_NO_RESOURCE_END_TAG);
+			}
+
 			/* Normal exit */
 
 			return_ACPI_STATUS(AE_OK);
diff --git a/drivers/acpi/acpica/utstate.c b/drivers/acpi/acpica/utstate.c
index f3d4dbd5fac0..64308c304ade 100644
--- a/drivers/acpi/acpica/utstate.c
+++ b/drivers/acpi/acpica/utstate.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index 288913a0e709..9eacbcb9e4f4 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utstrtoul64.c b/drivers/acpi/acpica/utstrtoul64.c
index b4f341c98a95..f42be01d99fd 100644
--- a/drivers/acpi/acpica/utstrtoul64.c
+++ b/drivers/acpi/acpica/utstrtoul64.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/uttrack.c b/drivers/acpi/acpica/uttrack.c
index df31d71ce596..9a07a42cae34 100644
--- a/drivers/acpi/acpica/uttrack.c
+++ b/drivers/acpi/acpica/uttrack.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utuuid.c b/drivers/acpi/acpica/utuuid.c
index 81088ff9d67b..5028e06718b1 100644
--- a/drivers/acpi/acpica/utuuid.c
+++ b/drivers/acpi/acpica/utuuid.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utxface.c b/drivers/acpi/acpica/utxface.c
index ec503c862961..6b9ba4029f8e 100644
--- a/drivers/acpi/acpica/utxface.c
+++ b/drivers/acpi/acpica/utxface.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utxferror.c b/drivers/acpi/acpica/utxferror.c
index d9f15cbcd8a0..a16bd9eac653 100644
--- a/drivers/acpi/acpica/utxferror.c
+++ b/drivers/acpi/acpica/utxferror.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utxfinit.c b/drivers/acpi/acpica/utxfinit.c
index a5ca0f57cd08..6d5180601cf2 100644
--- a/drivers/acpi/acpica/utxfinit.c
+++ b/drivers/acpi/acpica/utxfinit.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/acpica/utxfmutex.c b/drivers/acpi/acpica/utxfmutex.c
index 850de0155528..c016211c35ae 100644
--- a/drivers/acpi/acpica/utxfmutex.c
+++ b/drivers/acpi/acpica/utxfmutex.c
@@ -5,7 +5,7 @@
  ******************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index eebb7e39c49c..ec50c32ea3da 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -711,7 +711,7 @@ static int __init einj_init(void)
 
 	rc = einj_check_table(einj_tab);
 	if (rc) {
-		pr_warn(FW_BUG "Invalid EINJ table.n");
+		pr_warn(FW_BUG "Invalid EINJ table.\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index e0d2e6e6e40c..3752521c62ab 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -536,7 +536,7 @@ static const struct iommu_ops *iort_iommu_xlate(struct device *dev,
 		if (!iort_fwnode)
 			return NULL;
 
-		ops = iommu_get_instance(iort_fwnode);
+		ops = iommu_ops_from_fwnode(iort_fwnode);
 		if (!ops)
 			return NULL;
 
diff --git a/drivers/acpi/bgrt.c b/drivers/acpi/bgrt.c
index 75f128e766a9..ca28aa572aa9 100644
--- a/drivers/acpi/bgrt.c
+++ b/drivers/acpi/bgrt.c
@@ -15,40 +15,41 @@
 #include <linux/sysfs.h>
 #include <linux/efi-bgrt.h>
 
+static void *bgrt_image;
 static struct kobject *bgrt_kobj;
 
 static ssize_t show_version(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->version);
+	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.version);
 }
 static DEVICE_ATTR(version, S_IRUGO, show_version, NULL);
 
 static ssize_t show_status(struct device *dev,
 			   struct device_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->status);
+	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.status);
 }
 static DEVICE_ATTR(status, S_IRUGO, show_status, NULL);
 
 static ssize_t show_type(struct device *dev,
 			 struct device_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_type);
+	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_type);
 }
 static DEVICE_ATTR(type, S_IRUGO, show_type, NULL);
 
 static ssize_t show_xoffset(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_offset_x);
+	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_offset_x);
 }
 static DEVICE_ATTR(xoffset, S_IRUGO, show_xoffset, NULL);
 
 static ssize_t show_yoffset(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab->image_offset_y);
+	return snprintf(buf, PAGE_SIZE, "%d\n", bgrt_tab.image_offset_y);
 }
 static DEVICE_ATTR(yoffset, S_IRUGO, show_yoffset, NULL);
 
@@ -84,15 +85,24 @@ static int __init bgrt_init(void)
 {
 	int ret;
 
-	if (!bgrt_image)
+	if (!bgrt_tab.image_address)
 		return -ENODEV;
 
+	bgrt_image = memremap(bgrt_tab.image_address, bgrt_image_size,
+			      MEMREMAP_WB);
+	if (!bgrt_image) {
+		pr_notice("Ignoring BGRT: failed to map image memory\n");
+		return -ENOMEM;
+	}
+
 	bin_attr_image.private = bgrt_image;
 	bin_attr_image.size = bgrt_image_size;
 
 	bgrt_kobj = kobject_create_and_add("bgrt", acpi_kobj);
-	if (!bgrt_kobj)
-		return -EINVAL;
+	if (!bgrt_kobj) {
+		ret = -EINVAL;
+		goto out_memmap;
+	}
 
 	ret = sysfs_create_group(bgrt_kobj, &bgrt_attribute_group);
 	if (ret)
@@ -102,6 +112,8 @@ static int __init bgrt_init(void)
 
 out_kobject:
 	kobject_put(bgrt_kobj);
+out_memmap:
+	memunmap(bgrt_image);
 	return ret;
 }
 device_initcall(bgrt_init);
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 95855cb9d6fb..80cb5eb75b63 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -677,6 +677,48 @@ static bool acpi_of_match_device(struct acpi_device *adev,
 	return false;
 }
 
+static bool acpi_of_modalias(struct acpi_device *adev,
+			     char *modalias, size_t len)
+{
+	const union acpi_object *of_compatible;
+	const union acpi_object *obj;
+	const char *str, *chr;
+
+	of_compatible = adev->data.of_compatible;
+	if (!of_compatible)
+		return false;
+
+	if (of_compatible->type == ACPI_TYPE_PACKAGE)
+		obj = of_compatible->package.elements;
+	else /* Must be ACPI_TYPE_STRING. */
+		obj = of_compatible;
+
+	str = obj->string.pointer;
+	chr = strchr(str, ',');
+	strlcpy(modalias, chr ? chr + 1 : str, len);
+
+	return true;
+}
+
+/**
+ * acpi_set_modalias - Set modalias using "compatible" property or supplied ID
+ * @adev:	ACPI device object to match
+ * @default_id:	ID string to use as default if no compatible string found
+ * @modalias:   Pointer to buffer that modalias value will be copied into
+ * @len:	Length of modalias buffer
+ *
+ * This is a counterpart of of_modalias_node() for struct acpi_device objects.
+ * If there is a compatible string for @adev, it will be copied to @modalias
+ * with the vendor prefix stripped; otherwise, @default_id will be used.
+ */
+void acpi_set_modalias(struct acpi_device *adev, const char *default_id,
+		       char *modalias, size_t len)
+{
+	if (!acpi_of_modalias(adev, modalias, len))
+		strlcpy(modalias, default_id, len);
+}
+EXPORT_SYMBOL_GPL(acpi_set_modalias);
+
 static bool __acpi_match_device_cls(const struct acpi_device_id *id,
 				    struct acpi_hardware_id *hwid)
 {
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index e19f530f1083..668137e4a069 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -57,7 +57,6 @@
 
 #define ACPI_BUTTON_LID_INIT_IGNORE	0x00
 #define ACPI_BUTTON_LID_INIT_OPEN	0x01
-#define ACPI_BUTTON_LID_INIT_METHOD	0x02
 
 #define _COMPONENT		ACPI_BUTTON_COMPONENT
 ACPI_MODULE_NAME("button");
@@ -113,7 +112,7 @@ struct acpi_button {
 
 static BLOCKING_NOTIFIER_HEAD(acpi_lid_notifier);
 static struct acpi_device *lid_device;
-static u8 lid_init_state = ACPI_BUTTON_LID_INIT_METHOD;
+static u8 lid_init_state = ACPI_BUTTON_LID_INIT_OPEN;
 
 static unsigned long lid_report_interval __read_mostly = 500;
 module_param(lid_report_interval, ulong, 0644);
@@ -377,9 +376,6 @@ static void acpi_lid_initialize_state(struct acpi_device *device)
 	case ACPI_BUTTON_LID_INIT_OPEN:
 		(void)acpi_lid_notify_state(device, 1);
 		break;
-	case ACPI_BUTTON_LID_INIT_METHOD:
-		(void)acpi_lid_update_state(device);
-		break;
 	case ACPI_BUTTON_LID_INIT_IGNORE:
 	default:
 		break;
@@ -563,9 +559,6 @@ static int param_set_lid_init_state(const char *val, struct kernel_param *kp)
 	if (!strncmp(val, "open", sizeof("open") - 1)) {
 		lid_init_state = ACPI_BUTTON_LID_INIT_OPEN;
 		pr_info("Notify initial lid state as open\n");
-	} else if (!strncmp(val, "method", sizeof("method") - 1)) {
-		lid_init_state = ACPI_BUTTON_LID_INIT_METHOD;
-		pr_info("Notify initial lid state with _LID return value\n");
 	} else if (!strncmp(val, "ignore", sizeof("ignore") - 1)) {
 		lid_init_state = ACPI_BUTTON_LID_INIT_IGNORE;
 		pr_info("Do not notify initial lid state\n");
@@ -579,8 +572,6 @@ static int param_get_lid_init_state(char *buffer, struct kernel_param *kp)
 	switch (lid_init_state) {
 	case ACPI_BUTTON_LID_INIT_OPEN:
 		return sprintf(buffer, "open");
-	case ACPI_BUTTON_LID_INIT_METHOD:
-		return sprintf(buffer, "method");
 	case ACPI_BUTTON_LID_INIT_IGNORE:
 		return sprintf(buffer, "ignore");
 	default:
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 48e19d013170..c24235d8fb52 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -188,7 +188,6 @@ EXPORT_SYMBOL(first_ec);
 static bool boot_ec_is_ecdt = false;
 static struct workqueue_struct *ec_query_wq;
 
-static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */
 static int EC_FLAGS_QUERY_HANDSHAKE; /* Needs QR_EC issued when SCI_EVT set */
 static int EC_FLAGS_CORRECT_ECDT; /* Needs ECDT port address correction */
 
@@ -492,26 +491,6 @@ static inline void __acpi_ec_disable_event(struct acpi_ec *ec)
 		ec_log_drv("event blocked");
 }
 
-/*
- * Process _Q events that might have accumulated in the EC.
- * Run with locked ec mutex.
- */
-static void acpi_ec_clear(struct acpi_ec *ec)
-{
-	int i, status;
-	u8 value = 0;
-
-	for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) {
-		status = acpi_ec_query(ec, &value);
-		if (status || !value)
-			break;
-	}
-	if (unlikely(i == ACPI_EC_CLEAR_MAX))
-		pr_warn("Warning: Maximum of %d stale EC events cleared\n", i);
-	else
-		pr_info("%d stale EC events cleared\n", i);
-}
-
 static void acpi_ec_enable_event(struct acpi_ec *ec)
 {
 	unsigned long flags;
@@ -520,10 +499,6 @@ static void acpi_ec_enable_event(struct acpi_ec *ec)
 	if (acpi_ec_started(ec))
 		__acpi_ec_enable_event(ec);
 	spin_unlock_irqrestore(&ec->lock, flags);
-
-	/* Drain additional events if hardware requires that */
-	if (EC_FLAGS_CLEAR_ON_RESUME)
-		acpi_ec_clear(ec);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -729,12 +704,12 @@ static void start_transaction(struct acpi_ec *ec)
 
 static int ec_guard(struct acpi_ec *ec)
 {
-	unsigned long guard = usecs_to_jiffies(ec_polling_guard);
+	unsigned long guard = usecs_to_jiffies(ec->polling_guard);
 	unsigned long timeout = ec->timestamp + guard;
 
 	/* Ensure guarding period before polling EC status */
 	do {
-		if (ec_busy_polling) {
+		if (ec->busy_polling) {
 			/* Perform busy polling */
 			if (ec_transaction_completed(ec))
 				return 0;
@@ -998,6 +973,28 @@ static void acpi_ec_stop(struct acpi_ec *ec, bool suspending)
 	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
+static void acpi_ec_enter_noirq(struct acpi_ec *ec)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
+	ec->busy_polling = true;
+	ec->polling_guard = 0;
+	ec_log_drv("interrupt blocked");
+	spin_unlock_irqrestore(&ec->lock, flags);
+}
+
+static void acpi_ec_leave_noirq(struct acpi_ec *ec)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ec->lock, flags);
+	ec->busy_polling = ec_busy_polling;
+	ec->polling_guard = ec_polling_guard;
+	ec_log_drv("interrupt unblocked");
+	spin_unlock_irqrestore(&ec->lock, flags);
+}
+
 void acpi_ec_block_transactions(void)
 {
 	struct acpi_ec *ec = first_ec;
@@ -1278,7 +1275,7 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 	if (function != ACPI_READ && function != ACPI_WRITE)
 		return AE_BAD_PARAMETER;
 
-	if (ec_busy_polling || bits > 8)
+	if (ec->busy_polling || bits > 8)
 		acpi_ec_burst_enable(ec);
 
 	for (i = 0; i < bytes; ++i, ++address, ++value)
@@ -1286,7 +1283,7 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address,
 			acpi_ec_read(ec, address, value) :
 			acpi_ec_write(ec, address, *value);
 
-	if (ec_busy_polling || bits > 8)
+	if (ec->busy_polling || bits > 8)
 		acpi_ec_burst_disable(ec);
 
 	switch (result) {
@@ -1329,6 +1326,8 @@ static struct acpi_ec *acpi_ec_alloc(void)
 	spin_lock_init(&ec->lock);
 	INIT_WORK(&ec->work, acpi_ec_event_handler);
 	ec->timestamp = jiffies;
+	ec->busy_polling = true;
+	ec->polling_guard = 0;
 	return ec;
 }
 
@@ -1390,6 +1389,7 @@ static int ec_install_handlers(struct acpi_ec *ec, bool handle_events)
 	acpi_ec_start(ec, false);
 
 	if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) {
+		acpi_ec_enter_noirq(ec);
 		status = acpi_install_address_space_handler(ec->handle,
 							    ACPI_ADR_SPACE_EC,
 							    &acpi_ec_space_handler,
@@ -1429,6 +1429,7 @@ static int ec_install_handlers(struct acpi_ec *ec, bool handle_events)
 		/* This is not fatal as we can poll EC events */
 		if (ACPI_SUCCESS(status)) {
 			set_bit(EC_FLAGS_GPE_HANDLER_INSTALLED, &ec->flags);
+			acpi_ec_leave_noirq(ec);
 			if (test_bit(EC_FLAGS_STARTED, &ec->flags) &&
 			    ec->reference_count >= 1)
 				acpi_ec_enable_gpe(ec, true);
@@ -1741,31 +1742,6 @@ static int ec_flag_query_handshake(const struct dmi_system_id *id)
 #endif
 
 /*
- * On some hardware it is necessary to clear events accumulated by the EC during
- * sleep. These ECs stop reporting GPEs until they are manually polled, if too
- * many events are accumulated. (e.g. Samsung Series 5/9 notebooks)
- *
- * https://bugzilla.kernel.org/show_bug.cgi?id=44161
- *
- * Ideally, the EC should also be instructed NOT to accumulate events during
- * sleep (which Windows seems to do somehow), but the interface to control this
- * behaviour is not known at this time.
- *
- * Models known to be affected are Samsung 530Uxx/535Uxx/540Uxx/550Pxx/900Xxx,
- * however it is very likely that other Samsung models are affected.
- *
- * On systems which don't accumulate _Q events during sleep, this extra check
- * should be harmless.
- */
-static int ec_clear_on_resume(const struct dmi_system_id *id)
-{
-	pr_debug("Detected system needing EC poll on resume.\n");
-	EC_FLAGS_CLEAR_ON_RESUME = 1;
-	ec_event_clearing = ACPI_EC_EVT_TIMING_STATUS;
-	return 0;
-}
-
-/*
  * Some ECDTs contain wrong register addresses.
  * MSI MS-171F
  * https://bugzilla.kernel.org/show_bug.cgi?id=12461
@@ -1782,9 +1758,6 @@ static struct dmi_system_id ec_dmi_table[] __initdata = {
 	ec_correct_ecdt, "MSI MS-171F", {
 	DMI_MATCH(DMI_SYS_VENDOR, "Micro-Star"),
 	DMI_MATCH(DMI_PRODUCT_NAME, "MS-171F"),}, NULL},
-	{
-	ec_clear_on_resume, "Samsung hardware", {
-	DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD.")}, NULL},
 	{},
 };
 
@@ -1839,34 +1812,6 @@ error:
 }
 
 #ifdef CONFIG_PM_SLEEP
-static void acpi_ec_enter_noirq(struct acpi_ec *ec)
-{
-	unsigned long flags;
-
-	if (ec == first_ec) {
-		spin_lock_irqsave(&ec->lock, flags);
-		ec->saved_busy_polling = ec_busy_polling;
-		ec->saved_polling_guard = ec_polling_guard;
-		ec_busy_polling = true;
-		ec_polling_guard = 0;
-		ec_log_drv("interrupt blocked");
-		spin_unlock_irqrestore(&ec->lock, flags);
-	}
-}
-
-static void acpi_ec_leave_noirq(struct acpi_ec *ec)
-{
-	unsigned long flags;
-
-	if (ec == first_ec) {
-		spin_lock_irqsave(&ec->lock, flags);
-		ec_busy_polling = ec->saved_busy_polling;
-		ec_polling_guard = ec->saved_polling_guard;
-		ec_log_drv("interrupt unblocked");
-		spin_unlock_irqrestore(&ec->lock, flags);
-	}
-}
-
 static int acpi_ec_suspend_noirq(struct device *dev)
 {
 	struct acpi_ec *ec =
diff --git a/drivers/acpi/gsi.c b/drivers/acpi/gsi.c
deleted file mode 100644
index ee9e0f27b2bf..000000000000
--- a/drivers/acpi/gsi.c
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * ACPI GSI IRQ layer
- *
- * Copyright (C) 2015 ARM Ltd.
- * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/acpi.h>
-#include <linux/irq.h>
-#include <linux/irqdomain.h>
-#include <linux/of.h>
-
-enum acpi_irq_model_id acpi_irq_model;
-
-static struct fwnode_handle *acpi_gsi_domain_id;
-
-/**
- * acpi_gsi_to_irq() - Retrieve the linux irq number for a given GSI
- * @gsi: GSI IRQ number to map
- * @irq: pointer where linux IRQ number is stored
- *
- * irq location updated with irq value [>0 on success, 0 on failure]
- *
- * Returns: linux IRQ number on success (>0)
- *          -EINVAL on failure
- */
-int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
-{
-	struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id,
-							DOMAIN_BUS_ANY);
-
-	*irq = irq_find_mapping(d, gsi);
-	/*
-	 * *irq == 0 means no mapping, that should
-	 * be reported as a failure
-	 */
-	return (*irq > 0) ? *irq : -EINVAL;
-}
-EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
-
-/**
- * acpi_register_gsi() - Map a GSI to a linux IRQ number
- * @dev: device for which IRQ has to be mapped
- * @gsi: GSI IRQ number
- * @trigger: trigger type of the GSI number to be mapped
- * @polarity: polarity of the GSI to be mapped
- *
- * Returns: a valid linux IRQ number on success
- *          -EINVAL on failure
- */
-int acpi_register_gsi(struct device *dev, u32 gsi, int trigger,
-		      int polarity)
-{
-	struct irq_fwspec fwspec;
-
-	if (WARN_ON(!acpi_gsi_domain_id)) {
-		pr_warn("GSI: No registered irqchip, giving up\n");
-		return -EINVAL;
-	}
-
-	fwspec.fwnode = acpi_gsi_domain_id;
-	fwspec.param[0] = gsi;
-	fwspec.param[1] = acpi_dev_get_irq_type(trigger, polarity);
-	fwspec.param_count = 2;
-
-	return irq_create_fwspec_mapping(&fwspec);
-}
-EXPORT_SYMBOL_GPL(acpi_register_gsi);
-
-/**
- * acpi_unregister_gsi() - Free a GSI<->linux IRQ number mapping
- * @gsi: GSI IRQ number
- */
-void acpi_unregister_gsi(u32 gsi)
-{
-	struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id,
-							DOMAIN_BUS_ANY);
-	int irq = irq_find_mapping(d, gsi);
-
-	irq_dispose_mapping(irq);
-}
-EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
-
-/**
- * acpi_set_irq_model - Setup the GSI irqdomain information
- * @model: the value assigned to acpi_irq_model
- * @fwnode: the irq_domain identifier for mapping and looking up
- *          GSI interrupts
- */
-void __init acpi_set_irq_model(enum acpi_irq_model_id model,
-			       struct fwnode_handle *fwnode)
-{
-	acpi_irq_model = model;
-	acpi_gsi_domain_id = fwnode;
-}
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 0c452265c111..219b90bc0922 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -172,8 +172,8 @@ struct acpi_ec {
 	struct work_struct work;
 	unsigned long timestamp;
 	unsigned long nr_pending_queries;
-	bool saved_busy_polling;
-	unsigned int saved_polling_guard;
+	bool busy_polling;
+	unsigned int polling_guard;
 };
 
 extern struct acpi_ec *first_ec;
diff --git a/drivers/acpi/irq.c b/drivers/acpi/irq.c
new file mode 100644
index 000000000000..830299a74b84
--- /dev/null
+++ b/drivers/acpi/irq.c
@@ -0,0 +1,297 @@
+/*
+ * ACPI GSI IRQ layer
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/acpi.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
+#include <linux/of.h>
+
+enum acpi_irq_model_id acpi_irq_model;
+
+static struct fwnode_handle *acpi_gsi_domain_id;
+
+/**
+ * acpi_gsi_to_irq() - Retrieve the linux irq number for a given GSI
+ * @gsi: GSI IRQ number to map
+ * @irq: pointer where linux IRQ number is stored
+ *
+ * irq location updated with irq value [>0 on success, 0 on failure]
+ *
+ * Returns: linux IRQ number on success (>0)
+ *          -EINVAL on failure
+ */
+int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
+{
+	struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id,
+							DOMAIN_BUS_ANY);
+
+	*irq = irq_find_mapping(d, gsi);
+	/*
+	 * *irq == 0 means no mapping, that should
+	 * be reported as a failure
+	 */
+	return (*irq > 0) ? *irq : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
+
+/**
+ * acpi_register_gsi() - Map a GSI to a linux IRQ number
+ * @dev: device for which IRQ has to be mapped
+ * @gsi: GSI IRQ number
+ * @trigger: trigger type of the GSI number to be mapped
+ * @polarity: polarity of the GSI to be mapped
+ *
+ * Returns: a valid linux IRQ number on success
+ *          -EINVAL on failure
+ */
+int acpi_register_gsi(struct device *dev, u32 gsi, int trigger,
+		      int polarity)
+{
+	struct irq_fwspec fwspec;
+
+	if (WARN_ON(!acpi_gsi_domain_id)) {
+		pr_warn("GSI: No registered irqchip, giving up\n");
+		return -EINVAL;
+	}
+
+	fwspec.fwnode = acpi_gsi_domain_id;
+	fwspec.param[0] = gsi;
+	fwspec.param[1] = acpi_dev_get_irq_type(trigger, polarity);
+	fwspec.param_count = 2;
+
+	return irq_create_fwspec_mapping(&fwspec);
+}
+EXPORT_SYMBOL_GPL(acpi_register_gsi);
+
+/**
+ * acpi_unregister_gsi() - Free a GSI<->linux IRQ number mapping
+ * @gsi: GSI IRQ number
+ */
+void acpi_unregister_gsi(u32 gsi)
+{
+	struct irq_domain *d = irq_find_matching_fwnode(acpi_gsi_domain_id,
+							DOMAIN_BUS_ANY);
+	int irq = irq_find_mapping(d, gsi);
+
+	irq_dispose_mapping(irq);
+}
+EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
+
+/**
+ * acpi_get_irq_source_fwhandle() - Retrieve fwhandle from IRQ resource source.
+ * @source: acpi_resource_source to use for the lookup.
+ *
+ * Description:
+ * Retrieve the fwhandle of the device referenced by the given IRQ resource
+ * source.
+ *
+ * Return:
+ * The referenced device fwhandle or NULL on failure
+ */
+static struct fwnode_handle *
+acpi_get_irq_source_fwhandle(const struct acpi_resource_source *source)
+{
+	struct fwnode_handle *result;
+	struct acpi_device *device;
+	acpi_handle handle;
+	acpi_status status;
+
+	if (!source->string_length)
+		return acpi_gsi_domain_id;
+
+	status = acpi_get_handle(NULL, source->string_ptr, &handle);
+	if (WARN_ON(ACPI_FAILURE(status)))
+		return NULL;
+
+	device = acpi_bus_get_acpi_device(handle);
+	if (WARN_ON(!device))
+		return NULL;
+
+	result = &device->fwnode;
+	acpi_bus_put_acpi_device(device);
+	return result;
+}
+
+/*
+ * Context for the resource walk used to lookup IRQ resources.
+ * Contains a return code, the lookup index, and references to the flags
+ * and fwspec where the result is returned.
+ */
+struct acpi_irq_parse_one_ctx {
+	int rc;
+	unsigned int index;
+	unsigned long *res_flags;
+	struct irq_fwspec *fwspec;
+};
+
+/**
+ * acpi_irq_parse_one_match - Handle a matching IRQ resource.
+ * @fwnode: matching fwnode
+ * @hwirq: hardware IRQ number
+ * @triggering: triggering attributes of hwirq
+ * @polarity: polarity attributes of hwirq
+ * @polarity: polarity attributes of hwirq
+ * @shareable: shareable attributes of hwirq
+ * @ctx: acpi_irq_parse_one_ctx updated by this function
+ *
+ * Description:
+ * Handle a matching IRQ resource by populating the given ctx with
+ * the information passed.
+ */
+static inline void acpi_irq_parse_one_match(struct fwnode_handle *fwnode,
+					    u32 hwirq, u8 triggering,
+					    u8 polarity, u8 shareable,
+					    struct acpi_irq_parse_one_ctx *ctx)
+{
+	if (!fwnode)
+		return;
+	ctx->rc = 0;
+	*ctx->res_flags = acpi_dev_irq_flags(triggering, polarity, shareable);
+	ctx->fwspec->fwnode = fwnode;
+	ctx->fwspec->param[0] = hwirq;
+	ctx->fwspec->param[1] = acpi_dev_get_irq_type(triggering, polarity);
+	ctx->fwspec->param_count = 2;
+}
+
+/**
+ * acpi_irq_parse_one_cb - Handle the given resource.
+ * @ares: resource to handle
+ * @context: context for the walk
+ *
+ * Description:
+ * This is called by acpi_walk_resources passing each resource returned by
+ * the _CRS method. We only inspect IRQ resources. Since IRQ resources
+ * might contain multiple interrupts we check if the index is within this
+ * one's interrupt array, otherwise we subtract the current resource IRQ
+ * count from the lookup index to prepare for the next resource.
+ * Once a match is found we call acpi_irq_parse_one_match to populate
+ * the result and end the walk by returning AE_CTRL_TERMINATE.
+ *
+ * Return:
+ * AE_OK if the walk should continue, AE_CTRL_TERMINATE if a matching
+ * IRQ resource was found.
+ */
+static acpi_status acpi_irq_parse_one_cb(struct acpi_resource *ares,
+					 void *context)
+{
+	struct acpi_irq_parse_one_ctx *ctx = context;
+	struct acpi_resource_irq *irq;
+	struct acpi_resource_extended_irq *eirq;
+	struct fwnode_handle *fwnode;
+
+	switch (ares->type) {
+	case ACPI_RESOURCE_TYPE_IRQ:
+		irq = &ares->data.irq;
+		if (ctx->index >= irq->interrupt_count) {
+			ctx->index -= irq->interrupt_count;
+			return AE_OK;
+		}
+		fwnode = acpi_gsi_domain_id;
+		acpi_irq_parse_one_match(fwnode, irq->interrupts[ctx->index],
+					 irq->triggering, irq->polarity,
+					 irq->sharable, ctx);
+		return AE_CTRL_TERMINATE;
+	case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
+		eirq = &ares->data.extended_irq;
+		if (eirq->producer_consumer == ACPI_PRODUCER)
+			return AE_OK;
+		if (ctx->index >= eirq->interrupt_count) {
+			ctx->index -= eirq->interrupt_count;
+			return AE_OK;
+		}
+		fwnode = acpi_get_irq_source_fwhandle(&eirq->resource_source);
+		acpi_irq_parse_one_match(fwnode, eirq->interrupts[ctx->index],
+					 eirq->triggering, eirq->polarity,
+					 eirq->sharable, ctx);
+		return AE_CTRL_TERMINATE;
+	}
+
+	return AE_OK;
+}
+
+/**
+ * acpi_irq_parse_one - Resolve an interrupt for a device
+ * @handle: the device whose interrupt is to be resolved
+ * @index: index of the interrupt to resolve
+ * @fwspec: structure irq_fwspec filled by this function
+ * @flags: resource flags filled by this function
+ *
+ * Description:
+ * Resolves an interrupt for a device by walking its CRS resources to find
+ * the appropriate ACPI IRQ resource and populating the given struct irq_fwspec
+ * and flags.
+ *
+ * Return:
+ * The result stored in ctx.rc by the callback, or the default -EINVAL value
+ * if an error occurs.
+ */
+static int acpi_irq_parse_one(acpi_handle handle, unsigned int index,
+			      struct irq_fwspec *fwspec, unsigned long *flags)
+{
+	struct acpi_irq_parse_one_ctx ctx = { -EINVAL, index, flags, fwspec };
+
+	acpi_walk_resources(handle, METHOD_NAME__CRS, acpi_irq_parse_one_cb, &ctx);
+	return ctx.rc;
+}
+
+/**
+ * acpi_irq_get - Lookup an ACPI IRQ resource and use it to initialize resource.
+ * @handle: ACPI device handle
+ * @index:  ACPI IRQ resource index to lookup
+ * @res:    Linux IRQ resource to initialize
+ *
+ * Description:
+ * Look for the ACPI IRQ resource with the given index and use it to initialize
+ * the given Linux IRQ resource.
+ *
+ * Return:
+ * 0 on success
+ * -EINVAL if an error occurs
+ * -EPROBE_DEFER if the IRQ lookup/conversion failed
+ */
+int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res)
+{
+	struct irq_fwspec fwspec;
+	struct irq_domain *domain;
+	unsigned long flags;
+	int rc;
+
+	rc = acpi_irq_parse_one(handle, index, &fwspec, &flags);
+	if (rc)
+		return rc;
+
+	domain = irq_find_matching_fwnode(fwspec.fwnode, DOMAIN_BUS_ANY);
+	if (!domain)
+		return -EPROBE_DEFER;
+
+	rc = irq_create_fwspec_mapping(&fwspec);
+	if (rc <= 0)
+		return -EINVAL;
+
+	res->start = rc;
+	res->end = rc;
+	res->flags = flags;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(acpi_irq_get);
+
+/**
+ * acpi_set_irq_model - Setup the GSI irqdomain information
+ * @model: the value assigned to acpi_irq_model
+ * @fwnode: the irq_domain identifier for mapping and looking up
+ *          GSI interrupts
+ */
+void __init acpi_set_irq_model(enum acpi_irq_model_id model,
+			       struct fwnode_handle *fwnode)
+{
+	acpi_irq_model = model;
+	acpi_gsi_domain_id = fwnode;
+}
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 2f82b8eba360..7361d00818e2 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -2704,6 +2704,7 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc)
 	struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
 	struct device *dev = acpi_desc->dev;
 	struct acpi_nfit_flush_work flush;
+	int rc;
 
 	/* bounce the device lock to flush acpi_nfit_add / acpi_nfit_notify */
 	device_lock(dev);
@@ -2716,7 +2717,10 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc)
 	INIT_WORK_ONSTACK(&flush.work, flush_probe);
 	COMPLETION_INITIALIZER_ONSTACK(flush.cmp);
 	queue_work(nfit_wq, &flush.work);
-	return wait_for_completion_interruptible(&flush.cmp);
+
+	rc = wait_for_completion_interruptible(&flush.cmp);
+	cancel_work_sync(&flush.work);
+	return rc;
 }
 
 static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index e5ce81c38eed..3ba1c3472cf9 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/drivers/acpi/nfit/mce.c
@@ -90,6 +90,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 
 static struct notifier_block nfit_mce_dec = {
 	.notifier_call	= nfit_handle_mce,
+	.priority	= MCE_PRIO_NFIT,
 };
 
 void nfit_mce_register(void)
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 57fb5f468ac2..db78d353bab1 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -1686,7 +1686,7 @@ acpi_status acpi_os_prepare_sleep(u8 sleep_state, u32 pm1a_control,
 	if (rc < 0)
 		return AE_ERROR;
 	else if (rc > 0)
-		return AE_CTRL_SKIP;
+		return AE_CTRL_TERMINATE;
 
 	return AE_OK;
 }
@@ -1697,6 +1697,7 @@ void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state,
 	__acpi_os_prepare_sleep = func;
 }
 
+#if (ACPI_REDUCED_HARDWARE)
 acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a,
 				  u32 val_b)
 {
@@ -1707,13 +1708,35 @@ acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a,
 	if (rc < 0)
 		return AE_ERROR;
 	else if (rc > 0)
-		return AE_CTRL_SKIP;
+		return AE_CTRL_TERMINATE;
 
 	return AE_OK;
 }
+#else
+acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a,
+				  u32 val_b)
+{
+	return AE_OK;
+}
+#endif
 
 void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state,
 			       u32 val_a, u32 val_b))
 {
 	__acpi_os_prepare_extended_sleep = func;
 }
+
+acpi_status acpi_os_enter_sleep(u8 sleep_state,
+				u32 reg_a_value, u32 reg_b_value)
+{
+	acpi_status status;
+
+	if (acpi_gbl_reduced_hardware)
+		status = acpi_os_prepare_extended_sleep(sleep_state,
+							reg_a_value,
+							reg_b_value);
+	else
+		status = acpi_os_prepare_sleep(sleep_state,
+					       reg_a_value, reg_b_value);
+	return status;
+}
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index f0b4a981b8d3..18b72eec3507 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -75,10 +75,8 @@ static int acpi_processor_ppc_notifier(struct notifier_block *nb,
 	struct acpi_processor *pr;
 	unsigned int ppc = 0;
 
-	if (event == CPUFREQ_START && ignore_ppc <= 0) {
+	if (ignore_ppc < 0)
 		ignore_ppc = 0;
-		return 0;
-	}
 
 	if (ignore_ppc)
 		return 0;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index cb57962ef7c4..8b11d6d385dc 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -43,6 +43,19 @@ static inline bool
 acpi_iospace_resource_valid(struct resource *res) { return true; }
 #endif
 
+#if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI)
+static inline bool is_gsi(struct acpi_resource_extended_irq *ext_irq)
+{
+	return ext_irq->resource_source.string_length == 0 &&
+	       ext_irq->producer_consumer == ACPI_CONSUMER;
+}
+#else
+static inline bool is_gsi(struct acpi_resource_extended_irq *ext_irq)
+{
+	return true;
+}
+#endif
+
 static bool acpi_dev_resource_len_valid(u64 start, u64 end, u64 len, bool io)
 {
 	u64 reslen = end - start + 1;
@@ -470,9 +483,12 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
 			acpi_dev_irqresource_disabled(res, 0);
 			return false;
 		}
-		acpi_dev_get_irqresource(res, ext_irq->interrupts[index],
+		if (is_gsi(ext_irq))
+			acpi_dev_get_irqresource(res, ext_irq->interrupts[index],
 					 ext_irq->triggering, ext_irq->polarity,
 					 ext_irq->sharable, false);
+		else
+			acpi_dev_irqresource_disabled(res, 0);
 		break;
 	default:
 		res->flags = 0;
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 9b6cebe227a0..a4327af676fe 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -130,6 +130,12 @@ void __init acpi_nvs_nosave_s3(void)
 	nvs_nosave_s3 = true;
 }
 
+static int __init init_nvs_save_s3(const struct dmi_system_id *d)
+{
+	nvs_nosave_s3 = false;
+	return 0;
+}
+
 /*
  * ACPI 1.0 wants us to execute _PTS before suspending devices, so we allow the
  * user to request that behavior by using the 'acpi_old_suspend_ordering'
@@ -324,6 +330,19 @@ static struct dmi_system_id acpisleep_dmi_table[] __initdata = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "K54HR"),
 		},
 	},
+	/*
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=189431
+	 * Lenovo G50-45 is a platform later than 2012, but needs nvs memory
+	 * saving during S3.
+	 */
+	{
+	.callback = init_nvs_save_s3,
+	.ident = "Lenovo G50-45",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "80E3"),
+		},
+	},
 	{},
 };
 
@@ -674,14 +693,6 @@ static void acpi_sleep_suspend_setup(void)
 		if (acpi_sleep_state_supported(i))
 			sleep_states[i] = 1;
 
-	/*
-	 * Use suspend-to-idle by default if ACPI_FADT_LOW_POWER_S0 is set and
-	 * the default suspend mode was not selected from the command line.
-	 */
-	if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0 &&
-	    mem_sleep_default > PM_SUSPEND_MEM)
-		mem_sleep_default = PM_SUSPEND_FREEZE;
-
 	suspend_set_ops(old_suspend_ordering ?
 		&acpi_suspend_ops_old : &acpi_suspend_ops);
 	freeze_set_ops(&acpi_freeze_ops);
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 02ded25c82e4..7f48156cbc0c 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -305,17 +305,6 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "Dell System XPS L702X"),
 		},
 	},
-	{
-	/* https://bugzilla.redhat.com/show_bug.cgi?id=1204476 */
-	/* https://bugs.launchpad.net/ubuntu/+source/linux-lts-trusty/+bug/1416940 */
-	.callback = video_detect_force_native,
-	.ident = "HP Pavilion dv6",
-	.matches = {
-		DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-		DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv6 Notebook PC"),
-		},
-	},
-
 	{ },
 };
 
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 9cd0a2d41816..c2d3785ec227 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -1702,6 +1702,8 @@ unsigned ata_exec_internal_sg(struct ata_device *dev,
 
 		if (qc->err_mask & ~AC_ERR_OTHER)
 			qc->err_mask &= ~AC_ERR_OTHER;
+	} else if (qc->tf.command == ATA_CMD_REQ_SENSE_DATA) {
+		qc->result_tf.command |= ATA_SENSE;
 	}
 
 	/* finish up */
@@ -4356,10 +4358,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ "ST380013AS",		"3.20",		ATA_HORKAGE_MAX_SEC_1024 },
 
 	/*
-	 * Device times out with higher max sects.
+	 * These devices time out with higher max sects.
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=121671
 	 */
-	{ "LITEON CX1-JB256-HP", NULL,		ATA_HORKAGE_MAX_SEC_1024 },
+	{ "LITEON CX1-JB*-HP",	NULL,		ATA_HORKAGE_MAX_SEC_1024 },
 
 	/* Devices we expect to fail diagnostics */
 
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 0e1ec37070d1..50ee10db160f 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -549,6 +549,7 @@ enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd)
 	DPRINTK("EXIT, ret=%d\n", ret);
 	return ret;
 }
+EXPORT_SYMBOL(ata_scsi_timed_out);
 
 static void ata_eh_unload(struct ata_port *ap)
 {
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 1f863e757ee4..c771d4c341ea 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1265,13 +1265,13 @@ static void ata_scsi_sdev_config(struct scsi_device *sdev)
  */
 static int atapi_drain_needed(struct request *rq)
 {
-	if (likely(rq->cmd_type != REQ_TYPE_BLOCK_PC))
+	if (likely(!blk_rq_is_passthrough(rq)))
 		return 0;
 
 	if (!blk_rq_bytes(rq) || op_is_write(req_op(rq)))
 		return 0;
 
-	return atapi_cmd_type(rq->cmd[0]) == ATAPI_MISC;
+	return atapi_cmd_type(scsi_req(rq)->cmd[0]) == ATAPI_MISC;
 }
 
 static int ata_scsi_dev_config(struct scsi_device *sdev,
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index 7ef16c085058..46698232e6bf 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -716,7 +716,6 @@ struct scsi_transport_template *ata_attach_transport(void)
 		return NULL;
 
 	i->t.eh_strategy_handler	= ata_scsi_error;
-	i->t.eh_timed_out		= ata_scsi_timed_out;
 	i->t.user_scan			= ata_scsi_user_scan;
 
 	i->t.host_attrs.ac.attrs = &i->port_attrs[0];
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 8f3a5596dd67..06d479d1f302 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -159,7 +159,6 @@ extern unsigned long ata_internal_cmd_timeout(struct ata_device *dev, u8 cmd);
 extern void ata_internal_cmd_timed_out(struct ata_device *dev, u8 cmd);
 extern void ata_eh_acquire(struct ata_port *ap);
 extern void ata_eh_release(struct ata_port *ap);
-extern enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd);
 extern void ata_scsi_error(struct Scsi_Host *host);
 extern void ata_eh_fastdrain_timerfn(unsigned long arg);
 extern void ata_qc_schedule_eh(struct ata_queued_cmd *qc);
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 823e938c9a78..2f32782cea6d 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -4132,6 +4132,9 @@ static int mv_platform_probe(struct platform_device *pdev)
 	host->iomap = NULL;
 	hpriv->base = devm_ioremap(&pdev->dev, res->start,
 				   resource_size(res));
+	if (!hpriv->base)
+		return -ENOMEM;
+
 	hpriv->base -= SATAHC0_REG_BASE;
 
 	hpriv->clk = clk_get(&pdev->dev, NULL);
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 4c28e1a09786..2c3b359b3536 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -17,6 +17,7 @@
 #include <linux/of.h>
 #include <linux/cpufeature.h>
 #include <linux/tick.h>
+#include <linux/pm_qos.h>
 
 #include "base.h"
 
@@ -376,6 +377,7 @@ int register_cpu(struct cpu *cpu, int num)
 
 	per_cpu(cpu_sys_devices, num) = &cpu->dev;
 	register_cpu_under_node(num, cpu_to_node(num));
+	dev_pm_qos_expose_latency_limit(&cpu->dev, 0);
 
 	return 0;
 }
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 4497d263209f..ac350c518e0c 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -558,9 +558,6 @@ static void fw_load_abort(struct firmware_priv *fw_priv)
 	struct firmware_buf *buf = fw_priv->buf;
 
 	__fw_load_abort(buf);
-
-	/* avoid user action after loading abort */
-	fw_priv->buf = NULL;
 }
 
 static LIST_HEAD(pending_fw_head);
@@ -713,7 +710,7 @@ static ssize_t firmware_loading_store(struct device *dev,
 
 	mutex_lock(&fw_lock);
 	fw_buf = fw_priv->buf;
-	if (!fw_buf)
+	if (fw_state_is_aborted(&fw_buf->fw_st))
 		goto out;
 
 	switch (loading) {
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 8ab8ea1253e6..fa26ffd25fa6 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -389,33 +389,33 @@ static ssize_t show_valid_zones(struct device *dev,
 {
 	struct memory_block *mem = to_memory_block(dev);
 	unsigned long start_pfn, end_pfn;
+	unsigned long valid_start, valid_end, valid_pages;
 	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
-	struct page *first_page;
 	struct zone *zone;
 	int zone_shift = 0;
 
 	start_pfn = section_nr_to_pfn(mem->start_section_nr);
 	end_pfn = start_pfn + nr_pages;
-	first_page = pfn_to_page(start_pfn);
 
 	/* The block contains more than one zone can not be offlined. */
-	if (!test_pages_in_a_zone(start_pfn, end_pfn))
+	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
 		return sprintf(buf, "none\n");
 
-	zone = page_zone(first_page);
+	zone = page_zone(pfn_to_page(valid_start));
+	valid_pages = valid_end - valid_start;
 
 	/* MMOP_ONLINE_KEEP */
 	sprintf(buf, "%s", zone->name);
 
 	/* MMOP_ONLINE_KERNEL */
-	zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_NORMAL);
+	zone_can_shift(valid_start, valid_pages, ZONE_NORMAL, &zone_shift);
 	if (zone_shift) {
 		strcat(buf, " ");
 		strcat(buf, (zone + zone_shift)->name);
 	}
 
 	/* MMOP_ONLINE_MOVABLE */
-	zone_shift = zone_can_shift(start_pfn, nr_pages, ZONE_MOVABLE);
+	zone_can_shift(valid_start, valid_pages, ZONE_MOVABLE, &zone_shift);
 	if (zone_shift) {
 		strcat(buf, " ");
 		strcat(buf, (zone + zone_shift)->name);
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index be6a599bc0c1..0fc7c4da7756 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -206,7 +206,7 @@ platform_msi_alloc_priv_data(struct device *dev, unsigned int nvec,
 {
 	struct platform_msi_priv_data *datap;
 	/*
-	 * Limit the number of interrupts to 256 per device. Should we
+	 * Limit the number of interrupts to 2048 per device. Should we
 	 * need to bump this up, DEV_ID_SHIFT should be adjusted
 	 * accordingly (which would impact the max number of MSI
 	 * capable devices).
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index c4af00385502..647e4761dbf3 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -102,6 +102,16 @@ int platform_get_irq(struct platform_device *dev, unsigned int num)
 	}
 
 	r = platform_get_resource(dev, IORESOURCE_IRQ, num);
+	if (has_acpi_companion(&dev->dev)) {
+		if (r && r->flags & IORESOURCE_DISABLED) {
+			int ret;
+
+			ret = acpi_irq_get(ACPI_HANDLE(&dev->dev), num, r);
+			if (ret)
+				return ret;
+		}
+	}
+
 	/*
 	 * The resources may pass trigger flags to the irqs that need
 	 * to be set up. It so happens that the trigger flags for
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 2997026b4dfb..3a75fb1b4126 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -130,7 +130,7 @@ static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
 
 	ret = pm_runtime_is_irq_safe(dev) && !genpd_is_irq_safe(genpd);
 
-	/* Warn once for each IRQ safe dev in no sleep domain */
+	/* Warn once if IRQ safe dev in no sleep domain */
 	if (ret)
 		dev_warn_once(dev, "PM domain %s will not be powered off\n",
 				genpd->name);
@@ -201,7 +201,7 @@ static void genpd_sd_counter_inc(struct generic_pm_domain *genpd)
 	smp_mb__after_atomic();
 }
 
-static int genpd_power_on(struct generic_pm_domain *genpd, bool timed)
+static int _genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 {
 	unsigned int state_idx = genpd->state_idx;
 	ktime_t time_start;
@@ -231,7 +231,7 @@ static int genpd_power_on(struct generic_pm_domain *genpd, bool timed)
 	return ret;
 }
 
-static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
+static int _genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 {
 	unsigned int state_idx = genpd->state_idx;
 	ktime_t time_start;
@@ -262,10 +262,10 @@ static int genpd_power_off(struct generic_pm_domain *genpd, bool timed)
 }
 
 /**
- * genpd_queue_power_off_work - Queue up the execution of genpd_poweroff().
+ * genpd_queue_power_off_work - Queue up the execution of genpd_power_off().
  * @genpd: PM domain to power off.
  *
- * Queue up the execution of genpd_poweroff() unless it's already been done
+ * Queue up the execution of genpd_power_off() unless it's already been done
  * before.
  */
 static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
@@ -274,14 +274,14 @@ static void genpd_queue_power_off_work(struct generic_pm_domain *genpd)
 }
 
 /**
- * genpd_poweron - Restore power to a given PM domain and its masters.
+ * genpd_power_on - Restore power to a given PM domain and its masters.
  * @genpd: PM domain to power up.
  * @depth: nesting count for lockdep.
  *
  * Restore power to @genpd and all of its masters so that it is possible to
  * resume a device belonging to it.
  */
-static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
+static int genpd_power_on(struct generic_pm_domain *genpd, unsigned int depth)
 {
 	struct gpd_link *link;
 	int ret = 0;
@@ -300,7 +300,7 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
 		genpd_sd_counter_inc(master);
 
 		genpd_lock_nested(master, depth + 1);
-		ret = genpd_poweron(master, depth + 1);
+		ret = genpd_power_on(master, depth + 1);
 		genpd_unlock(master);
 
 		if (ret) {
@@ -309,7 +309,7 @@ static int genpd_poweron(struct generic_pm_domain *genpd, unsigned int depth)
 		}
 	}
 
-	ret = genpd_power_on(genpd, true);
+	ret = _genpd_power_on(genpd, true);
 	if (ret)
 		goto err;
 
@@ -368,14 +368,14 @@ static int genpd_dev_pm_qos_notifier(struct notifier_block *nb,
 }
 
 /**
- * genpd_poweroff - Remove power from a given PM domain.
+ * genpd_power_off - Remove power from a given PM domain.
  * @genpd: PM domain to power down.
  * @is_async: PM domain is powered down from a scheduled work
  *
  * If all of the @genpd's devices have been suspended and all of its subdomains
  * have been powered down, remove power from @genpd.
  */
-static int genpd_poweroff(struct generic_pm_domain *genpd, bool is_async)
+static int genpd_power_off(struct generic_pm_domain *genpd, bool is_async)
 {
 	struct pm_domain_data *pdd;
 	struct gpd_link *link;
@@ -427,13 +427,13 @@ static int genpd_poweroff(struct generic_pm_domain *genpd, bool is_async)
 
 		/*
 		 * If sd_count > 0 at this point, one of the subdomains hasn't
-		 * managed to call genpd_poweron() for the master yet after
-		 * incrementing it.  In that case genpd_poweron() will wait
+		 * managed to call genpd_power_on() for the master yet after
+		 * incrementing it.  In that case genpd_power_on() will wait
 		 * for us to drop the lock, so we can call .power_off() and let
-		 * the genpd_poweron() restore power for us (this shouldn't
+		 * the genpd_power_on() restore power for us (this shouldn't
 		 * happen very often).
 		 */
-		ret = genpd_power_off(genpd, true);
+		ret = _genpd_power_off(genpd, true);
 		if (ret)
 			return ret;
 	}
@@ -459,7 +459,7 @@ static void genpd_power_off_work_fn(struct work_struct *work)
 	genpd = container_of(work, struct generic_pm_domain, power_off_work);
 
 	genpd_lock(genpd);
-	genpd_poweroff(genpd, true);
+	genpd_power_off(genpd, true);
 	genpd_unlock(genpd);
 }
 
@@ -578,7 +578,7 @@ static int genpd_runtime_suspend(struct device *dev)
 		return 0;
 
 	genpd_lock(genpd);
-	genpd_poweroff(genpd, false);
+	genpd_power_off(genpd, false);
 	genpd_unlock(genpd);
 
 	return 0;
@@ -618,7 +618,7 @@ static int genpd_runtime_resume(struct device *dev)
 	}
 
 	genpd_lock(genpd);
-	ret = genpd_poweron(genpd, 0);
+	ret = genpd_power_on(genpd, 0);
 	genpd_unlock(genpd);
 
 	if (ret)
@@ -658,7 +658,7 @@ err_poweroff:
 	if (!pm_runtime_is_irq_safe(dev) ||
 		(pm_runtime_is_irq_safe(dev) && genpd_is_irq_safe(genpd))) {
 		genpd_lock(genpd);
-		genpd_poweroff(genpd, 0);
+		genpd_power_off(genpd, 0);
 		genpd_unlock(genpd);
 	}
 
@@ -674,9 +674,9 @@ static int __init pd_ignore_unused_setup(char *__unused)
 __setup("pd_ignore_unused", pd_ignore_unused_setup);
 
 /**
- * genpd_poweroff_unused - Power off all PM domains with no devices in use.
+ * genpd_power_off_unused - Power off all PM domains with no devices in use.
  */
-static int __init genpd_poweroff_unused(void)
+static int __init genpd_power_off_unused(void)
 {
 	struct generic_pm_domain *genpd;
 
@@ -694,7 +694,7 @@ static int __init genpd_poweroff_unused(void)
 
 	return 0;
 }
-late_initcall(genpd_poweroff_unused);
+late_initcall(genpd_power_off_unused);
 
 #if defined(CONFIG_PM_SLEEP) || defined(CONFIG_PM_GENERIC_DOMAINS_OF)
 
@@ -727,18 +727,20 @@ static bool genpd_dev_active_wakeup(struct generic_pm_domain *genpd,
 }
 
 /**
- * genpd_sync_poweroff - Synchronously power off a PM domain and its masters.
+ * genpd_sync_power_off - Synchronously power off a PM domain and its masters.
  * @genpd: PM domain to power off, if possible.
+ * @use_lock: use the lock.
+ * @depth: nesting count for lockdep.
  *
  * Check if the given PM domain can be powered off (during system suspend or
  * hibernation) and do that if so.  Also, in that case propagate to its masters.
  *
  * This function is only called in "noirq" and "syscore" stages of system power
- * transitions, so it need not acquire locks (all of the "noirq" callbacks are
- * executed sequentially, so it is guaranteed that it will never run twice in
- * parallel).
+ * transitions. The "noirq" callbacks may be executed asynchronously, thus in
+ * these cases the lock must be held.
  */
-static void genpd_sync_poweroff(struct generic_pm_domain *genpd)
+static void genpd_sync_power_off(struct generic_pm_domain *genpd, bool use_lock,
+				 unsigned int depth)
 {
 	struct gpd_link *link;
 
@@ -751,26 +753,35 @@ static void genpd_sync_poweroff(struct generic_pm_domain *genpd)
 
 	/* Choose the deepest state when suspending */
 	genpd->state_idx = genpd->state_count - 1;
-	genpd_power_off(genpd, false);
+	_genpd_power_off(genpd, false);
 
 	genpd->status = GPD_STATE_POWER_OFF;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
 		genpd_sd_counter_dec(link->master);
-		genpd_sync_poweroff(link->master);
+
+		if (use_lock)
+			genpd_lock_nested(link->master, depth + 1);
+
+		genpd_sync_power_off(link->master, use_lock, depth + 1);
+
+		if (use_lock)
+			genpd_unlock(link->master);
 	}
 }
 
 /**
- * genpd_sync_poweron - Synchronously power on a PM domain and its masters.
+ * genpd_sync_power_on - Synchronously power on a PM domain and its masters.
  * @genpd: PM domain to power on.
+ * @use_lock: use the lock.
+ * @depth: nesting count for lockdep.
  *
  * This function is only called in "noirq" and "syscore" stages of system power
- * transitions, so it need not acquire locks (all of the "noirq" callbacks are
- * executed sequentially, so it is guaranteed that it will never run twice in
- * parallel).
+ * transitions. The "noirq" callbacks may be executed asynchronously, thus in
+ * these cases the lock must be held.
  */
-static void genpd_sync_poweron(struct generic_pm_domain *genpd)
+static void genpd_sync_power_on(struct generic_pm_domain *genpd, bool use_lock,
+				unsigned int depth)
 {
 	struct gpd_link *link;
 
@@ -778,11 +789,18 @@ static void genpd_sync_poweron(struct generic_pm_domain *genpd)
 		return;
 
 	list_for_each_entry(link, &genpd->slave_links, slave_node) {
-		genpd_sync_poweron(link->master);
 		genpd_sd_counter_inc(link->master);
+
+		if (use_lock)
+			genpd_lock_nested(link->master, depth + 1);
+
+		genpd_sync_power_on(link->master, use_lock, depth + 1);
+
+		if (use_lock)
+			genpd_unlock(link->master);
 	}
 
-	genpd_power_on(genpd, false);
+	_genpd_power_on(genpd, false);
 
 	genpd->status = GPD_STATE_ACTIVE;
 }
@@ -888,13 +906,10 @@ static int pm_genpd_suspend_noirq(struct device *dev)
 			return ret;
 	}
 
-	/*
-	 * Since all of the "noirq" callbacks are executed sequentially, it is
-	 * guaranteed that this function will never run twice in parallel for
-	 * the same PM domain, so it is not necessary to use locking here.
-	 */
+	genpd_lock(genpd);
 	genpd->suspended_count++;
-	genpd_sync_poweroff(genpd);
+	genpd_sync_power_off(genpd, true, 0);
+	genpd_unlock(genpd);
 
 	return 0;
 }
@@ -919,13 +934,10 @@ static int pm_genpd_resume_noirq(struct device *dev)
 	if (dev->power.wakeup_path && genpd_dev_active_wakeup(genpd, dev))
 		return 0;
 
-	/*
-	 * Since all of the "noirq" callbacks are executed sequentially, it is
-	 * guaranteed that this function will never run twice in parallel for
-	 * the same PM domain, so it is not necessary to use locking here.
-	 */
-	genpd_sync_poweron(genpd);
+	genpd_lock(genpd);
+	genpd_sync_power_on(genpd, true, 0);
 	genpd->suspended_count--;
+	genpd_unlock(genpd);
 
 	if (genpd->dev_ops.stop && genpd->dev_ops.start)
 		ret = pm_runtime_force_resume(dev);
@@ -1002,22 +1014,20 @@ static int pm_genpd_restore_noirq(struct device *dev)
 		return -EINVAL;
 
 	/*
-	 * Since all of the "noirq" callbacks are executed sequentially, it is
-	 * guaranteed that this function will never run twice in parallel for
-	 * the same PM domain, so it is not necessary to use locking here.
-	 *
 	 * At this point suspended_count == 0 means we are being run for the
 	 * first time for the given domain in the present cycle.
 	 */
+	genpd_lock(genpd);
 	if (genpd->suspended_count++ == 0)
 		/*
 		 * The boot kernel might put the domain into arbitrary state,
-		 * so make it appear as powered off to genpd_sync_poweron(),
+		 * so make it appear as powered off to genpd_sync_power_on(),
 		 * so that it tries to power it on in case it was really off.
 		 */
 		genpd->status = GPD_STATE_POWER_OFF;
 
-	genpd_sync_poweron(genpd);
+	genpd_sync_power_on(genpd, true, 0);
+	genpd_unlock(genpd);
 
 	if (genpd->dev_ops.stop && genpd->dev_ops.start)
 		ret = pm_runtime_force_resume(dev);
@@ -1072,9 +1082,9 @@ static void genpd_syscore_switch(struct device *dev, bool suspend)
 
 	if (suspend) {
 		genpd->suspended_count++;
-		genpd_sync_poweroff(genpd);
+		genpd_sync_power_off(genpd, false, 0);
 	} else {
-		genpd_sync_poweron(genpd);
+		genpd_sync_power_on(genpd, false, 0);
 		genpd->suspended_count--;
 	}
 }
@@ -2043,7 +2053,7 @@ int genpd_dev_pm_attach(struct device *dev)
 	dev->pm_domain->sync = genpd_dev_pm_sync;
 
 	genpd_lock(pd);
-	ret = genpd_poweron(pd, 0);
+	ret = genpd_power_on(pd, 0);
 	genpd_unlock(pd);
 out:
 	return ret ? -EPROBE_DEFER : 0;
diff --git a/drivers/base/power/opp/core.c b/drivers/base/power/opp/core.c
index 35ff06283738..91ec3232d630 100644
--- a/drivers/base/power/opp/core.c
+++ b/drivers/base/power/opp/core.c
@@ -32,13 +32,7 @@ LIST_HEAD(opp_tables);
 /* Lock to allow exclusive modification to the device and opp lists */
 DEFINE_MUTEX(opp_table_lock);
 
-#define opp_rcu_lockdep_assert()					\
-do {									\
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&			\
-			 !lockdep_is_held(&opp_table_lock),		\
-			 "Missing rcu_read_lock() or "			\
-			 "opp_table_lock protection");			\
-} while (0)
+static void dev_pm_opp_get(struct dev_pm_opp *opp);
 
 static struct opp_device *_find_opp_dev(const struct device *dev,
 					struct opp_table *opp_table)
@@ -52,38 +46,46 @@ static struct opp_device *_find_opp_dev(const struct device *dev,
 	return NULL;
 }
 
+static struct opp_table *_find_opp_table_unlocked(struct device *dev)
+{
+	struct opp_table *opp_table;
+
+	list_for_each_entry(opp_table, &opp_tables, node) {
+		if (_find_opp_dev(dev, opp_table)) {
+			_get_opp_table_kref(opp_table);
+
+			return opp_table;
+		}
+	}
+
+	return ERR_PTR(-ENODEV);
+}
+
 /**
  * _find_opp_table() - find opp_table struct using device pointer
  * @dev:	device pointer used to lookup OPP table
  *
- * Search OPP table for one containing matching device. Does a RCU reader
- * operation to grab the pointer needed.
+ * Search OPP table for one containing matching device.
  *
  * Return: pointer to 'struct opp_table' if found, otherwise -ENODEV or
  * -EINVAL based on type of error.
  *
- * Locking: For readers, this function must be called under rcu_read_lock().
- * opp_table is a RCU protected pointer, which means that opp_table is valid
- * as long as we are under RCU lock.
- *
- * For Writers, this function must be called with opp_table_lock held.
+ * The callers must call dev_pm_opp_put_opp_table() after the table is used.
  */
 struct opp_table *_find_opp_table(struct device *dev)
 {
 	struct opp_table *opp_table;
 
-	opp_rcu_lockdep_assert();
-
 	if (IS_ERR_OR_NULL(dev)) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
 
-	list_for_each_entry_rcu(opp_table, &opp_tables, node)
-		if (_find_opp_dev(dev, opp_table))
-			return opp_table;
+	mutex_lock(&opp_table_lock);
+	opp_table = _find_opp_table_unlocked(dev);
+	mutex_unlock(&opp_table_lock);
 
-	return ERR_PTR(-ENODEV);
+	return opp_table;
 }
 
 /**
@@ -94,29 +96,15 @@ struct opp_table *_find_opp_table(struct device *dev)
  * return 0
  *
  * This is useful only for devices with single power supply.
- *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. This means that opp which could have been fetched by
- * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
- * under RCU lock. The pointer returned by the opp_find_freq family must be
- * used in the same section as the usage of this function with the pointer
- * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
- * pointer.
  */
 unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 {
-	struct dev_pm_opp *tmp_opp;
-	unsigned long v = 0;
-
-	opp_rcu_lockdep_assert();
-
-	tmp_opp = rcu_dereference(opp);
-	if (IS_ERR_OR_NULL(tmp_opp))
+	if (IS_ERR_OR_NULL(opp)) {
 		pr_err("%s: Invalid parameters\n", __func__);
-	else
-		v = tmp_opp->supplies[0].u_volt;
+		return 0;
+	}
 
-	return v;
+	return opp->supplies[0].u_volt;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
 
@@ -126,29 +114,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_voltage);
  *
  * Return: frequency in hertz corresponding to the opp, else
  * return 0
- *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. This means that opp which could have been fetched by
- * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
- * under RCU lock. The pointer returned by the opp_find_freq family must be
- * used in the same section as the usage of this function with the pointer
- * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
- * pointer.
  */
 unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp)
 {
-	struct dev_pm_opp *tmp_opp;
-	unsigned long f = 0;
-
-	opp_rcu_lockdep_assert();
-
-	tmp_opp = rcu_dereference(opp);
-	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available)
+	if (IS_ERR_OR_NULL(opp) || !opp->available) {
 		pr_err("%s: Invalid parameters\n", __func__);
-	else
-		f = tmp_opp->rate;
+		return 0;
+	}
 
-	return f;
+	return opp->rate;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
 
@@ -161,28 +135,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_freq);
  * quickly. Running on them for longer times may overheat the chip.
  *
  * Return: true if opp is turbo opp, else false.
- *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. This means that opp which could have been fetched by
- * opp_find_freq_{exact,ceil,floor} functions is valid as long as we are
- * under RCU lock. The pointer returned by the opp_find_freq family must be
- * used in the same section as the usage of this function with the pointer
- * prior to unlocking with rcu_read_unlock() to maintain the integrity of the
- * pointer.
  */
 bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp)
 {
-	struct dev_pm_opp *tmp_opp;
-
-	opp_rcu_lockdep_assert();
-
-	tmp_opp = rcu_dereference(opp);
-	if (IS_ERR_OR_NULL(tmp_opp) || !tmp_opp->available) {
+	if (IS_ERR_OR_NULL(opp) || !opp->available) {
 		pr_err("%s: Invalid parameters\n", __func__);
 		return false;
 	}
 
-	return tmp_opp->turbo;
+	return opp->turbo;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
 
@@ -191,52 +152,29 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_is_turbo);
  * @dev:	device for which we do this operation
  *
  * Return: This function returns the max clock latency in nanoseconds.
- *
- * Locking: This function takes rcu_read_lock().
  */
 unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev)
 {
 	struct opp_table *opp_table;
 	unsigned long clock_latency_ns;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table))
-		clock_latency_ns = 0;
-	else
-		clock_latency_ns = opp_table->clock_latency_ns_max;
-
-	rcu_read_unlock();
-	return clock_latency_ns;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
-
-static int _get_regulator_count(struct device *dev)
-{
-	struct opp_table *opp_table;
-	int count;
+		return 0;
 
-	rcu_read_lock();
+	clock_latency_ns = opp_table->clock_latency_ns_max;
 
-	opp_table = _find_opp_table(dev);
-	if (!IS_ERR(opp_table))
-		count = opp_table->regulator_count;
-	else
-		count = 0;
+	dev_pm_opp_put_opp_table(opp_table);
 
-	rcu_read_unlock();
-
-	return count;
+	return clock_latency_ns;
 }
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_clock_latency);
 
 /**
  * dev_pm_opp_get_max_volt_latency() - Get max voltage latency in nanoseconds
  * @dev: device for which we do this operation
  *
  * Return: This function returns the max voltage latency in nanoseconds.
- *
- * Locking: This function takes rcu_read_lock().
  */
 unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 {
@@ -250,35 +188,33 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 		unsigned long max;
 	} *uV;
 
-	count = _get_regulator_count(dev);
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return 0;
+
+	count = opp_table->regulator_count;
 
 	/* Regulator may not be required for the device */
 	if (!count)
-		return 0;
+		goto put_opp_table;
 
 	regulators = kmalloc_array(count, sizeof(*regulators), GFP_KERNEL);
 	if (!regulators)
-		return 0;
+		goto put_opp_table;
 
 	uV = kmalloc_array(count, sizeof(*uV), GFP_KERNEL);
 	if (!uV)
 		goto free_regulators;
 
-	rcu_read_lock();
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		rcu_read_unlock();
-		goto free_uV;
-	}
-
 	memcpy(regulators, opp_table->regulators, count * sizeof(*regulators));
 
+	mutex_lock(&opp_table->lock);
+
 	for (i = 0; i < count; i++) {
 		uV[i].min = ~0;
 		uV[i].max = 0;
 
-		list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
+		list_for_each_entry(opp, &opp_table->opp_list, node) {
 			if (!opp->available)
 				continue;
 
@@ -289,7 +225,7 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 		}
 	}
 
-	rcu_read_unlock();
+	mutex_unlock(&opp_table->lock);
 
 	/*
 	 * The caller needs to ensure that opp_table (and hence the regulator)
@@ -301,10 +237,11 @@ unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev)
 			latency_ns += ret * 1000;
 	}
 
-free_uV:
 	kfree(uV);
 free_regulators:
 	kfree(regulators);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return latency_ns;
 }
@@ -317,8 +254,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_volt_latency);
  *
  * Return: This function returns the max transition latency, in nanoseconds, to
  * switch from one OPP to other.
- *
- * Locking: This function takes rcu_read_lock().
  */
 unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev)
 {
@@ -328,32 +263,29 @@ unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev)
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_max_transition_latency);
 
 /**
- * dev_pm_opp_get_suspend_opp() - Get suspend opp
+ * dev_pm_opp_get_suspend_opp_freq() - Get frequency of suspend opp in Hz
  * @dev:	device for which we do this operation
  *
- * Return: This function returns pointer to the suspend opp if it is
- * defined and available, otherwise it returns NULL.
- *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * Return: This function returns the frequency of the OPP marked as suspend_opp
+ * if one is available, else returns 0;
  */
-struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev)
+unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
 {
 	struct opp_table *opp_table;
-
-	opp_rcu_lockdep_assert();
+	unsigned long freq = 0;
 
 	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table) || !opp_table->suspend_opp ||
-	    !opp_table->suspend_opp->available)
-		return NULL;
+	if (IS_ERR(opp_table))
+		return 0;
+
+	if (opp_table->suspend_opp && opp_table->suspend_opp->available)
+		freq = dev_pm_opp_get_freq(opp_table->suspend_opp);
 
-	return opp_table->suspend_opp;
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return freq;
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp);
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
 
 /**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp table
@@ -361,8 +293,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp);
  *
  * Return: This function returns the number of available opps if there are any,
  * else returns 0 if none or the corresponding error value.
- *
- * Locking: This function takes rcu_read_lock().
  */
 int dev_pm_opp_get_opp_count(struct device *dev)
 {
@@ -370,23 +300,24 @@ int dev_pm_opp_get_opp_count(struct device *dev)
 	struct dev_pm_opp *temp_opp;
 	int count = 0;
 
-	rcu_read_lock();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		count = PTR_ERR(opp_table);
 		dev_err(dev, "%s: OPP table not found (%d)\n",
 			__func__, count);
-		goto out_unlock;
+		return count;
 	}
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available)
 			count++;
 	}
 
-out_unlock:
-	rcu_read_unlock();
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
 	return count;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
@@ -411,11 +342,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_count);
  * This provides a mechanism to enable an opp which is not available currently
  * or the opposite as well.
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					      unsigned long freq,
@@ -424,8 +352,6 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
-	opp_rcu_lockdep_assert();
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		int r = PTR_ERR(opp_table);
@@ -434,14 +360,22 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 		return ERR_PTR(r);
 	}
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available == available &&
 				temp_opp->rate == freq) {
 			opp = temp_opp;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
 			break;
 		}
 	}
 
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
 	return opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_exact);
@@ -451,14 +385,21 @@ static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
 {
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available && temp_opp->rate >= *freq) {
 			opp = temp_opp;
 			*freq = opp->rate;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
 			break;
 		}
 	}
 
+	mutex_unlock(&opp_table->lock);
+
 	return opp;
 }
 
@@ -477,18 +418,14 @@ static noinline struct dev_pm_opp *_find_freq_ceil(struct opp_table *opp_table,
  * ERANGE:	no match found for search
  * ENODEV:	if device not found in list of registered devices
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq)
 {
 	struct opp_table *opp_table;
-
-	opp_rcu_lockdep_assert();
+	struct dev_pm_opp *opp;
 
 	if (!dev || !freq) {
 		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
@@ -499,7 +436,11 @@ struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 	if (IS_ERR(opp_table))
 		return ERR_CAST(opp_table);
 
-	return _find_freq_ceil(opp_table, freq);
+	opp = _find_freq_ceil(opp_table, freq);
+
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
 
@@ -518,11 +459,8 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil);
  * ERANGE:	no match found for search
  * ENODEV:	if device not found in list of registered devices
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					      unsigned long *freq)
@@ -530,8 +468,6 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	struct opp_table *opp_table;
 	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
 
-	opp_rcu_lockdep_assert();
-
 	if (!dev || !freq) {
 		dev_err(dev, "%s: Invalid argument freq=%p\n", __func__, freq);
 		return ERR_PTR(-EINVAL);
@@ -541,7 +477,9 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	if (IS_ERR(opp_table))
 		return ERR_CAST(opp_table);
 
-	list_for_each_entry_rcu(temp_opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
 		if (temp_opp->available) {
 			/* go to the next node, before choosing prev */
 			if (temp_opp->rate > *freq)
@@ -550,6 +488,13 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 				opp = temp_opp;
 		}
 	}
+
+	/* Increment the reference count of OPP */
+	if (!IS_ERR(opp))
+		dev_pm_opp_get(opp);
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
 	if (!IS_ERR(opp))
 		*freq = opp->rate;
 
@@ -557,34 +502,6 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
-/*
- * The caller needs to ensure that opp_table (and hence the clk) isn't freed,
- * while clk returned here is used.
- */
-static struct clk *_get_opp_clk(struct device *dev)
-{
-	struct opp_table *opp_table;
-	struct clk *clk;
-
-	rcu_read_lock();
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
-		clk = ERR_CAST(opp_table);
-		goto unlock;
-	}
-
-	clk = opp_table->clk;
-	if (IS_ERR(clk))
-		dev_err(dev, "%s: No clock available for the device\n",
-			__func__);
-
-unlock:
-	rcu_read_unlock();
-	return clk;
-}
-
 static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 			    struct dev_pm_opp_supply *supply)
 {
@@ -680,8 +597,6 @@ restore_voltage:
  *
  * This configures the power-supplies and clock source to the levels specified
  * by the OPP corresponding to the target_freq.
- *
- * Locking: This function takes rcu_read_lock().
  */
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 {
@@ -700,9 +615,19 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		return -EINVAL;
 	}
 
-	clk = _get_opp_clk(dev);
-	if (IS_ERR(clk))
-		return PTR_ERR(clk);
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table)) {
+		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
+		return PTR_ERR(opp_table);
+	}
+
+	clk = opp_table->clk;
+	if (IS_ERR(clk)) {
+		dev_err(dev, "%s: No clock available for the device\n",
+			__func__);
+		ret = PTR_ERR(clk);
+		goto put_opp_table;
+	}
 
 	freq = clk_round_rate(clk, target_freq);
 	if ((long)freq <= 0)
@@ -714,16 +639,8 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	if (old_freq == freq) {
 		dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n",
 			__func__, freq);
-		return 0;
-	}
-
-	rcu_read_lock();
-
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "%s: device opp doesn't exist\n", __func__);
-		rcu_read_unlock();
-		return PTR_ERR(opp_table);
+		ret = 0;
+		goto put_opp_table;
 	}
 
 	old_opp = _find_freq_ceil(opp_table, &old_freq);
@@ -737,8 +654,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 		ret = PTR_ERR(opp);
 		dev_err(dev, "%s: failed to find OPP for freq %lu (%d)\n",
 			__func__, freq, ret);
-		rcu_read_unlock();
-		return ret;
+		goto put_old_opp;
 	}
 
 	dev_dbg(dev, "%s: switching OPP: %lu Hz --> %lu Hz\n", __func__,
@@ -748,8 +664,8 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 
 	/* Only frequency scaling */
 	if (!regulators) {
-		rcu_read_unlock();
-		return _generic_set_opp_clk_only(dev, clk, old_freq, freq);
+		ret = _generic_set_opp_clk_only(dev, clk, old_freq, freq);
+		goto put_opps;
 	}
 
 	if (opp_table->set_opp)
@@ -773,28 +689,26 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 	data->new_opp.rate = freq;
 	memcpy(data->new_opp.supplies, opp->supplies, size);
 
-	rcu_read_unlock();
+	ret = set_opp(data);
 
-	return set_opp(data);
+put_opps:
+	dev_pm_opp_put(opp);
+put_old_opp:
+	if (!IS_ERR(old_opp))
+		dev_pm_opp_put(old_opp);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_rate);
 
 /* OPP-dev Helpers */
-static void _kfree_opp_dev_rcu(struct rcu_head *head)
-{
-	struct opp_device *opp_dev;
-
-	opp_dev = container_of(head, struct opp_device, rcu_head);
-	kfree_rcu(opp_dev, rcu_head);
-}
-
 static void _remove_opp_dev(struct opp_device *opp_dev,
 			    struct opp_table *opp_table)
 {
 	opp_debug_unregister(opp_dev, opp_table);
 	list_del(&opp_dev->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp_dev->rcu_head,
-		  _kfree_opp_dev_rcu);
+	kfree(opp_dev);
 }
 
 struct opp_device *_add_opp_dev(const struct device *dev,
@@ -809,7 +723,7 @@ struct opp_device *_add_opp_dev(const struct device *dev,
 
 	/* Initialize opp-dev */
 	opp_dev->dev = dev;
-	list_add_rcu(&opp_dev->node, &opp_table->dev_list);
+	list_add(&opp_dev->node, &opp_table->dev_list);
 
 	/* Create debugfs entries for the opp_table */
 	ret = opp_debug_register(opp_dev, opp_table);
@@ -820,26 +734,12 @@ struct opp_device *_add_opp_dev(const struct device *dev,
 	return opp_dev;
 }
 
-/**
- * _add_opp_table() - Find OPP table or allocate a new one
- * @dev:	device for which we do this operation
- *
- * It tries to find an existing table first, if it couldn't find one, it
- * allocates a new OPP table and returns that.
- *
- * Return: valid opp_table pointer if success, else NULL.
- */
-static struct opp_table *_add_opp_table(struct device *dev)
+static struct opp_table *_allocate_opp_table(struct device *dev)
 {
 	struct opp_table *opp_table;
 	struct opp_device *opp_dev;
 	int ret;
 
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (!IS_ERR(opp_table))
-		return opp_table;
-
 	/*
 	 * Allocate a new OPP table. In the infrequent case where a new
 	 * device is needed to be added, we pay this penalty.
@@ -867,50 +767,45 @@ static struct opp_table *_add_opp_table(struct device *dev)
 				ret);
 	}
 
-	srcu_init_notifier_head(&opp_table->srcu_head);
+	BLOCKING_INIT_NOTIFIER_HEAD(&opp_table->head);
 	INIT_LIST_HEAD(&opp_table->opp_list);
+	mutex_init(&opp_table->lock);
+	kref_init(&opp_table->kref);
 
 	/* Secure the device table modification */
-	list_add_rcu(&opp_table->node, &opp_tables);
+	list_add(&opp_table->node, &opp_tables);
 	return opp_table;
 }
 
-/**
- * _kfree_device_rcu() - Free opp_table RCU handler
- * @head:	RCU head
- */
-static void _kfree_device_rcu(struct rcu_head *head)
+void _get_opp_table_kref(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table = container_of(head, struct opp_table,
-						   rcu_head);
-
-	kfree_rcu(opp_table, rcu_head);
+	kref_get(&opp_table->kref);
 }
 
-/**
- * _remove_opp_table() - Removes a OPP table
- * @opp_table: OPP table to be removed.
- *
- * Removes/frees OPP table if it doesn't contain any OPPs.
- */
-static void _remove_opp_table(struct opp_table *opp_table)
+struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
 {
-	struct opp_device *opp_dev;
+	struct opp_table *opp_table;
 
-	if (!list_empty(&opp_table->opp_list))
-		return;
+	/* Hold our table modification lock here */
+	mutex_lock(&opp_table_lock);
 
-	if (opp_table->supported_hw)
-		return;
+	opp_table = _find_opp_table_unlocked(dev);
+	if (!IS_ERR(opp_table))
+		goto unlock;
 
-	if (opp_table->prop_name)
-		return;
+	opp_table = _allocate_opp_table(dev);
 
-	if (opp_table->regulators)
-		return;
+unlock:
+	mutex_unlock(&opp_table_lock);
 
-	if (opp_table->set_opp)
-		return;
+	return opp_table;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_opp_table);
+
+static void _opp_table_kref_release(struct kref *kref)
+{
+	struct opp_table *opp_table = container_of(kref, struct opp_table, kref);
+	struct opp_device *opp_dev;
 
 	/* Release clk */
 	if (!IS_ERR(opp_table->clk))
@@ -924,63 +819,60 @@ static void _remove_opp_table(struct opp_table *opp_table)
 	/* dev_list must be empty now */
 	WARN_ON(!list_empty(&opp_table->dev_list));
 
-	list_del_rcu(&opp_table->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp_table->rcu_head,
-		  _kfree_device_rcu);
+	mutex_destroy(&opp_table->lock);
+	list_del(&opp_table->node);
+	kfree(opp_table);
+
+	mutex_unlock(&opp_table_lock);
 }
 
-/**
- * _kfree_opp_rcu() - Free OPP RCU handler
- * @head:	RCU head
- */
-static void _kfree_opp_rcu(struct rcu_head *head)
+void dev_pm_opp_put_opp_table(struct opp_table *opp_table)
 {
-	struct dev_pm_opp *opp = container_of(head, struct dev_pm_opp, rcu_head);
+	kref_put_mutex(&opp_table->kref, _opp_table_kref_release,
+		       &opp_table_lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_put_opp_table);
 
-	kfree_rcu(opp, rcu_head);
+void _opp_free(struct dev_pm_opp *opp)
+{
+	kfree(opp);
 }
 
-/**
- * _opp_remove()  - Remove an OPP from a table definition
- * @opp_table:	points back to the opp_table struct this opp belongs to
- * @opp:	pointer to the OPP to remove
- * @notify:	OPP_EVENT_REMOVE notification should be sent or not
- *
- * This function removes an opp definition from the opp table.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * It is assumed that the caller holds required mutex for an RCU updater
- * strategy.
- */
-void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp,
-		 bool notify)
+static void _opp_kref_release(struct kref *kref)
 {
+	struct dev_pm_opp *opp = container_of(kref, struct dev_pm_opp, kref);
+	struct opp_table *opp_table = opp->opp_table;
+
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	if (notify)
-		srcu_notifier_call_chain(&opp_table->srcu_head,
-					 OPP_EVENT_REMOVE, opp);
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_REMOVE, opp);
 	opp_debug_remove_one(opp);
-	list_del_rcu(&opp->node);
-	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	list_del(&opp->node);
+	kfree(opp);
 
-	_remove_opp_table(opp_table);
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+}
+
+static void dev_pm_opp_get(struct dev_pm_opp *opp)
+{
+	kref_get(&opp->kref);
 }
 
+void dev_pm_opp_put(struct dev_pm_opp *opp)
+{
+	kref_put_mutex(&opp->kref, _opp_kref_release, &opp->opp_table->lock);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_put);
+
 /**
  * dev_pm_opp_remove()  - Remove an OPP from OPP table
  * @dev:	device for which we do this operation
  * @freq:	OPP to remove with matching 'freq'
  *
  * This function removes an opp from the opp table.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 {
@@ -988,12 +880,11 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 	struct opp_table *opp_table;
 	bool found = false;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table))
-		goto unlock;
+		return;
+
+	mutex_lock(&opp_table->lock);
 
 	list_for_each_entry(opp, &opp_table->opp_list, node) {
 		if (opp->rate == freq) {
@@ -1002,28 +893,23 @@ void dev_pm_opp_remove(struct device *dev, unsigned long freq)
 		}
 	}
 
-	if (!found) {
+	mutex_unlock(&opp_table->lock);
+
+	if (found) {
+		dev_pm_opp_put(opp);
+	} else {
 		dev_warn(dev, "%s: Couldn't find OPP with freq: %lu\n",
 			 __func__, freq);
-		goto unlock;
 	}
 
-	_opp_remove(opp_table, opp, true);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove);
 
-struct dev_pm_opp *_allocate_opp(struct device *dev,
-				 struct opp_table **opp_table)
+struct dev_pm_opp *_opp_allocate(struct opp_table *table)
 {
 	struct dev_pm_opp *opp;
 	int count, supply_size;
-	struct opp_table *table;
-
-	table = _add_opp_table(dev);
-	if (!table)
-		return NULL;
 
 	/* Allocate space for at least one supply */
 	count = table->regulator_count ? table->regulator_count : 1;
@@ -1031,17 +917,13 @@ struct dev_pm_opp *_allocate_opp(struct device *dev,
 
 	/* allocate new OPP node and supplies structures */
 	opp = kzalloc(sizeof(*opp) + supply_size, GFP_KERNEL);
-	if (!opp) {
-		kfree(table);
+	if (!opp)
 		return NULL;
-	}
 
 	/* Put the supplies at the end of the OPP structure as an empty array */
 	opp->supplies = (struct dev_pm_opp_supply *)(opp + 1);
 	INIT_LIST_HEAD(&opp->node);
 
-	*opp_table = table;
-
 	return opp;
 }
 
@@ -1067,11 +949,21 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 	return true;
 }
 
+/*
+ * Returns:
+ * 0: On success. And appropriate error message for duplicate OPPs.
+ * -EBUSY: For OPP with same freq/volt and is available. The callers of
+ *  _opp_add() must return 0 if they receive -EBUSY from it. This is to make
+ *  sure we don't print error messages unnecessarily if different parts of
+ *  kernel try to initialize the OPP table.
+ * -EEXIST: For OPP with same freq but different volt or is unavailable. This
+ *  should be considered an error by the callers of _opp_add().
+ */
 int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	     struct opp_table *opp_table)
 {
 	struct dev_pm_opp *opp;
-	struct list_head *head = &opp_table->opp_list;
+	struct list_head *head;
 	int ret;
 
 	/*
@@ -1082,7 +974,10 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	 * loop, don't replace it with head otherwise it will become an infinite
 	 * loop.
 	 */
-	list_for_each_entry_rcu(opp, &opp_table->opp_list, node) {
+	mutex_lock(&opp_table->lock);
+	head = &opp_table->opp_list;
+
+	list_for_each_entry(opp, &opp_table->opp_list, node) {
 		if (new_opp->rate > opp->rate) {
 			head = &opp->node;
 			continue;
@@ -1098,12 +993,21 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 			 new_opp->supplies[0].u_volt, new_opp->available);
 
 		/* Should we compare voltages for all regulators here ? */
-		return opp->available &&
-		       new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? 0 : -EEXIST;
+		ret = opp->available &&
+		      new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
+
+		mutex_unlock(&opp_table->lock);
+		return ret;
 	}
 
+	list_add(&new_opp->node, head);
+	mutex_unlock(&opp_table->lock);
+
 	new_opp->opp_table = opp_table;
-	list_add_rcu(&new_opp->node, head);
+	kref_init(&new_opp->kref);
+
+	/* Get a reference to the OPP table */
+	_get_opp_table_kref(opp_table);
 
 	ret = opp_debug_create_one(new_opp, opp_table);
 	if (ret)
@@ -1121,6 +1025,7 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 
 /**
  * _opp_add_v1() - Allocate a OPP based on v1 bindings.
+ * @opp_table:	OPP table
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP
  * @u_volt:	Voltage in uVolts for this OPP
@@ -1133,12 +1038,6 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
  * NOTE: "dynamic" parameter impacts OPPs added by the dev_pm_opp_of_add_table
  * and freed by dev_pm_opp_of_remove_table.
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
- *
  * Return:
  * 0		On success OR
  *		Duplicate OPPs (both freq and volt are same) and opp->available
@@ -1146,22 +1045,16 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
  *		Duplicate OPPs (both freq and volt are same) and !opp->available
  * -ENOMEM	Memory allocation failure
  */
-int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
-		bool dynamic)
+int _opp_add_v1(struct opp_table *opp_table, struct device *dev,
+		unsigned long freq, long u_volt, bool dynamic)
 {
-	struct opp_table *opp_table;
 	struct dev_pm_opp *new_opp;
 	unsigned long tol;
 	int ret;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
-	new_opp = _allocate_opp(dev, &opp_table);
-	if (!new_opp) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	new_opp = _opp_allocate(opp_table);
+	if (!new_opp)
+		return -ENOMEM;
 
 	/* populate the opp table */
 	new_opp->rate = freq;
@@ -1173,22 +1066,23 @@ int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt,
 	new_opp->dynamic = dynamic;
 
 	ret = _opp_add(dev, new_opp, opp_table);
-	if (ret)
+	if (ret) {
+		/* Don't return error for duplicate OPPs */
+		if (ret == -EBUSY)
+			ret = 0;
 		goto free_opp;
-
-	mutex_unlock(&opp_table_lock);
+	}
 
 	/*
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp);
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADD, new_opp);
 	return 0;
 
 free_opp:
-	_opp_remove(opp_table, new_opp, false);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	_opp_free(new_opp);
+
 	return ret;
 }
 
@@ -1202,27 +1096,16 @@ unlock:
  * specify the hierarchy of versions it supports. OPP layer will then enable
  * OPPs, which are available for those versions, based on its 'opp-supported-hw'
  * property.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
-int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
-				unsigned int count)
+struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
+			const u32 *versions, unsigned int count)
 {
 	struct opp_table *opp_table;
-	int ret = 0;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
+	int ret;
 
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
@@ -1243,65 +1126,40 @@ int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
 	}
 
 	opp_table->supported_hw_count = count;
-	mutex_unlock(&opp_table_lock);
-	return 0;
+
+	return opp_table;
 
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw);
 
 /**
  * dev_pm_opp_put_supported_hw() - Releases resources blocked for supported hw
- * @dev: Device for which supported-hw has to be put.
+ * @opp_table: OPP table returned by dev_pm_opp_set_supported_hw().
  *
  * This is required only for the V2 bindings, and is called for a matching
  * dev_pm_opp_set_supported_hw(). Until this is called, the opp_table structure
  * will not be freed.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
-void dev_pm_opp_put_supported_hw(struct device *dev)
+void dev_pm_opp_put_supported_hw(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "Failed to find opp_table: %ld\n",
-			PTR_ERR(opp_table));
-		goto unlock;
-	}
-
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
 	if (!opp_table->supported_hw) {
-		dev_err(dev, "%s: Doesn't have supported hardware list\n",
-			__func__);
-		goto unlock;
+		pr_err("%s: Doesn't have supported hardware list\n",
+		       __func__);
+		return;
 	}
 
 	kfree(opp_table->supported_hw);
 	opp_table->supported_hw = NULL;
 	opp_table->supported_hw_count = 0;
 
-	/* Try freeing opp_table if this was the last blocking resource */
-	_remove_opp_table(opp_table);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
 
@@ -1314,26 +1172,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
  * specify the extn to be used for certain property names. The properties to
  * which the extension will apply are opp-microvolt and opp-microamp. OPP core
  * should postfix the property name with -<name> while looking for them.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
-int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
+struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
 	struct opp_table *opp_table;
-	int ret = 0;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
+	int ret;
 
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
@@ -1352,63 +1199,37 @@ int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 		goto err;
 	}
 
-	mutex_unlock(&opp_table_lock);
-	return 0;
+	return opp_table;
 
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name);
 
 /**
  * dev_pm_opp_put_prop_name() - Releases resources blocked for prop-name
- * @dev: Device for which the prop-name has to be put.
+ * @opp_table: OPP table returned by dev_pm_opp_set_prop_name().
  *
  * This is required only for the V2 bindings, and is called for a matching
  * dev_pm_opp_set_prop_name(). Until this is called, the opp_table structure
  * will not be freed.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
-void dev_pm_opp_put_prop_name(struct device *dev)
+void dev_pm_opp_put_prop_name(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table;
-
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "Failed to find opp_table: %ld\n",
-			PTR_ERR(opp_table));
-		goto unlock;
-	}
-
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
 	if (!opp_table->prop_name) {
-		dev_err(dev, "%s: Doesn't have a prop-name\n", __func__);
-		goto unlock;
+		pr_err("%s: Doesn't have a prop-name\n", __func__);
+		return;
 	}
 
 	kfree(opp_table->prop_name);
 	opp_table->prop_name = NULL;
 
-	/* Try freeing opp_table if this was the last blocking resource */
-	_remove_opp_table(opp_table);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_prop_name);
 
@@ -1455,12 +1276,6 @@ static void _free_set_opp_data(struct opp_table *opp_table)
  * well.
  *
  * This must be called before any OPPs are initialized for the device.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 					    const char * const names[],
@@ -1470,13 +1285,9 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 	struct regulator *reg;
 	int ret, i;
 
-	mutex_lock(&opp_table_lock);
-
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* This should be called before OPPs are initialized */
 	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
@@ -1518,7 +1329,6 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 	if (ret)
 		goto free_regulators;
 
-	mutex_unlock(&opp_table_lock);
 	return opp_table;
 
 free_regulators:
@@ -1529,9 +1339,7 @@ free_regulators:
 	opp_table->regulators = NULL;
 	opp_table->regulator_count = 0;
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ERR_PTR(ret);
 }
@@ -1540,22 +1348,14 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_regulators);
 /**
  * dev_pm_opp_put_regulators() - Releases resources blocked for regulator
  * @opp_table: OPP table returned from dev_pm_opp_set_regulators().
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 {
 	int i;
 
-	mutex_lock(&opp_table_lock);
-
 	if (!opp_table->regulators) {
 		pr_err("%s: Doesn't have regulators set\n", __func__);
-		goto unlock;
+		return;
 	}
 
 	/* Make sure there are no concurrent readers while updating opp_table */
@@ -1570,11 +1370,7 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 	opp_table->regulators = NULL;
 	opp_table->regulator_count = 0;
 
-	/* Try freeing opp_table if this was the last blocking resource */
-	_remove_opp_table(opp_table);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
 
@@ -1587,29 +1383,19 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
  * regulators per device), instead of the generic OPP set rate helper.
  *
  * This must be called before any OPPs are initialized for the device.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
-int dev_pm_opp_register_set_opp_helper(struct device *dev,
+struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 			int (*set_opp)(struct dev_pm_set_opp_data *data))
 {
 	struct opp_table *opp_table;
 	int ret;
 
 	if (!set_opp)
-		return -EINVAL;
-
-	mutex_lock(&opp_table_lock);
+		return ERR_PTR(-EINVAL);
 
-	opp_table = _add_opp_table(dev);
-	if (!opp_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return ERR_PTR(-ENOMEM);
 
 	/* This should be called before OPPs are initialized */
 	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
@@ -1625,47 +1411,28 @@ int dev_pm_opp_register_set_opp_helper(struct device *dev,
 
 	opp_table->set_opp = set_opp;
 
-	mutex_unlock(&opp_table_lock);
-	return 0;
+	return opp_table;
 
 err:
-	_remove_opp_table(opp_table);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 
-	return ret;
+	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
 
 /**
  * dev_pm_opp_register_put_opp_helper() - Releases resources blocked for
  *					   set_opp helper
- * @dev: Device for which custom set_opp helper has to be cleared.
+ * @opp_table: OPP table returned from dev_pm_opp_register_set_opp_helper().
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
+ * Release resources blocked for platform specific set_opp helper.
  */
-void dev_pm_opp_register_put_opp_helper(struct device *dev)
+void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table)
 {
-	struct opp_table *opp_table;
-
-	mutex_lock(&opp_table_lock);
-
-	/* Check for existing table for 'dev' first */
-	opp_table = _find_opp_table(dev);
-	if (IS_ERR(opp_table)) {
-		dev_err(dev, "Failed to find opp_table: %ld\n",
-			PTR_ERR(opp_table));
-		goto unlock;
-	}
-
 	if (!opp_table->set_opp) {
-		dev_err(dev, "%s: Doesn't have custom set_opp helper set\n",
-			__func__);
-		goto unlock;
+		pr_err("%s: Doesn't have custom set_opp helper set\n",
+		       __func__);
+		return;
 	}
 
 	/* Make sure there are no concurrent readers while updating opp_table */
@@ -1673,11 +1440,7 @@ void dev_pm_opp_register_put_opp_helper(struct device *dev)
 
 	opp_table->set_opp = NULL;
 
-	/* Try freeing opp_table if this was the last blocking resource */
-	_remove_opp_table(opp_table);
-
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
 
@@ -1691,12 +1454,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
  * The opp is made available by default and it can be controlled using
  * dev_pm_opp_enable/disable functions.
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
- *
  * Return:
  * 0		On success OR
  *		Duplicate OPPs (both freq and volt are same) and opp->available
@@ -1706,7 +1463,17 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_register_put_opp_helper);
  */
 int dev_pm_opp_add(struct device *dev, unsigned long freq, unsigned long u_volt)
 {
-	return _opp_add_v1(dev, freq, u_volt, true);
+	struct opp_table *opp_table;
+	int ret;
+
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
+
+	ret = _opp_add_v1(opp_table, dev, freq, u_volt, true);
+
+	dev_pm_opp_put_opp_table(opp_table);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_add);
 
@@ -1716,41 +1483,30 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add);
  * @freq:		OPP frequency to modify availability
  * @availability_req:	availability status requested for this opp
  *
- * Set the availability of an OPP with an RCU operation, opp_{enable,disable}
- * share a common logic which is isolated here.
+ * Set the availability of an OPP, opp_{enable,disable} share a common logic
+ * which is isolated here.
  *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
  * copy operation, returns 0 if no modification was done OR modification was
  * successful.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks to
- * keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex locking or synchronize_rcu() blocking calls cannot be used.
  */
 static int _opp_set_availability(struct device *dev, unsigned long freq,
 				 bool availability_req)
 {
 	struct opp_table *opp_table;
-	struct dev_pm_opp *new_opp, *tmp_opp, *opp = ERR_PTR(-ENODEV);
+	struct dev_pm_opp *tmp_opp, *opp = ERR_PTR(-ENODEV);
 	int r = 0;
 
-	/* keep the node allocated */
-	new_opp = kmalloc(sizeof(*new_opp), GFP_KERNEL);
-	if (!new_opp)
-		return -ENOMEM;
-
-	mutex_lock(&opp_table_lock);
-
 	/* Find the opp_table */
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		r = PTR_ERR(opp_table);
 		dev_warn(dev, "%s: Device OPP not found (%d)\n", __func__, r);
-		goto unlock;
+		return r;
 	}
 
+	mutex_lock(&opp_table->lock);
+
 	/* Do we have the frequency? */
 	list_for_each_entry(tmp_opp, &opp_table->opp_list, node) {
 		if (tmp_opp->rate == freq) {
@@ -1758,6 +1514,7 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 			break;
 		}
 	}
+
 	if (IS_ERR(opp)) {
 		r = PTR_ERR(opp);
 		goto unlock;
@@ -1766,29 +1523,20 @@ static int _opp_set_availability(struct device *dev, unsigned long freq,
 	/* Is update really needed? */
 	if (opp->available == availability_req)
 		goto unlock;
-	/* copy the old data over */
-	*new_opp = *opp;
 
-	/* plug in new node */
-	new_opp->available = availability_req;
-
-	list_replace_rcu(&opp->node, &new_opp->node);
-	mutex_unlock(&opp_table_lock);
-	call_srcu(&opp_table->srcu_head.srcu, &opp->rcu_head, _kfree_opp_rcu);
+	opp->available = availability_req;
 
 	/* Notify the change of the OPP availability */
 	if (availability_req)
-		srcu_notifier_call_chain(&opp_table->srcu_head,
-					 OPP_EVENT_ENABLE, new_opp);
+		blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ENABLE,
+					     opp);
 	else
-		srcu_notifier_call_chain(&opp_table->srcu_head,
-					 OPP_EVENT_DISABLE, new_opp);
-
-	return 0;
+		blocking_notifier_call_chain(&opp_table->head,
+					     OPP_EVENT_DISABLE, opp);
 
 unlock:
-	mutex_unlock(&opp_table_lock);
-	kfree(new_opp);
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
 	return r;
 }
 
@@ -1801,12 +1549,6 @@ unlock:
  * corresponding error value. It is meant to be used for users an OPP available
  * after being temporarily made unavailable with dev_pm_opp_disable.
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly uses RCU and mutex locks to keep the
- * integrity of the internal data structures. Callers should ensure that
- * this function is *NOT* called under RCU protection or in contexts where
- * mutex locking or synchronize_rcu() blocking calls cannot be used.
- *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
  * copy operation, returns 0 if no modification was done OR modification was
  * successful.
@@ -1827,12 +1569,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable);
  * control by users to make this OPP not available until the circumstances are
  * right to make it available again (with a call to dev_pm_opp_enable).
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly uses RCU and mutex locks to keep the
- * integrity of the internal data structures. Callers should ensure that
- * this function is *NOT* called under RCU protection or in contexts where
- * mutex locking or synchronize_rcu() blocking calls cannot be used.
- *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
  * copy operation, returns 0 if no modification was done OR modification was
  * successful.
@@ -1844,41 +1580,78 @@ int dev_pm_opp_disable(struct device *dev, unsigned long freq)
 EXPORT_SYMBOL_GPL(dev_pm_opp_disable);
 
 /**
- * dev_pm_opp_get_notifier() - find notifier_head of the device with opp
- * @dev:	device pointer used to lookup OPP table.
+ * dev_pm_opp_register_notifier() - Register OPP notifier for the device
+ * @dev:	Device for which notifier needs to be registered
+ * @nb:		Notifier block to be registered
  *
- * Return: pointer to  notifier head if found, otherwise -ENODEV or
- * -EINVAL based on type of error casted as pointer. value must be checked
- *  with IS_ERR to determine valid pointer or error result.
+ * Return: 0 on success or a negative error value.
+ */
+int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb)
+{
+	struct opp_table *opp_table;
+	int ret;
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
+
+	ret = blocking_notifier_chain_register(&opp_table->head, nb);
+
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_pm_opp_register_notifier);
+
+/**
+ * dev_pm_opp_unregister_notifier() - Unregister OPP notifier for the device
+ * @dev:	Device for which notifier needs to be unregistered
+ * @nb:		Notifier block to be unregistered
  *
- * Locking: This function must be called under rcu_read_lock(). opp_table is a
- * RCU protected pointer. The reason for the same is that the opp pointer which
- * is returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * Return: 0 on success or a negative error value.
  */
-struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev)
+int dev_pm_opp_unregister_notifier(struct device *dev,
+				   struct notifier_block *nb)
 {
-	struct opp_table *opp_table = _find_opp_table(dev);
+	struct opp_table *opp_table;
+	int ret;
 
+	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table))
-		return ERR_CAST(opp_table); /* matching type */
+		return PTR_ERR(opp_table);
+
+	ret = blocking_notifier_chain_unregister(&opp_table->head, nb);
 
-	return &opp_table->srcu_head;
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return ret;
 }
-EXPORT_SYMBOL_GPL(dev_pm_opp_get_notifier);
+EXPORT_SYMBOL(dev_pm_opp_unregister_notifier);
 
 /*
  * Free OPPs either created using static entries present in DT or even the
  * dynamically added entries based on remove_all param.
  */
-void _dev_pm_opp_remove_table(struct device *dev, bool remove_all)
+void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev,
+			      bool remove_all)
 {
-	struct opp_table *opp_table;
 	struct dev_pm_opp *opp, *tmp;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
+	/* Find if opp_table manages a single device */
+	if (list_is_singular(&opp_table->dev_list)) {
+		/* Free static OPPs */
+		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
+			if (remove_all || !opp->dynamic)
+				dev_pm_opp_put(opp);
+		}
+	} else {
+		_remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table);
+	}
+}
+
+void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all)
+{
+	struct opp_table *opp_table;
 
 	/* Check for existing table for 'dev' */
 	opp_table = _find_opp_table(dev);
@@ -1890,22 +1663,12 @@ void _dev_pm_opp_remove_table(struct device *dev, bool remove_all)
 			     IS_ERR_OR_NULL(dev) ?
 					"Invalid device" : dev_name(dev),
 			     error);
-		goto unlock;
+		return;
 	}
 
-	/* Find if opp_table manages a single device */
-	if (list_is_singular(&opp_table->dev_list)) {
-		/* Free static OPPs */
-		list_for_each_entry_safe(opp, tmp, &opp_table->opp_list, node) {
-			if (remove_all || !opp->dynamic)
-				_opp_remove(opp_table, opp, true);
-		}
-	} else {
-		_remove_opp_dev(_find_opp_dev(dev, opp_table), opp_table);
-	}
+	_dev_pm_opp_remove_table(opp_table, dev, remove_all);
 
-unlock:
-	mutex_unlock(&opp_table_lock);
+	dev_pm_opp_put_opp_table(opp_table);
 }
 
 /**
@@ -1914,15 +1677,9 @@ unlock:
  *
  * Free both OPPs created using static entries present in DT and the
  * dynamically added entries.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 void dev_pm_opp_remove_table(struct device *dev)
 {
-	_dev_pm_opp_remove_table(dev, true);
+	_dev_pm_opp_find_and_remove_table(dev, true);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_remove_table);
diff --git a/drivers/base/power/opp/cpu.c b/drivers/base/power/opp/cpu.c
index 8c3434bdb26d..2d87bc1adf38 100644
--- a/drivers/base/power/opp/cpu.c
+++ b/drivers/base/power/opp/cpu.c
@@ -42,11 +42,6 @@
  *
  * WARNING: It is  important for the callers to ensure refreshing their copy of
  * the table if any of the mentioned functions have been invoked in the interim.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Since we just use the regular accessor functions to access the internal data
- * structures, we use RCU read lock inside this function. As a result, users of
- * this function DONOT need to use explicit locks for invoking.
  */
 int dev_pm_opp_init_cpufreq_table(struct device *dev,
 				  struct cpufreq_frequency_table **table)
@@ -56,19 +51,13 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 	int i, max_opps, ret = 0;
 	unsigned long rate;
 
-	rcu_read_lock();
-
 	max_opps = dev_pm_opp_get_opp_count(dev);
-	if (max_opps <= 0) {
-		ret = max_opps ? max_opps : -ENODATA;
-		goto out;
-	}
+	if (max_opps <= 0)
+		return max_opps ? max_opps : -ENODATA;
 
 	freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC);
-	if (!freq_table) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!freq_table)
+		return -ENOMEM;
 
 	for (i = 0, rate = 0; i < max_opps; i++, rate++) {
 		/* find next rate */
@@ -83,6 +72,8 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 		/* Is Boost/turbo opp ? */
 		if (dev_pm_opp_is_turbo(opp))
 			freq_table[i].flags = CPUFREQ_BOOST_FREQ;
+
+		dev_pm_opp_put(opp);
 	}
 
 	freq_table[i].driver_data = i;
@@ -91,7 +82,6 @@ int dev_pm_opp_init_cpufreq_table(struct device *dev,
 	*table = &freq_table[0];
 
 out:
-	rcu_read_unlock();
 	if (ret)
 		kfree(freq_table);
 
@@ -147,12 +137,6 @@ void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of)
  * This removes the OPP tables for CPUs present in the @cpumask.
  * This should be used to remove all the OPPs entries associated with
  * the cpus in @cpumask.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask)
 {
@@ -169,12 +153,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_cpumask_remove_table);
  * @cpumask.
  *
  * Returns -ENODEV if OPP table isn't already present.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
 				const struct cpumask *cpumask)
@@ -184,13 +162,9 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
 	struct device *dev;
 	int cpu, ret = 0;
 
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _find_opp_table(cpu_dev);
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
-		goto unlock;
-	}
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
 
 	for_each_cpu(cpu, cpumask) {
 		if (cpu == cpu_dev->id)
@@ -213,8 +187,8 @@ int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev,
 		/* Mark opp-table as multiple CPUs are sharing it now */
 		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
 	}
-unlock:
-	mutex_unlock(&opp_table_lock);
+
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
@@ -229,12 +203,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_set_sharing_cpus);
  *
  * Returns -ENODEV if OPP table isn't already present and -EINVAL if the OPP
  * table's status is access-unknown.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 {
@@ -242,17 +210,13 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 	struct opp_table *opp_table;
 	int ret = 0;
 
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _find_opp_table(cpu_dev);
-	if (IS_ERR(opp_table)) {
-		ret = PTR_ERR(opp_table);
-		goto unlock;
-	}
+	if (IS_ERR(opp_table))
+		return PTR_ERR(opp_table);
 
 	if (opp_table->shared_opp == OPP_TABLE_ACCESS_UNKNOWN) {
 		ret = -EINVAL;
-		goto unlock;
+		goto put_opp_table;
 	}
 
 	cpumask_clear(cpumask);
@@ -264,8 +228,8 @@ int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
 		cpumask_set_cpu(cpu_dev->id, cpumask);
 	}
 
-unlock:
-	mutex_unlock(&opp_table_lock);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
diff --git a/drivers/base/power/opp/of.c b/drivers/base/power/opp/of.c
index 3f7d2591b173..779428676f63 100644
--- a/drivers/base/power/opp/of.c
+++ b/drivers/base/power/opp/of.c
@@ -24,9 +24,11 @@
 
 static struct opp_table *_managed_opp(const struct device_node *np)
 {
-	struct opp_table *opp_table;
+	struct opp_table *opp_table, *managed_table = NULL;
+
+	mutex_lock(&opp_table_lock);
 
-	list_for_each_entry_rcu(opp_table, &opp_tables, node) {
+	list_for_each_entry(opp_table, &opp_tables, node) {
 		if (opp_table->np == np) {
 			/*
 			 * Multiple devices can point to the same OPP table and
@@ -35,14 +37,18 @@ static struct opp_table *_managed_opp(const struct device_node *np)
 			 * But the OPPs will be considered as shared only if the
 			 * OPP table contains a "opp-shared" property.
 			 */
-			if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED)
-				return opp_table;
+			if (opp_table->shared_opp == OPP_TABLE_ACCESS_SHARED) {
+				_get_opp_table_kref(opp_table);
+				managed_table = opp_table;
+			}
 
-			return NULL;
+			break;
 		}
 	}
 
-	return NULL;
+	mutex_unlock(&opp_table_lock);
+
+	return managed_table;
 }
 
 void _of_init_opp_table(struct opp_table *opp_table, struct device *dev)
@@ -229,34 +235,28 @@ free_microvolt:
  * @dev:	device pointer used to lookup OPP table.
  *
  * Free OPPs created using static entries present in DT.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 void dev_pm_opp_of_remove_table(struct device *dev)
 {
-	_dev_pm_opp_remove_table(dev, false);
+	_dev_pm_opp_find_and_remove_table(dev, false);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 
 /* Returns opp descriptor node for a device, caller must do of_node_put() */
-static struct device_node *_of_get_opp_desc_node(struct device *dev)
+struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev)
 {
 	/*
-	 * TODO: Support for multiple OPP tables.
-	 *
 	 * There should be only ONE phandle present in "operating-points-v2"
 	 * property.
 	 */
 
 	return of_parse_phandle(dev->of_node, "operating-points-v2", 0);
 }
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node);
 
 /**
  * _opp_add_static_v2() - Allocate static OPPs (As per 'v2' DT bindings)
+ * @opp_table:	OPP table
  * @dev:	device for which we do this operation
  * @np:		device node
  *
@@ -264,12 +264,6 @@ static struct device_node *_of_get_opp_desc_node(struct device *dev)
  * opp can be controlled using dev_pm_opp_enable/disable functions and may be
  * removed by dev_pm_opp_remove.
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
- *
  * Return:
  * 0		On success OR
  *		Duplicate OPPs (both freq and volt are same) and opp->available
@@ -278,22 +272,17 @@ static struct device_node *_of_get_opp_desc_node(struct device *dev)
  * -ENOMEM	Memory allocation failure
  * -EINVAL	Failed parsing the OPP node
  */
-static int _opp_add_static_v2(struct device *dev, struct device_node *np)
+static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
+			      struct device_node *np)
 {
-	struct opp_table *opp_table;
 	struct dev_pm_opp *new_opp;
 	u64 rate;
 	u32 val;
 	int ret;
 
-	/* Hold our table modification lock here */
-	mutex_lock(&opp_table_lock);
-
-	new_opp = _allocate_opp(dev, &opp_table);
-	if (!new_opp) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	new_opp = _opp_allocate(opp_table);
+	if (!new_opp)
+		return -ENOMEM;
 
 	ret = of_property_read_u64(np, "opp-hz", &rate);
 	if (ret < 0) {
@@ -327,8 +316,12 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 		goto free_opp;
 
 	ret = _opp_add(dev, new_opp, opp_table);
-	if (ret)
+	if (ret) {
+		/* Don't return error for duplicate OPPs */
+		if (ret == -EBUSY)
+			ret = 0;
 		goto free_opp;
+	}
 
 	/* OPP to select on device suspend */
 	if (of_property_read_bool(np, "opp-suspend")) {
@@ -345,8 +338,6 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	if (new_opp->clock_latency_ns > opp_table->clock_latency_ns_max)
 		opp_table->clock_latency_ns_max = new_opp->clock_latency_ns;
 
-	mutex_unlock(&opp_table_lock);
-
 	pr_debug("%s: turbo:%d rate:%lu uv:%lu uvmin:%lu uvmax:%lu latency:%lu\n",
 		 __func__, new_opp->turbo, new_opp->rate,
 		 new_opp->supplies[0].u_volt, new_opp->supplies[0].u_volt_min,
@@ -356,13 +347,12 @@ static int _opp_add_static_v2(struct device *dev, struct device_node *np)
 	 * Notify the changes in the availability of the operable
 	 * frequency/voltage list.
 	 */
-	srcu_notifier_call_chain(&opp_table->srcu_head, OPP_EVENT_ADD, new_opp);
+	blocking_notifier_call_chain(&opp_table->head, OPP_EVENT_ADD, new_opp);
 	return 0;
 
 free_opp:
-	_opp_remove(opp_table, new_opp, false);
-unlock:
-	mutex_unlock(&opp_table_lock);
+	_opp_free(new_opp);
+
 	return ret;
 }
 
@@ -373,41 +363,35 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 	struct opp_table *opp_table;
 	int ret = 0, count = 0;
 
-	mutex_lock(&opp_table_lock);
-
 	opp_table = _managed_opp(opp_np);
 	if (opp_table) {
 		/* OPPs are already managed */
 		if (!_add_opp_dev(dev, opp_table))
 			ret = -ENOMEM;
-		mutex_unlock(&opp_table_lock);
-		return ret;
+		goto put_opp_table;
 	}
-	mutex_unlock(&opp_table_lock);
+
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
 
 	/* We have opp-table node now, iterate over it and add OPPs */
 	for_each_available_child_of_node(opp_np, np) {
 		count++;
 
-		ret = _opp_add_static_v2(dev, np);
+		ret = _opp_add_static_v2(opp_table, dev, np);
 		if (ret) {
 			dev_err(dev, "%s: Failed to add OPP, %d\n", __func__,
 				ret);
-			goto free_table;
+			_dev_pm_opp_remove_table(opp_table, dev, false);
+			goto put_opp_table;
 		}
 	}
 
 	/* There should be one of more OPP defined */
-	if (WARN_ON(!count))
-		return -ENOENT;
-
-	mutex_lock(&opp_table_lock);
-
-	opp_table = _find_opp_table(dev);
-	if (WARN_ON(IS_ERR(opp_table))) {
-		ret = PTR_ERR(opp_table);
-		mutex_unlock(&opp_table_lock);
-		goto free_table;
+	if (WARN_ON(!count)) {
+		ret = -ENOENT;
+		goto put_opp_table;
 	}
 
 	opp_table->np = opp_np;
@@ -416,12 +400,8 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 	else
 		opp_table->shared_opp = OPP_TABLE_ACCESS_EXCLUSIVE;
 
-	mutex_unlock(&opp_table_lock);
-
-	return 0;
-
-free_table:
-	dev_pm_opp_of_remove_table(dev);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
 
 	return ret;
 }
@@ -429,9 +409,10 @@ free_table:
 /* Initializes OPP tables based on old-deprecated bindings */
 static int _of_add_opp_table_v1(struct device *dev)
 {
+	struct opp_table *opp_table;
 	const struct property *prop;
 	const __be32 *val;
-	int nr;
+	int nr, ret = 0;
 
 	prop = of_find_property(dev->of_node, "operating-points", NULL);
 	if (!prop)
@@ -449,18 +430,27 @@ static int _of_add_opp_table_v1(struct device *dev)
 		return -EINVAL;
 	}
 
+	opp_table = dev_pm_opp_get_opp_table(dev);
+	if (!opp_table)
+		return -ENOMEM;
+
 	val = prop->value;
 	while (nr) {
 		unsigned long freq = be32_to_cpup(val++) * 1000;
 		unsigned long volt = be32_to_cpup(val++);
 
-		if (_opp_add_v1(dev, freq, volt, false))
-			dev_warn(dev, "%s: Failed to add OPP %ld\n",
-				 __func__, freq);
+		ret = _opp_add_v1(opp_table, dev, freq, volt, false);
+		if (ret) {
+			dev_err(dev, "%s: Failed to add OPP %ld (%d)\n",
+				__func__, freq, ret);
+			_dev_pm_opp_remove_table(opp_table, dev, false);
+			break;
+		}
 		nr -= 2;
 	}
 
-	return 0;
+	dev_pm_opp_put_opp_table(opp_table);
+	return ret;
 }
 
 /**
@@ -469,12 +459,6 @@ static int _of_add_opp_table_v1(struct device *dev)
  *
  * Register the initial OPP table with the OPP library for given device.
  *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function indirectly uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
- *
  * Return:
  * 0		On success OR
  *		Duplicate OPPs (both freq and volt are same) and opp->available
@@ -495,7 +479,7 @@ int dev_pm_opp_of_add_table(struct device *dev)
 	 * OPPs have two version of bindings now. The older one is deprecated,
 	 * try for the new binding first.
 	 */
-	opp_np = _of_get_opp_desc_node(dev);
+	opp_np = dev_pm_opp_of_get_opp_desc_node(dev);
 	if (!opp_np) {
 		/*
 		 * Try old-deprecated bindings for backward compatibility with
@@ -519,12 +503,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
  *
  * This removes the OPP tables for CPUs present in the @cpumask.
  * This should be used only to remove static entries created from DT.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask)
 {
@@ -537,12 +515,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_remove_table);
  * @cpumask:	cpumask for which OPP table needs to be added.
  *
  * This adds the OPP tables for CPUs present in the @cpumask.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask)
 {
@@ -590,12 +562,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_cpumask_add_table);
  * This updates the @cpumask with CPUs that are sharing OPPs with @cpu_dev.
  *
  * Returns -ENOENT if operating-points-v2 isn't present for @cpu_dev.
- *
- * Locking: The internal opp_table and opp structures are RCU protected.
- * Hence this function internally uses RCU updater strategy with mutex locks
- * to keep the integrity of the internal data structures. Callers should ensure
- * that this function is *NOT* called under RCU protection or in contexts where
- * mutex cannot be locked.
  */
 int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 				   struct cpumask *cpumask)
@@ -605,7 +571,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 	int cpu, ret = 0;
 
 	/* Get OPP descriptor node */
-	np = _of_get_opp_desc_node(cpu_dev);
+	np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
 	if (!np) {
 		dev_dbg(cpu_dev, "%s: Couldn't find opp node.\n", __func__);
 		return -ENOENT;
@@ -630,7 +596,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 		}
 
 		/* Get OPP descriptor node */
-		tmp_np = _of_get_opp_desc_node(tcpu_dev);
+		tmp_np = dev_pm_opp_of_get_opp_desc_node(tcpu_dev);
 		if (!tmp_np) {
 			dev_err(tcpu_dev, "%s: Couldn't find opp node.\n",
 				__func__);
diff --git a/drivers/base/power/opp/opp.h b/drivers/base/power/opp/opp.h
index af9f2b849a66..166eef990599 100644
--- a/drivers/base/power/opp/opp.h
+++ b/drivers/base/power/opp/opp.h
@@ -16,11 +16,11 @@
 
 #include <linux/device.h>
 #include <linux/kernel.h>
+#include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <linux/pm_opp.h>
-#include <linux/rculist.h>
-#include <linux/rcupdate.h>
+#include <linux/notifier.h>
 
 struct clk;
 struct regulator;
@@ -51,11 +51,9 @@ extern struct list_head opp_tables;
  * @node:	opp table node. The nodes are maintained throughout the lifetime
  *		of boot. It is expected only an optimal set of OPPs are
  *		added to the library by the SoC framework.
- *		RCU usage: opp table is traversed with RCU locks. node
- *		modification is possible realtime, hence the modifications
- *		are protected by the opp_table_lock for integrity.
  *		IMPORTANT: the opp nodes should be maintained in increasing
  *		order.
+ * @kref:	for reference count of the OPP.
  * @available:	true/false - marks if this OPP as available or not
  * @dynamic:	not-created from static DT entries.
  * @turbo:	true if turbo (boost) OPP
@@ -65,7 +63,6 @@ extern struct list_head opp_tables;
  * @clock_latency_ns: Latency (in nanoseconds) of switching to this OPP's
  *		frequency from any other OPP's frequency.
  * @opp_table:	points back to the opp_table struct this opp belongs to
- * @rcu_head:	RCU callback head used for deferred freeing
  * @np:		OPP's device node.
  * @dentry:	debugfs dentry pointer (per opp)
  *
@@ -73,6 +70,7 @@ extern struct list_head opp_tables;
  */
 struct dev_pm_opp {
 	struct list_head node;
+	struct kref kref;
 
 	bool available;
 	bool dynamic;
@@ -85,7 +83,6 @@ struct dev_pm_opp {
 	unsigned long clock_latency_ns;
 
 	struct opp_table *opp_table;
-	struct rcu_head rcu_head;
 
 	struct device_node *np;
 
@@ -98,7 +95,6 @@ struct dev_pm_opp {
  * struct opp_device - devices managed by 'struct opp_table'
  * @node:	list node
  * @dev:	device to which the struct object belongs
- * @rcu_head:	RCU callback head used for deferred freeing
  * @dentry:	debugfs dentry pointer (per device)
  *
  * This is an internal data structure maintaining the devices that are managed
@@ -107,7 +103,6 @@ struct dev_pm_opp {
 struct opp_device {
 	struct list_head node;
 	const struct device *dev;
-	struct rcu_head rcu_head;
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
@@ -125,12 +120,11 @@ enum opp_table_access {
  * @node:	table node - contains the devices with OPPs that
  *		have been registered. Nodes once added are not modified in this
  *		table.
- *		RCU usage: nodes are not modified in the table of opp_table,
- *		however addition is possible and is secured by opp_table_lock
- * @srcu_head:	notifier head to notify the OPP availability changes.
- * @rcu_head:	RCU callback head used for deferred freeing
+ * @head:	notifier head to notify the OPP availability changes.
  * @dev_list:	list of devices that share these OPPs
  * @opp_list:	table of opps
+ * @kref:	for reference count of the table.
+ * @lock:	mutex protecting the opp_list.
  * @np:		struct device_node pointer for opp's DT node.
  * @clock_latency_ns_max: Max clock latency in nanoseconds.
  * @shared_opp: OPP is shared between multiple devices.
@@ -151,18 +145,15 @@ enum opp_table_access {
  * This is an internal data structure maintaining the link to opps attached to
  * a device. This structure is not meant to be shared to users as it is
  * meant for book keeping and private to OPP library.
- *
- * Because the opp structures can be used from both rcu and srcu readers, we
- * need to wait for the grace period of both of them before freeing any
- * resources. And so we have used kfree_rcu() from within call_srcu() handlers.
  */
 struct opp_table {
 	struct list_head node;
 
-	struct srcu_notifier_head srcu_head;
-	struct rcu_head rcu_head;
+	struct blocking_notifier_head head;
 	struct list_head dev_list;
 	struct list_head opp_list;
+	struct kref kref;
+	struct mutex lock;
 
 	struct device_node *np;
 	unsigned long clock_latency_ns_max;
@@ -190,14 +181,17 @@ struct opp_table {
 };
 
 /* Routines internal to opp core */
+void _get_opp_table_kref(struct opp_table *opp_table);
 struct opp_table *_find_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
-void _dev_pm_opp_remove_table(struct device *dev, bool remove_all);
-struct dev_pm_opp *_allocate_opp(struct device *dev, struct opp_table **opp_table);
+void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev, bool remove_all);
+void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all);
+struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table);
+void _opp_free(struct dev_pm_opp *opp);
 int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
-void _opp_remove(struct opp_table *opp_table, struct dev_pm_opp *opp, bool notify);
-int _opp_add_v1(struct device *dev, unsigned long freq, long u_volt, bool dynamic);
+int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic);
 void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of);
+struct opp_table *_add_opp_table(struct device *dev);
 
 #ifdef CONFIG_OF
 void _of_init_opp_table(struct opp_table *opp_table, struct device *dev);
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 58fcc758334e..d888d9869b6a 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -281,7 +281,7 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 	dev->power.qos = ERR_PTR(-ENODEV);
 	spin_unlock_irq(&dev->power.lock);
 
-	kfree(c->notifiers);
+	kfree(qos->resume_latency.notifiers);
 	kfree(qos);
 
  out:
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 872eac4cb1df..a14fac6a01d3 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -966,13 +966,13 @@ int __pm_runtime_idle(struct device *dev, int rpmflags)
 	unsigned long flags;
 	int retval;
 
-	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
-
 	if (rpmflags & RPM_GET_PUT) {
 		if (!atomic_dec_and_test(&dev->power.usage_count))
 			return 0;
 	}
 
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
 	spin_lock_irqsave(&dev->power.lock, flags);
 	retval = rpm_idle(dev, rpmflags);
 	spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -998,13 +998,13 @@ int __pm_runtime_suspend(struct device *dev, int rpmflags)
 	unsigned long flags;
 	int retval;
 
-	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
-
 	if (rpmflags & RPM_GET_PUT) {
 		if (!atomic_dec_and_test(&dev->power.usage_count))
 			return 0;
 	}
 
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+
 	spin_lock_irqsave(&dev->power.lock, flags);
 	retval = rpm_suspend(dev, rpmflags);
 	spin_unlock_irqrestore(&dev->power.lock, flags);
@@ -1029,7 +1029,8 @@ int __pm_runtime_resume(struct device *dev, int rpmflags)
 	unsigned long flags;
 	int retval;
 
-	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe);
+	might_sleep_if(!(rpmflags & RPM_ASYNC) && !dev->power.irq_safe &&
+			dev->power.runtime_status != RPM_ACTIVE);
 
 	if (rpmflags & RPM_GET_PUT)
 		atomic_inc(&dev->power.usage_count);
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 404d94c6c8bc..ae0429827f31 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -141,6 +141,13 @@ static irqreturn_t handle_threaded_wake_irq(int irq, void *_wirq)
 	struct wake_irq *wirq = _wirq;
 	int res;
 
+	/* Maybe abort suspend? */
+	if (irqd_is_wakeup_set(irq_get_irq_data(irq))) {
+		pm_wakeup_event(wirq->dev, 0);
+
+		return IRQ_HANDLED;
+	}
+
 	/* We don't want RPM_ASYNC or RPM_NOWAIT here */
 	res = pm_runtime_resume(wirq->dev);
 	if (res < 0)
@@ -183,6 +190,9 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq)
 	wirq->irq = irq;
 	irq_set_status_flags(irq, IRQ_NOAUTOEN);
 
+	/* Prevent deferred spurious wakeirqs with disable_irq_nosync() */
+	irq_set_status_flags(irq, IRQ_DISABLE_UNLAZY);
+
 	/*
 	 * Consumer device may need to power up and restore state
 	 * so we use a threaded irq.
@@ -312,8 +322,12 @@ void dev_pm_arm_wake_irq(struct wake_irq *wirq)
 	if (!wirq)
 		return;
 
-	if (device_may_wakeup(wirq->dev))
+	if (device_may_wakeup(wirq->dev)) {
+		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)
+			enable_irq(wirq->irq);
+
 		enable_irq_wake(wirq->irq);
+	}
 }
 
 /**
@@ -328,6 +342,10 @@ void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
 	if (!wirq)
 		return;
 
-	if (device_may_wakeup(wirq->dev))
+	if (device_may_wakeup(wirq->dev)) {
 		disable_irq_wake(wirq->irq);
+
+		if (wirq->status & WAKE_IRQ_DEDICATED_ALLOCATED)
+			disable_irq_nosync(wirq->irq);
+	}
 }
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 43a36d68c3fd..c458c63e353f 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -21,7 +21,7 @@
 
 struct property_set {
 	struct fwnode_handle fwnode;
-	struct property_entry *properties;
+	const struct property_entry *properties;
 };
 
 static inline bool is_pset_node(struct fwnode_handle *fwnode)
@@ -35,10 +35,10 @@ static inline struct property_set *to_pset_node(struct fwnode_handle *fwnode)
 		container_of(fwnode, struct property_set, fwnode) : NULL;
 }
 
-static struct property_entry *pset_prop_get(struct property_set *pset,
-					    const char *name)
+static const struct property_entry *pset_prop_get(struct property_set *pset,
+						  const char *name)
 {
-	struct property_entry *prop;
+	const struct property_entry *prop;
 
 	if (!pset || !pset->properties)
 		return NULL;
@@ -50,11 +50,11 @@ static struct property_entry *pset_prop_get(struct property_set *pset,
 	return NULL;
 }
 
-static void *pset_prop_find(struct property_set *pset, const char *propname,
-			    size_t length)
+static const void *pset_prop_find(struct property_set *pset,
+				  const char *propname, size_t length)
 {
-	struct property_entry *prop;
-	void *pointer;
+	const struct property_entry *prop;
+	const void *pointer;
 
 	prop = pset_prop_get(pset, propname);
 	if (!prop)
@@ -74,7 +74,7 @@ static int pset_prop_read_u8_array(struct property_set *pset,
 				   const char *propname,
 				   u8 *values, size_t nval)
 {
-	void *pointer;
+	const void *pointer;
 	size_t length = nval * sizeof(*values);
 
 	pointer = pset_prop_find(pset, propname, length);
@@ -89,7 +89,7 @@ static int pset_prop_read_u16_array(struct property_set *pset,
 				    const char *propname,
 				    u16 *values, size_t nval)
 {
-	void *pointer;
+	const void *pointer;
 	size_t length = nval * sizeof(*values);
 
 	pointer = pset_prop_find(pset, propname, length);
@@ -104,7 +104,7 @@ static int pset_prop_read_u32_array(struct property_set *pset,
 				    const char *propname,
 				    u32 *values, size_t nval)
 {
-	void *pointer;
+	const void *pointer;
 	size_t length = nval * sizeof(*values);
 
 	pointer = pset_prop_find(pset, propname, length);
@@ -119,7 +119,7 @@ static int pset_prop_read_u64_array(struct property_set *pset,
 				    const char *propname,
 				    u64 *values, size_t nval)
 {
-	void *pointer;
+	const void *pointer;
 	size_t length = nval * sizeof(*values);
 
 	pointer = pset_prop_find(pset, propname, length);
@@ -133,7 +133,7 @@ static int pset_prop_read_u64_array(struct property_set *pset,
 static int pset_prop_count_elems_of_size(struct property_set *pset,
 					 const char *propname, size_t length)
 {
-	struct property_entry *prop;
+	const struct property_entry *prop;
 
 	prop = pset_prop_get(pset, propname);
 	if (!prop)
@@ -146,7 +146,7 @@ static int pset_prop_read_string_array(struct property_set *pset,
 				       const char *propname,
 				       const char **strings, size_t nval)
 {
-	void *pointer;
+	const void *pointer;
 	size_t length = nval * sizeof(*strings);
 
 	pointer = pset_prop_find(pset, propname, length);
@@ -160,8 +160,8 @@ static int pset_prop_read_string_array(struct property_set *pset,
 static int pset_prop_read_string(struct property_set *pset,
 				 const char *propname, const char **strings)
 {
-	struct property_entry *prop;
-	const char **pointer;
+	const struct property_entry *prop;
+	const char * const *pointer;
 
 	prop = pset_prop_get(pset, propname);
 	if (!prop)
@@ -682,77 +682,64 @@ out:
 }
 EXPORT_SYMBOL_GPL(fwnode_property_match_string);
 
-/**
- * pset_free_set - releases memory allocated for copied property set
- * @pset: Property set to release
- *
- * Function takes previously copied property set and releases all the
- * memory allocated to it.
- */
-static void pset_free_set(struct property_set *pset)
+static int property_copy_string_array(struct property_entry *dst,
+				      const struct property_entry *src)
 {
-	const struct property_entry *prop;
-	size_t i, nval;
+	char **d;
+	size_t nval = src->length / sizeof(*d);
+	int i;
 
-	if (!pset)
-		return;
+	d = kcalloc(nval, sizeof(*d), GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
 
-	for (prop = pset->properties; prop->name; prop++) {
-		if (prop->is_array) {
-			if (prop->is_string && prop->pointer.str) {
-				nval = prop->length / sizeof(const char *);
-				for (i = 0; i < nval; i++)
-					kfree(prop->pointer.str[i]);
-			}
-			kfree(prop->pointer.raw_data);
-		} else if (prop->is_string) {
-			kfree(prop->value.str);
+	for (i = 0; i < nval; i++) {
+		d[i] = kstrdup(src->pointer.str[i], GFP_KERNEL);
+		if (!d[i] && src->pointer.str[i]) {
+			while (--i >= 0)
+				kfree(d[i]);
+			kfree(d);
+			return -ENOMEM;
 		}
-		kfree(prop->name);
 	}
 
-	kfree(pset->properties);
-	kfree(pset);
+	dst->pointer.raw_data = d;
+	return 0;
 }
 
-static int pset_copy_entry(struct property_entry *dst,
-			   const struct property_entry *src)
+static int property_entry_copy_data(struct property_entry *dst,
+				    const struct property_entry *src)
 {
-	const char **d, **s;
-	size_t i, nval;
+	int error;
 
 	dst->name = kstrdup(src->name, GFP_KERNEL);
 	if (!dst->name)
 		return -ENOMEM;
 
 	if (src->is_array) {
-		if (!src->length)
-			return -ENODATA;
+		if (!src->length) {
+			error = -ENODATA;
+			goto out_free_name;
+		}
 
 		if (src->is_string) {
-			nval = src->length / sizeof(const char *);
-			dst->pointer.str = kcalloc(nval, sizeof(const char *),
-						   GFP_KERNEL);
-			if (!dst->pointer.str)
-				return -ENOMEM;
-
-			d = dst->pointer.str;
-			s = src->pointer.str;
-			for (i = 0; i < nval; i++) {
-				d[i] = kstrdup(s[i], GFP_KERNEL);
-				if (!d[i] && s[i])
-					return -ENOMEM;
-			}
+			error = property_copy_string_array(dst, src);
+			if (error)
+				goto out_free_name;
 		} else {
 			dst->pointer.raw_data = kmemdup(src->pointer.raw_data,
 							src->length, GFP_KERNEL);
-			if (!dst->pointer.raw_data)
-				return -ENOMEM;
+			if (!dst->pointer.raw_data) {
+				error = -ENOMEM;
+				goto out_free_name;
+			}
 		}
 	} else if (src->is_string) {
 		dst->value.str = kstrdup(src->value.str, GFP_KERNEL);
-		if (!dst->value.str && src->value.str)
-			return -ENOMEM;
+		if (!dst->value.str && src->value.str) {
+			error = -ENOMEM;
+			goto out_free_name;
+		}
 	} else {
 		dst->value.raw_data = src->value.raw_data;
 	}
@@ -762,6 +749,95 @@ static int pset_copy_entry(struct property_entry *dst,
 	dst->is_string = src->is_string;
 
 	return 0;
+
+out_free_name:
+	kfree(dst->name);
+	return error;
+}
+
+static void property_entry_free_data(const struct property_entry *p)
+{
+	size_t i, nval;
+
+	if (p->is_array) {
+		if (p->is_string && p->pointer.str) {
+			nval = p->length / sizeof(const char *);
+			for (i = 0; i < nval; i++)
+				kfree(p->pointer.str[i]);
+		}
+		kfree(p->pointer.raw_data);
+	} else if (p->is_string) {
+		kfree(p->value.str);
+	}
+	kfree(p->name);
+}
+
+/**
+ * property_entries_dup - duplicate array of properties
+ * @properties: array of properties to copy
+ *
+ * This function creates a deep copy of the given NULL-terminated array
+ * of property entries.
+ */
+struct property_entry *
+property_entries_dup(const struct property_entry *properties)
+{
+	struct property_entry *p;
+	int i, n = 0;
+
+	while (properties[n].name)
+		n++;
+
+	p = kcalloc(n + 1, sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < n; i++) {
+		int ret = property_entry_copy_data(&p[i], &properties[i]);
+		if (ret) {
+			while (--i >= 0)
+				property_entry_free_data(&p[i]);
+			kfree(p);
+			return ERR_PTR(ret);
+		}
+	}
+
+	return p;
+}
+EXPORT_SYMBOL_GPL(property_entries_dup);
+
+/**
+ * property_entries_free - free previously allocated array of properties
+ * @properties: array of properties to destroy
+ *
+ * This function frees given NULL-terminated array of property entries,
+ * along with their data.
+ */
+void property_entries_free(const struct property_entry *properties)
+{
+	const struct property_entry *p;
+
+	for (p = properties; p->name; p++)
+		property_entry_free_data(p);
+
+	kfree(properties);
+}
+EXPORT_SYMBOL_GPL(property_entries_free);
+
+/**
+ * pset_free_set - releases memory allocated for copied property set
+ * @pset: Property set to release
+ *
+ * Function takes previously copied property set and releases all the
+ * memory allocated to it.
+ */
+static void pset_free_set(struct property_set *pset)
+{
+	if (!pset)
+		return;
+
+	property_entries_free(pset->properties);
+	kfree(pset);
 }
 
 /**
@@ -776,32 +852,20 @@ static int pset_copy_entry(struct property_entry *dst,
  */
 static struct property_set *pset_copy_set(const struct property_set *pset)
 {
-	const struct property_entry *entry;
+	struct property_entry *properties;
 	struct property_set *p;
-	size_t i, n = 0;
 
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return ERR_PTR(-ENOMEM);
 
-	while (pset->properties[n].name)
-		n++;
-
-	p->properties = kcalloc(n + 1, sizeof(*entry), GFP_KERNEL);
-	if (!p->properties) {
+	properties = property_entries_dup(pset->properties);
+	if (IS_ERR(properties)) {
 		kfree(p);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	for (i = 0; i < n; i++) {
-		int ret = pset_copy_entry(&p->properties[i],
-					  &pset->properties[i]);
-		if (ret) {
-			pset_free_set(p);
-			return ERR_PTR(ret);
-		}
+		return ERR_CAST(properties);
 	}
 
+	p->properties = properties;
 	return p;
 }
 
@@ -847,7 +911,8 @@ EXPORT_SYMBOL_GPL(device_remove_properties);
  * @dev as its secondary firmware node. The function takes a copy of
  * @properties.
  */
-int device_add_properties(struct device *dev, struct property_entry *properties)
+int device_add_properties(struct device *dev,
+			  const struct property_entry *properties)
 {
 	struct property_set *p, pset;
 
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index b11af3f2c1db..b1e9aae9a5d0 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -81,7 +81,7 @@ static struct regcache_rbtree_node *regcache_rbtree_lookup(struct regmap *map,
 
 	node = rbtree_ctx->root.rb_node;
 	while (node) {
-		rbnode = container_of(node, struct regcache_rbtree_node, node);
+		rbnode = rb_entry(node, struct regcache_rbtree_node, node);
 		regcache_rbtree_get_base_top_reg(map, rbnode, &base_reg,
 						 &top_reg);
 		if (reg >= base_reg && reg <= top_reg) {
@@ -108,8 +108,7 @@ static int regcache_rbtree_insert(struct regmap *map, struct rb_root *root,
 	parent = NULL;
 	new = &root->rb_node;
 	while (*new) {
-		rbnode_tmp = container_of(*new, struct regcache_rbtree_node,
-					  node);
+		rbnode_tmp = rb_entry(*new, struct regcache_rbtree_node, node);
 		/* base and top registers of the current rbnode */
 		regcache_rbtree_get_base_top_reg(map, rbnode_tmp, &base_reg_tmp,
 						 &top_reg_tmp);
@@ -152,7 +151,7 @@ static int rbtree_show(struct seq_file *s, void *ignored)
 
 	for (node = rb_first(&rbtree_ctx->root); node != NULL;
 	     node = rb_next(node)) {
-		n = container_of(node, struct regcache_rbtree_node, node);
+		n = rb_entry(node, struct regcache_rbtree_node, node);
 		mem_size += sizeof(*n);
 		mem_size += (n->blklen * map->cache_word_size);
 		mem_size += BITS_TO_LONGS(n->blklen) * sizeof(long);
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index 4e582561e1e7..b0a0dcf32fb7 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -224,7 +224,7 @@ void regcache_exit(struct regmap *map)
 }
 
 /**
- * regcache_read: Fetch the value of a given register from the cache.
+ * regcache_read - Fetch the value of a given register from the cache.
  *
  * @map: map to configure.
  * @reg: The register index.
@@ -255,7 +255,7 @@ int regcache_read(struct regmap *map,
 }
 
 /**
- * regcache_write: Set the value of a given register in the cache.
+ * regcache_write - Set the value of a given register in the cache.
  *
  * @map: map to configure.
  * @reg: The register index.
@@ -328,7 +328,7 @@ static int regcache_default_sync(struct regmap *map, unsigned int min,
 }
 
 /**
- * regcache_sync: Sync the register cache with the hardware.
+ * regcache_sync - Sync the register cache with the hardware.
  *
  * @map: map to configure.
  *
@@ -396,7 +396,7 @@ out:
 EXPORT_SYMBOL_GPL(regcache_sync);
 
 /**
- * regcache_sync_region: Sync part  of the register cache with the hardware.
+ * regcache_sync_region - Sync part  of the register cache with the hardware.
  *
  * @map: map to sync.
  * @min: first register to sync
@@ -452,7 +452,7 @@ out:
 EXPORT_SYMBOL_GPL(regcache_sync_region);
 
 /**
- * regcache_drop_region: Discard part of the register cache
+ * regcache_drop_region - Discard part of the register cache
  *
  * @map: map to operate on
  * @min: first register to discard
@@ -483,10 +483,10 @@ int regcache_drop_region(struct regmap *map, unsigned int min,
 EXPORT_SYMBOL_GPL(regcache_drop_region);
 
 /**
- * regcache_cache_only: Put a register map into cache only mode
+ * regcache_cache_only - Put a register map into cache only mode
  *
  * @map: map to configure
- * @cache_only: flag if changes should be written to the hardware
+ * @enable: flag if changes should be written to the hardware
  *
  * When a register map is marked as cache only writes to the register
  * map API will only update the register cache, they will not cause
@@ -505,7 +505,7 @@ void regcache_cache_only(struct regmap *map, bool enable)
 EXPORT_SYMBOL_GPL(regcache_cache_only);
 
 /**
- * regcache_mark_dirty: Indicate that HW registers were reset to default values
+ * regcache_mark_dirty - Indicate that HW registers were reset to default values
  *
  * @map: map to mark
  *
@@ -527,10 +527,10 @@ void regcache_mark_dirty(struct regmap *map)
 EXPORT_SYMBOL_GPL(regcache_mark_dirty);
 
 /**
- * regcache_cache_bypass: Put a register map into cache bypass mode
+ * regcache_cache_bypass - Put a register map into cache bypass mode
  *
  * @map: map to configure
- * @cache_bypass: flag if changes should not be written to the cache
+ * @enable: flag if changes should not be written to the cache
  *
  * When a register map is marked with the cache bypass option, writes
  * to the register map API will only update the hardware and not the
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index ec262476d043..cd54189f2b1d 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -398,13 +398,14 @@ static const struct irq_domain_ops regmap_domain_ops = {
 };
 
 /**
- * regmap_add_irq_chip(): Use standard regmap IRQ controller handling
+ * regmap_add_irq_chip() - Use standard regmap IRQ controller handling
  *
- * map:       The regmap for the device.
- * irq:       The IRQ the device uses to signal interrupts
- * irq_flags: The IRQF_ flags to use for the primary interrupt.
- * chip:      Configuration for the interrupt controller.
- * data:      Runtime data structure for the controller, allocated on success
+ * @map: The regmap for the device.
+ * @irq: The IRQ the device uses to signal interrupts.
+ * @irq_flags: The IRQF_ flags to use for the primary interrupt.
+ * @irq_base: Allocate at specific IRQ number if irq_base > 0.
+ * @chip: Configuration for the interrupt controller.
+ * @data: Runtime data structure for the controller, allocated on success.
  *
  * Returns 0 on success or an errno on failure.
  *
@@ -659,12 +660,12 @@ err_alloc:
 EXPORT_SYMBOL_GPL(regmap_add_irq_chip);
 
 /**
- * regmap_del_irq_chip(): Stop interrupt handling for a regmap IRQ chip
+ * regmap_del_irq_chip() - Stop interrupt handling for a regmap IRQ chip
  *
  * @irq: Primary IRQ for the device
- * @d:   regmap_irq_chip_data allocated by regmap_add_irq_chip()
+ * @d: &regmap_irq_chip_data allocated by regmap_add_irq_chip()
  *
- * This function also dispose all mapped irq on chip.
+ * This function also disposes of all mapped IRQs on the chip.
  */
 void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d)
 {
@@ -723,18 +724,19 @@ static int devm_regmap_irq_chip_match(struct device *dev, void *res, void *data)
 }
 
 /**
- * devm_regmap_add_irq_chip(): Resource manager regmap_add_irq_chip()
+ * devm_regmap_add_irq_chip() - Resource manager regmap_add_irq_chip()
  *
- * @dev:       The device pointer on which irq_chip belongs to.
- * @map:       The regmap for the device.
- * @irq:       The IRQ the device uses to signal interrupts
+ * @dev: The device pointer on which irq_chip belongs to.
+ * @map: The regmap for the device.
+ * @irq: The IRQ the device uses to signal interrupts
  * @irq_flags: The IRQF_ flags to use for the primary interrupt.
- * @chip:      Configuration for the interrupt controller.
- * @data:      Runtime data structure for the controller, allocated on success
+ * @irq_base: Allocate at specific IRQ number if irq_base > 0.
+ * @chip: Configuration for the interrupt controller.
+ * @data: Runtime data structure for the controller, allocated on success
  *
  * Returns 0 on success or an errno on failure.
  *
- * The regmap_irq_chip data automatically be released when the device is
+ * The &regmap_irq_chip_data will be automatically released when the device is
  * unbound.
  */
 int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
@@ -765,11 +767,13 @@ int devm_regmap_add_irq_chip(struct device *dev, struct regmap *map, int irq,
 EXPORT_SYMBOL_GPL(devm_regmap_add_irq_chip);
 
 /**
- * devm_regmap_del_irq_chip(): Resource managed regmap_del_irq_chip()
+ * devm_regmap_del_irq_chip() - Resource managed regmap_del_irq_chip()
  *
  * @dev: Device for which which resource was allocated.
- * @irq: Primary IRQ for the device
- * @d:   regmap_irq_chip_data allocated by regmap_add_irq_chip()
+ * @irq: Primary IRQ for the device.
+ * @data: &regmap_irq_chip_data allocated by regmap_add_irq_chip().
+ *
+ * A resource managed version of regmap_del_irq_chip().
  */
 void devm_regmap_del_irq_chip(struct device *dev, int irq,
 			      struct regmap_irq_chip_data *data)
@@ -786,11 +790,11 @@ void devm_regmap_del_irq_chip(struct device *dev, int irq,
 EXPORT_SYMBOL_GPL(devm_regmap_del_irq_chip);
 
 /**
- * regmap_irq_chip_get_base(): Retrieve interrupt base for a regmap IRQ chip
+ * regmap_irq_chip_get_base() - Retrieve interrupt base for a regmap IRQ chip
  *
- * Useful for drivers to request their own IRQs.
+ * @data: regmap irq controller to operate on.
  *
- * @data: regmap_irq controller to operate on.
+ * Useful for drivers to request their own IRQs.
  */
 int regmap_irq_chip_get_base(struct regmap_irq_chip_data *data)
 {
@@ -800,12 +804,12 @@ int regmap_irq_chip_get_base(struct regmap_irq_chip_data *data)
 EXPORT_SYMBOL_GPL(regmap_irq_chip_get_base);
 
 /**
- * regmap_irq_get_virq(): Map an interrupt on a chip to a virtual IRQ
+ * regmap_irq_get_virq() - Map an interrupt on a chip to a virtual IRQ
  *
- * Useful for drivers to request their own IRQs.
+ * @data: regmap irq controller to operate on.
+ * @irq: index of the interrupt requested in the chip IRQs.
  *
- * @data: regmap_irq controller to operate on.
- * @irq: index of the interrupt requested in the chip IRQs
+ * Useful for drivers to request their own IRQs.
  */
 int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq)
 {
@@ -818,14 +822,14 @@ int regmap_irq_get_virq(struct regmap_irq_chip_data *data, int irq)
 EXPORT_SYMBOL_GPL(regmap_irq_get_virq);
 
 /**
- * regmap_irq_get_domain(): Retrieve the irq_domain for the chip
+ * regmap_irq_get_domain() - Retrieve the irq_domain for the chip
+ *
+ * @data: regmap_irq controller to operate on.
  *
  * Useful for drivers to request their own IRQs and for integration
  * with subsystems.  For ease of integration NULL is accepted as a
  * domain, allowing devices to just call this even if no domain is
  * allocated.
- *
- * @data: regmap_irq controller to operate on.
  */
 struct irq_domain *regmap_irq_get_domain(struct regmap_irq_chip_data *data)
 {
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index ae63bb0875ea..b9a779a4a739 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -459,7 +459,7 @@ static bool _regmap_range_add(struct regmap *map,
 
 	while (*new) {
 		struct regmap_range_node *this =
-			container_of(*new, struct regmap_range_node, node);
+			rb_entry(*new, struct regmap_range_node, node);
 
 		parent = *new;
 		if (data->range_max < this->range_min)
@@ -483,7 +483,7 @@ static struct regmap_range_node *_regmap_range_lookup(struct regmap *map,
 
 	while (node) {
 		struct regmap_range_node *this =
-			container_of(node, struct regmap_range_node, node);
+			rb_entry(node, struct regmap_range_node, node);
 
 		if (reg < this->range_min)
 			node = node->rb_left;
@@ -1091,8 +1091,7 @@ static void regmap_field_init(struct regmap_field *rm_field,
 }
 
 /**
- * devm_regmap_field_alloc(): Allocate and initialise a register field
- * in a register map.
+ * devm_regmap_field_alloc() - Allocate and initialise a register field.
  *
  * @dev: Device that will be interacted with
  * @regmap: regmap bank in which this register field is located.
@@ -1118,13 +1117,15 @@ struct regmap_field *devm_regmap_field_alloc(struct device *dev,
 EXPORT_SYMBOL_GPL(devm_regmap_field_alloc);
 
 /**
- * devm_regmap_field_free(): Free register field allocated using
- * devm_regmap_field_alloc. Usally drivers need not call this function,
- * as the memory allocated via devm will be freed as per device-driver
- * life-cyle.
+ * devm_regmap_field_free() - Free a register field allocated using
+ *                            devm_regmap_field_alloc.
  *
  * @dev: Device that will be interacted with
  * @field: regmap field which should be freed.
+ *
+ * Free register field allocated using devm_regmap_field_alloc(). Usually
+ * drivers need not call this function, as the memory allocated via devm
+ * will be freed as per device-driver life-cyle.
  */
 void devm_regmap_field_free(struct device *dev,
 	struct regmap_field *field)
@@ -1134,8 +1135,7 @@ void devm_regmap_field_free(struct device *dev,
 EXPORT_SYMBOL_GPL(devm_regmap_field_free);
 
 /**
- * regmap_field_alloc(): Allocate and initialise a register field
- * in a register map.
+ * regmap_field_alloc() - Allocate and initialise a register field.
  *
  * @regmap: regmap bank in which this register field is located.
  * @reg_field: Register field with in the bank.
@@ -1159,7 +1159,8 @@ struct regmap_field *regmap_field_alloc(struct regmap *regmap,
 EXPORT_SYMBOL_GPL(regmap_field_alloc);
 
 /**
- * regmap_field_free(): Free register field allocated using regmap_field_alloc
+ * regmap_field_free() - Free register field allocated using
+ *                       regmap_field_alloc.
  *
  * @field: regmap field which should be freed.
  */
@@ -1170,7 +1171,7 @@ void regmap_field_free(struct regmap_field *field)
 EXPORT_SYMBOL_GPL(regmap_field_free);
 
 /**
- * regmap_reinit_cache(): Reinitialise the current register cache
+ * regmap_reinit_cache() - Reinitialise the current register cache
  *
  * @map: Register map to operate on.
  * @config: New configuration.  Only the cache data will be used.
@@ -1205,7 +1206,9 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config)
 EXPORT_SYMBOL_GPL(regmap_reinit_cache);
 
 /**
- * regmap_exit(): Free a previously allocated register map
+ * regmap_exit() - Free a previously allocated register map
+ *
+ * @map: Register map to operate on.
  */
 void regmap_exit(struct regmap *map)
 {
@@ -1245,7 +1248,7 @@ static int dev_get_regmap_match(struct device *dev, void *res, void *data)
 }
 
 /**
- * dev_get_regmap(): Obtain the regmap (if any) for a device
+ * dev_get_regmap() - Obtain the regmap (if any) for a device
  *
  * @dev: Device to retrieve the map for
  * @name: Optional name for the register map, usually NULL.
@@ -1268,7 +1271,7 @@ struct regmap *dev_get_regmap(struct device *dev, const char *name)
 EXPORT_SYMBOL_GPL(dev_get_regmap);
 
 /**
- * regmap_get_device(): Obtain the device from a regmap
+ * regmap_get_device() - Obtain the device from a regmap
  *
  * @map: Register map to operate on.
  *
@@ -1654,7 +1657,7 @@ int _regmap_write(struct regmap *map, unsigned int reg,
 }
 
 /**
- * regmap_write(): Write a value to a single register
+ * regmap_write() - Write a value to a single register
  *
  * @map: Register map to write to
  * @reg: Register to write to
@@ -1681,7 +1684,7 @@ int regmap_write(struct regmap *map, unsigned int reg, unsigned int val)
 EXPORT_SYMBOL_GPL(regmap_write);
 
 /**
- * regmap_write_async(): Write a value to a single register asynchronously
+ * regmap_write_async() - Write a value to a single register asynchronously
  *
  * @map: Register map to write to
  * @reg: Register to write to
@@ -1712,7 +1715,7 @@ int regmap_write_async(struct regmap *map, unsigned int reg, unsigned int val)
 EXPORT_SYMBOL_GPL(regmap_write_async);
 
 /**
- * regmap_raw_write(): Write raw values to one or more registers
+ * regmap_raw_write() - Write raw values to one or more registers
  *
  * @map: Register map to write to
  * @reg: Initial register to write to
@@ -1750,9 +1753,8 @@ int regmap_raw_write(struct regmap *map, unsigned int reg,
 EXPORT_SYMBOL_GPL(regmap_raw_write);
 
 /**
- * regmap_field_update_bits_base():
- *	Perform a read/modify/write cycle on the register field
- *	with change, async, force option
+ * regmap_field_update_bits_base() - Perform a read/modify/write cycle a
+ *                                   register field.
  *
  * @field: Register field to write to
  * @mask: Bitmask to change
@@ -1761,6 +1763,9 @@ EXPORT_SYMBOL_GPL(regmap_raw_write);
  * @async: Boolean indicating asynchronously
  * @force: Boolean indicating use force update
  *
+ * Perform a read/modify/write cycle on the register field with change,
+ * async, force option.
+ *
  * A value of zero will be returned on success, a negative errno will
  * be returned in error cases.
  */
@@ -1777,9 +1782,8 @@ int regmap_field_update_bits_base(struct regmap_field *field,
 EXPORT_SYMBOL_GPL(regmap_field_update_bits_base);
 
 /**
- * regmap_fields_update_bits_base():
- *	Perform a read/modify/write cycle on the register field
- *	with change, async, force option
+ * regmap_fields_update_bits_base() - Perform a read/modify/write cycle a
+ *                                    register field with port ID
  *
  * @field: Register field to write to
  * @id: port ID
@@ -1808,8 +1812,8 @@ int regmap_fields_update_bits_base(struct regmap_field *field,  unsigned int id,
 }
 EXPORT_SYMBOL_GPL(regmap_fields_update_bits_base);
 
-/*
- * regmap_bulk_write(): Write multiple registers to the device
+/**
+ * regmap_bulk_write() - Write multiple registers to the device
  *
  * @map: Register map to write to
  * @reg: First register to be write from
@@ -2174,18 +2178,18 @@ static int _regmap_multi_reg_write(struct regmap *map,
 	return _regmap_raw_multi_reg_write(map, regs, num_regs);
 }
 
-/*
- * regmap_multi_reg_write(): Write multiple registers to the device
- *
- * where the set of register,value pairs are supplied in any order,
- * possibly not all in a single range.
+/**
+ * regmap_multi_reg_write() - Write multiple registers to the device
  *
  * @map: Register map to write to
  * @regs: Array of structures containing register,value to be written
  * @num_regs: Number of registers to write
  *
+ * Write multiple registers to the device where the set of register, value
+ * pairs are supplied in any order, possibly not all in a single range.
+ *
  * The 'normal' block write mode will send ultimately send data on the
- * target bus as R,V1,V2,V3,..,Vn where successively higer registers are
+ * target bus as R,V1,V2,V3,..,Vn where successively higher registers are
  * addressed. However, this alternative block multi write mode will send
  * the data as R1,V1,R2,V2,..,Rn,Vn on the target bus. The target device
  * must of course support the mode.
@@ -2208,16 +2212,17 @@ int regmap_multi_reg_write(struct regmap *map, const struct reg_sequence *regs,
 }
 EXPORT_SYMBOL_GPL(regmap_multi_reg_write);
 
-/*
- * regmap_multi_reg_write_bypassed(): Write multiple registers to the
- *                                    device but not the cache
- *
- * where the set of register are supplied in any order
+/**
+ * regmap_multi_reg_write_bypassed() - Write multiple registers to the
+ *                                     device but not the cache
  *
  * @map: Register map to write to
  * @regs: Array of structures containing register,value to be written
  * @num_regs: Number of registers to write
  *
+ * Write multiple registers to the device but not the cache where the set
+ * of register are supplied in any order.
+ *
  * This function is intended to be used for writing a large block of data
  * atomically to the device in single transfer for those I2C client devices
  * that implement this alternative block write mode.
@@ -2248,8 +2253,8 @@ int regmap_multi_reg_write_bypassed(struct regmap *map,
 EXPORT_SYMBOL_GPL(regmap_multi_reg_write_bypassed);
 
 /**
- * regmap_raw_write_async(): Write raw values to one or more registers
- *                           asynchronously
+ * regmap_raw_write_async() - Write raw values to one or more registers
+ *                            asynchronously
  *
  * @map: Register map to write to
  * @reg: Initial register to write to
@@ -2385,7 +2390,7 @@ static int _regmap_read(struct regmap *map, unsigned int reg,
 }
 
 /**
- * regmap_read(): Read a value from a single register
+ * regmap_read() - Read a value from a single register
  *
  * @map: Register map to read from
  * @reg: Register to be read from
@@ -2412,7 +2417,7 @@ int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val)
 EXPORT_SYMBOL_GPL(regmap_read);
 
 /**
- * regmap_raw_read(): Read raw data from the device
+ * regmap_raw_read() - Read raw data from the device
  *
  * @map: Register map to read from
  * @reg: First register to be read from
@@ -2477,7 +2482,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 EXPORT_SYMBOL_GPL(regmap_raw_read);
 
 /**
- * regmap_field_read(): Read a value to a single register field
+ * regmap_field_read() - Read a value to a single register field
  *
  * @field: Register field to read from
  * @val: Pointer to store read value
@@ -2502,7 +2507,7 @@ int regmap_field_read(struct regmap_field *field, unsigned int *val)
 EXPORT_SYMBOL_GPL(regmap_field_read);
 
 /**
- * regmap_fields_read(): Read a value to a single register field with port ID
+ * regmap_fields_read() - Read a value to a single register field with port ID
  *
  * @field: Register field to read from
  * @id: port ID
@@ -2535,7 +2540,7 @@ int regmap_fields_read(struct regmap_field *field, unsigned int id,
 EXPORT_SYMBOL_GPL(regmap_fields_read);
 
 /**
- * regmap_bulk_read(): Read multiple registers from the device
+ * regmap_bulk_read() - Read multiple registers from the device
  *
  * @map: Register map to read from
  * @reg: First register to be read from
@@ -2692,9 +2697,7 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg,
 }
 
 /**
- * regmap_update_bits_base:
- *	Perform a read/modify/write cycle on the
- *	register map with change, async, force option
+ * regmap_update_bits_base() - Perform a read/modify/write cycle on a register
  *
  * @map: Register map to update
  * @reg: Register to update
@@ -2704,10 +2707,14 @@ static int _regmap_update_bits(struct regmap *map, unsigned int reg,
  * @async: Boolean indicating asynchronously
  * @force: Boolean indicating use force update
  *
- * if async was true,
- * With most buses the read must be done synchronously so this is most
- * useful for devices with a cache which do not need to interact with
- * the hardware to determine the current register value.
+ * Perform a read/modify/write cycle on a register map with change, async, force
+ * options.
+ *
+ * If async is true:
+ *
+ * With most buses the read must be done synchronously so this is most useful
+ * for devices with a cache which do not need to interact with the hardware to
+ * determine the current register value.
  *
  * Returns zero for success, a negative number on error.
  */
@@ -2765,7 +2772,7 @@ static int regmap_async_is_done(struct regmap *map)
 }
 
 /**
- * regmap_async_complete: Ensure all asynchronous I/O has completed.
+ * regmap_async_complete - Ensure all asynchronous I/O has completed.
  *
  * @map: Map to operate on.
  *
@@ -2797,8 +2804,8 @@ int regmap_async_complete(struct regmap *map)
 EXPORT_SYMBOL_GPL(regmap_async_complete);
 
 /**
- * regmap_register_patch: Register and apply register updates to be applied
- *                        on device initialistion
+ * regmap_register_patch - Register and apply register updates to be applied
+ *                         on device initialistion
  *
  * @map: Register map to apply updates to.
  * @regs: Values to update.
@@ -2855,8 +2862,10 @@ int regmap_register_patch(struct regmap *map, const struct reg_sequence *regs,
 }
 EXPORT_SYMBOL_GPL(regmap_register_patch);
 
-/*
- * regmap_get_val_bytes(): Report the size of a register value
+/**
+ * regmap_get_val_bytes() - Report the size of a register value
+ *
+ * @map: Register map to operate on.
  *
  * Report the size of a register value, mainly intended to for use by
  * generic infrastructure built on top of regmap.
@@ -2871,7 +2880,9 @@ int regmap_get_val_bytes(struct regmap *map)
 EXPORT_SYMBOL_GPL(regmap_get_val_bytes);
 
 /**
- * regmap_get_max_register(): Report the max register value
+ * regmap_get_max_register() - Report the max register value
+ *
+ * @map: Register map to operate on.
  *
  * Report the max register value, mainly intended to for use by
  * generic infrastructure built on top of regmap.
@@ -2883,7 +2894,9 @@ int regmap_get_max_register(struct regmap *map)
 EXPORT_SYMBOL_GPL(regmap_get_max_register);
 
 /**
- * regmap_get_reg_stride(): Report the register address stride
+ * regmap_get_reg_stride() - Report the register address stride
+ *
+ * @map: Register map to operate on.
  *
  * Report the register address stride, mainly intended to for use by
  * generic infrastructure built on top of regmap.
diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h
index f642c4264c27..168fa175d65a 100644
--- a/drivers/bcma/bcma_private.h
+++ b/drivers/bcma/bcma_private.h
@@ -45,6 +45,9 @@ int bcma_sprom_get(struct bcma_bus *bus);
 void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc);
 void bcma_core_chipcommon_init(struct bcma_drv_cc *cc);
 void bcma_chipco_bcm4331_ext_pa_lines_ctl(struct bcma_drv_cc *cc, bool enable);
+#ifdef CONFIG_BCMA_DRIVER_MIPS
+void bcma_chipco_serial_init(struct bcma_drv_cc *cc);
+#endif /* CONFIG_BCMA_DRIVER_MIPS */
 
 /* driver_chipcommon_b.c */
 int bcma_core_chipcommon_b_init(struct bcma_drv_cc_b *ccb);
diff --git a/drivers/bcma/driver_chipcommon.c b/drivers/bcma/driver_chipcommon.c
index b4f6520e74f0..62f5bfa5065d 100644
--- a/drivers/bcma/driver_chipcommon.c
+++ b/drivers/bcma/driver_chipcommon.c
@@ -15,8 +15,6 @@
 #include <linux/platform_device.h>
 #include <linux/bcma/bcma.h>
 
-static void bcma_chipco_serial_init(struct bcma_drv_cc *cc);
-
 static inline u32 bcma_cc_write32_masked(struct bcma_drv_cc *cc, u16 offset,
 					 u32 mask, u32 value)
 {
@@ -186,9 +184,6 @@ void bcma_core_chipcommon_early_init(struct bcma_drv_cc *cc)
 	if (cc->capabilities & BCMA_CC_CAP_PMU)
 		bcma_pmu_early_init(cc);
 
-	if (IS_BUILTIN(CONFIG_BCM47XX) && bus->hosttype == BCMA_HOSTTYPE_SOC)
-		bcma_chipco_serial_init(cc);
-
 	if (bus->hosttype == BCMA_HOSTTYPE_SOC)
 		bcma_core_chipcommon_flash_detect(cc);
 
@@ -378,9 +373,9 @@ u32 bcma_chipco_gpio_pulldown(struct bcma_drv_cc *cc, u32 mask, u32 value)
 	return res;
 }
 
-static void bcma_chipco_serial_init(struct bcma_drv_cc *cc)
+#ifdef CONFIG_BCMA_DRIVER_MIPS
+void bcma_chipco_serial_init(struct bcma_drv_cc *cc)
 {
-#if IS_BUILTIN(CONFIG_BCM47XX)
 	unsigned int irq;
 	u32 baud_base;
 	u32 i;
@@ -422,5 +417,5 @@ static void bcma_chipco_serial_init(struct bcma_drv_cc *cc)
 		ports[i].baud_base = baud_base;
 		ports[i].reg_shift = 0;
 	}
-#endif /* CONFIG_BCM47XX */
 }
+#endif /* CONFIG_BCMA_DRIVER_MIPS */
diff --git a/drivers/bcma/driver_mips.c b/drivers/bcma/driver_mips.c
index 96f171328200..89af807cf29c 100644
--- a/drivers/bcma/driver_mips.c
+++ b/drivers/bcma/driver_mips.c
@@ -278,9 +278,12 @@ static void bcma_core_mips_nvram_init(struct bcma_drv_mips *mcore)
 
 void bcma_core_mips_early_init(struct bcma_drv_mips *mcore)
 {
+	struct bcma_bus *bus = mcore->core->bus;
+
 	if (mcore->early_setup_done)
 		return;
 
+	bcma_chipco_serial_init(&bus->drv_cc);
 	bcma_core_mips_nvram_init(mcore);
 
 	mcore->early_setup_done = true;
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 223ff2fcae7e..f744de7a0f9b 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -69,6 +69,7 @@ config AMIGA_Z2RAM
 config GDROM
 	tristate "SEGA Dreamcast GD-ROM drive"
 	depends on SH_DREAMCAST
+	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	help
 	  A standard SEGA Dreamcast comes with a modified CD ROM drive called a
 	  "GD-ROM" by SEGA to signify it is capable of reading special disks
@@ -114,6 +115,7 @@ config BLK_CPQ_CISS_DA
 	tristate "Compaq Smart Array 5xxx support"
 	depends on PCI
 	select CHECK_SIGNATURE
+	select BLK_SCSI_REQUEST
 	help
 	  This is the driver for Compaq Smart Array 5xxx controllers.
 	  Everyone using these boards should say Y here.
@@ -386,6 +388,7 @@ config BLK_DEV_RAM_DAX
 config CDROM_PKTCDVD
 	tristate "Packet writing on CD/DVD media (DEPRECATED)"
 	depends on !UML
+	select BLK_SCSI_REQUEST
 	help
 	  Note: This driver is deprecated and will be removed from the
 	  kernel in the near future!
@@ -501,6 +504,16 @@ config VIRTIO_BLK
 	  This is the virtual block driver for virtio.  It can be used with
           lguest or QEMU based VMMs (like KVM or Xen).  Say Y or M.
 
+config VIRTIO_BLK_SCSI
+	bool "SCSI passthrough request for the Virtio block driver"
+	depends on VIRTIO_BLK
+	select BLK_SCSI_REQUEST
+	---help---
+	  Enable support for SCSI passthrough (e.g. the SG_IO ioctl) on
+	  virtio-blk devices.  This is only supported for the legacy
+	  virtio protocol and not enabled by default by any hypervisor.
+	  Your probably want to virtio-scsi instead.
+
 config BLK_DEV_HD
 	bool "Very old hard disk (MFM/RLL/IDE) driver"
 	depends on HAVE_IDE
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index ec9d8610b25f..027b876370bc 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -396,8 +396,8 @@ aoeblk_gdalloc(void *vp)
 	WARN_ON(d->gd);
 	WARN_ON(d->flags & DEVFL_UP);
 	blk_queue_max_hw_sectors(q, BLK_DEF_MAX_SECTORS);
-	q->backing_dev_info.name = "aoe";
-	q->backing_dev_info.ra_pages = READ_AHEAD / PAGE_SIZE;
+	q->backing_dev_info->name = "aoe";
+	q->backing_dev_info->ra_pages = READ_AHEAD / PAGE_SIZE;
 	d->bufpool = mp;
 	d->blkq = gd->queue = q;
 	q->queuedata = d;
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index e5c5b8eb14a9..27d613795653 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -52,6 +52,7 @@
 #include <scsi/scsi.h>
 #include <scsi/sg.h>
 #include <scsi/scsi_ioctl.h>
+#include <scsi/scsi_request.h>
 #include <linux/cdrom.h>
 #include <linux/scatterlist.h>
 #include <linux/kthread.h>
@@ -1853,8 +1854,8 @@ static void cciss_softirq_done(struct request *rq)
 	dev_dbg(&h->pdev->dev, "Done with %p\n", rq);
 
 	/* set the residual count for pc requests */
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
-		rq->resid_len = c->err_info->ResidualCnt;
+	if (blk_rq_is_passthrough(rq))
+		scsi_req(rq)->resid_len = c->err_info->ResidualCnt;
 
 	blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO);
 
@@ -1941,9 +1942,16 @@ static void cciss_get_serial_no(ctlr_info_t *h, int logvol,
 static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
 				int drv_index)
 {
-	disk->queue = blk_init_queue(do_cciss_request, &h->lock);
+	disk->queue = blk_alloc_queue(GFP_KERNEL);
 	if (!disk->queue)
 		goto init_queue_failure;
+
+	disk->queue->cmd_size = sizeof(struct scsi_request);
+	disk->queue->request_fn = do_cciss_request;
+	disk->queue->queue_lock = &h->lock;
+	if (blk_init_allocated_queue(disk->queue) < 0)
+		goto cleanup_queue;
+
 	sprintf(disk->disk_name, "cciss/c%dd%d", h->ctlr, drv_index);
 	disk->major = h->major;
 	disk->first_minor = drv_index << NWD_SHIFT;
@@ -3075,7 +3083,7 @@ static inline int evaluate_target_status(ctlr_info_t *h,
 	driver_byte = DRIVER_OK;
 	msg_byte = cmd->err_info->CommandStatus; /* correct?  seems too device specific */
 
-	if (cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC)
+	if (blk_rq_is_passthrough(cmd->rq))
 		host_byte = DID_PASSTHROUGH;
 	else
 		host_byte = DID_OK;
@@ -3084,7 +3092,7 @@ static inline int evaluate_target_status(ctlr_info_t *h,
 		host_byte, driver_byte);
 
 	if (cmd->err_info->ScsiStatus != SAM_STAT_CHECK_CONDITION) {
-		if (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC)
+		if (!blk_rq_is_passthrough(cmd->rq))
 			dev_warn(&h->pdev->dev, "cmd %p "
 			       "has SCSI Status 0x%x\n",
 			       cmd, cmd->err_info->ScsiStatus);
@@ -3095,31 +3103,23 @@ static inline int evaluate_target_status(ctlr_info_t *h,
 	sense_key = 0xf & cmd->err_info->SenseInfo[2];
 	/* no status or recovered error */
 	if (((sense_key == 0x0) || (sense_key == 0x1)) &&
-	    (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC))
+	    !blk_rq_is_passthrough(cmd->rq))
 		error_value = 0;
 
 	if (check_for_unit_attention(h, cmd)) {
-		*retry_cmd = !(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC);
+		*retry_cmd = !blk_rq_is_passthrough(cmd->rq);
 		return 0;
 	}
 
 	/* Not SG_IO or similar? */
-	if (cmd->rq->cmd_type != REQ_TYPE_BLOCK_PC) {
+	if (!blk_rq_is_passthrough(cmd->rq)) {
 		if (error_value != 0)
 			dev_warn(&h->pdev->dev, "cmd %p has CHECK CONDITION"
 			       " sense key = 0x%x\n", cmd, sense_key);
 		return error_value;
 	}
 
-	/* SG_IO or similar, copy sense data back */
-	if (cmd->rq->sense) {
-		if (cmd->rq->sense_len > cmd->err_info->SenseLen)
-			cmd->rq->sense_len = cmd->err_info->SenseLen;
-		memcpy(cmd->rq->sense, cmd->err_info->SenseInfo,
-			cmd->rq->sense_len);
-	} else
-		cmd->rq->sense_len = 0;
-
+	scsi_req(cmd->rq)->sense_len = cmd->err_info->SenseLen;
 	return error_value;
 }
 
@@ -3146,15 +3146,14 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		rq->errors = evaluate_target_status(h, cmd, &retry_cmd);
 		break;
 	case CMD_DATA_UNDERRUN:
-		if (cmd->rq->cmd_type == REQ_TYPE_FS) {
+		if (!blk_rq_is_passthrough(cmd->rq)) {
 			dev_warn(&h->pdev->dev, "cmd %p has"
 			       " completed with data underrun "
 			       "reported\n", cmd);
-			cmd->rq->resid_len = cmd->err_info->ResidualCnt;
 		}
 		break;
 	case CMD_DATA_OVERRUN:
-		if (cmd->rq->cmd_type == REQ_TYPE_FS)
+		if (!blk_rq_is_passthrough(cmd->rq))
 			dev_warn(&h->pdev->dev, "cciss: cmd %p has"
 			       " completed with data overrun "
 			       "reported\n", cmd);
@@ -3164,7 +3163,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       "reported invalid\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_PROTOCOL_ERR:
@@ -3172,7 +3171,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       "protocol error\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_HARDWARE_ERR:
@@ -3180,7 +3179,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       " hardware error\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_CONNECTION_LOST:
@@ -3188,7 +3187,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       "connection lost\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_ABORTED:
@@ -3196,7 +3195,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       "aborted\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ABORT);
 		break;
 	case CMD_ABORT_FAILED:
@@ -3204,7 +3203,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       "abort failed\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_UNSOLICITED_ABORT:
@@ -3219,21 +3218,21 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 				"%p retried too many times\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ABORT);
 		break;
 	case CMD_TIMEOUT:
 		dev_warn(&h->pdev->dev, "cmd %p timedout\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_UNABORTABLE:
 		dev_warn(&h->pdev->dev, "cmd %p unabortable\n", cmd);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	default:
@@ -3242,7 +3241,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		       cmd->err_info->CommandStatus);
 		rq->errors = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
-			(cmd->rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 	}
 
@@ -3395,7 +3394,9 @@ static void do_cciss_request(struct request_queue *q)
 		c->Header.SGList = h->max_cmd_sgentries;
 	set_performant_mode(h, c);
 
-	if (likely(creq->cmd_type == REQ_TYPE_FS)) {
+	switch (req_op(creq)) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
 		if(h->cciss_read == CCISS_READ_10) {
 			c->Request.CDB[1] = 0;
 			c->Request.CDB[2] = (start_blk >> 24) & 0xff; /* MSB */
@@ -3425,12 +3426,16 @@ static void do_cciss_request(struct request_queue *q)
 			c->Request.CDB[13]= blk_rq_sectors(creq) & 0xff;
 			c->Request.CDB[14] = c->Request.CDB[15] = 0;
 		}
-	} else if (creq->cmd_type == REQ_TYPE_BLOCK_PC) {
-		c->Request.CDBLen = creq->cmd_len;
-		memcpy(c->Request.CDB, creq->cmd, BLK_MAX_CDB);
-	} else {
+		break;
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
+		c->Request.CDBLen = scsi_req(creq)->cmd_len;
+		memcpy(c->Request.CDB, scsi_req(creq)->cmd, BLK_MAX_CDB);
+		scsi_req(creq)->sense = c->err_info->SenseInfo;
+		break;
+	default:
 		dev_warn(&h->pdev->dev, "bad request type %d\n",
-			creq->cmd_type);
+			creq->cmd_flags);
 		BUG();
 	}
 
@@ -4074,41 +4079,27 @@ clean_up:
 
 static void cciss_interrupt_mode(ctlr_info_t *h)
 {
-#ifdef CONFIG_PCI_MSI
-	int err;
-	struct msix_entry cciss_msix_entries[4] = { {0, 0}, {0, 1},
-	{0, 2}, {0, 3}
-	};
+	int ret;
 
 	/* Some boards advertise MSI but don't really support it */
 	if ((h->board_id == 0x40700E11) || (h->board_id == 0x40800E11) ||
 	    (h->board_id == 0x40820E11) || (h->board_id == 0x40830E11))
 		goto default_int_mode;
 
-	if (pci_find_capability(h->pdev, PCI_CAP_ID_MSIX)) {
-		err = pci_enable_msix_exact(h->pdev, cciss_msix_entries, 4);
-		if (!err) {
-			h->intr[0] = cciss_msix_entries[0].vector;
-			h->intr[1] = cciss_msix_entries[1].vector;
-			h->intr[2] = cciss_msix_entries[2].vector;
-			h->intr[3] = cciss_msix_entries[3].vector;
-			h->msix_vector = 1;
-			return;
-		} else {
-			dev_warn(&h->pdev->dev,
-				"MSI-X init failed %d\n", err);
-		}
-	}
-	if (pci_find_capability(h->pdev, PCI_CAP_ID_MSI)) {
-		if (!pci_enable_msi(h->pdev))
-			h->msi_vector = 1;
-		else
-			dev_warn(&h->pdev->dev, "MSI init failed\n");
+	ret = pci_alloc_irq_vectors(h->pdev, 4, 4, PCI_IRQ_MSIX);
+	if (ret >= 0)   {
+		h->intr[0] = pci_irq_vector(h->pdev, 0);
+		h->intr[1] = pci_irq_vector(h->pdev, 1);
+		h->intr[2] = pci_irq_vector(h->pdev, 2);
+		h->intr[3] = pci_irq_vector(h->pdev, 3);
+		return;
 	}
+
+	ret = pci_alloc_irq_vectors(h->pdev, 1, 1, PCI_IRQ_MSI);
+
 default_int_mode:
-#endif				/* CONFIG_PCI_MSI */
 	/* if we get here we're going to use the default interrupt mode */
-	h->intr[h->intr_mode] = h->pdev->irq;
+	h->intr[h->intr_mode] = pci_irq_vector(h->pdev, 0);
 	return;
 }
 
@@ -4888,7 +4879,7 @@ static int cciss_request_irq(ctlr_info_t *h,
 	irqreturn_t (*msixhandler)(int, void *),
 	irqreturn_t (*intxhandler)(int, void *))
 {
-	if (h->msix_vector || h->msi_vector) {
+	if (h->pdev->msi_enabled || h->pdev->msix_enabled) {
 		if (!request_irq(h->intr[h->intr_mode], msixhandler,
 				0, h->devname, h))
 			return 0;
@@ -4934,12 +4925,7 @@ static void cciss_undo_allocations_after_kdump_soft_reset(ctlr_info_t *h)
 	int ctlr = h->ctlr;
 
 	free_irq(h->intr[h->intr_mode], h);
-#ifdef CONFIG_PCI_MSI
-	if (h->msix_vector)
-		pci_disable_msix(h->pdev);
-	else if (h->msi_vector)
-		pci_disable_msi(h->pdev);
-#endif /* CONFIG_PCI_MSI */
+	pci_free_irq_vectors(h->pdev);
 	cciss_free_sg_chain_blocks(h->cmd_sg_list, h->nr_cmds);
 	cciss_free_scatterlists(h);
 	cciss_free_cmd_pool(h);
@@ -5295,12 +5281,7 @@ static void cciss_remove_one(struct pci_dev *pdev)
 
 	cciss_shutdown(pdev);
 
-#ifdef CONFIG_PCI_MSI
-	if (h->msix_vector)
-		pci_disable_msix(h->pdev);
-	else if (h->msi_vector)
-		pci_disable_msi(h->pdev);
-#endif				/* CONFIG_PCI_MSI */
+	pci_free_irq_vectors(h->pdev);
 
 	iounmap(h->transtable);
 	iounmap(h->cfgtable);
diff --git a/drivers/block/cciss.h b/drivers/block/cciss.h
index 7fda30e4a241..24b5fd75501a 100644
--- a/drivers/block/cciss.h
+++ b/drivers/block/cciss.h
@@ -90,8 +90,6 @@ struct ctlr_info
 #	define SIMPLE_MODE_INT	2
 #	define MEMQ_MODE_INT	3
 	unsigned int intr[4];
-	unsigned int msix_vector;
-	unsigned int msi_vector;
 	int	intr_mode;
 	int 	cciss_max_sectors;
 	BYTE	cciss_read;
@@ -333,7 +331,7 @@ static unsigned long SA5_performant_completed(ctlr_info_t *h)
 	 */
 	register_value = readl(h->vaddr + SA5_OUTDB_STATUS);
 	/* msi auto clears the interrupt pending bit. */
-	if (!(h->msi_vector || h->msix_vector)) {
+	if (!(h->pdev->msi_enabled || h->pdev->msix_enabled)) {
 		writel(SA5_OUTDB_CLEAR_PERF_BIT, h->vaddr + SA5_OUTDB_CLEAR);
 		/* Do a read in order to flush the write to the controller
 		 * (as per spec.)
@@ -393,7 +391,7 @@ static bool SA5_performant_intr_pending(ctlr_info_t *h)
 	if (!register_value)
 		return false;
 
-	if (h->msi_vector || h->msix_vector)
+	if (h->pdev->msi_enabled || h->pdev->msix_enabled)
 		return true;
 
 	/* Read outbound doorbell to flush */
@@ -402,27 +400,27 @@ static bool SA5_performant_intr_pending(ctlr_info_t *h)
 }
 
 static struct access_method SA5_access = {
-	SA5_submit_command,
-	SA5_intr_mask,
-	SA5_fifo_full,
-	SA5_intr_pending,
-	SA5_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5_intr_mask,
+	.fifo_full = SA5_fifo_full,
+	.intr_pending = SA5_intr_pending,
+	.command_completed = SA5_completed,
 };
 
 static struct access_method SA5B_access = {
-        SA5_submit_command,
-        SA5B_intr_mask,
-        SA5_fifo_full,
-        SA5B_intr_pending,
-        SA5_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5B_intr_mask,
+	.fifo_full = SA5_fifo_full,
+	.intr_pending = SA5B_intr_pending,
+	.command_completed = SA5_completed,
 };
 
 static struct access_method SA5_performant_access = {
-	SA5_submit_command,
-	SA5_performant_intr_mask,
-	SA5_fifo_full,
-	SA5_performant_intr_pending,
-	SA5_performant_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5_performant_intr_mask,
+	.fifo_full = SA5_fifo_full,
+	.intr_pending = SA5_performant_intr_pending,
+	.command_completed = SA5_performant_completed,
 };
 
 struct board_type {
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index ab62b81c2ca7..dece26f119d4 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -1070,7 +1070,7 @@ static int bm_rw(struct drbd_device *device, const unsigned int flags, unsigned
 		.done = 0,
 		.flags = flags,
 		.error = 0,
-		.kref = { ATOMIC_INIT(2) },
+		.kref = KREF_INIT(2),
 	};
 
 	if (!get_ldev_if_state(device, D_ATTACHING)) {  /* put is in drbd_bm_aio_ctx_destroy() */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 83482721bc01..615e5b5178a0 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2462,7 +2462,7 @@ static int drbd_congested(void *congested_data, int bdi_bits)
 
 	if (get_ldev(device)) {
 		q = bdev_get_queue(device->ldev->backing_bdev);
-		r = bdi_congested(&q->backing_dev_info, bdi_bits);
+		r = bdi_congested(q->backing_dev_info, bdi_bits);
 		put_ldev(device);
 		if (r)
 			reason = 'b';
@@ -2834,8 +2834,8 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	/* we have no partitions. we contain only ourselves. */
 	device->this_bdev->bd_contains = device->this_bdev;
 
-	q->backing_dev_info.congested_fn = drbd_congested;
-	q->backing_dev_info.congested_data = device;
+	q->backing_dev_info->congested_fn = drbd_congested;
+	q->backing_dev_info->congested_data = device;
 
 	blk_queue_make_request(q, drbd_make_request);
 	blk_queue_write_cache(q, true, true);
@@ -2948,7 +2948,6 @@ void drbd_delete_device(struct drbd_device *device)
 	struct drbd_resource *resource = device->resource;
 	struct drbd_connection *connection;
 	struct drbd_peer_device *peer_device;
-	int refs = 3;
 
 	/* move to free_peer_device() */
 	for_each_peer_device(peer_device, device)
@@ -2956,13 +2955,15 @@ void drbd_delete_device(struct drbd_device *device)
 	drbd_debugfs_device_cleanup(device);
 	for_each_connection(connection, resource) {
 		idr_remove(&connection->peer_devices, device->vnr);
-		refs++;
+		kref_put(&device->kref, drbd_destroy_device);
 	}
 	idr_remove(&resource->devices, device->vnr);
+	kref_put(&device->kref, drbd_destroy_device);
 	idr_remove(&drbd_devices, device_to_minor(device));
+	kref_put(&device->kref, drbd_destroy_device);
 	del_gendisk(device->vdisk);
 	synchronize_rcu();
-	kref_sub(&device->kref, refs, drbd_destroy_device);
+	kref_put(&device->kref, drbd_destroy_device);
 }
 
 static int __init drbd_init(void)
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index f35db29cac76..908c704e20aa 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1328,11 +1328,13 @@ static void drbd_setup_queue_param(struct drbd_device *device, struct drbd_backi
 	if (b) {
 		blk_queue_stack_limits(q, b);
 
-		if (q->backing_dev_info.ra_pages != b->backing_dev_info.ra_pages) {
+		if (q->backing_dev_info->ra_pages !=
+		    b->backing_dev_info->ra_pages) {
 			drbd_info(device, "Adjusting my ra_pages to backing device's (%lu -> %lu)\n",
-				 q->backing_dev_info.ra_pages,
-				 b->backing_dev_info.ra_pages);
-			q->backing_dev_info.ra_pages = b->backing_dev_info.ra_pages;
+				 q->backing_dev_info->ra_pages,
+				 b->backing_dev_info->ra_pages);
+			q->backing_dev_info->ra_pages =
+						b->backing_dev_info->ra_pages;
 		}
 	}
 	fixup_discard_if_not_supported(q);
@@ -3345,7 +3347,7 @@ static void device_to_statistics(struct device_statistics *s,
 		s->dev_disk_flags = md->flags;
 		q = bdev_get_queue(device->ldev->backing_bdev);
 		s->dev_lower_blocked =
-			bdi_congested(&q->backing_dev_info,
+			bdi_congested(q->backing_dev_info,
 				      (1 << WB_async_congested) |
 				      (1 << WB_sync_congested));
 		put_ldev(device);
diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c
index be2b93fd2c11..8378142f7a55 100644
--- a/drivers/block/drbd/drbd_proc.c
+++ b/drivers/block/drbd/drbd_proc.c
@@ -288,7 +288,7 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 			seq_printf(seq, "%2d: cs:Unconfigured\n", i);
 		} else {
 			/* reset device->congestion_reason */
-			bdi_rw_congested(&device->rq_queue->backing_dev_info);
+			bdi_rw_congested(device->rq_queue->backing_dev_info);
 
 			nc = rcu_dereference(first_peer_device(device)->connection->net_conf);
 			wp = nc ? nc->wire_protocol - DRBD_PROT_A + 'A' : ' ';
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index de279fe4e4fd..652114ae1a8a 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -421,7 +421,6 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 	struct drbd_peer_device *peer_device = first_peer_device(device);
 	unsigned s = req->rq_state;
 	int c_put = 0;
-	int k_put = 0;
 
 	if (drbd_suspended(device) && !((s | clear) & RQ_COMPLETION_SUSP))
 		set |= RQ_COMPLETION_SUSP;
@@ -437,6 +436,8 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 
 	/* intent: get references */
 
+	kref_get(&req->kref);
+
 	if (!(s & RQ_LOCAL_PENDING) && (set & RQ_LOCAL_PENDING))
 		atomic_inc(&req->completion_ref);
 
@@ -473,15 +474,12 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 
 	if (!(s & RQ_LOCAL_ABORTED) && (set & RQ_LOCAL_ABORTED)) {
 		D_ASSERT(device, req->rq_state & RQ_LOCAL_PENDING);
-		/* local completion may still come in later,
-		 * we need to keep the req object around. */
-		kref_get(&req->kref);
 		++c_put;
 	}
 
 	if ((s & RQ_LOCAL_PENDING) && (clear & RQ_LOCAL_PENDING)) {
 		if (req->rq_state & RQ_LOCAL_ABORTED)
-			++k_put;
+			kref_put(&req->kref, drbd_req_destroy);
 		else
 			++c_put;
 		list_del_init(&req->req_pending_local);
@@ -503,7 +501,7 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 		if (s & RQ_NET_SENT)
 			atomic_sub(req->i.size >> 9, &device->ap_in_flight);
 		if (s & RQ_EXP_BARR_ACK)
-			++k_put;
+			kref_put(&req->kref, drbd_req_destroy);
 		req->net_done_jif = jiffies;
 
 		/* in ahead/behind mode, or just in case,
@@ -516,25 +514,16 @@ static void mod_rq_state(struct drbd_request *req, struct bio_and_error *m,
 
 	/* potentially complete and destroy */
 
-	if (k_put || c_put) {
-		/* Completion does it's own kref_put.  If we are going to
-		 * kref_sub below, we need req to be still around then. */
-		int at_least = k_put + !!c_put;
-		int refcount = atomic_read(&req->kref.refcount);
-		if (refcount < at_least)
-			drbd_err(device,
-				"mod_rq_state: Logic BUG: %x -> %x: refcount = %d, should be >= %d\n",
-				s, req->rq_state, refcount, at_least);
-	}
-
 	/* If we made progress, retry conflicting peer requests, if any. */
 	if (req->i.waiting)
 		wake_up(&device->misc_wait);
 
-	if (c_put)
-		k_put += drbd_req_put_completion_ref(req, m, c_put);
-	if (k_put)
-		kref_sub(&req->kref, k_put, drbd_req_destroy);
+	if (c_put) {
+		if (drbd_req_put_completion_ref(req, m, c_put))
+			kref_put(&req->kref, drbd_req_destroy);
+	} else {
+		kref_put(&req->kref, drbd_req_destroy);
+	}
 }
 
 static void drbd_report_io_error(struct drbd_device *device, struct drbd_request *req)
@@ -938,7 +927,7 @@ static bool remote_due_to_read_balancing(struct drbd_device *device, sector_t se
 
 	switch (rbm) {
 	case RB_CONGESTED_REMOTE:
-		bdi = &device->ldev->backing_bdev->bd_disk->queue->backing_dev_info;
+		bdi = device->ldev->backing_bdev->bd_disk->queue->backing_dev_info;
 		return bdi_read_congested(bdi);
 	case RB_LEAST_PENDING:
 		return atomic_read(&device->local_cnt) >
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index a391a3cfb3fe..45b4384f650c 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -2900,8 +2900,8 @@ static void do_fd_request(struct request_queue *q)
 		return;
 
 	if (WARN(atomic_read(&usage_count) == 0,
-		 "warning: usage count=0, current_req=%p sect=%ld type=%x flags=%llx\n",
-		 current_req, (long)blk_rq_pos(current_req), current_req->cmd_type,
+		 "warning: usage count=0, current_req=%p sect=%ld flags=%llx\n",
+		 current_req, (long)blk_rq_pos(current_req),
 		 (unsigned long long) current_req->cmd_flags))
 		return;
 
@@ -3119,7 +3119,7 @@ static int raw_cmd_copyin(int cmd, void __user *param,
 	*rcmd = NULL;
 
 loop:
-	ptr = kmalloc(sizeof(struct floppy_raw_cmd), GFP_USER);
+	ptr = kmalloc(sizeof(struct floppy_raw_cmd), GFP_KERNEL);
 	if (!ptr)
 		return -ENOMEM;
 	*rcmd = ptr;
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
index a9b48ed7a3cd..6043648da1e8 100644
--- a/drivers/block/hd.c
+++ b/drivers/block/hd.c
@@ -626,30 +626,29 @@ repeat:
 		req_data_dir(req) == READ ? "read" : "writ",
 		cyl, head, sec, nsect, bio_data(req->bio));
 #endif
-	if (req->cmd_type == REQ_TYPE_FS) {
-		switch (rq_data_dir(req)) {
-		case READ:
-			hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ,
-				&read_intr);
-			if (reset)
-				goto repeat;
-			break;
-		case WRITE:
-			hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_WRITE,
-				&write_intr);
-			if (reset)
-				goto repeat;
-			if (wait_DRQ()) {
-				bad_rw_intr();
-				goto repeat;
-			}
-			outsw(HD_DATA, bio_data(req->bio), 256);
-			break;
-		default:
-			printk("unknown hd-command\n");
-			hd_end_request_cur(-EIO);
-			break;
+
+	switch (req_op(req)) {
+	case REQ_OP_READ:
+		hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ,
+			&read_intr);
+		if (reset)
+			goto repeat;
+		break;
+	case REQ_OP_WRITE:
+		hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_WRITE,
+			&write_intr);
+		if (reset)
+			goto repeat;
+		if (wait_DRQ()) {
+			bad_rw_intr();
+			goto repeat;
 		}
+		outsw(HD_DATA, bio_data(req->bio), 256);
+		break;
+	default:
+		printk("unknown hd-command\n");
+		hd_end_request_cur(-EIO);
+		break;
 	}
 }
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f347285c67ec..304377182c1a 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1097,9 +1097,12 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
 		return -EINVAL;
 
+	/* I/O need to be drained during transfer transition */
+	blk_mq_freeze_queue(lo->lo_queue);
+
 	err = loop_release_xfer(lo);
 	if (err)
-		return err;
+		goto exit;
 
 	if (info->lo_encrypt_type) {
 		unsigned int type = info->lo_encrypt_type;
@@ -1114,12 +1117,14 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 
 	err = loop_init_xfer(lo, xfer, info);
 	if (err)
-		return err;
+		goto exit;
 
 	if (lo->lo_offset != info->lo_offset ||
 	    lo->lo_sizelimit != info->lo_sizelimit)
-		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit))
-			return -EFBIG;
+		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
+			err = -EFBIG;
+			goto exit;
+		}
 
 	loop_config_discard(lo);
 
@@ -1156,7 +1161,9 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	/* update dio if lo_offset or transfer is changed */
 	__loop_update_dio(lo, lo->use_dio);
 
-	return 0;
+ exit:
+	blk_mq_unfreeze_queue(lo->lo_queue);
+	return err;
 }
 
 static int
diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c
index e937fcf71769..286f276f586e 100644
--- a/drivers/block/mg_disk.c
+++ b/drivers/block/mg_disk.c
@@ -670,15 +670,17 @@ static void mg_request_poll(struct request_queue *q)
 				break;
 		}
 
-		if (unlikely(host->req->cmd_type != REQ_TYPE_FS)) {
-			mg_end_request_cur(host, -EIO);
-			continue;
-		}
-
-		if (rq_data_dir(host->req) == READ)
+		switch (req_op(host->req)) {
+		case REQ_OP_READ:
 			mg_read(host->req);
-		else
+			break;
+		case REQ_OP_WRITE:
 			mg_write(host->req);
+			break;
+		default:
+			mg_end_request_cur(host, -EIO);
+			break;
+		}
 	}
 }
 
@@ -687,13 +689,15 @@ static unsigned int mg_issue_req(struct request *req,
 		unsigned int sect_num,
 		unsigned int sect_cnt)
 {
-	if (rq_data_dir(req) == READ) {
+	switch (req_op(host->req)) {
+	case REQ_OP_READ:
 		if (mg_out(host, sect_num, sect_cnt, MG_CMD_RD, &mg_read_intr)
 				!= MG_ERR_NONE) {
 			mg_bad_rw_intr(host);
 			return host->error;
 		}
-	} else {
+		break;
+	case REQ_OP_WRITE:
 		/* TODO : handler */
 		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
 		if (mg_out(host, sect_num, sect_cnt, MG_CMD_WR, &mg_write_intr)
@@ -712,6 +716,10 @@ static unsigned int mg_issue_req(struct request *req,
 		mod_timer(&host->timer, jiffies + 3 * HZ);
 		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
 				MG_REG_COMMAND);
+		break;
+	default:
+		mg_end_request_cur(host, -EIO);
+		break;
 	}
 	return MG_ERR_NONE;
 }
@@ -753,11 +761,6 @@ static void mg_request(struct request_queue *q)
 			continue;
 		}
 
-		if (unlikely(req->cmd_type != REQ_TYPE_FS)) {
-			mg_end_request_cur(host, -EIO);
-			continue;
-		}
-
 		if (!mg_issue_req(req, host, sect_num, sect_cnt))
 			return;
 	}
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 9fd06eeb1a17..0be84a3cb6d7 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -41,6 +41,9 @@
 
 #include <linux/nbd.h>
 
+static DEFINE_IDR(nbd_index_idr);
+static DEFINE_MUTEX(nbd_index_mutex);
+
 struct nbd_sock {
 	struct socket *sock;
 	struct mutex tx_lock;
@@ -89,8 +92,9 @@ static struct dentry *nbd_dbg_dir;
 #define NBD_MAGIC 0x68797548
 
 static unsigned int nbds_max = 16;
-static struct nbd_device *nbd_dev;
 static int max_part;
+static struct workqueue_struct *recv_workqueue;
+static int part_shift;
 
 static inline struct device *nbd_to_dev(struct nbd_device *nbd)
 {
@@ -193,13 +197,6 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	set_bit(NBD_TIMEDOUT, &nbd->runtime_flags);
 	req->errors++;
 
-	/*
-	 * If our disconnect packet times out then we're already holding the
-	 * config_lock and could deadlock here, so just set an error and return,
-	 * we'll handle shutting everything down later.
-	 */
-	if (req->cmd_type == REQ_TYPE_DRV_PRIV)
-		return BLK_EH_HANDLED;
 	mutex_lock(&nbd->config_lock);
 	sock_shutdown(nbd);
 	mutex_unlock(&nbd->config_lock);
@@ -278,14 +275,29 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	u32 type;
 	u32 tag = blk_mq_unique_tag(req);
 
-	if (req_op(req) == REQ_OP_DISCARD)
+	switch (req_op(req)) {
+	case REQ_OP_DISCARD:
 		type = NBD_CMD_TRIM;
-	else if (req_op(req) == REQ_OP_FLUSH)
+		break;
+	case REQ_OP_FLUSH:
 		type = NBD_CMD_FLUSH;
-	else if (rq_data_dir(req) == WRITE)
+		break;
+	case REQ_OP_WRITE:
 		type = NBD_CMD_WRITE;
-	else
+		break;
+	case REQ_OP_READ:
 		type = NBD_CMD_READ;
+		break;
+	default:
+		return -EIO;
+	}
+
+	if (rq_data_dir(req) == WRITE &&
+	    (nbd->flags & NBD_FLAG_READ_ONLY)) {
+		dev_err_ratelimited(disk_to_dev(nbd->disk),
+				    "Write on read-only\n");
+		return -EIO;
+	}
 
 	memset(&request, 0, sizeof(request));
 	request.magic = htonl(NBD_REQUEST_MAGIC);
@@ -510,18 +522,6 @@ static void nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 		goto error_out;
 	}
 
-	if (req->cmd_type != REQ_TYPE_FS &&
-	    req->cmd_type != REQ_TYPE_DRV_PRIV)
-		goto error_out;
-
-	if (req->cmd_type == REQ_TYPE_FS &&
-	    rq_data_dir(req) == WRITE &&
-	    (nbd->flags & NBD_FLAG_READ_ONLY)) {
-		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Write on read-only\n");
-		goto error_out;
-	}
-
 	req->errors = 0;
 
 	nsock = nbd->socks[index];
@@ -785,7 +785,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 			INIT_WORK(&args[i].work, recv_work);
 			args[i].nbd = nbd;
 			args[i].index = i;
-			queue_work(system_long_wq, &args[i].work);
+			queue_work(recv_workqueue, &args[i].work);
 		}
 		wait_event_interruptible(nbd->recv_wq,
 					 atomic_read(&nbd->recv_threads) == 0);
@@ -996,6 +996,103 @@ static struct blk_mq_ops nbd_mq_ops = {
 	.timeout	= nbd_xmit_timeout,
 };
 
+static void nbd_dev_remove(struct nbd_device *nbd)
+{
+	struct gendisk *disk = nbd->disk;
+	nbd->magic = 0;
+	if (disk) {
+		del_gendisk(disk);
+		blk_cleanup_queue(disk->queue);
+		blk_mq_free_tag_set(&nbd->tag_set);
+		put_disk(disk);
+	}
+	kfree(nbd);
+}
+
+static int nbd_dev_add(int index)
+{
+	struct nbd_device *nbd;
+	struct gendisk *disk;
+	struct request_queue *q;
+	int err = -ENOMEM;
+
+	nbd = kzalloc(sizeof(struct nbd_device), GFP_KERNEL);
+	if (!nbd)
+		goto out;
+
+	disk = alloc_disk(1 << part_shift);
+	if (!disk)
+		goto out_free_nbd;
+
+	if (index >= 0) {
+		err = idr_alloc(&nbd_index_idr, nbd, index, index + 1,
+				GFP_KERNEL);
+		if (err == -ENOSPC)
+			err = -EEXIST;
+	} else {
+		err = idr_alloc(&nbd_index_idr, nbd, 0, 0, GFP_KERNEL);
+		if (err >= 0)
+			index = err;
+	}
+	if (err < 0)
+		goto out_free_disk;
+
+	nbd->disk = disk;
+	nbd->tag_set.ops = &nbd_mq_ops;
+	nbd->tag_set.nr_hw_queues = 1;
+	nbd->tag_set.queue_depth = 128;
+	nbd->tag_set.numa_node = NUMA_NO_NODE;
+	nbd->tag_set.cmd_size = sizeof(struct nbd_cmd);
+	nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE |
+		BLK_MQ_F_SG_MERGE | BLK_MQ_F_BLOCKING;
+	nbd->tag_set.driver_data = nbd;
+
+	err = blk_mq_alloc_tag_set(&nbd->tag_set);
+	if (err)
+		goto out_free_idr;
+
+	q = blk_mq_init_queue(&nbd->tag_set);
+	if (IS_ERR(q)) {
+		err = PTR_ERR(q);
+		goto out_free_tags;
+	}
+	disk->queue = q;
+
+	/*
+	 * Tell the block layer that we are not a rotational device
+	 */
+	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, disk->queue);
+	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
+	disk->queue->limits.discard_granularity = 512;
+	blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
+	disk->queue->limits.discard_zeroes_data = 0;
+	blk_queue_max_hw_sectors(disk->queue, 65536);
+	disk->queue->limits.max_sectors = 256;
+
+	nbd->magic = NBD_MAGIC;
+	mutex_init(&nbd->config_lock);
+	disk->major = NBD_MAJOR;
+	disk->first_minor = index << part_shift;
+	disk->fops = &nbd_fops;
+	disk->private_data = nbd;
+	sprintf(disk->disk_name, "nbd%d", index);
+	init_waitqueue_head(&nbd->recv_wq);
+	nbd_reset(nbd);
+	add_disk(disk);
+	return index;
+
+out_free_tags:
+	blk_mq_free_tag_set(&nbd->tag_set);
+out_free_idr:
+	idr_remove(&nbd_index_idr, index);
+out_free_disk:
+	put_disk(disk);
+out_free_nbd:
+	kfree(nbd);
+out:
+	return err;
+}
+
 /*
  * And here should be modules and kernel interface 
  *  (Just smiley confuses emacs :-)
@@ -1003,9 +1100,7 @@ static struct blk_mq_ops nbd_mq_ops = {
 
 static int __init nbd_init(void)
 {
-	int err = -ENOMEM;
 	int i;
-	int part_shift;
 
 	BUILD_BUG_ON(sizeof(struct nbd_request) != 28);
 
@@ -1034,111 +1129,38 @@ static int __init nbd_init(void)
 
 	if (nbds_max > 1UL << (MINORBITS - part_shift))
 		return -EINVAL;
-
-	nbd_dev = kcalloc(nbds_max, sizeof(*nbd_dev), GFP_KERNEL);
-	if (!nbd_dev)
+	recv_workqueue = alloc_workqueue("knbd-recv",
+					 WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
+	if (!recv_workqueue)
 		return -ENOMEM;
 
-	for (i = 0; i < nbds_max; i++) {
-		struct request_queue *q;
-		struct gendisk *disk = alloc_disk(1 << part_shift);
-		if (!disk)
-			goto out;
-		nbd_dev[i].disk = disk;
-
-		nbd_dev[i].tag_set.ops = &nbd_mq_ops;
-		nbd_dev[i].tag_set.nr_hw_queues = 1;
-		nbd_dev[i].tag_set.queue_depth = 128;
-		nbd_dev[i].tag_set.numa_node = NUMA_NO_NODE;
-		nbd_dev[i].tag_set.cmd_size = sizeof(struct nbd_cmd);
-		nbd_dev[i].tag_set.flags = BLK_MQ_F_SHOULD_MERGE |
-			BLK_MQ_F_SG_MERGE | BLK_MQ_F_BLOCKING;
-		nbd_dev[i].tag_set.driver_data = &nbd_dev[i];
-
-		err = blk_mq_alloc_tag_set(&nbd_dev[i].tag_set);
-		if (err) {
-			put_disk(disk);
-			goto out;
-		}
-
-		/*
-		 * The new linux 2.5 block layer implementation requires
-		 * every gendisk to have its very own request_queue struct.
-		 * These structs are big so we dynamically allocate them.
-		 */
-		q = blk_mq_init_queue(&nbd_dev[i].tag_set);
-		if (IS_ERR(q)) {
-			blk_mq_free_tag_set(&nbd_dev[i].tag_set);
-			put_disk(disk);
-			goto out;
-		}
-		disk->queue = q;
-
-		/*
-		 * Tell the block layer that we are not a rotational device
-		 */
-		queue_flag_set_unlocked(QUEUE_FLAG_NONROT, disk->queue);
-		queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
-		disk->queue->limits.discard_granularity = 512;
-		blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
-		disk->queue->limits.discard_zeroes_data = 0;
-		blk_queue_max_hw_sectors(disk->queue, 65536);
-		disk->queue->limits.max_sectors = 256;
-	}
-
-	if (register_blkdev(NBD_MAJOR, "nbd")) {
-		err = -EIO;
-		goto out;
-	}
-
-	printk(KERN_INFO "nbd: registered device at major %d\n", NBD_MAJOR);
+	if (register_blkdev(NBD_MAJOR, "nbd"))
+		return -EIO;
 
 	nbd_dbg_init();
 
-	for (i = 0; i < nbds_max; i++) {
-		struct gendisk *disk = nbd_dev[i].disk;
-		nbd_dev[i].magic = NBD_MAGIC;
-		mutex_init(&nbd_dev[i].config_lock);
-		disk->major = NBD_MAJOR;
-		disk->first_minor = i << part_shift;
-		disk->fops = &nbd_fops;
-		disk->private_data = &nbd_dev[i];
-		sprintf(disk->disk_name, "nbd%d", i);
-		init_waitqueue_head(&nbd_dev[i].recv_wq);
-		nbd_reset(&nbd_dev[i]);
-		add_disk(disk);
-	}
+	mutex_lock(&nbd_index_mutex);
+	for (i = 0; i < nbds_max; i++)
+		nbd_dev_add(i);
+	mutex_unlock(&nbd_index_mutex);
+	return 0;
+}
 
+static int nbd_exit_cb(int id, void *ptr, void *data)
+{
+	struct nbd_device *nbd = ptr;
+	nbd_dev_remove(nbd);
 	return 0;
-out:
-	while (i--) {
-		blk_mq_free_tag_set(&nbd_dev[i].tag_set);
-		blk_cleanup_queue(nbd_dev[i].disk->queue);
-		put_disk(nbd_dev[i].disk);
-	}
-	kfree(nbd_dev);
-	return err;
 }
 
 static void __exit nbd_cleanup(void)
 {
-	int i;
-
 	nbd_dbg_close();
 
-	for (i = 0; i < nbds_max; i++) {
-		struct gendisk *disk = nbd_dev[i].disk;
-		nbd_dev[i].magic = 0;
-		if (disk) {
-			del_gendisk(disk);
-			blk_cleanup_queue(disk->queue);
-			blk_mq_free_tag_set(&nbd_dev[i].tag_set);
-			put_disk(disk);
-		}
-	}
+	idr_for_each(&nbd_index_idr, &nbd_exit_cb, NULL);
+	idr_destroy(&nbd_index_idr);
+	destroy_workqueue(recv_workqueue);
 	unregister_blkdev(NBD_MAJOR, "nbd");
-	kfree(nbd_dev);
-	printk(KERN_INFO "nbd: unregistered device at major %d\n", NBD_MAJOR);
 }
 
 module_init(nbd_init);
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index c0e14e54909b..6f2e565bccc5 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -420,7 +420,8 @@ static void null_lnvm_end_io(struct request *rq, int error)
 {
 	struct nvm_rq *rqd = rq->end_io_data;
 
-	nvm_end_io(rqd, error);
+	rqd->error = error;
+	nvm_end_io(rqd);
 
 	blk_put_request(rq);
 }
@@ -431,11 +432,11 @@ static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	struct request *rq;
 	struct bio *bio = rqd->bio;
 
-	rq = blk_mq_alloc_request(q, bio_data_dir(bio), 0);
+	rq = blk_mq_alloc_request(q,
+		op_is_write(bio_op(bio)) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
 	if (IS_ERR(rq))
 		return -ENOMEM;
 
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->__sector = bio->bi_iter.bi_sector;
 	rq->ioprio = bio_prio(bio);
 
@@ -460,7 +461,6 @@ static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
 
 	id->ver_id = 0x1;
 	id->vmnt = 0;
-	id->cgrps = 1;
 	id->cap = 0x2;
 	id->dom = 0x1;
 
@@ -479,7 +479,7 @@ static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
 
 	sector_div(size, bs); /* convert size to pages */
 	size >>= 8; /* concert size to pgs pr blk */
-	grp = &id->groups[0];
+	grp = &id->grp;
 	grp->mtype = 0;
 	grp->fmtype = 0;
 	grp->num_ch = 1;
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index 92900f5f0b47..8127b8201a01 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -308,12 +308,6 @@ static void osdblk_rq_fn(struct request_queue *q)
 		if (!rq)
 			break;
 
-		/* filter out block requests we don't understand */
-		if (rq->cmd_type != REQ_TYPE_FS) {
-			blk_end_request_all(rq, 0);
-			continue;
-		}
-
 		/* deduce our operation (read, write, flush) */
 		/* I wish the block layer simplified cmd_type/cmd_flags/cmd[]
 		 * into a clearly defined set of RPC commands:
diff --git a/drivers/block/paride/Kconfig b/drivers/block/paride/Kconfig
index efefb5ac3004..3a15247942e4 100644
--- a/drivers/block/paride/Kconfig
+++ b/drivers/block/paride/Kconfig
@@ -25,6 +25,7 @@ config PARIDE_PD
 config PARIDE_PCD
 	tristate "Parallel port ATAPI CD-ROMs"
 	depends on PARIDE
+	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	---help---
 	  This option enables the high-level driver for ATAPI CD-ROM devices
 	  connected through a parallel port. If you chose to build PARIDE
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 5fd2d0e25567..10aed84244f5 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -273,7 +273,7 @@ static const struct block_device_operations pcd_bdops = {
 	.check_events	= pcd_block_check_events,
 };
 
-static struct cdrom_device_ops pcd_dops = {
+static const struct cdrom_device_ops pcd_dops = {
 	.open		= pcd_open,
 	.release	= pcd_release,
 	.drive_status	= pcd_drive_status,
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index c3ed2fc72daa..644ba0888bd4 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -439,18 +439,16 @@ static int pd_retries = 0;	/* i/o error retry count */
 static int pd_block;		/* address of next requested block */
 static int pd_count;		/* number of blocks still to do */
 static int pd_run;		/* sectors in current cluster */
-static int pd_cmd;		/* current command READ/WRITE */
 static char *pd_buf;		/* buffer for request in progress */
 
 static enum action do_pd_io_start(void)
 {
-	if (pd_req->cmd_type == REQ_TYPE_DRV_PRIV) {
+	switch (req_op(pd_req)) {
+	case REQ_OP_DRV_IN:
 		phase = pd_special;
 		return pd_special();
-	}
-
-	pd_cmd = rq_data_dir(pd_req);
-	if (pd_cmd == READ || pd_cmd == WRITE) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
 		pd_block = blk_rq_pos(pd_req);
 		pd_count = blk_rq_cur_sectors(pd_req);
 		if (pd_block + pd_count > get_capacity(pd_req->rq_disk))
@@ -458,7 +456,7 @@ static enum action do_pd_io_start(void)
 		pd_run = blk_rq_sectors(pd_req);
 		pd_buf = bio_data(pd_req->bio);
 		pd_retries = 0;
-		if (pd_cmd == READ)
+		if (req_op(pd_req) == REQ_OP_READ)
 			return do_pd_read_start();
 		else
 			return do_pd_write_start();
@@ -723,11 +721,10 @@ static int pd_special_command(struct pd_unit *disk,
 	struct request *rq;
 	int err = 0;
 
-	rq = blk_get_request(disk->gd->queue, READ, __GFP_RECLAIM);
+	rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	rq->special = func;
 
 	err = blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 1b94c1ca5c5f..66d846ba85a9 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -704,10 +704,10 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 	int ret = 0;
 
 	rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
-			     WRITE : READ, __GFP_RECLAIM);
+			     REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
-	blk_rq_set_block_pc(rq);
+	scsi_req_init(rq);
 
 	if (cgc->buflen) {
 		ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
@@ -716,8 +716,8 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 			goto out;
 	}
 
-	rq->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
-	memcpy(rq->cmd, cgc->cmd, CDROM_PACKET_SIZE);
+	scsi_req(rq)->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
+	memcpy(scsi_req(rq)->cmd, cgc->cmd, CDROM_PACKET_SIZE);
 
 	rq->timeout = 60*HZ;
 	if (cgc->quiet)
@@ -1243,7 +1243,7 @@ try_next_bio:
 	 		&& pd->bio_queue_size <= pd->write_congestion_off);
 	spin_unlock(&pd->lock);
 	if (wakeup) {
-		clear_bdi_congested(&pd->disk->queue->backing_dev_info,
+		clear_bdi_congested(pd->disk->queue->backing_dev_info,
 					BLK_RW_ASYNC);
 	}
 
@@ -2370,7 +2370,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
 	spin_lock(&pd->lock);
 	if (pd->write_congestion_on > 0
 	    && pd->bio_queue_size >= pd->write_congestion_on) {
-		set_bdi_congested(&q->backing_dev_info, BLK_RW_ASYNC);
+		set_bdi_congested(q->backing_dev_info, BLK_RW_ASYNC);
 		do {
 			spin_unlock(&pd->lock);
 			congestion_wait(BLK_RW_ASYNC, HZ);
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 76f33c84ce3d..a809e3e9feb8 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -196,16 +196,19 @@ static void ps3disk_do_request(struct ps3_storage_device *dev,
 	dev_dbg(&dev->sbd.core, "%s:%u\n", __func__, __LINE__);
 
 	while ((req = blk_fetch_request(q))) {
-		if (req_op(req) == REQ_OP_FLUSH) {
+		switch (req_op(req)) {
+		case REQ_OP_FLUSH:
 			if (ps3disk_submit_flush_request(dev, req))
-				break;
-		} else if (req->cmd_type == REQ_TYPE_FS) {
+				return;
+			break;
+		case REQ_OP_READ:
+		case REQ_OP_WRITE:
 			if (ps3disk_submit_request_sg(dev, req))
-				break;
-		} else {
+				return;
+			break;
+		default:
 			blk_dump_rq_flags(req, DEVICE_NAME " bad request");
 			__blk_end_request_all(req, -EIO);
-			continue;
 		}
 	}
 }
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 36d2b9f4e836..362cecc77130 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1535,7 +1535,7 @@ static bool obj_request_overlaps_parent(struct rbd_obj_request *obj_request)
 static void rbd_obj_request_get(struct rbd_obj_request *obj_request)
 {
 	dout("%s: obj %p (was %d)\n", __func__, obj_request,
-		atomic_read(&obj_request->kref.refcount));
+		kref_read(&obj_request->kref));
 	kref_get(&obj_request->kref);
 }
 
@@ -1544,14 +1544,14 @@ static void rbd_obj_request_put(struct rbd_obj_request *obj_request)
 {
 	rbd_assert(obj_request != NULL);
 	dout("%s: obj %p (was %d)\n", __func__, obj_request,
-		atomic_read(&obj_request->kref.refcount));
+		kref_read(&obj_request->kref));
 	kref_put(&obj_request->kref, rbd_obj_request_destroy);
 }
 
 static void rbd_img_request_get(struct rbd_img_request *img_request)
 {
 	dout("%s: img %p (was %d)\n", __func__, img_request,
-	     atomic_read(&img_request->kref.refcount));
+	     kref_read(&img_request->kref));
 	kref_get(&img_request->kref);
 }
 
@@ -1562,7 +1562,7 @@ static void rbd_img_request_put(struct rbd_img_request *img_request)
 {
 	rbd_assert(img_request != NULL);
 	dout("%s: img %p (was %d)\n", __func__, img_request,
-		atomic_read(&img_request->kref.refcount));
+		kref_read(&img_request->kref));
 	if (img_request_child_test(img_request))
 		kref_put(&img_request->kref, rbd_parent_request_destroy);
 	else
@@ -4099,19 +4099,21 @@ static void rbd_queue_workfn(struct work_struct *work)
 	bool must_be_locked;
 	int result;
 
-	if (rq->cmd_type != REQ_TYPE_FS) {
-		dout("%s: non-fs request type %d\n", __func__,
-			(int) rq->cmd_type);
-		result = -EIO;
-		goto err;
-	}
-
-	if (req_op(rq) == REQ_OP_DISCARD)
+	switch (req_op(rq)) {
+	case REQ_OP_DISCARD:
 		op_type = OBJ_OP_DISCARD;
-	else if (req_op(rq) == REQ_OP_WRITE)
+		break;
+	case REQ_OP_WRITE:
 		op_type = OBJ_OP_WRITE;
-	else
+		break;
+	case REQ_OP_READ:
 		op_type = OBJ_OP_READ;
+		break;
+	default:
+		dout("%s: non-fs request type %d\n", __func__, req_op(rq));
+		result = -EIO;
+		goto err;
+	}
 
 	/* Ignore/skip any zero-length requests */
 
@@ -4524,7 +4526,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	q->limits.discard_zeroes_data = 1;
 
 	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
-		q->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES;
+		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
 
 	disk->queue = q;
 
diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index abf805e332e2..27833e4dae2a 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -1204,10 +1204,11 @@ static void skd_complete_special(struct skd_device *skdev,
 static int skd_bdev_ioctl(struct block_device *bdev, fmode_t mode,
 			  uint cmd_in, ulong arg)
 {
-	int rc = 0;
+	static const int sg_version_num = 30527;
+	int rc = 0, timeout;
 	struct gendisk *disk = bdev->bd_disk;
 	struct skd_device *skdev = disk->private_data;
-	void __user *p = (void *)arg;
+	int __user *p = (int __user *)arg;
 
 	pr_debug("%s:%s:%d %s: CMD[%s] ioctl  mode 0x%x, cmd 0x%x arg %0lx\n",
 		 skdev->name, __func__, __LINE__,
@@ -1218,12 +1219,18 @@ static int skd_bdev_ioctl(struct block_device *bdev, fmode_t mode,
 
 	switch (cmd_in) {
 	case SG_SET_TIMEOUT:
+		rc = get_user(timeout, p);
+		if (!rc)
+			disk->queue->sg_timeout = clock_t_to_jiffies(timeout);
+		break;
 	case SG_GET_TIMEOUT:
+		rc = jiffies_to_clock_t(disk->queue->sg_timeout);
+		break;
 	case SG_GET_VERSION_NUM:
-		rc = scsi_cmd_ioctl(disk->queue, disk, mode, cmd_in, p);
+		rc = put_user(sg_version_num, p);
 		break;
 	case SG_IO:
-		rc = skd_ioctl_sg_io(skdev, mode, p);
+		rc = skd_ioctl_sg_io(skdev, mode, (void __user *)arg);
 		break;
 
 	default:
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index 0e93ad7b8511..c8e072caf56f 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -567,7 +567,7 @@ static struct carm_request *carm_get_special(struct carm_host *host)
 	if (!crq)
 		return NULL;
 
-	rq = blk_get_request(host->oob_q, WRITE /* bogus */, GFP_KERNEL);
+	rq = blk_get_request(host->oob_q, REQ_OP_DRV_OUT, GFP_KERNEL);
 	if (IS_ERR(rq)) {
 		spin_lock_irqsave(&host->lock, flags);
 		carm_put_request(host, crq);
@@ -620,7 +620,6 @@ static int carm_array_info (struct carm_host *host, unsigned int array_idx)
 	spin_unlock_irq(&host->lock);
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx);
-	crq->rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	crq->rq->special = crq;
 	blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL);
 
@@ -661,7 +660,6 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func)
 	crq->msg_bucket = (u32) rc;
 
 	DPRINTK("blk_execute_rq_nowait, tag == %u\n", idx);
-	crq->rq->cmd_type = REQ_TYPE_DRV_PRIV;
 	crq->rq->special = crq;
 	blk_execute_rq_nowait(host->oob_q, NULL, crq->rq, true, NULL);
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 10332c24f961..024b473524c0 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -52,11 +52,13 @@ struct virtio_blk {
 };
 
 struct virtblk_req {
-	struct request *req;
-	struct virtio_blk_outhdr out_hdr;
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+	struct scsi_request sreq;	/* for SCSI passthrough, must be first */
+	u8 sense[SCSI_SENSE_BUFFERSIZE];
 	struct virtio_scsi_inhdr in_hdr;
+#endif
+	struct virtio_blk_outhdr out_hdr;
 	u8 status;
-	u8 sense[SCSI_SENSE_BUFFERSIZE];
 	struct scatterlist sg[];
 };
 
@@ -72,28 +74,88 @@ static inline int virtblk_result(struct virtblk_req *vbr)
 	}
 }
 
-static int __virtblk_add_req(struct virtqueue *vq,
-			     struct virtblk_req *vbr,
-			     struct scatterlist *data_sg,
-			     bool have_data)
+/*
+ * If this is a packet command we need a couple of additional headers.  Behind
+ * the normal outhdr we put a segment with the scsi command block, and before
+ * the normal inhdr we put the sense data and the inhdr with additional status
+ * information.
+ */
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+static int virtblk_add_req_scsi(struct virtqueue *vq, struct virtblk_req *vbr,
+		struct scatterlist *data_sg, bool have_data)
 {
 	struct scatterlist hdr, status, cmd, sense, inhdr, *sgs[6];
 	unsigned int num_out = 0, num_in = 0;
-	__virtio32 type = vbr->out_hdr.type & ~cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT);
 
 	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
 	sgs[num_out++] = &hdr;
+	sg_init_one(&cmd, vbr->sreq.cmd, vbr->sreq.cmd_len);
+	sgs[num_out++] = &cmd;
+
+	if (have_data) {
+		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
+			sgs[num_out++] = data_sg;
+		else
+			sgs[num_out + num_in++] = data_sg;
+	}
+
+	sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE);
+	sgs[num_out + num_in++] = &sense;
+	sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
+	sgs[num_out + num_in++] = &inhdr;
+	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
+	sgs[num_out + num_in++] = &status;
+
+	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
+}
+
+static inline void virtblk_scsi_reques_done(struct request *req)
+{
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+	struct virtio_blk *vblk = req->q->queuedata;
+	struct scsi_request *sreq = &vbr->sreq;
+
+	sreq->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
+	sreq->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
+	req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
+}
+
+static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
+			     unsigned int cmd, unsigned long data)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	struct virtio_blk *vblk = disk->private_data;
 
 	/*
-	 * If this is a packet command we need a couple of additional headers.
-	 * Behind the normal outhdr we put a segment with the scsi command
-	 * block, and before the normal inhdr we put the sense data and the
-	 * inhdr with additional status information.
+	 * Only allow the generic SCSI ioctls if the host can support it.
 	 */
-	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
-		sg_init_one(&cmd, vbr->req->cmd, vbr->req->cmd_len);
-		sgs[num_out++] = &cmd;
-	}
+	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
+		return -ENOTTY;
+
+	return scsi_cmd_blk_ioctl(bdev, mode, cmd,
+				  (void __user *)data);
+}
+#else
+static inline int virtblk_add_req_scsi(struct virtqueue *vq,
+		struct virtblk_req *vbr, struct scatterlist *data_sg,
+		bool have_data)
+{
+	return -EIO;
+}
+static inline void virtblk_scsi_reques_done(struct request *req)
+{
+}
+#define virtblk_ioctl	NULL
+#endif /* CONFIG_VIRTIO_BLK_SCSI */
+
+static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
+		struct scatterlist *data_sg, bool have_data)
+{
+	struct scatterlist hdr, status, *sgs[3];
+	unsigned int num_out = 0, num_in = 0;
+
+	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
+	sgs[num_out++] = &hdr;
 
 	if (have_data) {
 		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
@@ -102,14 +164,6 @@ static int __virtblk_add_req(struct virtqueue *vq,
 			sgs[num_out + num_in++] = data_sg;
 	}
 
-	if (type == cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_SCSI_CMD)) {
-		memcpy(vbr->sense, vbr->req->sense, SCSI_SENSE_BUFFERSIZE);
-		sg_init_one(&sense, vbr->sense, SCSI_SENSE_BUFFERSIZE);
-		sgs[num_out + num_in++] = &sense;
-		sg_init_one(&inhdr, &vbr->in_hdr, sizeof(vbr->in_hdr));
-		sgs[num_out + num_in++] = &inhdr;
-	}
-
 	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
 	sgs[num_out + num_in++] = &status;
 
@@ -119,15 +173,16 @@ static int __virtblk_add_req(struct virtqueue *vq,
 static inline void virtblk_request_done(struct request *req)
 {
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
-	struct virtio_blk *vblk = req->q->queuedata;
 	int error = virtblk_result(vbr);
 
-	if (req->cmd_type == REQ_TYPE_BLOCK_PC) {
-		req->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
-		req->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
-		req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
-	} else if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
+	switch (req_op(req)) {
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
+		virtblk_scsi_reques_done(req);
+		break;
+	case REQ_OP_DRV_IN:
 		req->errors = (error != 0);
+		break;
 	}
 
 	blk_mq_end_request(req, error);
@@ -146,7 +201,9 @@ static void virtblk_done(struct virtqueue *vq)
 	do {
 		virtqueue_disable_cb(vq);
 		while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
-			blk_mq_complete_request(vbr->req, vbr->req->errors);
+			struct request *req = blk_mq_rq_from_pdu(vbr);
+
+			blk_mq_complete_request(req, req->errors);
 			req_done = true;
 		}
 		if (unlikely(virtqueue_is_broken(vq)))
@@ -170,49 +227,50 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	int qid = hctx->queue_num;
 	int err;
 	bool notify = false;
+	u32 type;
 
 	BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems);
 
-	vbr->req = req;
-	if (req_op(req) == REQ_OP_FLUSH) {
-		vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_FLUSH);
-		vbr->out_hdr.sector = 0;
-		vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
-	} else {
-		switch (req->cmd_type) {
-		case REQ_TYPE_FS:
-			vbr->out_hdr.type = 0;
-			vbr->out_hdr.sector = cpu_to_virtio64(vblk->vdev, blk_rq_pos(vbr->req));
-			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
-			break;
-		case REQ_TYPE_BLOCK_PC:
-			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_SCSI_CMD);
-			vbr->out_hdr.sector = 0;
-			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
-			break;
-		case REQ_TYPE_DRV_PRIV:
-			vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_GET_ID);
-			vbr->out_hdr.sector = 0;
-			vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(vbr->req));
-			break;
-		default:
-			/* We don't put anything else in the queue. */
-			BUG();
-		}
+	switch (req_op(req)) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
+		type = 0;
+		break;
+	case REQ_OP_FLUSH:
+		type = VIRTIO_BLK_T_FLUSH;
+		break;
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
+		type = VIRTIO_BLK_T_SCSI_CMD;
+		break;
+	case REQ_OP_DRV_IN:
+		type = VIRTIO_BLK_T_GET_ID;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return BLK_MQ_RQ_QUEUE_ERROR;
 	}
 
+	vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type);
+	vbr->out_hdr.sector = type ?
+		0 : cpu_to_virtio64(vblk->vdev, blk_rq_pos(req));
+	vbr->out_hdr.ioprio = cpu_to_virtio32(vblk->vdev, req_get_ioprio(req));
+
 	blk_mq_start_request(req);
 
-	num = blk_rq_map_sg(hctx->queue, vbr->req, vbr->sg);
+	num = blk_rq_map_sg(hctx->queue, req, vbr->sg);
 	if (num) {
-		if (rq_data_dir(vbr->req) == WRITE)
+		if (rq_data_dir(req) == WRITE)
 			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_OUT);
 		else
 			vbr->out_hdr.type |= cpu_to_virtio32(vblk->vdev, VIRTIO_BLK_T_IN);
 	}
 
 	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
-	err = __virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
+	if (req_op(req) == REQ_OP_SCSI_IN || req_op(req) == REQ_OP_SCSI_OUT)
+		err = virtblk_add_req_scsi(vblk->vqs[qid].vq, vbr, vbr->sg, num);
+	else
+		err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg, num);
 	if (err) {
 		virtqueue_kick(vblk->vqs[qid].vq);
 		blk_mq_stop_hw_queue(hctx);
@@ -242,10 +300,9 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 	struct request *req;
 	int err;
 
-	req = blk_get_request(q, READ, GFP_KERNEL);
+	req = blk_get_request(q, REQ_OP_DRV_IN, GFP_KERNEL);
 	if (IS_ERR(req))
 		return PTR_ERR(req);
-	req->cmd_type = REQ_TYPE_DRV_PRIV;
 
 	err = blk_rq_map_kern(q, req, id_str, VIRTIO_BLK_ID_BYTES, GFP_KERNEL);
 	if (err)
@@ -257,22 +314,6 @@ out:
 	return err;
 }
 
-static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
-			     unsigned int cmd, unsigned long data)
-{
-	struct gendisk *disk = bdev->bd_disk;
-	struct virtio_blk *vblk = disk->private_data;
-
-	/*
-	 * Only allow the generic SCSI ioctls if the host can support it.
-	 */
-	if (!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_SCSI))
-		return -ENOTTY;
-
-	return scsi_cmd_blk_ioctl(bdev, mode, cmd,
-				  (void __user *)data);
-}
-
 /* We provide getgeo only to please some old bootloader/partitioning tools */
 static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 {
@@ -538,6 +579,9 @@ static int virtblk_init_request(void *data, struct request *rq,
 	struct virtio_blk *vblk = data;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(rq);
 
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+	vbr->sreq.sense = vbr->sense;
+#endif
 	sg_init_table(vbr->sg, vblk->sg_elems);
 	return 0;
 }
@@ -770,7 +814,7 @@ static void virtblk_remove(struct virtio_device *vdev)
 	/* Stop all the virtqueues. */
 	vdev->config->reset(vdev);
 
-	refc = atomic_read(&disk_to_dev(vblk->disk)->kobj.kref.refcount);
+	refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref);
 	put_disk(vblk->disk);
 	vdev->config->del_vqs(vdev);
 	kfree(vblk->vqs);
@@ -821,7 +865,10 @@ static const struct virtio_device_id id_table[] = {
 
 static unsigned int features_legacy[] = {
 	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
-	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
+	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
+#ifdef CONFIG_VIRTIO_BLK_SCSI
+	VIRTIO_BLK_F_SCSI,
+#endif
 	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE,
 	VIRTIO_BLK_F_MQ,
 }
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index b2bdfa81f929..5067a0a952cb 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -197,13 +197,13 @@ struct blkfront_info
 	/* Number of pages per ring buffer. */
 	unsigned int nr_ring_pages;
 	struct request_queue *rq;
-	unsigned int feature_flush;
-	unsigned int feature_fua;
+	unsigned int feature_flush:1;
+	unsigned int feature_fua:1;
 	unsigned int feature_discard:1;
 	unsigned int feature_secdiscard:1;
+	unsigned int feature_persistent:1;
 	unsigned int discard_granularity;
 	unsigned int discard_alignment;
-	unsigned int feature_persistent:1;
 	/* Number of 4KB segments handled */
 	unsigned int max_indirect_segments;
 	int is_ready;
@@ -865,7 +865,7 @@ static inline void flush_requests(struct blkfront_ring_info *rinfo)
 static inline bool blkif_request_flush_invalid(struct request *req,
 					       struct blkfront_info *info)
 {
-	return ((req->cmd_type != REQ_TYPE_FS) ||
+	return (blk_rq_is_passthrough(req) ||
 		((req_op(req) == REQ_OP_FLUSH) &&
 		 !info->feature_flush) ||
 		((req->cmd_flags & REQ_FUA) &&
@@ -2223,7 +2223,7 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo)
 	}
 	else
 		grants = info->max_indirect_segments;
-	psegs = grants / GRANTS_PER_PSEG;
+	psegs = DIV_ROUND_UP(grants, GRANTS_PER_PSEG);
 
 	err = fill_grant_buffer(rinfo,
 				(grants + INDIRECT_GREFS(grants)) * BLK_RING_SIZE(info));
@@ -2323,13 +2323,16 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
 		blkfront_setup_discard(info);
 
 	info->feature_persistent =
-		xenbus_read_unsigned(info->xbdev->otherend,
-				     "feature-persistent", 0);
+		!!xenbus_read_unsigned(info->xbdev->otherend,
+				       "feature-persistent", 0);
 
 	indirect_segments = xenbus_read_unsigned(info->xbdev->otherend,
 					"feature-max-indirect-segments", 0);
-	info->max_indirect_segments = min(indirect_segments,
-					  xen_blkif_max_segments);
+	if (indirect_segments > xen_blkif_max_segments)
+		indirect_segments = xen_blkif_max_segments;
+	if (indirect_segments <= BLKIF_MAX_SEGMENTS_PER_REQUEST)
+		indirect_segments = 0;
+	info->max_indirect_segments = indirect_segments;
 }
 
 /*
@@ -2652,6 +2655,9 @@ static int __init xlblk_init(void)
 	if (!xen_domain())
 		return -ENODEV;
 
+	if (xen_blkif_max_segments < BLKIF_MAX_SEGMENTS_PER_REQUEST)
+		xen_blkif_max_segments = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+
 	if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) {
 		pr_info("Invalid max_ring_order (%d), will use default max: %d.\n",
 			xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER);
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index c4328d9d9981..757dce2147e0 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -468,7 +468,7 @@ static struct request *ace_get_next_request(struct request_queue *q)
 	struct request *req;
 
 	while ((req = blk_peek_request(q)) != NULL) {
-		if (req->cmd_type == REQ_TYPE_FS)
+		if (!blk_rq_is_passthrough(req))
 			break;
 		blk_start_request(req);
 		__blk_end_request_all(req, -EIO);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e5ab7d9e8c45..3cd7856156b4 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -117,7 +117,7 @@ static void zram_revalidate_disk(struct zram *zram)
 {
 	revalidate_disk(zram->disk);
 	/* revalidate_disk reset the BDI_CAP_STABLE_WRITES so set again */
-	zram->disk->queue->backing_dev_info.capabilities |=
+	zram->disk->queue->backing_dev_info->capabilities |=
 		BDI_CAP_STABLE_WRITES;
 }
 
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 59cca72647a6..87739649eac2 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -281,8 +281,8 @@
 #include <linux/fcntl.h>
 #include <linux/blkdev.h>
 #include <linux/times.h>
-
 #include <linux/uaccess.h>
+#include <scsi/scsi_request.h>
 
 /* used to tell the module to turn on full debugging messages */
 static bool debug;
@@ -342,8 +342,8 @@ static void cdrom_sysctl_register(void);
 
 static LIST_HEAD(cdrom_list);
 
-static int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi,
-				      struct packet_command *cgc)
+int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi,
+			       struct packet_command *cgc)
 {
 	if (cgc->sense) {
 		cgc->sense->sense_key = 0x05;
@@ -354,6 +354,7 @@ static int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi,
 	cgc->stat = -EIO;
 	return -EIO;
 }
+EXPORT_SYMBOL(cdrom_dummy_generic_packet);
 
 static int cdrom_flush_cache(struct cdrom_device_info *cdi)
 {
@@ -371,7 +372,7 @@ static int cdrom_flush_cache(struct cdrom_device_info *cdi)
 static int cdrom_get_disc_info(struct cdrom_device_info *cdi,
 			       disc_information *di)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	struct packet_command cgc;
 	int ret, buflen;
 
@@ -586,7 +587,7 @@ static int cdrom_mrw_set_lba_space(struct cdrom_device_info *cdi, int space)
 int register_cdrom(struct cdrom_device_info *cdi)
 {
 	static char banner_printed;
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	int *change_capability = (int *)&cdo->capability; /* hack */
 
 	cd_dbg(CD_OPEN, "entering register_cdrom\n");
@@ -610,7 +611,6 @@ int register_cdrom(struct cdrom_device_info *cdi)
 	ENSURE(reset, CDC_RESET);
 	ENSURE(generic_packet, CDC_GENERIC_PACKET);
 	cdi->mc_flags = 0;
-	cdo->n_minors = 0;
 	cdi->options = CDO_USE_FFLAGS;
 
 	if (autoclose == 1 && CDROM_CAN(CDC_CLOSE_TRAY))
@@ -630,8 +630,7 @@ int register_cdrom(struct cdrom_device_info *cdi)
 	else
 		cdi->cdda_method = CDDA_OLD;
 
-	if (!cdo->generic_packet)
-		cdo->generic_packet = cdrom_dummy_generic_packet;
+	WARN_ON(!cdo->generic_packet);
 
 	cd_dbg(CD_REG_UNREG, "drive \"/dev/%s\" registered\n", cdi->name);
 	mutex_lock(&cdrom_mutex);
@@ -652,7 +651,6 @@ void unregister_cdrom(struct cdrom_device_info *cdi)
 	if (cdi->exit)
 		cdi->exit(cdi);
 
-	cdi->ops->n_minors--;
 	cd_dbg(CD_REG_UNREG, "drive \"/dev/%s\" unregistered\n", cdi->name);
 }
 
@@ -1036,7 +1034,7 @@ static
 int open_for_data(struct cdrom_device_info *cdi)
 {
 	int ret;
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	tracktype tracks;
 	cd_dbg(CD_OPEN, "entering open_for_data\n");
 	/* Check if the driver can report drive status.  If it can, we
@@ -1198,8 +1196,8 @@ err:
 /* This code is similar to that in open_for_data. The routine is called
    whenever an audio play operation is requested.
 */
-static int check_for_audio_disc(struct cdrom_device_info * cdi,
-				struct cdrom_device_ops * cdo)
+static int check_for_audio_disc(struct cdrom_device_info *cdi,
+				const struct cdrom_device_ops *cdo)
 {
         int ret;
 	tracktype tracks;
@@ -1254,7 +1252,7 @@ static int check_for_audio_disc(struct cdrom_device_info * cdi,
 
 void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	int opened_for_data;
 
 	cd_dbg(CD_CLOSE, "entering cdrom_release\n");
@@ -1294,7 +1292,7 @@ static int cdrom_read_mech_status(struct cdrom_device_info *cdi,
 				  struct cdrom_changer_info *buf)
 {
 	struct packet_command cgc;
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	int length;
 
 	/*
@@ -1643,7 +1641,7 @@ static int dvd_do_auth(struct cdrom_device_info *cdi, dvd_authinfo *ai)
 	int ret;
 	u_char buf[20];
 	struct packet_command cgc;
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	rpc_state_t rpc_state;
 
 	memset(buf, 0, sizeof(buf));
@@ -1791,7 +1789,7 @@ static int dvd_read_physical(struct cdrom_device_info *cdi, dvd_struct *s,
 {
 	unsigned char buf[21], *base;
 	struct dvd_layer *layer;
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	int ret, layer_num = s->physical.layer_num;
 
 	if (layer_num >= DVD_LAYERS)
@@ -1842,7 +1840,7 @@ static int dvd_read_copyright(struct cdrom_device_info *cdi, dvd_struct *s,
 {
 	int ret;
 	u_char buf[8];
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 
 	init_cdrom_command(cgc, buf, sizeof(buf), CGC_DATA_READ);
 	cgc->cmd[0] = GPCMD_READ_DVD_STRUCTURE;
@@ -1866,7 +1864,7 @@ static int dvd_read_disckey(struct cdrom_device_info *cdi, dvd_struct *s,
 {
 	int ret, size;
 	u_char *buf;
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 
 	size = sizeof(s->disckey.value) + 4;
 
@@ -1894,7 +1892,7 @@ static int dvd_read_bca(struct cdrom_device_info *cdi, dvd_struct *s,
 {
 	int ret, size = 4 + 188;
 	u_char *buf;
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 
 	buf = kmalloc(size, GFP_KERNEL);
 	if (!buf)
@@ -1928,7 +1926,7 @@ static int dvd_read_manufact(struct cdrom_device_info *cdi, dvd_struct *s,
 {
 	int ret = 0, size;
 	u_char *buf;
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 
 	size = sizeof(s->manufact.value) + 4;
 
@@ -1995,7 +1993,7 @@ int cdrom_mode_sense(struct cdrom_device_info *cdi,
 		     struct packet_command *cgc,
 		     int page_code, int page_control)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 
 	memset(cgc->cmd, 0, sizeof(cgc->cmd));
 
@@ -2010,7 +2008,7 @@ int cdrom_mode_sense(struct cdrom_device_info *cdi,
 int cdrom_mode_select(struct cdrom_device_info *cdi,
 		      struct packet_command *cgc)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 
 	memset(cgc->cmd, 0, sizeof(cgc->cmd));
 	memset(cgc->buffer, 0, 2);
@@ -2025,7 +2023,7 @@ int cdrom_mode_select(struct cdrom_device_info *cdi,
 static int cdrom_read_subchannel(struct cdrom_device_info *cdi,
 				 struct cdrom_subchnl *subchnl, int mcn)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	struct packet_command cgc;
 	char buffer[32];
 	int ret;
@@ -2073,7 +2071,7 @@ static int cdrom_read_cd(struct cdrom_device_info *cdi,
 			 struct packet_command *cgc, int lba,
 			 int blocksize, int nblocks)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 
 	memset(&cgc->cmd, 0, sizeof(cgc->cmd));
 	cgc->cmd[0] = GPCMD_READ_10;
@@ -2093,7 +2091,7 @@ static int cdrom_read_block(struct cdrom_device_info *cdi,
 			    struct packet_command *cgc,
 			    int lba, int nblocks, int format, int blksize)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 
 	memset(&cgc->cmd, 0, sizeof(cgc->cmd));
 	cgc->cmd[0] = GPCMD_READ_CD;
@@ -2172,6 +2170,7 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 {
 	struct request_queue *q = cdi->disk->queue;
 	struct request *rq;
+	struct scsi_request *req;
 	struct bio *bio;
 	unsigned int len;
 	int nr, ret = 0;
@@ -2190,12 +2189,13 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 
 		len = nr * CD_FRAMESIZE_RAW;
 
-		rq = blk_get_request(q, READ, GFP_KERNEL);
+		rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
 		if (IS_ERR(rq)) {
 			ret = PTR_ERR(rq);
 			break;
 		}
-		blk_rq_set_block_pc(rq);
+		req = scsi_req(rq);
+		scsi_req_init(rq);
 
 		ret = blk_rq_map_user(q, rq, NULL, ubuf, len, GFP_KERNEL);
 		if (ret) {
@@ -2203,23 +2203,23 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 			break;
 		}
 
-		rq->cmd[0] = GPCMD_READ_CD;
-		rq->cmd[1] = 1 << 2;
-		rq->cmd[2] = (lba >> 24) & 0xff;
-		rq->cmd[3] = (lba >> 16) & 0xff;
-		rq->cmd[4] = (lba >>  8) & 0xff;
-		rq->cmd[5] = lba & 0xff;
-		rq->cmd[6] = (nr >> 16) & 0xff;
-		rq->cmd[7] = (nr >>  8) & 0xff;
-		rq->cmd[8] = nr & 0xff;
-		rq->cmd[9] = 0xf8;
-
-		rq->cmd_len = 12;
+		req->cmd[0] = GPCMD_READ_CD;
+		req->cmd[1] = 1 << 2;
+		req->cmd[2] = (lba >> 24) & 0xff;
+		req->cmd[3] = (lba >> 16) & 0xff;
+		req->cmd[4] = (lba >>  8) & 0xff;
+		req->cmd[5] = lba & 0xff;
+		req->cmd[6] = (nr >> 16) & 0xff;
+		req->cmd[7] = (nr >>  8) & 0xff;
+		req->cmd[8] = nr & 0xff;
+		req->cmd[9] = 0xf8;
+
+		req->cmd_len = 12;
 		rq->timeout = 60 * HZ;
 		bio = rq->bio;
 
 		if (blk_execute_rq(q, cdi->disk, rq, 0)) {
-			struct request_sense *s = rq->sense;
+			struct request_sense *s = req->sense;
 			ret = -EIO;
 			cdi->last_sense = s->sense_key;
 		}
@@ -2764,7 +2764,7 @@ static int cdrom_ioctl_audioctl(struct cdrom_device_info *cdi,
  */
 static int cdrom_switch_blocksize(struct cdrom_device_info *cdi, int size)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	struct packet_command cgc;
 	struct modesel_head mh;
 
@@ -2790,7 +2790,7 @@ static int cdrom_switch_blocksize(struct cdrom_device_info *cdi, int size)
 static int cdrom_get_track_info(struct cdrom_device_info *cdi,
 				__u16 track, __u8 type, track_information *ti)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	struct packet_command cgc;
 	int ret, buflen;
 
@@ -3049,7 +3049,7 @@ static noinline int mmc_ioctl_cdrom_play_msf(struct cdrom_device_info *cdi,
 					     void __user *arg,
 					     struct packet_command *cgc)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	struct cdrom_msf msf;
 	cd_dbg(CD_DO_IOCTL, "entering CDROMPLAYMSF\n");
 	if (copy_from_user(&msf, (struct cdrom_msf __user *)arg, sizeof(msf)))
@@ -3069,7 +3069,7 @@ static noinline int mmc_ioctl_cdrom_play_blk(struct cdrom_device_info *cdi,
 					     void __user *arg,
 					     struct packet_command *cgc)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	struct cdrom_blk blk;
 	cd_dbg(CD_DO_IOCTL, "entering CDROMPLAYBLK\n");
 	if (copy_from_user(&blk, (struct cdrom_blk __user *)arg, sizeof(blk)))
@@ -3164,7 +3164,7 @@ static noinline int mmc_ioctl_cdrom_start_stop(struct cdrom_device_info *cdi,
 					       struct packet_command *cgc,
 					       int cmd)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	cd_dbg(CD_DO_IOCTL, "entering CDROMSTART/CDROMSTOP\n");
 	cgc->cmd[0] = GPCMD_START_STOP_UNIT;
 	cgc->cmd[1] = 1;
@@ -3177,7 +3177,7 @@ static noinline int mmc_ioctl_cdrom_pause_resume(struct cdrom_device_info *cdi,
 						 struct packet_command *cgc,
 						 int cmd)
 {
-	struct cdrom_device_ops *cdo = cdi->ops;
+	const struct cdrom_device_ops *cdo = cdi->ops;
 	cd_dbg(CD_DO_IOCTL, "entering CDROMPAUSE/CDROMRESUME\n");
 	cgc->cmd[0] = GPCMD_PAUSE_RESUME;
 	cgc->cmd[8] = (cmd == CDROMRESUME) ? 1 : 0;
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index 584bc3126403..1372763a948f 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -481,7 +481,7 @@ static int gdrom_audio_ioctl(struct cdrom_device_info *cdi, unsigned int cmd,
 	return -EINVAL;
 }
 
-static struct cdrom_device_ops gdrom_ops = {
+static const struct cdrom_device_ops gdrom_ops = {
 	.open			= gdrom_open,
 	.release		= gdrom_release,
 	.drive_status		= gdrom_drivestatus,
@@ -489,9 +489,9 @@ static struct cdrom_device_ops gdrom_ops = {
 	.get_last_session	= gdrom_get_last_session,
 	.reset			= gdrom_hardreset,
 	.audio_ioctl		= gdrom_audio_ioctl,
+	.generic_packet		= cdrom_dummy_generic_packet,
 	.capability		= CDC_MULTI_SESSION | CDC_MEDIA_CHANGED |
 				  CDC_RESET | CDC_DRIVE_STATUS | CDC_CD_R,
-	.n_minors		= 1,
 };
 
 static int gdrom_bdops_open(struct block_device *bdev, fmode_t mode)
@@ -659,23 +659,24 @@ static void gdrom_request(struct request_queue *rq)
 	struct request *req;
 
 	while ((req = blk_fetch_request(rq)) != NULL) {
-		if (req->cmd_type != REQ_TYPE_FS) {
-			printk(KERN_DEBUG "gdrom: Non-fs request ignored\n");
-			__blk_end_request_all(req, -EIO);
-			continue;
-		}
-		if (rq_data_dir(req) != READ) {
+		switch (req_op(req)) {
+		case REQ_OP_READ:
+			/*
+			 * Add to list of deferred work and then schedule
+			 * workqueue.
+			 */
+			list_add_tail(&req->queuelist, &gdrom_deferred);
+			schedule_work(&work);
+			break;
+		case REQ_OP_WRITE:
 			pr_notice("Read only device - write request ignored\n");
 			__blk_end_request_all(req, -EIO);
-			continue;
+			break;
+		default:
+			printk(KERN_DEBUG "gdrom: Non-fs request ignored\n");
+			__blk_end_request_all(req, -EIO);
+			break;
 		}
-
-		/*
-		 * Add to list of deferred work and then schedule
-		 * workqueue.
-		 */
-		list_add_tail(&req->queuelist, &gdrom_deferred);
-		schedule_work(&work);
 	}
 }
 
@@ -807,16 +808,20 @@ static int probe_gdrom(struct platform_device *devptr)
 	if (err)
 		goto probe_fail_cmdirq_register;
 	gd.gdrom_rq = blk_init_queue(gdrom_request, &gdrom_lock);
-	if (!gd.gdrom_rq)
+	if (!gd.gdrom_rq) {
+		err = -ENOMEM;
 		goto probe_fail_requestq;
+	}
 
 	err = probe_gdrom_setupqueue();
 	if (err)
 		goto probe_fail_toc;
 
 	gd.toc = kzalloc(sizeof(struct gdromtoc), GFP_KERNEL);
-	if (!gd.toc)
+	if (!gd.toc) {
+		err = -ENOMEM;
 		goto probe_fail_toc;
+	}
 	add_disk(gd.disk);
 	return 0;
 
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index 6ce5ce8be2f2..87fba424817e 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -92,7 +92,6 @@ static void add_early_randomness(struct hwrng *rng)
 	mutex_unlock(&reading_mutex);
 	if (bytes_read > 0)
 		add_device_randomness(rng_buffer, bytes_read);
-	memset(rng_buffer, 0, size);
 }
 
 static inline void cleanup_rng(struct kref *kref)
@@ -288,7 +287,6 @@ static ssize_t rng_dev_read(struct file *filp, char __user *buf,
 		}
 	}
 out:
-	memset(rng_buffer, 0, rng_buffer_size());
 	return ret ? : err;
 
 out_unlock_reading:
@@ -427,7 +425,6 @@ static int hwrng_fillfn(void *unused)
 		/* Outside lock, sure, but y'know: randomness. */
 		add_hwgenerator_randomness((void *)rng_fillbuf, rc,
 					   rc * current_quality * 8 >> 10);
-		memset(rng_fillbuf, 0, rng_buffer_size());
 	}
 	hwrng_fill = NULL;
 	return 0;
diff --git a/drivers/clk/tegra/clk-dfll.c b/drivers/clk/tegra/clk-dfll.c
index f010562534eb..2c44aeb0b97c 100644
--- a/drivers/clk/tegra/clk-dfll.c
+++ b/drivers/clk/tegra/clk-dfll.c
@@ -633,16 +633,12 @@ static int find_lut_index_for_rate(struct tegra_dfll *td, unsigned long rate)
 	struct dev_pm_opp *opp;
 	int i, uv;
 
-	rcu_read_lock();
-
 	opp = dev_pm_opp_find_freq_ceil(td->soc->dev, &rate);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp))
 		return PTR_ERR(opp);
-	}
-	uv = dev_pm_opp_get_voltage(opp);
 
-	rcu_read_unlock();
+	uv = dev_pm_opp_get_voltage(opp);
+	dev_pm_opp_put(opp);
 
 	for (i = 0; i < td->i2c_lut_size; i++) {
 		if (regulator_list_voltage(td->vdd_reg, td->i2c_lut[i]) == uv)
@@ -1440,8 +1436,6 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 	struct dev_pm_opp *opp;
 	int lut;
 
-	rcu_read_lock();
-
 	rate = ULONG_MAX;
 	opp = dev_pm_opp_find_freq_floor(td->soc->dev, &rate);
 	if (IS_ERR(opp)) {
@@ -1449,6 +1443,7 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 		goto out;
 	}
 	v_max = dev_pm_opp_get_voltage(opp);
+	dev_pm_opp_put(opp);
 
 	v = td->soc->cvb->min_millivolts * 1000;
 	lut = find_vdd_map_entry_exact(td, v);
@@ -1465,6 +1460,8 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 		if (v_opp <= td->soc->cvb->min_millivolts * 1000)
 			td->dvco_rate_min = dev_pm_opp_get_freq(opp);
 
+		dev_pm_opp_put(opp);
+
 		for (;;) {
 			v += max(1, (v_max - v) / (MAX_DFLL_VOLTAGES - j));
 			if (v >= v_opp)
@@ -1496,8 +1493,6 @@ static int dfll_build_i2c_lut(struct tegra_dfll *td)
 		ret = 0;
 
 out:
-	rcu_read_unlock();
-
 	return ret;
 }
 
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 4866f7aa32e6..3356ab821624 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -5,6 +5,10 @@ config CLKSRC_OF
 	bool
 	select CLKSRC_PROBE
 
+config CLKEVT_OF
+	bool
+	select CLKEVT_PROBE
+
 config CLKSRC_ACPI
 	bool
 	select CLKSRC_PROBE
@@ -12,6 +16,9 @@ config CLKSRC_ACPI
 config CLKSRC_PROBE
 	bool
 
+config CLKEVT_PROBE
+	bool
+
 config CLKSRC_I8253
 	bool
 
@@ -60,6 +67,16 @@ config DW_APB_TIMER_OF
 	select DW_APB_TIMER
 	select CLKSRC_OF
 
+config GEMINI_TIMER
+	bool "Cortina Gemini timer driver" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
+	depends on HAS_IOMEM
+	select CLKSRC_MMIO
+	select CLKSRC_OF
+	select MFD_SYSCON
+	help
+	  Enables support for the Gemini timer
+
 config ROCKCHIP_TIMER
 	bool "Rockchip timer driver" if COMPILE_TEST
 	depends on ARM || ARM64
@@ -325,16 +342,30 @@ config ARM_ARCH_TIMER_EVTSTREAM
 	  This must be disabled for hardware validation purposes to detect any
 	  hardware anomalies of missing events.
 
+config ARM_ARCH_TIMER_OOL_WORKAROUND
+	bool
+
 config FSL_ERRATUM_A008585
 	bool "Workaround for Freescale/NXP Erratum A-008585"
 	default y
 	depends on ARM_ARCH_TIMER && ARM64
+	select ARM_ARCH_TIMER_OOL_WORKAROUND
 	help
 	  This option enables a workaround for Freescale/NXP Erratum
 	  A-008585 ("ARM generic timer may contain an erroneous
 	  value").  The workaround will only be active if the
 	  fsl,erratum-a008585 property is found in the timer node.
 
+config HISILICON_ERRATUM_161010101
+	bool "Workaround for Hisilicon Erratum 161010101"
+	default y
+	select ARM_ARCH_TIMER_OOL_WORKAROUND
+	depends on ARM_ARCH_TIMER && ARM64
+	help
+	  This option enables a workaround for Hisilicon Erratum
+	  161010101. The workaround will be active if the hisilicon,erratum-161010101
+	  property is found in the timer node.
+
 config ARM_GLOBAL_TIMER
 	bool "Support for the ARM global timer" if COMPILE_TEST
 	select CLKSRC_OF if OF
@@ -467,6 +498,13 @@ config SH_TIMER_MTU2
 	  Timer Pulse Unit 2 (MTU2) hardware available on SoCs from Renesas.
 	  This hardware comes with 16 bit-timer registers.
 
+config RENESAS_OSTM
+	bool "Renesas OSTM timer driver" if COMPILE_TEST
+	depends on GENERIC_CLOCKEVENTS
+	select CLKSRC_MMIO
+	help
+	  Enables the support for the Renesas OSTM.
+
 config SH_TIMER_TMU
 	bool "Renesas TMU timer driver" if COMPILE_TEST
 	depends on GENERIC_CLOCKEVENTS
diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index a14111e1f087..d227d1314f14 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -1,4 +1,5 @@
 obj-$(CONFIG_CLKSRC_PROBE)	+= clksrc-probe.o
+obj-$(CONFIG_CLKEVT_PROBE)	+= clkevt-probe.o
 obj-$(CONFIG_ATMEL_PIT)		+= timer-atmel-pit.o
 obj-$(CONFIG_ATMEL_ST)		+= timer-atmel-st.o
 obj-$(CONFIG_ATMEL_TCB_CLKSRC)	+= tcb_clksrc.o
@@ -8,6 +9,7 @@ obj-$(CONFIG_CS5535_CLOCK_EVENT_SRC)	+= cs5535-clockevt.o
 obj-$(CONFIG_CLKSRC_JCORE_PIT)		+= jcore-pit.o
 obj-$(CONFIG_SH_TIMER_CMT)	+= sh_cmt.o
 obj-$(CONFIG_SH_TIMER_MTU2)	+= sh_mtu2.o
+obj-$(CONFIG_RENESAS_OSTM)	+= renesas-ostm.o
 obj-$(CONFIG_SH_TIMER_TMU)	+= sh_tmu.o
 obj-$(CONFIG_EM_TIMER_STI)	+= em_sti.o
 obj-$(CONFIG_CLKBLD_I8253)	+= i8253.o
@@ -15,6 +17,7 @@ obj-$(CONFIG_CLKSRC_MMIO)	+= mmio.o
 obj-$(CONFIG_DIGICOLOR_TIMER)	+= timer-digicolor.o
 obj-$(CONFIG_DW_APB_TIMER)	+= dw_apb_timer.o
 obj-$(CONFIG_DW_APB_TIMER_OF)	+= dw_apb_timer_of.o
+obj-$(CONFIG_GEMINI_TIMER)	+= timer-gemini.o
 obj-$(CONFIG_ROCKCHIP_TIMER)      += rockchip_timer.o
 obj-$(CONFIG_CLKSRC_NOMADIK_MTU)	+= nomadik-mtu.o
 obj-$(CONFIG_CLKSRC_DBX500_PRCMU)	+= clksrc-dbx500-prcmu.o
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 4c8c3fb2e8b2..93aa1364376a 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -96,41 +96,107 @@ early_param("clocksource.arm_arch_timer.evtstrm", early_evtstrm_cfg);
  */
 
 #ifdef CONFIG_FSL_ERRATUM_A008585
-DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
-EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
-
-static int fsl_a008585_enable = -1;
-
-static int __init early_fsl_a008585_cfg(char *buf)
+/*
+ * The number of retries is an arbitrary value well beyond the highest number
+ * of iterations the loop has been observed to take.
+ */
+#define __fsl_a008585_read_reg(reg) ({			\
+	u64 _old, _new;					\
+	int _retries = 200;				\
+							\
+	do {						\
+		_old = read_sysreg(reg);		\
+		_new = read_sysreg(reg);		\
+		_retries--;				\
+	} while (unlikely(_old != _new) && _retries);	\
+							\
+	WARN_ON_ONCE(!_retries);			\
+	_new;						\
+})
+
+static u32 notrace fsl_a008585_read_cntp_tval_el0(void)
 {
-	int ret;
-	bool val;
+	return __fsl_a008585_read_reg(cntp_tval_el0);
+}
 
-	ret = strtobool(buf, &val);
-	if (ret)
-		return ret;
+static u32 notrace fsl_a008585_read_cntv_tval_el0(void)
+{
+	return __fsl_a008585_read_reg(cntv_tval_el0);
+}
 
-	fsl_a008585_enable = val;
-	return 0;
+static u64 notrace fsl_a008585_read_cntvct_el0(void)
+{
+	return __fsl_a008585_read_reg(cntvct_el0);
 }
-early_param("clocksource.arm_arch_timer.fsl-a008585", early_fsl_a008585_cfg);
+#endif
 
-u32 __fsl_a008585_read_cntp_tval_el0(void)
+#ifdef CONFIG_HISILICON_ERRATUM_161010101
+/*
+ * Verify whether the value of the second read is larger than the first by
+ * less than 32 is the only way to confirm the value is correct, so clear the
+ * lower 5 bits to check whether the difference is greater than 32 or not.
+ * Theoretically the erratum should not occur more than twice in succession
+ * when reading the system counter, but it is possible that some interrupts
+ * may lead to more than twice read errors, triggering the warning, so setting
+ * the number of retries far beyond the number of iterations the loop has been
+ * observed to take.
+ */
+#define __hisi_161010101_read_reg(reg) ({				\
+	u64 _old, _new;						\
+	int _retries = 50;					\
+								\
+	do {							\
+		_old = read_sysreg(reg);			\
+		_new = read_sysreg(reg);			\
+		_retries--;					\
+	} while (unlikely((_new - _old) >> 5) && _retries);	\
+								\
+	WARN_ON_ONCE(!_retries);				\
+	_new;							\
+})
+
+static u32 notrace hisi_161010101_read_cntp_tval_el0(void)
 {
-	return __fsl_a008585_read_reg(cntp_tval_el0);
+	return __hisi_161010101_read_reg(cntp_tval_el0);
 }
 
-u32 __fsl_a008585_read_cntv_tval_el0(void)
+static u32 notrace hisi_161010101_read_cntv_tval_el0(void)
 {
-	return __fsl_a008585_read_reg(cntv_tval_el0);
+	return __hisi_161010101_read_reg(cntv_tval_el0);
 }
 
-u64 __fsl_a008585_read_cntvct_el0(void)
+static u64 notrace hisi_161010101_read_cntvct_el0(void)
 {
-	return __fsl_a008585_read_reg(cntvct_el0);
+	return __hisi_161010101_read_reg(cntvct_el0);
 }
-EXPORT_SYMBOL(__fsl_a008585_read_cntvct_el0);
-#endif /* CONFIG_FSL_ERRATUM_A008585 */
+#endif
+
+#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
+const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround = NULL;
+EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
+
+DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
+EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+
+static const struct arch_timer_erratum_workaround ool_workarounds[] = {
+#ifdef CONFIG_FSL_ERRATUM_A008585
+	{
+		.id = "fsl,erratum-a008585",
+		.read_cntp_tval_el0 = fsl_a008585_read_cntp_tval_el0,
+		.read_cntv_tval_el0 = fsl_a008585_read_cntv_tval_el0,
+		.read_cntvct_el0 = fsl_a008585_read_cntvct_el0,
+	},
+#endif
+#ifdef CONFIG_HISILICON_ERRATUM_161010101
+	{
+		.id = "hisilicon,erratum-161010101",
+		.read_cntp_tval_el0 = hisi_161010101_read_cntp_tval_el0,
+		.read_cntv_tval_el0 = hisi_161010101_read_cntv_tval_el0,
+		.read_cntvct_el0 = hisi_161010101_read_cntvct_el0,
+	},
+#endif
+};
+#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
 
 static __always_inline
 void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
@@ -281,8 +347,8 @@ static __always_inline void set_next_event(const int access, unsigned long evt,
 	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 }
 
-#ifdef CONFIG_FSL_ERRATUM_A008585
-static __always_inline void fsl_a008585_set_next_event(const int access,
+#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
+static __always_inline void erratum_set_next_event_generic(const int access,
 		unsigned long evt, struct clock_event_device *clk)
 {
 	unsigned long ctrl;
@@ -300,20 +366,20 @@ static __always_inline void fsl_a008585_set_next_event(const int access,
 	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 }
 
-static int fsl_a008585_set_next_event_virt(unsigned long evt,
+static int erratum_set_next_event_virt(unsigned long evt,
 					   struct clock_event_device *clk)
 {
-	fsl_a008585_set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
+	erratum_set_next_event_generic(ARCH_TIMER_VIRT_ACCESS, evt, clk);
 	return 0;
 }
 
-static int fsl_a008585_set_next_event_phys(unsigned long evt,
+static int erratum_set_next_event_phys(unsigned long evt,
 					   struct clock_event_device *clk)
 {
-	fsl_a008585_set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
+	erratum_set_next_event_generic(ARCH_TIMER_PHYS_ACCESS, evt, clk);
 	return 0;
 }
-#endif /* CONFIG_FSL_ERRATUM_A008585 */
+#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
 
 static int arch_timer_set_next_event_virt(unsigned long evt,
 					  struct clock_event_device *clk)
@@ -343,16 +409,16 @@ static int arch_timer_set_next_event_phys_mem(unsigned long evt,
 	return 0;
 }
 
-static void fsl_a008585_set_sne(struct clock_event_device *clk)
+static void erratum_workaround_set_sne(struct clock_event_device *clk)
 {
-#ifdef CONFIG_FSL_ERRATUM_A008585
+#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
 	if (!static_branch_unlikely(&arch_timer_read_ool_enabled))
 		return;
 
 	if (arch_timer_uses_ppi == VIRT_PPI)
-		clk->set_next_event = fsl_a008585_set_next_event_virt;
+		clk->set_next_event = erratum_set_next_event_virt;
 	else
-		clk->set_next_event = fsl_a008585_set_next_event_phys;
+		clk->set_next_event = erratum_set_next_event_phys;
 #endif
 }
 
@@ -385,7 +451,7 @@ static void __arch_timer_setup(unsigned type,
 			BUG();
 		}
 
-		fsl_a008585_set_sne(clk);
+		erratum_workaround_set_sne(clk);
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
@@ -580,7 +646,7 @@ static struct clocksource clocksource_counter = {
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static struct cyclecounter cyclecounter = {
+static struct cyclecounter cyclecounter __ro_after_init = {
 	.read	= arch_counter_read_cc,
 	.mask	= CLOCKSOURCE_MASK(56),
 };
@@ -605,7 +671,7 @@ static void __init arch_counter_register(unsigned type)
 
 		clocksource_counter.archdata.vdso_direct = true;
 
-#ifdef CONFIG_FSL_ERRATUM_A008585
+#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
 		/*
 		 * Don't use the vdso fastpath if errata require using
 		 * the out-of-line counter accessor.
@@ -893,12 +959,15 @@ static int __init arch_timer_of_init(struct device_node *np)
 
 	arch_timer_c3stop = !of_property_read_bool(np, "always-on");
 
-#ifdef CONFIG_FSL_ERRATUM_A008585
-	if (fsl_a008585_enable < 0)
-		fsl_a008585_enable = of_property_read_bool(np, "fsl,erratum-a008585");
-	if (fsl_a008585_enable) {
-		static_branch_enable(&arch_timer_read_ool_enabled);
-		pr_info("Enabling workaround for FSL erratum A-008585\n");
+#ifdef CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND
+	for (i = 0; i < ARRAY_SIZE(ool_workarounds); i++) {
+		if (of_property_read_bool(np, ool_workarounds[i].id)) {
+			timer_unstable_counter_workaround = &ool_workarounds[i];
+			static_branch_enable(&arch_timer_read_ool_enabled);
+			pr_info("arch_timer: Enabling workaround for %s\n",
+				timer_unstable_counter_workaround->id);
+			break;
+		}
 	}
 #endif
 
diff --git a/drivers/clocksource/clkevt-probe.c b/drivers/clocksource/clkevt-probe.c
new file mode 100644
index 000000000000..8c30fec86094
--- /dev/null
+++ b/drivers/clocksource/clkevt-probe.c
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2016, Linaro Ltd.  All rights reserved.
+ * Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/clockchip.h>
+
+extern struct of_device_id __clkevt_of_table[];
+
+static const struct of_device_id __clkevt_of_table_sentinel
+	__used __section(__clkevt_of_table_end);
+
+int __init clockevent_probe(void)
+{
+	struct device_node *np;
+	const struct of_device_id *match;
+	of_init_fn_1_ret init_func;
+	int ret, clockevents = 0;
+
+	for_each_matching_node_and_match(np, __clkevt_of_table, &match) {
+		if (!of_device_is_available(np))
+			continue;
+
+		init_func = match->data;
+
+		ret = init_func(np);
+		if (ret) {
+			pr_warn("Failed to initialize '%s' (%d)\n",
+				np->name, ret);
+			continue;
+		}
+
+		clockevents++;
+	}
+
+	if (!clockevents) {
+		pr_crit("%s: no matching clockevent found\n", __func__);
+		return -ENODEV;
+	}
+
+	return 0;
+}
diff --git a/drivers/clocksource/renesas-ostm.c b/drivers/clocksource/renesas-ostm.c
new file mode 100644
index 000000000000..c76f57668fb2
--- /dev/null
+++ b/drivers/clocksource/renesas-ostm.c
@@ -0,0 +1,265 @@
+/*
+ * Renesas Timer Support - OSTM
+ *
+ * Copyright (C) 2017 Renesas Electronics America, Inc.
+ * Copyright (C) 2017 Chris Brandt
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+
+/*
+ * The OSTM contains independent channels.
+ * The first OSTM channel probed will be set up as a free running
+ * clocksource. Additionally we will use this clocksource for the system
+ * schedule timer sched_clock().
+ *
+ * The second (or more) channel probed will be set up as an interrupt
+ * driven clock event.
+ */
+
+struct ostm_device {
+	void __iomem *base;
+	unsigned long ticks_per_jiffy;
+	struct clock_event_device ced;
+};
+
+static void __iomem *system_clock;	/* For sched_clock() */
+
+/* OSTM REGISTERS */
+#define	OSTM_CMP		0x000	/* RW,32 */
+#define	OSTM_CNT		0x004	/* R,32 */
+#define	OSTM_TE			0x010	/* R,8 */
+#define	OSTM_TS			0x014	/* W,8 */
+#define	OSTM_TT			0x018	/* W,8 */
+#define	OSTM_CTL		0x020	/* RW,8 */
+
+#define	TE			0x01
+#define	TS			0x01
+#define	TT			0x01
+#define	CTL_PERIODIC		0x00
+#define	CTL_ONESHOT		0x02
+#define	CTL_FREERUN		0x02
+
+static struct ostm_device *ced_to_ostm(struct clock_event_device *ced)
+{
+	return container_of(ced, struct ostm_device, ced);
+}
+
+static void ostm_timer_stop(struct ostm_device *ostm)
+{
+	if (readb(ostm->base + OSTM_TE) & TE) {
+		writeb(TT, ostm->base + OSTM_TT);
+
+		/*
+		 * Read back the register simply to confirm the write operation
+		 * has completed since I/O writes can sometimes get queued by
+		 * the bus architecture.
+		 */
+		while (readb(ostm->base + OSTM_TE) & TE)
+			;
+	}
+}
+
+static int __init ostm_init_clksrc(struct ostm_device *ostm, unsigned long rate)
+{
+	/*
+	 * irq not used (clock sources don't use interrupts)
+	 */
+
+	ostm_timer_stop(ostm);
+
+	writel(0, ostm->base + OSTM_CMP);
+	writeb(CTL_FREERUN, ostm->base + OSTM_CTL);
+	writeb(TS, ostm->base + OSTM_TS);
+
+	return clocksource_mmio_init(ostm->base + OSTM_CNT,
+			"ostm", rate,
+			300, 32, clocksource_mmio_readl_up);
+}
+
+static u64 notrace ostm_read_sched_clock(void)
+{
+	return readl(system_clock);
+}
+
+static void __init ostm_init_sched_clock(struct ostm_device *ostm,
+			unsigned long rate)
+{
+	system_clock = ostm->base + OSTM_CNT;
+	sched_clock_register(ostm_read_sched_clock, 32, rate);
+}
+
+static int ostm_clock_event_next(unsigned long delta,
+				     struct clock_event_device *ced)
+{
+	struct ostm_device *ostm = ced_to_ostm(ced);
+
+	ostm_timer_stop(ostm);
+
+	writel(delta, ostm->base + OSTM_CMP);
+	writeb(CTL_ONESHOT, ostm->base + OSTM_CTL);
+	writeb(TS, ostm->base + OSTM_TS);
+
+	return 0;
+}
+
+static int ostm_shutdown(struct clock_event_device *ced)
+{
+	struct ostm_device *ostm = ced_to_ostm(ced);
+
+	ostm_timer_stop(ostm);
+
+	return 0;
+}
+static int ostm_set_periodic(struct clock_event_device *ced)
+{
+	struct ostm_device *ostm = ced_to_ostm(ced);
+
+	if (clockevent_state_oneshot(ced) || clockevent_state_periodic(ced))
+		ostm_timer_stop(ostm);
+
+	writel(ostm->ticks_per_jiffy - 1, ostm->base + OSTM_CMP);
+	writeb(CTL_PERIODIC, ostm->base + OSTM_CTL);
+	writeb(TS, ostm->base + OSTM_TS);
+
+	return 0;
+}
+
+static int ostm_set_oneshot(struct clock_event_device *ced)
+{
+	struct ostm_device *ostm = ced_to_ostm(ced);
+
+	ostm_timer_stop(ostm);
+
+	return 0;
+}
+
+static irqreturn_t ostm_timer_interrupt(int irq, void *dev_id)
+{
+	struct ostm_device *ostm = dev_id;
+
+	if (clockevent_state_oneshot(&ostm->ced))
+		ostm_timer_stop(ostm);
+
+	/* notify clockevent layer */
+	if (ostm->ced.event_handler)
+		ostm->ced.event_handler(&ostm->ced);
+
+	return IRQ_HANDLED;
+}
+
+static int __init ostm_init_clkevt(struct ostm_device *ostm, int irq,
+			unsigned long rate)
+{
+	struct clock_event_device *ced = &ostm->ced;
+	int ret = -ENXIO;
+
+	ret = request_irq(irq, ostm_timer_interrupt,
+			  IRQF_TIMER | IRQF_IRQPOLL,
+			  "ostm", ostm);
+	if (ret) {
+		pr_err("ostm: failed to request irq\n");
+		return ret;
+	}
+
+	ced->name = "ostm";
+	ced->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC;
+	ced->set_state_shutdown = ostm_shutdown;
+	ced->set_state_periodic = ostm_set_periodic;
+	ced->set_state_oneshot = ostm_set_oneshot;
+	ced->set_next_event = ostm_clock_event_next;
+	ced->shift = 32;
+	ced->rating = 300;
+	ced->cpumask = cpumask_of(0);
+	clockevents_config_and_register(ced, rate, 0xf, 0xffffffff);
+
+	return 0;
+}
+
+static int __init ostm_init(struct device_node *np)
+{
+	struct ostm_device *ostm;
+	int ret = -EFAULT;
+	struct clk *ostm_clk = NULL;
+	int irq;
+	unsigned long rate;
+
+	ostm = kzalloc(sizeof(*ostm), GFP_KERNEL);
+	if (!ostm)
+		return -ENOMEM;
+
+	ostm->base = of_iomap(np, 0);
+	if (!ostm->base) {
+		pr_err("ostm: failed to remap I/O memory\n");
+		goto err;
+	}
+
+	irq = irq_of_parse_and_map(np, 0);
+	if (irq < 0) {
+		pr_err("ostm: Failed to get irq\n");
+		goto err;
+	}
+
+	ostm_clk = of_clk_get(np, 0);
+	if (IS_ERR(ostm_clk)) {
+		pr_err("ostm: Failed to get clock\n");
+		ostm_clk = NULL;
+		goto err;
+	}
+
+	ret = clk_prepare_enable(ostm_clk);
+	if (ret) {
+		pr_err("ostm: Failed to enable clock\n");
+		goto err;
+	}
+
+	rate = clk_get_rate(ostm_clk);
+	ostm->ticks_per_jiffy = (rate + HZ / 2) / HZ;
+
+	/*
+	 * First probed device will be used as system clocksource. Any
+	 * additional devices will be used as clock events.
+	 */
+	if (!system_clock) {
+		ret = ostm_init_clksrc(ostm, rate);
+
+		if (!ret) {
+			ostm_init_sched_clock(ostm, rate);
+			pr_info("ostm: used for clocksource\n");
+		}
+
+	} else {
+		ret = ostm_init_clkevt(ostm, irq, rate);
+
+		if (!ret)
+			pr_info("ostm: used for clock events\n");
+	}
+
+err:
+	if (ret) {
+		clk_disable_unprepare(ostm_clk);
+		iounmap(ostm->base);
+		kfree(ostm);
+		return ret;
+	}
+
+	return 0;
+}
+
+CLOCKSOURCE_OF_DECLARE(ostm, "renesas,ostm", ostm_init);
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index d4ca9962a759..745844ee973e 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -10,6 +10,7 @@
 #include <linux/io.h>
 #include <linux/platform_device.h>
 #include <linux/atmel_tc.h>
+#include <linux/sched_clock.h>
 
 
 /*
@@ -56,11 +57,16 @@ static u64 tc_get_cycles(struct clocksource *cs)
 	return (upper << 16) | lower;
 }
 
-static u64 tc_get_cycles32(struct clocksource *cs)
+static u32 tc_get_cv32(void)
 {
 	return __raw_readl(tcaddr + ATMEL_TC_REG(0, CV));
 }
 
+static u64 tc_get_cycles32(struct clocksource *cs)
+{
+	return tc_get_cv32();
+}
+
 static struct clocksource clksrc = {
 	.name           = "tcb_clksrc",
 	.rating         = 200,
@@ -69,6 +75,11 @@ static struct clocksource clksrc = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
+static u64 notrace tc_read_sched_clock(void)
+{
+	return tc_get_cv32();
+}
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
 struct tc_clkevt_device {
@@ -339,6 +350,9 @@ static int __init tcb_clksrc_init(void)
 		clksrc.read = tc_get_cycles32;
 		/* setup ony channel 0 */
 		tcb_setup_single_chan(tc, best_divisor_idx);
+
+		/* register sched_clock on chips with single 32 bit counter */
+		sched_clock_register(tc_read_sched_clock, 32, divided_rate);
 	} else {
 		/* tclib will give us three clocks no matter what the
 		 * underlying platform supports.
diff --git a/drivers/clocksource/timer-gemini.c b/drivers/clocksource/timer-gemini.c
new file mode 100644
index 000000000000..dda27b7bf1a1
--- /dev/null
+++ b/drivers/clocksource/timer-gemini.c
@@ -0,0 +1,277 @@
+/*
+ * Gemini timer driver
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * Based on a rewrite of arch/arm/mach-gemini/timer.c:
+ * Copyright (C) 2001-2006 Storlink, Corp.
+ * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
+ */
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/sched_clock.h>
+
+/*
+ * Relevant registers in the global syscon
+ */
+#define GLOBAL_STATUS		0x04
+#define CPU_AHB_RATIO_MASK	(0x3 << 18)
+#define CPU_AHB_1_1		(0x0 << 18)
+#define CPU_AHB_3_2		(0x1 << 18)
+#define CPU_AHB_24_13		(0x2 << 18)
+#define CPU_AHB_2_1		(0x3 << 18)
+#define REG_TO_AHB_SPEED(reg)	((((reg) >> 15) & 0x7) * 10 + 130)
+
+/*
+ * Register definitions for the timers
+ */
+#define TIMER1_COUNT		(0x00)
+#define TIMER1_LOAD		(0x04)
+#define TIMER1_MATCH1		(0x08)
+#define TIMER1_MATCH2		(0x0c)
+#define TIMER2_COUNT		(0x10)
+#define TIMER2_LOAD		(0x14)
+#define TIMER2_MATCH1		(0x18)
+#define TIMER2_MATCH2		(0x1c)
+#define TIMER3_COUNT		(0x20)
+#define TIMER3_LOAD		(0x24)
+#define TIMER3_MATCH1		(0x28)
+#define TIMER3_MATCH2		(0x2c)
+#define TIMER_CR		(0x30)
+#define TIMER_INTR_STATE	(0x34)
+#define TIMER_INTR_MASK		(0x38)
+
+#define TIMER_1_CR_ENABLE	(1 << 0)
+#define TIMER_1_CR_CLOCK	(1 << 1)
+#define TIMER_1_CR_INT		(1 << 2)
+#define TIMER_2_CR_ENABLE	(1 << 3)
+#define TIMER_2_CR_CLOCK	(1 << 4)
+#define TIMER_2_CR_INT		(1 << 5)
+#define TIMER_3_CR_ENABLE	(1 << 6)
+#define TIMER_3_CR_CLOCK	(1 << 7)
+#define TIMER_3_CR_INT		(1 << 8)
+#define TIMER_1_CR_UPDOWN	(1 << 9)
+#define TIMER_2_CR_UPDOWN	(1 << 10)
+#define TIMER_3_CR_UPDOWN	(1 << 11)
+#define TIMER_DEFAULT_FLAGS	(TIMER_1_CR_UPDOWN | \
+				 TIMER_3_CR_ENABLE | \
+				 TIMER_3_CR_UPDOWN)
+
+#define TIMER_1_INT_MATCH1	(1 << 0)
+#define TIMER_1_INT_MATCH2	(1 << 1)
+#define TIMER_1_INT_OVERFLOW	(1 << 2)
+#define TIMER_2_INT_MATCH1	(1 << 3)
+#define TIMER_2_INT_MATCH2	(1 << 4)
+#define TIMER_2_INT_OVERFLOW	(1 << 5)
+#define TIMER_3_INT_MATCH1	(1 << 6)
+#define TIMER_3_INT_MATCH2	(1 << 7)
+#define TIMER_3_INT_OVERFLOW	(1 << 8)
+#define TIMER_INT_ALL_MASK	0x1ff
+
+static unsigned int tick_rate;
+static void __iomem *base;
+
+static u64 notrace gemini_read_sched_clock(void)
+{
+	return readl(base + TIMER3_COUNT);
+}
+
+static int gemini_timer_set_next_event(unsigned long cycles,
+				       struct clock_event_device *evt)
+{
+	u32 cr;
+
+	/* Setup the match register */
+	cr = readl(base + TIMER1_COUNT);
+	writel(cr + cycles, base + TIMER1_MATCH1);
+	if (readl(base + TIMER1_COUNT) - cr > cycles)
+		return -ETIME;
+
+	return 0;
+}
+
+static int gemini_timer_shutdown(struct clock_event_device *evt)
+{
+	u32 cr;
+
+	/*
+	 * Disable also for oneshot: the set_next() call will arm the timer
+	 * instead.
+	 */
+	/* Stop timer and interrupt. */
+	cr = readl(base + TIMER_CR);
+	cr &= ~(TIMER_1_CR_ENABLE | TIMER_1_CR_INT);
+	writel(cr, base + TIMER_CR);
+
+	/* Setup counter start from 0 */
+	writel(0, base + TIMER1_COUNT);
+	writel(0, base + TIMER1_LOAD);
+
+	/* enable interrupt */
+	cr = readl(base + TIMER_INTR_MASK);
+	cr &= ~(TIMER_1_INT_OVERFLOW | TIMER_1_INT_MATCH2);
+	cr |= TIMER_1_INT_MATCH1;
+	writel(cr, base + TIMER_INTR_MASK);
+
+	/* start the timer */
+	cr = readl(base + TIMER_CR);
+	cr |= TIMER_1_CR_ENABLE;
+	writel(cr, base + TIMER_CR);
+
+	return 0;
+}
+
+static int gemini_timer_set_periodic(struct clock_event_device *evt)
+{
+	u32 period = DIV_ROUND_CLOSEST(tick_rate, HZ);
+	u32 cr;
+
+	/* Stop timer and interrupt */
+	cr = readl(base + TIMER_CR);
+	cr &= ~(TIMER_1_CR_ENABLE | TIMER_1_CR_INT);
+	writel(cr, base + TIMER_CR);
+
+	/* Setup timer to fire at 1/HT intervals. */
+	cr = 0xffffffff - (period - 1);
+	writel(cr, base + TIMER1_COUNT);
+	writel(cr, base + TIMER1_LOAD);
+
+	/* enable interrupt on overflow */
+	cr = readl(base + TIMER_INTR_MASK);
+	cr &= ~(TIMER_1_INT_MATCH1 | TIMER_1_INT_MATCH2);
+	cr |= TIMER_1_INT_OVERFLOW;
+	writel(cr, base + TIMER_INTR_MASK);
+
+	/* Start the timer */
+	cr = readl(base + TIMER_CR);
+	cr |= TIMER_1_CR_ENABLE;
+	cr |= TIMER_1_CR_INT;
+	writel(cr, base + TIMER_CR);
+
+	return 0;
+}
+
+/* Use TIMER1 as clock event */
+static struct clock_event_device gemini_clockevent = {
+	.name			= "TIMER1",
+	/* Reasonably fast and accurate clock event */
+	.rating			= 300,
+	.shift                  = 32,
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_next_event		= gemini_timer_set_next_event,
+	.set_state_shutdown	= gemini_timer_shutdown,
+	.set_state_periodic	= gemini_timer_set_periodic,
+	.set_state_oneshot	= gemini_timer_shutdown,
+	.tick_resume		= gemini_timer_shutdown,
+};
+
+/*
+ * IRQ handler for the timer
+ */
+static irqreturn_t gemini_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = &gemini_clockevent;
+
+	evt->event_handler(evt);
+	return IRQ_HANDLED;
+}
+
+static struct irqaction gemini_timer_irq = {
+	.name		= "Gemini Timer Tick",
+	.flags		= IRQF_TIMER,
+	.handler	= gemini_timer_interrupt,
+};
+
+static int __init gemini_timer_of_init(struct device_node *np)
+{
+	static struct regmap *map;
+	int irq;
+	int ret;
+	u32 val;
+
+	map = syscon_regmap_lookup_by_phandle(np, "syscon");
+	if (IS_ERR(map)) {
+		pr_err("Can't get regmap for syscon handle");
+		return -ENODEV;
+	}
+	ret = regmap_read(map, GLOBAL_STATUS, &val);
+	if (ret) {
+		pr_err("Can't read syscon status register");
+		return -ENXIO;
+	}
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		pr_err("Can't remap registers");
+		return -ENXIO;
+	}
+	/* IRQ for timer 1 */
+	irq = irq_of_parse_and_map(np, 0);
+	if (irq <= 0) {
+		pr_err("Can't parse IRQ");
+		return -EINVAL;
+	}
+
+	tick_rate = REG_TO_AHB_SPEED(val) * 1000000;
+	printk(KERN_INFO "Bus: %dMHz", tick_rate / 1000000);
+
+	tick_rate /= 6;		/* APB bus run AHB*(1/6) */
+
+	switch (val & CPU_AHB_RATIO_MASK) {
+	case CPU_AHB_1_1:
+		printk(KERN_CONT "(1/1)\n");
+		break;
+	case CPU_AHB_3_2:
+		printk(KERN_CONT "(3/2)\n");
+		break;
+	case CPU_AHB_24_13:
+		printk(KERN_CONT "(24/13)\n");
+		break;
+	case CPU_AHB_2_1:
+		printk(KERN_CONT "(2/1)\n");
+		break;
+	}
+
+	/*
+	 * Reset the interrupt mask and status
+	 */
+	writel(TIMER_INT_ALL_MASK, base + TIMER_INTR_MASK);
+	writel(0, base + TIMER_INTR_STATE);
+	writel(TIMER_DEFAULT_FLAGS, base + TIMER_CR);
+
+	/*
+	 * Setup free-running clocksource timer (interrupts
+	 * disabled.)
+	 */
+	writel(0, base + TIMER3_COUNT);
+	writel(0, base + TIMER3_LOAD);
+	writel(0, base + TIMER3_MATCH1);
+	writel(0, base + TIMER3_MATCH2);
+	clocksource_mmio_init(base + TIMER3_COUNT,
+			      "gemini_clocksource", tick_rate,
+			      300, 32, clocksource_mmio_readl_up);
+	sched_clock_register(gemini_read_sched_clock, 32, tick_rate);
+
+	/*
+	 * Setup clockevent timer (interrupt-driven.)
+	 */
+	writel(0, base + TIMER1_COUNT);
+	writel(0, base + TIMER1_LOAD);
+	writel(0, base + TIMER1_MATCH1);
+	writel(0, base + TIMER1_MATCH2);
+	setup_irq(irq, &gemini_timer_irq);
+	gemini_clockevent.cpumask = cpumask_of(0);
+	clockevents_config_and_register(&gemini_clockevent, tick_rate,
+					1, 0xffffffff);
+
+	return 0;
+}
+CLOCKSOURCE_OF_DECLARE(nomadik_mtu, "cortina,gemini-timer",
+		       gemini_timer_of_init);
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index d8b164a7c4e5..4ebae43118ef 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -37,14 +37,6 @@ config CPU_FREQ_STAT
 
 	  If in doubt, say N.
 
-config CPU_FREQ_STAT_DETAILS
-	bool "CPU frequency transition statistics details"
-	depends on CPU_FREQ_STAT
-	help
-	  Show detailed CPU frequency transition table in sysfs.
-
-	  If in doubt, say N.
-
 choice
 	prompt "Default CPUFreq governor"
 	default CPU_FREQ_DEFAULT_GOV_USERSPACE if ARM_SA1100_CPUFREQ || ARM_SA1110_CPUFREQ
@@ -271,6 +263,16 @@ config IA64_ACPI_CPUFREQ
 endif
 
 if MIPS
+config BMIPS_CPUFREQ
+	tristate "BMIPS CPUfreq Driver"
+	help
+	  This option adds a CPUfreq driver for BMIPS processors with
+	  support for configurable CPU frequency.
+
+	  For now, BMIPS5 chips are supported (such as the Broadcom 7425).
+
+	  If in doubt, say N.
+
 config LOONGSON2_CPUFREQ
 	tristate "Loongson2 CPUFreq Driver"
 	help
@@ -332,7 +334,7 @@ endif
 
 config QORIQ_CPUFREQ
 	tristate "CPU frequency scaling driver for Freescale QorIQ SoCs"
-	depends on OF && COMMON_CLK && (PPC_E500MC || ARM)
+	depends on OF && COMMON_CLK && (PPC_E500MC || ARM || ARM64)
 	depends on !CPU_THERMAL || THERMAL
 	select CLK_QORIQ
 	help
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 920c469f3953..74fa5c5904d3 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -247,6 +247,17 @@ config ARM_TEGRA124_CPUFREQ
 	help
 	  This adds the CPUFreq driver support for Tegra124 SOCs.
 
+config ARM_TI_CPUFREQ
+	bool "Texas Instruments CPUFreq support"
+	depends on ARCH_OMAP2PLUS
+	help
+	  This driver enables valid OPPs on the running platform based on
+	  values contained within the SoC in use. Enable this in order to
+	  use the cpufreq-dt driver on all Texas Instruments platforms that
+	  provide dt based operating-points-v2 tables with opp-supported-hw
+	  data provided. Required for cpufreq support on AM335x, AM437x,
+	  DRA7x, and AM57x platforms.
+
 config ARM_PXA2xx_CPUFREQ
 	tristate "Intel PXA2xx CPUfreq driver"
 	depends on PXA27x || PXA25x
@@ -257,7 +268,7 @@ config ARM_PXA2xx_CPUFREQ
 
 config ACPI_CPPC_CPUFREQ
 	tristate "CPUFreq driver based on the ACPI CPPC spec"
-	depends on ACPI
+	depends on ACPI_PROCESSOR
 	select ACPI_CPPC_LIB
 	default n
 	help
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 1e46c3918e7a..9f5a8045f36d 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -77,6 +77,7 @@ obj-$(CONFIG_ARM_SPEAR_CPUFREQ)		+= spear-cpufreq.o
 obj-$(CONFIG_ARM_STI_CPUFREQ)		+= sti-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA20_CPUFREQ)	+= tegra20-cpufreq.o
 obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
+obj-$(CONFIG_ARM_TI_CPUFREQ)		+= ti-cpufreq.o
 obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ)	+= vexpress-spc-cpufreq.o
 obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o
 obj-$(CONFIG_MACH_MVEBU_V7)		+= mvebu-cpufreq.o
@@ -98,6 +99,7 @@ obj-$(CONFIG_POWERNV_CPUFREQ)		+= powernv-cpufreq.o
 # Other platform drivers
 obj-$(CONFIG_AVR32_AT32AP_CPUFREQ)	+= at32ap-cpufreq.o
 obj-$(CONFIG_BFIN_CPU_FREQ)		+= blackfin-cpufreq.o
+obj-$(CONFIG_BMIPS_CPUFREQ)		+= bmips-cpufreq.o
 obj-$(CONFIG_CRIS_MACH_ARTPEC3)		+= cris-artpec3-cpufreq.o
 obj-$(CONFIG_ETRAXFS)			+= cris-etraxfs-cpufreq.o
 obj-$(CONFIG_IA64_ACPI_CPUFREQ)		+= ia64-acpi-cpufreq.o
diff --git a/drivers/cpufreq/bmips-cpufreq.c b/drivers/cpufreq/bmips-cpufreq.c
new file mode 100644
index 000000000000..1653151b77df
--- /dev/null
+++ b/drivers/cpufreq/bmips-cpufreq.c
@@ -0,0 +1,188 @@
+/*
+ * CPU frequency scaling for Broadcom BMIPS SoCs
+ *
+ * Copyright (c) 2017 Broadcom
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/cpufreq.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+
+/* for mips_hpt_frequency */
+#include <asm/time.h>
+
+#define BMIPS_CPUFREQ_PREFIX	"bmips"
+#define BMIPS_CPUFREQ_NAME	BMIPS_CPUFREQ_PREFIX "-cpufreq"
+
+#define TRANSITION_LATENCY	(25 * 1000)	/* 25 us */
+
+#define BMIPS5_CLK_DIV_SET_SHIFT	0x7
+#define BMIPS5_CLK_DIV_SHIFT		0x4
+#define BMIPS5_CLK_DIV_MASK		0xf
+
+enum bmips_type {
+	BMIPS5000,
+	BMIPS5200,
+};
+
+struct cpufreq_compat {
+	const char *compatible;
+	unsigned int bmips_type;
+	unsigned int clk_mult;
+	unsigned int max_freqs;
+};
+
+#define BMIPS(c, t, m, f) { \
+	.compatible = c, \
+	.bmips_type = (t), \
+	.clk_mult = (m), \
+	.max_freqs = (f), \
+}
+
+static struct cpufreq_compat bmips_cpufreq_compat[] = {
+	BMIPS("brcm,bmips5000", BMIPS5000, 8, 4),
+	BMIPS("brcm,bmips5200", BMIPS5200, 8, 4),
+	{ }
+};
+
+static struct cpufreq_compat *priv;
+
+static int htp_freq_to_cpu_freq(unsigned int clk_mult)
+{
+	return mips_hpt_frequency * clk_mult / 1000;
+}
+
+static struct cpufreq_frequency_table *
+bmips_cpufreq_get_freq_table(const struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *table;
+	unsigned long cpu_freq;
+	int i;
+
+	cpu_freq = htp_freq_to_cpu_freq(priv->clk_mult);
+
+	table = kmalloc((priv->max_freqs + 1) * sizeof(*table), GFP_KERNEL);
+	if (!table)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < priv->max_freqs; i++) {
+		table[i].frequency = cpu_freq / (1 << i);
+		table[i].driver_data = i;
+	}
+	table[i].frequency = CPUFREQ_TABLE_END;
+
+	return table;
+}
+
+static unsigned int bmips_cpufreq_get(unsigned int cpu)
+{
+	unsigned int div;
+	uint32_t mode;
+
+	switch (priv->bmips_type) {
+	case BMIPS5200:
+	case BMIPS5000:
+		mode = read_c0_brcm_mode();
+		div = ((mode >> BMIPS5_CLK_DIV_SHIFT) & BMIPS5_CLK_DIV_MASK);
+		break;
+	default:
+		div = 0;
+	}
+
+	return htp_freq_to_cpu_freq(priv->clk_mult) / (1 << div);
+}
+
+static int bmips_cpufreq_target_index(struct cpufreq_policy *policy,
+				      unsigned int index)
+{
+	unsigned int div = policy->freq_table[index].driver_data;
+
+	switch (priv->bmips_type) {
+	case BMIPS5200:
+	case BMIPS5000:
+		change_c0_brcm_mode(BMIPS5_CLK_DIV_MASK << BMIPS5_CLK_DIV_SHIFT,
+				    (1 << BMIPS5_CLK_DIV_SET_SHIFT) |
+				    (div << BMIPS5_CLK_DIV_SHIFT));
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return 0;
+}
+
+static int bmips_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	kfree(policy->freq_table);
+
+	return 0;
+}
+
+static int bmips_cpufreq_init(struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *freq_table;
+	int ret;
+
+	freq_table = bmips_cpufreq_get_freq_table(policy);
+	if (IS_ERR(freq_table)) {
+		ret = PTR_ERR(freq_table);
+		pr_err("%s: couldn't determine frequency table (%d).\n",
+			BMIPS_CPUFREQ_NAME, ret);
+		return ret;
+	}
+
+	ret = cpufreq_generic_init(policy, freq_table, TRANSITION_LATENCY);
+	if (ret)
+		bmips_cpufreq_exit(policy);
+	else
+		pr_info("%s: registered\n", BMIPS_CPUFREQ_NAME);
+
+	return ret;
+}
+
+static struct cpufreq_driver bmips_cpufreq_driver = {
+	.flags		= CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.verify		= cpufreq_generic_frequency_table_verify,
+	.target_index	= bmips_cpufreq_target_index,
+	.get		= bmips_cpufreq_get,
+	.init		= bmips_cpufreq_init,
+	.exit		= bmips_cpufreq_exit,
+	.attr		= cpufreq_generic_attr,
+	.name		= BMIPS_CPUFREQ_PREFIX,
+};
+
+static int __init bmips_cpufreq_probe(void)
+{
+	struct cpufreq_compat *cc;
+	struct device_node *np;
+
+	for (cc = bmips_cpufreq_compat; cc->compatible; cc++) {
+		np = of_find_compatible_node(NULL, "cpu", cc->compatible);
+		if (np) {
+			of_node_put(np);
+			priv = cc;
+			break;
+		}
+	}
+
+	/* We hit the guard element of the array. No compatible CPU found. */
+	if (!cc->compatible)
+		return -ENODEV;
+
+	return cpufreq_register_driver(&bmips_cpufreq_driver);
+}
+device_initcall(bmips_cpufreq_probe);
+
+MODULE_AUTHOR("Markus Mayer <mmayer@broadcom.com>");
+MODULE_DESCRIPTION("CPUfreq driver for Broadcom BMIPS SoCs");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index 4fda623e55bb..7281a2c19c36 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -784,8 +784,19 @@ static int brcm_avs_target_index(struct cpufreq_policy *policy,
 static int brcm_avs_suspend(struct cpufreq_policy *policy)
 {
 	struct private_data *priv = policy->driver_data;
+	int ret;
+
+	ret = brcm_avs_get_pmap(priv, &priv->pmap);
+	if (ret)
+		return ret;
 
-	return brcm_avs_get_pmap(priv, &priv->pmap);
+	/*
+	 * We can't use the P-state returned by brcm_avs_get_pmap(), since
+	 * that's the initial P-state from when the P-map was downloaded to the
+	 * AVS co-processor, not necessarily the P-state we are running at now.
+	 * So, we get the current P-state explicitly.
+	 */
+	return brcm_avs_get_pstate(priv, &priv->pmap.state);
 }
 
 static int brcm_avs_resume(struct cpufreq_policy *policy)
@@ -867,7 +878,6 @@ unmap_intr_base:
 	iounmap(priv->avs_intr_base);
 unmap_base:
 	iounmap(priv->base);
-	platform_set_drvdata(pdev, NULL);
 
 	return ret;
 }
@@ -954,9 +964,9 @@ static ssize_t show_brcm_avs_pmap(struct cpufreq_policy *policy, char *buf)
 	brcm_avs_parse_p1(pmap.p1, &mdiv_p0, &pdiv, &ndiv);
 	brcm_avs_parse_p2(pmap.p2, &mdiv_p1, &mdiv_p2, &mdiv_p3, &mdiv_p4);
 
-	return sprintf(buf, "0x%08x 0x%08x %u %u %u %u %u %u %u\n",
+	return sprintf(buf, "0x%08x 0x%08x %u %u %u %u %u %u %u %u %u\n",
 		pmap.p1, pmap.p2, ndiv, pdiv, mdiv_p0, mdiv_p1, mdiv_p2,
-		mdiv_p3, mdiv_p4);
+		mdiv_p3, mdiv_p4, pmap.mode, pmap.state);
 }
 
 static ssize_t show_brcm_avs_voltage(struct cpufreq_policy *policy, char *buf)
@@ -1031,7 +1041,6 @@ static int brcm_avs_cpufreq_remove(struct platform_device *pdev)
 	priv = platform_get_drvdata(pdev);
 	iounmap(priv->base);
 	iounmap(priv->avs_intr_base);
-	platform_set_drvdata(pdev, NULL);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 7fcaf26e8f81..921b4a6c3d16 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -87,8 +87,6 @@ static const struct of_device_id machines[] __initconst = {
 	{ .compatible = "socionext,uniphier-ld11", },
 	{ .compatible = "socionext,uniphier-ld20", },
 
-	{ .compatible = "ti,am33xx", },
-	{ .compatible = "ti,dra7", },
 	{ .compatible = "ti,omap2", },
 	{ .compatible = "ti,omap3", },
 	{ .compatible = "ti,omap4", },
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 269013311e79..c943787d761e 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -148,7 +148,6 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	struct private_data *priv;
 	struct device *cpu_dev;
 	struct clk *cpu_clk;
-	struct dev_pm_opp *suspend_opp;
 	unsigned int transition_latency;
 	bool fallback = false;
 	const char *name;
@@ -252,11 +251,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	policy->driver_data = priv;
 	policy->clk = cpu_clk;
 
-	rcu_read_lock();
-	suspend_opp = dev_pm_opp_get_suspend_opp(cpu_dev);
-	if (suspend_opp)
-		policy->suspend_freq = dev_pm_opp_get_freq(suspend_opp) / 1000;
-	rcu_read_unlock();
+	policy->suspend_freq = dev_pm_opp_get_suspend_opp_freq(cpu_dev) / 1000;
 
 	ret = cpufreq_table_validate_and_show(policy, freq_table);
 	if (ret) {
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index cc475eff90b3..a47543281864 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -132,7 +132,7 @@ static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 	u64 cur_wall_time;
 	u64 busy_time;
 
-	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
+	cur_wall_time = jiffies64_to_nsecs(get_jiffies_64());
 
 	busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
 	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
@@ -143,9 +143,9 @@ static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 
 	idle_time = cur_wall_time - busy_time;
 	if (wall)
-		*wall = cputime_to_usecs(cur_wall_time);
+		*wall = div_u64(cur_wall_time, NSEC_PER_USEC);
 
-	return cputime_to_usecs(idle_time);
+	return div_u64(idle_time, NSEC_PER_USEC);
 }
 
 u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
@@ -1078,15 +1078,11 @@ err_free_policy:
 	return NULL;
 }
 
-static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify)
+static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
 {
 	struct kobject *kobj;
 	struct completion *cmp;
 
-	if (notify)
-		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-					     CPUFREQ_REMOVE_POLICY, policy);
-
 	down_write(&policy->rwsem);
 	cpufreq_stats_free_table(policy);
 	kobj = &policy->kobj;
@@ -1104,7 +1100,7 @@ static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify)
 	pr_debug("wait complete\n");
 }
 
-static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify)
+static void cpufreq_policy_free(struct cpufreq_policy *policy)
 {
 	unsigned long flags;
 	int cpu;
@@ -1117,7 +1113,7 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify)
 		per_cpu(cpufreq_cpu_data, cpu) = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	cpufreq_policy_put_kobj(policy, notify);
+	cpufreq_policy_put_kobj(policy);
 	free_cpumask_var(policy->real_cpus);
 	free_cpumask_var(policy->related_cpus);
 	free_cpumask_var(policy->cpus);
@@ -1170,8 +1166,6 @@ static int cpufreq_online(unsigned int cpu)
 	if (new_policy) {
 		/* related_cpus should at least include policy->cpus. */
 		cpumask_copy(policy->related_cpus, policy->cpus);
-		/* Clear mask of registered CPUs */
-		cpumask_clear(policy->real_cpus);
 	}
 
 	/*
@@ -1244,17 +1238,12 @@ static int cpufreq_online(unsigned int cpu)
 			goto out_exit_policy;
 
 		cpufreq_stats_create_table(policy);
-		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-				CPUFREQ_CREATE_POLICY, policy);
 
 		write_lock_irqsave(&cpufreq_driver_lock, flags);
 		list_add(&policy->policy_list, &cpufreq_policy_list);
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 	}
 
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-				     CPUFREQ_START, policy);
-
 	ret = cpufreq_init_policy(policy);
 	if (ret) {
 		pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n",
@@ -1282,7 +1271,7 @@ out_exit_policy:
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 out_free_policy:
-	cpufreq_policy_free(policy, !new_policy);
+	cpufreq_policy_free(policy);
 	return ret;
 }
 
@@ -1403,7 +1392,7 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	remove_cpu_dev_symlink(policy, dev);
 
 	if (cpumask_empty(policy->real_cpus))
-		cpufreq_policy_free(policy, true);
+		cpufreq_policy_free(policy);
 }
 
 /**
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 0196467280bd..631bd2c86c5e 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -152,7 +152,7 @@ unsigned int dbs_update(struct cpufreq_policy *policy)
 		if (ignore_nice) {
 			u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
-			idle_time += cputime_to_usecs(cur_nice - j_cdbs->prev_cpu_nice);
+			idle_time += div_u64(cur_nice - j_cdbs->prev_cpu_nice, NSEC_PER_USEC);
 			j_cdbs->prev_cpu_nice = cur_nice;
 		}
 
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index ac284e66839c..f570ead62454 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -13,7 +13,6 @@
 #include <linux/cpufreq.h>
 #include <linux/module.h>
 #include <linux/slab.h>
-#include <linux/cputime.h>
 
 static DEFINE_SPINLOCK(cpufreq_stats_lock);
 
@@ -25,9 +24,7 @@ struct cpufreq_stats {
 	unsigned int last_index;
 	u64 *time_in_state;
 	unsigned int *freq_table;
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	unsigned int *trans_table;
-#endif
 };
 
 static int cpufreq_stats_update(struct cpufreq_stats *stats)
@@ -46,9 +43,7 @@ static void cpufreq_stats_clear_table(struct cpufreq_stats *stats)
 	unsigned int count = stats->max_state;
 
 	memset(stats->time_in_state, 0, count * sizeof(u64));
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	memset(stats->trans_table, 0, count * count * sizeof(int));
-#endif
 	stats->last_time = get_jiffies_64();
 	stats->total_trans = 0;
 }
@@ -84,7 +79,6 @@ static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf,
 	return count;
 }
 
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 {
 	struct cpufreq_stats *stats = policy->stats;
@@ -129,7 +123,6 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 	return len;
 }
 cpufreq_freq_attr_ro(trans_table);
-#endif
 
 cpufreq_freq_attr_ro(total_trans);
 cpufreq_freq_attr_ro(time_in_state);
@@ -139,9 +132,7 @@ static struct attribute *default_attrs[] = {
 	&total_trans.attr,
 	&time_in_state.attr,
 	&reset.attr,
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	&trans_table.attr,
-#endif
 	NULL
 };
 static struct attribute_group stats_attr_group = {
@@ -200,9 +191,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 
 	alloc_size = count * sizeof(int) + count * sizeof(u64);
 
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	alloc_size += count * count * sizeof(int);
-#endif
 
 	/* Allocate memory for time_in_state/freq_table/trans_table in one go */
 	stats->time_in_state = kzalloc(alloc_size, GFP_KERNEL);
@@ -211,9 +200,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 
 	stats->freq_table = (unsigned int *)(stats->time_in_state + count);
 
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	stats->trans_table = stats->freq_table + count;
-#endif
 
 	stats->max_state = count;
 
@@ -259,8 +246,6 @@ void cpufreq_stats_record_transition(struct cpufreq_policy *policy,
 	cpufreq_stats_update(stats);
 
 	stats->last_index = new_index;
-#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	stats->trans_table[old_index * stats->max_state + new_index]++;
-#endif
 	stats->total_trans++;
 }
diff --git a/drivers/cpufreq/exynos5440-cpufreq.c b/drivers/cpufreq/exynos5440-cpufreq.c
index c0f3373706f4..9180d34cc9fc 100644
--- a/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/drivers/cpufreq/exynos5440-cpufreq.c
@@ -118,12 +118,10 @@ static int init_div_table(void)
 	unsigned int tmp, clk_div, ema_div, freq, volt_id;
 	struct dev_pm_opp *opp;
 
-	rcu_read_lock();
 	cpufreq_for_each_entry(pos, freq_tbl) {
 		opp = dev_pm_opp_find_freq_exact(dvfs_info->dev,
 					pos->frequency * 1000, true);
 		if (IS_ERR(opp)) {
-			rcu_read_unlock();
 			dev_err(dvfs_info->dev,
 				"failed to find valid OPP for %u KHZ\n",
 				pos->frequency);
@@ -140,6 +138,7 @@ static int init_div_table(void)
 
 		/* Calculate EMA */
 		volt_id = dev_pm_opp_get_voltage(opp);
+
 		volt_id = (MAX_VOLTAGE - volt_id) / VOLTAGE_STEP;
 		if (volt_id < PMIC_HIGH_VOLT) {
 			ema_div = (CPUEMA_HIGH << P0_7_CPUEMA_SHIFT) |
@@ -157,9 +156,9 @@ static int init_div_table(void)
 
 		__raw_writel(tmp, dvfs_info->base + XMU_PMU_P0_7 + 4 *
 						(pos - freq_tbl));
+		dev_pm_opp_put(opp);
 	}
 
-	rcu_read_unlock();
 	return 0;
 }
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index ef1fa8145419..7719b02e04f5 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -53,16 +53,15 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 	freq_hz = new_freq * 1000;
 	old_freq = clk_get_rate(arm_clk) / 1000;
 
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		dev_err(cpu_dev, "failed to find OPP for %ld\n", freq_hz);
 		return PTR_ERR(opp);
 	}
 
 	volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
+
 	volt_old = regulator_get_voltage(arm_reg);
 
 	dev_dbg(cpu_dev, "%u MHz, %ld mV --> %u MHz, %ld mV\n",
@@ -321,14 +320,15 @@ soc_opp_out:
 	 * freq_table initialised from OPP is therefore sorted in the
 	 * same order.
 	 */
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_exact(cpu_dev,
 				  freq_table[0].frequency * 1000, true);
 	min_volt = dev_pm_opp_get_voltage(opp);
+	dev_pm_opp_put(opp);
 	opp = dev_pm_opp_find_freq_exact(cpu_dev,
 				  freq_table[--num].frequency * 1000, true);
 	max_volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
+
 	ret = regulator_set_voltage_time(arm_reg, min_volt, max_volt);
 	if (ret > 0)
 		transition_latency += ret * 1000;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f91c25718d16..eb0f7fb71685 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -358,6 +358,8 @@ static struct pstate_funcs pstate_funcs __read_mostly;
 static int hwp_active __read_mostly;
 static bool per_cpu_limits __read_mostly;
 
+static bool driver_registered __read_mostly;
+
 #ifdef CONFIG_ACPI
 static bool acpi_ppc;
 #endif
@@ -394,6 +396,7 @@ static struct perf_limits *limits = &performance_limits;
 static struct perf_limits *limits = &powersave_limits;
 #endif
 
+static DEFINE_MUTEX(intel_pstate_driver_lock);
 static DEFINE_MUTEX(intel_pstate_limits_lock);
 
 #ifdef CONFIG_ACPI
@@ -538,7 +541,6 @@ static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
 
 	acpi_processor_unregister_performance(policy->cpu);
 }
-
 #else
 static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
 {
@@ -873,7 +875,10 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
 
 		rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
 		hw_min = HWP_LOWEST_PERF(cap);
-		hw_max = HWP_HIGHEST_PERF(cap);
+		if (limits->no_turbo)
+			hw_max = HWP_GUARANTEED_PERF(cap);
+		else
+			hw_max = HWP_HIGHEST_PERF(cap);
 		range = hw_max - hw_min;
 
 		max_perf_pct = perf_limits->max_perf_pct;
@@ -887,11 +892,6 @@ static void intel_pstate_hwp_set(struct cpufreq_policy *policy)
 
 		adj_range = max_perf_pct * range / 100;
 		max = hw_min + adj_range;
-		if (limits->no_turbo) {
-			hw_max = HWP_GUARANTEED_PERF(cap);
-			if (hw_max < max)
-				max = hw_max;
-		}
 
 		value &= ~HWP_MAX_PERF(~0L);
 		value |= HWP_MAX_PERF(max);
@@ -1007,37 +1007,59 @@ static int pid_param_get(void *data, u64 *val)
 }
 DEFINE_SIMPLE_ATTRIBUTE(fops_pid_param, pid_param_get, pid_param_set, "%llu\n");
 
+static struct dentry *debugfs_parent;
+
 struct pid_param {
 	char *name;
 	void *value;
+	struct dentry *dentry;
 };
 
 static struct pid_param pid_files[] = {
-	{"sample_rate_ms", &pid_params.sample_rate_ms},
-	{"d_gain_pct", &pid_params.d_gain_pct},
-	{"i_gain_pct", &pid_params.i_gain_pct},
-	{"deadband", &pid_params.deadband},
-	{"setpoint", &pid_params.setpoint},
-	{"p_gain_pct", &pid_params.p_gain_pct},
-	{NULL, NULL}
+	{"sample_rate_ms", &pid_params.sample_rate_ms, },
+	{"d_gain_pct", &pid_params.d_gain_pct, },
+	{"i_gain_pct", &pid_params.i_gain_pct, },
+	{"deadband", &pid_params.deadband, },
+	{"setpoint", &pid_params.setpoint, },
+	{"p_gain_pct", &pid_params.p_gain_pct, },
+	{NULL, NULL, }
 };
 
-static void __init intel_pstate_debug_expose_params(void)
+static void intel_pstate_debug_expose_params(void)
 {
-	struct dentry *debugfs_parent;
-	int i = 0;
+	int i;
 
 	debugfs_parent = debugfs_create_dir("pstate_snb", NULL);
 	if (IS_ERR_OR_NULL(debugfs_parent))
 		return;
-	while (pid_files[i].name) {
-		debugfs_create_file(pid_files[i].name, 0660,
-				    debugfs_parent, pid_files[i].value,
-				    &fops_pid_param);
-		i++;
+
+	for (i = 0; pid_files[i].name; i++) {
+		struct dentry *dentry;
+
+		dentry = debugfs_create_file(pid_files[i].name, 0660,
+					     debugfs_parent, pid_files[i].value,
+					     &fops_pid_param);
+		if (!IS_ERR(dentry))
+			pid_files[i].dentry = dentry;
 	}
 }
 
+static void intel_pstate_debug_hide_params(void)
+{
+	int i;
+
+	if (IS_ERR_OR_NULL(debugfs_parent))
+		return;
+
+	for (i = 0; pid_files[i].name; i++) {
+		debugfs_remove(pid_files[i].dentry);
+		pid_files[i].dentry = NULL;
+	}
+
+	debugfs_remove(debugfs_parent);
+	debugfs_parent = NULL;
+}
+
 /************************** debugfs end ************************/
 
 /************************** sysfs begin ************************/
@@ -1048,6 +1070,34 @@ static void __init intel_pstate_debug_expose_params(void)
 		return sprintf(buf, "%u\n", limits->object);		\
 	}
 
+static ssize_t intel_pstate_show_status(char *buf);
+static int intel_pstate_update_status(const char *buf, size_t size);
+
+static ssize_t show_status(struct kobject *kobj,
+			   struct attribute *attr, char *buf)
+{
+	ssize_t ret;
+
+	mutex_lock(&intel_pstate_driver_lock);
+	ret = intel_pstate_show_status(buf);
+	mutex_unlock(&intel_pstate_driver_lock);
+
+	return ret;
+}
+
+static ssize_t store_status(struct kobject *a, struct attribute *b,
+			    const char *buf, size_t count)
+{
+	char *p = memchr(buf, '\n', count);
+	int ret;
+
+	mutex_lock(&intel_pstate_driver_lock);
+	ret = intel_pstate_update_status(buf, p ? p - buf : count);
+	mutex_unlock(&intel_pstate_driver_lock);
+
+	return ret < 0 ? ret : count;
+}
+
 static ssize_t show_turbo_pct(struct kobject *kobj,
 				struct attribute *attr, char *buf)
 {
@@ -1055,12 +1105,22 @@ static ssize_t show_turbo_pct(struct kobject *kobj,
 	int total, no_turbo, turbo_pct;
 	uint32_t turbo_fp;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	cpu = all_cpu_data[0];
 
 	total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1;
 	no_turbo = cpu->pstate.max_pstate - cpu->pstate.min_pstate + 1;
 	turbo_fp = div_fp(no_turbo, total);
 	turbo_pct = 100 - fp_toint(mul_fp(turbo_fp, int_tofp(100)));
+
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return sprintf(buf, "%u\n", turbo_pct);
 }
 
@@ -1070,8 +1130,18 @@ static ssize_t show_num_pstates(struct kobject *kobj,
 	struct cpudata *cpu;
 	int total;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	cpu = all_cpu_data[0];
 	total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1;
+
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return sprintf(buf, "%u\n", total);
 }
 
@@ -1080,12 +1150,21 @@ static ssize_t show_no_turbo(struct kobject *kobj,
 {
 	ssize_t ret;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	update_turbo_state();
 	if (limits->turbo_disabled)
 		ret = sprintf(buf, "%u\n", limits->turbo_disabled);
 	else
 		ret = sprintf(buf, "%u\n", limits->no_turbo);
 
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return ret;
 }
 
@@ -1099,12 +1178,20 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	mutex_lock(&intel_pstate_limits_lock);
 
 	update_turbo_state();
 	if (limits->turbo_disabled) {
 		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
 		mutex_unlock(&intel_pstate_limits_lock);
+		mutex_unlock(&intel_pstate_driver_lock);
 		return -EPERM;
 	}
 
@@ -1114,6 +1201,8 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 
 	intel_pstate_update_policies();
 
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return count;
 }
 
@@ -1127,6 +1216,13 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	mutex_lock(&intel_pstate_limits_lock);
 
 	limits->max_sysfs_pct = clamp_t(int, input, 0 , 100);
@@ -1142,6 +1238,8 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 
 	intel_pstate_update_policies();
 
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return count;
 }
 
@@ -1155,6 +1253,13 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
+	mutex_lock(&intel_pstate_driver_lock);
+
+	if (!driver_registered) {
+		mutex_unlock(&intel_pstate_driver_lock);
+		return -EAGAIN;
+	}
+
 	mutex_lock(&intel_pstate_limits_lock);
 
 	limits->min_sysfs_pct = clamp_t(int, input, 0 , 100);
@@ -1170,12 +1275,15 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 
 	intel_pstate_update_policies();
 
+	mutex_unlock(&intel_pstate_driver_lock);
+
 	return count;
 }
 
 show_one(max_perf_pct, max_perf_pct);
 show_one(min_perf_pct, min_perf_pct);
 
+define_one_global_rw(status);
 define_one_global_rw(no_turbo);
 define_one_global_rw(max_perf_pct);
 define_one_global_rw(min_perf_pct);
@@ -1183,6 +1291,7 @@ define_one_global_ro(turbo_pct);
 define_one_global_ro(num_pstates);
 
 static struct attribute *intel_pstate_attributes[] = {
+	&status.attr,
 	&no_turbo.attr,
 	&turbo_pct.attr,
 	&num_pstates.attr,
@@ -1235,6 +1344,25 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 		cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
 }
 
+#define MSR_IA32_POWER_CTL_BIT_EE	19
+
+/* Disable energy efficiency optimization */
+static void intel_pstate_disable_ee(int cpu)
+{
+	u64 power_ctl;
+	int ret;
+
+	ret = rdmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, &power_ctl);
+	if (ret)
+		return;
+
+	if (!(power_ctl & BIT(MSR_IA32_POWER_CTL_BIT_EE))) {
+		pr_info("Disabling energy efficiency optimization\n");
+		power_ctl |= BIT(MSR_IA32_POWER_CTL_BIT_EE);
+		wrmsrl_on_cpu(cpu, MSR_IA32_POWER_CTL, power_ctl);
+	}
+}
+
 static int atom_get_min_pstate(void)
 {
 	u64 value;
@@ -1345,48 +1473,71 @@ static int core_get_max_pstate_physical(void)
 	return (value >> 8) & 0xFF;
 }
 
+static int core_get_tdp_ratio(u64 plat_info)
+{
+	/* Check how many TDP levels present */
+	if (plat_info & 0x600000000) {
+		u64 tdp_ctrl;
+		u64 tdp_ratio;
+		int tdp_msr;
+		int err;
+
+		/* Get the TDP level (0, 1, 2) to get ratios */
+		err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
+		if (err)
+			return err;
+
+		/* TDP MSR are continuous starting at 0x648 */
+		tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x03);
+		err = rdmsrl_safe(tdp_msr, &tdp_ratio);
+		if (err)
+			return err;
+
+		/* For level 1 and 2, bits[23:16] contain the ratio */
+		if (tdp_ctrl & 0x03)
+			tdp_ratio >>= 16;
+
+		tdp_ratio &= 0xff; /* ratios are only 8 bits long */
+		pr_debug("tdp_ratio %x\n", (int)tdp_ratio);
+
+		return (int)tdp_ratio;
+	}
+
+	return -ENXIO;
+}
+
 static int core_get_max_pstate(void)
 {
 	u64 tar;
 	u64 plat_info;
 	int max_pstate;
+	int tdp_ratio;
 	int err;
 
 	rdmsrl(MSR_PLATFORM_INFO, plat_info);
 	max_pstate = (plat_info >> 8) & 0xFF;
 
+	tdp_ratio = core_get_tdp_ratio(plat_info);
+	if (tdp_ratio <= 0)
+		return max_pstate;
+
+	if (hwp_active) {
+		/* Turbo activation ratio is not used on HWP platforms */
+		return tdp_ratio;
+	}
+
 	err = rdmsrl_safe(MSR_TURBO_ACTIVATION_RATIO, &tar);
 	if (!err) {
+		int tar_levels;
+
 		/* Do some sanity checking for safety */
-		if (plat_info & 0x600000000) {
-			u64 tdp_ctrl;
-			u64 tdp_ratio;
-			int tdp_msr;
-
-			err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
-			if (err)
-				goto skip_tar;
-
-			tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x3);
-			err = rdmsrl_safe(tdp_msr, &tdp_ratio);
-			if (err)
-				goto skip_tar;
-
-			/* For level 1 and 2, bits[23:16] contain the ratio */
-			if (tdp_ctrl)
-				tdp_ratio >>= 16;
-
-			tdp_ratio &= 0xff; /* ratios are only 8 bits long */
-			if (tdp_ratio - 1 == tar) {
-				max_pstate = tar;
-				pr_debug("max_pstate=TAC %x\n", max_pstate);
-			} else {
-				goto skip_tar;
-			}
+		tar_levels = tar & 0xff;
+		if (tdp_ratio - 1 == tar_levels) {
+			max_pstate = tar_levels;
+			pr_debug("max_pstate=TAC %x\n", max_pstate);
 		}
 	}
 
-skip_tar:
 	return max_pstate;
 }
 
@@ -1845,6 +1996,11 @@ static const struct x86_cpu_id intel_pstate_cpu_oob_ids[] __initconst = {
 	{}
 };
 
+static const struct x86_cpu_id intel_pstate_cpu_ee_disable_ids[] = {
+	ICPU(INTEL_FAM6_KABYLAKE_DESKTOP, core_params),
+	{}
+};
+
 static int intel_pstate_init_cpu(unsigned int cpunum)
 {
 	struct cpudata *cpu;
@@ -1875,6 +2031,12 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	cpu->cpu = cpunum;
 
 	if (hwp_active) {
+		const struct x86_cpu_id *id;
+
+		id = x86_match_cpu(intel_pstate_cpu_ee_disable_ids);
+		if (id)
+			intel_pstate_disable_ee(cpunum);
+
 		intel_pstate_hwp_enable(cpu);
 		pid_params.sample_rate_ms = 50;
 		pid_params.sample_rate_ns = 50 * NSEC_PER_MSEC;
@@ -2005,7 +2167,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 			limits = &performance_limits;
 			perf_limits = limits;
 		}
-		if (policy->max >= policy->cpuinfo.max_freq) {
+		if (policy->max >= policy->cpuinfo.max_freq &&
+		    !limits->no_turbo) {
 			pr_debug("set performance\n");
 			intel_pstate_set_performance_limits(perf_limits);
 			goto out;
@@ -2041,12 +2204,37 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 
 static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
 {
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+	struct perf_limits *perf_limits;
+
+	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE)
+		perf_limits = &performance_limits;
+	else
+		perf_limits = &powersave_limits;
+
+	update_turbo_state();
+	policy->cpuinfo.max_freq = perf_limits->turbo_disabled ||
+					perf_limits->no_turbo ?
+					cpu->pstate.max_freq :
+					cpu->pstate.turbo_freq;
+
 	cpufreq_verify_within_cpu_limits(policy);
 
 	if (policy->policy != CPUFREQ_POLICY_POWERSAVE &&
 	    policy->policy != CPUFREQ_POLICY_PERFORMANCE)
 		return -EINVAL;
 
+	/* When per-CPU limits are used, sysfs limits are not used */
+	if (!per_cpu_limits) {
+		unsigned int max_freq, min_freq;
+
+		max_freq = policy->cpuinfo.max_freq *
+						limits->max_sysfs_pct / 100;
+		min_freq = policy->cpuinfo.max_freq *
+						limits->min_sysfs_pct / 100;
+		cpufreq_verify_within_limits(policy, min_freq, max_freq);
+	}
+
 	return 0;
 }
 
@@ -2257,6 +2445,111 @@ static struct cpufreq_driver intel_cpufreq = {
 
 static struct cpufreq_driver *intel_pstate_driver = &intel_pstate;
 
+static void intel_pstate_driver_cleanup(void)
+{
+	unsigned int cpu;
+
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		if (all_cpu_data[cpu]) {
+			if (intel_pstate_driver == &intel_pstate)
+				intel_pstate_clear_update_util_hook(cpu);
+
+			kfree(all_cpu_data[cpu]);
+			all_cpu_data[cpu] = NULL;
+		}
+	}
+	put_online_cpus();
+}
+
+static int intel_pstate_register_driver(void)
+{
+	int ret;
+
+	ret = cpufreq_register_driver(intel_pstate_driver);
+	if (ret) {
+		intel_pstate_driver_cleanup();
+		return ret;
+	}
+
+	mutex_lock(&intel_pstate_limits_lock);
+	driver_registered = true;
+	mutex_unlock(&intel_pstate_limits_lock);
+
+	if (intel_pstate_driver == &intel_pstate && !hwp_active &&
+	    pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
+		intel_pstate_debug_expose_params();
+
+	return 0;
+}
+
+static int intel_pstate_unregister_driver(void)
+{
+	if (hwp_active)
+		return -EBUSY;
+
+	if (intel_pstate_driver == &intel_pstate && !hwp_active &&
+	    pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
+		intel_pstate_debug_hide_params();
+
+	mutex_lock(&intel_pstate_limits_lock);
+	driver_registered = false;
+	mutex_unlock(&intel_pstate_limits_lock);
+
+	cpufreq_unregister_driver(intel_pstate_driver);
+	intel_pstate_driver_cleanup();
+
+	return 0;
+}
+
+static ssize_t intel_pstate_show_status(char *buf)
+{
+	if (!driver_registered)
+		return sprintf(buf, "off\n");
+
+	return sprintf(buf, "%s\n", intel_pstate_driver == &intel_pstate ?
+					"active" : "passive");
+}
+
+static int intel_pstate_update_status(const char *buf, size_t size)
+{
+	int ret;
+
+	if (size == 3 && !strncmp(buf, "off", size))
+		return driver_registered ?
+			intel_pstate_unregister_driver() : -EINVAL;
+
+	if (size == 6 && !strncmp(buf, "active", size)) {
+		if (driver_registered) {
+			if (intel_pstate_driver == &intel_pstate)
+				return 0;
+
+			ret = intel_pstate_unregister_driver();
+			if (ret)
+				return ret;
+		}
+
+		intel_pstate_driver = &intel_pstate;
+		return intel_pstate_register_driver();
+	}
+
+	if (size == 7 && !strncmp(buf, "passive", size)) {
+		if (driver_registered) {
+			if (intel_pstate_driver != &intel_pstate)
+				return 0;
+
+			ret = intel_pstate_unregister_driver();
+			if (ret)
+				return ret;
+		}
+
+		intel_pstate_driver = &intel_cpufreq;
+		return intel_pstate_register_driver();
+	}
+
+	return -EINVAL;
+}
+
 static int no_load __initdata;
 static int no_hwp __initdata;
 static int hwp_only __initdata;
@@ -2444,9 +2737,9 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = {
 
 static int __init intel_pstate_init(void)
 {
-	int cpu, rc = 0;
 	const struct x86_cpu_id *id;
 	struct cpu_defaults *cpu_def;
+	int rc = 0;
 
 	if (no_load)
 		return -ENODEV;
@@ -2478,45 +2771,29 @@ hwp_cpu_matched:
 	if (intel_pstate_platform_pwr_mgmt_exists())
 		return -ENODEV;
 
+	if (!hwp_active && hwp_only)
+		return -ENOTSUPP;
+
 	pr_info("Intel P-state driver initializing\n");
 
 	all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
 	if (!all_cpu_data)
 		return -ENOMEM;
 
-	if (!hwp_active && hwp_only)
-		goto out;
-
 	intel_pstate_request_control_from_smm();
 
-	rc = cpufreq_register_driver(intel_pstate_driver);
-	if (rc)
-		goto out;
-
-	if (intel_pstate_driver == &intel_pstate && !hwp_active &&
-	    pstate_funcs.get_target_pstate != get_target_pstate_use_cpu_load)
-		intel_pstate_debug_expose_params();
-
 	intel_pstate_sysfs_expose_params();
 
+	mutex_lock(&intel_pstate_driver_lock);
+	rc = intel_pstate_register_driver();
+	mutex_unlock(&intel_pstate_driver_lock);
+	if (rc)
+		return rc;
+
 	if (hwp_active)
 		pr_info("HWP enabled\n");
 
-	return rc;
-out:
-	get_online_cpus();
-	for_each_online_cpu(cpu) {
-		if (all_cpu_data[cpu]) {
-			if (intel_pstate_driver == &intel_pstate)
-				intel_pstate_clear_update_util_hook(cpu);
-
-			kfree(all_cpu_data[cpu]);
-		}
-	}
-
-	put_online_cpus();
-	vfree(all_cpu_data);
-	return -ENODEV;
+	return 0;
 }
 device_initcall(intel_pstate_init);
 
diff --git a/drivers/cpufreq/mt8173-cpufreq.c b/drivers/cpufreq/mt8173-cpufreq.c
index 643f43179df1..ab25b1235a5e 100644
--- a/drivers/cpufreq/mt8173-cpufreq.c
+++ b/drivers/cpufreq/mt8173-cpufreq.c
@@ -232,16 +232,14 @@ static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
 
 	freq_hz = freq_table[index].frequency * 1000;
 
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		pr_err("cpu%d: failed to find OPP for %ld\n",
 		       policy->cpu, freq_hz);
 		return PTR_ERR(opp);
 	}
 	vproc = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	/*
 	 * If the new voltage or the intermediate voltage is higher than the
@@ -411,16 +409,14 @@ static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
 
 	/* Search a safe voltage for intermediate frequency. */
 	rate = clk_get_rate(inter_clk);
-	rcu_read_lock();
 	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &rate);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		pr_err("failed to get intermediate opp for cpu%d\n", cpu);
 		ret = PTR_ERR(opp);
 		goto out_free_opp_table;
 	}
 	info->intermediate_voltage = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	info->cpu_dev = cpu_dev;
 	info->proc_reg = proc_reg;
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 376e63ca94e8..71e81bbf031b 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -63,16 +63,14 @@ static int omap_target(struct cpufreq_policy *policy, unsigned int index)
 	freq = ret;
 
 	if (mpu_reg) {
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_ceil(mpu_dev, &freq);
 		if (IS_ERR(opp)) {
-			rcu_read_unlock();
 			dev_err(mpu_dev, "%s: unable to find MPU OPP for %d\n",
 				__func__, new_freq);
 			return -EINVAL;
 		}
 		volt = dev_pm_opp_get_voltage(opp);
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 		tol = volt * OPP_TOLERANCE / 100;
 		volt_old = regulator_get_voltage(mpu_reg);
 	}
diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c
index 37671b545880..3ff5160451b4 100644
--- a/drivers/cpufreq/powernv-cpufreq.c
+++ b/drivers/cpufreq/powernv-cpufreq.c
@@ -144,6 +144,7 @@ static struct powernv_pstate_info {
 	unsigned int max;
 	unsigned int nominal;
 	unsigned int nr_pstates;
+	bool wof_enabled;
 } powernv_pstate_info;
 
 /* Use following macros for conversions between pstate_id and index */
@@ -203,6 +204,7 @@ static int init_powernv_pstates(void)
 	const __be32 *pstate_ids, *pstate_freqs;
 	u32 len_ids, len_freqs;
 	u32 pstate_min, pstate_max, pstate_nominal;
+	u32 pstate_turbo, pstate_ultra_turbo;
 
 	power_mgt = of_find_node_by_path("/ibm,opal/power-mgt");
 	if (!power_mgt) {
@@ -225,8 +227,29 @@ static int init_powernv_pstates(void)
 		pr_warn("ibm,pstate-nominal not found\n");
 		return -ENODEV;
 	}
+
+	if (of_property_read_u32(power_mgt, "ibm,pstate-ultra-turbo",
+				 &pstate_ultra_turbo)) {
+		powernv_pstate_info.wof_enabled = false;
+		goto next;
+	}
+
+	if (of_property_read_u32(power_mgt, "ibm,pstate-turbo",
+				 &pstate_turbo)) {
+		powernv_pstate_info.wof_enabled = false;
+		goto next;
+	}
+
+	if (pstate_turbo == pstate_ultra_turbo)
+		powernv_pstate_info.wof_enabled = false;
+	else
+		powernv_pstate_info.wof_enabled = true;
+
+next:
 	pr_info("cpufreq pstate min %d nominal %d max %d\n", pstate_min,
 		pstate_nominal, pstate_max);
+	pr_info("Workload Optimized Frequency is %s in the platform\n",
+		(powernv_pstate_info.wof_enabled) ? "enabled" : "disabled");
 
 	pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids);
 	if (!pstate_ids) {
@@ -268,6 +291,13 @@ static int init_powernv_pstates(void)
 			powernv_pstate_info.nominal = i;
 		else if (id == pstate_min)
 			powernv_pstate_info.min = i;
+
+		if (powernv_pstate_info.wof_enabled && id == pstate_turbo) {
+			int j;
+
+			for (j = i - 1; j >= (int)powernv_pstate_info.max; j--)
+				powernv_freqs[j].flags = CPUFREQ_BOOST_FREQ;
+		}
 	}
 
 	/* End of list marker entry */
@@ -305,9 +335,12 @@ static ssize_t cpuinfo_nominal_freq_show(struct cpufreq_policy *policy,
 struct freq_attr cpufreq_freq_attr_cpuinfo_nominal_freq =
 	__ATTR_RO(cpuinfo_nominal_freq);
 
+#define SCALING_BOOST_FREQS_ATTR_INDEX		2
+
 static struct freq_attr *powernv_cpu_freq_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
 	&cpufreq_freq_attr_cpuinfo_nominal_freq,
+	&cpufreq_freq_attr_scaling_boost_freqs,
 	NULL,
 };
 
@@ -1013,11 +1046,22 @@ static int __init powernv_cpufreq_init(void)
 	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
 	opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb);
 
+	if (powernv_pstate_info.wof_enabled)
+		powernv_cpufreq_driver.boost_enabled = true;
+	else
+		powernv_cpu_freq_attr[SCALING_BOOST_FREQS_ATTR_INDEX] = NULL;
+
 	rc = cpufreq_register_driver(&powernv_cpufreq_driver);
-	if (!rc)
-		return 0;
+	if (rc) {
+		pr_info("Failed to register the cpufreq driver (%d)\n", rc);
+		goto cleanup_notifiers;
+	}
 
-	pr_info("Failed to register the cpufreq driver (%d)\n", rc);
+	if (powernv_pstate_info.wof_enabled)
+		cpufreq_enable_boost_support();
+
+	return 0;
+cleanup_notifiers:
 	unregister_all_notifiers();
 	clean_chip_info();
 out:
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index dc112481a408..eeaa92251512 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -100,9 +100,6 @@ static int pmi_notifier(struct notifier_block *nb,
 	/* Should this really be called for CPUFREQ_ADJUST and CPUFREQ_NOTIFY
 	 * policy events?)
 	 */
-	if (event == CPUFREQ_START)
-		return 0;
-
 	node = cbe_cpu_to_node(policy->cpu);
 
 	pr_debug("got notified, event=%lu, node=%u\n", event, node);
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index 53d8c3fb16f6..a6fefac8afe4 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -11,6 +11,7 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/clk.h>
+#include <linux/clk-provider.h>
 #include <linux/cpufreq.h>
 #include <linux/cpu_cooling.h>
 #include <linux/errno.h>
@@ -37,53 +38,20 @@ struct cpu_data {
 	struct thermal_cooling_device *cdev;
 };
 
+/*
+ * Don't use cpufreq on this SoC -- used when the SoC would have otherwise
+ * matched a more generic compatible.
+ */
+#define SOC_BLACKLIST		1
+
 /**
  * struct soc_data - SoC specific data
- * @freq_mask: mask the disallowed frequencies
- * @flag: unique flags
+ * @flags: SOC_xxx
  */
 struct soc_data {
-	u32 freq_mask[4];
-	u32 flag;
-};
-
-#define FREQ_MASK	1
-/* see hardware specification for the allowed frqeuencies */
-static const struct soc_data sdata[] = {
-	{ /* used by p2041 and p3041 */
-		.freq_mask = {0x8, 0x8, 0x2, 0x2},
-		.flag = FREQ_MASK,
-	},
-	{ /* used by p5020 */
-		.freq_mask = {0x8, 0x2},
-		.flag = FREQ_MASK,
-	},
-	{ /* used by p4080, p5040 */
-		.freq_mask = {0},
-		.flag = 0,
-	},
+	u32 flags;
 };
 
-/*
- * the minimum allowed core frequency, in Hz
- * for chassis v1.0, >= platform frequency
- * for chassis v2.0, >= platform frequency / 2
- */
-static u32 min_cpufreq;
-static const u32 *fmask;
-
-#if defined(CONFIG_ARM)
-static int get_cpu_physical_id(int cpu)
-{
-	return topology_core_id(cpu);
-}
-#else
-static int get_cpu_physical_id(int cpu)
-{
-	return get_hard_smp_processor_id(cpu);
-}
-#endif
-
 static u32 get_bus_freq(void)
 {
 	struct device_node *soc;
@@ -101,9 +69,10 @@ static u32 get_bus_freq(void)
 	return sysfreq;
 }
 
-static struct device_node *cpu_to_clk_node(int cpu)
+static struct clk *cpu_to_clk(int cpu)
 {
-	struct device_node *np, *clk_np;
+	struct device_node *np;
+	struct clk *clk;
 
 	if (!cpu_present(cpu))
 		return NULL;
@@ -112,37 +81,28 @@ static struct device_node *cpu_to_clk_node(int cpu)
 	if (!np)
 		return NULL;
 
-	clk_np = of_parse_phandle(np, "clocks", 0);
-	if (!clk_np)
-		return NULL;
-
+	clk = of_clk_get(np, 0);
 	of_node_put(np);
-
-	return clk_np;
+	return clk;
 }
 
 /* traverse cpu nodes to get cpu mask of sharing clock wire */
 static void set_affected_cpus(struct cpufreq_policy *policy)
 {
-	struct device_node *np, *clk_np;
 	struct cpumask *dstp = policy->cpus;
+	struct clk *clk;
 	int i;
 
-	np = cpu_to_clk_node(policy->cpu);
-	if (!np)
-		return;
-
 	for_each_present_cpu(i) {
-		clk_np = cpu_to_clk_node(i);
-		if (!clk_np)
+		clk = cpu_to_clk(i);
+		if (IS_ERR(clk)) {
+			pr_err("%s: no clock for cpu %d\n", __func__, i);
 			continue;
+		}
 
-		if (clk_np == np)
+		if (clk_is_match(policy->clk, clk))
 			cpumask_set_cpu(i, dstp);
-
-		of_node_put(clk_np);
 	}
-	of_node_put(np);
 }
 
 /* reduce the duplicated frequencies in frequency table */
@@ -198,10 +158,11 @@ static void freq_table_sort(struct cpufreq_frequency_table *freq_table,
 
 static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	struct device_node *np, *pnode;
+	struct device_node *np;
 	int i, count, ret;
-	u32 freq, mask;
+	u32 freq;
 	struct clk *clk;
+	const struct clk_hw *hwclk;
 	struct cpufreq_frequency_table *table;
 	struct cpu_data *data;
 	unsigned int cpu = policy->cpu;
@@ -221,17 +182,13 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_nomem2;
 	}
 
-	pnode = of_parse_phandle(np, "clocks", 0);
-	if (!pnode) {
-		pr_err("%s: could not get clock information\n", __func__);
-		goto err_nomem2;
-	}
+	hwclk = __clk_get_hw(policy->clk);
+	count = clk_hw_get_num_parents(hwclk);
 
-	count = of_property_count_strings(pnode, "clock-names");
 	data->pclk = kcalloc(count, sizeof(struct clk *), GFP_KERNEL);
 	if (!data->pclk) {
 		pr_err("%s: no memory\n", __func__);
-		goto err_node;
+		goto err_nomem2;
 	}
 
 	table = kcalloc(count + 1, sizeof(*table), GFP_KERNEL);
@@ -240,23 +197,11 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_pclk;
 	}
 
-	if (fmask)
-		mask = fmask[get_cpu_physical_id(cpu)];
-	else
-		mask = 0x0;
-
 	for (i = 0; i < count; i++) {
-		clk = of_clk_get(pnode, i);
+		clk = clk_hw_get_parent_by_index(hwclk, i)->clk;
 		data->pclk[i] = clk;
 		freq = clk_get_rate(clk);
-		/*
-		 * the clock is valid if its frequency is not masked
-		 * and large than minimum allowed frequency.
-		 */
-		if (freq < min_cpufreq || (mask & (1 << i)))
-			table[i].frequency = CPUFREQ_ENTRY_INVALID;
-		else
-			table[i].frequency = freq / 1000;
+		table[i].frequency = freq / 1000;
 		table[i].driver_data = i;
 	}
 	freq_table_redup(table, count);
@@ -282,7 +227,6 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency = u64temp + 1;
 
 	of_node_put(np);
-	of_node_put(pnode);
 
 	return 0;
 
@@ -290,10 +234,7 @@ err_nomem1:
 	kfree(table);
 err_pclk:
 	kfree(data->pclk);
-err_node:
-	of_node_put(pnode);
 err_nomem2:
-	policy->driver_data = NULL;
 	kfree(data);
 err_np:
 	of_node_put(np);
@@ -357,12 +298,25 @@ static struct cpufreq_driver qoriq_cpufreq_driver = {
 	.attr		= cpufreq_generic_attr,
 };
 
+static const struct soc_data blacklist = {
+	.flags = SOC_BLACKLIST,
+};
+
 static const struct of_device_id node_matches[] __initconst = {
-	{ .compatible = "fsl,p2041-clockgen", .data = &sdata[0], },
-	{ .compatible = "fsl,p3041-clockgen", .data = &sdata[0], },
-	{ .compatible = "fsl,p5020-clockgen", .data = &sdata[1], },
-	{ .compatible = "fsl,p4080-clockgen", .data = &sdata[2], },
-	{ .compatible = "fsl,p5040-clockgen", .data = &sdata[2], },
+	/* e6500 cannot use cpufreq due to erratum A-008083 */
+	{ .compatible = "fsl,b4420-clockgen", &blacklist },
+	{ .compatible = "fsl,b4860-clockgen", &blacklist },
+	{ .compatible = "fsl,t2080-clockgen", &blacklist },
+	{ .compatible = "fsl,t4240-clockgen", &blacklist },
+
+	{ .compatible = "fsl,ls1012a-clockgen", },
+	{ .compatible = "fsl,ls1021a-clockgen", },
+	{ .compatible = "fsl,ls1043a-clockgen", },
+	{ .compatible = "fsl,ls1046a-clockgen", },
+	{ .compatible = "fsl,ls1088a-clockgen", },
+	{ .compatible = "fsl,ls2080a-clockgen", },
+	{ .compatible = "fsl,p4080-clockgen", },
+	{ .compatible = "fsl,qoriq-clockgen-1.0", },
 	{ .compatible = "fsl,qoriq-clockgen-2.0", },
 	{}
 };
@@ -380,16 +334,12 @@ static int __init qoriq_cpufreq_init(void)
 
 	match = of_match_node(node_matches, np);
 	data = match->data;
-	if (data) {
-		if (data->flag)
-			fmask = data->freq_mask;
-		min_cpufreq = get_bus_freq();
-	} else {
-		min_cpufreq = get_bus_freq() / 2;
-	}
 
 	of_node_put(np);
 
+	if (data && data->flags & SOC_BLACKLIST)
+		return -ENODEV;
+
 	ret = cpufreq_register_driver(&qoriq_cpufreq_driver);
 	if (!ret)
 		pr_info("Freescale QorIQ CPU frequency scaling driver\n");
diff --git a/drivers/cpufreq/s3c2416-cpufreq.c b/drivers/cpufreq/s3c2416-cpufreq.c
index d6d425773fa4..5b2db3c6568f 100644
--- a/drivers/cpufreq/s3c2416-cpufreq.c
+++ b/drivers/cpufreq/s3c2416-cpufreq.c
@@ -400,7 +400,6 @@ static int s3c2416_cpufreq_driver_init(struct cpufreq_policy *policy)
 	rate = clk_get_rate(s3c_freq->hclk);
 	if (rate < 133 * 1000 * 1000) {
 		pr_err("cpufreq: HCLK not at 133MHz\n");
-		clk_put(s3c_freq->hclk);
 		ret = -EINVAL;
 		goto err_armclk;
 	}
diff --git a/drivers/cpufreq/sti-cpufreq.c b/drivers/cpufreq/sti-cpufreq.c
index b366e6d830ea..a7db9011d5fe 100644
--- a/drivers/cpufreq/sti-cpufreq.c
+++ b/drivers/cpufreq/sti-cpufreq.c
@@ -160,6 +160,7 @@ static int sti_cpufreq_set_opp_info(void)
 	int pcode, substrate, major, minor;
 	int ret;
 	char name[MAX_PCODE_NAME_LEN];
+	struct opp_table *opp_table;
 
 	reg_fields = sti_cpufreq_match();
 	if (!reg_fields) {
@@ -211,20 +212,20 @@ use_defaults:
 
 	snprintf(name, MAX_PCODE_NAME_LEN, "pcode%d", pcode);
 
-	ret = dev_pm_opp_set_prop_name(dev, name);
-	if (ret) {
+	opp_table = dev_pm_opp_set_prop_name(dev, name);
+	if (IS_ERR(opp_table)) {
 		dev_err(dev, "Failed to set prop name\n");
-		return ret;
+		return PTR_ERR(opp_table);
 	}
 
 	version[0] = BIT(major);
 	version[1] = BIT(minor);
 	version[2] = BIT(substrate);
 
-	ret = dev_pm_opp_set_supported_hw(dev, version, VERSION_ELEMENTS);
-	if (ret) {
+	opp_table = dev_pm_opp_set_supported_hw(dev, version, VERSION_ELEMENTS);
+	if (IS_ERR(opp_table)) {
 		dev_err(dev, "Failed to set supported hardware\n");
-		return ret;
+		return PTR_ERR(opp_table);
 	}
 
 	dev_dbg(dev, "pcode: %d major: %d minor: %d substrate: %d\n",
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
new file mode 100644
index 000000000000..a7b5658c0460
--- /dev/null
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -0,0 +1,268 @@
+/*
+ * TI CPUFreq/OPP hw-supported driver
+ *
+ * Copyright (C) 2016-2017 Texas Instruments, Inc.
+ *	 Dave Gerlach <d-gerlach@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/pm_opp.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#define REVISION_MASK				0xF
+#define REVISION_SHIFT				28
+
+#define AM33XX_800M_ARM_MPU_MAX_FREQ		0x1E2F
+#define AM43XX_600M_ARM_MPU_MAX_FREQ		0xFFA
+
+#define DRA7_EFUSE_HAS_OD_MPU_OPP		11
+#define DRA7_EFUSE_HAS_HIGH_MPU_OPP		15
+#define DRA7_EFUSE_HAS_ALL_MPU_OPP		23
+
+#define DRA7_EFUSE_NOM_MPU_OPP			BIT(0)
+#define DRA7_EFUSE_OD_MPU_OPP			BIT(1)
+#define DRA7_EFUSE_HIGH_MPU_OPP			BIT(2)
+
+#define VERSION_COUNT				2
+
+struct ti_cpufreq_data;
+
+struct ti_cpufreq_soc_data {
+	unsigned long (*efuse_xlate)(struct ti_cpufreq_data *opp_data,
+				     unsigned long efuse);
+	unsigned long efuse_fallback;
+	unsigned long efuse_offset;
+	unsigned long efuse_mask;
+	unsigned long efuse_shift;
+	unsigned long rev_offset;
+};
+
+struct ti_cpufreq_data {
+	struct device *cpu_dev;
+	struct device_node *opp_node;
+	struct regmap *syscon;
+	const struct ti_cpufreq_soc_data *soc_data;
+};
+
+static unsigned long amx3_efuse_xlate(struct ti_cpufreq_data *opp_data,
+				      unsigned long efuse)
+{
+	if (!efuse)
+		efuse = opp_data->soc_data->efuse_fallback;
+	/* AM335x and AM437x use "OPP disable" bits, so invert */
+	return ~efuse;
+}
+
+static unsigned long dra7_efuse_xlate(struct ti_cpufreq_data *opp_data,
+				      unsigned long efuse)
+{
+	unsigned long calculated_efuse = DRA7_EFUSE_NOM_MPU_OPP;
+
+	/*
+	 * The efuse on dra7 and am57 parts contains a specific
+	 * value indicating the highest available OPP.
+	 */
+
+	switch (efuse) {
+	case DRA7_EFUSE_HAS_ALL_MPU_OPP:
+	case DRA7_EFUSE_HAS_HIGH_MPU_OPP:
+		calculated_efuse |= DRA7_EFUSE_HIGH_MPU_OPP;
+	case DRA7_EFUSE_HAS_OD_MPU_OPP:
+		calculated_efuse |= DRA7_EFUSE_OD_MPU_OPP;
+	}
+
+	return calculated_efuse;
+}
+
+static struct ti_cpufreq_soc_data am3x_soc_data = {
+	.efuse_xlate = amx3_efuse_xlate,
+	.efuse_fallback = AM33XX_800M_ARM_MPU_MAX_FREQ,
+	.efuse_offset = 0x07fc,
+	.efuse_mask = 0x1fff,
+	.rev_offset = 0x600,
+};
+
+static struct ti_cpufreq_soc_data am4x_soc_data = {
+	.efuse_xlate = amx3_efuse_xlate,
+	.efuse_fallback = AM43XX_600M_ARM_MPU_MAX_FREQ,
+	.efuse_offset = 0x0610,
+	.efuse_mask = 0x3f,
+	.rev_offset = 0x600,
+};
+
+static struct ti_cpufreq_soc_data dra7_soc_data = {
+	.efuse_xlate = dra7_efuse_xlate,
+	.efuse_offset = 0x020c,
+	.efuse_mask = 0xf80000,
+	.efuse_shift = 19,
+	.rev_offset = 0x204,
+};
+
+/**
+ * ti_cpufreq_get_efuse() - Parse and return efuse value present on SoC
+ * @opp_data: pointer to ti_cpufreq_data context
+ * @efuse_value: Set to the value parsed from efuse
+ *
+ * Returns error code if efuse not read properly.
+ */
+static int ti_cpufreq_get_efuse(struct ti_cpufreq_data *opp_data,
+				u32 *efuse_value)
+{
+	struct device *dev = opp_data->cpu_dev;
+	u32 efuse;
+	int ret;
+
+	ret = regmap_read(opp_data->syscon, opp_data->soc_data->efuse_offset,
+			  &efuse);
+	if (ret) {
+		dev_err(dev,
+			"Failed to read the efuse value from syscon: %d\n",
+			ret);
+		return ret;
+	}
+
+	efuse = (efuse & opp_data->soc_data->efuse_mask);
+	efuse >>= opp_data->soc_data->efuse_shift;
+
+	*efuse_value = opp_data->soc_data->efuse_xlate(opp_data, efuse);
+
+	return 0;
+}
+
+/**
+ * ti_cpufreq_get_rev() - Parse and return rev value present on SoC
+ * @opp_data: pointer to ti_cpufreq_data context
+ * @revision_value: Set to the value parsed from revision register
+ *
+ * Returns error code if revision not read properly.
+ */
+static int ti_cpufreq_get_rev(struct ti_cpufreq_data *opp_data,
+			      u32 *revision_value)
+{
+	struct device *dev = opp_data->cpu_dev;
+	u32 revision;
+	int ret;
+
+	ret = regmap_read(opp_data->syscon, opp_data->soc_data->rev_offset,
+			  &revision);
+	if (ret) {
+		dev_err(dev,
+			"Failed to read the revision number from syscon: %d\n",
+			ret);
+		return ret;
+	}
+
+	*revision_value = BIT((revision >> REVISION_SHIFT) & REVISION_MASK);
+
+	return 0;
+}
+
+static int ti_cpufreq_setup_syscon_register(struct ti_cpufreq_data *opp_data)
+{
+	struct device *dev = opp_data->cpu_dev;
+	struct device_node *np = opp_data->opp_node;
+
+	opp_data->syscon = syscon_regmap_lookup_by_phandle(np,
+							"syscon");
+	if (IS_ERR(opp_data->syscon)) {
+		dev_err(dev,
+			"\"syscon\" is missing, cannot use OPPv2 table.\n");
+		return PTR_ERR(opp_data->syscon);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id ti_cpufreq_of_match[] = {
+	{ .compatible = "ti,am33xx", .data = &am3x_soc_data, },
+	{ .compatible = "ti,am4372", .data = &am4x_soc_data, },
+	{ .compatible = "ti,dra7", .data = &dra7_soc_data },
+	{},
+};
+
+static int ti_cpufreq_init(void)
+{
+	u32 version[VERSION_COUNT];
+	struct device_node *np;
+	const struct of_device_id *match;
+	struct ti_cpufreq_data *opp_data;
+	int ret;
+
+	np = of_find_node_by_path("/");
+	match = of_match_node(ti_cpufreq_of_match, np);
+	if (!match)
+		return -ENODEV;
+
+	opp_data = kzalloc(sizeof(*opp_data), GFP_KERNEL);
+	if (!opp_data)
+		return -ENOMEM;
+
+	opp_data->soc_data = match->data;
+
+	opp_data->cpu_dev = get_cpu_device(0);
+	if (!opp_data->cpu_dev) {
+		pr_err("%s: Failed to get device for CPU0\n", __func__);
+		return -ENODEV;
+	}
+
+	opp_data->opp_node = dev_pm_opp_of_get_opp_desc_node(opp_data->cpu_dev);
+	if (!opp_data->opp_node) {
+		dev_info(opp_data->cpu_dev,
+			 "OPP-v2 not supported, cpufreq-dt will attempt to use legacy tables.\n");
+		goto register_cpufreq_dt;
+	}
+
+	ret = ti_cpufreq_setup_syscon_register(opp_data);
+	if (ret)
+		goto fail_put_node;
+
+	/*
+	 * OPPs determine whether or not they are supported based on
+	 * two metrics:
+	 *	0 - SoC Revision
+	 *	1 - eFuse value
+	 */
+	ret = ti_cpufreq_get_rev(opp_data, &version[0]);
+	if (ret)
+		goto fail_put_node;
+
+	ret = ti_cpufreq_get_efuse(opp_data, &version[1]);
+	if (ret)
+		goto fail_put_node;
+
+	of_node_put(opp_data->opp_node);
+
+	ret = PTR_ERR_OR_ZERO(dev_pm_opp_set_supported_hw(opp_data->cpu_dev,
+							  version, VERSION_COUNT));
+	if (ret) {
+		dev_err(opp_data->cpu_dev,
+			"Failed to set supported hardware\n");
+		goto fail_put_node;
+	}
+
+register_cpufreq_dt:
+	platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
+
+	return 0;
+
+fail_put_node:
+	of_node_put(opp_data->opp_node);
+
+	return ret;
+}
+device_initcall(ti_cpufreq_init);
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index d9b5b9398a0f..8d6d25c38c02 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -19,6 +19,7 @@
 #include <linux/tick.h>
 #include <linux/sched.h>
 #include <linux/math64.h>
+#include <linux/cpu.h>
 
 /*
  * Please note when changing the tuning values:
@@ -280,17 +281,23 @@ again:
 static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
+	struct device *device = get_cpu_device(dev->cpu);
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
 	int i;
 	unsigned int interactivity_req;
 	unsigned int expected_interval;
 	unsigned long nr_iowaiters, cpu_load;
+	int resume_latency = dev_pm_qos_read_value(device);
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
 		data->needs_update = 0;
 	}
 
+	/* resume_latency is 0 means no restriction */
+	if (resume_latency && resume_latency < latency_req)
+		latency_req = resume_latency;
+
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0))
 		return 0;
@@ -357,9 +364,9 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		if (s->disabled || su->disable)
 			continue;
 		if (s->target_residency > data->predicted_us)
-			continue;
+			break;
 		if (s->exit_latency > latency_req)
-			continue;
+			break;
 
 		data->last_state_idx = i;
 	}
diff --git a/drivers/crypto/ccp/ccp-dev-v5.c b/drivers/crypto/ccp/ccp-dev-v5.c
index e2ce8190ecc9..612898b4aaad 100644
--- a/drivers/crypto/ccp/ccp-dev-v5.c
+++ b/drivers/crypto/ccp/ccp-dev-v5.c
@@ -959,7 +959,7 @@ static irqreturn_t ccp5_irq_handler(int irq, void *data)
 static void ccp5_config(struct ccp_device *ccp)
 {
 	/* Public side */
-	iowrite32(0x00001249, ccp->io_regs + CMD5_REQID_CONFIG_OFFSET);
+	iowrite32(0x0, ccp->io_regs + CMD5_REQID_CONFIG_OFFSET);
 }
 
 static void ccp5other_config(struct ccp_device *ccp)
diff --git a/drivers/crypto/ccp/ccp-dev.h b/drivers/crypto/ccp/ccp-dev.h
index 830f35e6005f..649e5610a5ce 100644
--- a/drivers/crypto/ccp/ccp-dev.h
+++ b/drivers/crypto/ccp/ccp-dev.h
@@ -238,6 +238,7 @@ struct ccp_dma_chan {
 	struct ccp_device *ccp;
 
 	spinlock_t lock;
+	struct list_head created;
 	struct list_head pending;
 	struct list_head active;
 	struct list_head complete;
diff --git a/drivers/crypto/ccp/ccp-dmaengine.c b/drivers/crypto/ccp/ccp-dmaengine.c
index 6553912804f7..e5d9278f4019 100644
--- a/drivers/crypto/ccp/ccp-dmaengine.c
+++ b/drivers/crypto/ccp/ccp-dmaengine.c
@@ -63,6 +63,7 @@ static void ccp_free_chan_resources(struct dma_chan *dma_chan)
 	ccp_free_desc_resources(chan->ccp, &chan->complete);
 	ccp_free_desc_resources(chan->ccp, &chan->active);
 	ccp_free_desc_resources(chan->ccp, &chan->pending);
+	ccp_free_desc_resources(chan->ccp, &chan->created);
 
 	spin_unlock_irqrestore(&chan->lock, flags);
 }
@@ -273,6 +274,7 @@ static dma_cookie_t ccp_tx_submit(struct dma_async_tx_descriptor *tx_desc)
 	spin_lock_irqsave(&chan->lock, flags);
 
 	cookie = dma_cookie_assign(tx_desc);
+	list_del(&desc->entry);
 	list_add_tail(&desc->entry, &chan->pending);
 
 	spin_unlock_irqrestore(&chan->lock, flags);
@@ -426,7 +428,7 @@ static struct ccp_dma_desc *ccp_create_desc(struct dma_chan *dma_chan,
 
 	spin_lock_irqsave(&chan->lock, sflags);
 
-	list_add_tail(&desc->entry, &chan->pending);
+	list_add_tail(&desc->entry, &chan->created);
 
 	spin_unlock_irqrestore(&chan->lock, sflags);
 
@@ -610,6 +612,7 @@ static int ccp_terminate_all(struct dma_chan *dma_chan)
 	/*TODO: Purge the complete list? */
 	ccp_free_desc_resources(chan->ccp, &chan->active);
 	ccp_free_desc_resources(chan->ccp, &chan->pending);
+	ccp_free_desc_resources(chan->ccp, &chan->created);
 
 	spin_unlock_irqrestore(&chan->lock, flags);
 
@@ -679,6 +682,7 @@ int ccp_dmaengine_register(struct ccp_device *ccp)
 		chan->ccp = ccp;
 
 		spin_lock_init(&chan->lock);
+		INIT_LIST_HEAD(&chan->created);
 		INIT_LIST_HEAD(&chan->pending);
 		INIT_LIST_HEAD(&chan->active);
 		INIT_LIST_HEAD(&chan->complete);
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 2ed1e24b44a8..b4b78b37f8a6 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -158,7 +158,7 @@ int chcr_handle_resp(struct crypto_async_request *req, unsigned char *input,
 	case CRYPTO_ALG_TYPE_AEAD:
 		ctx_req.req.aead_req = (struct aead_request *)req;
 		ctx_req.ctx.reqctx = aead_request_ctx(ctx_req.req.aead_req);
-		dma_unmap_sg(&u_ctx->lldi.pdev->dev, ctx_req.req.aead_req->dst,
+		dma_unmap_sg(&u_ctx->lldi.pdev->dev, ctx_req.ctx.reqctx->dst,
 			     ctx_req.ctx.reqctx->dst_nents, DMA_FROM_DEVICE);
 		if (ctx_req.ctx.reqctx->skb) {
 			kfree_skb(ctx_req.ctx.reqctx->skb);
@@ -1362,8 +1362,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	struct chcr_wr *chcr_req;
 	struct cpl_rx_phys_dsgl *phys_cpl;
 	struct phys_sge_parm sg_param;
-	struct scatterlist *src, *dst;
-	struct scatterlist src_sg[2], dst_sg[2];
+	struct scatterlist *src;
 	unsigned int frags = 0, transhdr_len;
 	unsigned int ivsize = crypto_aead_ivsize(tfm), dst_size = 0;
 	unsigned int   kctx_len = 0;
@@ -1383,19 +1382,21 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 
 	if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0)
 		goto err;
-	src = scatterwalk_ffwd(src_sg, req->src, req->assoclen);
-	dst = src;
+	src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen);
+	reqctx->dst = src;
+
 	if (req->src != req->dst) {
 		err = chcr_copy_assoc(req, aeadctx);
 		if (err)
 			return ERR_PTR(err);
-		dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen);
+		reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst,
+					       req->assoclen);
 	}
 	if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_NULL) {
 		null = 1;
 		assoclen = 0;
 	}
-	reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen +
+	reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen +
 					     (op_type ? -authsize : authsize));
 	if (reqctx->dst_nents <= 0) {
 		pr_err("AUTHENC:Invalid Destination sg entries\n");
@@ -1460,7 +1461,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req,
 	sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize);
 	sg_param.qid = qid;
 	sg_param.align = 0;
-	if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst,
+	if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst,
 				  &sg_param))
 		goto dstmap_fail;
 
@@ -1711,8 +1712,7 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 	struct chcr_wr *chcr_req;
 	struct cpl_rx_phys_dsgl *phys_cpl;
 	struct phys_sge_parm sg_param;
-	struct scatterlist *src, *dst;
-	struct scatterlist src_sg[2], dst_sg[2];
+	struct scatterlist *src;
 	unsigned int frags = 0, transhdr_len, ivsize = AES_BLOCK_SIZE;
 	unsigned int dst_size = 0, kctx_len;
 	unsigned int sub_type;
@@ -1728,17 +1728,19 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 	if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0)
 		goto err;
 	sub_type = get_aead_subtype(tfm);
-	src = scatterwalk_ffwd(src_sg, req->src, req->assoclen);
-	dst = src;
+	src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen);
+	reqctx->dst = src;
+
 	if (req->src != req->dst) {
 		err = chcr_copy_assoc(req, aeadctx);
 		if (err) {
 			pr_err("AAD copy to destination buffer fails\n");
 			return ERR_PTR(err);
 		}
-		dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen);
+		reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst,
+					       req->assoclen);
 	}
-	reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen +
+	reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen +
 					     (op_type ? -authsize : authsize));
 	if (reqctx->dst_nents <= 0) {
 		pr_err("CCM:Invalid Destination sg entries\n");
@@ -1777,7 +1779,7 @@ static struct sk_buff *create_aead_ccm_wr(struct aead_request *req,
 	sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize);
 	sg_param.qid = qid;
 	sg_param.align = 0;
-	if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst,
+	if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst,
 				  &sg_param))
 		goto dstmap_fail;
 
@@ -1809,8 +1811,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	struct chcr_wr *chcr_req;
 	struct cpl_rx_phys_dsgl *phys_cpl;
 	struct phys_sge_parm sg_param;
-	struct scatterlist *src, *dst;
-	struct scatterlist src_sg[2], dst_sg[2];
+	struct scatterlist *src;
 	unsigned int frags = 0, transhdr_len;
 	unsigned int ivsize = AES_BLOCK_SIZE;
 	unsigned int dst_size = 0, kctx_len;
@@ -1832,13 +1833,14 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	if (sg_nents_for_len(req->src, req->assoclen + req->cryptlen) < 0)
 		goto err;
 
-	src = scatterwalk_ffwd(src_sg, req->src, req->assoclen);
-	dst = src;
+	src = scatterwalk_ffwd(reqctx->srcffwd, req->src, req->assoclen);
+	reqctx->dst = src;
 	if (req->src != req->dst) {
 		err = chcr_copy_assoc(req, aeadctx);
 		if (err)
 			return	ERR_PTR(err);
-		dst = scatterwalk_ffwd(dst_sg, req->dst, req->assoclen);
+		reqctx->dst = scatterwalk_ffwd(reqctx->dstffwd, req->dst,
+					       req->assoclen);
 	}
 
 	if (!req->cryptlen)
@@ -1848,7 +1850,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 		crypt_len = AES_BLOCK_SIZE;
 	else
 		crypt_len = req->cryptlen;
-	reqctx->dst_nents = sg_nents_for_len(dst, req->cryptlen +
+	reqctx->dst_nents = sg_nents_for_len(reqctx->dst, req->cryptlen +
 					     (op_type ? -authsize : authsize));
 	if (reqctx->dst_nents <= 0) {
 		pr_err("GCM:Invalid Destination sg entries\n");
@@ -1923,7 +1925,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 	sg_param.obsize = req->cryptlen + (op_type ? -authsize : authsize);
 	sg_param.qid = qid;
 	sg_param.align = 0;
-	if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, dst,
+	if (map_writesg_phys_cpl(&u_ctx->lldi.pdev->dev, phys_cpl, reqctx->dst,
 				  &sg_param))
 		goto dstmap_fail;
 
@@ -1937,7 +1939,8 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req,
 		write_sg_to_skb(skb, &frags, src, req->cryptlen);
 	} else {
 		aes_gcm_empty_pld_pad(req->dst, authsize - 1);
-		write_sg_to_skb(skb, &frags, dst, crypt_len);
+		write_sg_to_skb(skb, &frags, reqctx->dst, crypt_len);
+
 	}
 
 	create_wreq(ctx, chcr_req, req, skb, kctx_len, size, 1,
@@ -2189,8 +2192,8 @@ static int chcr_gcm_setkey(struct crypto_aead *aead, const u8 *key,
 	unsigned int ck_size;
 	int ret = 0, key_ctx_size = 0;
 
-	if (get_aead_subtype(aead) ==
-	    CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106) {
+	if (get_aead_subtype(aead) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106 &&
+	    keylen > 3) {
 		keylen -= 4;  /* nonce/salt is present in the last 4 bytes */
 		memcpy(aeadctx->salt, key + keylen, 4);
 	}
diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c
index 918da8e6e2d8..1c65f07e1cc9 100644
--- a/drivers/crypto/chelsio/chcr_core.c
+++ b/drivers/crypto/chelsio/chcr_core.c
@@ -52,6 +52,7 @@ static struct cxgb4_uld_info chcr_uld_info = {
 int assign_chcr_device(struct chcr_dev **dev)
 {
 	struct uld_ctx *u_ctx;
+	int ret = -ENXIO;
 
 	/*
 	 * Which device to use if multiple devices are available TODO
@@ -59,15 +60,14 @@ int assign_chcr_device(struct chcr_dev **dev)
 	 * must go to the same device to maintain the ordering.
 	 */
 	mutex_lock(&dev_mutex); /* TODO ? */
-	u_ctx = list_first_entry(&uld_ctx_list, struct uld_ctx, entry);
-	if (!u_ctx) {
-		mutex_unlock(&dev_mutex);
-		return -ENXIO;
+	list_for_each_entry(u_ctx, &uld_ctx_list, entry)
+		if (u_ctx && u_ctx->dev) {
+			*dev = u_ctx->dev;
+			ret = 0;
+			break;
 	}
-
-	*dev = u_ctx->dev;
 	mutex_unlock(&dev_mutex);
-	return 0;
+	return ret;
 }
 
 static int chcr_dev_add(struct uld_ctx *u_ctx)
@@ -202,10 +202,8 @@ static int chcr_uld_state_change(void *handle, enum cxgb4_state state)
 
 static int __init chcr_crypto_init(void)
 {
-	if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info)) {
+	if (cxgb4_register_uld(CXGB4_ULD_CRYPTO, &chcr_uld_info))
 		pr_err("ULD register fail: No chcr crypto support in cxgb4");
-		return -1;
-	}
 
 	return 0;
 }
diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h
index d5af7d64a763..7ec0a8f12475 100644
--- a/drivers/crypto/chelsio/chcr_crypto.h
+++ b/drivers/crypto/chelsio/chcr_crypto.h
@@ -158,6 +158,9 @@ struct ablk_ctx {
 };
 struct chcr_aead_reqctx {
 	struct	sk_buff	*skb;
+	struct scatterlist *dst;
+	struct scatterlist srcffwd[2];
+	struct scatterlist dstffwd[2];
 	short int dst_nents;
 	u16 verify;
 	u8 iv[CHCR_MAX_CRYPTO_IV_LEN];
diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/qat/qat_c62x/adf_drv.c
index bc5cbc193aae..5b2d78a5b5aa 100644
--- a/drivers/crypto/qat/qat_c62x/adf_drv.c
+++ b/drivers/crypto/qat/qat_c62x/adf_drv.c
@@ -233,7 +233,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			      &hw_data->accel_capabilities_mask);
 
 	/* Find and map all the device's BARS */
-	i = 0;
+	i = (hw_data->fuses & ADF_DEVICE_FUSECTL_MASK) ? 1 : 0;
 	bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
 	for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
 			 ADF_PCI_MAX_BARS * 2) {
diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h
index e8822536530b..33f0a6251e38 100644
--- a/drivers/crypto/qat/qat_common/adf_accel_devices.h
+++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h
@@ -69,6 +69,7 @@
 #define ADF_ERRSOU5 (0x3A000 + 0xD8)
 #define ADF_DEVICE_FUSECTL_OFFSET 0x40
 #define ADF_DEVICE_LEGFUSE_OFFSET 0x4C
+#define ADF_DEVICE_FUSECTL_MASK 0x80000000
 #define ADF_PCI_MAX_BARS 3
 #define ADF_DEVICE_NAME_LENGTH 32
 #define ADF_ETR_MAX_RINGS_PER_BANK 16
diff --git a/drivers/crypto/qat/qat_common/qat_hal.c b/drivers/crypto/qat/qat_common/qat_hal.c
index 1e480f140663..8c4fd255a601 100644
--- a/drivers/crypto/qat/qat_common/qat_hal.c
+++ b/drivers/crypto/qat/qat_common/qat_hal.c
@@ -456,7 +456,7 @@ static int qat_hal_init_esram(struct icp_qat_fw_loader_handle *handle)
 	unsigned int csr_val;
 	int times = 30;
 
-	if (handle->pci_dev->device == ADF_C3XXX_PCI_DEVICE_ID)
+	if (handle->pci_dev->device != ADF_DH895XCC_PCI_DEVICE_ID)
 		return 0;
 
 	csr_val = ADF_CSR_RD(csr_addr, 0);
@@ -716,7 +716,7 @@ int qat_hal_init(struct adf_accel_dev *accel_dev)
 		(void __iomem *)((uintptr_t)handle->hal_cap_ae_xfer_csr_addr_v +
 				 LOCAL_TO_XFER_REG_OFFSET);
 	handle->pci_dev = pci_info->pci_dev;
-	if (handle->pci_dev->device != ADF_C3XXX_PCI_DEVICE_ID) {
+	if (handle->pci_dev->device == ADF_DH895XCC_PCI_DEVICE_ID) {
 		sram_bar =
 			&pci_info->pci_bars[hw_data->get_sram_bar_id(hw_data)];
 		handle->hal_sram_addr_v = sram_bar->virt_addr;
diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c
index 9aea2c7ecbe6..8648b32ebc89 100644
--- a/drivers/devfreq/devfreq-event.c
+++ b/drivers/devfreq/devfreq-event.c
@@ -306,7 +306,7 @@ struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev,
 						struct devfreq_event_desc *desc)
 {
 	struct devfreq_event_dev *edev;
-	static atomic_t event_no = ATOMIC_INIT(0);
+	static atomic_t event_no = ATOMIC_INIT(-1);
 	int ret;
 
 	if (!dev || !desc)
@@ -329,7 +329,7 @@ struct devfreq_event_dev *devfreq_event_add_edev(struct device *dev,
 	edev->dev.class = devfreq_event_class;
 	edev->dev.release = devfreq_event_release_edev;
 
-	dev_set_name(&edev->dev, "event.%d", atomic_inc_return(&event_no) - 1);
+	dev_set_name(&edev->dev, "event%d", atomic_inc_return(&event_no));
 	ret = device_register(&edev->dev);
 	if (ret < 0) {
 		put_device(&edev->dev);
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 47206a21bb90..551a271353d2 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -111,18 +111,16 @@ static void devfreq_set_freq_table(struct devfreq *devfreq)
 		return;
 	}
 
-	rcu_read_lock();
 	for (i = 0, freq = 0; i < profile->max_state; i++, freq++) {
 		opp = dev_pm_opp_find_freq_ceil(devfreq->dev.parent, &freq);
 		if (IS_ERR(opp)) {
 			devm_kfree(devfreq->dev.parent, profile->freq_table);
 			profile->max_state = 0;
-			rcu_read_unlock();
 			return;
 		}
+		dev_pm_opp_put(opp);
 		profile->freq_table[i] = freq;
 	}
-	rcu_read_unlock();
 }
 
 /**
@@ -130,7 +128,7 @@ static void devfreq_set_freq_table(struct devfreq *devfreq)
  * @devfreq:	the devfreq instance
  * @freq:	the update target frequency
  */
-static int devfreq_update_status(struct devfreq *devfreq, unsigned long freq)
+int devfreq_update_status(struct devfreq *devfreq, unsigned long freq)
 {
 	int lev, prev_lev, ret = 0;
 	unsigned long cur_time;
@@ -166,6 +164,7 @@ out:
 	devfreq->last_stat_updated = cur_time;
 	return ret;
 }
+EXPORT_SYMBOL(devfreq_update_status);
 
 /**
  * find_devfreq_governor() - find devfreq governor from name
@@ -474,11 +473,15 @@ static int devfreq_notifier_call(struct notifier_block *nb, unsigned long type,
 }
 
 /**
- * _remove_devfreq() - Remove devfreq from the list and release its resources.
- * @devfreq:	the devfreq struct
+ * devfreq_dev_release() - Callback for struct device to release the device.
+ * @dev:	the devfreq device
+ *
+ * Remove devfreq from the list and release its resources.
  */
-static void _remove_devfreq(struct devfreq *devfreq)
+static void devfreq_dev_release(struct device *dev)
 {
+	struct devfreq *devfreq = to_devfreq(dev);
+
 	mutex_lock(&devfreq_list_lock);
 	if (IS_ERR(find_device_devfreq(devfreq->dev.parent))) {
 		mutex_unlock(&devfreq_list_lock);
@@ -500,19 +503,6 @@ static void _remove_devfreq(struct devfreq *devfreq)
 }
 
 /**
- * devfreq_dev_release() - Callback for struct device to release the device.
- * @dev:	the devfreq device
- *
- * This calls _remove_devfreq() if _remove_devfreq() is not called.
- */
-static void devfreq_dev_release(struct device *dev)
-{
-	struct devfreq *devfreq = to_devfreq(dev);
-
-	_remove_devfreq(devfreq);
-}
-
-/**
  * devfreq_add_device() - Add devfreq feature to the device
  * @dev:	the device to add devfreq feature.
  * @profile:	device-specific profile to run devfreq.
@@ -527,6 +517,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 {
 	struct devfreq *devfreq;
 	struct devfreq_governor *governor;
+	static atomic_t devfreq_no = ATOMIC_INIT(-1);
 	int err = 0;
 
 	if (!dev || !profile || !governor_name) {
@@ -538,15 +529,14 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	devfreq = find_device_devfreq(dev);
 	mutex_unlock(&devfreq_list_lock);
 	if (!IS_ERR(devfreq)) {
-		dev_err(dev, "%s: Unable to create devfreq for the device. It already has one.\n", __func__);
+		dev_err(dev, "%s: Unable to create devfreq for the device.\n",
+			__func__);
 		err = -EINVAL;
 		goto err_out;
 	}
 
 	devfreq = kzalloc(sizeof(struct devfreq), GFP_KERNEL);
 	if (!devfreq) {
-		dev_err(dev, "%s: Unable to create devfreq for the device\n",
-			__func__);
 		err = -ENOMEM;
 		goto err_out;
 	}
@@ -569,18 +559,21 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		mutex_lock(&devfreq->lock);
 	}
 
-	dev_set_name(&devfreq->dev, "%s", dev_name(dev));
+	dev_set_name(&devfreq->dev, "devfreq%d",
+				atomic_inc_return(&devfreq_no));
 	err = device_register(&devfreq->dev);
 	if (err) {
 		mutex_unlock(&devfreq->lock);
 		goto err_out;
 	}
 
-	devfreq->trans_table =	devm_kzalloc(&devfreq->dev, sizeof(unsigned int) *
+	devfreq->trans_table =	devm_kzalloc(&devfreq->dev,
+						sizeof(unsigned int) *
 						devfreq->profile->max_state *
 						devfreq->profile->max_state,
 						GFP_KERNEL);
-	devfreq->time_in_state = devm_kzalloc(&devfreq->dev, sizeof(unsigned long) *
+	devfreq->time_in_state = devm_kzalloc(&devfreq->dev,
+						sizeof(unsigned long) *
 						devfreq->profile->max_state,
 						GFP_KERNEL);
 	devfreq->last_stat_updated = jiffies;
@@ -939,6 +932,9 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr,
 	if (df->governor == governor) {
 		ret = 0;
 		goto out;
+	} else if (df->governor->immutable || governor->immutable) {
+		ret = -EINVAL;
+		goto out;
 	}
 
 	if (df->governor) {
@@ -968,13 +964,33 @@ static ssize_t available_governors_show(struct device *d,
 					struct device_attribute *attr,
 					char *buf)
 {
-	struct devfreq_governor *tmp_governor;
+	struct devfreq *df = to_devfreq(d);
 	ssize_t count = 0;
 
 	mutex_lock(&devfreq_list_lock);
-	list_for_each_entry(tmp_governor, &devfreq_governor_list, node)
-		count += scnprintf(&buf[count], (PAGE_SIZE - count - 2),
-				   "%s ", tmp_governor->name);
+
+	/*
+	 * The devfreq with immutable governor (e.g., passive) shows
+	 * only own governor.
+	 */
+	if (df->governor->immutable) {
+		count = scnprintf(&buf[count], DEVFREQ_NAME_LEN,
+				   "%s ", df->governor_name);
+	/*
+	 * The devfreq device shows the registered governor except for
+	 * immutable governors such as passive governor .
+	 */
+	} else {
+		struct devfreq_governor *governor;
+
+		list_for_each_entry(governor, &devfreq_governor_list, node) {
+			if (governor->immutable)
+				continue;
+			count += scnprintf(&buf[count], (PAGE_SIZE - count - 2),
+					   "%s ", governor->name);
+		}
+	}
+
 	mutex_unlock(&devfreq_list_lock);
 
 	/* Truncate the trailing space */
@@ -995,7 +1011,7 @@ static ssize_t cur_freq_show(struct device *dev, struct device_attribute *attr,
 
 	if (devfreq->profile->get_cur_freq &&
 		!devfreq->profile->get_cur_freq(devfreq->dev.parent, &freq))
-			return sprintf(buf, "%lu\n", freq);
+		return sprintf(buf, "%lu\n", freq);
 
 	return sprintf(buf, "%lu\n", devfreq->previous_freq);
 }
@@ -1112,17 +1128,16 @@ static ssize_t available_frequencies_show(struct device *d,
 	ssize_t count = 0;
 	unsigned long freq = 0;
 
-	rcu_read_lock();
 	do {
 		opp = dev_pm_opp_find_freq_ceil(dev, &freq);
 		if (IS_ERR(opp))
 			break;
 
+		dev_pm_opp_put(opp);
 		count += scnprintf(&buf[count], (PAGE_SIZE - count - 2),
 				   "%lu ", freq);
 		freq++;
 	} while (1);
-	rcu_read_unlock();
 
 	/* Truncate the trailing space */
 	if (count)
@@ -1224,11 +1239,8 @@ subsys_initcall(devfreq_init);
  * @freq:	The frequency given to target function
  * @flags:	Flags handed from devfreq framework.
  *
- * Locking: This function must be called under rcu_read_lock(). opp is a rcu
- * protected pointer. The reason for the same is that the opp pointer which is
- * returned will remain valid for use with opp_get_{voltage, freq} only while
- * under the locked area. The pointer returned must be used prior to unlocking
- * with rcu_read_unlock() to maintain the integrity of the pointer.
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
  */
 struct dev_pm_opp *devfreq_recommended_opp(struct device *dev,
 					   unsigned long *freq,
@@ -1265,18 +1277,7 @@ EXPORT_SYMBOL(devfreq_recommended_opp);
  */
 int devfreq_register_opp_notifier(struct device *dev, struct devfreq *devfreq)
 {
-	struct srcu_notifier_head *nh;
-	int ret = 0;
-
-	rcu_read_lock();
-	nh = dev_pm_opp_get_notifier(dev);
-	if (IS_ERR(nh))
-		ret = PTR_ERR(nh);
-	rcu_read_unlock();
-	if (!ret)
-		ret = srcu_notifier_chain_register(nh, &devfreq->nb);
-
-	return ret;
+	return dev_pm_opp_register_notifier(dev, &devfreq->nb);
 }
 EXPORT_SYMBOL(devfreq_register_opp_notifier);
 
@@ -1292,18 +1293,7 @@ EXPORT_SYMBOL(devfreq_register_opp_notifier);
  */
 int devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq)
 {
-	struct srcu_notifier_head *nh;
-	int ret = 0;
-
-	rcu_read_lock();
-	nh = dev_pm_opp_get_notifier(dev);
-	if (IS_ERR(nh))
-		ret = PTR_ERR(nh);
-	rcu_read_unlock();
-	if (!ret)
-		ret = srcu_notifier_chain_unregister(nh, &devfreq->nb);
-
-	return ret;
+	return dev_pm_opp_unregister_notifier(dev, &devfreq->nb);
 }
 EXPORT_SYMBOL(devfreq_unregister_opp_notifier);
 
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 107eb91a9415..9b7350935b73 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -17,13 +17,13 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/suspend.h>
 #include <linux/devfreq-event.h>
 
 #include "exynos-ppmu.h"
 
 struct exynos_ppmu_data {
-	void __iomem *base;
 	struct clk *clk;
 };
 
@@ -33,6 +33,7 @@ struct exynos_ppmu {
 	unsigned int num_events;
 
 	struct device *dev;
+	struct regmap *regmap;
 
 	struct exynos_ppmu_data ppmu;
 };
@@ -107,20 +108,28 @@ static int exynos_ppmu_find_ppmu_id(struct devfreq_event_dev *edev)
 static int exynos_ppmu_disable(struct devfreq_event_dev *edev)
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	int ret;
 	u32 pmnc;
 
 	/* Disable all counters */
-	__raw_writel(PPMU_CCNT_MASK |
-		     PPMU_PMCNT0_MASK |
-		     PPMU_PMCNT1_MASK |
-		     PPMU_PMCNT2_MASK |
-		     PPMU_PMCNT3_MASK,
-		     info->ppmu.base + PPMU_CNTENC);
+	ret = regmap_write(info->regmap, PPMU_CNTENC,
+				PPMU_CCNT_MASK |
+				PPMU_PMCNT0_MASK |
+				PPMU_PMCNT1_MASK |
+				PPMU_PMCNT2_MASK |
+				PPMU_PMCNT3_MASK);
+	if (ret < 0)
+		return ret;
 
 	/* Disable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC);
+	ret = regmap_read(info->regmap, PPMU_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
-	__raw_writel(pmnc, info->ppmu.base + PPMU_PMNC);
+	ret = regmap_write(info->regmap, PPMU_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -129,29 +138,42 @@ static int exynos_ppmu_set_event(struct devfreq_event_dev *edev)
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
 	int id = exynos_ppmu_find_ppmu_id(edev);
+	int ret;
 	u32 pmnc, cntens;
 
 	if (id < 0)
 		return id;
 
 	/* Enable specific counter */
-	cntens = __raw_readl(info->ppmu.base + PPMU_CNTENS);
+	ret = regmap_read(info->regmap, PPMU_CNTENS, &cntens);
+	if (ret < 0)
+		return ret;
+
 	cntens |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
-	__raw_writel(cntens, info->ppmu.base + PPMU_CNTENS);
+	ret = regmap_write(info->regmap, PPMU_CNTENS, cntens);
+	if (ret < 0)
+		return ret;
 
 	/* Set the event of Read/Write data count  */
-	__raw_writel(PPMU_RO_DATA_CNT | PPMU_WO_DATA_CNT,
-			info->ppmu.base + PPMU_BEVTxSEL(id));
+	ret = regmap_write(info->regmap, PPMU_BEVTxSEL(id),
+				PPMU_RO_DATA_CNT | PPMU_WO_DATA_CNT);
+	if (ret < 0)
+		return ret;
 
 	/* Reset cycle counter/performance counter and enable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC);
+	ret = regmap_read(info->regmap, PPMU_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~(PPMU_PMNC_ENABLE_MASK
 			| PPMU_PMNC_COUNTER_RESET_MASK
 			| PPMU_PMNC_CC_RESET_MASK);
 	pmnc |= (PPMU_ENABLE << PPMU_PMNC_ENABLE_SHIFT);
 	pmnc |= (PPMU_ENABLE << PPMU_PMNC_COUNTER_RESET_SHIFT);
 	pmnc |= (PPMU_ENABLE << PPMU_PMNC_CC_RESET_SHIFT);
-	__raw_writel(pmnc, info->ppmu.base + PPMU_PMNC);
+	ret = regmap_write(info->regmap, PPMU_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -161,40 +183,64 @@ static int exynos_ppmu_get_event(struct devfreq_event_dev *edev,
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
 	int id = exynos_ppmu_find_ppmu_id(edev);
-	u32 pmnc, cntenc;
+	unsigned int total_count, load_count;
+	unsigned int pmcnt3_high, pmcnt3_low;
+	unsigned int pmnc, cntenc;
+	int ret;
 
 	if (id < 0)
 		return -EINVAL;
 
 	/* Disable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_PMNC);
+	ret = regmap_read(info->regmap, PPMU_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
-	__raw_writel(pmnc, info->ppmu.base + PPMU_PMNC);
+	ret = regmap_write(info->regmap, PPMU_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	/* Read cycle count */
-	edata->total_count = __raw_readl(info->ppmu.base + PPMU_CCNT);
+	ret = regmap_read(info->regmap, PPMU_CCNT, &total_count);
+	if (ret < 0)
+		return ret;
+	edata->total_count = total_count;
 
 	/* Read performance count */
 	switch (id) {
 	case PPMU_PMNCNT0:
 	case PPMU_PMNCNT1:
 	case PPMU_PMNCNT2:
-		edata->load_count
-			= __raw_readl(info->ppmu.base + PPMU_PMNCT(id));
+		ret = regmap_read(info->regmap, PPMU_PMNCT(id), &load_count);
+		if (ret < 0)
+			return ret;
+		edata->load_count = load_count;
 		break;
 	case PPMU_PMNCNT3:
-		edata->load_count =
-			((__raw_readl(info->ppmu.base + PPMU_PMCNT3_HIGH) << 8)
-			| __raw_readl(info->ppmu.base + PPMU_PMCNT3_LOW));
+		ret = regmap_read(info->regmap, PPMU_PMCNT3_HIGH, &pmcnt3_high);
+		if (ret < 0)
+			return ret;
+
+		ret = regmap_read(info->regmap, PPMU_PMCNT3_LOW, &pmcnt3_low);
+		if (ret < 0)
+			return ret;
+
+		edata->load_count = ((pmcnt3_high << 8) | pmcnt3_low);
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Disable specific counter */
-	cntenc = __raw_readl(info->ppmu.base + PPMU_CNTENC);
+	ret = regmap_read(info->regmap, PPMU_CNTENC, &cntenc);
+	if (ret < 0)
+		return ret;
+
 	cntenc |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
-	__raw_writel(cntenc, info->ppmu.base + PPMU_CNTENC);
+	ret = regmap_write(info->regmap, PPMU_CNTENC, cntenc);
+	if (ret < 0)
+		return ret;
 
 	dev_dbg(&edev->dev, "%s (event: %ld/%ld)\n", edev->desc->name,
 					edata->load_count, edata->total_count);
@@ -214,36 +260,93 @@ static const struct devfreq_event_ops exynos_ppmu_ops = {
 static int exynos_ppmu_v2_disable(struct devfreq_event_dev *edev)
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	int ret;
 	u32 pmnc, clear;
 
 	/* Disable all counters */
 	clear = (PPMU_CCNT_MASK | PPMU_PMCNT0_MASK | PPMU_PMCNT1_MASK
 		| PPMU_PMCNT2_MASK | PPMU_PMCNT3_MASK);
+	ret = regmap_write(info->regmap, PPMU_V2_FLAG, clear);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_INTENC, clear);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CNTENC, clear);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CNT_RESET, clear);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CIG_CFG0, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CIG_CFG1, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CIG_CFG2, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CIG_RESULT, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CNT_AUTO, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CH_EV0_TYPE, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CH_EV1_TYPE, 0x0);
+	if (ret < 0)
+		return ret;
 
-	__raw_writel(clear, info->ppmu.base + PPMU_V2_FLAG);
-	__raw_writel(clear, info->ppmu.base + PPMU_V2_INTENC);
-	__raw_writel(clear, info->ppmu.base + PPMU_V2_CNTENC);
-	__raw_writel(clear, info->ppmu.base + PPMU_V2_CNT_RESET);
-
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_CFG0);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_CFG1);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_CFG2);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CIG_RESULT);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CNT_AUTO);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV0_TYPE);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV1_TYPE);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV2_TYPE);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_CH_EV3_TYPE);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_ID_V);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_ID_A);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_OTHERS_V);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_SM_OTHERS_A);
-	__raw_writel(0x0, info->ppmu.base + PPMU_V2_INTERRUPT_RESET);
+	ret = regmap_write(info->regmap, PPMU_V2_CH_EV2_TYPE, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_CH_EV3_TYPE, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_SM_ID_V, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_SM_ID_A, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_SM_OTHERS_V, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_SM_OTHERS_A, 0x0);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(info->regmap, PPMU_V2_INTERRUPT_RESET, 0x0);
+	if (ret < 0)
+		return ret;
 
 	/* Disable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_V2_PMNC);
+	ret = regmap_read(info->regmap, PPMU_V2_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
-	__raw_writel(pmnc, info->ppmu.base + PPMU_V2_PMNC);
+	ret = regmap_write(info->regmap, PPMU_V2_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -251,30 +354,43 @@ static int exynos_ppmu_v2_disable(struct devfreq_event_dev *edev)
 static int exynos_ppmu_v2_set_event(struct devfreq_event_dev *edev)
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
+	unsigned int pmnc, cntens;
 	int id = exynos_ppmu_find_ppmu_id(edev);
-	u32 pmnc, cntens;
+	int ret;
 
 	/* Enable all counters */
-	cntens = __raw_readl(info->ppmu.base + PPMU_V2_CNTENS);
+	ret = regmap_read(info->regmap, PPMU_V2_CNTENS, &cntens);
+	if (ret < 0)
+		return ret;
+
 	cntens |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
-	__raw_writel(cntens, info->ppmu.base + PPMU_V2_CNTENS);
+	ret = regmap_write(info->regmap, PPMU_V2_CNTENS, cntens);
+	if (ret < 0)
+		return ret;
 
 	/* Set the event of Read/Write data count  */
 	switch (id) {
 	case PPMU_PMNCNT0:
 	case PPMU_PMNCNT1:
 	case PPMU_PMNCNT2:
-		__raw_writel(PPMU_V2_RO_DATA_CNT | PPMU_V2_WO_DATA_CNT,
-				info->ppmu.base + PPMU_V2_CH_EVx_TYPE(id));
+		ret = regmap_write(info->regmap, PPMU_V2_CH_EVx_TYPE(id),
+				PPMU_V2_RO_DATA_CNT | PPMU_V2_WO_DATA_CNT);
+		if (ret < 0)
+			return ret;
 		break;
 	case PPMU_PMNCNT3:
-		__raw_writel(PPMU_V2_EVT3_RW_DATA_CNT,
-				info->ppmu.base + PPMU_V2_CH_EVx_TYPE(id));
+		ret = regmap_write(info->regmap, PPMU_V2_CH_EVx_TYPE(id),
+				PPMU_V2_EVT3_RW_DATA_CNT);
+		if (ret < 0)
+			return ret;
 		break;
 	}
 
 	/* Reset cycle counter/performance counter and enable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_V2_PMNC);
+	ret = regmap_read(info->regmap, PPMU_V2_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~(PPMU_PMNC_ENABLE_MASK
 			| PPMU_PMNC_COUNTER_RESET_MASK
 			| PPMU_PMNC_CC_RESET_MASK
@@ -284,7 +400,10 @@ static int exynos_ppmu_v2_set_event(struct devfreq_event_dev *edev)
 	pmnc |= (PPMU_ENABLE << PPMU_PMNC_COUNTER_RESET_SHIFT);
 	pmnc |= (PPMU_ENABLE << PPMU_PMNC_CC_RESET_SHIFT);
 	pmnc |= (PPMU_V2_MODE_MANUAL << PPMU_V2_PMNC_START_MODE_SHIFT);
-	__raw_writel(pmnc, info->ppmu.base + PPMU_V2_PMNC);
+
+	ret = regmap_write(info->regmap, PPMU_V2_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -294,37 +413,61 @@ static int exynos_ppmu_v2_get_event(struct devfreq_event_dev *edev,
 {
 	struct exynos_ppmu *info = devfreq_event_get_drvdata(edev);
 	int id = exynos_ppmu_find_ppmu_id(edev);
-	u32 pmnc, cntenc;
-	u32 pmcnt_high, pmcnt_low;
-	u64 load_count = 0;
+	int ret;
+	unsigned int pmnc, cntenc;
+	unsigned int pmcnt_high, pmcnt_low;
+	unsigned int total_count, count;
+	unsigned long load_count = 0;
 
 	/* Disable PPMU */
-	pmnc = __raw_readl(info->ppmu.base + PPMU_V2_PMNC);
+	ret = regmap_read(info->regmap, PPMU_V2_PMNC, &pmnc);
+	if (ret < 0)
+		return ret;
+
 	pmnc &= ~PPMU_PMNC_ENABLE_MASK;
-	__raw_writel(pmnc, info->ppmu.base + PPMU_V2_PMNC);
+	ret = regmap_write(info->regmap, PPMU_V2_PMNC, pmnc);
+	if (ret < 0)
+		return ret;
 
 	/* Read cycle count and performance count */
-	edata->total_count = __raw_readl(info->ppmu.base + PPMU_V2_CCNT);
+	ret = regmap_read(info->regmap, PPMU_V2_CCNT, &total_count);
+	if (ret < 0)
+		return ret;
+	edata->total_count = total_count;
 
 	switch (id) {
 	case PPMU_PMNCNT0:
 	case PPMU_PMNCNT1:
 	case PPMU_PMNCNT2:
-		load_count = __raw_readl(info->ppmu.base + PPMU_V2_PMNCT(id));
+		ret = regmap_read(info->regmap, PPMU_V2_PMNCT(id), &count);
+		if (ret < 0)
+			return ret;
+		load_count = count;
 		break;
 	case PPMU_PMNCNT3:
-		pmcnt_high = __raw_readl(info->ppmu.base + PPMU_V2_PMCNT3_HIGH);
-		pmcnt_low = __raw_readl(info->ppmu.base + PPMU_V2_PMCNT3_LOW);
-		load_count = ((u64)((pmcnt_high & 0xff)) << 32)
-			   + (u64)pmcnt_low;
+		ret = regmap_read(info->regmap, PPMU_V2_PMCNT3_HIGH,
+						&pmcnt_high);
+		if (ret < 0)
+			return ret;
+
+		ret = regmap_read(info->regmap, PPMU_V2_PMCNT3_LOW, &pmcnt_low);
+		if (ret < 0)
+			return ret;
+
+		load_count = ((u64)((pmcnt_high & 0xff)) << 32)+ (u64)pmcnt_low;
 		break;
 	}
 	edata->load_count = load_count;
 
 	/* Disable all counters */
-	cntenc = __raw_readl(info->ppmu.base + PPMU_V2_CNTENC);
+	ret = regmap_read(info->regmap, PPMU_V2_CNTENC, &cntenc);
+	if (ret < 0)
+		return 0;
+
 	cntenc |= (PPMU_CCNT_MASK | (PPMU_ENABLE << id));
-	__raw_writel(cntenc, info->ppmu.base + PPMU_V2_CNTENC);
+	ret = regmap_write(info->regmap, PPMU_V2_CNTENC, cntenc);
+	if (ret < 0)
+		return ret;
 
 	dev_dbg(&edev->dev, "%25s (load: %ld / %ld)\n", edev->desc->name,
 					edata->load_count, edata->total_count);
@@ -411,10 +554,19 @@ static int of_get_devfreq_events(struct device_node *np,
 	return 0;
 }
 
-static int exynos_ppmu_parse_dt(struct exynos_ppmu *info)
+static struct regmap_config exynos_ppmu_regmap_config = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+};
+
+static int exynos_ppmu_parse_dt(struct platform_device *pdev,
+				struct exynos_ppmu *info)
 {
 	struct device *dev = info->dev;
 	struct device_node *np = dev->of_node;
+	struct resource *res;
+	void __iomem *base;
 	int ret = 0;
 
 	if (!np) {
@@ -423,10 +575,17 @@ static int exynos_ppmu_parse_dt(struct exynos_ppmu *info)
 	}
 
 	/* Maps the memory mapped IO to control PPMU register */
-	info->ppmu.base = of_iomap(np, 0);
-	if (IS_ERR_OR_NULL(info->ppmu.base)) {
-		dev_err(dev, "failed to map memory region\n");
-		return -ENOMEM;
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	exynos_ppmu_regmap_config.max_register = resource_size(res) - 4;
+	info->regmap = devm_regmap_init_mmio(dev, base,
+					&exynos_ppmu_regmap_config);
+	if (IS_ERR(info->regmap)) {
+		dev_err(dev, "failed to initialize regmap\n");
+		return PTR_ERR(info->regmap);
 	}
 
 	info->ppmu.clk = devm_clk_get(dev, "ppmu");
@@ -438,15 +597,10 @@ static int exynos_ppmu_parse_dt(struct exynos_ppmu *info)
 	ret = of_get_devfreq_events(np, info);
 	if (ret < 0) {
 		dev_err(dev, "failed to parse exynos ppmu dt node\n");
-		goto err;
+		return ret;
 	}
 
 	return 0;
-
-err:
-	iounmap(info->ppmu.base);
-
-	return ret;
 }
 
 static int exynos_ppmu_probe(struct platform_device *pdev)
@@ -463,7 +617,7 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 	info->dev = &pdev->dev;
 
 	/* Parse dt data to get resource */
-	ret = exynos_ppmu_parse_dt(info);
+	ret = exynos_ppmu_parse_dt(pdev, info);
 	if (ret < 0) {
 		dev_err(&pdev->dev,
 			"failed to parse devicetree for resource\n");
@@ -476,8 +630,7 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 	if (!info->edev) {
 		dev_err(&pdev->dev,
 			"failed to allocate memory devfreq-event devices\n");
-		ret = -ENOMEM;
-		goto err;
+		return -ENOMEM;
 	}
 	edev = info->edev;
 	platform_set_drvdata(pdev, info);
@@ -488,17 +641,16 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 			ret = PTR_ERR(edev[i]);
 			dev_err(&pdev->dev,
 				"failed to add devfreq-event device\n");
-			goto err;
+			return PTR_ERR(edev[i]);
 		}
+
+		pr_info("exynos-ppmu: new PPMU device registered %s (%s)\n",
+			dev_name(&pdev->dev), desc[i].name);
 	}
 
 	clk_prepare_enable(info->ppmu.clk);
 
 	return 0;
-err:
-	iounmap(info->ppmu.base);
-
-	return ret;
 }
 
 static int exynos_ppmu_remove(struct platform_device *pdev)
@@ -506,7 +658,6 @@ static int exynos_ppmu_remove(struct platform_device *pdev)
 	struct exynos_ppmu *info = platform_get_drvdata(pdev);
 
 	clk_disable_unprepare(info->ppmu.clk);
-	iounmap(info->ppmu.base);
 
 	return 0;
 }
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index 9af86f46fbec..49f68929e024 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -103,18 +103,17 @@ static int exynos_bus_target(struct device *dev, unsigned long *freq, u32 flags)
 	int ret = 0;
 
 	/* Get new opp-bus instance according to new bus clock */
-	rcu_read_lock();
 	new_opp = devfreq_recommended_opp(dev, freq, flags);
 	if (IS_ERR(new_opp)) {
 		dev_err(dev, "failed to get recommended opp instance\n");
-		rcu_read_unlock();
 		return PTR_ERR(new_opp);
 	}
 
 	new_freq = dev_pm_opp_get_freq(new_opp);
 	new_volt = dev_pm_opp_get_voltage(new_opp);
+	dev_pm_opp_put(new_opp);
+
 	old_freq = bus->curr_freq;
-	rcu_read_unlock();
 
 	if (old_freq == new_freq)
 		return 0;
@@ -147,8 +146,8 @@ static int exynos_bus_target(struct device *dev, unsigned long *freq, u32 flags)
 	}
 	bus->curr_freq = new_freq;
 
-	dev_dbg(dev, "Set the frequency of bus (%lukHz -> %lukHz)\n",
-			old_freq/1000, new_freq/1000);
+	dev_dbg(dev, "Set the frequency of bus (%luHz -> %luHz, %luHz)\n",
+			old_freq, new_freq, clk_get_rate(bus->clk));
 out:
 	mutex_unlock(&bus->lock);
 
@@ -214,17 +213,16 @@ static int exynos_bus_passive_target(struct device *dev, unsigned long *freq,
 	int ret = 0;
 
 	/* Get new opp-bus instance according to new bus clock */
-	rcu_read_lock();
 	new_opp = devfreq_recommended_opp(dev, freq, flags);
 	if (IS_ERR(new_opp)) {
 		dev_err(dev, "failed to get recommended opp instance\n");
-		rcu_read_unlock();
 		return PTR_ERR(new_opp);
 	}
 
 	new_freq = dev_pm_opp_get_freq(new_opp);
+	dev_pm_opp_put(new_opp);
+
 	old_freq = bus->curr_freq;
-	rcu_read_unlock();
 
 	if (old_freq == new_freq)
 		return 0;
@@ -241,8 +239,8 @@ static int exynos_bus_passive_target(struct device *dev, unsigned long *freq,
 	*freq = new_freq;
 	bus->curr_freq = new_freq;
 
-	dev_dbg(dev, "Set the frequency of bus (%lukHz -> %lukHz)\n",
-			old_freq/1000, new_freq/1000);
+	dev_dbg(dev, "Set the frequency of bus (%luHz -> %luHz, %luHz)\n",
+			old_freq, new_freq, clk_get_rate(bus->clk));
 out:
 	mutex_unlock(&bus->lock);
 
@@ -358,16 +356,14 @@ static int exynos_bus_parse_of(struct device_node *np,
 
 	rate = clk_get_rate(bus->clk);
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, &rate, 0);
 	if (IS_ERR(opp)) {
 		dev_err(dev, "failed to find dev_pm_opp\n");
-		rcu_read_unlock();
 		ret = PTR_ERR(opp);
 		goto err_opp;
 	}
 	bus->curr_freq = dev_pm_opp_get_freq(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	return 0;
 
diff --git a/drivers/devfreq/governor.h b/drivers/devfreq/governor.h
index fad7d6321978..71576b8bdfef 100644
--- a/drivers/devfreq/governor.h
+++ b/drivers/devfreq/governor.h
@@ -38,4 +38,6 @@ extern void devfreq_interval_update(struct devfreq *devfreq,
 extern int devfreq_add_governor(struct devfreq_governor *governor);
 extern int devfreq_remove_governor(struct devfreq_governor *governor);
 
+extern int devfreq_update_status(struct devfreq *devfreq, unsigned long freq);
+
 #endif /* _GOVERNOR_H */
diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c
index 9ef46e2592c4..673ad8cc9a1d 100644
--- a/drivers/devfreq/governor_passive.c
+++ b/drivers/devfreq/governor_passive.c
@@ -59,14 +59,14 @@ static int devfreq_passive_get_target_freq(struct devfreq *devfreq,
 	 * list of parent device. Because in this case, *freq is temporary
 	 * value which is decided by ondemand governor.
 	 */
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(parent_devfreq->dev.parent, freq, 0);
-	rcu_read_unlock();
 	if (IS_ERR(opp)) {
 		ret = PTR_ERR(opp);
 		goto out;
 	}
 
+	dev_pm_opp_put(opp);
+
 	/*
 	 * Get the OPP table's index of decided freqeuncy by governor
 	 * of parent device.
@@ -112,6 +112,11 @@ static int update_devfreq_passive(struct devfreq *devfreq, unsigned long freq)
 	if (ret < 0)
 		goto out;
 
+	if (devfreq->profile->freq_table
+		&& (devfreq_update_status(devfreq, freq)))
+		dev_err(&devfreq->dev,
+			"Couldn't update frequency transition information.\n");
+
 	devfreq->previous_freq = freq;
 
 out:
@@ -179,6 +184,7 @@ static int devfreq_passive_event_handler(struct devfreq *devfreq,
 
 static struct devfreq_governor devfreq_passive = {
 	.name = "passive",
+	.immutable = 1,
 	.get_target_freq = devfreq_passive_get_target_freq,
 	.event_handler = devfreq_passive_event_handler,
 };
diff --git a/drivers/devfreq/governor_userspace.c b/drivers/devfreq/governor_userspace.c
index 35de6e83c1fe..176976068bcd 100644
--- a/drivers/devfreq/governor_userspace.c
+++ b/drivers/devfreq/governor_userspace.c
@@ -1,5 +1,5 @@
 /*
- *  linux/drivers/devfreq/governor_simpleondemand.c
+ *  linux/drivers/devfreq/governor_userspace.c
  *
  *  Copyright (C) 2011 Samsung Electronics
  *	MyungJoo Ham <myungjoo.ham@samsung.com>
@@ -50,7 +50,6 @@ static ssize_t store_freq(struct device *dev, struct device_attribute *attr,
 	unsigned long wanted;
 	int err = 0;
 
-
 	mutex_lock(&devfreq->lock);
 	data = devfreq->data;
 
@@ -112,7 +111,13 @@ out:
 
 static void userspace_exit(struct devfreq *devfreq)
 {
-	sysfs_remove_group(&devfreq->dev.kobj, &dev_attr_group);
+	/*
+	 * Remove the sysfs entry, unless this is being called after
+	 * device_del(), which should have done this already via kobject_del().
+	 */
+	if (devfreq->dev.kobj.sd)
+		sysfs_remove_group(&devfreq->dev.kobj, &dev_attr_group);
+
 	kfree(devfreq->data);
 	devfreq->data = NULL;
 }
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 27d2f349b53c..40a2499730fc 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -91,17 +91,13 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 	unsigned long target_volt, target_rate;
 	int err;
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, freq, flags);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp))
 		return PTR_ERR(opp);
-	}
 
 	target_rate = dev_pm_opp_get_freq(opp);
 	target_volt = dev_pm_opp_get_voltage(opp);
-
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	if (dmcfreq->rate == target_rate)
 		return 0;
@@ -422,15 +418,13 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 
 	data->rate = clk_get_rate(data->dmc_clk);
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, &data->rate, 0);
-	if (IS_ERR(opp)) {
-		rcu_read_unlock();
+	if (IS_ERR(opp))
 		return PTR_ERR(opp);
-	}
+
 	data->rate = dev_pm_opp_get_freq(opp);
 	data->volt = dev_pm_opp_get_voltage(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	rk3399_devfreq_dmc_profile.initial_freq = data->rate;
 
diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c
index fe9dce0245bf..214fff96fa4a 100644
--- a/drivers/devfreq/tegra-devfreq.c
+++ b/drivers/devfreq/tegra-devfreq.c
@@ -487,15 +487,13 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq,
 	struct dev_pm_opp *opp;
 	unsigned long rate = *freq * KHZ;
 
-	rcu_read_lock();
 	opp = devfreq_recommended_opp(dev, &rate, flags);
 	if (IS_ERR(opp)) {
-		rcu_read_unlock();
 		dev_err(dev, "Failed to find opp for %lu KHz\n", *freq);
 		return PTR_ERR(opp);
 	}
 	rate = dev_pm_opp_get_freq(opp);
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	clk_set_min_rate(tegra->emc_clock, rate);
 	clk_set_rate(tegra->emc_clock, 0);
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index d5ba43a87a68..200828c60db9 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -153,6 +153,8 @@ struct cppi41_dd {
 
 	/* context for suspend/resume */
 	unsigned int dma_tdfdq;
+
+	bool is_suspended;
 };
 
 #define FIST_COMPLETION_QUEUE	93
@@ -257,6 +259,10 @@ static struct cppi41_channel *desc_to_chan(struct cppi41_dd *cdd, u32 desc)
 	BUG_ON(desc_num >= ALLOC_DECS_NUM);
 	c = cdd->chan_busy[desc_num];
 	cdd->chan_busy[desc_num] = NULL;
+
+	/* Usecount for chan_busy[], paired with push_desc_queue() */
+	pm_runtime_put(cdd->ddev.dev);
+
 	return c;
 }
 
@@ -317,12 +323,12 @@ static irqreturn_t cppi41_irq(int irq, void *data)
 
 		while (val) {
 			u32 desc, len;
-			int error;
 
-			error = pm_runtime_get(cdd->ddev.dev);
-			if (error < 0)
-				dev_err(cdd->ddev.dev, "%s pm runtime get: %i\n",
-					__func__, error);
+			/*
+			 * This should never trigger, see the comments in
+			 * push_desc_queue()
+			 */
+			WARN_ON(cdd->is_suspended);
 
 			q_num = __fls(val);
 			val &= ~(1 << q_num);
@@ -343,9 +349,6 @@ static irqreturn_t cppi41_irq(int irq, void *data)
 			c->residue = pd_trans_len(c->desc->pd6) - len;
 			dma_cookie_complete(&c->txd);
 			dmaengine_desc_get_callback_invoke(&c->txd, NULL);
-
-			pm_runtime_mark_last_busy(cdd->ddev.dev);
-			pm_runtime_put_autosuspend(cdd->ddev.dev);
 		}
 	}
 	return IRQ_HANDLED;
@@ -447,6 +450,15 @@ static void push_desc_queue(struct cppi41_channel *c)
 	 */
 	__iowmb();
 
+	/*
+	 * DMA transfers can take at least 200ms to complete with USB mass
+	 * storage connected. To prevent autosuspend timeouts, we must use
+	 * pm_runtime_get/put() when chan_busy[] is modified. This will get
+	 * cleared in desc_to_chan() or cppi41_stop_chan() depending on the
+	 * outcome of the transfer.
+	 */
+	pm_runtime_get(cdd->ddev.dev);
+
 	desc_phys = lower_32_bits(c->desc_phys);
 	desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc);
 	WARN_ON(cdd->chan_busy[desc_num]);
@@ -457,20 +469,26 @@ static void push_desc_queue(struct cppi41_channel *c)
 	cppi_writel(reg, cdd->qmgr_mem + QMGR_QUEUE_D(c->q_num));
 }
 
-static void pending_desc(struct cppi41_channel *c)
+/*
+ * Caller must hold cdd->lock to prevent push_desc_queue()
+ * getting called out of order. We have both cppi41_dma_issue_pending()
+ * and cppi41_runtime_resume() call this function.
+ */
+static void cppi41_run_queue(struct cppi41_dd *cdd)
 {
-	struct cppi41_dd *cdd = c->cdd;
-	unsigned long flags;
+	struct cppi41_channel *c, *_c;
 
-	spin_lock_irqsave(&cdd->lock, flags);
-	list_add_tail(&c->node, &cdd->pending);
-	spin_unlock_irqrestore(&cdd->lock, flags);
+	list_for_each_entry_safe(c, _c, &cdd->pending, node) {
+		push_desc_queue(c);
+		list_del(&c->node);
+	}
 }
 
 static void cppi41_dma_issue_pending(struct dma_chan *chan)
 {
 	struct cppi41_channel *c = to_cpp41_chan(chan);
 	struct cppi41_dd *cdd = c->cdd;
+	unsigned long flags;
 	int error;
 
 	error = pm_runtime_get(cdd->ddev.dev);
@@ -482,10 +500,11 @@ static void cppi41_dma_issue_pending(struct dma_chan *chan)
 		return;
 	}
 
-	if (likely(pm_runtime_active(cdd->ddev.dev)))
-		push_desc_queue(c);
-	else
-		pending_desc(c);
+	spin_lock_irqsave(&cdd->lock, flags);
+	list_add_tail(&c->node, &cdd->pending);
+	if (!cdd->is_suspended)
+		cppi41_run_queue(cdd);
+	spin_unlock_irqrestore(&cdd->lock, flags);
 
 	pm_runtime_mark_last_busy(cdd->ddev.dev);
 	pm_runtime_put_autosuspend(cdd->ddev.dev);
@@ -705,6 +724,9 @@ static int cppi41_stop_chan(struct dma_chan *chan)
 	WARN_ON(!cdd->chan_busy[desc_num]);
 	cdd->chan_busy[desc_num] = NULL;
 
+	/* Usecount for chan_busy[], paired with push_desc_queue() */
+	pm_runtime_put(cdd->ddev.dev);
+
 	return 0;
 }
 
@@ -1150,8 +1172,12 @@ static int __maybe_unused cppi41_resume(struct device *dev)
 static int __maybe_unused cppi41_runtime_suspend(struct device *dev)
 {
 	struct cppi41_dd *cdd = dev_get_drvdata(dev);
+	unsigned long flags;
 
+	spin_lock_irqsave(&cdd->lock, flags);
+	cdd->is_suspended = true;
 	WARN_ON(!list_empty(&cdd->pending));
+	spin_unlock_irqrestore(&cdd->lock, flags);
 
 	return 0;
 }
@@ -1159,14 +1185,11 @@ static int __maybe_unused cppi41_runtime_suspend(struct device *dev)
 static int __maybe_unused cppi41_runtime_resume(struct device *dev)
 {
 	struct cppi41_dd *cdd = dev_get_drvdata(dev);
-	struct cppi41_channel *c, *_c;
 	unsigned long flags;
 
 	spin_lock_irqsave(&cdd->lock, flags);
-	list_for_each_entry_safe(c, _c, &cdd->pending, node) {
-		push_desc_queue(c);
-		list_del(&c->node);
-	}
+	cdd->is_suspended = false;
+	cppi41_run_queue(cdd);
 	spin_unlock_irqrestore(&cdd->lock, flags);
 
 	return 0;
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 740bbb942594..f37f4978dabb 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -1699,7 +1699,6 @@ static bool _chan_ns(const struct pl330_dmac *pl330, int i)
 static struct pl330_thread *pl330_request_channel(struct pl330_dmac *pl330)
 {
 	struct pl330_thread *thrd = NULL;
-	unsigned long flags;
 	int chans, i;
 
 	if (pl330->state == DYING)
@@ -1707,8 +1706,6 @@ static struct pl330_thread *pl330_request_channel(struct pl330_dmac *pl330)
 
 	chans = pl330->pcfg.num_chan;
 
-	spin_lock_irqsave(&pl330->lock, flags);
-
 	for (i = 0; i < chans; i++) {
 		thrd = &pl330->channels[i];
 		if ((thrd->free) && (!_manager_ns(thrd) ||
@@ -1726,8 +1723,6 @@ static struct pl330_thread *pl330_request_channel(struct pl330_dmac *pl330)
 		thrd = NULL;
 	}
 
-	spin_unlock_irqrestore(&pl330->lock, flags);
-
 	return thrd;
 }
 
@@ -1745,7 +1740,6 @@ static inline void _free_event(struct pl330_thread *thrd, int ev)
 static void pl330_release_channel(struct pl330_thread *thrd)
 {
 	struct pl330_dmac *pl330;
-	unsigned long flags;
 
 	if (!thrd || thrd->free)
 		return;
@@ -1757,10 +1751,8 @@ static void pl330_release_channel(struct pl330_thread *thrd)
 
 	pl330 = thrd->dmac;
 
-	spin_lock_irqsave(&pl330->lock, flags);
 	_free_event(thrd, thrd->ev);
 	thrd->free = true;
-	spin_unlock_irqrestore(&pl330->lock, flags);
 }
 
 /* Initialize the structure for PL330 configuration, that can be used
@@ -1867,9 +1859,10 @@ static int dmac_alloc_resources(struct pl330_dmac *pl330)
 	 * Alloc MicroCode buffer for 'chans' Channel threads.
 	 * A channel's buffer offset is (Channel_Id * MCODE_BUFF_PERCHAN)
 	 */
-	pl330->mcode_cpu = dma_alloc_coherent(pl330->ddma.dev,
+	pl330->mcode_cpu = dma_alloc_attrs(pl330->ddma.dev,
 				chans * pl330->mcbufsz,
-				&pl330->mcode_bus, GFP_KERNEL);
+				&pl330->mcode_bus, GFP_KERNEL,
+				DMA_ATTR_PRIVILEGED);
 	if (!pl330->mcode_cpu) {
 		dev_err(pl330->ddma.dev, "%s:%d Can't allocate memory!\n",
 			__func__, __LINE__);
@@ -2122,20 +2115,20 @@ static int pl330_alloc_chan_resources(struct dma_chan *chan)
 	struct pl330_dmac *pl330 = pch->dmac;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pch->lock, flags);
+	spin_lock_irqsave(&pl330->lock, flags);
 
 	dma_cookie_init(chan);
 	pch->cyclic = false;
 
 	pch->thread = pl330_request_channel(pl330);
 	if (!pch->thread) {
-		spin_unlock_irqrestore(&pch->lock, flags);
+		spin_unlock_irqrestore(&pl330->lock, flags);
 		return -ENOMEM;
 	}
 
 	tasklet_init(&pch->task, pl330_tasklet, (unsigned long) pch);
 
-	spin_unlock_irqrestore(&pch->lock, flags);
+	spin_unlock_irqrestore(&pl330->lock, flags);
 
 	return 1;
 }
@@ -2238,12 +2231,13 @@ static int pl330_pause(struct dma_chan *chan)
 static void pl330_free_chan_resources(struct dma_chan *chan)
 {
 	struct dma_pl330_chan *pch = to_pchan(chan);
+	struct pl330_dmac *pl330 = pch->dmac;
 	unsigned long flags;
 
 	tasklet_kill(&pch->task);
 
 	pm_runtime_get_sync(pch->dmac->ddma.dev);
-	spin_lock_irqsave(&pch->lock, flags);
+	spin_lock_irqsave(&pl330->lock, flags);
 
 	pl330_release_channel(pch->thread);
 	pch->thread = NULL;
@@ -2251,7 +2245,7 @@ static void pl330_free_chan_resources(struct dma_chan *chan)
 	if (pch->cyclic)
 		list_splice_tail_init(&pch->work_list, &pch->dmac->desc_pool);
 
-	spin_unlock_irqrestore(&pch->lock, flags);
+	spin_unlock_irqrestore(&pl330->lock, flags);
 	pm_runtime_mark_last_busy(pch->dmac->ddma.dev);
 	pm_runtime_put_autosuspend(pch->dmac->ddma.dev);
 }
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 260251177830..82dab1692264 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -3065,6 +3065,8 @@ static bool ecc_enabled(struct pci_dev *F3, u16 nid)
 		/* Check whether at least one UMC is enabled: */
 		if (umc_en_mask)
 			ecc_en = umc_en_mask == ecc_en_mask;
+		else
+			edac_dbg(0, "Node %d: No enabled UMCs.\n", nid);
 
 		/* Assume UMC MCA banks are enabled. */
 		nb_mce_en = true;
@@ -3075,14 +3077,15 @@ static bool ecc_enabled(struct pci_dev *F3, u16 nid)
 
 		nb_mce_en = nb_mce_bank_enabled_on_node(nid);
 		if (!nb_mce_en)
-			amd64_notice("NB MCE bank disabled, set MSR 0x%08x[4] on node %d to enable.\n",
+			edac_dbg(0, "NB MCE bank disabled, set MSR 0x%08x[4] on node %d to enable.\n",
 				     MSR_IA32_MCG_CTL, nid);
 	}
 
-	amd64_info("DRAM ECC %s.\n", (ecc_en ? "enabled" : "disabled"));
+	amd64_info("Node %d: DRAM ECC %s.\n",
+		   nid, (ecc_en ? "enabled" : "disabled"));
 
 	if (!ecc_en || !nb_mce_en) {
-		amd64_notice("%s", ecc_msg);
+		amd64_info("%s", ecc_msg);
 		return false;
 	}
 	return true;
@@ -3300,15 +3303,6 @@ static int init_one_instance(unsigned int nid)
 		goto err_add_mc;
 	}
 
-	/* register stuff with EDAC MCE */
-	if (report_gart_errors)
-		amd_report_gart_errors(true);
-
-	if (pvt->umc)
-		amd_register_ecc_decoder(decode_umc_error);
-	else
-		amd_register_ecc_decoder(decode_bus_error);
-
 	return 0;
 
 err_add_mc:
@@ -3342,7 +3336,7 @@ static int probe_one_instance(unsigned int nid)
 	ecc_stngs[nid] = s;
 
 	if (!ecc_enabled(F3, nid)) {
-		ret = -ENODEV;
+		ret = 0;
 
 		if (!ecc_enable_override)
 			goto err_enable;
@@ -3363,6 +3357,8 @@ static int probe_one_instance(unsigned int nid)
 
 		if (boot_cpu_data.x86 < 0x17)
 			restore_ecc_error_reporting(s, nid, F3);
+
+		goto err_enable;
 	}
 
 	return ret;
@@ -3396,14 +3392,6 @@ static void remove_one_instance(unsigned int nid)
 
 	free_mc_sibling_devs(pvt);
 
-	/* unregister from EDAC MCE */
-	amd_report_gart_errors(false);
-
-	if (pvt->umc)
-		amd_unregister_ecc_decoder(decode_umc_error);
-	else
-		amd_unregister_ecc_decoder(decode_bus_error);
-
 	kfree(ecc_stngs[nid]);
 	ecc_stngs[nid] = NULL;
 
@@ -3452,8 +3440,11 @@ static int __init amd64_edac_init(void)
 	int err = -ENODEV;
 	int i;
 
+	if (!x86_match_cpu(amd64_cpuids))
+		return -ENODEV;
+
 	if (amd_cache_northbridges() < 0)
-		goto err_ret;
+		return -ENODEV;
 
 	opstate_init();
 
@@ -3466,14 +3457,30 @@ static int __init amd64_edac_init(void)
 	if (!msrs)
 		goto err_free;
 
-	for (i = 0; i < amd_nb_num(); i++)
-		if (probe_one_instance(i)) {
+	for (i = 0; i < amd_nb_num(); i++) {
+		err = probe_one_instance(i);
+		if (err) {
 			/* unwind properly */
 			while (--i >= 0)
 				remove_one_instance(i);
 
 			goto err_pci;
 		}
+	}
+
+	if (!edac_has_mcs()) {
+		err = -ENODEV;
+		goto err_pci;
+	}
+
+	/* register stuff with EDAC MCE */
+	if (report_gart_errors)
+		amd_report_gart_errors(true);
+
+	if (boot_cpu_data.x86 >= 0x17)
+		amd_register_ecc_decoder(decode_umc_error);
+	else
+		amd_register_ecc_decoder(decode_bus_error);
 
 	setup_pci_device();
 
@@ -3493,7 +3500,6 @@ err_free:
 	kfree(ecc_stngs);
 	ecc_stngs = NULL;
 
-err_ret:
 	return err;
 }
 
@@ -3504,6 +3510,14 @@ static void __exit amd64_edac_exit(void)
 	if (pci_ctl)
 		edac_pci_release_generic_ctl(pci_ctl);
 
+	/* unregister from EDAC MCE */
+	amd_report_gart_errors(false);
+
+	if (boot_cpu_data.x86 >= 0x17)
+		amd_unregister_ecc_decoder(decode_umc_error);
+	else
+		amd_unregister_ecc_decoder(decode_bus_error);
+
 	for (i = 0; i < amd_nb_num(); i++)
 		remove_one_instance(i);
 
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 496603d8f3d2..1d4b74e9a037 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -16,19 +16,14 @@
 #include <linux/slab.h>
 #include <linux/mmzone.h>
 #include <linux/edac.h>
+#include <asm/cpu_device_id.h>
 #include <asm/msr.h>
 #include "edac_module.h"
 #include "mce_amd.h"
 
-#define amd64_debug(fmt, arg...) \
-	edac_printk(KERN_DEBUG, "amd64", fmt, ##arg)
-
 #define amd64_info(fmt, arg...) \
 	edac_printk(KERN_INFO, "amd64", fmt, ##arg)
 
-#define amd64_notice(fmt, arg...) \
-	edac_printk(KERN_NOTICE, "amd64", fmt, ##arg)
-
 #define amd64_warn(fmt, arg...) \
 	edac_printk(KERN_WARNING, "amd64", "Warning: " fmt, ##arg)
 
@@ -90,7 +85,7 @@
  *         sections 3.5.4 and 3.5.5 for more information.
  */
 
-#define EDAC_AMD64_VERSION		"3.4.0"
+#define EDAC_AMD64_VERSION		"3.5.0"
 #define EDAC_MOD_STR			"amd64_edac"
 
 /* Extended Model from CPUID, for CPU Revision numbers */
diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c
index 750891ea07de..e5573c56b15e 100644
--- a/drivers/edac/edac_mc.c
+++ b/drivers/edac/edac_mc.c
@@ -453,6 +453,20 @@ void edac_mc_free(struct mem_ctl_info *mci)
 }
 EXPORT_SYMBOL_GPL(edac_mc_free);
 
+bool edac_has_mcs(void)
+{
+	bool ret;
+
+	mutex_lock(&mem_ctls_mutex);
+
+	ret = list_empty(&mc_devices);
+
+	mutex_unlock(&mem_ctls_mutex);
+
+	return !ret;
+}
+EXPORT_SYMBOL_GPL(edac_has_mcs);
+
 /* Caller must hold mem_ctls_mutex */
 static struct mem_ctl_info *__find_mci_by_dev(struct device *dev)
 {
diff --git a/drivers/edac/edac_mc.h b/drivers/edac/edac_mc.h
index 50fc1dc9c0d8..5357800e418d 100644
--- a/drivers/edac/edac_mc.h
+++ b/drivers/edac/edac_mc.h
@@ -149,6 +149,15 @@ extern int edac_mc_add_mc_with_groups(struct mem_ctl_info *mci,
 extern void edac_mc_free(struct mem_ctl_info *mci);
 
 /**
+ * edac_has_mcs() - Check if any MCs have been allocated.
+ *
+ * Returns:
+ *	True if MC instances have been registered successfully.
+ *	False otherwise.
+ */
+extern bool edac_has_mcs(void);
+
+/**
  * edac_mc_find() - Search for a mem_ctl_info structure whose index is @idx.
  *
  * @idx: index to be seek
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 39dbab7d62f1..445862dac273 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -569,6 +569,40 @@ static ssize_t dimmdev_edac_mode_show(struct device *dev,
 	return sprintf(data, "%s\n", edac_caps[dimm->edac_mode]);
 }
 
+static ssize_t dimmdev_ce_count_show(struct device *dev,
+				      struct device_attribute *mattr,
+				      char *data)
+{
+	struct dimm_info *dimm = to_dimm(dev);
+	u32 count;
+	int off;
+
+	off = EDAC_DIMM_OFF(dimm->mci->layers,
+			    dimm->mci->n_layers,
+			    dimm->location[0],
+			    dimm->location[1],
+			    dimm->location[2]);
+	count = dimm->mci->ce_per_layer[dimm->mci->n_layers-1][off];
+	return sprintf(data, "%u\n", count);
+}
+
+static ssize_t dimmdev_ue_count_show(struct device *dev,
+				      struct device_attribute *mattr,
+				      char *data)
+{
+	struct dimm_info *dimm = to_dimm(dev);
+	u32 count;
+	int off;
+
+	off = EDAC_DIMM_OFF(dimm->mci->layers,
+			    dimm->mci->n_layers,
+			    dimm->location[0],
+			    dimm->location[1],
+			    dimm->location[2]);
+	count = dimm->mci->ue_per_layer[dimm->mci->n_layers-1][off];
+	return sprintf(data, "%u\n", count);
+}
+
 /* dimm/rank attribute files */
 static DEVICE_ATTR(dimm_label, S_IRUGO | S_IWUSR,
 		   dimmdev_label_show, dimmdev_label_store);
@@ -577,6 +611,8 @@ static DEVICE_ATTR(size, S_IRUGO, dimmdev_size_show, NULL);
 static DEVICE_ATTR(dimm_mem_type, S_IRUGO, dimmdev_mem_type_show, NULL);
 static DEVICE_ATTR(dimm_dev_type, S_IRUGO, dimmdev_dev_type_show, NULL);
 static DEVICE_ATTR(dimm_edac_mode, S_IRUGO, dimmdev_edac_mode_show, NULL);
+static DEVICE_ATTR(dimm_ce_count, S_IRUGO, dimmdev_ce_count_show, NULL);
+static DEVICE_ATTR(dimm_ue_count, S_IRUGO, dimmdev_ue_count_show, NULL);
 
 /* attributes of the dimm<id>/rank<id> object */
 static struct attribute *dimm_attrs[] = {
@@ -586,6 +622,8 @@ static struct attribute *dimm_attrs[] = {
 	&dev_attr_dimm_mem_type.attr,
 	&dev_attr_dimm_dev_type.attr,
 	&dev_attr_dimm_edac_mode.attr,
+	&dev_attr_dimm_ce_count.attr,
+	&dev_attr_dimm_ue_count.attr,
 	NULL,
 };
 
@@ -831,7 +869,7 @@ static DEVICE_ATTR(ce_count, S_IRUGO, mci_ce_count_show, NULL);
 static DEVICE_ATTR(max_location, S_IRUGO, mci_max_location_show, NULL);
 
 /* memory scrubber attribute file */
-DEVICE_ATTR(sdram_scrub_rate, 0, mci_sdram_scrub_rate_show,
+static DEVICE_ATTR(sdram_scrub_rate, 0, mci_sdram_scrub_rate_show,
 	    mci_sdram_scrub_rate_store); /* umode set later in is_visible */
 
 static struct attribute *mci_attrs[] = {
diff --git a/drivers/edac/fsl_ddr_edac.c b/drivers/edac/fsl_ddr_edac.c
index 4e9608a958e7..efc8276d1d9c 100644
--- a/drivers/edac/fsl_ddr_edac.c
+++ b/drivers/edac/fsl_ddr_edac.c
@@ -145,12 +145,12 @@ static ssize_t fsl_mc_inject_ctrl_store(struct device *dev,
 	return 0;
 }
 
-DEVICE_ATTR(inject_data_hi, S_IRUGO | S_IWUSR,
-	    fsl_mc_inject_data_hi_show, fsl_mc_inject_data_hi_store);
-DEVICE_ATTR(inject_data_lo, S_IRUGO | S_IWUSR,
-	    fsl_mc_inject_data_lo_show, fsl_mc_inject_data_lo_store);
-DEVICE_ATTR(inject_ctrl, S_IRUGO | S_IWUSR,
-	    fsl_mc_inject_ctrl_show, fsl_mc_inject_ctrl_store);
+static DEVICE_ATTR(inject_data_hi, S_IRUGO | S_IWUSR,
+		   fsl_mc_inject_data_hi_show, fsl_mc_inject_data_hi_store);
+static DEVICE_ATTR(inject_data_lo, S_IRUGO | S_IWUSR,
+		   fsl_mc_inject_data_lo_show, fsl_mc_inject_data_lo_store);
+static DEVICE_ATTR(inject_ctrl, S_IRUGO | S_IWUSR,
+		   fsl_mc_inject_ctrl_show, fsl_mc_inject_ctrl_store);
 
 static struct attribute *fsl_ddr_dev_attrs[] = {
 	&dev_attr_inject_data_hi.attr,
diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index 0a912bf6de00..e391f5a716be 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -304,7 +304,6 @@ static const char *ferr_global_lo_name[] = {
 #define REDMEMA		0xdc
 
 #define REDMEMB		0x7c
-  #define IS_SECOND_CH(v)	((v) * (1 << 17))
 
 #define RECMEMA		0xe0
   #define RECMEMA_BANK(v)	(((v) >> 12) & 7)
@@ -483,8 +482,9 @@ static void i7300_process_fbd_error(struct mem_ctl_info *mci)
 		pci_read_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
 				     REDMEMB, &value);
 		channel = (branch << 1);
-		if (IS_SECOND_CH(value))
-			channel++;
+
+		/* Second channel ? */
+		channel += !!(value & BIT(17));
 
 		/* Clear the error bit */
 		pci_write_config_dword(pvt->pci_dev_16_1_fsb_addr_map,
diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 69b5adead0ad..75ad847593b7 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1835,6 +1835,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 static struct notifier_block i7_mce_dec = {
 	.notifier_call	= i7core_mce_check_error,
+	.priority	= MCE_PRIO_EDAC,
 };
 
 struct memdev_dmi_entry {
diff --git a/drivers/edac/i82975x_edac.c b/drivers/edac/i82975x_edac.c
index 7baa8ace267b..9dcdab28f665 100644
--- a/drivers/edac/i82975x_edac.c
+++ b/drivers/edac/i82975x_edac.c
@@ -494,6 +494,10 @@ static int i82975x_probe1(struct pci_dev *pdev, int dev_idx)
 	}
 	mchbar &= 0xffffc000;	/* bits 31:14 used for 16K window */
 	mch_window = ioremap_nocache(mchbar, 0x1000);
+	if (!mch_window) {
+		edac_dbg(3, "error ioremapping MCHBAR!\n");
+		goto fail0;
+	}
 
 #ifdef i82975x_DEBUG_IOMEM
 	i82975x_printk(KERN_INFO, "MCHBAR real = %0x, remapped = %p\n",
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 34208f38c5b1..ba35b7ea3686 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -937,12 +937,13 @@ static const char *decode_error_status(struct mce *m)
 	}
 
 	if (m->status & MCI_STATUS_DEFERRED)
-		return "Deferred error.";
+		return "Deferred error, no action required.";
 
 	return "Corrected error, no action required.";
 }
 
-int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
+static int
+amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 {
 	struct mce *m = (struct mce *)data;
 	struct cpuinfo_x86 *c = &cpu_data(m->extcpu);
@@ -991,20 +992,22 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	pr_cont("]: 0x%016llx\n", m->status);
 
 	if (m->status & MCI_STATUS_ADDRV)
-		pr_emerg(HW_ERR "Error Addr: 0x%016llx", m->addr);
+		pr_emerg(HW_ERR "Error Addr: 0x%016llx\n", m->addr);
 
 	if (boot_cpu_has(X86_FEATURE_SMCA)) {
+		pr_emerg(HW_ERR "IPID: 0x%016llx", m->ipid);
+
 		if (m->status & MCI_STATUS_SYNDV)
 			pr_cont(", Syndrome: 0x%016llx", m->synd);
 
-		pr_cont(", IPID: 0x%016llx", m->ipid);
-
 		pr_cont("\n");
 
 		decode_smca_errors(m);
 		goto err_code;
-	} else
-		pr_cont("\n");
+	}
+
+	if (m->tsc)
+		pr_emerg(HW_ERR "TSC: %llu\n", m->tsc);
 
 	if (!fam_ops)
 		goto err_code;
@@ -1047,10 +1050,10 @@ int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 
 	return NOTIFY_STOP;
 }
-EXPORT_SYMBOL_GPL(amd_decode_mce);
 
 static struct notifier_block amd_mce_dec_nb = {
 	.notifier_call	= amd_decode_mce,
+	.priority	= MCE_PRIO_EDAC,
 };
 
 static int __init mce_amd_init(void)
diff --git a/drivers/edac/mce_amd.h b/drivers/edac/mce_amd.h
index c2359a1ea6b3..0b6a68673e0e 100644
--- a/drivers/edac/mce_amd.h
+++ b/drivers/edac/mce_amd.h
@@ -79,6 +79,5 @@ struct amd_decoder_ops {
 void amd_report_gart_errors(bool);
 void amd_register_ecc_decoder(void (*f)(int, struct mce *));
 void amd_unregister_ecc_decoder(void (*f)(int, struct mce *));
-int amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data);
 
 #endif /* _EDAC_MCE_AMD_H */
diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c
index 8f66cbed70b7..67f7bc3fe5b3 100644
--- a/drivers/edac/mpc85xx_edac.c
+++ b/drivers/edac/mpc85xx_edac.c
@@ -629,6 +629,7 @@ static const struct of_device_id mpc85xx_l2_err_of_match[] = {
 	{ .compatible = "fsl,p1020-l2-cache-controller", },
 	{ .compatible = "fsl,p1021-l2-cache-controller", },
 	{ .compatible = "fsl,p2020-l2-cache-controller", },
+	{ .compatible = "fsl,t2080-l2-cache-controller", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, mpc85xx_l2_err_of_match);
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 54ae6dc45ab2..a65ea44e3b0b 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -304,7 +304,6 @@ struct sbridge_info {
 	u64		(*rir_limit)(u32 reg);
 	u64		(*sad_limit)(u32 reg);
 	u32		(*interleave_mode)(u32 reg);
-	char*		(*show_interleave_mode)(u32 reg);
 	u32		(*dram_attr)(u32 reg);
 	const u32	*dram_rule;
 	const u32	*interleave_list;
@@ -811,11 +810,6 @@ static u32 interleave_mode(u32 reg)
 	return GET_BITFIELD(reg, 1, 1);
 }
 
-char *show_interleave_mode(u32 reg)
-{
-	return interleave_mode(reg) ? "8:6" : "[8:6]XOR[18:16]";
-}
-
 static u32 dram_attr(u32 reg)
 {
 	return GET_BITFIELD(reg, 2, 3);
@@ -831,29 +825,16 @@ static u32 knl_interleave_mode(u32 reg)
 	return GET_BITFIELD(reg, 1, 2);
 }
 
-static char *knl_show_interleave_mode(u32 reg)
-{
-	char *s;
-
-	switch (knl_interleave_mode(reg)) {
-	case 0:
-		s = "use address bits [8:6]";
-		break;
-	case 1:
-		s = "use address bits [10:8]";
-		break;
-	case 2:
-		s = "use address bits [14:12]";
-		break;
-	case 3:
-		s = "use address bits [32:30]";
-		break;
-	default:
-		WARN_ON(1);
-		break;
-	}
+static const char * const knl_intlv_mode[] = {
+	"[8:6]", "[10:8]", "[14:12]", "[32:30]"
+};
 
-	return s;
+static const char *get_intlv_mode_str(u32 reg, enum type t)
+{
+	if (t == KNIGHTS_LANDING)
+		return knl_intlv_mode[knl_interleave_mode(reg)];
+	else
+		return interleave_mode(reg) ? "[8:6]" : "[8:6]XOR[18:16]";
 }
 
 static u32 dram_attr_knl(u32 reg)
@@ -1810,7 +1791,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 			 show_dram_attr(pvt->info.dram_attr(reg)),
 			 gb, (mb*1000)/1024,
 			 ((u64)tmp_mb) << 20L,
-			 pvt->info.show_interleave_mode(reg),
+			 get_intlv_mode_str(reg, pvt->info.type),
 			 reg);
 		prv = limit;
 
@@ -3136,7 +3117,8 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 }
 
 static struct notifier_block sbridge_mce_dec = {
-	.notifier_call      = sbridge_mce_check_error,
+	.notifier_call	= sbridge_mce_check_error,
+	.priority	= MCE_PRIO_EDAC,
 };
 
 /****************************************************************************
@@ -3227,7 +3209,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type)
 		pvt->info.rir_limit = rir_limit;
 		pvt->info.sad_limit = sad_limit;
 		pvt->info.interleave_mode = interleave_mode;
-		pvt->info.show_interleave_mode = show_interleave_mode;
 		pvt->info.dram_attr = dram_attr;
 		pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule);
 		pvt->info.interleave_list = ibridge_interleave_list;
@@ -3251,7 +3232,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type)
 		pvt->info.rir_limit = rir_limit;
 		pvt->info.sad_limit = sad_limit;
 		pvt->info.interleave_mode = interleave_mode;
-		pvt->info.show_interleave_mode = show_interleave_mode;
 		pvt->info.dram_attr = dram_attr;
 		pvt->info.max_sad = ARRAY_SIZE(sbridge_dram_rule);
 		pvt->info.interleave_list = sbridge_interleave_list;
@@ -3275,7 +3255,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type)
 		pvt->info.rir_limit = haswell_rir_limit;
 		pvt->info.sad_limit = sad_limit;
 		pvt->info.interleave_mode = interleave_mode;
-		pvt->info.show_interleave_mode = show_interleave_mode;
 		pvt->info.dram_attr = dram_attr;
 		pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule);
 		pvt->info.interleave_list = ibridge_interleave_list;
@@ -3299,7 +3278,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type)
 		pvt->info.rir_limit = haswell_rir_limit;
 		pvt->info.sad_limit = sad_limit;
 		pvt->info.interleave_mode = interleave_mode;
-		pvt->info.show_interleave_mode = show_interleave_mode;
 		pvt->info.dram_attr = dram_attr;
 		pvt->info.max_sad = ARRAY_SIZE(ibridge_dram_rule);
 		pvt->info.interleave_list = ibridge_interleave_list;
@@ -3323,7 +3301,6 @@ static int sbridge_register_mci(struct sbridge_dev *sbridge_dev, enum type type)
 		pvt->info.rir_limit = NULL;
 		pvt->info.sad_limit = knl_sad_limit;
 		pvt->info.interleave_mode = knl_interleave_mode;
-		pvt->info.show_interleave_mode = knl_show_interleave_mode;
 		pvt->info.dram_attr = dram_attr_knl;
 		pvt->info.max_sad = ARRAY_SIZE(knl_dram_rule);
 		pvt->info.interleave_list = knl_interleave_list;
diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c
index 79ef675e4d6f..1159dba4671f 100644
--- a/drivers/edac/skx_edac.c
+++ b/drivers/edac/skx_edac.c
@@ -1007,7 +1007,8 @@ static int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 }
 
 static struct notifier_block skx_mce_dec = {
-	.notifier_call = skx_mce_check_error,
+	.notifier_call	= skx_mce_check_error,
+	.priority	= MCE_PRIO_EDAC,
 };
 
 static void skx_remove(void)
diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index f853ad2c4ca0..1027d7b44358 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -250,7 +250,6 @@ void __init efi_init(void)
 	}
 
 	reserve_regions();
-	efi_memattr_init();
 	efi_esrt_init();
 	efi_memmap_unmap();
 
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 92914801e388..e7d404059b73 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -529,6 +529,8 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz,
 		}
 	}
 
+	efi_memattr_init();
+
 	/* Parse the EFI Properties table if it exists */
 	if (efi.properties_table != EFI_INVALID_TABLE_ADDR) {
 		efi_properties_table_t *tbl;
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 14914074f716..08b026864d4e 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -269,7 +269,7 @@ void __init efi_esrt_init(void)
 	max -= efi.esrt;
 
 	if (max < size) {
-		pr_err("ESRT header doen't fit on single memory map entry. (size: %zu max: %zu)\n",
+		pr_err("ESRT header doesn't fit on single memory map entry. (size: %zu max: %zu)\n",
 		       size, max);
 		return;
 	}
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index d564d25df8ab..f7425960f6a5 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -11,7 +11,7 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -O2 \
 				   -mno-mmx -mno-sse
 
 cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS))
-cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -g0 \
+cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
 				   -fno-builtin -fpic -mno-single-pic-base
 
 cflags-$(CONFIG_EFI_ARMSTUB)	+= -I$(srctree)/scripts/dtc/libfdt
@@ -28,7 +28,7 @@ OBJECT_FILES_NON_STANDARD	:= y
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
 KCOV_INSTRUMENT			:= n
 
-lib-y				:= efi-stub-helper.o gop.o
+lib-y				:= efi-stub-helper.o gop.o secureboot.o
 
 # include the stub's generic dependencies from lib/ when building for ARM/arm64
 arm-deps := fdt_rw.c fdt_ro.c fdt_wip.c fdt.c fdt_empty_tree.c fdt_sw.c sort.c
@@ -60,7 +60,7 @@ CFLAGS_arm64-stub.o 		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 extra-$(CONFIG_EFI_ARMSTUB)	:= $(lib-y)
 lib-$(CONFIG_EFI_ARMSTUB)	:= $(patsubst %.o,%.stub.o,$(lib-y))
 
-STUBCOPY_FLAGS-y		:= -R .debug* -R *ksymtab* -R *kcrctab*
+STUBCOPY_RM-y			:= -R *ksymtab* -R *kcrctab*
 STUBCOPY_FLAGS-$(CONFIG_ARM64)	+= --prefix-alloc-sections=.init \
 				   --prefix-symbols=__efistub_
 STUBCOPY_RELOC-$(CONFIG_ARM64)	:= R_AARCH64_ABS
@@ -68,17 +68,25 @@ STUBCOPY_RELOC-$(CONFIG_ARM64)	:= R_AARCH64_ABS
 $(obj)/%.stub.o: $(obj)/%.o FORCE
 	$(call if_changed,stubcopy)
 
+#
+# Strip debug sections and some other sections that may legally contain
+# absolute relocations, so that we can inspect the remaining sections for
+# such relocations. If none are found, regenerate the output object, but
+# this time, use objcopy and leave all sections in place.
+#
 quiet_cmd_stubcopy = STUBCPY $@
-      cmd_stubcopy = if $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@; then	\
-		     $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y)	\
-		     && (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \
-			 rm -f $@; /bin/false); else /bin/false; fi
+      cmd_stubcopy = if $(STRIP) --strip-debug $(STUBCOPY_RM-y) -o $@ $<; \
+		     then if $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y); \
+		     then (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \
+			   rm -f $@; /bin/false); 			  \
+		     else $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@; fi	  \
+		     else /bin/false; fi
 
 #
 # ARM discards the .data section because it disallows r/w data in the
 # decompressor. So move our .data to .data.efistub, which is preserved
 # explicitly by the decompressor linker script.
 #
-STUBCOPY_FLAGS-$(CONFIG_ARM)	+= --rename-section .data=.data.efistub \
-				   -R ___ksymtab+sort -R ___kcrctab+sort
+STUBCOPY_FLAGS-$(CONFIG_ARM)	+= --rename-section .data=.data.efistub
+STUBCOPY_RM-$(CONFIG_ARM)	+= -R ___ksymtab+sort -R ___kcrctab+sort
 STUBCOPY_RELOC-$(CONFIG_ARM)	:= R_ARM_ABS
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index b4f7d78f9e8b..d4056c6be1ec 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -20,52 +20,6 @@
 
 bool __nokaslr;
 
-static int efi_get_secureboot(efi_system_table_t *sys_table_arg)
-{
-	static efi_char16_t const sb_var_name[] = {
-		'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0 };
-	static efi_char16_t const sm_var_name[] = {
-		'S', 'e', 't', 'u', 'p', 'M', 'o', 'd', 'e', 0 };
-
-	efi_guid_t var_guid = EFI_GLOBAL_VARIABLE_GUID;
-	efi_get_variable_t *f_getvar = sys_table_arg->runtime->get_variable;
-	u8 val;
-	unsigned long size = sizeof(val);
-	efi_status_t status;
-
-	status = f_getvar((efi_char16_t *)sb_var_name, (efi_guid_t *)&var_guid,
-			  NULL, &size, &val);
-
-	if (status != EFI_SUCCESS)
-		goto out_efi_err;
-
-	if (val == 0)
-		return 0;
-
-	status = f_getvar((efi_char16_t *)sm_var_name, (efi_guid_t *)&var_guid,
-			  NULL, &size, &val);
-
-	if (status != EFI_SUCCESS)
-		goto out_efi_err;
-
-	if (val == 1)
-		return 0;
-
-	return 1;
-
-out_efi_err:
-	switch (status) {
-	case EFI_NOT_FOUND:
-		return 0;
-	case EFI_DEVICE_ERROR:
-		return -EIO;
-	case EFI_SECURITY_VIOLATION:
-		return -EACCES;
-	default:
-		return -EINVAL;
-	}
-}
-
 efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
 			     void *__image, void **__fh)
 {
@@ -91,75 +45,6 @@ efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
 	return status;
 }
 
-efi_status_t efi_file_close(void *handle)
-{
-	efi_file_handle_t *fh = handle;
-
-	return fh->close(handle);
-}
-
-efi_status_t
-efi_file_read(void *handle, unsigned long *size, void *addr)
-{
-	efi_file_handle_t *fh = handle;
-
-	return fh->read(handle, size, addr);
-}
-
-
-efi_status_t
-efi_file_size(efi_system_table_t *sys_table_arg, void *__fh,
-	      efi_char16_t *filename_16, void **handle, u64 *file_sz)
-{
-	efi_file_handle_t *h, *fh = __fh;
-	efi_file_info_t *info;
-	efi_status_t status;
-	efi_guid_t info_guid = EFI_FILE_INFO_ID;
-	unsigned long info_sz;
-
-	status = fh->open(fh, &h, filename_16, EFI_FILE_MODE_READ, (u64)0);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table_arg, "Failed to open file: ");
-		efi_char16_printk(sys_table_arg, filename_16);
-		efi_printk(sys_table_arg, "\n");
-		return status;
-	}
-
-	*handle = h;
-
-	info_sz = 0;
-	status = h->get_info(h, &info_guid, &info_sz, NULL);
-	if (status != EFI_BUFFER_TOO_SMALL) {
-		efi_printk(sys_table_arg, "Failed to get file info size\n");
-		return status;
-	}
-
-grow:
-	status = sys_table_arg->boottime->allocate_pool(EFI_LOADER_DATA,
-				 info_sz, (void **)&info);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table_arg, "Failed to alloc mem for file info\n");
-		return status;
-	}
-
-	status = h->get_info(h, &info_guid, &info_sz,
-						   info);
-	if (status == EFI_BUFFER_TOO_SMALL) {
-		sys_table_arg->boottime->free_pool(info);
-		goto grow;
-	}
-
-	*file_sz = info->file_size;
-	sys_table_arg->boottime->free_pool(info);
-
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table_arg, "Failed to get initrd info\n");
-
-	return status;
-}
-
-
-
 void efi_char16_printk(efi_system_table_t *sys_table_arg,
 			      efi_char16_t *str)
 {
@@ -226,7 +111,7 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 	efi_guid_t loaded_image_proto = LOADED_IMAGE_PROTOCOL_GUID;
 	unsigned long reserve_addr = 0;
 	unsigned long reserve_size = 0;
-	int secure_boot = 0;
+	enum efi_secureboot_mode secure_boot;
 	struct screen_info *si;
 
 	/* Check if we were booted by the EFI firmware */
@@ -296,19 +181,14 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 		pr_efi_err(sys_table, "Failed to parse EFI cmdline options\n");
 
 	secure_boot = efi_get_secureboot(sys_table);
-	if (secure_boot > 0)
-		pr_efi(sys_table, "UEFI Secure Boot is enabled.\n");
-
-	if (secure_boot < 0) {
-		pr_efi_err(sys_table,
-			"could not determine UEFI Secure Boot status.\n");
-	}
 
 	/*
-	 * Unauthenticated device tree data is a security hazard, so
-	 * ignore 'dtb=' unless UEFI Secure Boot is disabled.
+	 * Unauthenticated device tree data is a security hazard, so ignore
+	 * 'dtb=' unless UEFI Secure Boot is disabled.  We assume that secure
+	 * boot is enabled if we can't determine its state.
 	 */
-	if (secure_boot != 0 && strstr(cmdline_ptr, "dtb=")) {
+	if (secure_boot != efi_secureboot_mode_disabled &&
+	    strstr(cmdline_ptr, "dtb=")) {
 		pr_efi(sys_table, "Ignoring DTB from command line.\n");
 	} else {
 		status = handle_cmdline_files(sys_table, image, cmdline_ptr,
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 757badc1debb..919822b7773d 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -338,6 +338,69 @@ void efi_free(efi_system_table_t *sys_table_arg, unsigned long size,
 	efi_call_early(free_pages, addr, nr_pages);
 }
 
+static efi_status_t efi_file_size(efi_system_table_t *sys_table_arg, void *__fh,
+				  efi_char16_t *filename_16, void **handle,
+				  u64 *file_sz)
+{
+	efi_file_handle_t *h, *fh = __fh;
+	efi_file_info_t *info;
+	efi_status_t status;
+	efi_guid_t info_guid = EFI_FILE_INFO_ID;
+	unsigned long info_sz;
+
+	status = efi_call_proto(efi_file_handle, open, fh, &h, filename_16,
+				EFI_FILE_MODE_READ, (u64)0);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table_arg, "Failed to open file: ");
+		efi_char16_printk(sys_table_arg, filename_16);
+		efi_printk(sys_table_arg, "\n");
+		return status;
+	}
+
+	*handle = h;
+
+	info_sz = 0;
+	status = efi_call_proto(efi_file_handle, get_info, h, &info_guid,
+				&info_sz, NULL);
+	if (status != EFI_BUFFER_TOO_SMALL) {
+		efi_printk(sys_table_arg, "Failed to get file info size\n");
+		return status;
+	}
+
+grow:
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				info_sz, (void **)&info);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table_arg, "Failed to alloc mem for file info\n");
+		return status;
+	}
+
+	status = efi_call_proto(efi_file_handle, get_info, h, &info_guid,
+				&info_sz, info);
+	if (status == EFI_BUFFER_TOO_SMALL) {
+		efi_call_early(free_pool, info);
+		goto grow;
+	}
+
+	*file_sz = info->file_size;
+	efi_call_early(free_pool, info);
+
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table_arg, "Failed to get initrd info\n");
+
+	return status;
+}
+
+static efi_status_t efi_file_read(void *handle, unsigned long *size, void *addr)
+{
+	return efi_call_proto(efi_file_handle, read, handle, size, addr);
+}
+
+static efi_status_t efi_file_close(void *handle)
+{
+	return efi_call_proto(efi_file_handle, close, handle);
+}
+
 /*
  * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi=
  * option, e.g. efi=nochunk.
@@ -351,6 +414,14 @@ efi_status_t efi_parse_options(char *cmdline)
 	char *str;
 
 	/*
+	 * Currently, the only efi= option we look for is 'nochunk', which
+	 * is intended to work around known issues on certain x86 UEFI
+	 * versions. So ignore for now on other architectures.
+	 */
+	if (!IS_ENABLED(CONFIG_X86))
+		return EFI_SUCCESS;
+
+	/*
 	 * If no EFI parameters were specified on the cmdline we've got
 	 * nothing to do.
 	 */
@@ -523,7 +594,8 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
 			size = files[j].size;
 			while (size) {
 				unsigned long chunksize;
-				if (size > __chunk_size)
+
+				if (IS_ENABLED(CONFIG_X86) && size > __chunk_size)
 					chunksize = __chunk_size;
 				else
 					chunksize = size;
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index 0e2a96b12cb3..71c4d0e3c4ed 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -29,14 +29,6 @@ void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
 			     void **__fh);
 
-efi_status_t efi_file_size(efi_system_table_t *sys_table_arg, void *__fh,
-			   efi_char16_t *filename_16, void **handle,
-			   u64 *file_sz);
-
-efi_status_t efi_file_read(void *handle, unsigned long *size, void *addr);
-
-efi_status_t efi_file_close(void *handle);
-
 unsigned long get_dram_base(efi_system_table_t *sys_table_arg);
 
 efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
diff --git a/drivers/firmware/efi/libstub/fdt.c b/drivers/firmware/efi/libstub/fdt.c
index 921dfa047202..260c4b4b492e 100644
--- a/drivers/firmware/efi/libstub/fdt.c
+++ b/drivers/firmware/efi/libstub/fdt.c
@@ -187,6 +187,7 @@ static efi_status_t update_fdt_memmap(void *fdt, struct efi_boot_memmap *map)
 struct exit_boot_struct {
 	efi_memory_desc_t *runtime_map;
 	int *runtime_entry_count;
+	void *new_fdt_addr;
 };
 
 static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
@@ -202,7 +203,7 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
 	efi_get_virtmap(*map->map, *map->map_size, *map->desc_size,
 			p->runtime_map, p->runtime_entry_count);
 
-	return EFI_SUCCESS;
+	return update_fdt_memmap(p->new_fdt_addr, map);
 }
 
 /*
@@ -300,22 +301,13 @@ efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
 
 	priv.runtime_map = runtime_map;
 	priv.runtime_entry_count = &runtime_entry_count;
+	priv.new_fdt_addr = (void *)*new_fdt_addr;
 	status = efi_exit_boot_services(sys_table, handle, &map, &priv,
 					exit_boot_func);
 
 	if (status == EFI_SUCCESS) {
 		efi_set_virtual_address_map_t *svam;
 
-		status = update_fdt_memmap((void *)*new_fdt_addr, &map);
-		if (status != EFI_SUCCESS) {
-			/*
-			 * The kernel won't get far without the memory map, but
-			 * may still be able to print something meaningful so
-			 * return success here.
-			 */
-			return EFI_SUCCESS;
-		}
-
 		/* Install the new virtual address map */
 		svam = sys_table->runtime->set_virtual_address_map;
 		status = svam(runtime_entry_count * desc_size, desc_size,
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
new file mode 100644
index 000000000000..6def402bf569
--- /dev/null
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -0,0 +1,84 @@
+/*
+ * Secure boot handling.
+ *
+ * Copyright (C) 2013,2014 Linaro Limited
+ *     Roy Franz <roy.franz@linaro.org
+ * Copyright (C) 2013 Red Hat, Inc.
+ *     Mark Salter <msalter@redhat.com>
+ *
+ * This file is part of the Linux kernel, and is made available under the
+ * terms of the GNU General Public License version 2.
+ */
+#include <linux/efi.h>
+#include <asm/efi.h>
+
+/* BIOS variables */
+static const efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
+static const efi_char16_t const efi_SecureBoot_name[] = {
+	'S', 'e', 'c', 'u', 'r', 'e', 'B', 'o', 'o', 't', 0
+};
+static const efi_char16_t const efi_SetupMode_name[] = {
+	'S', 'e', 't', 'u', 'p', 'M', 'o', 'd', 'e', 0
+};
+
+/* SHIM variables */
+static const efi_guid_t shim_guid = EFI_SHIM_LOCK_GUID;
+static efi_char16_t const shim_MokSBState_name[] = {
+	'M', 'o', 'k', 'S', 'B', 'S', 't', 'a', 't', 'e', 0
+};
+
+#define get_efi_var(name, vendor, ...) \
+	efi_call_runtime(get_variable, \
+			 (efi_char16_t *)(name), (efi_guid_t *)(vendor), \
+			 __VA_ARGS__);
+
+/*
+ * Determine whether we're in secure boot mode.
+ */
+enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg)
+{
+	u32 attr;
+	u8 secboot, setupmode, moksbstate;
+	unsigned long size;
+	efi_status_t status;
+
+	size = sizeof(secboot);
+	status = get_efi_var(efi_SecureBoot_name, &efi_variable_guid,
+			     NULL, &size, &secboot);
+	if (status != EFI_SUCCESS)
+		goto out_efi_err;
+
+	size = sizeof(setupmode);
+	status = get_efi_var(efi_SetupMode_name, &efi_variable_guid,
+			     NULL, &size, &setupmode);
+	if (status != EFI_SUCCESS)
+		goto out_efi_err;
+
+	if (secboot == 0 || setupmode == 1)
+		return efi_secureboot_mode_disabled;
+
+	/*
+	 * See if a user has put the shim into insecure mode. If so, and if the
+	 * variable doesn't have the runtime attribute set, we might as well
+	 * honor that.
+	 */
+	size = sizeof(moksbstate);
+	status = get_efi_var(shim_MokSBState_name, &shim_guid,
+			     &attr, &size, &moksbstate);
+
+	/* If it fails, we don't care why. Default to secure */
+	if (status != EFI_SUCCESS)
+		goto secure_boot_enabled;
+	if (!(attr & EFI_VARIABLE_RUNTIME_ACCESS) && moksbstate == 1)
+		return efi_secureboot_mode_disabled;
+
+secure_boot_enabled:
+	pr_efi(sys_table_arg, "UEFI Secure Boot is enabled.\n");
+	return efi_secureboot_mode_enabled;
+
+out_efi_err:
+	pr_efi_err(sys_table_arg, "Could not determine UEFI Secure Boot status.\n");
+	if (status == EFI_NOT_FOUND)
+		return efi_secureboot_mode_disabled;
+	return efi_secureboot_mode_unknown;
+}
diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c
index 236004b9a50d..8986757eafaf 100644
--- a/drivers/firmware/efi/memattr.c
+++ b/drivers/firmware/efi/memattr.c
@@ -43,6 +43,7 @@ int __init efi_memattr_init(void)
 
 	tbl_size = sizeof(*tbl) + tbl->num_entries * tbl->desc_size;
 	memblock_reserve(efi.mem_attr_table, tbl_size);
+	set_bit(EFI_MEM_ATTR, &efi.flags);
 
 unmap:
 	early_memunmap(tbl, sizeof(*tbl));
@@ -174,8 +175,11 @@ int __init efi_memattr_apply_permissions(struct mm_struct *mm,
 				md.phys_addr + size - 1,
 				efi_md_typeattr_format(buf, sizeof(buf), &md));
 
-		if (valid)
+		if (valid) {
 			ret = fn(mm, &md);
+			if (ret)
+				pr_err("Error updating mappings, skipping subsequent md's\n");
+		}
 	}
 	memunmap(tbl);
 	return ret;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 86bf3b84ada5..a07ae9e37930 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1723,7 +1723,7 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip)
 }
 
 /**
- * _gpiochip_irqchip_add() - adds an irqchip to a gpiochip
+ * gpiochip_irqchip_add_key() - adds an irqchip to a gpiochip
  * @gpiochip: the gpiochip to add the irqchip to
  * @irqchip: the irqchip to add to the gpiochip
  * @first_irq: if not dynamically assigned, the base (first) IRQ to
@@ -1749,13 +1749,13 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip)
  * the pins on the gpiochip can generate a unique IRQ. Everything else
  * need to be open coded.
  */
-int _gpiochip_irqchip_add(struct gpio_chip *gpiochip,
-			  struct irq_chip *irqchip,
-			  unsigned int first_irq,
-			  irq_flow_handler_t handler,
-			  unsigned int type,
-			  bool nested,
-			  struct lock_class_key *lock_key)
+int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip,
+			     struct irq_chip *irqchip,
+			     unsigned int first_irq,
+			     irq_flow_handler_t handler,
+			     unsigned int type,
+			     bool nested,
+			     struct lock_class_key *lock_key)
 {
 	struct device_node *of_node;
 	bool irq_base_set = false;
@@ -1840,7 +1840,7 @@ int _gpiochip_irqchip_add(struct gpio_chip *gpiochip,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(_gpiochip_irqchip_add);
+EXPORT_SYMBOL_GPL(gpiochip_irqchip_add_key);
 
 #else /* CONFIG_GPIOLIB_IRQCHIP */
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 29d6d84d1c28..41e41f90265d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -83,6 +83,13 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
 		}
 		break;
 	}
+
+	if (!(*out_ring && (*out_ring)->adev)) {
+		DRM_ERROR("Ring %d is not initialized on IP %d\n",
+			  ring, ip_type);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 9999dc71b998..ccb5e02e7b20 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2512,6 +2512,8 @@ static int dce_v10_0_cursor_move_locked(struct drm_crtc *crtc,
 
 	WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
 	WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+	WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+	       ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
 
 	return 0;
 }
@@ -2537,7 +2539,6 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc,
 				      int32_t hot_y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *aobj;
 	int ret;
@@ -2578,7 +2579,9 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 	dce_v10_0_lock_cursor(crtc, true);
 
-	if (hot_x != amdgpu_crtc->cursor_hot_x ||
+	if (width != amdgpu_crtc->cursor_width ||
+	    height != amdgpu_crtc->cursor_height ||
+	    hot_x != amdgpu_crtc->cursor_hot_x ||
 	    hot_y != amdgpu_crtc->cursor_hot_y) {
 		int x, y;
 
@@ -2587,16 +2590,10 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 		dce_v10_0_cursor_move_locked(crtc, x, y);
 
-		amdgpu_crtc->cursor_hot_x = hot_x;
-		amdgpu_crtc->cursor_hot_y = hot_y;
-	}
-
-	if (width != amdgpu_crtc->cursor_width ||
-	    height != amdgpu_crtc->cursor_height) {
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (width - 1) << 16 | (height - 1));
 		amdgpu_crtc->cursor_width = width;
 		amdgpu_crtc->cursor_height = height;
+		amdgpu_crtc->cursor_hot_x = hot_x;
+		amdgpu_crtc->cursor_hot_y = hot_y;
 	}
 
 	dce_v10_0_show_cursor(crtc);
@@ -2620,7 +2617,6 @@ unpin:
 static void dce_v10_0_cursor_reset(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 
 	if (amdgpu_crtc->cursor_bo) {
 		dce_v10_0_lock_cursor(crtc, true);
@@ -2628,10 +2624,6 @@ static void dce_v10_0_cursor_reset(struct drm_crtc *crtc)
 		dce_v10_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
 					     amdgpu_crtc->cursor_y);
 
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (amdgpu_crtc->cursor_width - 1) << 16 |
-		       (amdgpu_crtc->cursor_height - 1));
-
 		dce_v10_0_show_cursor(crtc);
 
 		dce_v10_0_lock_cursor(crtc, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 2006abbbfb62..a7af5b33a5e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -2532,6 +2532,8 @@ static int dce_v11_0_cursor_move_locked(struct drm_crtc *crtc,
 
 	WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
 	WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+	WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+	       ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
 
 	return 0;
 }
@@ -2557,7 +2559,6 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc,
 				      int32_t hot_y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *aobj;
 	int ret;
@@ -2598,7 +2599,9 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 	dce_v11_0_lock_cursor(crtc, true);
 
-	if (hot_x != amdgpu_crtc->cursor_hot_x ||
+	if (width != amdgpu_crtc->cursor_width ||
+	    height != amdgpu_crtc->cursor_height ||
+	    hot_x != amdgpu_crtc->cursor_hot_x ||
 	    hot_y != amdgpu_crtc->cursor_hot_y) {
 		int x, y;
 
@@ -2607,16 +2610,10 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 		dce_v11_0_cursor_move_locked(crtc, x, y);
 
-		amdgpu_crtc->cursor_hot_x = hot_x;
-		amdgpu_crtc->cursor_hot_y = hot_y;
-	}
-
-	if (width != amdgpu_crtc->cursor_width ||
-	    height != amdgpu_crtc->cursor_height) {
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (width - 1) << 16 | (height - 1));
 		amdgpu_crtc->cursor_width = width;
 		amdgpu_crtc->cursor_height = height;
+		amdgpu_crtc->cursor_hot_x = hot_x;
+		amdgpu_crtc->cursor_hot_y = hot_y;
 	}
 
 	dce_v11_0_show_cursor(crtc);
@@ -2640,7 +2637,6 @@ unpin:
 static void dce_v11_0_cursor_reset(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 
 	if (amdgpu_crtc->cursor_bo) {
 		dce_v11_0_lock_cursor(crtc, true);
@@ -2648,10 +2644,6 @@ static void dce_v11_0_cursor_reset(struct drm_crtc *crtc)
 		dce_v11_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
 					     amdgpu_crtc->cursor_y);
 
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (amdgpu_crtc->cursor_width - 1) << 16 |
-		       (amdgpu_crtc->cursor_height - 1));
-
 		dce_v11_0_show_cursor(crtc);
 
 		dce_v11_0_lock_cursor(crtc, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index b4e4ec630e8c..39df6a50637f 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1859,6 +1859,8 @@ static int dce_v6_0_cursor_move_locked(struct drm_crtc *crtc,
 	struct amdgpu_device *adev = crtc->dev->dev_private;
 	int xorigin = 0, yorigin = 0;
 
+	int w = amdgpu_crtc->cursor_width;
+
 	amdgpu_crtc->cursor_x = x;
 	amdgpu_crtc->cursor_y = y;
 
@@ -1878,6 +1880,8 @@ static int dce_v6_0_cursor_move_locked(struct drm_crtc *crtc,
 
 	WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
 	WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+	WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+	       ((w - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
 
 	return 0;
 }
@@ -1903,7 +1907,6 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc,
 				     int32_t hot_y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *aobj;
 	int ret;
@@ -1944,7 +1947,9 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 	dce_v6_0_lock_cursor(crtc, true);
 
-	if (hot_x != amdgpu_crtc->cursor_hot_x ||
+	if (width != amdgpu_crtc->cursor_width ||
+	    height != amdgpu_crtc->cursor_height ||
+	    hot_x != amdgpu_crtc->cursor_hot_x ||
 	    hot_y != amdgpu_crtc->cursor_hot_y) {
 		int x, y;
 
@@ -1953,16 +1958,10 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 		dce_v6_0_cursor_move_locked(crtc, x, y);
 
-		amdgpu_crtc->cursor_hot_x = hot_x;
-		amdgpu_crtc->cursor_hot_y = hot_y;
-	}
-
-	if (width != amdgpu_crtc->cursor_width ||
-	    height != amdgpu_crtc->cursor_height) {
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (width - 1) << 16 | (height - 1));
 		amdgpu_crtc->cursor_width = width;
 		amdgpu_crtc->cursor_height = height;
+		amdgpu_crtc->cursor_hot_x = hot_x;
+		amdgpu_crtc->cursor_hot_y = hot_y;
 	}
 
 	dce_v6_0_show_cursor(crtc);
@@ -1986,7 +1985,6 @@ unpin:
 static void dce_v6_0_cursor_reset(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 
 	if (amdgpu_crtc->cursor_bo) {
 		dce_v6_0_lock_cursor(crtc, true);
@@ -1994,10 +1992,6 @@ static void dce_v6_0_cursor_reset(struct drm_crtc *crtc)
 		dce_v6_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
 					    amdgpu_crtc->cursor_y);
 
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (amdgpu_crtc->cursor_width - 1) << 16 |
-		       (amdgpu_crtc->cursor_height - 1));
-
 		dce_v6_0_show_cursor(crtc);
 		dce_v6_0_lock_cursor(crtc, false);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index 584abe834a3c..28102bb1704d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2363,6 +2363,8 @@ static int dce_v8_0_cursor_move_locked(struct drm_crtc *crtc,
 
 	WREG32(mmCUR_POSITION + amdgpu_crtc->crtc_offset, (x << 16) | y);
 	WREG32(mmCUR_HOT_SPOT + amdgpu_crtc->crtc_offset, (xorigin << 16) | yorigin);
+	WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
+	       ((amdgpu_crtc->cursor_width - 1) << 16) | (amdgpu_crtc->cursor_height - 1));
 
 	return 0;
 }
@@ -2388,7 +2390,6 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc,
 				     int32_t hot_y)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 	struct drm_gem_object *obj;
 	struct amdgpu_bo *aobj;
 	int ret;
@@ -2429,7 +2430,9 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 	dce_v8_0_lock_cursor(crtc, true);
 
-	if (hot_x != amdgpu_crtc->cursor_hot_x ||
+	if (width != amdgpu_crtc->cursor_width ||
+	    height != amdgpu_crtc->cursor_height ||
+	    hot_x != amdgpu_crtc->cursor_hot_x ||
 	    hot_y != amdgpu_crtc->cursor_hot_y) {
 		int x, y;
 
@@ -2438,16 +2441,10 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc,
 
 		dce_v8_0_cursor_move_locked(crtc, x, y);
 
-		amdgpu_crtc->cursor_hot_x = hot_x;
-		amdgpu_crtc->cursor_hot_y = hot_y;
-	}
-
-	if (width != amdgpu_crtc->cursor_width ||
-	    height != amdgpu_crtc->cursor_height) {
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (width - 1) << 16 | (height - 1));
 		amdgpu_crtc->cursor_width = width;
 		amdgpu_crtc->cursor_height = height;
+		amdgpu_crtc->cursor_hot_x = hot_x;
+		amdgpu_crtc->cursor_hot_y = hot_y;
 	}
 
 	dce_v8_0_show_cursor(crtc);
@@ -2471,7 +2468,6 @@ unpin:
 static void dce_v8_0_cursor_reset(struct drm_crtc *crtc)
 {
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-	struct amdgpu_device *adev = crtc->dev->dev_private;
 
 	if (amdgpu_crtc->cursor_bo) {
 		dce_v8_0_lock_cursor(crtc, true);
@@ -2479,10 +2475,6 @@ static void dce_v8_0_cursor_reset(struct drm_crtc *crtc)
 		dce_v8_0_cursor_move_locked(crtc, amdgpu_crtc->cursor_x,
 					    amdgpu_crtc->cursor_y);
 
-		WREG32(mmCUR_SIZE + amdgpu_crtc->crtc_offset,
-		       (amdgpu_crtc->cursor_width - 1) << 16 |
-		       (amdgpu_crtc->cursor_height - 1));
-
 		dce_v8_0_show_cursor(crtc);
 
 		dce_v8_0_lock_cursor(crtc, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index 762f8e82ceb7..e9a176891e13 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -627,11 +627,8 @@ static const struct drm_encoder_helper_funcs dce_virtual_encoder_helper_funcs =
 
 static void dce_virtual_encoder_destroy(struct drm_encoder *encoder)
 {
-	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
-
-	kfree(amdgpu_encoder->enc_priv);
 	drm_encoder_cleanup(encoder);
-	kfree(amdgpu_encoder);
+	kfree(encoder);
 }
 
 static const struct drm_encoder_funcs dce_virtual_encoder_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 45a573e63d4a..0635829b18cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -44,6 +44,7 @@ MODULE_FIRMWARE("radeon/tahiti_mc.bin");
 MODULE_FIRMWARE("radeon/pitcairn_mc.bin");
 MODULE_FIRMWARE("radeon/verde_mc.bin");
 MODULE_FIRMWARE("radeon/oland_mc.bin");
+MODULE_FIRMWARE("radeon/si58_mc.bin");
 
 #define MC_SEQ_MISC0__MT__MASK   0xf0000000
 #define MC_SEQ_MISC0__MT__GDDR1  0x10000000
@@ -113,6 +114,7 @@ static int gmc_v6_0_init_microcode(struct amdgpu_device *adev)
 	const char *chip_name;
 	char fw_name[30];
 	int err;
+	bool is_58_fw = false;
 
 	DRM_DEBUG("\n");
 
@@ -135,7 +137,14 @@ static int gmc_v6_0_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+	/* this memory configuration requires special firmware */
+	if (((RREG32(mmMC_SEQ_MISC0) & 0xff000000) >> 24) == 0x58)
+		is_58_fw = true;
+
+	if (is_58_fw)
+		snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin");
+	else
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
 	err = request_firmware(&adev->mc.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -245,6 +254,9 @@ static void gmc_v6_0_mc_program(struct amdgpu_device *adev)
 	}
 	WREG32(mmHDP_REG_COHERENCY_FLUSH_CNTL, 0);
 
+	if (adev->mode_info.num_crtc)
+		amdgpu_display_set_vga_render_state(adev, false);
+
 	gmc_v6_0_mc_stop(adev, &save);
 
 	if (gmc_v6_0_wait_for_idle((void *)adev)) {
@@ -274,7 +286,6 @@ static void gmc_v6_0_mc_program(struct amdgpu_device *adev)
 		dev_warn(adev->dev, "Wait for MC idle timedout !\n");
 	}
 	gmc_v6_0_mc_resume(adev, &save);
-	amdgpu_display_set_vga_render_state(adev, false);
 }
 
 static int gmc_v6_0_mc_init(struct amdgpu_device *adev)
@@ -463,19 +474,11 @@ static int gmc_v6_0_gart_enable(struct amdgpu_device *adev)
 	WREG32(mmVM_CONTEXT1_CNTL,
 	       VM_CONTEXT1_CNTL__ENABLE_CONTEXT_MASK |
 	       (1UL << VM_CONTEXT1_CNTL__PAGE_TABLE_DEPTH__SHIFT) |
-	       ((amdgpu_vm_block_size - 9) << VM_CONTEXT1_CNTL__PAGE_TABLE_BLOCK_SIZE__SHIFT) |
-	       VM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__RANGE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
-	       VM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__DUMMY_PAGE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
-	       VM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__PDE0_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
-	       VM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__VALID_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
-	       VM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__READ_PROTECTION_FAULT_ENABLE_DEFAULT_MASK |
-	       VM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_INTERRUPT_MASK |
-	       VM_CONTEXT1_CNTL__WRITE_PROTECTION_FAULT_ENABLE_DEFAULT_MASK);
+	       ((amdgpu_vm_block_size - 9) << VM_CONTEXT1_CNTL__PAGE_TABLE_BLOCK_SIZE__SHIFT));
+	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
+		gmc_v6_0_set_fault_enable_default(adev, false);
+	else
+		gmc_v6_0_set_fault_enable_default(adev, true);
 
 	gmc_v6_0_gart_flush_gpu_tlb(adev, 0);
 	dev_info(adev->dev, "PCIE GART of %uM enabled (table at 0x%016llX).\n",
@@ -754,7 +757,10 @@ static int gmc_v6_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	if (amdgpu_vm_fault_stop != AMDGPU_VM_FAULT_STOP_ALWAYS)
+		return amdgpu_irq_get(adev, &adev->mc.vm_fault, 0);
+	else
+		return 0;
 }
 
 static int gmc_v6_0_sw_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 10bedfac27b8..6e150db8f380 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -64,6 +64,7 @@ MODULE_FIRMWARE("radeon/oland_smc.bin");
 MODULE_FIRMWARE("radeon/oland_k_smc.bin");
 MODULE_FIRMWARE("radeon/hainan_smc.bin");
 MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
+MODULE_FIRMWARE("radeon/banks_k_2_smc.bin");
 
 union power_info {
 	struct _ATOM_POWERPLAY_INFO info;
@@ -3487,17 +3488,6 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		    (adev->pdev->device == 0x6817) ||
 		    (adev->pdev->device == 0x6806))
 			max_mclk = 120000;
-	} else if (adev->asic_type == CHIP_OLAND) {
-		if ((adev->pdev->revision == 0xC7) ||
-		    (adev->pdev->revision == 0x80) ||
-		    (adev->pdev->revision == 0x81) ||
-		    (adev->pdev->revision == 0x83) ||
-		    (adev->pdev->revision == 0x87) ||
-		    (adev->pdev->device == 0x6604) ||
-		    (adev->pdev->device == 0x6605)) {
-			max_sclk = 75000;
-			max_mclk = 80000;
-		}
 	} else if (adev->asic_type == CHIP_HAINAN) {
 		if ((adev->pdev->revision == 0x81) ||
 		    (adev->pdev->revision == 0x83) ||
@@ -3506,7 +3496,6 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		    (adev->pdev->device == 0x6665) ||
 		    (adev->pdev->device == 0x6667)) {
 			max_sclk = 75000;
-			max_mclk = 80000;
 		}
 	}
 	/* Apply dpm quirks */
@@ -7713,10 +7702,11 @@ static int si_dpm_init_microcode(struct amdgpu_device *adev)
 			((adev->pdev->device == 0x6660) ||
 			(adev->pdev->device == 0x6663) ||
 			(adev->pdev->device == 0x6665) ||
-			(adev->pdev->device == 0x6667))) ||
-		    ((adev->pdev->revision == 0xc3) &&
-			(adev->pdev->device == 0x6665)))
+			 (adev->pdev->device == 0x6667))))
 			chip_name = "hainan_k";
+		else if ((adev->pdev->revision == 0xc3) &&
+			 (adev->pdev->device == 0x6665))
+			chip_name = "banks_k_2";
 		else
 			chip_name = "hainan";
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 96444e4d862a..7fb9137dd89b 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -40,13 +40,14 @@
 #include "smu/smu_7_0_1_sh_mask.h"
 
 static void uvd_v4_2_mc_resume(struct amdgpu_device *adev);
-static void uvd_v4_2_init_cg(struct amdgpu_device *adev);
 static void uvd_v4_2_set_ring_funcs(struct amdgpu_device *adev);
 static void uvd_v4_2_set_irq_funcs(struct amdgpu_device *adev);
 static int uvd_v4_2_start(struct amdgpu_device *adev);
 static void uvd_v4_2_stop(struct amdgpu_device *adev);
 static int uvd_v4_2_set_clockgating_state(void *handle,
 				enum amd_clockgating_state state);
+static void uvd_v4_2_set_dcm(struct amdgpu_device *adev,
+			     bool sw_mode);
 /**
  * uvd_v4_2_ring_get_rptr - get read pointer
  *
@@ -140,7 +141,8 @@ static int uvd_v4_2_sw_fini(void *handle)
 
 	return r;
 }
-
+static void uvd_v4_2_enable_mgcg(struct amdgpu_device *adev,
+				 bool enable);
 /**
  * uvd_v4_2_hw_init - start and test UVD block
  *
@@ -155,8 +157,7 @@ static int uvd_v4_2_hw_init(void *handle)
 	uint32_t tmp;
 	int r;
 
-	uvd_v4_2_init_cg(adev);
-	uvd_v4_2_set_clockgating_state(adev, AMD_CG_STATE_GATE);
+	uvd_v4_2_enable_mgcg(adev, true);
 	amdgpu_asic_set_uvd_clocks(adev, 10000, 10000);
 	r = uvd_v4_2_start(adev);
 	if (r)
@@ -266,11 +267,13 @@ static int uvd_v4_2_start(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring = &adev->uvd.ring;
 	uint32_t rb_bufsz;
 	int i, j, r;
-
 	/* disable byte swapping */
 	u32 lmi_swap_cntl = 0;
 	u32 mp_swap_cntl = 0;
 
+	WREG32(mmUVD_CGC_GATE, 0);
+	uvd_v4_2_set_dcm(adev, true);
+
 	uvd_v4_2_mc_resume(adev);
 
 	/* disable interupt */
@@ -406,6 +409,8 @@ static void uvd_v4_2_stop(struct amdgpu_device *adev)
 
 	/* Unstall UMC and register bus */
 	WREG32_P(mmUVD_LMI_CTRL2, 0, ~(1 << 8));
+
+	uvd_v4_2_set_dcm(adev, false);
 }
 
 /**
@@ -619,19 +624,6 @@ static void uvd_v4_2_set_dcm(struct amdgpu_device *adev,
 	WREG32_UVD_CTX(ixUVD_CGC_CTRL2, tmp2);
 }
 
-static void uvd_v4_2_init_cg(struct amdgpu_device *adev)
-{
-	bool hw_mode = true;
-
-	if (hw_mode) {
-		uvd_v4_2_set_dcm(adev, false);
-	} else {
-		u32 tmp = RREG32(mmUVD_CGC_CTRL);
-		tmp &= ~UVD_CGC_CTRL__DYN_CLOCK_MODE_MASK;
-		WREG32(mmUVD_CGC_CTRL, tmp);
-	}
-}
-
 static bool uvd_v4_2_is_idle(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -685,17 +677,6 @@ static int uvd_v4_2_process_interrupt(struct amdgpu_device *adev,
 static int uvd_v4_2_set_clockgating_state(void *handle,
 					  enum amd_clockgating_state state)
 {
-	bool gate = false;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	if (!(adev->cg_flags & AMD_CG_SUPPORT_UVD_MGCG))
-		return 0;
-
-	if (state == AMD_CG_STATE_GATE)
-		gate = true;
-
-	uvd_v4_2_enable_mgcg(adev, gate);
-
 	return 0;
 }
 
@@ -711,9 +692,6 @@ static int uvd_v4_2_set_powergating_state(void *handle,
 	 */
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (!(adev->pg_flags & AMD_PG_SUPPORT_UVD))
-		return 0;
-
 	if (state == AMD_PG_STATE_GATE) {
 		uvd_v4_2_stop(adev);
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 5fb0b7f5c065..37ca685e5a9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -43,9 +43,13 @@
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK	0x10
+#define GRBM_GFX_INDEX__VCE_ALL_PIPE		0x07
+
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR0	0x8616
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR1	0x8617
 #define mmVCE_LMI_VCPU_CACHE_40BIT_BAR2	0x8618
+#define mmGRBM_GFX_INDEX_DEFAULT 0xE0000000
+
 #define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK	0x02
 
 #define VCE_V3_0_FW_SIZE	(384 * 1024)
@@ -54,6 +58,9 @@
 
 #define FW_52_8_3	((52 << 24) | (8 << 16) | (3 << 8))
 
+#define GET_VCE_INSTANCE(i)  ((i) << GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT \
+					| GRBM_GFX_INDEX__VCE_ALL_PIPE)
+
 static void vce_v3_0_mc_resume(struct amdgpu_device *adev, int idx);
 static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev);
 static void vce_v3_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -175,7 +182,7 @@ static void vce_v3_0_set_vce_sw_clock_gating(struct amdgpu_device *adev,
 		WREG32(mmVCE_UENC_CLOCK_GATING_2, data);
 
 		data = RREG32(mmVCE_UENC_REG_CLOCK_GATING);
-		data &= ~0xffc00000;
+		data &= ~0x3ff;
 		WREG32(mmVCE_UENC_REG_CLOCK_GATING, data);
 
 		data = RREG32(mmVCE_UENC_DMA_DCLK_CTRL);
@@ -249,7 +256,7 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 		if (adev->vce.harvest_config & (1 << idx))
 			continue;
 
-		WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, idx);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx));
 		vce_v3_0_mc_resume(adev, idx);
 		WREG32_FIELD(VCE_STATUS, JOB_BUSY, 1);
 
@@ -273,7 +280,7 @@ static int vce_v3_0_start(struct amdgpu_device *adev)
 		}
 	}
 
-	WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+	WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
@@ -288,7 +295,7 @@ static int vce_v3_0_stop(struct amdgpu_device *adev)
 		if (adev->vce.harvest_config & (1 << idx))
 			continue;
 
-		WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, idx);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx));
 
 		if (adev->asic_type >= CHIP_STONEY)
 			WREG32_P(mmVCE_VCPU_CNTL, 0, ~0x200001);
@@ -306,7 +313,7 @@ static int vce_v3_0_stop(struct amdgpu_device *adev)
 			vce_v3_0_set_vce_sw_clock_gating(adev, false);
 	}
 
-	WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+	WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
@@ -586,17 +593,17 @@ static bool vce_v3_0_check_soft_reset(void *handle)
 	 * VCE team suggest use bit 3--bit 6 for busy status check
 	 */
 	mutex_lock(&adev->grbm_idx_mutex);
-	WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0);
+	WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
 	if (RREG32(mmVCE_STATUS) & AMDGPU_VCE_STATUS_BUSY_MASK) {
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE0, 1);
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1);
 	}
-	WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0x10);
+	WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 	if (RREG32(mmVCE_STATUS) & AMDGPU_VCE_STATUS_BUSY_MASK) {
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE0, 1);
 		srbm_soft_reset = REG_SET_FIELD(srbm_soft_reset, SRBM_SOFT_RESET, SOFT_RESET_VCE1, 1);
 	}
-	WREG32_FIELD(GRBM_GFX_INDEX, INSTANCE_INDEX, 0);
+	WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0));
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	if (srbm_soft_reset) {
@@ -734,7 +741,7 @@ static int vce_v3_0_set_clockgating_state(void *handle,
 		if (adev->vce.harvest_config & (1 << i))
 			continue;
 
-		WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, i);
+		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(i));
 
 		if (enable) {
 			/* initialize VCE_CLOCK_GATING_A: Clock ON/OFF delay */
@@ -753,7 +760,7 @@ static int vce_v3_0_set_clockgating_state(void *handle,
 		vce_v3_0_set_vce_sw_clock_gating(adev, enable);
 	}
 
-	WREG32_FIELD(GRBM_GFX_INDEX, VCE_INSTANCE, 0);
+	WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT);
 	mutex_unlock(&adev->grbm_idx_mutex);
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
index b0c63c5f54c9..6bb79c94cb9f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_clockpowergating.c
@@ -200,7 +200,7 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 				cgs_set_clockgating_state(
 							hwmgr->device,
 							AMD_IP_BLOCK_TYPE_VCE,
-							AMD_CG_STATE_UNGATE);
+							AMD_CG_STATE_GATE);
 				cgs_set_powergating_state(
 							hwmgr->device,
 							AMD_IP_BLOCK_TYPE_VCE,
@@ -218,7 +218,7 @@ int cz_dpm_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 				cgs_set_clockgating_state(
 							hwmgr->device,
 							AMD_IP_BLOCK_TYPE_VCE,
-							AMD_PG_STATE_GATE);
+							AMD_PG_STATE_UNGATE);
 				cz_dpm_update_vce_dpm(hwmgr);
 				cz_enable_disable_vce_dpm(hwmgr, true);
 				return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
index 4b14f259a147..0fb4e8c8f5e1 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c
@@ -1402,14 +1402,22 @@ int  cz_dpm_update_vce_dpm(struct pp_hwmgr *hwmgr)
 					     cz_hwmgr->vce_dpm.hard_min_clk,
 						PPSMC_MSG_SetEclkHardMin));
 	} else {
-		/*EPR# 419220 -HW limitation to to */
-		cz_hwmgr->vce_dpm.hard_min_clk = hwmgr->vce_arbiter.ecclk;
-		smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
-					    PPSMC_MSG_SetEclkHardMin,
-					    cz_get_eclk_level(hwmgr,
-				     cz_hwmgr->vce_dpm.hard_min_clk,
-					  PPSMC_MSG_SetEclkHardMin));
-
+		/*Program HardMin based on the vce_arbiter.ecclk */
+		if (hwmgr->vce_arbiter.ecclk == 0) {
+			smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+					    PPSMC_MSG_SetEclkHardMin, 0);
+		/* disable ECLK DPM 0. Otherwise VCE could hang if
+		 * switching SCLK from DPM 0 to 6/7 */
+			smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+					PPSMC_MSG_SetEclkSoftMin, 1);
+		} else {
+			cz_hwmgr->vce_dpm.hard_min_clk = hwmgr->vce_arbiter.ecclk;
+			smum_send_msg_to_smc_with_parameter(hwmgr->smumgr,
+						PPSMC_MSG_SetEclkHardMin,
+						cz_get_eclk_level(hwmgr,
+						cz_hwmgr->vce_dpm.hard_min_clk,
+						PPSMC_MSG_SetEclkHardMin));
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
index 908011d2c8f5..7abda94fc2cf 100644
--- a/drivers/gpu/drm/ast/ast_drv.h
+++ b/drivers/gpu/drm/ast/ast_drv.h
@@ -113,6 +113,7 @@ struct ast_private {
 	struct ttm_bo_kmap_obj cache_kmap;
 	int next_cursor;
 	bool support_wide_screen;
+	bool DisableP2A;
 
 	enum ast_tx_chip tx_chip_type;
 	u8 dp501_maxclk;
diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c
index f75c6421db62..533e762d036d 100644
--- a/drivers/gpu/drm/ast/ast_main.c
+++ b/drivers/gpu/drm/ast/ast_main.c
@@ -124,6 +124,12 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post)
 	} else
 		*need_post = false;
 
+	/* Check P2A Access */
+	ast->DisableP2A = true;
+	data = ast_read32(ast, 0xf004);
+	if (data != 0xFFFFFFFF)
+		ast->DisableP2A = false;
+
 	/* Check if we support wide screen */
 	switch (ast->chip) {
 	case AST1180:
@@ -140,15 +146,17 @@ static int ast_detect_chip(struct drm_device *dev, bool *need_post)
 			ast->support_wide_screen = true;
 		else {
 			ast->support_wide_screen = false;
-			/* Read SCU7c (silicon revision register) */
-			ast_write32(ast, 0xf004, 0x1e6e0000);
-			ast_write32(ast, 0xf000, 0x1);
-			data = ast_read32(ast, 0x1207c);
-			data &= 0x300;
-			if (ast->chip == AST2300 && data == 0x0) /* ast1300 */
-				ast->support_wide_screen = true;
-			if (ast->chip == AST2400 && data == 0x100) /* ast1400 */
-				ast->support_wide_screen = true;
+			if (ast->DisableP2A == false) {
+				/* Read SCU7c (silicon revision register) */
+				ast_write32(ast, 0xf004, 0x1e6e0000);
+				ast_write32(ast, 0xf000, 0x1);
+				data = ast_read32(ast, 0x1207c);
+				data &= 0x300;
+				if (ast->chip == AST2300 && data == 0x0) /* ast1300 */
+					ast->support_wide_screen = true;
+				if (ast->chip == AST2400 && data == 0x100) /* ast1400 */
+					ast->support_wide_screen = true;
+			}
 		}
 		break;
 	}
@@ -216,80 +224,81 @@ static int ast_get_dram_info(struct drm_device *dev)
 	uint32_t data, data2;
 	uint32_t denum, num, div, ref_pll;
 
-	ast_write32(ast, 0xf004, 0x1e6e0000);
-	ast_write32(ast, 0xf000, 0x1);
-
-
-	ast_write32(ast, 0x10000, 0xfc600309);
-
-	do {
-		if (pci_channel_offline(dev->pdev))
-			return -EIO;
-	} while (ast_read32(ast, 0x10000) != 0x01);
-	data = ast_read32(ast, 0x10004);
-
-	if (data & 0x40)
+	if (ast->DisableP2A)
+	{
 		ast->dram_bus_width = 16;
+		ast->dram_type = AST_DRAM_1Gx16;
+		ast->mclk = 396;
+	}
 	else
-		ast->dram_bus_width = 32;
+	{
+		ast_write32(ast, 0xf004, 0x1e6e0000);
+		ast_write32(ast, 0xf000, 0x1);
+		data = ast_read32(ast, 0x10004);
+
+		if (data & 0x40)
+			ast->dram_bus_width = 16;
+		else
+			ast->dram_bus_width = 32;
+
+		if (ast->chip == AST2300 || ast->chip == AST2400) {
+			switch (data & 0x03) {
+			case 0:
+				ast->dram_type = AST_DRAM_512Mx16;
+				break;
+			default:
+			case 1:
+				ast->dram_type = AST_DRAM_1Gx16;
+				break;
+			case 2:
+				ast->dram_type = AST_DRAM_2Gx16;
+				break;
+			case 3:
+				ast->dram_type = AST_DRAM_4Gx16;
+				break;
+			}
+		} else {
+			switch (data & 0x0c) {
+			case 0:
+			case 4:
+				ast->dram_type = AST_DRAM_512Mx16;
+				break;
+			case 8:
+				if (data & 0x40)
+					ast->dram_type = AST_DRAM_1Gx16;
+				else
+					ast->dram_type = AST_DRAM_512Mx32;
+				break;
+			case 0xc:
+				ast->dram_type = AST_DRAM_1Gx32;
+				break;
+			}
+		}
 
-	if (ast->chip == AST2300 || ast->chip == AST2400) {
-		switch (data & 0x03) {
-		case 0:
-			ast->dram_type = AST_DRAM_512Mx16;
-			break;
-		default:
-		case 1:
-			ast->dram_type = AST_DRAM_1Gx16;
-			break;
-		case 2:
-			ast->dram_type = AST_DRAM_2Gx16;
-			break;
+		data = ast_read32(ast, 0x10120);
+		data2 = ast_read32(ast, 0x10170);
+		if (data2 & 0x2000)
+			ref_pll = 14318;
+		else
+			ref_pll = 12000;
+
+		denum = data & 0x1f;
+		num = (data & 0x3fe0) >> 5;
+		data = (data & 0xc000) >> 14;
+		switch (data) {
 		case 3:
-			ast->dram_type = AST_DRAM_4Gx16;
-			break;
-		}
-	} else {
-		switch (data & 0x0c) {
-		case 0:
-		case 4:
-			ast->dram_type = AST_DRAM_512Mx16;
+			div = 0x4;
 			break;
-		case 8:
-			if (data & 0x40)
-				ast->dram_type = AST_DRAM_1Gx16;
-			else
-				ast->dram_type = AST_DRAM_512Mx32;
+		case 2:
+		case 1:
+			div = 0x2;
 			break;
-		case 0xc:
-			ast->dram_type = AST_DRAM_1Gx32;
+		default:
+			div = 0x1;
 			break;
 		}
+		ast->mclk = ref_pll * (num + 2) / (denum + 2) * (div * 1000);
 	}
-
-	data = ast_read32(ast, 0x10120);
-	data2 = ast_read32(ast, 0x10170);
-	if (data2 & 0x2000)
-		ref_pll = 14318;
-	else
-		ref_pll = 12000;
-
-	denum = data & 0x1f;
-	num = (data & 0x3fe0) >> 5;
-	data = (data & 0xc000) >> 14;
-	switch (data) {
-	case 3:
-		div = 0x4;
-		break;
-	case 2:
-	case 1:
-		div = 0x2;
-		break;
-	default:
-		div = 0x1;
-		break;
-	}
-	ast->mclk = ref_pll * (num + 2) / (denum + 2) * (div * 1000);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c
index 810c51d92b99..5331ee1df086 100644
--- a/drivers/gpu/drm/ast/ast_post.c
+++ b/drivers/gpu/drm/ast/ast_post.c
@@ -379,12 +379,20 @@ void ast_post_gpu(struct drm_device *dev)
 	ast_open_key(ast);
 	ast_set_def_ext_reg(dev);
 
-	if (ast->chip == AST2300 || ast->chip == AST2400)
-		ast_init_dram_2300(dev);
-	else
-		ast_init_dram_reg(dev);
+	if (ast->DisableP2A == false)
+	{
+		if (ast->chip == AST2300 || ast->chip == AST2400)
+			ast_init_dram_2300(dev);
+		else
+			ast_init_dram_reg(dev);
 
-	ast_init_3rdtx(dev);
+		ast_init_3rdtx(dev);
+	}
+	else
+	{
+		if (ast->tx_chip_type != AST_TX_NONE)
+			ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xa3, 0xcf, 0x80);	/* Enable DVO */
+	}
 }
 
 /* AST 2300 DRAM settings */
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index eb9bf8786c24..18eefdcbf1ba 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1382,6 +1382,7 @@ int analogix_dp_bind(struct device *dev, struct drm_device *drm_dev,
 
 	pm_runtime_enable(dev);
 
+	pm_runtime_get_sync(dev);
 	phy_power_on(dp->phy);
 
 	analogix_dp_init_dp(dp);
@@ -1414,9 +1415,15 @@ int analogix_dp_bind(struct device *dev, struct drm_device *drm_dev,
 		goto err_disable_pm_runtime;
 	}
 
+	phy_power_off(dp->phy);
+	pm_runtime_put(dev);
+
 	return 0;
 
 err_disable_pm_runtime:
+
+	phy_power_off(dp->phy);
+	pm_runtime_put(dev);
 	pm_runtime_disable(dev);
 
 	return ret;
diff --git a/drivers/gpu/drm/cirrus/Kconfig b/drivers/gpu/drm/cirrus/Kconfig
index 04b3c161dfae..7f4cc6e172ab 100644
--- a/drivers/gpu/drm/cirrus/Kconfig
+++ b/drivers/gpu/drm/cirrus/Kconfig
@@ -7,3 +7,12 @@ config DRM_CIRRUS_QEMU
 	 This is a KMS driver for emulated cirrus device in qemu.
 	 It is *NOT* intended for real cirrus devices. This requires
 	 the modesetting userspace X.org driver.
+
+	 Cirrus is obsolete, the hardware was designed in the 90ies
+	 and can't keep up with todays needs.  More background:
+	 https://www.kraxel.org/blog/2014/10/qemu-using-cirrus-considered-harmful/
+
+	 Better alternatives are:
+	   - stdvga (DRM_BOCHS, qemu -vga std, default in qemu 2.2+)
+	   - qxl (DRM_QXL, qemu -vga qxl, works best with spice)
+	   - virtio (DRM_VIRTIO_GPU), qemu -vga virtio)
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 60697482b94c..fdfb1ec17e66 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -291,15 +291,15 @@ drm_atomic_get_crtc_state(struct drm_atomic_state *state,
 EXPORT_SYMBOL(drm_atomic_get_crtc_state);
 
 static void set_out_fence_for_crtc(struct drm_atomic_state *state,
-				   struct drm_crtc *crtc, s64 __user *fence_ptr)
+				   struct drm_crtc *crtc, s32 __user *fence_ptr)
 {
 	state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = fence_ptr;
 }
 
-static s64 __user *get_out_fence_for_crtc(struct drm_atomic_state *state,
+static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state,
 					  struct drm_crtc *crtc)
 {
-	s64 __user *fence_ptr;
+	s32 __user *fence_ptr;
 
 	fence_ptr = state->crtcs[drm_crtc_index(crtc)].out_fence_ptr;
 	state->crtcs[drm_crtc_index(crtc)].out_fence_ptr = NULL;
@@ -512,7 +512,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
 		state->color_mgmt_changed |= replaced;
 		return ret;
 	} else if (property == config->prop_out_fence_ptr) {
-		s64 __user *fence_ptr = u64_to_user_ptr(val);
+		s32 __user *fence_ptr = u64_to_user_ptr(val);
 
 		if (!fence_ptr)
 			return 0;
@@ -1915,7 +1915,7 @@ EXPORT_SYMBOL(drm_atomic_clean_old_fb);
  */
 
 struct drm_out_fence_state {
-	s64 __user *out_fence_ptr;
+	s32 __user *out_fence_ptr;
 	struct sync_file *sync_file;
 	int fd;
 };
@@ -1952,7 +1952,7 @@ static int prepare_crtc_signaling(struct drm_device *dev,
 		return 0;
 
 	for_each_crtc_in_state(state, crtc, crtc_state, i) {
-		u64 __user *fence_ptr;
+		s32 __user *fence_ptr;
 
 		fence_ptr = get_out_fence_for_crtc(crtc_state->state, crtc);
 
@@ -2032,13 +2032,16 @@ static void complete_crtc_signaling(struct drm_device *dev,
 	}
 
 	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		struct drm_pending_vblank_event *event = crtc_state->event;
 		/*
-		 * TEST_ONLY and PAGE_FLIP_EVENT are mutually
-		 * exclusive, if they weren't, this code should be
-		 * called on success for TEST_ONLY too.
+		 * Free the allocated event. drm_atomic_helper_setup_commit
+		 * can allocate an event too, so only free it if it's ours
+		 * to prevent a double free in drm_atomic_state_clear.
 		 */
-		if (crtc_state->event)
-			drm_event_cancel_free(dev, &crtc_state->event->base);
+		if (event && (event->base.fence || event->base.file_priv)) {
+			drm_event_cancel_free(dev, &event->base);
+			crtc_state->event = NULL;
+		}
 	}
 
 	if (!fence_state)
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 34f757bcabae..4594477dee00 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1666,9 +1666,6 @@ int drm_atomic_helper_prepare_planes(struct drm_device *dev,
 
 		funcs = plane->helper_private;
 
-		if (!drm_atomic_helper_framebuffer_changed(dev, state, plane_state->crtc))
-			continue;
-
 		if (funcs->prepare_fb) {
 			ret = funcs->prepare_fb(plane, plane_state);
 			if (ret)
@@ -1685,9 +1682,6 @@ fail:
 		if (j >= i)
 			continue;
 
-		if (!drm_atomic_helper_framebuffer_changed(dev, state, plane_state->crtc))
-			continue;
-
 		funcs = plane->helper_private;
 
 		if (funcs->cleanup_fb)
@@ -1954,9 +1948,6 @@ void drm_atomic_helper_cleanup_planes(struct drm_device *dev,
 	for_each_plane_in_state(old_state, plane, plane_state, i) {
 		const struct drm_plane_helper_funcs *funcs;
 
-		if (!drm_atomic_helper_framebuffer_changed(dev, old_state, plane_state->crtc))
-			continue;
-
 		funcs = plane->helper_private;
 
 		if (funcs->cleanup_fb)
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 5a4526289392..7a7019ac9388 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -225,6 +225,7 @@ int drm_connector_init(struct drm_device *dev,
 
 	INIT_LIST_HEAD(&connector->probed_modes);
 	INIT_LIST_HEAD(&connector->modes);
+	mutex_init(&connector->mutex);
 	connector->edid_blob_ptr = NULL;
 	connector->status = connector_status_unknown;
 
@@ -359,6 +360,8 @@ void drm_connector_cleanup(struct drm_connector *connector)
 		connector->funcs->atomic_destroy_state(connector,
 						       connector->state);
 
+	mutex_destroy(&connector->mutex);
+
 	memset(connector, 0, sizeof(*connector));
 }
 EXPORT_SYMBOL(drm_connector_cleanup);
@@ -374,14 +377,18 @@ EXPORT_SYMBOL(drm_connector_cleanup);
  */
 int drm_connector_register(struct drm_connector *connector)
 {
-	int ret;
+	int ret = 0;
 
-	if (connector->registered)
+	if (!connector->dev->registered)
 		return 0;
 
+	mutex_lock(&connector->mutex);
+	if (connector->registered)
+		goto unlock;
+
 	ret = drm_sysfs_connector_add(connector);
 	if (ret)
-		return ret;
+		goto unlock;
 
 	ret = drm_debugfs_connector_add(connector);
 	if (ret) {
@@ -397,12 +404,14 @@ int drm_connector_register(struct drm_connector *connector)
 	drm_mode_object_register(connector->dev, &connector->base);
 
 	connector->registered = true;
-	return 0;
+	goto unlock;
 
 err_debugfs:
 	drm_debugfs_connector_remove(connector);
 err_sysfs:
 	drm_sysfs_connector_remove(connector);
+unlock:
+	mutex_unlock(&connector->mutex);
 	return ret;
 }
 EXPORT_SYMBOL(drm_connector_register);
@@ -415,8 +424,11 @@ EXPORT_SYMBOL(drm_connector_register);
  */
 void drm_connector_unregister(struct drm_connector *connector)
 {
-	if (!connector->registered)
+	mutex_lock(&connector->mutex);
+	if (!connector->registered) {
+		mutex_unlock(&connector->mutex);
 		return;
+	}
 
 	if (connector->funcs->early_unregister)
 		connector->funcs->early_unregister(connector);
@@ -425,6 +437,7 @@ void drm_connector_unregister(struct drm_connector *connector)
 	drm_debugfs_connector_remove(connector);
 
 	connector->registered = false;
+	mutex_unlock(&connector->mutex);
 }
 EXPORT_SYMBOL(drm_connector_unregister);
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index aa644487749c..f59771da52ee 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1817,7 +1817,7 @@ int drm_dp_update_payload_part1(struct drm_dp_mst_topology_mgr *mgr)
 				mgr->payloads[i].vcpi = req_payload.vcpi;
 			} else if (mgr->payloads[i].num_slots) {
 				mgr->payloads[i].num_slots = 0;
-				drm_dp_destroy_payload_step1(mgr, port, port->vcpi.vcpi, &mgr->payloads[i]);
+				drm_dp_destroy_payload_step1(mgr, port, mgr->payloads[i].vcpi, &mgr->payloads[i]);
 				req_payload.payload_state = mgr->payloads[i].payload_state;
 				mgr->payloads[i].start_slot = 0;
 			}
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index a525751b4559..6594b4088f11 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -745,6 +745,8 @@ int drm_dev_register(struct drm_device *dev, unsigned long flags)
 	if (ret)
 		goto err_minors;
 
+	dev->registered = true;
+
 	if (dev->driver->load) {
 		ret = dev->driver->load(dev, flags);
 		if (ret)
@@ -785,6 +787,8 @@ void drm_dev_unregister(struct drm_device *dev)
 
 	drm_lastclose(dev);
 
+	dev->registered = false;
+
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_modeset_unregister_all(dev);
 
diff --git a/drivers/gpu/drm/drm_gem_cma_helper.c b/drivers/gpu/drm/drm_gem_cma_helper.c
index 1d6c335584ec..33cd51632721 100644
--- a/drivers/gpu/drm/drm_gem_cma_helper.c
+++ b/drivers/gpu/drm/drm_gem_cma_helper.c
@@ -376,7 +376,7 @@ void drm_gem_cma_describe(struct drm_gem_cma_object *cma_obj,
 	off = drm_vma_node_start(&obj->vma_node);
 
 	seq_printf(m, "%2d (%2d) %08llx %pad %p %zu",
-			obj->name, obj->refcount.refcount.counter,
+			obj->name, kref_read(&obj->refcount),
 			off, &cma_obj->paddr, cma_obj->vaddr, obj->size);
 
 	seq_printf(m, "\n");
diff --git a/drivers/gpu/drm/drm_info.c b/drivers/gpu/drm/drm_info.c
index ffb2ab389d1d..6b68e9088436 100644
--- a/drivers/gpu/drm/drm_info.c
+++ b/drivers/gpu/drm/drm_info.c
@@ -118,7 +118,7 @@ static int drm_gem_one_name_info(int id, void *ptr, void *data)
 	seq_printf(m, "%6d %8zd %7d %8d\n",
 		   obj->name, obj->size,
 		   obj->handle_count,
-		   atomic_read(&obj->refcount.refcount));
+		   kref_read(&obj->refcount));
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index 9f17085b1fdd..c6885a4911c0 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -159,7 +159,7 @@ EXPORT_SYMBOL(drm_mode_object_find);
 void drm_mode_object_unreference(struct drm_mode_object *obj)
 {
 	if (obj->free_cb) {
-		DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, atomic_read(&obj->refcount.refcount));
+		DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, kref_read(&obj->refcount));
 		kref_put(&obj->refcount, obj->free_cb);
 	}
 }
@@ -176,7 +176,7 @@ EXPORT_SYMBOL(drm_mode_object_unreference);
 void drm_mode_object_reference(struct drm_mode_object *obj)
 {
 	if (obj->free_cb) {
-		DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, atomic_read(&obj->refcount.refcount));
+		DRM_DEBUG("OBJ ID: %d (%d)\n", obj->id, kref_read(&obj->refcount));
 		kref_get(&obj->refcount);
 	}
 }
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index ac6a35212501..e6b19bc9021a 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1460,6 +1460,13 @@ drm_mode_create_from_cmdline_mode(struct drm_device *dev,
 		return NULL;
 
 	mode->type |= DRM_MODE_TYPE_USERDEF;
+	/* fix up 1368x768: GFT/CVT can't express 1366 width due to alignment */
+	if (cmd->xres == 1366 && mode->hdisplay == 1368) {
+		mode->hdisplay = 1366;
+		mode->hsync_start--;
+		mode->hsync_end--;
+		drm_mode_set_name(mode);
+	}
 	drm_mode_set_crtcinfo(mode, CRTC_INTERLACE_HALVE_V);
 	return mode;
 }
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index ac953f037be7..cf8f0128c161 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -143,8 +143,18 @@ void drm_kms_helper_poll_enable_locked(struct drm_device *dev)
 	}
 
 	if (dev->mode_config.delayed_event) {
+		/*
+		 * FIXME:
+		 *
+		 * Use short (1s) delay to handle the initial delayed event.
+		 * This delay should not be needed, but Optimus/nouveau will
+		 * fail in a mysterious way if the delayed event is handled as
+		 * soon as possible like it is done in
+		 * drm_helper_probe_single_connector_modes() in case the poll
+		 * was enabled before.
+		 */
 		poll = true;
-		delay = 0;
+		delay = HZ;
 	}
 
 	if (poll)
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 114dddbd297b..aa6e35ddc87f 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -486,7 +486,7 @@ static void etnaviv_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 
 	seq_printf(m, "%08x: %c %2d (%2d) %08lx %p %zd\n",
 			etnaviv_obj->flags, is_active(etnaviv_obj) ? 'A' : 'I',
-			obj->name, obj->refcount.refcount.counter,
+			obj->name, kref_read(&obj->refcount),
 			off, etnaviv_obj->vaddr, obj->size);
 
 	rcu_read_lock();
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index 169ac96e8f08..fe0e85b41310 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -116,9 +116,14 @@ static int etnaviv_iommu_find_iova(struct etnaviv_iommu *mmu,
 		struct list_head list;
 		bool found;
 
+		/*
+		 * XXX: The DRM_MM_SEARCH_BELOW is really a hack to trick
+		 * drm_mm into giving out a low IOVA after address space
+		 * rollover. This needs a proper fix.
+		 */
 		ret = drm_mm_insert_node_in_range(&mmu->mm, node,
 			size, 0, mmu->last_iova, ~0UL,
-			DRM_MM_SEARCH_DEFAULT);
+			mmu->last_iova ? DRM_MM_SEARCH_DEFAULT : DRM_MM_SEARCH_BELOW);
 
 		if (ret != -ENOSPC)
 			break;
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 6ca1f3117fe8..75eeb831ed6a 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -46,7 +46,8 @@ enum decon_flag_bits {
 	BIT_CLKS_ENABLED,
 	BIT_IRQS_ENABLED,
 	BIT_WIN_UPDATED,
-	BIT_SUSPENDED
+	BIT_SUSPENDED,
+	BIT_REQUEST_UPDATE
 };
 
 struct decon_context {
@@ -141,12 +142,6 @@ static void decon_commit(struct exynos_drm_crtc *crtc)
 		m->crtc_vsync_end = m->crtc_vsync_start + 1;
 	}
 
-	decon_set_bits(ctx, DECON_VIDCON0, VIDCON0_ENVID, 0);
-
-	/* enable clock gate */
-	val = CMU_CLKGAGE_MODE_SFR_F | CMU_CLKGAGE_MODE_MEM_F;
-	writel(val, ctx->addr + DECON_CMU);
-
 	if (ctx->out_type & (IFTYPE_I80 | I80_HW_TRG))
 		decon_setup_trigger(ctx);
 
@@ -315,6 +310,7 @@ static void decon_update_plane(struct exynos_drm_crtc *crtc,
 
 	/* window enable */
 	decon_set_bits(ctx, DECON_WINCONx(win), WINCONx_ENWIN_F, ~0);
+	set_bit(BIT_REQUEST_UPDATE, &ctx->flags);
 }
 
 static void decon_disable_plane(struct exynos_drm_crtc *crtc,
@@ -327,6 +323,7 @@ static void decon_disable_plane(struct exynos_drm_crtc *crtc,
 		return;
 
 	decon_set_bits(ctx, DECON_WINCONx(win), WINCONx_ENWIN_F, 0);
+	set_bit(BIT_REQUEST_UPDATE, &ctx->flags);
 }
 
 static void decon_atomic_flush(struct exynos_drm_crtc *crtc)
@@ -340,8 +337,8 @@ static void decon_atomic_flush(struct exynos_drm_crtc *crtc)
 	for (i = ctx->first_win; i < WINDOWS_NR; i++)
 		decon_shadow_protect_win(ctx, i, false);
 
-	/* standalone update */
-	decon_set_bits(ctx, DECON_UPDATE, STANDALONE_UPDATE_F, ~0);
+	if (test_and_clear_bit(BIT_REQUEST_UPDATE, &ctx->flags))
+		decon_set_bits(ctx, DECON_UPDATE, STANDALONE_UPDATE_F, ~0);
 
 	if (ctx->out_type & IFTYPE_I80)
 		set_bit(BIT_WIN_UPDATED, &ctx->flags);
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 0d41ebc4aea6..f7bce8603958 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -37,13 +37,6 @@
 #include "i915_drv.h"
 #include "gvt.h"
 
-#define MB_TO_BYTES(mb) ((mb) << 20ULL)
-#define BYTES_TO_MB(b) ((b) >> 20ULL)
-
-#define HOST_LOW_GM_SIZE MB_TO_BYTES(128)
-#define HOST_HIGH_GM_SIZE MB_TO_BYTES(384)
-#define HOST_FENCE 4
-
 static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
@@ -165,6 +158,14 @@ void intel_vgpu_write_fence(struct intel_vgpu *vgpu,
 	POSTING_READ(fence_reg_lo);
 }
 
+static void _clear_vgpu_fence(struct intel_vgpu *vgpu)
+{
+	int i;
+
+	for (i = 0; i < vgpu_fence_sz(vgpu); i++)
+		intel_vgpu_write_fence(vgpu, i, 0);
+}
+
 static void free_vgpu_fence(struct intel_vgpu *vgpu)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
@@ -178,9 +179,9 @@ static void free_vgpu_fence(struct intel_vgpu *vgpu)
 	intel_runtime_pm_get(dev_priv);
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
+	_clear_vgpu_fence(vgpu);
 	for (i = 0; i < vgpu_fence_sz(vgpu); i++) {
 		reg = vgpu->fence.regs[i];
-		intel_vgpu_write_fence(vgpu, i, 0);
 		list_add_tail(&reg->link,
 			      &dev_priv->mm.fence_list);
 	}
@@ -208,13 +209,14 @@ static int alloc_vgpu_fence(struct intel_vgpu *vgpu)
 			continue;
 		list_del(pos);
 		vgpu->fence.regs[i] = reg;
-		intel_vgpu_write_fence(vgpu, i, 0);
 		if (++i == vgpu_fence_sz(vgpu))
 			break;
 	}
 	if (i != vgpu_fence_sz(vgpu))
 		goto out_free_fence;
 
+	_clear_vgpu_fence(vgpu);
+
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 	intel_runtime_pm_put(dev_priv);
 	return 0;
@@ -314,6 +316,22 @@ void intel_vgpu_free_resource(struct intel_vgpu *vgpu)
 }
 
 /**
+ * intel_vgpu_reset_resource - reset resource state owned by a vGPU
+ * @vgpu: a vGPU
+ *
+ * This function is used to reset resource state owned by a vGPU.
+ *
+ */
+void intel_vgpu_reset_resource(struct intel_vgpu *vgpu)
+{
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+
+	intel_runtime_pm_get(dev_priv);
+	_clear_vgpu_fence(vgpu);
+	intel_runtime_pm_put(dev_priv);
+}
+
+/**
  * intel_alloc_vgpu_resource - allocate HW resource for a vGPU
  * @vgpu: vGPU
  * @param: vGPU creation params
diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c
index 711c31c8d8b4..4a6a2ed65732 100644
--- a/drivers/gpu/drm/i915/gvt/cfg_space.c
+++ b/drivers/gpu/drm/i915/gvt/cfg_space.c
@@ -282,3 +282,77 @@ int intel_vgpu_emulate_cfg_write(struct intel_vgpu *vgpu, unsigned int offset,
 	}
 	return 0;
 }
+
+/**
+ * intel_vgpu_init_cfg_space - init vGPU configuration space when create vGPU
+ *
+ * @vgpu: a vGPU
+ * @primary: is the vGPU presented as primary
+ *
+ */
+void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu,
+			       bool primary)
+{
+	struct intel_gvt *gvt = vgpu->gvt;
+	const struct intel_gvt_device_info *info = &gvt->device_info;
+	u16 *gmch_ctl;
+	int i;
+
+	memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space,
+	       info->cfg_space_size);
+
+	if (!primary) {
+		vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] =
+			INTEL_GVT_PCI_CLASS_VGA_OTHER;
+		vgpu_cfg_space(vgpu)[PCI_CLASS_PROG] =
+			INTEL_GVT_PCI_CLASS_VGA_OTHER;
+	}
+
+	/* Show guest that there isn't any stolen memory.*/
+	gmch_ctl = (u16 *)(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_GMCH_CONTROL);
+	*gmch_ctl &= ~(BDW_GMCH_GMS_MASK << BDW_GMCH_GMS_SHIFT);
+
+	intel_vgpu_write_pci_bar(vgpu, PCI_BASE_ADDRESS_2,
+				 gvt_aperture_pa_base(gvt), true);
+
+	vgpu_cfg_space(vgpu)[PCI_COMMAND] &= ~(PCI_COMMAND_IO
+					     | PCI_COMMAND_MEMORY
+					     | PCI_COMMAND_MASTER);
+	/*
+	 * Clear the bar upper 32bit and let guest to assign the new value
+	 */
+	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4);
+	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4);
+	memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4);
+
+	for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) {
+		vgpu->cfg_space.bar[i].size = pci_resource_len(
+					      gvt->dev_priv->drm.pdev, i * 2);
+		vgpu->cfg_space.bar[i].tracked = false;
+	}
+}
+
+/**
+ * intel_vgpu_reset_cfg_space - reset vGPU configuration space
+ *
+ * @vgpu: a vGPU
+ *
+ */
+void intel_vgpu_reset_cfg_space(struct intel_vgpu *vgpu)
+{
+	u8 cmd = vgpu_cfg_space(vgpu)[PCI_COMMAND];
+	bool primary = vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] !=
+				INTEL_GVT_PCI_CLASS_VGA_OTHER;
+
+	if (cmd & PCI_COMMAND_MEMORY) {
+		trap_gttmmio(vgpu, false);
+		map_aperture(vgpu, false);
+	}
+
+	/**
+	 * Currently we only do such reset when vGPU is not
+	 * owned by any VM, so we simply restore entire cfg
+	 * space to default value.
+	 */
+	intel_vgpu_init_cfg_space(vgpu, primary);
+}
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index d26a092c70e8..e4563984cb1e 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -481,7 +481,6 @@ struct parser_exec_state {
 	(s->vgpu->gvt->device_info.gmadr_bytes_in_cmd >> 2)
 
 static unsigned long bypass_scan_mask = 0;
-static bool bypass_batch_buffer_scan = true;
 
 /* ring ALL, type = 0 */
 static struct sub_op_bits sub_op_mi[] = {
@@ -1525,9 +1524,6 @@ static int batch_buffer_needs_scan(struct parser_exec_state *s)
 {
 	struct intel_gvt *gvt = s->vgpu->gvt;
 
-	if (bypass_batch_buffer_scan)
-		return 0;
-
 	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)) {
 		/* BDW decides privilege based on address space */
 		if (cmd_val(s, 0) & (1 << 8))
diff --git a/drivers/gpu/drm/i915/gvt/execlist.c b/drivers/gpu/drm/i915/gvt/execlist.c
index f32bb6f6495c..34083731669d 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.c
+++ b/drivers/gpu/drm/i915/gvt/execlist.c
@@ -364,58 +364,30 @@ static void free_workload(struct intel_vgpu_workload *workload)
 #define get_desc_from_elsp_dwords(ed, i) \
 	((struct execlist_ctx_descriptor_format *)&((ed)->data[i * 2]))
 
-
-#define BATCH_BUFFER_ADDR_MASK ((1UL << 32) - (1U << 2))
-#define BATCH_BUFFER_ADDR_HIGH_MASK ((1UL << 16) - (1U))
-static int set_gma_to_bb_cmd(struct intel_shadow_bb_entry *entry_obj,
-			     unsigned long add, int gmadr_bytes)
-{
-	if (WARN_ON(gmadr_bytes != 4 && gmadr_bytes != 8))
-		return -1;
-
-	*((u32 *)(entry_obj->bb_start_cmd_va + (1 << 2))) = add &
-		BATCH_BUFFER_ADDR_MASK;
-	if (gmadr_bytes == 8) {
-		*((u32 *)(entry_obj->bb_start_cmd_va + (2 << 2))) =
-			add & BATCH_BUFFER_ADDR_HIGH_MASK;
-	}
-
-	return 0;
-}
-
 static void prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 {
-	int gmadr_bytes = workload->vgpu->gvt->device_info.gmadr_bytes_in_cmd;
+	const int gmadr_bytes = workload->vgpu->gvt->device_info.gmadr_bytes_in_cmd;
+	struct intel_shadow_bb_entry *entry_obj;
 
 	/* pin the gem object to ggtt */
-	if (!list_empty(&workload->shadow_bb)) {
-		struct intel_shadow_bb_entry *entry_obj =
-			list_first_entry(&workload->shadow_bb,
-					 struct intel_shadow_bb_entry,
-					 list);
-		struct intel_shadow_bb_entry *temp;
+	list_for_each_entry(entry_obj, &workload->shadow_bb, list) {
+		struct i915_vma *vma;
 
-		list_for_each_entry_safe(entry_obj, temp, &workload->shadow_bb,
-				list) {
-			struct i915_vma *vma;
-
-			vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0,
-						       4, 0);
-			if (IS_ERR(vma)) {
-				gvt_err("Cannot pin\n");
-				return;
-			}
-
-			/* FIXME: we are not tracking our pinned VMA leaving it
-			 * up to the core to fix up the stray pin_count upon
-			 * free.
-			 */
-
-			/* update the relocate gma with shadow batch buffer*/
-			set_gma_to_bb_cmd(entry_obj,
-					  i915_ggtt_offset(vma),
-					  gmadr_bytes);
+		vma = i915_gem_object_ggtt_pin(entry_obj->obj, NULL, 0, 4, 0);
+		if (IS_ERR(vma)) {
+			gvt_err("Cannot pin\n");
+			return;
 		}
+
+		/* FIXME: we are not tracking our pinned VMA leaving it
+		 * up to the core to fix up the stray pin_count upon
+		 * free.
+		 */
+
+		/* update the relocate gma with shadow batch buffer*/
+		entry_obj->bb_start_cmd_va[1] = i915_ggtt_offset(vma);
+		if (gmadr_bytes == 8)
+			entry_obj->bb_start_cmd_va[2] = 0;
 	}
 }
 
@@ -826,7 +798,7 @@ int intel_vgpu_init_execlist(struct intel_vgpu *vgpu)
 		INIT_LIST_HEAD(&vgpu->workload_q_head[i]);
 	}
 
-	vgpu->workloads = kmem_cache_create("gvt-g vgpu workload",
+	vgpu->workloads = kmem_cache_create("gvt-g_vgpu_workload",
 			sizeof(struct intel_vgpu_workload), 0,
 			SLAB_HWCACHE_ALIGN,
 			NULL);
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 6c5fdf5b2ce2..47dec4acf7ff 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -240,15 +240,8 @@ static inline int get_pse_type(int type)
 static u64 read_pte64(struct drm_i915_private *dev_priv, unsigned long index)
 {
 	void __iomem *addr = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + index;
-	u64 pte;
 
-#ifdef readq
-	pte = readq(addr);
-#else
-	pte = ioread32(addr);
-	pte |= (u64)ioread32(addr + 4) << 32;
-#endif
-	return pte;
+	return readq(addr);
 }
 
 static void write_pte64(struct drm_i915_private *dev_priv,
@@ -256,12 +249,8 @@ static void write_pte64(struct drm_i915_private *dev_priv,
 {
 	void __iomem *addr = (gen8_pte_t __iomem *)dev_priv->ggtt.gsm + index;
 
-#ifdef writeq
 	writeq(pte, addr);
-#else
-	iowrite32((u32)pte, addr);
-	iowrite32(pte >> 32, addr + 4);
-#endif
+
 	I915_WRITE(GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
 	POSTING_READ(GFX_FLSH_CNTL_GEN6);
 }
@@ -1380,8 +1369,7 @@ static int gen8_mm_alloc_page_table(struct intel_vgpu_mm *mm)
 			info->gtt_entry_size;
 		mem = kzalloc(mm->has_shadow_page_table ?
 			mm->page_table_entry_size * 2
-				: mm->page_table_entry_size,
-			GFP_ATOMIC);
+				: mm->page_table_entry_size, GFP_KERNEL);
 		if (!mem)
 			return -ENOMEM;
 		mm->virtual_page_table = mem;
@@ -1532,7 +1520,7 @@ struct intel_vgpu_mm *intel_vgpu_create_mm(struct intel_vgpu *vgpu,
 	struct intel_vgpu_mm *mm;
 	int ret;
 
-	mm = kzalloc(sizeof(*mm), GFP_ATOMIC);
+	mm = kzalloc(sizeof(*mm), GFP_KERNEL);
 	if (!mm) {
 		ret = -ENOMEM;
 		goto fail;
@@ -1886,30 +1874,27 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu,
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	int page_entry_num = GTT_PAGE_SIZE >>
 				vgpu->gvt->device_info.gtt_entry_size_shift;
-	struct page *scratch_pt;
+	void *scratch_pt;
 	unsigned long mfn;
 	int i;
-	void *p;
 
 	if (WARN_ON(type < GTT_TYPE_PPGTT_PTE_PT || type >= GTT_TYPE_MAX))
 		return -EINVAL;
 
-	scratch_pt = alloc_page(GFP_KERNEL | GFP_ATOMIC | __GFP_ZERO);
+	scratch_pt = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!scratch_pt) {
 		gvt_err("fail to allocate scratch page\n");
 		return -ENOMEM;
 	}
 
-	p = kmap_atomic(scratch_pt);
-	mfn = intel_gvt_hypervisor_virt_to_mfn(p);
+	mfn = intel_gvt_hypervisor_virt_to_mfn(scratch_pt);
 	if (mfn == INTEL_GVT_INVALID_ADDR) {
-		gvt_err("fail to translate vaddr:0x%llx\n", (u64)p);
-		kunmap_atomic(p);
-		__free_page(scratch_pt);
+		gvt_err("fail to translate vaddr:0x%lx\n", (unsigned long)scratch_pt);
+		free_page((unsigned long)scratch_pt);
 		return -EFAULT;
 	}
 	gtt->scratch_pt[type].page_mfn = mfn;
-	gtt->scratch_pt[type].page = scratch_pt;
+	gtt->scratch_pt[type].page = virt_to_page(scratch_pt);
 	gvt_dbg_mm("vgpu%d create scratch_pt: type %d mfn=0x%lx\n",
 			vgpu->id, type, mfn);
 
@@ -1918,7 +1903,7 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu,
 	 * scratch_pt[type] indicate the scratch pt/scratch page used by the
 	 * 'type' pt.
 	 * e.g. scratch_pt[GTT_TYPE_PPGTT_PDE_PT] is used by
-	 * GTT_TYPE_PPGTT_PDE_PT level pt, that means this scatch_pt it self
+	 * GTT_TYPE_PPGTT_PDE_PT level pt, that means this scratch_pt it self
 	 * is GTT_TYPE_PPGTT_PTE_PT, and full filled by scratch page mfn.
 	 */
 	if (type > GTT_TYPE_PPGTT_PTE_PT && type < GTT_TYPE_MAX) {
@@ -1936,11 +1921,9 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu,
 			se.val64 |= PPAT_CACHED_INDEX;
 
 		for (i = 0; i < page_entry_num; i++)
-			ops->set_entry(p, &se, i, false, 0, vgpu);
+			ops->set_entry(scratch_pt, &se, i, false, 0, vgpu);
 	}
 
-	kunmap_atomic(p);
-
 	return 0;
 }
 
@@ -2208,7 +2191,7 @@ int intel_vgpu_g2v_destroy_ppgtt_mm(struct intel_vgpu *vgpu,
 int intel_gvt_init_gtt(struct intel_gvt *gvt)
 {
 	int ret;
-	void *page_addr;
+	void *page;
 
 	gvt_dbg_core("init gtt\n");
 
@@ -2221,17 +2204,14 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt)
 		return -ENODEV;
 	}
 
-	gvt->gtt.scratch_ggtt_page =
-		alloc_page(GFP_KERNEL | GFP_ATOMIC | __GFP_ZERO);
-	if (!gvt->gtt.scratch_ggtt_page) {
+	page = (void *)get_zeroed_page(GFP_KERNEL);
+	if (!page) {
 		gvt_err("fail to allocate scratch ggtt page\n");
 		return -ENOMEM;
 	}
+	gvt->gtt.scratch_ggtt_page = virt_to_page(page);
 
-	page_addr = page_address(gvt->gtt.scratch_ggtt_page);
-
-	gvt->gtt.scratch_ggtt_mfn =
-		intel_gvt_hypervisor_virt_to_mfn(page_addr);
+	gvt->gtt.scratch_ggtt_mfn = intel_gvt_hypervisor_virt_to_mfn(page);
 	if (gvt->gtt.scratch_ggtt_mfn == INTEL_GVT_INVALID_ADDR) {
 		gvt_err("fail to translate scratch ggtt page\n");
 		__free_page(gvt->gtt.scratch_ggtt_page);
@@ -2297,3 +2277,30 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu)
 	for (offset = 0; offset < num_entries; offset++)
 		ops->set_entry(NULL, &e, index + offset, false, 0, vgpu);
 }
+
+/**
+ * intel_vgpu_reset_gtt - reset the all GTT related status
+ * @vgpu: a vGPU
+ * @dmlr: true for vGPU Device Model Level Reset, false for GT Reset
+ *
+ * This function is called from vfio core to reset reset all
+ * GTT related status, including GGTT, PPGTT, scratch page.
+ *
+ */
+void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr)
+{
+	int i;
+
+	ppgtt_free_all_shadow_page(vgpu);
+	if (!dmlr)
+		return;
+
+	intel_vgpu_reset_ggtt(vgpu);
+
+	/* clear scratch page for security */
+	for (i = GTT_TYPE_PPGTT_PTE_PT; i < GTT_TYPE_MAX; i++) {
+		if (vgpu->gtt.scratch_pt[i].page != NULL)
+			memset(page_address(vgpu->gtt.scratch_pt[i].page),
+				0, PAGE_SIZE);
+	}
+}
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index b315ab3593ec..f88eb5e89bea 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -208,6 +208,7 @@ extern void intel_vgpu_clean_gtt(struct intel_vgpu *vgpu);
 void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu);
 
 extern int intel_gvt_init_gtt(struct intel_gvt *gvt);
+extern void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu, bool dmlr);
 extern void intel_gvt_clean_gtt(struct intel_gvt *gvt);
 
 extern struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu,
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 398877c3d2fd..e6bf5c533fbe 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -201,6 +201,8 @@ void intel_gvt_clean_device(struct drm_i915_private *dev_priv)
 	intel_gvt_hypervisor_host_exit(&dev_priv->drm.pdev->dev, gvt);
 	intel_gvt_clean_vgpu_types(gvt);
 
+	idr_destroy(&gvt->vgpu_idr);
+
 	kfree(dev_priv->gvt);
 	dev_priv->gvt = NULL;
 }
@@ -237,6 +239,8 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv)
 
 	gvt_dbg_core("init gvt device\n");
 
+	idr_init(&gvt->vgpu_idr);
+
 	mutex_init(&gvt->lock);
 	gvt->dev_priv = dev_priv;
 
@@ -244,7 +248,7 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv)
 
 	ret = intel_gvt_setup_mmio_info(gvt);
 	if (ret)
-		return ret;
+		goto out_clean_idr;
 
 	ret = intel_gvt_load_firmware(gvt);
 	if (ret)
@@ -313,6 +317,8 @@ out_free_firmware:
 	intel_gvt_free_firmware(gvt);
 out_clean_mmio_info:
 	intel_gvt_clean_mmio_info(gvt);
+out_clean_idr:
+	idr_destroy(&gvt->vgpu_idr);
 	kfree(gvt);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 0af17016f33f..e227caf5859e 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -323,6 +323,7 @@ struct intel_vgpu_creation_params {
 
 int intel_vgpu_alloc_resource(struct intel_vgpu *vgpu,
 			      struct intel_vgpu_creation_params *param);
+void intel_vgpu_reset_resource(struct intel_vgpu *vgpu);
 void intel_vgpu_free_resource(struct intel_vgpu *vgpu);
 void intel_vgpu_write_fence(struct intel_vgpu *vgpu,
 	u32 fence, u64 value);
@@ -375,6 +376,8 @@ void intel_gvt_clean_vgpu_types(struct intel_gvt *gvt);
 struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
 					 struct intel_vgpu_type *type);
 void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu);
+void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
+				 unsigned int engine_mask);
 void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu);
 
 
@@ -411,6 +414,10 @@ int intel_gvt_ggtt_index_g2h(struct intel_vgpu *vgpu, unsigned long g_index,
 int intel_gvt_ggtt_h2g_index(struct intel_vgpu *vgpu, unsigned long h_index,
 			     unsigned long *g_index);
 
+void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu,
+		bool primary);
+void intel_vgpu_reset_cfg_space(struct intel_vgpu *vgpu);
+
 int intel_vgpu_emulate_cfg_read(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes);
 
@@ -424,7 +431,6 @@ void intel_vgpu_clean_opregion(struct intel_vgpu *vgpu);
 int intel_vgpu_init_opregion(struct intel_vgpu *vgpu, u32 gpa);
 
 int intel_vgpu_emulate_opregion_request(struct intel_vgpu *vgpu, u32 swsci);
-int setup_vgpu_mmio(struct intel_vgpu *vgpu);
 void populate_pvinfo_page(struct intel_vgpu *vgpu);
 
 struct intel_gvt_ops {
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 522809710312..ab2ea157da4c 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -93,7 +93,8 @@ static void write_vreg(struct intel_vgpu *vgpu, unsigned int offset,
 static int new_mmio_info(struct intel_gvt *gvt,
 		u32 offset, u32 flags, u32 size,
 		u32 addr_mask, u32 ro_mask, u32 device,
-		void *read, void *write)
+		int (*read)(struct intel_vgpu *, unsigned int, void *, unsigned int),
+		int (*write)(struct intel_vgpu *, unsigned int, void *, unsigned int))
 {
 	struct intel_gvt_mmio_info *info, *p;
 	u32 start, end, i;
@@ -219,7 +220,7 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu,
 		default:
 			/*should not hit here*/
 			gvt_err("invalid forcewake offset 0x%x\n", offset);
-			return 1;
+			return -EINVAL;
 		}
 	} else {
 		ack_reg_offset = FORCEWAKE_ACK_HSW_REG;
@@ -230,77 +231,45 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu,
 	return 0;
 }
 
-static int handle_device_reset(struct intel_vgpu *vgpu, unsigned int offset,
-		void *p_data, unsigned int bytes, unsigned long bitmap)
-{
-	struct intel_gvt_workload_scheduler *scheduler =
-		&vgpu->gvt->scheduler;
-
-	vgpu->resetting = true;
-
-	intel_vgpu_stop_schedule(vgpu);
-	/*
-	 * The current_vgpu will set to NULL after stopping the
-	 * scheduler when the reset is triggered by current vgpu.
-	 */
-	if (scheduler->current_vgpu == NULL) {
-		mutex_unlock(&vgpu->gvt->lock);
-		intel_gvt_wait_vgpu_idle(vgpu);
-		mutex_lock(&vgpu->gvt->lock);
-	}
-
-	intel_vgpu_reset_execlist(vgpu, bitmap);
-
-	/* full GPU reset */
-	if (bitmap == 0xff) {
-		mutex_unlock(&vgpu->gvt->lock);
-		intel_vgpu_clean_gtt(vgpu);
-		mutex_lock(&vgpu->gvt->lock);
-		setup_vgpu_mmio(vgpu);
-		populate_pvinfo_page(vgpu);
-		intel_vgpu_init_gtt(vgpu);
-	}
-
-	vgpu->resetting = false;
-
-	return 0;
-}
-
 static int gdrst_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
-		void *p_data, unsigned int bytes)
+			    void *p_data, unsigned int bytes)
 {
+	unsigned int engine_mask = 0;
 	u32 data;
-	u64 bitmap = 0;
 
 	write_vreg(vgpu, offset, p_data, bytes);
 	data = vgpu_vreg(vgpu, offset);
 
 	if (data & GEN6_GRDOM_FULL) {
 		gvt_dbg_mmio("vgpu%d: request full GPU reset\n", vgpu->id);
-		bitmap = 0xff;
-	}
-	if (data & GEN6_GRDOM_RENDER) {
-		gvt_dbg_mmio("vgpu%d: request RCS reset\n", vgpu->id);
-		bitmap |= (1 << RCS);
-	}
-	if (data & GEN6_GRDOM_MEDIA) {
-		gvt_dbg_mmio("vgpu%d: request VCS reset\n", vgpu->id);
-		bitmap |= (1 << VCS);
-	}
-	if (data & GEN6_GRDOM_BLT) {
-		gvt_dbg_mmio("vgpu%d: request BCS Reset\n", vgpu->id);
-		bitmap |= (1 << BCS);
-	}
-	if (data & GEN6_GRDOM_VECS) {
-		gvt_dbg_mmio("vgpu%d: request VECS Reset\n", vgpu->id);
-		bitmap |= (1 << VECS);
-	}
-	if (data & GEN8_GRDOM_MEDIA2) {
-		gvt_dbg_mmio("vgpu%d: request VCS2 Reset\n", vgpu->id);
-		if (HAS_BSD2(vgpu->gvt->dev_priv))
-			bitmap |= (1 << VCS2);
+		engine_mask = ALL_ENGINES;
+	} else {
+		if (data & GEN6_GRDOM_RENDER) {
+			gvt_dbg_mmio("vgpu%d: request RCS reset\n", vgpu->id);
+			engine_mask |= (1 << RCS);
+		}
+		if (data & GEN6_GRDOM_MEDIA) {
+			gvt_dbg_mmio("vgpu%d: request VCS reset\n", vgpu->id);
+			engine_mask |= (1 << VCS);
+		}
+		if (data & GEN6_GRDOM_BLT) {
+			gvt_dbg_mmio("vgpu%d: request BCS Reset\n", vgpu->id);
+			engine_mask |= (1 << BCS);
+		}
+		if (data & GEN6_GRDOM_VECS) {
+			gvt_dbg_mmio("vgpu%d: request VECS Reset\n", vgpu->id);
+			engine_mask |= (1 << VECS);
+		}
+		if (data & GEN8_GRDOM_MEDIA2) {
+			gvt_dbg_mmio("vgpu%d: request VCS2 Reset\n", vgpu->id);
+			if (HAS_BSD2(vgpu->gvt->dev_priv))
+				engine_mask |= (1 << VCS2);
+		}
 	}
-	return handle_device_reset(vgpu, offset, p_data, bytes, bitmap);
+
+	intel_gvt_reset_vgpu_locked(vgpu, false, engine_mask);
+
+	return 0;
 }
 
 static int gmbus_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
@@ -974,7 +943,7 @@ static int sbi_data_mmio_read(struct intel_vgpu *vgpu, unsigned int offset,
 	return 0;
 }
 
-static bool sbi_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+static int sbi_ctl_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		void *p_data, unsigned int bytes)
 {
 	u32 data;
@@ -1366,7 +1335,6 @@ static int ring_mode_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 static int gvt_reg_tlb_control_handler(struct intel_vgpu *vgpu,
 		unsigned int offset, void *p_data, unsigned int bytes)
 {
-	int rc = 0;
 	unsigned int id = 0;
 
 	write_vreg(vgpu, offset, p_data, bytes);
@@ -1389,12 +1357,11 @@ static int gvt_reg_tlb_control_handler(struct intel_vgpu *vgpu,
 		id = VECS;
 		break;
 	default:
-		rc = -EINVAL;
-		break;
+		return -EINVAL;
 	}
 	set_bit(id, (void *)vgpu->tlb_handle_pending);
 
-	return rc;
+	return 0;
 }
 
 static int ring_reset_ctl_write(struct intel_vgpu *vgpu,
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index faaae07ae487..3f656e3a6e5a 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -230,8 +230,8 @@ static struct intel_vgpu_type *intel_gvt_find_vgpu_type(struct intel_gvt *gvt,
 	return NULL;
 }
 
-static ssize_t available_instance_show(struct kobject *kobj, struct device *dev,
-		char *buf)
+static ssize_t available_instances_show(struct kobject *kobj,
+					struct device *dev, char *buf)
 {
 	struct intel_vgpu_type *type;
 	unsigned int num = 0;
@@ -269,12 +269,12 @@ static ssize_t description_show(struct kobject *kobj, struct device *dev,
 				type->fence);
 }
 
-static MDEV_TYPE_ATTR_RO(available_instance);
+static MDEV_TYPE_ATTR_RO(available_instances);
 static MDEV_TYPE_ATTR_RO(device_api);
 static MDEV_TYPE_ATTR_RO(description);
 
 static struct attribute *type_attrs[] = {
-	&mdev_type_attr_available_instance.attr,
+	&mdev_type_attr_available_instances.attr,
 	&mdev_type_attr_device_api.attr,
 	&mdev_type_attr_description.attr,
 	NULL,
@@ -398,6 +398,7 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
 	struct intel_vgpu_type *type;
 	struct device *pdev;
 	void *gvt;
+	int ret;
 
 	pdev = mdev_parent_dev(mdev);
 	gvt = kdev_to_i915(pdev)->gvt;
@@ -406,13 +407,15 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
 	if (!type) {
 		gvt_err("failed to find type %s to create\n",
 						kobject_name(kobj));
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	vgpu = intel_gvt_ops->vgpu_create(gvt, type);
 	if (IS_ERR_OR_NULL(vgpu)) {
-		gvt_err("create intel vgpu failed\n");
-		return -EINVAL;
+		ret = vgpu == NULL ? -EFAULT : PTR_ERR(vgpu);
+		gvt_err("failed to create intel vgpu: %d\n", ret);
+		goto out;
 	}
 
 	INIT_WORK(&vgpu->vdev.release_work, intel_vgpu_release_work);
@@ -422,7 +425,10 @@ static int intel_vgpu_create(struct kobject *kobj, struct mdev_device *mdev)
 
 	gvt_dbg_core("intel_vgpu_create succeeded for mdev: %s\n",
 		     dev_name(mdev_dev(mdev)));
-	return 0;
+	ret = 0;
+
+out:
+	return ret;
 }
 
 static int intel_vgpu_remove(struct mdev_device *mdev)
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index 09c9450a1946..4df078bc5d04 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -125,25 +125,12 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
 	if (WARN_ON(!reg_is_mmio(gvt, offset + bytes - 1)))
 		goto err;
 
-	mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4));
-	if (!mmio && !vgpu->mmio.disable_warn_untrack) {
-		gvt_err("vgpu%d: read untracked MMIO %x len %d val %x\n",
-				vgpu->id, offset, bytes, *(u32 *)p_data);
-
-		if (offset == 0x206c) {
-			gvt_err("------------------------------------------\n");
-			gvt_err("vgpu%d: likely triggers a gfx reset\n",
-			vgpu->id);
-			gvt_err("------------------------------------------\n");
-			vgpu->mmio.disable_warn_untrack = true;
-		}
-	}
-
 	if (!intel_gvt_mmio_is_unalign(gvt, offset)) {
 		if (WARN_ON(!IS_ALIGNED(offset, bytes)))
 			goto err;
 	}
 
+	mmio = intel_gvt_find_mmio_info(gvt, rounddown(offset, 4));
 	if (mmio) {
 		if (!intel_gvt_mmio_is_unalign(gvt, mmio->offset)) {
 			if (WARN_ON(offset + bytes > mmio->offset + mmio->size))
@@ -152,9 +139,23 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
 				goto err;
 		}
 		ret = mmio->read(vgpu, offset, p_data, bytes);
-	} else
+	} else {
 		ret = intel_vgpu_default_mmio_read(vgpu, offset, p_data, bytes);
 
+		if (!vgpu->mmio.disable_warn_untrack) {
+			gvt_err("vgpu%d: read untracked MMIO %x(%dB) val %x\n",
+				vgpu->id, offset, bytes, *(u32 *)p_data);
+
+			if (offset == 0x206c) {
+				gvt_err("------------------------------------------\n");
+				gvt_err("vgpu%d: likely triggers a gfx reset\n",
+					vgpu->id);
+				gvt_err("------------------------------------------\n");
+				vgpu->mmio.disable_warn_untrack = true;
+			}
+		}
+	}
+
 	if (ret)
 		goto err;
 
@@ -302,3 +303,56 @@ err:
 	mutex_unlock(&gvt->lock);
 	return ret;
 }
+
+
+/**
+ * intel_vgpu_reset_mmio - reset virtual MMIO space
+ * @vgpu: a vGPU
+ *
+ */
+void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu)
+{
+	struct intel_gvt *gvt = vgpu->gvt;
+	const struct intel_gvt_device_info *info = &gvt->device_info;
+
+	memcpy(vgpu->mmio.vreg, gvt->firmware.mmio, info->mmio_size);
+	memcpy(vgpu->mmio.sreg, gvt->firmware.mmio, info->mmio_size);
+
+	vgpu_vreg(vgpu, GEN6_GT_THREAD_STATUS_REG) = 0;
+
+	/* set the bit 0:2(Core C-State ) to C0 */
+	vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0;
+}
+
+/**
+ * intel_vgpu_init_mmio - init MMIO  space
+ * @vgpu: a vGPU
+ *
+ * Returns:
+ * Zero on success, negative error code if failed
+ */
+int intel_vgpu_init_mmio(struct intel_vgpu *vgpu)
+{
+	const struct intel_gvt_device_info *info = &vgpu->gvt->device_info;
+
+	vgpu->mmio.vreg = vzalloc(info->mmio_size * 2);
+	if (!vgpu->mmio.vreg)
+		return -ENOMEM;
+
+	vgpu->mmio.sreg = vgpu->mmio.vreg + info->mmio_size;
+
+	intel_vgpu_reset_mmio(vgpu);
+
+	return 0;
+}
+
+/**
+ * intel_vgpu_clean_mmio - clean MMIO space
+ * @vgpu: a vGPU
+ *
+ */
+void intel_vgpu_clean_mmio(struct intel_vgpu *vgpu)
+{
+	vfree(vgpu->mmio.vreg);
+	vgpu->mmio.vreg = vgpu->mmio.sreg = NULL;
+}
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index 87d5b5e366a3..3bc620f56f35 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -86,6 +86,10 @@ struct intel_gvt_mmio_info *intel_gvt_find_mmio_info(struct intel_gvt *gvt,
 	*offset; \
 })
 
+int intel_vgpu_init_mmio(struct intel_vgpu *vgpu);
+void intel_vgpu_reset_mmio(struct intel_vgpu *vgpu);
+void intel_vgpu_clean_mmio(struct intel_vgpu *vgpu);
+
 int intel_vgpu_gpa_to_mmio_offset(struct intel_vgpu *vgpu, u64 gpa);
 
 int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, u64 pa,
diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c
index 81cd921770c6..d9fb41ab7119 100644
--- a/drivers/gpu/drm/i915/gvt/opregion.c
+++ b/drivers/gpu/drm/i915/gvt/opregion.c
@@ -36,9 +36,9 @@ static int init_vgpu_opregion(struct intel_vgpu *vgpu, u32 gpa)
 			vgpu->id))
 		return -EINVAL;
 
-	vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_ATOMIC |
-			GFP_DMA32 | __GFP_ZERO,
-			INTEL_GVT_OPREGION_PORDER);
+	vgpu_opregion(vgpu)->va = (void *)__get_free_pages(GFP_KERNEL |
+			__GFP_ZERO,
+			get_order(INTEL_GVT_OPREGION_SIZE));
 
 	if (!vgpu_opregion(vgpu)->va)
 		return -ENOMEM;
@@ -97,7 +97,7 @@ void intel_vgpu_clean_opregion(struct intel_vgpu *vgpu)
 	if (intel_gvt_host.hypervisor_type == INTEL_GVT_HYPERVISOR_XEN) {
 		map_vgpu_opregion(vgpu, false);
 		free_pages((unsigned long)vgpu_opregion(vgpu)->va,
-				INTEL_GVT_OPREGION_PORDER);
+				get_order(INTEL_GVT_OPREGION_SIZE));
 
 		vgpu_opregion(vgpu)->va = NULL;
 	}
diff --git a/drivers/gpu/drm/i915/gvt/reg.h b/drivers/gpu/drm/i915/gvt/reg.h
index 0dfe789d8f02..fbd023a16f18 100644
--- a/drivers/gpu/drm/i915/gvt/reg.h
+++ b/drivers/gpu/drm/i915/gvt/reg.h
@@ -50,8 +50,7 @@
 #define INTEL_GVT_OPREGION_PARM                   0x204
 
 #define INTEL_GVT_OPREGION_PAGES	2
-#define INTEL_GVT_OPREGION_PORDER	1
-#define INTEL_GVT_OPREGION_SIZE		(2 * 4096)
+#define INTEL_GVT_OPREGION_SIZE		(INTEL_GVT_OPREGION_PAGES * PAGE_SIZE)
 
 #define VGT_SPRSTRIDE(pipe)	_PIPE(pipe, _SPRA_STRIDE, _PLANE_STRIDE_2_B)
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 4db242250235..e91885dffeff 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -350,13 +350,15 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 {
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
 	struct intel_vgpu_workload *workload;
+	struct intel_vgpu *vgpu;
 	int event;
 
 	mutex_lock(&gvt->lock);
 
 	workload = scheduler->current_workload[ring_id];
+	vgpu = workload->vgpu;
 
-	if (!workload->status && !workload->vgpu->resetting) {
+	if (!workload->status && !vgpu->resetting) {
 		wait_event(workload->shadow_ctx_status_wq,
 			   !atomic_read(&workload->shadow_ctx_active));
 
@@ -364,8 +366,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 
 		for_each_set_bit(event, workload->pending_events,
 				 INTEL_GVT_EVENT_MAX)
-			intel_vgpu_trigger_virtual_event(workload->vgpu,
-					event);
+			intel_vgpu_trigger_virtual_event(vgpu, event);
 	}
 
 	gvt_dbg_sched("ring id %d complete workload %p status %d\n",
@@ -373,11 +374,10 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 
 	scheduler->current_workload[ring_id] = NULL;
 
-	atomic_dec(&workload->vgpu->running_workload_num);
-
 	list_del_init(&workload->list);
 	workload->complete(workload);
 
+	atomic_dec(&vgpu->running_workload_num);
 	wake_up(&scheduler->workload_complete_wq);
 	mutex_unlock(&gvt->lock);
 }
@@ -459,11 +459,11 @@ complete:
 		gvt_dbg_sched("will complete workload %p\n, status: %d\n",
 				workload, workload->status);
 
-		complete_current_workload(gvt, ring_id);
-
 		if (workload->req)
 			i915_gem_request_put(fetch_and_zero(&workload->req));
 
+		complete_current_workload(gvt, ring_id);
+
 		if (need_force_wake)
 			intel_uncore_forcewake_put(gvt->dev_priv,
 					FORCEWAKE_ALL);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 3b30c28bff51..2833dfa8c9ae 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -113,7 +113,7 @@ struct intel_shadow_bb_entry {
 	struct drm_i915_gem_object *obj;
 	void *va;
 	unsigned long len;
-	void *bb_start_cmd_va;
+	u32 *bb_start_cmd_va;
 };
 
 #define workload_q_head(vgpu, ring_id) \
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 536d2b9d5777..7295bc8e12fb 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -35,79 +35,6 @@
 #include "gvt.h"
 #include "i915_pvinfo.h"
 
-static void clean_vgpu_mmio(struct intel_vgpu *vgpu)
-{
-	vfree(vgpu->mmio.vreg);
-	vgpu->mmio.vreg = vgpu->mmio.sreg = NULL;
-}
-
-int setup_vgpu_mmio(struct intel_vgpu *vgpu)
-{
-	struct intel_gvt *gvt = vgpu->gvt;
-	const struct intel_gvt_device_info *info = &gvt->device_info;
-
-	if (vgpu->mmio.vreg)
-		memset(vgpu->mmio.vreg, 0, info->mmio_size * 2);
-	else {
-		vgpu->mmio.vreg = vzalloc(info->mmio_size * 2);
-		if (!vgpu->mmio.vreg)
-			return -ENOMEM;
-	}
-
-	vgpu->mmio.sreg = vgpu->mmio.vreg + info->mmio_size;
-
-	memcpy(vgpu->mmio.vreg, gvt->firmware.mmio, info->mmio_size);
-	memcpy(vgpu->mmio.sreg, gvt->firmware.mmio, info->mmio_size);
-
-	vgpu_vreg(vgpu, GEN6_GT_THREAD_STATUS_REG) = 0;
-
-	/* set the bit 0:2(Core C-State ) to C0 */
-	vgpu_vreg(vgpu, GEN6_GT_CORE_STATUS) = 0;
-	return 0;
-}
-
-static void setup_vgpu_cfg_space(struct intel_vgpu *vgpu,
-	struct intel_vgpu_creation_params *param)
-{
-	struct intel_gvt *gvt = vgpu->gvt;
-	const struct intel_gvt_device_info *info = &gvt->device_info;
-	u16 *gmch_ctl;
-	int i;
-
-	memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space,
-	       info->cfg_space_size);
-
-	if (!param->primary) {
-		vgpu_cfg_space(vgpu)[PCI_CLASS_DEVICE] =
-			INTEL_GVT_PCI_CLASS_VGA_OTHER;
-		vgpu_cfg_space(vgpu)[PCI_CLASS_PROG] =
-			INTEL_GVT_PCI_CLASS_VGA_OTHER;
-	}
-
-	/* Show guest that there isn't any stolen memory.*/
-	gmch_ctl = (u16 *)(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_GMCH_CONTROL);
-	*gmch_ctl &= ~(BDW_GMCH_GMS_MASK << BDW_GMCH_GMS_SHIFT);
-
-	intel_vgpu_write_pci_bar(vgpu, PCI_BASE_ADDRESS_2,
-				 gvt_aperture_pa_base(gvt), true);
-
-	vgpu_cfg_space(vgpu)[PCI_COMMAND] &= ~(PCI_COMMAND_IO
-					     | PCI_COMMAND_MEMORY
-					     | PCI_COMMAND_MASTER);
-	/*
-	 * Clear the bar upper 32bit and let guest to assign the new value
-	 */
-	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_1, 0, 4);
-	memset(vgpu_cfg_space(vgpu) + PCI_BASE_ADDRESS_3, 0, 4);
-	memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4);
-
-	for (i = 0; i < INTEL_GVT_MAX_BAR_NUM; i++) {
-		vgpu->cfg_space.bar[i].size = pci_resource_len(
-					      gvt->dev_priv->drm.pdev, i * 2);
-		vgpu->cfg_space.bar[i].tracked = false;
-	}
-}
-
 void populate_pvinfo_page(struct intel_vgpu *vgpu)
 {
 	/* setup the ballooning information */
@@ -177,7 +104,7 @@ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt)
 		if (low_avail / min_low == 0)
 			break;
 		gvt->types[i].low_gm_size = min_low;
-		gvt->types[i].high_gm_size = 3 * gvt->types[i].low_gm_size;
+		gvt->types[i].high_gm_size = max((min_low<<3), MB_TO_BYTES(384U));
 		gvt->types[i].fence = 4;
 		gvt->types[i].max_instance = low_avail / min_low;
 		gvt->types[i].avail_instance = gvt->types[i].max_instance;
@@ -217,7 +144,7 @@ static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt)
 	 */
 	low_gm_avail = MB_TO_BYTES(256) - HOST_LOW_GM_SIZE -
 		gvt->gm.vgpu_allocated_low_gm_size;
-	high_gm_avail = MB_TO_BYTES(256) * 3 - HOST_HIGH_GM_SIZE -
+	high_gm_avail = MB_TO_BYTES(256) * 8UL - HOST_HIGH_GM_SIZE -
 		gvt->gm.vgpu_allocated_high_gm_size;
 	fence_avail = gvt_fence_sz(gvt) - HOST_FENCE -
 		gvt->fence.vgpu_allocated_fence_num;
@@ -268,7 +195,7 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 	intel_vgpu_clean_gtt(vgpu);
 	intel_gvt_hypervisor_detach_vgpu(vgpu);
 	intel_vgpu_free_resource(vgpu);
-	clean_vgpu_mmio(vgpu);
+	intel_vgpu_clean_mmio(vgpu);
 	vfree(vgpu);
 
 	intel_gvt_update_vgpu_types(gvt);
@@ -300,11 +227,11 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	vgpu->gvt = gvt;
 	bitmap_zero(vgpu->tlb_handle_pending, I915_NUM_ENGINES);
 
-	setup_vgpu_cfg_space(vgpu, param);
+	intel_vgpu_init_cfg_space(vgpu, param->primary);
 
-	ret = setup_vgpu_mmio(vgpu);
+	ret = intel_vgpu_init_mmio(vgpu);
 	if (ret)
-		goto out_free_vgpu;
+		goto out_clean_idr;
 
 	ret = intel_vgpu_alloc_resource(vgpu, param);
 	if (ret)
@@ -354,7 +281,9 @@ out_detach_hypervisor_vgpu:
 out_clean_vgpu_resource:
 	intel_vgpu_free_resource(vgpu);
 out_clean_vgpu_mmio:
-	clean_vgpu_mmio(vgpu);
+	intel_vgpu_clean_mmio(vgpu);
+out_clean_idr:
+	idr_remove(&gvt->vgpu_idr, vgpu->id);
 out_free_vgpu:
 	vfree(vgpu);
 	mutex_unlock(&gvt->lock);
@@ -398,7 +327,75 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
 }
 
 /**
- * intel_gvt_reset_vgpu - reset a virtual GPU
+ * intel_gvt_reset_vgpu_locked - reset a virtual GPU by DMLR or GT reset
+ * @vgpu: virtual GPU
+ * @dmlr: vGPU Device Model Level Reset or GT Reset
+ * @engine_mask: engines to reset for GT reset
+ *
+ * This function is called when user wants to reset a virtual GPU through
+ * device model reset or GT reset. The caller should hold the gvt lock.
+ *
+ * vGPU Device Model Level Reset (DMLR) simulates the PCI level reset to reset
+ * the whole vGPU to default state as when it is created. This vGPU function
+ * is required both for functionary and security concerns.The ultimate goal
+ * of vGPU FLR is that reuse a vGPU instance by virtual machines. When we
+ * assign a vGPU to a virtual machine we must isse such reset first.
+ *
+ * Full GT Reset and Per-Engine GT Reset are soft reset flow for GPU engines
+ * (Render, Blitter, Video, Video Enhancement). It is defined by GPU Spec.
+ * Unlike the FLR, GT reset only reset particular resource of a vGPU per
+ * the reset request. Guest driver can issue a GT reset by programming the
+ * virtual GDRST register to reset specific virtual GPU engine or all
+ * engines.
+ *
+ * The parameter dev_level is to identify if we will do DMLR or GT reset.
+ * The parameter engine_mask is to specific the engines that need to be
+ * resetted. If value ALL_ENGINES is given for engine_mask, it means
+ * the caller requests a full GT reset that we will reset all virtual
+ * GPU engines. For FLR, engine_mask is ignored.
+ */
+void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
+				 unsigned int engine_mask)
+{
+	struct intel_gvt *gvt = vgpu->gvt;
+	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
+
+	gvt_dbg_core("------------------------------------------\n");
+	gvt_dbg_core("resseting vgpu%d, dmlr %d, engine_mask %08x\n",
+		     vgpu->id, dmlr, engine_mask);
+	vgpu->resetting = true;
+
+	intel_vgpu_stop_schedule(vgpu);
+	/*
+	 * The current_vgpu will set to NULL after stopping the
+	 * scheduler when the reset is triggered by current vgpu.
+	 */
+	if (scheduler->current_vgpu == NULL) {
+		mutex_unlock(&gvt->lock);
+		intel_gvt_wait_vgpu_idle(vgpu);
+		mutex_lock(&gvt->lock);
+	}
+
+	intel_vgpu_reset_execlist(vgpu, dmlr ? ALL_ENGINES : engine_mask);
+
+	/* full GPU reset or device model level reset */
+	if (engine_mask == ALL_ENGINES || dmlr) {
+		intel_vgpu_reset_gtt(vgpu, dmlr);
+		intel_vgpu_reset_resource(vgpu);
+		intel_vgpu_reset_mmio(vgpu);
+		populate_pvinfo_page(vgpu);
+
+		if (dmlr)
+			intel_vgpu_reset_cfg_space(vgpu);
+	}
+
+	vgpu->resetting = false;
+	gvt_dbg_core("reset vgpu%d done\n", vgpu->id);
+	gvt_dbg_core("------------------------------------------\n");
+}
+
+/**
+ * intel_gvt_reset_vgpu - reset a virtual GPU (Function Level)
  * @vgpu: virtual GPU
  *
  * This function is called when user wants to reset a virtual GPU.
@@ -406,4 +403,7 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
  */
 void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu)
 {
+	mutex_lock(&vgpu->gvt->lock);
+	intel_gvt_reset_vgpu_locked(vgpu, true, 0);
+	mutex_unlock(&vgpu->gvt->lock);
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 445fec9c2841..728ca3ea74d2 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -213,7 +213,8 @@ static void intel_detect_pch(struct drm_device *dev)
 			} else if (id == INTEL_PCH_KBP_DEVICE_ID_TYPE) {
 				dev_priv->pch_type = PCH_KBP;
 				DRM_DEBUG_KMS("Found KabyPoint PCH\n");
-				WARN_ON(!IS_KABYLAKE(dev_priv));
+				WARN_ON(!IS_SKYLAKE(dev_priv) &&
+					!IS_KABYLAKE(dev_priv));
 			} else if ((id == INTEL_PCH_P2X_DEVICE_ID_TYPE) ||
 				   (id == INTEL_PCH_P3X_DEVICE_ID_TYPE) ||
 				   ((id == INTEL_PCH_QEMU_DEVICE_ID_TYPE) &&
@@ -2378,7 +2379,7 @@ static int intel_runtime_suspend(struct device *kdev)
 
 	assert_forcewakes_inactive(dev_priv);
 
-	if (!IS_VALLEYVIEW(dev_priv) || !IS_CHERRYVIEW(dev_priv))
+	if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
 		intel_hpd_poll_init(dev_priv);
 
 	DRM_DEBUG_KMS("Device suspended\n");
@@ -2427,6 +2428,7 @@ static int intel_runtime_resume(struct device *kdev)
 	 * we can do is to hope that things will still work (and disable RPM).
 	 */
 	i915_gem_init_swizzling(dev_priv);
+	i915_gem_restore_fences(dev_priv);
 
 	intel_runtime_pm_enable_interrupts(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 243224aeabf8..8493e19b563a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1012,6 +1012,8 @@ struct intel_fbc {
 	struct work_struct underrun_work;
 
 	struct intel_fbc_state_cache {
+		struct i915_vma *vma;
+
 		struct {
 			unsigned int mode_flags;
 			uint32_t hsw_bdw_pixel_rate;
@@ -1025,15 +1027,14 @@ struct intel_fbc {
 		} plane;
 
 		struct {
-			u64 ilk_ggtt_offset;
 			uint32_t pixel_format;
 			unsigned int stride;
-			int fence_reg;
-			unsigned int tiling_mode;
 		} fb;
 	} state_cache;
 
 	struct intel_fbc_reg_params {
+		struct i915_vma *vma;
+
 		struct {
 			enum pipe pipe;
 			enum plane plane;
@@ -1041,10 +1042,8 @@ struct intel_fbc {
 		} crtc;
 
 		struct {
-			u64 ggtt_offset;
 			uint32_t pixel_format;
 			unsigned int stride;
-			int fence_reg;
 		} fb;
 
 		int cfb_size;
@@ -1977,6 +1976,11 @@ struct drm_i915_private {
 
 	struct i915_frontbuffer_tracking fb_tracking;
 
+	struct intel_atomic_helper {
+		struct llist_head free_list;
+		struct work_struct free_work;
+	} atomic_helper;
+
 	u16 orig_clock;
 
 	bool mchbar_need_disable;
@@ -3163,13 +3167,6 @@ i915_gem_object_to_ggtt(struct drm_i915_gem_object *obj,
 	return i915_gem_obj_to_vma(obj, &to_i915(obj->base.dev)->ggtt.base, view);
 }
 
-static inline unsigned long
-i915_gem_object_ggtt_offset(struct drm_i915_gem_object *o,
-			    const struct i915_ggtt_view *view)
-{
-	return i915_ggtt_offset(i915_gem_object_to_ggtt(o, view));
-}
-
 /* i915_gem_fence_reg.c */
 int __must_check i915_vma_get_fence(struct i915_vma *vma);
 int __must_check i915_vma_put_fence(struct i915_vma *vma);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 3dd7fc662859..24b5b046754b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -595,47 +595,21 @@ i915_gem_phys_pwrite(struct drm_i915_gem_object *obj,
 		     struct drm_i915_gem_pwrite *args,
 		     struct drm_file *file)
 {
-	struct drm_device *dev = obj->base.dev;
 	void *vaddr = obj->phys_handle->vaddr + args->offset;
 	char __user *user_data = u64_to_user_ptr(args->data_ptr);
-	int ret;
 
 	/* We manually control the domain here and pretend that it
 	 * remains coherent i.e. in the GTT domain, like shmem_pwrite.
 	 */
-	lockdep_assert_held(&obj->base.dev->struct_mutex);
-	ret = i915_gem_object_wait(obj,
-				   I915_WAIT_INTERRUPTIBLE |
-				   I915_WAIT_LOCKED |
-				   I915_WAIT_ALL,
-				   MAX_SCHEDULE_TIMEOUT,
-				   to_rps_client(file));
-	if (ret)
-		return ret;
-
 	intel_fb_obj_invalidate(obj, ORIGIN_CPU);
-	if (__copy_from_user_inatomic_nocache(vaddr, user_data, args->size)) {
-		unsigned long unwritten;
-
-		/* The physical object once assigned is fixed for the lifetime
-		 * of the obj, so we can safely drop the lock and continue
-		 * to access vaddr.
-		 */
-		mutex_unlock(&dev->struct_mutex);
-		unwritten = copy_from_user(vaddr, user_data, args->size);
-		mutex_lock(&dev->struct_mutex);
-		if (unwritten) {
-			ret = -EFAULT;
-			goto out;
-		}
-	}
+	if (copy_from_user(vaddr, user_data, args->size))
+		return -EFAULT;
 
 	drm_clflush_virt_range(vaddr, args->size);
-	i915_gem_chipset_flush(to_i915(dev));
+	i915_gem_chipset_flush(to_i915(obj->base.dev));
 
-out:
 	intel_fb_obj_flush(obj, false, ORIGIN_CPU);
-	return ret;
+	return 0;
 }
 
 void *i915_gem_object_alloc(struct drm_device *dev)
@@ -2036,8 +2010,16 @@ void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv)
 	for (i = 0; i < dev_priv->num_fence_regs; i++) {
 		struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
 
-		if (WARN_ON(reg->pin_count))
-			continue;
+		/* Ideally we want to assert that the fence register is not
+		 * live at this point (i.e. that no piece of code will be
+		 * trying to write through fence + GTT, as that both violates
+		 * our tracking of activity and associated locking/barriers,
+		 * but also is illegal given that the hw is powered down).
+		 *
+		 * Previously we used reg->pin_count as a "liveness" indicator.
+		 * That is not sufficient, and we need a more fine-grained
+		 * tool if we want to have a sanity check here.
+		 */
 
 		if (!reg->vma)
 			continue;
@@ -3504,7 +3486,7 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 	vma->display_alignment = max_t(u64, vma->display_alignment, alignment);
 
 	/* Treat this as an end-of-frame, like intel_user_framebuffer_dirty() */
-	if (obj->cache_dirty) {
+	if (obj->cache_dirty || obj->base.write_domain == I915_GEM_DOMAIN_CPU) {
 		i915_gem_clflush_object(obj, true);
 		intel_fb_obj_flush(obj, false, ORIGIN_DIRTYFB);
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index bd08814b015c..d534a316a16e 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -199,6 +199,7 @@ found:
 	}
 
 	/* Unbinding will emit any required flushes */
+	ret = 0;
 	while (!list_empty(&eviction_list)) {
 		vma = list_first_entry(&eviction_list,
 				       struct i915_vma,
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 097d9d8c2315..b8b877c91b0a 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1181,14 +1181,14 @@ validate_exec_list(struct drm_device *dev,
 			if (exec[i].offset !=
 			    gen8_canonical_addr(exec[i].offset & PAGE_MASK))
 				return -EINVAL;
-
-			/* From drm_mm perspective address space is continuous,
-			 * so from this point we're always using non-canonical
-			 * form internally.
-			 */
-			exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
 		}
 
+		/* From drm_mm perspective address space is continuous,
+		 * so from this point we're always using non-canonical
+		 * form internally.
+		 */
+		exec[i].offset = gen8_noncanonical_addr(exec[i].offset);
+
 		if (exec[i].alignment && !is_power_of_2(exec[i].alignment))
 			return -EINVAL;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_internal.c b/drivers/gpu/drm/i915/i915_gem_internal.c
index 4b3ff3e5b911..d09c74973cb3 100644
--- a/drivers/gpu/drm/i915/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/i915_gem_internal.c
@@ -66,8 +66,16 @@ i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
 
 	max_order = MAX_ORDER;
 #ifdef CONFIG_SWIOTLB
-	if (swiotlb_nr_tbl()) /* minimum max swiotlb size is IO_TLB_SEGSIZE */
-		max_order = min(max_order, ilog2(IO_TLB_SEGPAGES));
+	if (swiotlb_nr_tbl()) {
+		unsigned int max_segment;
+
+		max_segment = swiotlb_max_segment();
+		if (max_segment) {
+			max_segment = max_t(unsigned int, max_segment,
+					    PAGE_SIZE) >> PAGE_SHIFT;
+			max_order = min(max_order, ilog2(max_segment));
+		}
+	}
 #endif
 
 	gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_RECLAIMABLE;
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index 6a368de9d81e..ecfefb9d42e4 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -256,7 +256,7 @@ extern void drm_gem_object_unreference_unlocked(struct drm_gem_object *);
 static inline bool
 i915_gem_object_is_dead(const struct drm_i915_gem_object *obj)
 {
-	return atomic_read(&obj->base.refcount.refcount) == 0;
+	return kref_read(&obj->base.refcount) == 0;
 }
 
 static inline bool
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index a792dcb902b5..e924a9516079 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -185,6 +185,7 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 			return ret;
 	}
 
+	trace_i915_vma_bind(vma, bind_flags);
 	ret = vma->vm->bind_vma(vma, cache_level, bind_flags);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c
index dbe9fb41ae53..8d3e515f27ba 100644
--- a/drivers/gpu/drm/i915/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/intel_atomic_plane.c
@@ -85,6 +85,8 @@ intel_plane_duplicate_state(struct drm_plane *plane)
 
 	__drm_atomic_helper_plane_duplicate_state(plane, state);
 
+	intel_state->vma = NULL;
+
 	return state;
 }
 
@@ -100,6 +102,24 @@ void
 intel_plane_destroy_state(struct drm_plane *plane,
 			  struct drm_plane_state *state)
 {
+	struct i915_vma *vma;
+
+	vma = fetch_and_zero(&to_intel_plane_state(state)->vma);
+
+	/*
+	 * FIXME: Normally intel_cleanup_plane_fb handles destruction of vma.
+	 * We currently don't clear all planes during driver unload, so we have
+	 * to be able to unpin vma here for now.
+	 *
+	 * Normally this can only happen during unload when kmscon is disabled
+	 * and userspace doesn't attempt to set a framebuffer at all.
+	 */
+	if (vma) {
+		mutex_lock(&plane->dev->struct_mutex);
+		intel_unpin_fb_vma(vma);
+		mutex_unlock(&plane->dev->struct_mutex);
+	}
+
 	drm_atomic_helper_plane_destroy_state(plane, state);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 86ecec5601d4..588470eb8d39 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -499,6 +499,7 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 	struct drm_i915_private *dev_priv = to_i915(crt->base.base.dev);
 	struct edid *edid;
 	struct i2c_adapter *i2c;
+	bool ret = false;
 
 	BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG);
 
@@ -515,17 +516,17 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 		 */
 		if (!is_digital) {
 			DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n");
-			return true;
+			ret = true;
+		} else {
+			DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
 		}
-
-		DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
 	} else {
 		DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [no valid EDID found]\n");
 	}
 
 	kfree(edid);
 
-	return false;
+	return ret;
 }
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3dc8724df400..891c86aef99d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2235,24 +2235,22 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, unsigned int rotation)
 			i915_vma_pin_fence(vma);
 	}
 
+	i915_vma_get(vma);
 err:
 	intel_runtime_pm_put(dev_priv);
 	return vma;
 }
 
-void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation)
+void intel_unpin_fb_vma(struct i915_vma *vma)
 {
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
-	struct i915_ggtt_view view;
-	struct i915_vma *vma;
+	lockdep_assert_held(&vma->vm->dev->struct_mutex);
 
-	WARN_ON(!mutex_is_locked(&obj->base.dev->struct_mutex));
-
-	intel_fill_fb_ggtt_view(&view, fb, rotation);
-	vma = i915_gem_object_to_ggtt(obj, &view);
+	if (WARN_ON_ONCE(!vma))
+		return;
 
 	i915_vma_unpin_fence(vma);
 	i915_gem_object_unpin_from_display_plane(vma);
+	i915_vma_put(vma);
 }
 
 static int intel_fb_pitch(const struct drm_framebuffer *fb, int plane,
@@ -2585,8 +2583,9 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 			 * We only keep the x/y offsets, so push all of the
 			 * gtt offset into the x/y offsets.
 			 */
-			_intel_adjust_tile_offset(&x, &y, tile_size,
-						  tile_width, tile_height, pitch_tiles,
+			_intel_adjust_tile_offset(&x, &y,
+						  tile_width, tile_height,
+						  tile_size, pitch_tiles,
 						  gtt_offset_rotated * tile_size, 0);
 
 			gtt_offset_rotated += rot_info->plane[i].width * rot_info->plane[i].height;
@@ -2746,7 +2745,6 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	struct drm_device *dev = intel_crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_crtc *c;
-	struct intel_crtc *i;
 	struct drm_i915_gem_object *obj;
 	struct drm_plane *primary = intel_crtc->base.primary;
 	struct drm_plane_state *plane_state = primary->state;
@@ -2771,20 +2769,20 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	 * an fb with another CRTC instead
 	 */
 	for_each_crtc(dev, c) {
-		i = to_intel_crtc(c);
+		struct intel_plane_state *state;
 
 		if (c == &intel_crtc->base)
 			continue;
 
-		if (!i->active)
+		if (!to_intel_crtc(c)->active)
 			continue;
 
-		fb = c->primary->fb;
-		if (!fb)
+		state = to_intel_plane_state(c->primary->state);
+		if (!state->vma)
 			continue;
 
-		obj = intel_fb_obj(fb);
-		if (i915_gem_object_ggtt_offset(obj, NULL) == plane_config->base) {
+		if (intel_plane_ggtt_offset(state) == plane_config->base) {
+			fb = c->primary->fb;
 			drm_framebuffer_reference(fb);
 			goto valid_fb;
 		}
@@ -2805,6 +2803,19 @@ intel_find_initial_plane_obj(struct intel_crtc *intel_crtc,
 	return;
 
 valid_fb:
+	mutex_lock(&dev->struct_mutex);
+	intel_state->vma =
+		intel_pin_and_fence_fb_obj(fb, primary->state->rotation);
+	mutex_unlock(&dev->struct_mutex);
+	if (IS_ERR(intel_state->vma)) {
+		DRM_ERROR("failed to pin boot fb on pipe %d: %li\n",
+			  intel_crtc->pipe, PTR_ERR(intel_state->vma));
+
+		intel_state->vma = NULL;
+		drm_framebuffer_unreference(fb);
+		return;
+	}
+
 	plane_state->src_x = 0;
 	plane_state->src_y = 0;
 	plane_state->src_w = fb->width << 16;
@@ -2967,6 +2978,9 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state)
 	unsigned int rotation = plane_state->base.rotation;
 	int ret;
 
+	if (!plane_state->base.visible)
+		return 0;
+
 	/* Rotate src coordinates to match rotated GTT view */
 	if (drm_rotation_90_or_270(rotation))
 		drm_rect_rotate(&plane_state->base.src,
@@ -3097,13 +3111,13 @@ static void i9xx_update_primary_plane(struct drm_plane *primary,
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	if (INTEL_GEN(dev_priv) >= 4) {
 		I915_WRITE(DSPSURF(plane),
-			   intel_fb_gtt_offset(fb, rotation) +
+			   intel_plane_ggtt_offset(plane_state) +
 			   intel_crtc->dspaddr_offset);
 		I915_WRITE(DSPTILEOFF(plane), (y << 16) | x);
 		I915_WRITE(DSPLINOFF(plane), linear_offset);
 	} else {
 		I915_WRITE(DSPADDR(plane),
-			   intel_fb_gtt_offset(fb, rotation) +
+			   intel_plane_ggtt_offset(plane_state) +
 			   intel_crtc->dspaddr_offset);
 	}
 	POSTING_READ(reg);
@@ -3200,7 +3214,7 @@ static void ironlake_update_primary_plane(struct drm_plane *primary,
 
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	I915_WRITE(DSPSURF(plane),
-		   intel_fb_gtt_offset(fb, rotation) +
+		   intel_plane_ggtt_offset(plane_state) +
 		   intel_crtc->dspaddr_offset);
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
 		I915_WRITE(DSPOFFSET(plane), (y << 16) | x);
@@ -3223,23 +3237,6 @@ u32 intel_fb_stride_alignment(const struct drm_i915_private *dev_priv,
 	}
 }
 
-u32 intel_fb_gtt_offset(struct drm_framebuffer *fb,
-			unsigned int rotation)
-{
-	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
-	struct i915_ggtt_view view;
-	struct i915_vma *vma;
-
-	intel_fill_fb_ggtt_view(&view, fb, rotation);
-
-	vma = i915_gem_object_to_ggtt(obj, &view);
-	if (WARN(!vma, "ggtt vma for display object not found! (view=%u)\n",
-		 view.type))
-		return -1;
-
-	return i915_ggtt_offset(vma);
-}
-
 static void skl_detach_scaler(struct intel_crtc *intel_crtc, int id)
 {
 	struct drm_device *dev = intel_crtc->base.dev;
@@ -3434,7 +3431,7 @@ static void skylake_update_primary_plane(struct drm_plane *plane,
 	}
 
 	I915_WRITE(PLANE_SURF(pipe, 0),
-		   intel_fb_gtt_offset(fb, rotation) + surf_addr);
+		   intel_plane_ggtt_offset(plane_state) + surf_addr);
 
 	POSTING_READ(PLANE_SURF(pipe, 0));
 }
@@ -4265,10 +4262,10 @@ static void page_flip_completed(struct intel_crtc *intel_crtc)
 	drm_crtc_vblank_put(&intel_crtc->base);
 
 	wake_up_all(&dev_priv->pending_flip_queue);
-	queue_work(dev_priv->wq, &work->unpin_work);
-
 	trace_i915_flip_complete(intel_crtc->plane,
 				 work->pending_flip_obj);
+
+	queue_work(dev_priv->wq, &work->unpin_work);
 }
 
 static int intel_crtc_wait_for_pending_flips(struct drm_crtc *crtc)
@@ -6846,6 +6843,12 @@ static void intel_crtc_disable_noatomic(struct drm_crtc *crtc)
 	}
 
 	state = drm_atomic_state_alloc(crtc->dev);
+	if (!state) {
+		DRM_DEBUG_KMS("failed to disable [CRTC:%d:%s], out of memory",
+			      crtc->base.id, crtc->name);
+		return;
+	}
+
 	state->acquire_ctx = crtc->dev->mode_config.acquire_ctx;
 
 	/* Everything's already locked, -EDEADLK can't happen. */
@@ -11243,6 +11246,7 @@ found:
 	}
 
 	old->restore_state = restore_state;
+	drm_atomic_state_put(state);
 
 	/* let the connector get through one full cycle before testing */
 	intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
@@ -11522,7 +11526,7 @@ static void intel_unpin_work_fn(struct work_struct *__work)
 		flush_work(&work->mmio_work);
 
 	mutex_lock(&dev->struct_mutex);
-	intel_unpin_fb_obj(work->old_fb, primary->state->rotation);
+	intel_unpin_fb_vma(work->old_vma);
 	i915_gem_object_put(work->pending_flip_obj);
 	mutex_unlock(&dev->struct_mutex);
 
@@ -12232,8 +12236,10 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 		goto cleanup_pending;
 	}
 
-	work->gtt_offset = intel_fb_gtt_offset(fb, primary->state->rotation);
-	work->gtt_offset += intel_crtc->dspaddr_offset;
+	work->old_vma = to_intel_plane_state(primary->state)->vma;
+	to_intel_plane_state(primary->state)->vma = vma;
+
+	work->gtt_offset = i915_ggtt_offset(vma) + intel_crtc->dspaddr_offset;
 	work->rotation = crtc->primary->state->rotation;
 
 	/*
@@ -12287,7 +12293,8 @@ static int intel_crtc_page_flip(struct drm_crtc *crtc,
 cleanup_request:
 	i915_add_request_no_flush(request);
 cleanup_unpin:
-	intel_unpin_fb_obj(fb, crtc->primary->state->rotation);
+	to_intel_plane_state(primary->state)->vma = work->old_vma;
+	intel_unpin_fb_vma(vma);
 cleanup_pending:
 	atomic_dec(&intel_crtc->unpin_work_count);
 unlock:
@@ -14512,8 +14519,14 @@ intel_atomic_commit_ready(struct i915_sw_fence *fence,
 		break;
 
 	case FENCE_FREE:
-		drm_atomic_state_put(&state->base);
-		break;
+		{
+			struct intel_atomic_helper *helper =
+				&to_i915(state->base.dev)->atomic_helper;
+
+			if (llist_add(&state->freed, &helper->free_list))
+				schedule_work(&helper->free_work);
+			break;
+		}
 	}
 
 	return NOTIFY_DONE;
@@ -14774,6 +14787,8 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 			DRM_DEBUG_KMS("failed to pin object\n");
 			return PTR_ERR(vma);
 		}
+
+		to_intel_plane_state(new_state)->vma = vma;
 	}
 
 	return 0;
@@ -14792,19 +14807,12 @@ void
 intel_cleanup_plane_fb(struct drm_plane *plane,
 		       struct drm_plane_state *old_state)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane->dev);
-	struct intel_plane_state *old_intel_state;
-	struct drm_i915_gem_object *old_obj = intel_fb_obj(old_state->fb);
-	struct drm_i915_gem_object *obj = intel_fb_obj(plane->state->fb);
-
-	old_intel_state = to_intel_plane_state(old_state);
-
-	if (!obj && !old_obj)
-		return;
+	struct i915_vma *vma;
 
-	if (old_obj && (plane->type != DRM_PLANE_TYPE_CURSOR ||
-	    !INTEL_INFO(dev_priv)->cursor_needs_physical))
-		intel_unpin_fb_obj(old_state->fb, old_state->rotation);
+	/* Should only be called after a successful intel_prepare_plane_fb()! */
+	vma = fetch_and_zero(&to_intel_plane_state(old_state)->vma);
+	if (vma)
+		intel_unpin_fb_vma(vma);
 }
 
 int
@@ -15146,7 +15154,7 @@ intel_update_cursor_plane(struct drm_plane *plane,
 	if (!obj)
 		addr = 0;
 	else if (!INTEL_INFO(dev_priv)->cursor_needs_physical)
-		addr = i915_gem_object_ggtt_offset(obj, NULL);
+		addr = intel_plane_ggtt_offset(state);
 	else
 		addr = obj->phys_handle->busaddr;
 
@@ -16392,6 +16400,18 @@ fail:
 	drm_modeset_acquire_fini(&ctx);
 }
 
+static void intel_atomic_helper_free_state(struct work_struct *work)
+{
+	struct drm_i915_private *dev_priv =
+		container_of(work, typeof(*dev_priv), atomic_helper.free_work);
+	struct intel_atomic_state *state, *next;
+	struct llist_node *freed;
+
+	freed = llist_del_all(&dev_priv->atomic_helper.free_list);
+	llist_for_each_entry_safe(state, next, freed, freed)
+		drm_atomic_state_put(&state->base);
+}
+
 int intel_modeset_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
@@ -16411,6 +16431,9 @@ int intel_modeset_init(struct drm_device *dev)
 
 	dev->mode_config.funcs = &intel_mode_funcs;
 
+	INIT_WORK(&dev_priv->atomic_helper.free_work,
+		  intel_atomic_helper_free_state);
+
 	intel_init_quirks(dev);
 
 	intel_init_pm(dev_priv);
@@ -17024,47 +17047,19 @@ void intel_display_resume(struct drm_device *dev)
 
 	if (ret)
 		DRM_ERROR("Restoring old state failed with %i\n", ret);
-	drm_atomic_state_put(state);
+	if (state)
+		drm_atomic_state_put(state);
 }
 
 void intel_modeset_gem_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_crtc *c;
-	struct drm_i915_gem_object *obj;
 
 	intel_init_gt_powersave(dev_priv);
 
 	intel_modeset_init_hw(dev);
 
 	intel_setup_overlay(dev_priv);
-
-	/*
-	 * Make sure any fbs we allocated at startup are properly
-	 * pinned & fenced.  When we do the allocation it's too early
-	 * for this.
-	 */
-	for_each_crtc(dev, c) {
-		struct i915_vma *vma;
-
-		obj = intel_fb_obj(c->primary->fb);
-		if (obj == NULL)
-			continue;
-
-		mutex_lock(&dev->struct_mutex);
-		vma = intel_pin_and_fence_fb_obj(c->primary->fb,
-						 c->primary->state->rotation);
-		mutex_unlock(&dev->struct_mutex);
-		if (IS_ERR(vma)) {
-			DRM_ERROR("failed to pin boot fb on pipe %d\n",
-				  to_intel_crtc(c)->pipe);
-			drm_framebuffer_unreference(c->primary->fb);
-			c->primary->fb = NULL;
-			c->primary->crtc = c->primary->state->crtc = NULL;
-			update_state_fb(c->primary);
-			c->state->plane_mask &= ~(1 << drm_plane_index(c->primary));
-		}
-	}
 }
 
 int intel_connector_register(struct drm_connector *connector)
@@ -17094,6 +17089,9 @@ void intel_modeset_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
+	flush_work(&dev_priv->atomic_helper.free_work);
+	WARN_ON(!llist_empty(&dev_priv->atomic_helper.free_list));
+
 	intel_disable_gt_powersave(dev_priv);
 
 	/*
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 58a756f2f224..a2f0e070d38d 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -1730,7 +1730,8 @@ bxt_get_dpll(struct intel_crtc *crtc,
 		return NULL;
 
 	if ((encoder->type == INTEL_OUTPUT_DP ||
-	     encoder->type == INTEL_OUTPUT_EDP) &&
+	     encoder->type == INTEL_OUTPUT_EDP ||
+	     encoder->type == INTEL_OUTPUT_DP_MST) &&
 	    !bxt_ddi_dp_set_dpll_hw_state(clock, &dpll_hw_state))
 		return NULL;
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index cd132c216a67..03a2112004f9 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -370,11 +370,14 @@ struct intel_atomic_state {
 	struct skl_wm_values wm_results;
 
 	struct i915_sw_fence commit_ready;
+
+	struct llist_node freed;
 };
 
 struct intel_plane_state {
 	struct drm_plane_state base;
 	struct drm_rect clip;
+	struct i915_vma *vma;
 
 	struct {
 		u32 offset;
@@ -1044,6 +1047,7 @@ struct intel_flip_work {
 	struct work_struct mmio_work;
 
 	struct drm_crtc *crtc;
+	struct i915_vma *old_vma;
 	struct drm_framebuffer *old_fb;
 	struct drm_i915_gem_object *pending_flip_obj;
 	struct drm_pending_vblank_event *event;
@@ -1271,7 +1275,7 @@ void intel_release_load_detect_pipe(struct drm_connector *connector,
 				    struct drm_modeset_acquire_ctx *ctx);
 struct i915_vma *
 intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb, unsigned int rotation);
-void intel_unpin_fb_obj(struct drm_framebuffer *fb, unsigned int rotation);
+void intel_unpin_fb_vma(struct i915_vma *vma);
 struct drm_framebuffer *
 __intel_framebuffer_create(struct drm_device *dev,
 			   struct drm_mode_fb_cmd2 *mode_cmd,
@@ -1360,7 +1364,10 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
 int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state);
 
-u32 intel_fb_gtt_offset(struct drm_framebuffer *fb, unsigned int rotation);
+static inline u32 intel_plane_ggtt_offset(const struct intel_plane_state *state)
+{
+	return i915_ggtt_offset(state->vma);
+}
 
 u32 skl_plane_ctl_format(uint32_t pixel_format);
 u32 skl_plane_ctl_tiling(uint64_t fb_modifier);
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index 62f215b12eb5..f3a1d6a5cabe 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -173,7 +173,7 @@ static void i8xx_fbc_activate(struct drm_i915_private *dev_priv)
 	if (IS_I945GM(dev_priv))
 		fbc_ctl |= FBC_CTL_C3_IDLE; /* 945 needs special SR handling */
 	fbc_ctl |= (cfb_pitch & 0xff) << FBC_CTL_STRIDE_SHIFT;
-	fbc_ctl |= params->fb.fence_reg;
+	fbc_ctl |= params->vma->fence->id;
 	I915_WRITE(FBC_CONTROL, fbc_ctl);
 }
 
@@ -193,8 +193,8 @@ static void g4x_fbc_activate(struct drm_i915_private *dev_priv)
 	else
 		dpfc_ctl |= DPFC_CTL_LIMIT_1X;
 
-	if (params->fb.fence_reg != I915_FENCE_REG_NONE) {
-		dpfc_ctl |= DPFC_CTL_FENCE_EN | params->fb.fence_reg;
+	if (params->vma->fence) {
+		dpfc_ctl |= DPFC_CTL_FENCE_EN | params->vma->fence->id;
 		I915_WRITE(DPFC_FENCE_YOFF, params->crtc.fence_y_offset);
 	} else {
 		I915_WRITE(DPFC_FENCE_YOFF, 0);
@@ -251,13 +251,14 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv)
 		break;
 	}
 
-	if (params->fb.fence_reg != I915_FENCE_REG_NONE) {
+	if (params->vma->fence) {
 		dpfc_ctl |= DPFC_CTL_FENCE_EN;
 		if (IS_GEN5(dev_priv))
-			dpfc_ctl |= params->fb.fence_reg;
+			dpfc_ctl |= params->vma->fence->id;
 		if (IS_GEN6(dev_priv)) {
 			I915_WRITE(SNB_DPFC_CTL_SA,
-				   SNB_CPU_FENCE_ENABLE | params->fb.fence_reg);
+				   SNB_CPU_FENCE_ENABLE |
+				   params->vma->fence->id);
 			I915_WRITE(DPFC_CPU_FENCE_OFFSET,
 				   params->crtc.fence_y_offset);
 		}
@@ -269,7 +270,8 @@ static void ilk_fbc_activate(struct drm_i915_private *dev_priv)
 	}
 
 	I915_WRITE(ILK_DPFC_FENCE_YOFF, params->crtc.fence_y_offset);
-	I915_WRITE(ILK_FBC_RT_BASE, params->fb.ggtt_offset | ILK_FBC_RT_VALID);
+	I915_WRITE(ILK_FBC_RT_BASE,
+		   i915_ggtt_offset(params->vma) | ILK_FBC_RT_VALID);
 	/* enable it... */
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
@@ -319,10 +321,11 @@ static void gen7_fbc_activate(struct drm_i915_private *dev_priv)
 		break;
 	}
 
-	if (params->fb.fence_reg != I915_FENCE_REG_NONE) {
+	if (params->vma->fence) {
 		dpfc_ctl |= IVB_DPFC_CTL_FENCE_EN;
 		I915_WRITE(SNB_DPFC_CTL_SA,
-			   SNB_CPU_FENCE_ENABLE | params->fb.fence_reg);
+			   SNB_CPU_FENCE_ENABLE |
+			   params->vma->fence->id);
 		I915_WRITE(DPFC_CPU_FENCE_OFFSET, params->crtc.fence_y_offset);
 	} else {
 		I915_WRITE(SNB_DPFC_CTL_SA,0);
@@ -727,14 +730,6 @@ static bool intel_fbc_hw_tracking_covers_screen(struct intel_crtc *crtc)
 	return effective_w <= max_w && effective_h <= max_h;
 }
 
-/* XXX replace me when we have VMA tracking for intel_plane_state */
-static int get_fence_id(struct drm_framebuffer *fb)
-{
-	struct i915_vma *vma = i915_gem_object_to_ggtt(intel_fb_obj(fb), NULL);
-
-	return vma && vma->fence ? vma->fence->id : I915_FENCE_REG_NONE;
-}
-
 static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
 					 struct intel_crtc_state *crtc_state,
 					 struct intel_plane_state *plane_state)
@@ -743,7 +738,8 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
 	struct intel_fbc *fbc = &dev_priv->fbc;
 	struct intel_fbc_state_cache *cache = &fbc->state_cache;
 	struct drm_framebuffer *fb = plane_state->base.fb;
-	struct drm_i915_gem_object *obj;
+
+	cache->vma = NULL;
 
 	cache->crtc.mode_flags = crtc_state->base.adjusted_mode.flags;
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
@@ -758,16 +754,10 @@ static void intel_fbc_update_state_cache(struct intel_crtc *crtc,
 	if (!cache->plane.visible)
 		return;
 
-	obj = intel_fb_obj(fb);
-
-	/* FIXME: We lack the proper locking here, so only run this on the
-	 * platforms that need. */
-	if (IS_GEN(dev_priv, 5, 6))
-		cache->fb.ilk_ggtt_offset = i915_gem_object_ggtt_offset(obj, NULL);
 	cache->fb.pixel_format = fb->pixel_format;
 	cache->fb.stride = fb->pitches[0];
-	cache->fb.fence_reg = get_fence_id(fb);
-	cache->fb.tiling_mode = i915_gem_object_get_tiling(obj);
+
+	cache->vma = plane_state->vma;
 }
 
 static bool intel_fbc_can_activate(struct intel_crtc *crtc)
@@ -784,7 +774,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 		return false;
 	}
 
-	if (!cache->plane.visible) {
+	if (!cache->vma) {
 		fbc->no_fbc_reason = "primary plane not visible";
 		return false;
 	}
@@ -807,8 +797,7 @@ static bool intel_fbc_can_activate(struct intel_crtc *crtc)
 	 * so have no fence associated with it) due to aperture constaints
 	 * at the time of pinning.
 	 */
-	if (cache->fb.tiling_mode != I915_TILING_X ||
-	    cache->fb.fence_reg == I915_FENCE_REG_NONE) {
+	if (!cache->vma->fence) {
 		fbc->no_fbc_reason = "framebuffer not tiled or fenced";
 		return false;
 	}
@@ -888,17 +877,16 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 	 * zero. */
 	memset(params, 0, sizeof(*params));
 
+	params->vma = cache->vma;
+
 	params->crtc.pipe = crtc->pipe;
 	params->crtc.plane = crtc->plane;
 	params->crtc.fence_y_offset = get_crtc_fence_y_offset(crtc);
 
 	params->fb.pixel_format = cache->fb.pixel_format;
 	params->fb.stride = cache->fb.stride;
-	params->fb.fence_reg = cache->fb.fence_reg;
 
 	params->cfb_size = intel_fbc_calculate_cfb_size(dev_priv, cache);
-
-	params->fb.ggtt_offset = cache->fb.ilk_ggtt_offset;
 }
 
 static bool intel_fbc_reg_params_equal(struct intel_fbc_reg_params *params1,
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index beb08982dc0b..f4a8c4fc57c4 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -284,7 +284,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 out_destroy_fbi:
 	drm_fb_helper_release_fbi(helper);
 out_unpin:
-	intel_unpin_fb_obj(&ifbdev->fb->base, DRM_ROTATE_0);
+	intel_unpin_fb_vma(vma);
 out_unlock:
 	mutex_unlock(&dev->struct_mutex);
 	return ret;
@@ -549,7 +549,7 @@ static void intel_fbdev_destroy(struct intel_fbdev *ifbdev)
 
 	if (ifbdev->fb) {
 		mutex_lock(&ifbdev->helper.dev->struct_mutex);
-		intel_unpin_fb_obj(&ifbdev->fb->base, DRM_ROTATE_0);
+		intel_unpin_fb_vma(ifbdev->vma);
 		mutex_unlock(&ifbdev->helper.dev->struct_mutex);
 
 		drm_framebuffer_remove(&ifbdev->fb->base);
@@ -742,6 +742,9 @@ void intel_fbdev_initial_config_async(struct drm_device *dev)
 {
 	struct intel_fbdev *ifbdev = to_i915(dev)->fbdev;
 
+	if (!ifbdev)
+		return;
+
 	ifbdev->cookie = async_schedule(intel_fbdev_initial_config, ifbdev);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index d4961fa20c73..beabc17e7c8a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -979,18 +979,8 @@ static inline int gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine,
 						uint32_t *batch,
 						uint32_t index)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
 	uint32_t l3sqc4_flush = (0x40400000 | GEN8_LQSC_FLUSH_COHERENT_LINES);
 
-	/*
-	 * WaDisableLSQCROPERFforOCL:kbl
-	 * This WA is implemented in skl_init_clock_gating() but since
-	 * this batch updates GEN8_L3SQCREG4 with default value we need to
-	 * set this bit here to retain the WA during flush.
-	 */
-	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0))
-		l3sqc4_flush |= GEN8_LQSC_RO_PERF_DIS;
-
 	wa_ctx_emit(batch, index, (MI_STORE_REGISTER_MEM_GEN8 |
 				   MI_SRM_LRM_GLOBAL_GTT));
 	wa_ctx_emit_reg(batch, index, GEN8_L3SQCREG4);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index aeb637dc1fdf..91cb4c422ad5 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1095,14 +1095,6 @@ static int kbl_init_workarounds(struct intel_engine_cs *engine)
 		WA_SET_BIT_MASKED(HDC_CHICKEN0,
 				  HDC_FENCE_DEST_SLM_DISABLE);
 
-	/* GEN8_L3SQCREG4 has a dependency with WA batch so any new changes
-	 * involving this register should also be added to WA batch as required.
-	 */
-	if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_E0))
-		/* WaDisableLSQCROPERFforOCL:kbl */
-		I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) |
-			   GEN8_LQSC_RO_PERF_DIS);
-
 	/* WaToEnableHwFixForPushConstHWBug:kbl */
 	if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER))
 		WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2,
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 8f131a08d440..242a73e66d82 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -273,7 +273,7 @@ skl_update_plane(struct drm_plane *drm_plane,
 
 	I915_WRITE(PLANE_CTL(pipe, plane), plane_ctl);
 	I915_WRITE(PLANE_SURF(pipe, plane),
-		   intel_fb_gtt_offset(fb, rotation) + surf_addr);
+		   intel_plane_ggtt_offset(plane_state) + surf_addr);
 	POSTING_READ(PLANE_SURF(pipe, plane));
 }
 
@@ -458,7 +458,7 @@ vlv_update_plane(struct drm_plane *dplane,
 	I915_WRITE(SPSIZE(pipe, plane), (crtc_h << 16) | crtc_w);
 	I915_WRITE(SPCNTR(pipe, plane), sprctl);
 	I915_WRITE(SPSURF(pipe, plane),
-		   intel_fb_gtt_offset(fb, rotation) + sprsurf_offset);
+		   intel_plane_ggtt_offset(plane_state) + sprsurf_offset);
 	POSTING_READ(SPSURF(pipe, plane));
 }
 
@@ -594,7 +594,7 @@ ivb_update_plane(struct drm_plane *plane,
 		I915_WRITE(SPRSCALE(pipe), sprscale);
 	I915_WRITE(SPRCTL(pipe), sprctl);
 	I915_WRITE(SPRSURF(pipe),
-		   intel_fb_gtt_offset(fb, rotation) + sprsurf_offset);
+		   intel_plane_ggtt_offset(plane_state) + sprsurf_offset);
 	POSTING_READ(SPRSURF(pipe));
 }
 
@@ -721,7 +721,7 @@ ilk_update_plane(struct drm_plane *plane,
 	I915_WRITE(DVSSCALE(pipe), dvsscale);
 	I915_WRITE(DVSCNTR(pipe), dvscntr);
 	I915_WRITE(DVSSURF(pipe),
-		   intel_fb_gtt_offset(fb, rotation) + dvssurf_offset);
+		   intel_plane_ggtt_offset(plane_state) + dvssurf_offset);
 	POSTING_READ(DVSSURF(pipe));
 }
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 14ff87686a36..686a580c711a 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -345,7 +345,6 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 {
 	struct adreno_platform_config *config = pdev->dev.platform_data;
 	struct msm_gpu *gpu = &adreno_gpu->base;
-	struct msm_mmu *mmu;
 	int ret;
 
 	adreno_gpu->funcs = funcs;
@@ -385,8 +384,8 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		return ret;
 	}
 
-	mmu = gpu->aspace->mmu;
-	if (mmu) {
+	if (gpu->aspace && gpu->aspace->mmu) {
+		struct msm_mmu *mmu = gpu->aspace->mmu;
 		ret = mmu->funcs->attach(mmu, iommu_ports,
 				ARRAY_SIZE(iommu_ports));
 		if (ret)
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index 5f6cd8745dbc..c396d459a9d0 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -119,13 +119,7 @@ static void mdp5_prepare_commit(struct msm_kms *kms, struct drm_atomic_state *st
 
 static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
-	int i;
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
-	struct drm_plane *plane;
-	struct drm_plane_state *plane_state;
-
-	for_each_plane_in_state(state, plane, plane_state, i)
-		mdp5_plane_complete_commit(plane, plane_state);
 
 	if (mdp5_kms->smp)
 		mdp5_smp_complete_commit(mdp5_kms->smp, &mdp5_kms->state->smp);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
index 17b0cc101171..cdfc63d90c7b 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
@@ -104,8 +104,6 @@ struct mdp5_plane_state {
 
 	/* assigned by crtc blender */
 	enum mdp_mixer_stage_id stage;
-
-	bool pending : 1;
 };
 #define to_mdp5_plane_state(x) \
 		container_of(x, struct mdp5_plane_state, base)
@@ -232,8 +230,6 @@ int mdp5_irq_domain_init(struct mdp5_kms *mdp5_kms);
 void mdp5_irq_domain_fini(struct mdp5_kms *mdp5_kms);
 
 uint32_t mdp5_plane_get_flush(struct drm_plane *plane);
-void mdp5_plane_complete_commit(struct drm_plane *plane,
-	struct drm_plane_state *state);
 enum mdp5_pipe mdp5_plane_pipe(struct drm_plane *plane);
 struct drm_plane *mdp5_plane_init(struct drm_device *dev, bool primary);
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index c099da7bc212..25d9d0a97156 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -179,7 +179,6 @@ mdp5_plane_atomic_print_state(struct drm_printer *p,
 	drm_printf(p, "\tzpos=%u\n", pstate->zpos);
 	drm_printf(p, "\talpha=%u\n", pstate->alpha);
 	drm_printf(p, "\tstage=%s\n", stage2name(pstate->stage));
-	drm_printf(p, "\tpending=%u\n", pstate->pending);
 }
 
 static void mdp5_plane_reset(struct drm_plane *plane)
@@ -220,8 +219,6 @@ mdp5_plane_duplicate_state(struct drm_plane *plane)
 	if (mdp5_state && mdp5_state->base.fb)
 		drm_framebuffer_reference(mdp5_state->base.fb);
 
-	mdp5_state->pending = false;
-
 	return &mdp5_state->base;
 }
 
@@ -288,13 +285,6 @@ static int mdp5_plane_atomic_check(struct drm_plane *plane,
 	DBG("%s: check (%d -> %d)", plane->name,
 			plane_enabled(old_state), plane_enabled(state));
 
-	/* We don't allow faster-than-vblank updates.. if we did add this
-	 * some day, we would need to disallow in cases where hwpipe
-	 * changes
-	 */
-	if (WARN_ON(to_mdp5_plane_state(old_state)->pending))
-		return -EBUSY;
-
 	max_width = config->hw->lm.max_width << 16;
 	max_height = config->hw->lm.max_height << 16;
 
@@ -370,12 +360,9 @@ static void mdp5_plane_atomic_update(struct drm_plane *plane,
 				     struct drm_plane_state *old_state)
 {
 	struct drm_plane_state *state = plane->state;
-	struct mdp5_plane_state *mdp5_state = to_mdp5_plane_state(state);
 
 	DBG("%s: update", plane->name);
 
-	mdp5_state->pending = true;
-
 	if (plane_enabled(state)) {
 		int ret;
 
@@ -851,15 +838,6 @@ uint32_t mdp5_plane_get_flush(struct drm_plane *plane)
 	return pstate->hwpipe->flush_mask;
 }
 
-/* called after vsync in thread context */
-void mdp5_plane_complete_commit(struct drm_plane *plane,
-	struct drm_plane_state *state)
-{
-	struct mdp5_plane_state *pstate = to_mdp5_plane_state(plane->state);
-
-	pstate->pending = false;
-}
-
 /* initialize plane */
 struct drm_plane *mdp5_plane_init(struct drm_device *dev, bool primary)
 {
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index d8bc59c7e261..1974ccb781de 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -294,6 +294,8 @@ put_iova(struct drm_gem_object *obj)
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
 	for (id = 0; id < ARRAY_SIZE(msm_obj->domain); id++) {
+		if (!priv->aspace[id])
+			continue;
 		msm_gem_unmap_vma(priv->aspace[id],
 				&msm_obj->domain[id], msm_obj->sgt);
 	}
@@ -640,7 +642,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 
 	seq_printf(m, "%08x: %c %2d (%2d) %08llx %p\t",
 			msm_obj->flags, is_active(msm_obj) ? 'A' : 'I',
-			obj->name, obj->refcount.refcount.counter,
+			obj->name, kref_read(&obj->refcount),
 			off, msm_obj->vaddr);
 
 	for (id = 0; id < priv->num_aspaces; id++)
diff --git a/drivers/gpu/drm/nouveau/dispnv04/hw.c b/drivers/gpu/drm/nouveau/dispnv04/hw.c
index 74856a8b8f35..e64f52464ecf 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/hw.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/hw.c
@@ -222,6 +222,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype)
 		uint32_t mpllP;
 
 		pci_read_config_dword(pci_get_bus_and_slot(0, 3), 0x6c, &mpllP);
+		mpllP = (mpllP >> 8) & 0xf;
 		if (!mpllP)
 			mpllP = 4;
 
@@ -232,7 +233,7 @@ nouveau_hw_get_clock(struct drm_device *dev, enum nvbios_pll_type plltype)
 		uint32_t clock;
 
 		pci_read_config_dword(pci_get_bus_and_slot(0, 5), 0x4c, &clock);
-		return clock;
+		return clock / 1000;
 	}
 
 	ret = nouveau_hw_get_pllvals(dev, plltype, &pllvals);
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index cef08da1da4e..6a157763dfc3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -411,7 +411,8 @@ nouveau_display_init(struct drm_device *dev)
 		return ret;
 
 	/* enable polling for external displays */
-	drm_kms_helper_poll_enable(dev);
+	if (!dev->mode_config.poll_enabled)
+		drm_kms_helper_poll_enable(dev);
 
 	/* enable hotplug interrupts */
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 59348fc41c77..bc85a45f91cd 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -773,7 +773,10 @@ nouveau_pmops_runtime_resume(struct device *dev)
 	pci_set_master(pdev);
 
 	ret = nouveau_do_resume(drm_dev, true);
-	drm_kms_helper_poll_enable(drm_dev);
+
+	if (!drm_dev->mode_config.poll_enabled)
+		drm_kms_helper_poll_enable(drm_dev);
+
 	/* do magic */
 	nvif_mask(&device->object, 0x088488, (1 << 25), (1 << 25));
 	vga_switcheroo_set_dynamic_switch(pdev, VGA_SWITCHEROO_ON);
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 8d5ed5bfdacb..42c1fa53d431 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -165,6 +165,8 @@ struct nouveau_drm {
 	struct backlight_device *backlight;
 	struct list_head bl_connectors;
 	struct work_struct hpd_work;
+	struct work_struct fbcon_work;
+	int fbcon_new_state;
 #ifdef CONFIG_ACPI
 	struct notifier_block acpi_nb;
 #endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 2f2a3dcd4ad7..fa2d0a978ccc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -470,19 +470,43 @@ static const struct drm_fb_helper_funcs nouveau_fbcon_helper_funcs = {
 	.fb_probe = nouveau_fbcon_create,
 };
 
+static void
+nouveau_fbcon_set_suspend_work(struct work_struct *work)
+{
+	struct nouveau_drm *drm = container_of(work, typeof(*drm), fbcon_work);
+	int state = READ_ONCE(drm->fbcon_new_state);
+
+	if (state == FBINFO_STATE_RUNNING)
+		pm_runtime_get_sync(drm->dev->dev);
+
+	console_lock();
+	if (state == FBINFO_STATE_RUNNING)
+		nouveau_fbcon_accel_restore(drm->dev);
+	drm_fb_helper_set_suspend(&drm->fbcon->helper, state);
+	if (state != FBINFO_STATE_RUNNING)
+		nouveau_fbcon_accel_save_disable(drm->dev);
+	console_unlock();
+
+	if (state == FBINFO_STATE_RUNNING) {
+		pm_runtime_mark_last_busy(drm->dev->dev);
+		pm_runtime_put_sync(drm->dev->dev);
+	}
+}
+
 void
 nouveau_fbcon_set_suspend(struct drm_device *dev, int state)
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
-	if (drm->fbcon) {
-		console_lock();
-		if (state == FBINFO_STATE_RUNNING)
-			nouveau_fbcon_accel_restore(dev);
-		drm_fb_helper_set_suspend(&drm->fbcon->helper, state);
-		if (state != FBINFO_STATE_RUNNING)
-			nouveau_fbcon_accel_save_disable(dev);
-		console_unlock();
-	}
+
+	if (!drm->fbcon)
+		return;
+
+	drm->fbcon_new_state = state;
+	/* Since runtime resume can happen as a result of a sysfs operation,
+	 * it's possible we already have the console locked. So handle fbcon
+	 * init/deinit from a seperate work thread
+	 */
+	schedule_work(&drm->fbcon_work);
 }
 
 int
@@ -502,6 +526,7 @@ nouveau_fbcon_init(struct drm_device *dev)
 		return -ENOMEM;
 
 	drm->fbcon = fbcon;
+	INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work);
 
 	drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index a6126c93f215..88ee60d1b907 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -527,7 +527,7 @@ static bool nouveau_fence_no_signaling(struct dma_fence *f)
 	 * caller should have a reference on the fence,
 	 * else fence could get freed here
 	 */
-	WARN_ON(atomic_read(&fence->base.refcount.refcount) <= 1);
+	WARN_ON(kref_read(&fence->base.refcount) <= 1);
 
 	/*
 	 * This needs uevents to work correctly, but dma_fence_add_callback relies on
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index ccdce1b4eec4..d5e58a38f160 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -99,6 +99,7 @@ struct nv84_fence_priv {
 	struct nouveau_bo *bo;
 	struct nouveau_bo *bo_gart;
 	u32 *suspend;
+	struct mutex mutex;
 };
 
 int  nv84_fence_context_new(struct nouveau_channel *);
diff --git a/drivers/gpu/drm/nouveau/nouveau_led.h b/drivers/gpu/drm/nouveau/nouveau_led.h
index 187ecdb82002..21a5775028cc 100644
--- a/drivers/gpu/drm/nouveau/nouveau_led.h
+++ b/drivers/gpu/drm/nouveau/nouveau_led.h
@@ -42,7 +42,7 @@ nouveau_led(struct drm_device *dev)
 }
 
 /* nouveau_led.c */
-#if IS_ENABLED(CONFIG_LEDS_CLASS)
+#if IS_REACHABLE(CONFIG_LEDS_CLASS)
 int  nouveau_led_init(struct drm_device *dev);
 void nouveau_led_suspend(struct drm_device *dev);
 void nouveau_led_resume(struct drm_device *dev);
diff --git a/drivers/gpu/drm/nouveau/nouveau_usif.c b/drivers/gpu/drm/nouveau/nouveau_usif.c
index 08f9c6fa0f7f..1fba38622744 100644
--- a/drivers/gpu/drm/nouveau/nouveau_usif.c
+++ b/drivers/gpu/drm/nouveau/nouveau_usif.c
@@ -313,7 +313,8 @@ usif_ioctl(struct drm_file *filp, void __user *user, u32 argc)
 	if (!(ret = nvif_unpack(-ENOSYS, &data, &size, argv->v0, 0, 0, true))) {
 		/* block access to objects not created via this interface */
 		owner = argv->v0.owner;
-		if (argv->v0.object == 0ULL)
+		if (argv->v0.object == 0ULL &&
+		    argv->v0.type != NVIF_IOCTL_V0_DEL)
 			argv->v0.owner = NVDRM_OBJECT_ANY; /* except client */
 		else
 			argv->v0.owner = NVDRM_OBJECT_USIF;
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 2c2c64507661..32097fd615fd 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -4052,6 +4052,11 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 		}
 	}
 
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		if (crtc->state->event)
+			drm_crtc_vblank_get(crtc);
+	}
+
 	/* Update plane(s). */
 	for_each_plane_in_state(state, plane, plane_state, i) {
 		struct nv50_wndw_atom *asyw = nv50_wndw_atom(plane->state);
@@ -4101,6 +4106,7 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 			drm_crtc_send_vblank_event(crtc, crtc->state->event);
 			spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 			crtc->state->event = NULL;
+			drm_crtc_vblank_put(crtc);
 		}
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nv84_fence.c b/drivers/gpu/drm/nouveau/nv84_fence.c
index 52b87ae83e7b..f0b322bec7df 100644
--- a/drivers/gpu/drm/nouveau/nv84_fence.c
+++ b/drivers/gpu/drm/nouveau/nv84_fence.c
@@ -107,8 +107,10 @@ nv84_fence_context_del(struct nouveau_channel *chan)
 	struct nv84_fence_chan *fctx = chan->fence;
 
 	nouveau_bo_wr32(priv->bo, chan->chid * 16 / 4, fctx->base.sequence);
+	mutex_lock(&priv->mutex);
 	nouveau_bo_vma_del(priv->bo, &fctx->vma_gart);
 	nouveau_bo_vma_del(priv->bo, &fctx->vma);
+	mutex_unlock(&priv->mutex);
 	nouveau_fence_context_del(&fctx->base);
 	chan->fence = NULL;
 	nouveau_fence_context_free(&fctx->base);
@@ -134,11 +136,13 @@ nv84_fence_context_new(struct nouveau_channel *chan)
 	fctx->base.sync32 = nv84_fence_sync32;
 	fctx->base.sequence = nv84_fence_read(chan);
 
+	mutex_lock(&priv->mutex);
 	ret = nouveau_bo_vma_add(priv->bo, cli->vm, &fctx->vma);
 	if (ret == 0) {
 		ret = nouveau_bo_vma_add(priv->bo_gart, cli->vm,
 					&fctx->vma_gart);
 	}
+	mutex_unlock(&priv->mutex);
 
 	if (ret)
 		nv84_fence_context_del(chan);
@@ -212,6 +216,8 @@ nv84_fence_create(struct nouveau_drm *drm)
 	priv->base.context_base = dma_fence_context_alloc(priv->base.contexts);
 	priv->base.uevent = true;
 
+	mutex_init(&priv->mutex);
+
 	/* Use VRAM if there is any ; otherwise fallback to system memory */
 	domain = drm->device.info.ram_size != 0 ? TTM_PL_FLAG_VRAM :
 			 /*
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c
index 6f0436df0219..f8f2f16c22a2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/hdagt215.c
@@ -59,7 +59,7 @@ gt215_hda_eld(NV50_DISP_MTHD_V1)
 			);
 		}
 		for (i = 0; i < size; i++)
-			nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[0]);
+			nvkm_wr32(device, 0x61c440 + soff, (i << 8) | args->v0.data[i]);
 		for (; i < 0x60; i++)
 			nvkm_wr32(device, 0x61c440 + soff, (i << 8));
 		nvkm_mask(device, 0x61c448 + soff, 0x80000003, 0x80000003);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
index 567466f93cd5..0db8efbf1c2e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c
@@ -433,8 +433,6 @@ nv50_disp_dptmds_war(struct nvkm_device *device)
 	case 0x94:
 	case 0x96:
 	case 0x98:
-	case 0xaa:
-	case 0xac:
 		return true;
 	default:
 		break;
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 4a90c690f09e..74a9968df421 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -1033,7 +1033,7 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 	off = drm_vma_node_start(&obj->vma_node);
 
 	seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d",
-			omap_obj->flags, obj->name, obj->refcount.refcount.counter,
+			omap_obj->flags, obj->name, kref_read(&obj->refcount),
 			off, &omap_obj->paddr, omap_obj->paddr_cnt,
 			omap_obj->vaddr, omap_obj->roll);
 
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index fb16070b266e..4a4f9533c53b 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -205,8 +205,8 @@ static int radeon_cursor_move_locked(struct drm_crtc *crtc, int x, int y)
 	}
 
 	if (x <= (crtc->x - w) || y <= (crtc->y - radeon_crtc->cursor_height) ||
-	    x >= (crtc->x + crtc->mode.crtc_hdisplay) ||
-	    y >= (crtc->y + crtc->mode.crtc_vdisplay))
+	    x >= (crtc->x + crtc->mode.hdisplay) ||
+	    y >= (crtc->y + crtc->mode.vdisplay))
 		goto out_of_bounds;
 
 	x += xorigin;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 00ea0002b539..30bd4a6a9d46 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -97,9 +97,10 @@
  *   2.46.0 - Add PFP_SYNC_ME support on evergreen
  *   2.47.0 - Add UVD_NO_OP register support
  *   2.48.0 - TA_CS_BC_BASE_ADDR allowed on SI
+ *   2.49.0 - DRM_RADEON_GEM_INFO ioctl returns correct vram_size/visible values
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	48
+#define KMS_DRIVER_MINOR	49
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
@@ -366,11 +367,10 @@ static void
 radeon_pci_shutdown(struct pci_dev *pdev)
 {
 	/* if we are running in a VM, make sure the device
-	 * torn down properly on reboot/shutdown.
-	 * unfortunately we can't detect certain
-	 * hypervisors so just do this all the time.
+	 * torn down properly on reboot/shutdown
 	 */
-	radeon_pci_remove(pdev);
+	if (radeon_device_is_virtual())
+		radeon_pci_remove(pdev);
 }
 
 static int radeon_pmops_suspend(struct device *dev)
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index 0bcffd8a7bd3..96683f5b2b1b 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -220,8 +220,8 @@ int radeon_gem_info_ioctl(struct drm_device *dev, void *data,
 
 	man = &rdev->mman.bdev.man[TTM_PL_VRAM];
 
-	args->vram_size = rdev->mc.real_vram_size;
-	args->vram_visible = (u64)man->size << PAGE_SHIFT;
+	args->vram_size = (u64)man->size << PAGE_SHIFT;
+	args->vram_visible = rdev->mc.visible_vram_size;
 	args->vram_visible -= rdev->vram_pin_size;
 	args->gart_size = rdev->mc.gtt_size;
 	args->gart_size -= rdev->gart_pin_size;
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index e8a38d296855..414776811e71 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -114,6 +114,9 @@ MODULE_FIRMWARE("radeon/hainan_mc.bin");
 MODULE_FIRMWARE("radeon/hainan_rlc.bin");
 MODULE_FIRMWARE("radeon/hainan_smc.bin");
 MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
+MODULE_FIRMWARE("radeon/banks_k_2_smc.bin");
+
+MODULE_FIRMWARE("radeon/si58_mc.bin");
 
 static u32 si_get_cu_active_bitmap(struct radeon_device *rdev, u32 se, u32 sh);
 static void si_pcie_gen3_enable(struct radeon_device *rdev);
@@ -1650,6 +1653,8 @@ static int si_init_microcode(struct radeon_device *rdev)
 	int err;
 	int new_fw = 0;
 	bool new_smc = false;
+	bool si58_fw = false;
+	bool banks2_fw = false;
 
 	DRM_DEBUG("\n");
 
@@ -1727,10 +1732,11 @@ static int si_init_microcode(struct radeon_device *rdev)
 		     ((rdev->pdev->device == 0x6660) ||
 		      (rdev->pdev->device == 0x6663) ||
 		      (rdev->pdev->device == 0x6665) ||
-		      (rdev->pdev->device == 0x6667))) ||
-		    ((rdev->pdev->revision == 0xc3) &&
-		     (rdev->pdev->device == 0x6665)))
+		      (rdev->pdev->device == 0x6667))))
 			new_smc = true;
+		else if ((rdev->pdev->revision == 0xc3) &&
+			 (rdev->pdev->device == 0x6665))
+			banks2_fw = true;
 		new_chip_name = "hainan";
 		pfp_req_size = SI_PFP_UCODE_SIZE * 4;
 		me_req_size = SI_PM4_UCODE_SIZE * 4;
@@ -1742,6 +1748,10 @@ static int si_init_microcode(struct radeon_device *rdev)
 	default: BUG();
 	}
 
+	/* this memory configuration requires special firmware */
+	if (((RREG32(MC_SEQ_MISC0) & 0xff000000) >> 24) == 0x58)
+		si58_fw = true;
+
 	DRM_INFO("Loading %s Microcode\n", new_chip_name);
 
 	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", new_chip_name);
@@ -1845,7 +1855,10 @@ static int si_init_microcode(struct radeon_device *rdev)
 		}
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", new_chip_name);
+	if (si58_fw)
+		snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin");
+	else
+		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", new_chip_name);
 	err = request_firmware(&rdev->mc_fw, fw_name, rdev->dev);
 	if (err) {
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc2.bin", chip_name);
@@ -1876,7 +1889,9 @@ static int si_init_microcode(struct radeon_device *rdev)
 		}
 	}
 
-	if (new_smc)
+	if (banks2_fw)
+		snprintf(fw_name, sizeof(fw_name), "radeon/banks_k_2_smc.bin");
+	else if (new_smc)
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_k_smc.bin", new_chip_name);
 	else
 		snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", new_chip_name);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 13ba73fd9b68..2944916f7102 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -3008,17 +3008,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		    (rdev->pdev->device == 0x6817) ||
 		    (rdev->pdev->device == 0x6806))
 			max_mclk = 120000;
-	} else if (rdev->family == CHIP_OLAND) {
-		if ((rdev->pdev->revision == 0xC7) ||
-		    (rdev->pdev->revision == 0x80) ||
-		    (rdev->pdev->revision == 0x81) ||
-		    (rdev->pdev->revision == 0x83) ||
-		    (rdev->pdev->revision == 0x87) ||
-		    (rdev->pdev->device == 0x6604) ||
-		    (rdev->pdev->device == 0x6605)) {
-			max_sclk = 75000;
-			max_mclk = 80000;
-		}
 	} else if (rdev->family == CHIP_HAINAN) {
 		if ((rdev->pdev->revision == 0x81) ||
 		    (rdev->pdev->revision == 0x83) ||
@@ -3027,7 +3016,6 @@ static void si_apply_state_adjust_rules(struct radeon_device *rdev,
 		    (rdev->pdev->device == 0x6665) ||
 		    (rdev->pdev->device == 0x6667)) {
 			max_sclk = 75000;
-			max_mclk = 80000;
 		}
 	}
 	/* Apply dpm quirks */
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index d5063618efa7..ffc6cb55c78c 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -140,8 +140,8 @@ static void ttm_bo_release_list(struct kref *list_kref)
 	struct ttm_bo_device *bdev = bo->bdev;
 	size_t acc_size = bo->acc_size;
 
-	BUG_ON(atomic_read(&bo->list_kref.refcount));
-	BUG_ON(atomic_read(&bo->kref.refcount));
+	BUG_ON(kref_read(&bo->list_kref));
+	BUG_ON(kref_read(&bo->kref));
 	BUG_ON(atomic_read(&bo->cpu_writers));
 	BUG_ON(bo->mem.mm_node != NULL);
 	BUG_ON(!list_empty(&bo->lru));
@@ -181,61 +181,46 @@ void ttm_bo_add_to_lru(struct ttm_buffer_object *bo)
 }
 EXPORT_SYMBOL(ttm_bo_add_to_lru);
 
-int ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
+static void ttm_bo_ref_bug(struct kref *list_kref)
+{
+	BUG();
+}
+
+void ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	int put_count = 0;
 
 	if (bdev->driver->lru_removal)
 		bdev->driver->lru_removal(bo);
 
 	if (!list_empty(&bo->swap)) {
 		list_del_init(&bo->swap);
-		++put_count;
+		kref_put(&bo->list_kref, ttm_bo_ref_bug);
 	}
 	if (!list_empty(&bo->lru)) {
 		list_del_init(&bo->lru);
-		++put_count;
+		kref_put(&bo->list_kref, ttm_bo_ref_bug);
 	}
-
-	return put_count;
-}
-
-static void ttm_bo_ref_bug(struct kref *list_kref)
-{
-	BUG();
-}
-
-void ttm_bo_list_ref_sub(struct ttm_buffer_object *bo, int count,
-			 bool never_free)
-{
-	kref_sub(&bo->list_kref, count,
-		 (never_free) ? ttm_bo_ref_bug : ttm_bo_release_list);
 }
 
 void ttm_bo_del_sub_from_lru(struct ttm_buffer_object *bo)
 {
-	int put_count;
-
 	spin_lock(&bo->glob->lru_lock);
-	put_count = ttm_bo_del_from_lru(bo);
+	ttm_bo_del_from_lru(bo);
 	spin_unlock(&bo->glob->lru_lock);
-	ttm_bo_list_ref_sub(bo, put_count, true);
 }
 EXPORT_SYMBOL(ttm_bo_del_sub_from_lru);
 
 void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	int put_count = 0;
 
 	lockdep_assert_held(&bo->resv->lock.base);
 
 	if (bdev->driver->lru_removal)
 		bdev->driver->lru_removal(bo);
 
-	put_count = ttm_bo_del_from_lru(bo);
-	ttm_bo_list_ref_sub(bo, put_count, true);
+	ttm_bo_del_from_lru(bo);
 	ttm_bo_add_to_lru(bo);
 }
 EXPORT_SYMBOL(ttm_bo_move_to_lru_tail);
@@ -447,7 +432,6 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct ttm_bo_global *glob = bo->glob;
-	int put_count;
 	int ret;
 
 	spin_lock(&glob->lru_lock);
@@ -455,13 +439,10 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 
 	if (!ret) {
 		if (!ttm_bo_wait(bo, false, true)) {
-			put_count = ttm_bo_del_from_lru(bo);
-
+			ttm_bo_del_from_lru(bo);
 			spin_unlock(&glob->lru_lock);
 			ttm_bo_cleanup_memtype_use(bo);
 
-			ttm_bo_list_ref_sub(bo, put_count, true);
-
 			return;
 		} else
 			ttm_bo_flush_all_fences(bo);
@@ -504,7 +485,6 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 					  bool no_wait_gpu)
 {
 	struct ttm_bo_global *glob = bo->glob;
-	int put_count;
 	int ret;
 
 	ret = ttm_bo_wait(bo, false, true);
@@ -554,15 +534,13 @@ static int ttm_bo_cleanup_refs_and_unlock(struct ttm_buffer_object *bo,
 		return ret;
 	}
 
-	put_count = ttm_bo_del_from_lru(bo);
+	ttm_bo_del_from_lru(bo);
 	list_del_init(&bo->ddestroy);
-	++put_count;
+	kref_put(&bo->list_kref, ttm_bo_ref_bug);
 
 	spin_unlock(&glob->lru_lock);
 	ttm_bo_cleanup_memtype_use(bo);
 
-	ttm_bo_list_ref_sub(bo, put_count, true);
-
 	return 0;
 }
 
@@ -740,7 +718,7 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 	struct ttm_bo_global *glob = bdev->glob;
 	struct ttm_mem_type_manager *man = &bdev->man[mem_type];
 	struct ttm_buffer_object *bo;
-	int ret = -EBUSY, put_count;
+	int ret = -EBUSY;
 
 	spin_lock(&glob->lru_lock);
 	list_for_each_entry(bo, &man->lru, lru) {
@@ -771,13 +749,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 		return ret;
 	}
 
-	put_count = ttm_bo_del_from_lru(bo);
+	ttm_bo_del_from_lru(bo);
 	spin_unlock(&glob->lru_lock);
 
 	BUG_ON(ret != 0);
 
-	ttm_bo_list_ref_sub(bo, put_count, true);
-
 	ret = ttm_bo_evict(bo, interruptible, no_wait_gpu);
 	ttm_bo_unreserve(bo);
 
@@ -1669,7 +1645,6 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 	    container_of(shrink, struct ttm_bo_global, shrink);
 	struct ttm_buffer_object *bo;
 	int ret = -EBUSY;
-	int put_count;
 	uint32_t swap_placement = (TTM_PL_FLAG_CACHED | TTM_PL_FLAG_SYSTEM);
 
 	spin_lock(&glob->lru_lock);
@@ -1692,11 +1667,9 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink)
 		return ret;
 	}
 
-	put_count = ttm_bo_del_from_lru(bo);
+	ttm_bo_del_from_lru(bo);
 	spin_unlock(&glob->lru_lock);
 
-	ttm_bo_list_ref_sub(bo, put_count, true);
-
 	/**
 	 * Move to system cached
 	 */
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index d35bc491e8de..5e1bcabffef5 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -48,9 +48,7 @@ static void ttm_eu_del_from_lru_locked(struct list_head *list)
 
 	list_for_each_entry(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
-		unsigned put_count = ttm_bo_del_from_lru(bo);
-
-		ttm_bo_list_ref_sub(bo, put_count, true);
+		ttm_bo_del_from_lru(bo);
 	}
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_object.c b/drivers/gpu/drm/ttm/ttm_object.c
index 4f5fa8d65fe9..fdb451e3ec01 100644
--- a/drivers/gpu/drm/ttm/ttm_object.c
+++ b/drivers/gpu/drm/ttm/ttm_object.c
@@ -304,7 +304,7 @@ bool ttm_ref_object_exists(struct ttm_object_file *tfile,
 	 * Verify that the ref->obj pointer was actually valid!
 	 */
 	rmb();
-	if (unlikely(atomic_read(&ref->kref.refcount) == 0))
+	if (unlikely(kref_read(&ref->kref) == 0))
 		goto out_false;
 
 	rcu_read_unlock();
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index a0fd3e66bc4b..7aadce1f7e7a 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -839,7 +839,7 @@ static void vc4_crtc_destroy_state(struct drm_crtc *crtc,
 
 	}
 
-	__drm_atomic_helper_crtc_destroy_state(state);
+	drm_atomic_helper_crtc_destroy_state(crtc, state);
 }
 
 static const struct drm_crtc_funcs vc4_crtc_funcs = {
diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c
index db920771bfb5..ab3016982466 100644
--- a/drivers/gpu/drm/vc4/vc4_gem.c
+++ b/drivers/gpu/drm/vc4/vc4_gem.c
@@ -594,12 +594,14 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec)
 					  args->shader_rec_count);
 	struct vc4_bo *bo;
 
-	if (uniforms_offset < shader_rec_offset ||
+	if (shader_rec_offset < args->bin_cl_size ||
+	    uniforms_offset < shader_rec_offset ||
 	    exec_size < uniforms_offset ||
 	    args->shader_rec_count >= (UINT_MAX /
 					  sizeof(struct vc4_shader_state)) ||
 	    temp_size < exec_size) {
 		DRM_ERROR("overflow in exec arguments\n");
+		ret = -EINVAL;
 		goto fail;
 	}
 
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 881bf489478b..686cdd3c86f2 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -858,7 +858,7 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev,
 		}
 	}
 	plane = &vc4_plane->base;
-	ret = drm_universal_plane_init(dev, plane, 0xff,
+	ret = drm_universal_plane_init(dev, plane, 0,
 				       &vc4_plane_funcs,
 				       formats, num_formats,
 				       type, NULL);
diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c
index 08886a309757..5cdd003605f5 100644
--- a/drivers/gpu/drm/vc4/vc4_render_cl.c
+++ b/drivers/gpu/drm/vc4/vc4_render_cl.c
@@ -461,7 +461,7 @@ static int vc4_rcl_surface_setup(struct vc4_exec_info *exec,
 		}
 
 		ret = vc4_full_res_bounds_check(exec, *obj, surf);
-		if (!ret)
+		if (ret)
 			return ret;
 
 		return 0;
diff --git a/drivers/gpu/drm/virtio/virtgpu_fb.c b/drivers/gpu/drm/virtio/virtgpu_fb.c
index dd21f950e129..cde9f3758106 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fb.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fb.c
@@ -331,7 +331,7 @@ static int virtio_gpufb_create(struct drm_fb_helper *helper,
 	info->fbops = &virtio_gpufb_ops;
 	info->pixmap.flags = FB_PIXMAP_SYSTEM;
 
-	info->screen_base = obj->vmap;
+	info->screen_buffer = obj->vmap;
 	info->screen_size = obj->gem_base.size;
 	drm_fb_helper_fill_fix(info, fb->pitches[0], fb->depth);
 	drm_fb_helper_fill_var(info, &vfbdev->helper,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 723fd763da8e..7a96798b9c0a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -481,8 +481,7 @@ static int vmw_fb_kms_framebuffer(struct fb_info *info)
 	mode_cmd.height = var->yres;
 	mode_cmd.pitches[0] = ((var->bits_per_pixel + 7) / 8) * mode_cmd.width;
 	mode_cmd.pixel_format =
-		drm_mode_legacy_fb_format(var->bits_per_pixel,
-			((var->bits_per_pixel + 7) / 8) * mode_cmd.width);
+		drm_mode_legacy_fb_format(var->bits_per_pixel, depth);
 
 	cur_fb = par->set_fb;
 	if (cur_fb && cur_fb->width == mode_cmd.width &&
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 4070b7386e9d..1aeb80e52424 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -785,6 +785,11 @@ config HID_SUNPLUS
 config HID_RMI
 	tristate "Synaptics RMI4 device support"
 	depends on HID
+	select RMI4_CORE
+	select RMI4_F03
+	select RMI4_F11
+	select RMI4_F12
+	select RMI4_F30
 	---help---
 	Support for Synaptics RMI4 touchpads.
 	Say Y here if you have a Synaptics RMI4 touchpads over i2c-hid or usbhid
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index ea36b557d5ee..538ff697a4cf 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -43,7 +43,6 @@
  */
 
 #define DRIVER_DESC "HID core driver"
-#define DRIVER_LICENSE "GPL"
 
 int hid_debug = 0;
 module_param_named(debug, hid_debug, int, 0600);
@@ -724,13 +723,7 @@ static void hid_scan_collection(struct hid_parser *parser, unsigned type)
 		hid->group = HID_GROUP_SENSOR_HUB;
 
 	if (hid->vendor == USB_VENDOR_ID_MICROSOFT &&
-	    (hid->product == USB_DEVICE_ID_MS_TYPE_COVER_PRO_3 ||
-	     hid->product == USB_DEVICE_ID_MS_TYPE_COVER_PRO_3_2 ||
-	     hid->product == USB_DEVICE_ID_MS_TYPE_COVER_PRO_3_JP ||
-	     hid->product == USB_DEVICE_ID_MS_TYPE_COVER_PRO_4 ||
-	     hid->product == USB_DEVICE_ID_MS_TYPE_COVER_PRO_4_2 ||
-	     hid->product == USB_DEVICE_ID_MS_TYPE_COVER_PRO_4_JP ||
-	     hid->product == USB_DEVICE_ID_MS_POWER_COVER) &&
+	    hid->product == USB_DEVICE_ID_MS_POWER_COVER &&
 	    hid->group == HID_GROUP_MULTITOUCH)
 		hid->group = HID_GROUP_GENERIC;
 
@@ -826,7 +819,8 @@ static int hid_scan_report(struct hid_device *hid)
 		hid->group = HID_GROUP_WACOM;
 		break;
 	case USB_VENDOR_ID_SYNAPTICS:
-		if (hid->group == HID_GROUP_GENERIC)
+		if (hid->group == HID_GROUP_GENERIC ||
+		    hid->group == HID_GROUP_MULTITOUCH_WIN_8)
 			if ((parser->scan_flags & HID_SCAN_FLAG_VENDOR_SPECIFIC)
 			    && (parser->scan_flags & HID_SCAN_FLAG_GD_POINTER))
 				/*
@@ -1887,6 +1881,9 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, 0x0011) },
 #if IS_ENABLED(CONFIG_HID_MAYFLASH)
 	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_PS3) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_DOLPHINBAR) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_GAMECUBE1) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_GAMECUBE2) },
 #endif
 	{ HID_USB_DEVICE(USB_VENDOR_ID_DREAM_CHEEKY, USB_DEVICE_ID_DREAM_CHEEKY_WN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_DREAM_CHEEKY, USB_DEVICE_ID_DREAM_CHEEKY_FA) },
@@ -1933,6 +1930,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CBTKBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPPRODOCK) },
 #endif
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LG, USB_DEVICE_ID_LG_MELFAS_MT) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER_2) },
@@ -1985,12 +1983,6 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_DIGITAL_MEDIA_3K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_WIRELESS_OPTICAL_DESKTOP_3_0) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_OFFICE_KB) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_3) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_3_2) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_3_JP) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_4) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_4_2) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_4_JP) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_DIGITAL_MEDIA_7K) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_DIGITAL_MEDIA_600) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_DIGITAL_MEDIA_3KV1) },
@@ -2126,6 +2118,7 @@ static const struct hid_device_id hid_have_special_driver[] = {
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_NINTENDO, USB_DEVICE_ID_NINTENDO_WIIMOTE2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_RAZER, USB_DEVICE_ID_RAZER_BLADE_14) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CMEDIA, USB_DEVICE_ID_CM6533) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_COVER) },
 	{ }
 };
 
@@ -2314,7 +2307,7 @@ __ATTRIBUTE_GROUPS(hid_dev);
 
 static int hid_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
-	struct hid_device *hdev = to_hid_device(dev);	
+	struct hid_device *hdev = to_hid_device(dev);
 
 	if (add_uevent_var(env, "HID_ID=%04X:%08X:%08X",
 			hdev->bus, hdev->vendor, hdev->product))
@@ -2867,5 +2860,5 @@ module_exit(hid_exit);
 MODULE_AUTHOR("Andreas Gal");
 MODULE_AUTHOR("Vojtech Pavlik");
 MODULE_AUTHOR("Jiri Kosina");
-MODULE_LICENSE(DRIVER_LICENSE);
+MODULE_LICENSE("GPL");
 
diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c
index f31a778b0851..b22d0f83f8e3 100644
--- a/drivers/hid/hid-cp2112.c
+++ b/drivers/hid/hid-cp2112.c
@@ -168,7 +168,7 @@ struct cp2112_device {
 	atomic_t xfer_avail;
 	struct gpio_chip gc;
 	u8 *in_out_buffer;
-	spinlock_t lock;
+	struct mutex lock;
 
 	struct gpio_desc *desc[8];
 	bool gpio_poll;
@@ -186,10 +186,9 @@ static int cp2112_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 	struct cp2112_device *dev = gpiochip_get_data(chip);
 	struct hid_device *hdev = dev->hdev;
 	u8 *buf = dev->in_out_buffer;
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&dev->lock, flags);
+	mutex_lock(&dev->lock);
 
 	ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf,
 				 CP2112_GPIO_CONFIG_LENGTH, HID_FEATURE_REPORT,
@@ -213,8 +212,8 @@ static int cp2112_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 	ret = 0;
 
 exit:
-	spin_unlock_irqrestore(&dev->lock, flags);
-	return ret <= 0 ? ret : -EIO;
+	mutex_unlock(&dev->lock);
+	return ret < 0 ? ret : -EIO;
 }
 
 static void cp2112_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
@@ -222,10 +221,9 @@ static void cp2112_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	struct cp2112_device *dev = gpiochip_get_data(chip);
 	struct hid_device *hdev = dev->hdev;
 	u8 *buf = dev->in_out_buffer;
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&dev->lock, flags);
+	mutex_lock(&dev->lock);
 
 	buf[0] = CP2112_GPIO_SET;
 	buf[1] = value ? 0xff : 0;
@@ -237,7 +235,7 @@ static void cp2112_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	if (ret < 0)
 		hid_err(hdev, "error setting GPIO values: %d\n", ret);
 
-	spin_unlock_irqrestore(&dev->lock, flags);
+	mutex_unlock(&dev->lock);
 }
 
 static int cp2112_gpio_get_all(struct gpio_chip *chip)
@@ -245,10 +243,9 @@ static int cp2112_gpio_get_all(struct gpio_chip *chip)
 	struct cp2112_device *dev = gpiochip_get_data(chip);
 	struct hid_device *hdev = dev->hdev;
 	u8 *buf = dev->in_out_buffer;
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&dev->lock, flags);
+	mutex_lock(&dev->lock);
 
 	ret = hid_hw_raw_request(hdev, CP2112_GPIO_GET, buf,
 				 CP2112_GPIO_GET_LENGTH, HID_FEATURE_REPORT,
@@ -262,7 +259,7 @@ static int cp2112_gpio_get_all(struct gpio_chip *chip)
 	ret = buf[1];
 
 exit:
-	spin_unlock_irqrestore(&dev->lock, flags);
+	mutex_unlock(&dev->lock);
 
 	return ret;
 }
@@ -284,10 +281,9 @@ static int cp2112_gpio_direction_output(struct gpio_chip *chip,
 	struct cp2112_device *dev = gpiochip_get_data(chip);
 	struct hid_device *hdev = dev->hdev;
 	u8 *buf = dev->in_out_buffer;
-	unsigned long flags;
 	int ret;
 
-	spin_lock_irqsave(&dev->lock, flags);
+	mutex_lock(&dev->lock);
 
 	ret = hid_hw_raw_request(hdev, CP2112_GPIO_CONFIG, buf,
 				 CP2112_GPIO_CONFIG_LENGTH, HID_FEATURE_REPORT,
@@ -308,7 +304,7 @@ static int cp2112_gpio_direction_output(struct gpio_chip *chip,
 		goto fail;
 	}
 
-	spin_unlock_irqrestore(&dev->lock, flags);
+	mutex_unlock(&dev->lock);
 
 	/*
 	 * Set gpio value when output direction is already set,
@@ -319,7 +315,7 @@ static int cp2112_gpio_direction_output(struct gpio_chip *chip,
 	return 0;
 
 fail:
-	spin_unlock_irqrestore(&dev->lock, flags);
+	mutex_unlock(&dev->lock);
 	return ret < 0 ? ret : -EIO;
 }
 
@@ -1235,7 +1231,7 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (!dev->in_out_buffer)
 		return -ENOMEM;
 
-	spin_lock_init(&dev->lock);
+	mutex_init(&dev->lock);
 
 	ret = hid_parse(hdev);
 	if (ret) {
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index f46f2c5117fa..86c95d30ac80 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -76,6 +76,9 @@
 #define USB_VENDOR_ID_ALPS_JP		0x044E
 #define HID_DEVICE_ID_ALPS_U1_DUAL	0x120B
 
+#define USB_VENDOR_ID_AMI		0x046b
+#define USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE	0xff10
+
 #define USB_VENDOR_ID_ANTON		0x1130
 #define USB_DEVICE_ID_ANTON_TOUCH_PAD	0x3101
 
@@ -320,7 +323,8 @@
 #define USB_DEVICE_ID_DRAGONRISE_WIIU		0x1800
 #define USB_DEVICE_ID_DRAGONRISE_PS3		0x1801
 #define USB_DEVICE_ID_DRAGONRISE_DOLPHINBAR	0x1803
-#define USB_DEVICE_ID_DRAGONRISE_GAMECUBE	0x1843
+#define USB_DEVICE_ID_DRAGONRISE_GAMECUBE1	0x1843
+#define USB_DEVICE_ID_DRAGONRISE_GAMECUBE2	0x1844
 
 #define USB_VENDOR_ID_DWAV		0x0eef
 #define USB_DEVICE_ID_EGALAX_TOUCHCONTROLLER	0x0001
@@ -627,9 +631,11 @@
 #define USB_DEVICE_ID_LENOVO_CUSBKBD	0x6047
 #define USB_DEVICE_ID_LENOVO_CBTKBD	0x6048
 #define USB_DEVICE_ID_LENOVO_TPPRODOCK	0x6067
+#define USB_DEVICE_ID_LENOVO_X1_COVER	0x6085
 
 #define USB_VENDOR_ID_LG		0x1fd2
 #define USB_DEVICE_ID_LG_MULTITOUCH	0x0064
+#define USB_DEVICE_ID_LG_MELFAS_MT	0x6007
 
 #define USB_VENDOR_ID_LOGITECH		0x046d
 #define USB_DEVICE_ID_LOGITECH_AUDIOHUB 0x0a0e
@@ -722,12 +728,6 @@
 #define USB_DEVICE_ID_MS_SURFACE_PRO_2   0x0799
 #define USB_DEVICE_ID_MS_TOUCH_COVER_2   0x07a7
 #define USB_DEVICE_ID_MS_TYPE_COVER_2    0x07a9
-#define USB_DEVICE_ID_MS_TYPE_COVER_PRO_3    0x07dc
-#define USB_DEVICE_ID_MS_TYPE_COVER_PRO_3_2  0x07e2
-#define USB_DEVICE_ID_MS_TYPE_COVER_PRO_3_JP 0x07dd
-#define USB_DEVICE_ID_MS_TYPE_COVER_PRO_4 0x07e4
-#define USB_DEVICE_ID_MS_TYPE_COVER_PRO_4_2 0x07e8
-#define USB_DEVICE_ID_MS_TYPE_COVER_PRO_4_JP 0x07e9
 #define USB_DEVICE_ID_MS_POWER_COVER     0x07da
 
 #define USB_VENDOR_ID_MOJO		0x8282
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index c5c5fbe9d605..52026dc94d5c 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -872,7 +872,7 @@ static const struct hid_device_id lg_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_WINGMAN_FFG),
 		.driver_data = LG_NOGET | LG_FF4 },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_RUMBLEPAD2),
-		.driver_data = LG_FF2 },
+		.driver_data = LG_NOGET | LG_FF2 },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_FLIGHT_SYSTEM_G940),
 		.driver_data = LG_FF3 },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_SPACENAVIGATOR),
diff --git a/drivers/hid/hid-mf.c b/drivers/hid/hid-mf.c
index d9090765a6e5..03f10516131d 100644
--- a/drivers/hid/hid-mf.c
+++ b/drivers/hid/hid-mf.c
@@ -6,12 +6,14 @@
  *
  * Tested with:
  * 0079:1801 "DragonRise Inc. Mayflash PS3 Game Controller Adapter"
+ * 0079:1803 "DragonRise Inc. Mayflash Wireless Sensor DolphinBar"
+ * 0079:1843 "DragonRise Inc. Mayflash GameCube Game Controller Adapter"
+ * 0079:1844 "DragonRise Inc. Mayflash GameCube Game Controller Adapter (v04)"
  *
  * The following adapters probably work too, but need to be tested:
  * 0079:1800 "DragonRise Inc. Mayflash WIIU Game Controller Adapter"
- * 0079:1843 "DragonRise Inc. Mayflash GameCube Game Controller Adapter"
  *
- * Copyright (c) 2016 Marcel Hasler <mahasler@gmail.com>
+ * Copyright (c) 2016-2017 Marcel Hasler <mahasler@gmail.com>
  */
 
 /*
@@ -125,8 +127,8 @@ static int mf_probe(struct hid_device *hid, const struct hid_device_id *id)
 
 	dev_dbg(&hid->dev, "Mayflash HID hardware probe...\n");
 
-	/* Split device into four inputs */
-	hid->quirks |= HID_QUIRK_MULTI_INPUT;
+	/* Apply quirks as needed */
+	hid->quirks |= id->driver_data;
 
 	error = hid_parse(hid);
 	if (error) {
@@ -151,7 +153,14 @@ static int mf_probe(struct hid_device *hid, const struct hid_device_id *id)
 }
 
 static const struct hid_device_id mf_devices[] = {
-	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_PS3),  },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_PS3),
+		.driver_data = HID_QUIRK_MULTI_INPUT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_DOLPHINBAR),
+		.driver_data = HID_QUIRK_MULTI_INPUT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_GAMECUBE1),
+		.driver_data = HID_QUIRK_MULTI_INPUT },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_GAMECUBE2),
+		.driver_data = 0 }, /* No quirk required */
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, mf_devices);
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index 74b7b84a0420..96e7d3231d2f 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -274,18 +274,6 @@ static const struct hid_device_id ms_devices[] = {
 		.driver_data = MS_NOGET },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_COMFORT_MOUSE_4500),
 		.driver_data = MS_DUPLICATE_USAGES },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_3),
-		.driver_data = MS_HIDINPUT },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_3_2),
-		.driver_data = MS_HIDINPUT },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_3_JP),
-		.driver_data = MS_HIDINPUT },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_4),
-		.driver_data = MS_HIDINPUT },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_4_2),
-		.driver_data = MS_HIDINPUT },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_4_JP),
-		.driver_data = MS_HIDINPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER),
 		.driver_data = MS_HIDINPUT },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_COMFORT_KEYBOARD),
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 6dca66806844..692647485a53 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -68,6 +68,7 @@ MODULE_LICENSE("GPL");
 #define MT_QUIRK_HOVERING		(1 << 11)
 #define MT_QUIRK_CONTACT_CNT_ACCURATE	(1 << 12)
 #define MT_QUIRK_FORCE_GET_FEATURE	(1 << 13)
+#define MT_QUIRK_FIX_CONST_CONTACT_ID	(1 << 14)
 
 #define MT_INPUTMODE_TOUCHSCREEN	0x02
 #define MT_INPUTMODE_TOUCHPAD		0x03
@@ -157,6 +158,7 @@ static void mt_post_parse(struct mt_device *td);
 #define MT_CLS_FLATFROG				0x0107
 #define MT_CLS_GENERALTOUCH_TWOFINGERS		0x0108
 #define MT_CLS_GENERALTOUCH_PWT_TENFINGERS	0x0109
+#define MT_CLS_LG				0x010a
 #define MT_CLS_VTL				0x0110
 
 #define MT_DEFAULT_MAXCONTACT	10
@@ -263,6 +265,12 @@ static struct mt_class mt_classes[] = {
 		.sn_move = 2048,
 		.maxcontacts = 40,
 	},
+	{ .name = MT_CLS_LG,
+		.quirks = MT_QUIRK_ALWAYS_VALID |
+			MT_QUIRK_FIX_CONST_CONTACT_ID |
+			MT_QUIRK_IGNORE_DUPLICATES |
+			MT_QUIRK_HOVERING |
+			MT_QUIRK_CONTACT_CNT_ACCURATE },
 	{ .name = MT_CLS_VTL,
 		.quirks = MT_QUIRK_ALWAYS_VALID |
 			MT_QUIRK_CONTACT_CNT_ACCURATE |
@@ -1078,6 +1086,34 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi)
 	return 0;
 }
 
+static void mt_fix_const_field(struct hid_field *field, unsigned int usage)
+{
+	if (field->usage[0].hid != usage ||
+	    !(field->flags & HID_MAIN_ITEM_CONSTANT))
+		return;
+
+	field->flags &= ~HID_MAIN_ITEM_CONSTANT;
+	field->flags |= HID_MAIN_ITEM_VARIABLE;
+}
+
+static void mt_fix_const_fields(struct hid_device *hdev, unsigned int usage)
+{
+	struct hid_report *report;
+	int i;
+
+	list_for_each_entry(report,
+			    &hdev->report_enum[HID_INPUT_REPORT].report_list,
+			    list) {
+
+		if (!report->maxfield)
+			continue;
+
+		for (i = 0; i < report->maxfield; i++)
+			if (report->field[i]->maxusage >= 1)
+				mt_fix_const_field(report->field[i], usage);
+	}
+}
+
 static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
 {
 	int ret, i;
@@ -1151,6 +1187,9 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	if (ret != 0)
 		return ret;
 
+	if (mtclass->quirks & MT_QUIRK_FIX_CONST_CONTACT_ID)
+		mt_fix_const_fields(hdev, HID_DG_CONTACTID);
+
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret)
 		return ret;
@@ -1398,6 +1437,11 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_ILITEK,
 			USB_DEVICE_ID_ILITEK_MULTITOUCH) },
 
+	/* LG Melfas panel */
+	{ .driver_data = MT_CLS_LG,
+		HID_USB_DEVICE(USB_VENDOR_ID_LG,
+			USB_DEVICE_ID_LG_MELFAS_MT) },
+
 	/* MosArt panels */
 	{ .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE,
 		MT_USB_DEVICE(USB_VENDOR_ID_ASUS,
diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c
index be89bcbf6a71..5b40c2614599 100644
--- a/drivers/hid/hid-rmi.c
+++ b/drivers/hid/hid-rmi.c
@@ -14,11 +14,14 @@
 #include <linux/hid.h>
 #include <linux/input.h>
 #include <linux/input/mt.h>
+#include <linux/irq.h>
+#include <linux/irqdomain.h>
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/slab.h>
 #include <linux/wait.h>
 #include <linux/sched.h>
+#include <linux/rmi.h>
 #include "hid-ids.h"
 
 #define RMI_MOUSE_REPORT_ID		0x01 /* Mouse emulation Report */
@@ -33,9 +36,6 @@
 #define RMI_READ_DATA_PENDING		1
 #define RMI_STARTED			2
 
-#define RMI_SLEEP_NORMAL		0x0
-#define RMI_SLEEP_DEEP_SLEEP		0x1
-
 /* device flags */
 #define RMI_DEVICE			BIT(0)
 #define RMI_DEVICE_HAS_PHYS_BUTTONS	BIT(1)
@@ -54,25 +54,12 @@ enum rmi_mode_type {
 	RMI_MODE_NO_PACKED_ATTN_REPORTS	= 2,
 };
 
-struct rmi_function {
-	unsigned page;			/* page of the function */
-	u16 query_base_addr;		/* base address for queries */
-	u16 command_base_addr;		/* base address for commands */
-	u16 control_base_addr;		/* base address for controls */
-	u16 data_base_addr;		/* base address for datas */
-	unsigned int interrupt_base;	/* cross-function interrupt number
-					 * (uniq in the device)*/
-	unsigned int interrupt_count;	/* number of interrupts */
-	unsigned int report_size;	/* size of a report */
-	unsigned long irq_mask;		/* mask of the interrupts
-					 * (to be applied against ATTN IRQ) */
-};
-
 /**
  * struct rmi_data - stores information for hid communication
  *
  * @page_mutex: Locks current page to avoid changing pages in unexpected ways.
  * @page: Keeps track of the current virtual page
+ * @xport: transport device to be registered with the RMI4 core.
  *
  * @wait: Used for waiting for read data
  *
@@ -84,26 +71,18 @@ struct rmi_function {
  *
  * @flags: flags for the current device (started, reading, etc...)
  *
- * @f11: placeholder of internal RMI function F11 description
- * @f30: placeholder of internal RMI function F30 description
- *
- * @max_fingers: maximum finger count reported by the device
- * @max_x: maximum x value reported by the device
- * @max_y: maximum y value reported by the device
- *
- * @gpio_led_count: count of GPIOs + LEDs reported by F30
- * @button_count: actual physical buttons count
- * @button_mask: button mask used to decode GPIO ATTN reports
- * @button_state_mask: pull state of the buttons
- *
- * @input: pointer to the kernel input device
- *
  * @reset_work: worker which will be called in case of a mouse report
  * @hdev: pointer to the struct hid_device
+ *
+ * @device_flags: flags which describe the device
+ *
+ * @domain: the IRQ domain allocated for this RMI4 device
+ * @rmi_irq: the irq that will be used to generate events to rmi-core
  */
 struct rmi_data {
 	struct mutex page_mutex;
 	int page;
+	struct rmi_transport_dev xport;
 
 	wait_queue_head_t wait;
 
@@ -115,34 +94,13 @@ struct rmi_data {
 
 	unsigned long flags;
 
-	struct rmi_function f01;
-	struct rmi_function f11;
-	struct rmi_function f30;
-
-	unsigned int max_fingers;
-	unsigned int max_x;
-	unsigned int max_y;
-	unsigned int x_size_mm;
-	unsigned int y_size_mm;
-	bool read_f11_ctrl_regs;
-	u8 f11_ctrl_regs[RMI_F11_CTRL_REG_COUNT];
-
-	unsigned int gpio_led_count;
-	unsigned int button_count;
-	unsigned long button_mask;
-	unsigned long button_state_mask;
-
-	struct input_dev *input;
-
 	struct work_struct reset_work;
 	struct hid_device *hdev;
 
 	unsigned long device_flags;
-	unsigned long firmware_id;
 
-	u8 f01_ctrl0;
-	u8 interrupt_enable_mask;
-	bool restore_interrupt_mask;
+	struct irq_domain *domain;
+	int rmi_irq;
 };
 
 #define RMI_PAGE(addr) (((addr) >> 8) & 0xff)
@@ -220,10 +178,11 @@ static int rmi_write_report(struct hid_device *hdev, u8 *report, int len)
 	return ret;
 }
 
-static int rmi_read_block(struct hid_device *hdev, u16 addr, void *buf,
-		const int len)
+static int rmi_hid_read_block(struct rmi_transport_dev *xport, u16 addr,
+		void *buf, size_t len)
 {
-	struct rmi_data *data = hid_get_drvdata(hdev);
+	struct rmi_data *data = container_of(xport, struct rmi_data, xport);
+	struct hid_device *hdev = data->hdev;
 	int ret;
 	int bytes_read;
 	int bytes_needed;
@@ -292,15 +251,11 @@ exit:
 	return ret;
 }
 
-static inline int rmi_read(struct hid_device *hdev, u16 addr, void *buf)
-{
-	return rmi_read_block(hdev, addr, buf, 1);
-}
-
-static int rmi_write_block(struct hid_device *hdev, u16 addr, void *buf,
-		const int len)
+static int rmi_hid_write_block(struct rmi_transport_dev *xport, u16 addr,
+		const void *buf, size_t len)
 {
-	struct rmi_data *data = hid_get_drvdata(hdev);
+	struct rmi_data *data = container_of(xport, struct rmi_data, xport);
+	struct hid_device *hdev = data->hdev;
 	int ret;
 
 	mutex_lock(&data->page_mutex);
@@ -332,62 +287,20 @@ exit:
 	return ret;
 }
 
-static inline int rmi_write(struct hid_device *hdev, u16 addr, void *buf)
-{
-	return rmi_write_block(hdev, addr, buf, 1);
-}
-
-static void rmi_f11_process_touch(struct rmi_data *hdata, int slot,
-		u8 finger_state, u8 *touch_data)
-{
-	int x, y, wx, wy;
-	int wide, major, minor;
-	int z;
-
-	input_mt_slot(hdata->input, slot);
-	input_mt_report_slot_state(hdata->input, MT_TOOL_FINGER,
-			finger_state == 0x01);
-	if (finger_state == 0x01) {
-		x = (touch_data[0] << 4) | (touch_data[2] & 0x0F);
-		y = (touch_data[1] << 4) | (touch_data[2] >> 4);
-		wx = touch_data[3] & 0x0F;
-		wy = touch_data[3] >> 4;
-		wide = (wx > wy);
-		major = max(wx, wy);
-		minor = min(wx, wy);
-		z = touch_data[4];
-
-		/* y is inverted */
-		y = hdata->max_y - y;
-
-		input_event(hdata->input, EV_ABS, ABS_MT_POSITION_X, x);
-		input_event(hdata->input, EV_ABS, ABS_MT_POSITION_Y, y);
-		input_event(hdata->input, EV_ABS, ABS_MT_ORIENTATION, wide);
-		input_event(hdata->input, EV_ABS, ABS_MT_PRESSURE, z);
-		input_event(hdata->input, EV_ABS, ABS_MT_TOUCH_MAJOR, major);
-		input_event(hdata->input, EV_ABS, ABS_MT_TOUCH_MINOR, minor);
-	}
-}
-
 static int rmi_reset_attn_mode(struct hid_device *hdev)
 {
 	struct rmi_data *data = hid_get_drvdata(hdev);
+	struct rmi_device *rmi_dev = data->xport.rmi_dev;
 	int ret;
 
 	ret = rmi_set_mode(hdev, RMI_MODE_ATTN_REPORTS);
 	if (ret)
 		return ret;
 
-	if (data->restore_interrupt_mask) {
-		ret = rmi_write(hdev, data->f01.control_base_addr + 1,
-				&data->interrupt_enable_mask);
-		if (ret) {
-			hid_err(hdev, "can not write F01 control register\n");
-			return ret;
-		}
-	}
+	if (test_bit(RMI_STARTED, &data->flags))
+		ret = rmi_dev->driver->reset_handler(rmi_dev);
 
-	return 0;
+	return ret;
 }
 
 static void rmi_reset_work(struct work_struct *work)
@@ -399,102 +312,22 @@ static void rmi_reset_work(struct work_struct *work)
 	rmi_reset_attn_mode(hdata->hdev);
 }
 
-static inline int rmi_schedule_reset(struct hid_device *hdev)
-{
-	struct rmi_data *hdata = hid_get_drvdata(hdev);
-	return schedule_work(&hdata->reset_work);
-}
-
-static int rmi_f11_input_event(struct hid_device *hdev, u8 irq, u8 *data,
-		int size)
-{
-	struct rmi_data *hdata = hid_get_drvdata(hdev);
-	int offset;
-	int i;
-
-	if (!(irq & hdata->f11.irq_mask) || size <= 0)
-		return 0;
-
-	offset = (hdata->max_fingers >> 2) + 1;
-	for (i = 0; i < hdata->max_fingers; i++) {
-		int fs_byte_position = i >> 2;
-		int fs_bit_position = (i & 0x3) << 1;
-		int finger_state = (data[fs_byte_position] >> fs_bit_position) &
-					0x03;
-		int position = offset + 5 * i;
-
-		if (position + 5 > size) {
-			/* partial report, go on with what we received */
-			printk_once(KERN_WARNING
-				"%s %s: Detected incomplete finger report. Finger reports may occasionally get dropped on this platform.\n",
-				 dev_driver_string(&hdev->dev),
-				 dev_name(&hdev->dev));
-			hid_dbg(hdev, "Incomplete finger report\n");
-			break;
-		}
-
-		rmi_f11_process_touch(hdata, i, finger_state, &data[position]);
-	}
-	input_mt_sync_frame(hdata->input);
-	input_sync(hdata->input);
-	return hdata->f11.report_size;
-}
-
-static int rmi_f30_input_event(struct hid_device *hdev, u8 irq, u8 *data,
-		int size)
+static int rmi_input_event(struct hid_device *hdev, u8 *data, int size)
 {
 	struct rmi_data *hdata = hid_get_drvdata(hdev);
-	int i;
-	int button = 0;
-	bool value;
+	struct rmi_device *rmi_dev = hdata->xport.rmi_dev;
+	unsigned long flags;
 
-	if (!(irq & hdata->f30.irq_mask))
+	if (!(test_bit(RMI_STARTED, &hdata->flags)))
 		return 0;
 
-	if (size < (int)hdata->f30.report_size) {
-		hid_warn(hdev, "Click Button pressed, but the click data is missing\n");
-		return 0;
-	}
+	local_irq_save(flags);
 
-	for (i = 0; i < hdata->gpio_led_count; i++) {
-		if (test_bit(i, &hdata->button_mask)) {
-			value = (data[i / 8] >> (i & 0x07)) & BIT(0);
-			if (test_bit(i, &hdata->button_state_mask))
-				value = !value;
-			input_event(hdata->input, EV_KEY, BTN_LEFT + button++,
-					value);
-		}
-	}
-	return hdata->f30.report_size;
-}
-
-static int rmi_input_event(struct hid_device *hdev, u8 *data, int size)
-{
-	struct rmi_data *hdata = hid_get_drvdata(hdev);
-	unsigned long irq_mask = 0;
-	unsigned index = 2;
+	rmi_set_attn_data(rmi_dev, data[1], &data[2], size - 2);
 
-	if (!(test_bit(RMI_STARTED, &hdata->flags)))
-		return 0;
+	generic_handle_irq(hdata->rmi_irq);
 
-	irq_mask |= hdata->f11.irq_mask;
-	irq_mask |= hdata->f30.irq_mask;
-
-	if (data[1] & ~irq_mask)
-		hid_dbg(hdev, "unknown intr source:%02lx %s:%d\n",
-			data[1] & ~irq_mask, __FILE__, __LINE__);
-
-	if (hdata->f11.interrupt_base < hdata->f30.interrupt_base) {
-		index += rmi_f11_input_event(hdev, data[1], &data[index],
-				size - index);
-		index += rmi_f30_input_event(hdev, data[1], &data[index],
-				size - index);
-	} else {
-		index += rmi_f30_input_event(hdev, data[1], &data[index],
-				size - index);
-		index += rmi_f11_input_event(hdev, data[1], &data[index],
-				size - index);
-	}
+	local_irq_restore(flags);
 
 	return 1;
 }
@@ -568,7 +401,7 @@ static int rmi_event(struct hid_device *hdev, struct hid_field *field,
 				return 1;
 		}
 
-		rmi_schedule_reset(hdev);
+		schedule_work(&data->reset_work);
 		return 1;
 	}
 
@@ -576,637 +409,71 @@ static int rmi_event(struct hid_device *hdev, struct hid_field *field,
 }
 
 #ifdef CONFIG_PM
-static int rmi_set_sleep_mode(struct hid_device *hdev, int sleep_mode)
-{
-	struct rmi_data *data = hid_get_drvdata(hdev);
-	int ret;
-	u8 f01_ctrl0;
-
-	f01_ctrl0 = (data->f01_ctrl0 & ~0x3) | sleep_mode;
-
-	ret = rmi_write(hdev, data->f01.control_base_addr,
-			&f01_ctrl0);
-	if (ret) {
-		hid_err(hdev, "can not write sleep mode\n");
-		return ret;
-	}
-
-	return 0;
-}
-
 static int rmi_suspend(struct hid_device *hdev, pm_message_t message)
 {
 	struct rmi_data *data = hid_get_drvdata(hdev);
-	int ret;
-	u8 buf[RMI_F11_CTRL_REG_COUNT];
-
-	if (!(data->device_flags & RMI_DEVICE))
-		return 0;
-
-	ret = rmi_read_block(hdev, data->f11.control_base_addr, buf,
-				RMI_F11_CTRL_REG_COUNT);
-	if (ret)
-		hid_warn(hdev, "can not read F11 control registers\n");
-	else
-		memcpy(data->f11_ctrl_regs, buf, RMI_F11_CTRL_REG_COUNT);
-
-
-	if (!device_may_wakeup(hdev->dev.parent))
-		return rmi_set_sleep_mode(hdev, RMI_SLEEP_DEEP_SLEEP);
-
-	return 0;
-}
-
-static int rmi_post_reset(struct hid_device *hdev)
-{
-	struct rmi_data *data = hid_get_drvdata(hdev);
+	struct rmi_device *rmi_dev = data->xport.rmi_dev;
 	int ret;
 
 	if (!(data->device_flags & RMI_DEVICE))
 		return 0;
 
-	ret = rmi_reset_attn_mode(hdev);
+	ret = rmi_driver_suspend(rmi_dev, false);
 	if (ret) {
-		hid_err(hdev, "can not set rmi mode\n");
+		hid_warn(hdev, "Failed to suspend device: %d\n", ret);
 		return ret;
 	}
 
-	if (data->read_f11_ctrl_regs) {
-		ret = rmi_write_block(hdev, data->f11.control_base_addr,
-				data->f11_ctrl_regs, RMI_F11_CTRL_REG_COUNT);
-		if (ret)
-			hid_warn(hdev,
-				"can not write F11 control registers after reset\n");
-	}
-
-	if (!device_may_wakeup(hdev->dev.parent)) {
-		ret = rmi_set_sleep_mode(hdev, RMI_SLEEP_NORMAL);
-		if (ret) {
-			hid_err(hdev, "can not write sleep mode\n");
-			return ret;
-		}
-	}
-
-	return ret;
+	return 0;
 }
 
 static int rmi_post_resume(struct hid_device *hdev)
 {
 	struct rmi_data *data = hid_get_drvdata(hdev);
+	struct rmi_device *rmi_dev = data->xport.rmi_dev;
+	int ret;
 
 	if (!(data->device_flags & RMI_DEVICE))
 		return 0;
 
-	return rmi_reset_attn_mode(hdev);
-}
-#endif /* CONFIG_PM */
-
-#define RMI4_MAX_PAGE 0xff
-#define RMI4_PAGE_SIZE 0x0100
-
-#define PDT_START_SCAN_LOCATION 0x00e9
-#define PDT_END_SCAN_LOCATION	0x0005
-#define RMI4_END_OF_PDT(id) ((id) == 0x00 || (id) == 0xff)
-
-struct pdt_entry {
-	u8 query_base_addr:8;
-	u8 command_base_addr:8;
-	u8 control_base_addr:8;
-	u8 data_base_addr:8;
-	u8 interrupt_source_count:3;
-	u8 bits3and4:2;
-	u8 function_version:2;
-	u8 bit7:1;
-	u8 function_number:8;
-} __attribute__((__packed__));
-
-static inline unsigned long rmi_gen_mask(unsigned irq_base, unsigned irq_count)
-{
-	return GENMASK(irq_count + irq_base - 1, irq_base);
-}
-
-static void rmi_register_function(struct rmi_data *data,
-	struct pdt_entry *pdt_entry, int page, unsigned interrupt_count)
-{
-	struct rmi_function *f = NULL;
-	u16 page_base = page << 8;
-
-	switch (pdt_entry->function_number) {
-	case 0x01:
-		f = &data->f01;
-		break;
-	case 0x11:
-		f = &data->f11;
-		break;
-	case 0x30:
-		f = &data->f30;
-		break;
-	}
-
-	if (f) {
-		f->page = page;
-		f->query_base_addr = page_base | pdt_entry->query_base_addr;
-		f->command_base_addr = page_base | pdt_entry->command_base_addr;
-		f->control_base_addr = page_base | pdt_entry->control_base_addr;
-		f->data_base_addr = page_base | pdt_entry->data_base_addr;
-		f->interrupt_base = interrupt_count;
-		f->interrupt_count = pdt_entry->interrupt_source_count;
-		f->irq_mask = rmi_gen_mask(f->interrupt_base,
-						f->interrupt_count);
-		data->interrupt_enable_mask |= f->irq_mask;
-	}
-}
-
-static int rmi_scan_pdt(struct hid_device *hdev)
-{
-	struct rmi_data *data = hid_get_drvdata(hdev);
-	struct pdt_entry entry;
-	int page;
-	bool page_has_function;
-	int i;
-	int retval;
-	int interrupt = 0;
-	u16 page_start, pdt_start , pdt_end;
-
-	hid_info(hdev, "Scanning PDT...\n");
-
-	for (page = 0; (page <= RMI4_MAX_PAGE); page++) {
-		page_start = RMI4_PAGE_SIZE * page;
-		pdt_start = page_start + PDT_START_SCAN_LOCATION;
-		pdt_end = page_start + PDT_END_SCAN_LOCATION;
-
-		page_has_function = false;
-		for (i = pdt_start; i >= pdt_end; i -= sizeof(entry)) {
-			retval = rmi_read_block(hdev, i, &entry, sizeof(entry));
-			if (retval) {
-				hid_err(hdev,
-					"Read of PDT entry at %#06x failed.\n",
-					i);
-				goto error_exit;
-			}
-
-			if (RMI4_END_OF_PDT(entry.function_number))
-				break;
-
-			page_has_function = true;
-
-			hid_info(hdev, "Found F%02X on page %#04x\n",
-					entry.function_number, page);
-
-			rmi_register_function(data, &entry, page, interrupt);
-			interrupt += entry.interrupt_source_count;
-		}
-
-		if (!page_has_function)
-			break;
-	}
-
-	hid_info(hdev, "%s: Done with PDT scan.\n", __func__);
-	retval = 0;
-
-error_exit:
-	return retval;
-}
-
-#define RMI_DEVICE_F01_BASIC_QUERY_LEN	11
-
-static int rmi_populate_f01(struct hid_device *hdev)
-{
-	struct rmi_data *data = hid_get_drvdata(hdev);
-	u8 basic_queries[RMI_DEVICE_F01_BASIC_QUERY_LEN];
-	u8 info[3];
-	int ret;
-	bool has_query42;
-	bool has_lts;
-	bool has_sensor_id;
-	bool has_ds4_queries = false;
-	bool has_build_id_query = false;
-	bool has_package_id_query = false;
-	u16 query_offset = data->f01.query_base_addr;
-	u16 prod_info_addr;
-	u8 ds4_query_len;
-
-	ret = rmi_read_block(hdev, query_offset, basic_queries,
-				RMI_DEVICE_F01_BASIC_QUERY_LEN);
-	if (ret) {
-		hid_err(hdev, "Can not read basic queries from Function 0x1.\n");
-		return ret;
-	}
-
-	has_lts = !!(basic_queries[0] & BIT(2));
-	has_sensor_id = !!(basic_queries[1] & BIT(3));
-	has_query42 = !!(basic_queries[1] & BIT(7));
-
-	query_offset += 11;
-	prod_info_addr = query_offset + 6;
-	query_offset += 10;
-
-	if (has_lts)
-		query_offset += 20;
-
-	if (has_sensor_id)
-		query_offset++;
-
-	if (has_query42) {
-		ret = rmi_read(hdev, query_offset, info);
-		if (ret) {
-			hid_err(hdev, "Can not read query42.\n");
-			return ret;
-		}
-		has_ds4_queries = !!(info[0] & BIT(0));
-		query_offset++;
-	}
-
-	if (has_ds4_queries) {
-		ret = rmi_read(hdev, query_offset, &ds4_query_len);
-		if (ret) {
-			hid_err(hdev, "Can not read DS4 Query length.\n");
-			return ret;
-		}
-		query_offset++;
-
-		if (ds4_query_len > 0) {
-			ret = rmi_read(hdev, query_offset, info);
-			if (ret) {
-				hid_err(hdev, "Can not read DS4 query.\n");
-				return ret;
-			}
-
-			has_package_id_query = !!(info[0] & BIT(0));
-			has_build_id_query = !!(info[0] & BIT(1));
-		}
-	}
-
-	if (has_package_id_query)
-		prod_info_addr++;
-
-	if (has_build_id_query) {
-		ret = rmi_read_block(hdev, prod_info_addr, info, 3);
-		if (ret) {
-			hid_err(hdev, "Can not read product info.\n");
-			return ret;
-		}
-
-		data->firmware_id = info[1] << 8 | info[0];
-		data->firmware_id += info[2] * 65536;
-	}
-
-	ret = rmi_read_block(hdev, data->f01.control_base_addr, info,
-				2);
-
-	if (ret) {
-		hid_err(hdev, "can not read f01 ctrl registers\n");
-		return ret;
-	}
-
-	data->f01_ctrl0 = info[0];
-
-	if (!info[1]) {
-		/*
-		 * Do to a firmware bug in some touchpads the F01 interrupt
-		 * enable control register will be cleared on reset.
-		 * This will stop the touchpad from reporting data, so
-		 * if F01 CTRL1 is 0 then we need to explicitly enable
-		 * interrupts for the functions we want data for.
-		 */
-		data->restore_interrupt_mask = true;
-
-		ret = rmi_write(hdev, data->f01.control_base_addr + 1,
-				&data->interrupt_enable_mask);
-		if (ret) {
-			hid_err(hdev, "can not write to control reg 1: %d.\n",
-				ret);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-static int rmi_populate_f11(struct hid_device *hdev)
-{
-	struct rmi_data *data = hid_get_drvdata(hdev);
-	u8 buf[20];
-	int ret;
-	bool has_query9;
-	bool has_query10 = false;
-	bool has_query11;
-	bool has_query12;
-	bool has_query27;
-	bool has_query28;
-	bool has_query36 = false;
-	bool has_physical_props;
-	bool has_gestures;
-	bool has_rel;
-	bool has_data40 = false;
-	bool has_dribble = false;
-	bool has_palm_detect = false;
-	unsigned x_size, y_size;
-	u16 query_offset;
-
-	if (!data->f11.query_base_addr) {
-		hid_err(hdev, "No 2D sensor found, giving up.\n");
-		return -ENODEV;
-	}
-
-	/* query 0 contains some useful information */
-	ret = rmi_read(hdev, data->f11.query_base_addr, buf);
-	if (ret) {
-		hid_err(hdev, "can not get query 0: %d.\n", ret);
-		return ret;
-	}
-	has_query9 = !!(buf[0] & BIT(3));
-	has_query11 = !!(buf[0] & BIT(4));
-	has_query12 = !!(buf[0] & BIT(5));
-	has_query27 = !!(buf[0] & BIT(6));
-	has_query28 = !!(buf[0] & BIT(7));
-
-	/* query 1 to get the max number of fingers */
-	ret = rmi_read(hdev, data->f11.query_base_addr + 1, buf);
-	if (ret) {
-		hid_err(hdev, "can not get NumberOfFingers: %d.\n", ret);
-		return ret;
-	}
-	data->max_fingers = (buf[0] & 0x07) + 1;
-	if (data->max_fingers > 5)
-		data->max_fingers = 10;
-
-	data->f11.report_size = data->max_fingers * 5 +
-				DIV_ROUND_UP(data->max_fingers, 4);
-
-	if (!(buf[0] & BIT(4))) {
-		hid_err(hdev, "No absolute events, giving up.\n");
-		return -ENODEV;
-	}
-
-	has_rel = !!(buf[0] & BIT(3));
-	has_gestures = !!(buf[0] & BIT(5));
-
-	ret = rmi_read(hdev, data->f11.query_base_addr + 5, buf);
-	if (ret) {
-		hid_err(hdev, "can not get absolute data sources: %d.\n", ret);
+	ret = rmi_reset_attn_mode(hdev);
+	if (ret)
 		return ret;
-	}
-
-	has_dribble = !!(buf[0] & BIT(4));
-
-	/*
-	 * At least 4 queries are guaranteed to be present in F11
-	 * +1 for query 5 which is present since absolute events are
-	 * reported and +1 for query 12.
-	 */
-	query_offset = 6;
-
-	if (has_rel)
-		++query_offset; /* query 6 is present */
-
-	if (has_gestures) {
-		/* query 8 to find out if query 10 exists */
-		ret = rmi_read(hdev,
-			data->f11.query_base_addr + query_offset + 1, buf);
-		if (ret) {
-			hid_err(hdev, "can not read gesture information: %d.\n",
-				ret);
-			return ret;
-		}
-		has_palm_detect = !!(buf[0] & BIT(0));
-		has_query10 = !!(buf[0] & BIT(2));
-
-		query_offset += 2; /* query 7 and 8 are present */
-	}
-
-	if (has_query9)
-		++query_offset;
-
-	if (has_query10)
-		++query_offset;
-
-	if (has_query11)
-		++query_offset;
-
-	/* query 12 to know if the physical properties are reported */
-	if (has_query12) {
-		ret = rmi_read(hdev, data->f11.query_base_addr
-				+ query_offset, buf);
-		if (ret) {
-			hid_err(hdev, "can not get query 12: %d.\n", ret);
-			return ret;
-		}
-		has_physical_props = !!(buf[0] & BIT(5));
-
-		if (has_physical_props) {
-			query_offset += 1;
-			ret = rmi_read_block(hdev,
-					data->f11.query_base_addr
-						+ query_offset, buf, 4);
-			if (ret) {
-				hid_err(hdev, "can not read query 15-18: %d.\n",
-					ret);
-				return ret;
-			}
-
-			x_size = buf[0] | (buf[1] << 8);
-			y_size = buf[2] | (buf[3] << 8);
-
-			data->x_size_mm = DIV_ROUND_CLOSEST(x_size, 10);
-			data->y_size_mm = DIV_ROUND_CLOSEST(y_size, 10);
-
-			hid_info(hdev, "%s: size in mm: %d x %d\n",
-				 __func__, data->x_size_mm, data->y_size_mm);
-
-			/*
-			 * query 15 - 18 contain the size of the sensor
-			 * and query 19 - 26 contain bezel dimensions
-			 */
-			query_offset += 12;
-		}
-	}
-
-	if (has_query27)
-		++query_offset;
 
-	if (has_query28) {
-		ret = rmi_read(hdev, data->f11.query_base_addr
-				+ query_offset, buf);
-		if (ret) {
-			hid_err(hdev, "can not get query 28: %d.\n", ret);
-			return ret;
-		}
-
-		has_query36 = !!(buf[0] & BIT(6));
-	}
-
-	if (has_query36) {
-		query_offset += 2;
-		ret = rmi_read(hdev, data->f11.query_base_addr
-				+ query_offset, buf);
-		if (ret) {
-			hid_err(hdev, "can not get query 36: %d.\n", ret);
-			return ret;
-		}
-
-		has_data40 = !!(buf[0] & BIT(5));
-	}
-
-
-	if (has_data40)
-		data->f11.report_size += data->max_fingers * 2;
-
-	ret = rmi_read_block(hdev, data->f11.control_base_addr,
-			data->f11_ctrl_regs, RMI_F11_CTRL_REG_COUNT);
+	ret = rmi_driver_resume(rmi_dev, false);
 	if (ret) {
-		hid_err(hdev, "can not read ctrl block of size 11: %d.\n", ret);
+		hid_warn(hdev, "Failed to resume device: %d\n", ret);
 		return ret;
 	}
 
-	/* data->f11_ctrl_regs now contains valid register data */
-	data->read_f11_ctrl_regs = true;
-
-	data->max_x = data->f11_ctrl_regs[6] | (data->f11_ctrl_regs[7] << 8);
-	data->max_y = data->f11_ctrl_regs[8] | (data->f11_ctrl_regs[9] << 8);
-
-	if (has_dribble) {
-		data->f11_ctrl_regs[0] = data->f11_ctrl_regs[0] & ~BIT(6);
-		ret = rmi_write(hdev, data->f11.control_base_addr,
-				data->f11_ctrl_regs);
-		if (ret) {
-			hid_err(hdev, "can not write to control reg 0: %d.\n",
-				ret);
-			return ret;
-		}
-	}
-
-	if (has_palm_detect) {
-		data->f11_ctrl_regs[11] = data->f11_ctrl_regs[11] & ~BIT(0);
-		ret = rmi_write(hdev, data->f11.control_base_addr + 11,
-				&data->f11_ctrl_regs[11]);
-		if (ret) {
-			hid_err(hdev, "can not write to control reg 11: %d.\n",
-				ret);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-static int rmi_populate_f30(struct hid_device *hdev)
-{
-	struct rmi_data *data = hid_get_drvdata(hdev);
-	u8 buf[20];
-	int ret;
-	bool has_gpio, has_led;
-	unsigned bytes_per_ctrl;
-	u8 ctrl2_addr;
-	int ctrl2_3_length;
-	int i;
-
-	/* function F30 is for physical buttons */
-	if (!data->f30.query_base_addr) {
-		hid_err(hdev, "No GPIO/LEDs found, giving up.\n");
-		return -ENODEV;
-	}
-
-	ret = rmi_read_block(hdev, data->f30.query_base_addr, buf, 2);
-	if (ret) {
-		hid_err(hdev, "can not get F30 query registers: %d.\n", ret);
-		return ret;
-	}
-
-	has_gpio = !!(buf[0] & BIT(3));
-	has_led = !!(buf[0] & BIT(2));
-	data->gpio_led_count = buf[1] & 0x1f;
-
-	/* retrieve ctrl 2 & 3 registers */
-	bytes_per_ctrl = (data->gpio_led_count + 7) / 8;
-	/* Ctrl0 is present only if both has_gpio and has_led are set*/
-	ctrl2_addr = (has_gpio && has_led) ? bytes_per_ctrl : 0;
-	/* Ctrl1 is always be present */
-	ctrl2_addr += bytes_per_ctrl;
-	ctrl2_3_length = 2 * bytes_per_ctrl;
-
-	data->f30.report_size = bytes_per_ctrl;
-
-	ret = rmi_read_block(hdev, data->f30.control_base_addr + ctrl2_addr,
-				buf, ctrl2_3_length);
-	if (ret) {
-		hid_err(hdev, "can not read ctrl 2&3 block of size %d: %d.\n",
-			ctrl2_3_length, ret);
-		return ret;
-	}
-
-	for (i = 0; i < data->gpio_led_count; i++) {
-		int byte_position = i >> 3;
-		int bit_position = i & 0x07;
-		u8 dir_byte = buf[byte_position];
-		u8 data_byte = buf[byte_position + bytes_per_ctrl];
-		bool dir = (dir_byte >> bit_position) & BIT(0);
-		bool dat = (data_byte >> bit_position) & BIT(0);
-
-		if (dir == 0) {
-			/* input mode */
-			if (dat) {
-				/* actual buttons have pull up resistor */
-				data->button_count++;
-				set_bit(i, &data->button_mask);
-				set_bit(i, &data->button_state_mask);
-			}
-		}
-
-	}
-
 	return 0;
 }
+#endif /* CONFIG_PM */
 
-static int rmi_populate(struct hid_device *hdev)
+static int rmi_hid_reset(struct rmi_transport_dev *xport, u16 reset_addr)
 {
-	struct rmi_data *data = hid_get_drvdata(hdev);
-	int ret;
-
-	ret = rmi_scan_pdt(hdev);
-	if (ret) {
-		hid_err(hdev, "PDT scan failed with code %d.\n", ret);
-		return ret;
-	}
-
-	ret = rmi_populate_f01(hdev);
-	if (ret) {
-		hid_err(hdev, "Error while initializing F01 (%d).\n", ret);
-		return ret;
-	}
-
-	ret = rmi_populate_f11(hdev);
-	if (ret) {
-		hid_err(hdev, "Error while initializing F11 (%d).\n", ret);
-		return ret;
-	}
-
-	if (!(data->device_flags & RMI_DEVICE_HAS_PHYS_BUTTONS)) {
-		ret = rmi_populate_f30(hdev);
-		if (ret)
-			hid_warn(hdev, "Error while initializing F30 (%d).\n", ret);
-	}
+	struct rmi_data *data = container_of(xport, struct rmi_data, xport);
+	struct hid_device *hdev = data->hdev;
 
-	return 0;
+	return rmi_reset_attn_mode(hdev);
 }
 
 static int rmi_input_configured(struct hid_device *hdev, struct hid_input *hi)
 {
 	struct rmi_data *data = hid_get_drvdata(hdev);
 	struct input_dev *input = hi->input;
-	int ret;
-	int res_x, res_y, i;
+	int ret = 0;
+
+	if (!(data->device_flags & RMI_DEVICE))
+		return 0;
 
-	data->input = input;
+	data->xport.input = input;
 
 	hid_dbg(hdev, "Opening low level driver\n");
 	ret = hid_hw_open(hdev);
 	if (ret)
 		return ret;
 
-	if (!(data->device_flags & RMI_DEVICE))
-		return 0;
-
 	/* Allow incoming hid reports */
 	hid_device_io_start(hdev);
 
@@ -1222,40 +489,10 @@ static int rmi_input_configured(struct hid_device *hdev, struct hid_input *hi)
 		goto exit;
 	}
 
-	ret = rmi_populate(hdev);
-	if (ret)
-		goto exit;
-
-	hid_info(hdev, "firmware id: %ld\n", data->firmware_id);
-
-	__set_bit(EV_ABS, input->evbit);
-	input_set_abs_params(input, ABS_MT_POSITION_X, 1, data->max_x, 0, 0);
-	input_set_abs_params(input, ABS_MT_POSITION_Y, 1, data->max_y, 0, 0);
-
-	if (data->x_size_mm && data->y_size_mm) {
-		res_x = (data->max_x - 1) / data->x_size_mm;
-		res_y = (data->max_y - 1) / data->y_size_mm;
-
-		input_abs_set_res(input, ABS_MT_POSITION_X, res_x);
-		input_abs_set_res(input, ABS_MT_POSITION_Y, res_y);
-	}
-
-	input_set_abs_params(input, ABS_MT_ORIENTATION, 0, 1, 0, 0);
-	input_set_abs_params(input, ABS_MT_PRESSURE, 0, 0xff, 0, 0);
-	input_set_abs_params(input, ABS_MT_TOUCH_MAJOR, 0, 0x0f, 0, 0);
-	input_set_abs_params(input, ABS_MT_TOUCH_MINOR, 0, 0x0f, 0, 0);
-
-	ret = input_mt_init_slots(input, data->max_fingers, INPUT_MT_POINTER);
-	if (ret < 0)
+	ret = rmi_register_transport_device(&data->xport);
+	if (ret < 0) {
+		dev_err(&hdev->dev, "failed to register transport driver\n");
 		goto exit;
-
-	if (data->button_count) {
-		__set_bit(EV_KEY, input->evbit);
-		for (i = 0; i < data->button_count; i++)
-			__set_bit(BTN_LEFT + i, input->keybit);
-
-		if (data->button_count == 1)
-			__set_bit(INPUT_PROP_BUTTONPAD, input->propbit);
 	}
 
 	set_bit(RMI_STARTED, &data->flags);
@@ -1304,6 +541,71 @@ static int rmi_check_valid_report_id(struct hid_device *hdev, unsigned type,
 	return 0;
 }
 
+static struct rmi_device_platform_data rmi_hid_pdata = {
+	.sensor_pdata = {
+		.sensor_type = rmi_sensor_touchpad,
+		.axis_align.flip_y = true,
+		.dribble = RMI_REG_STATE_ON,
+		.palm_detect = RMI_REG_STATE_OFF,
+	},
+};
+
+static const struct rmi_transport_ops hid_rmi_ops = {
+	.write_block	= rmi_hid_write_block,
+	.read_block	= rmi_hid_read_block,
+	.reset		= rmi_hid_reset,
+};
+
+static void rmi_irq_teardown(void *data)
+{
+	struct rmi_data *hdata = data;
+	struct irq_domain *domain = hdata->domain;
+
+	if (!domain)
+		return;
+
+	irq_dispose_mapping(irq_find_mapping(domain, 0));
+
+	irq_domain_remove(domain);
+	hdata->domain = NULL;
+	hdata->rmi_irq = 0;
+}
+
+static int rmi_irq_map(struct irq_domain *h, unsigned int virq,
+		       irq_hw_number_t hw_irq_num)
+{
+	irq_set_chip_and_handler(virq, &dummy_irq_chip, handle_simple_irq);
+
+	return 0;
+}
+
+static const struct irq_domain_ops rmi_irq_ops = {
+	.map = rmi_irq_map,
+};
+
+static int rmi_setup_irq_domain(struct hid_device *hdev)
+{
+	struct rmi_data *hdata = hid_get_drvdata(hdev);
+	int ret;
+
+	hdata->domain = irq_domain_create_linear(hdev->dev.fwnode, 1,
+						 &rmi_irq_ops, hdata);
+	if (!hdata->domain)
+		return -ENOMEM;
+
+	ret = devm_add_action_or_reset(&hdev->dev, &rmi_irq_teardown, hdata);
+	if (ret)
+		return ret;
+
+	hdata->rmi_irq = irq_create_mapping(hdata->domain, 0);
+	if (hdata->rmi_irq <= 0) {
+		hid_err(hdev, "Can't allocate an IRQ\n");
+		return hdata->rmi_irq < 0 ? hdata->rmi_irq : -ENXIO;
+	}
+
+	return 0;
+}
+
 static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id)
 {
 	struct rmi_data *data = NULL;
@@ -1365,8 +667,8 @@ static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id)
 
 	data->writeReport = devm_kzalloc(&hdev->dev, alloc_size, GFP_KERNEL);
 	if (!data->writeReport) {
-		ret = -ENOMEM;
-		return ret;
+		hid_err(hdev, "failed to allocate buffer for HID reports\n");
+		return -ENOMEM;
 	}
 
 	data->readReport = data->writeReport + data->output_report_size;
@@ -1375,6 +677,21 @@ static int rmi_probe(struct hid_device *hdev, const struct hid_device_id *id)
 
 	mutex_init(&data->page_mutex);
 
+	ret = rmi_setup_irq_domain(hdev);
+	if (ret) {
+		hid_err(hdev, "failed to allocate IRQ domain\n");
+		return ret;
+	}
+
+	if (data->device_flags & RMI_DEVICE_HAS_PHYS_BUTTONS)
+		rmi_hid_pdata.f30_data.disable = true;
+
+	data->xport.dev = hdev->dev.parent;
+	data->xport.pdata = rmi_hid_pdata;
+	data->xport.pdata.irq = data->rmi_irq;
+	data->xport.proto_name = "hid";
+	data->xport.ops = &hid_rmi_ops;
+
 start:
 	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	if (ret) {
@@ -1382,17 +699,6 @@ start:
 		return ret;
 	}
 
-	if ((data->device_flags & RMI_DEVICE) &&
-	    !test_bit(RMI_STARTED, &data->flags))
-		/*
-		 * The device maybe in the bootloader if rmi_input_configured
-		 * failed to find F11 in the PDT. Print an error, but don't
-		 * return an error from rmi_probe so that hidraw will be
-		 * accessible from userspace. That way a userspace tool
-		 * can be used to reload working firmware on the touchpad.
-		 */
-		hid_err(hdev, "Device failed to be properly configured\n");
-
 	return 0;
 }
 
@@ -1401,6 +707,8 @@ static void rmi_remove(struct hid_device *hdev)
 	struct rmi_data *hdata = hid_get_drvdata(hdev);
 
 	clear_bit(RMI_STARTED, &hdata->flags);
+	cancel_work_sync(&hdata->reset_work);
+	rmi_unregister_transport_device(&hdata->xport);
 
 	hid_hw_stop(hdev);
 }
@@ -1408,6 +716,7 @@ static void rmi_remove(struct hid_device *hdev)
 static const struct hid_device_id rmi_id[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_RAZER, USB_DEVICE_ID_RAZER_BLADE_14),
 		.driver_data = RMI_DEVICE_HAS_PHYS_BUTTONS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_COVER) },
 	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_RMI, HID_ANY_ID, HID_ANY_ID) },
 	{ }
 };
@@ -1425,7 +734,7 @@ static struct hid_driver rmi_driver = {
 #ifdef CONFIG_PM
 	.suspend		= rmi_suspend,
 	.resume			= rmi_post_resume,
-	.reset_resume		= rmi_post_reset,
+	.reset_resume		= rmi_post_resume,
 #endif
 };
 
diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish-regs.h b/drivers/hid/intel-ish-hid/ipc/hw-ish-regs.h
index ab68afcba2a2..a5897b9c0956 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish-regs.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish-regs.h
@@ -111,6 +111,14 @@
 #define IPC_ILUP_BIT			(1<<IPC_ILUP_OFFS)
 
 /*
+ * ISH FW status bits in ISH FW Status Register
+ */
+#define IPC_ISH_FWSTS_SHIFT		12
+#define IPC_ISH_FWSTS_MASK		GENMASK(15, 12)
+#define IPC_GET_ISH_FWSTS(status)	\
+	(((status) & IPC_ISH_FWSTS_MASK) >> IPC_ISH_FWSTS_SHIFT)
+
+/*
  * FW status bits (relevant)
  */
 #define	IPC_FWSTS_ILUP		0x1
diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
index 46615a03e78f..fd34307a7a70 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
@@ -61,6 +61,18 @@ struct ish_hw {
 	void __iomem *mem_addr;
 };
 
+/*
+ * ISH FW status type
+ */
+enum {
+	FWSTS_AFTER_RESET		= 0,
+	FWSTS_WAIT_FOR_HOST		= 4,
+	FWSTS_START_KERNEL_DMA		= 5,
+	FWSTS_FW_IS_RUNNING		= 7,
+	FWSTS_SENSOR_APP_LOADED		= 8,
+	FWSTS_SENSOR_APP_RUNNING	= 15
+};
+
 #define to_ish_hw(dev) (struct ish_hw *)((dev)->hw)
 
 irqreturn_t ish_irq_handler(int irq, void *dev_id);
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index 20d647d2dd2c..8df81dc84529 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -24,7 +24,6 @@
 #include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/workqueue.h>
-#include <linux/miscdevice.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/intel_ish.h>
 #include "ishtp-dev.h"
@@ -47,7 +46,8 @@ MODULE_DEVICE_TABLE(pci, ish_pci_tbl);
  *
  * Callback to direct log messages to Linux trace buffers
  */
-static void ish_event_tracer(struct ishtp_device *dev, char *format, ...)
+static __printf(2, 3)
+void ish_event_tracer(struct ishtp_device *dev, const char *format, ...)
 {
 	if (trace_ishtp_dump_enabled()) {
 		va_list args;
@@ -205,12 +205,15 @@ static void ish_remove(struct pci_dev *pdev)
 #ifdef CONFIG_PM
 static struct device *ish_resume_device;
 
+/* 50ms to get resume response */
+#define WAIT_FOR_RESUME_ACK_MS		50
+
 /**
  * ish_resume_handler() - Work function to complete resume
  * @work:	work struct
  *
  * The resume work function to complete resume function asynchronously.
- * There are two types of platforms, one where ISH is not powered off,
+ * There are two resume paths, one where ISH is not powered off,
  * in that case a simple resume message is enough, others we need
  * a reset sequence.
  */
@@ -218,20 +221,31 @@ static void ish_resume_handler(struct work_struct *work)
 {
 	struct pci_dev *pdev = to_pci_dev(ish_resume_device);
 	struct ishtp_device *dev = pci_get_drvdata(pdev);
+	uint32_t fwsts;
 	int ret;
 
-	ishtp_send_resume(dev);
+	/* Get ISH FW status */
+	fwsts = IPC_GET_ISH_FWSTS(dev->ops->get_fw_status(dev));
 
-	/* 50 ms to get resume response */
-	if (dev->resume_flag)
-		ret = wait_event_interruptible_timeout(dev->resume_wait,
-						       !dev->resume_flag,
-						       msecs_to_jiffies(50));
+	/*
+	 * If currently, in ISH FW, sensor app is loaded or beyond that,
+	 * it means ISH isn't powered off, in this case, send a resume message.
+	 */
+	if (fwsts >= FWSTS_SENSOR_APP_LOADED) {
+		ishtp_send_resume(dev);
+
+		/* Waiting to get resume response */
+		if (dev->resume_flag)
+			ret = wait_event_interruptible_timeout(dev->resume_wait,
+				!dev->resume_flag,
+				msecs_to_jiffies(WAIT_FOR_RESUME_ACK_MS));
+	}
 
 	/*
-	 * If no resume response. This platform  is not S0ix compatible
-	 * So on resume full reboot of ISH processor will happen, so
-	 * need to go through init sequence again
+	 * If in ISH FW, sensor app isn't loaded yet, or no resume response.
+	 * That means this platform is not S0ix compatible, or something is
+	 * wrong with ISH FW. So on resume, full reboot of ISH processor will
+	 * happen, so need to go through init sequence again.
 	 */
 	if (dev->resume_flag)
 		ish_init(dev);
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.c b/drivers/hid/intel-ish-hid/ishtp-hid.c
index 277983aa1d90..cd23903ddcf1 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid.c
@@ -208,7 +208,7 @@ int ishtp_hid_probe(unsigned int cur_hid_dev,
 	hid->version = le16_to_cpu(ISH_HID_VERSION);
 	hid->vendor = le16_to_cpu(ISH_HID_VENDOR);
 	hid->product = le16_to_cpu(ISH_HID_PRODUCT);
-	snprintf(hid->name, sizeof(hid->name), "%s %04hX:%04hX", "hid-ishtp",
+	snprintf(hid->name, sizeof(hid->name), "%s %04X:%04X", "hid-ishtp",
 		hid->vendor, hid->product);
 
 	rv = hid_add_device(hid);
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index f4cbc744e657..5f382fedc2ab 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -358,7 +358,7 @@ static void ishtp_cl_dev_release(struct device *dev)
 	kfree(to_ishtp_cl_device(dev));
 }
 
-static struct device_type ishtp_cl_device_type = {
+static const struct device_type ishtp_cl_device_type = {
 	.release	= ishtp_cl_dev_release,
 };
 
diff --git a/drivers/hid/intel-ish-hid/ishtp/hbm.c b/drivers/hid/intel-ish-hid/ishtp/hbm.c
index 59460b66e689..b7213608ce43 100644
--- a/drivers/hid/intel-ish-hid/ishtp/hbm.c
+++ b/drivers/hid/intel-ish-hid/ishtp/hbm.c
@@ -19,7 +19,6 @@
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/spinlock.h>
-#include <linux/miscdevice.h>
 #include "ishtp-dev.h"
 #include "hbm.h"
 #include "client.h"
diff --git a/drivers/hid/intel-ish-hid/ishtp/init.c b/drivers/hid/intel-ish-hid/ishtp/init.c
index ac364418e17c..d27e03526acd 100644
--- a/drivers/hid/intel-ish-hid/ishtp/init.c
+++ b/drivers/hid/intel-ish-hid/ishtp/init.c
@@ -16,7 +16,6 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
-#include <linux/miscdevice.h>
 #include "ishtp-dev.h"
 #include "hbm.h"
 #include "client.h"
diff --git a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
index a94f9a8a96a0..6a6d927b78b0 100644
--- a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
+++ b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h
@@ -238,7 +238,8 @@ struct ishtp_device {
 	uint64_t ishtp_host_dma_rx_buf_phys;
 
 	/* Dump to trace buffers if enabled*/
-	void (*print_log)(struct ishtp_device *dev, char *format, ...);
+	__printf(2, 3) void (*print_log)(struct ishtp_device *dev,
+					 const char *format, ...);
 
 	/* Debug stats */
 	unsigned int	ipc_rx_cnt;
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 333108ef18cf..961bc6fdd2d9 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -43,7 +43,6 @@
  */
 
 #define DRIVER_DESC "USB HID core driver"
-#define DRIVER_LICENSE "GPL"
 
 /*
  * Module parameters.
@@ -1660,4 +1659,4 @@ MODULE_AUTHOR("Andreas Gal");
 MODULE_AUTHOR("Vojtech Pavlik");
 MODULE_AUTHOR("Jiri Kosina");
 MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE(DRIVER_LICENSE);
+MODULE_LICENSE("GPL");
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index e9d6cc7cdfc5..d6847a664446 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -57,6 +57,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_AIREN, USB_DEVICE_ID_AIREN_SLIMPLUS, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_AKAI, USB_DEVICE_ID_AKAI_MPKMINI2, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_AKAI_09E8, USB_DEVICE_ID_AKAI_09E8_MIDIMIX, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_AMI, USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_UC100KM, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_CS124U, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_2PORTKVM, HID_QUIRK_NOGET },
@@ -84,7 +85,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_WIIU, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_PS3, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_DOLPHINBAR, HID_QUIRK_MULTI_INPUT },
-	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_GAMECUBE, HID_QUIRK_MULTI_INPUT },
+	{ USB_VENDOR_ID_DRAGONRISE, USB_DEVICE_ID_DRAGONRISE_GAMECUBE1, HID_QUIRK_MULTI_INPUT },
 	{ USB_VENDOR_ID_ELAN, HID_ANY_ID, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_ELO, USB_DEVICE_ID_ELO_TS2700, HID_QUIRK_NOGET },
 	{ USB_VENDOR_ID_FORMOSA, USB_DEVICE_ID_FORMOSA_IR_RECEIVER, HID_QUIRK_NO_INIT_REPORTS },
@@ -102,12 +103,6 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE_PRO_2, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2, HID_QUIRK_NO_INIT_REPORTS },
-	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_3, HID_QUIRK_NO_INIT_REPORTS },
-	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_3_2, HID_QUIRK_NO_INIT_REPORTS },
-	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_3_JP, HID_QUIRK_NO_INIT_REPORTS },
-	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_4, HID_QUIRK_NO_INIT_REPORTS },
-	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_4_2, HID_QUIRK_NO_INIT_REPORTS },
-	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_PRO_4_JP, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MSI, USB_DEVICE_ID_MSI_GT683R_LED_PANEL, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_NEXIO, USB_DEVICE_ID_NEXIO_MULTITOUCH_PTI0750, HID_QUIRK_NO_INIT_REPORTS },
@@ -296,7 +291,7 @@ static void usbhid_remove_all_dquirks(void)
 
 }
 
-/** 
+/**
  * usbhid_quirks_init: apply USB HID quirks specified at module load time
  */
 int usbhid_quirks_init(char **quirks_param)
@@ -360,7 +355,7 @@ static const struct hid_blacklist *usbhid_exists_squirk(const u16 idVendor,
 
 	if (bl_entry != NULL)
 		dbg_hid("Found squirk 0x%x for USB HID vendor 0x%hx prod 0x%hx\n",
-				bl_entry->quirks, bl_entry->idVendor, 
+				bl_entry->quirks, bl_entry->idVendor,
 				bl_entry->idProduct);
 	return bl_entry;
 }
diff --git a/drivers/hid/usbhid/usbkbd.c b/drivers/hid/usbhid/usbkbd.c
index 9a332e683db7..7fb2d1e4f5dd 100644
--- a/drivers/hid/usbhid/usbkbd.c
+++ b/drivers/hid/usbhid/usbkbd.c
@@ -39,11 +39,10 @@
 #define DRIVER_VERSION ""
 #define DRIVER_AUTHOR "Vojtech Pavlik <vojtech@ucw.cz>"
 #define DRIVER_DESC "USB HID Boot Protocol keyboard driver"
-#define DRIVER_LICENSE "GPL"
 
 MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE(DRIVER_LICENSE);
+MODULE_LICENSE("GPL");
 
 static const unsigned char usb_kbd_keycode[256] = {
 	  0,  0,  0,  0, 30, 48, 46, 32, 18, 33, 34, 35, 23, 36, 37, 38,
diff --git a/drivers/hid/usbhid/usbmouse.c b/drivers/hid/usbhid/usbmouse.c
index bf16d72dc370..dd911c5241d8 100644
--- a/drivers/hid/usbhid/usbmouse.c
+++ b/drivers/hid/usbhid/usbmouse.c
@@ -42,11 +42,10 @@
 #define DRIVER_VERSION "v1.6"
 #define DRIVER_AUTHOR "Vojtech Pavlik <vojtech@ucw.cz>"
 #define DRIVER_DESC "USB HID Boot Protocol mouse driver"
-#define DRIVER_LICENSE "GPL"
 
 MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE(DRIVER_LICENSE);
+MODULE_LICENSE("GPL");
 
 struct usb_mouse {
 	char name[128];
diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h
index d303e413306d..38ee2125412f 100644
--- a/drivers/hid/wacom.h
+++ b/drivers/hid/wacom.h
@@ -102,7 +102,6 @@
 #define DRIVER_VERSION "v2.00"
 #define DRIVER_AUTHOR "Vojtech Pavlik <vojtech@ucw.cz>"
 #define DRIVER_DESC "USB Wacom tablet driver"
-#define DRIVER_LICENSE "GPL"
 
 #define USB_VENDOR_ID_WACOM	0x056a
 #define USB_VENDOR_ID_LENOVO	0x17ef
@@ -166,7 +165,9 @@ struct wacom {
 	struct work_struct wireless_work;
 	struct work_struct battery_work;
 	struct work_struct remote_work;
+	struct delayed_work init_work;
 	struct wacom_remote *remote;
+	bool generic_has_leds;
 	struct wacom_leds {
 		struct wacom_group_leds *groups;
 		unsigned int count;
@@ -218,4 +219,6 @@ enum led_brightness wacom_leds_brightness_get(struct wacom_led *led);
 struct wacom_led *wacom_led_find(struct wacom *wacom, unsigned int group,
 				 unsigned int id);
 struct wacom_led *wacom_led_next(struct wacom *wacom, struct wacom_led *cur);
+int wacom_equivalent_usage(int usage);
+int wacom_initialize_leds(struct wacom *wacom);
 #endif
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 8aeca038cc73..be8f7e2a026f 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -16,15 +16,7 @@
 #include <linux/input/mt.h>
 
 #define WAC_MSG_RETRIES		5
-
-#define WAC_CMD_WL_LED_CONTROL	0x03
-#define WAC_CMD_LED_CONTROL	0x20
-#define WAC_CMD_ICON_START	0x21
-#define WAC_CMD_ICON_XFER	0x23
-#define WAC_CMD_ICON_BT_XFER	0x26
 #define WAC_CMD_RETRIES		10
-#define WAC_CMD_DELETE_PAIRING	0x20
-#define WAC_CMD_UNPAIR_ALL	0xFF
 
 #define DEV_ATTR_RW_PERM (S_IRUGO | S_IWUSR | S_IWGRP)
 #define DEV_ATTR_WO_PERM (S_IWUSR | S_IWGRP)
@@ -120,11 +112,12 @@ static void wacom_feature_mapping(struct hid_device *hdev,
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_features *features = &wacom->wacom_wac.features;
 	struct hid_data *hid_data = &wacom->wacom_wac.hid_data;
+	unsigned int equivalent_usage = wacom_equivalent_usage(usage->hid);
 	u8 *data;
 	int ret;
 	int n;
 
-	switch (usage->hid) {
+	switch (equivalent_usage) {
 	case HID_DG_CONTACTMAX:
 		/* leave touch_max as is if predefined */
 		if (!features->touch_max) {
@@ -333,8 +326,14 @@ static void wacom_post_parse_hid(struct hid_device *hdev,
 	if (features->type == HID_GENERIC) {
 		/* Any last-minute generic device setup */
 		if (features->touch_max > 1) {
-			input_mt_init_slots(wacom_wac->touch_input, wacom_wac->features.touch_max,
-				    INPUT_MT_DIRECT);
+			if (features->device_type & WACOM_DEVICETYPE_DIRECT)
+				input_mt_init_slots(wacom_wac->touch_input,
+						    wacom_wac->features.touch_max,
+						    INPUT_MT_DIRECT);
+			else
+				input_mt_init_slots(wacom_wac->touch_input,
+						    wacom_wac->features.touch_max,
+						    INPUT_MT_POINTER);
 		}
 	}
 }
@@ -497,11 +496,11 @@ static int wacom_bt_query_tablet_data(struct hid_device *hdev, u8 speed,
  * from the tablet, it is necessary to switch the tablet out of this
  * mode and into one which sends the full range of tablet data.
  */
-static int wacom_query_tablet_data(struct hid_device *hdev,
-		struct wacom_features *features)
+static int _wacom_query_tablet_data(struct wacom *wacom)
 {
-	struct wacom *wacom = hid_get_drvdata(hdev);
+	struct hid_device *hdev = wacom->hdev;
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
+	struct wacom_features *features = &wacom_wac->features;
 
 	if (hdev->bus == BUS_BLUETOOTH)
 		return wacom_bt_query_tablet_data(hdev, 1, features);
@@ -757,9 +756,6 @@ static int wacom_led_control(struct wacom *wacom)
 	unsigned char report_id = WAC_CMD_LED_CONTROL;
 	int buf_size = 9;
 
-	if (!hid_get_drvdata(wacom->hdev))
-		return -ENODEV;
-
 	if (!wacom->led.groups)
 		return -ENOTSUPP;
 
@@ -767,12 +763,21 @@ static int wacom_led_control(struct wacom *wacom)
 		report_id = WAC_CMD_WL_LED_CONTROL;
 		buf_size = 13;
 	}
+	else if (wacom->wacom_wac.features.type == INTUOSP2_BT) {
+		report_id = WAC_CMD_WL_INTUOSP2;
+		buf_size = 51;
+	}
 	buf = kzalloc(buf_size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	if (wacom->wacom_wac.features.type >= INTUOS5S &&
-	    wacom->wacom_wac.features.type <= INTUOSPL) {
+	if (wacom->wacom_wac.features.type == HID_GENERIC) {
+		buf[0] = WAC_CMD_LED_CONTROL_GENERIC;
+		buf[1] = wacom->led.llv;
+		buf[2] = wacom->led.groups[0].select & 0x03;
+
+	} else if ((wacom->wacom_wac.features.type >= INTUOS5S &&
+	    wacom->wacom_wac.features.type <= INTUOSPL)) {
 		/*
 		 * Touch Ring and crop mark LED luminance may take on
 		 * one of four values:
@@ -792,6 +797,16 @@ static int wacom_led_control(struct wacom *wacom)
 		} else
 			buf[1] = led_bits;
 	}
+	else if (wacom->wacom_wac.features.type == INTUOSP2_BT) {
+		buf[0] = report_id;
+		buf[4] = 100; // Power Connection LED (ORANGE)
+		buf[5] = 100; // BT Connection LED (BLUE)
+		buf[6] = 100; // Paper Mode (RED?)
+		buf[7] = 100; // Paper Mode (GREEN?)
+		buf[8] = 100; // Paper Mode (BLUE?)
+		buf[9] = wacom->led.llv;
+		buf[10] = wacom->led.groups[0].select & 0x03;
+	}
 	else {
 		int led = wacom->led.groups[0].select | 0x4;
 
@@ -1032,6 +1047,17 @@ static struct attribute_group intuos5_led_attr_group = {
 	.attrs = intuos5_led_attrs,
 };
 
+static struct attribute *generic_led_attrs[] = {
+	&dev_attr_status0_luminance.attr,
+	&dev_attr_status_led0_select.attr,
+	NULL
+};
+
+static struct attribute_group generic_led_attr_group = {
+	.name = "wacom_led",
+	.attrs = generic_led_attrs,
+};
+
 struct wacom_sysfs_group_devres {
 	struct attribute_group *group;
 	struct kobject *root;
@@ -1353,7 +1379,7 @@ static int wacom_leds_alloc_and_register(struct wacom *wacom, int group_count,
 	return 0;
 }
 
-static int wacom_initialize_leds(struct wacom *wacom)
+int wacom_initialize_leds(struct wacom *wacom)
 {
 	int error;
 
@@ -1362,6 +1388,23 @@ static int wacom_initialize_leds(struct wacom *wacom)
 
 	/* Initialize default values */
 	switch (wacom->wacom_wac.features.type) {
+	case HID_GENERIC:
+		if (!wacom->generic_has_leds)
+			return 0;
+		wacom->led.llv = 100;
+		wacom->led.max_llv = 100;
+
+		error = wacom_leds_alloc_and_register(wacom, 1, 4, false);
+		if (error) {
+			hid_err(wacom->hdev,
+				"cannot create leds err: %d\n", error);
+			return error;
+		}
+
+		error = wacom_devm_sysfs_create_group(wacom,
+						      &generic_led_attr_group);
+		break;
+
 	case INTUOS4S:
 	case INTUOS4:
 	case INTUOS4WL:
@@ -1420,6 +1463,17 @@ static int wacom_initialize_leds(struct wacom *wacom)
 						      &intuos5_led_attr_group);
 		break;
 
+	case INTUOSP2_BT:
+		wacom->led.llv = 50;
+		wacom->led.max_llv = 100;
+		error = wacom_leds_alloc_and_register(wacom, 1, 4, false);
+		if (error) {
+			hid_err(wacom->hdev,
+				"cannot create leds err: %d\n", error);
+			return error;
+		}
+		return 0;
+
 	case REMOTE:
 		wacom->led.llv = 255;
 		wacom->led.max_llv = 255;
@@ -1440,11 +1494,23 @@ static int wacom_initialize_leds(struct wacom *wacom)
 			"cannot create sysfs group err: %d\n", error);
 		return error;
 	}
-	wacom_led_control(wacom);
 
 	return 0;
 }
 
+static void wacom_init_work(struct work_struct *work)
+{
+	struct wacom *wacom = container_of(work, struct wacom, init_work.work);
+
+	_wacom_query_tablet_data(wacom);
+	wacom_led_control(wacom);
+}
+
+static void wacom_query_tablet_data(struct wacom *wacom)
+{
+	schedule_delayed_work(&wacom->init_work, msecs_to_jiffies(1000));
+}
+
 static enum power_supply_property wacom_battery_props[] = {
 	POWER_SUPPLY_PROP_MODEL_NAME,
 	POWER_SUPPLY_PROP_PRESENT,
@@ -2020,6 +2086,24 @@ static void wacom_release_resources(struct wacom *wacom)
 	wacom->wacom_wac.pad_input = NULL;
 }
 
+static void wacom_set_shared_values(struct wacom_wac *wacom_wac)
+{
+	if (wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH) {
+		wacom_wac->shared->type = wacom_wac->features.type;
+		wacom_wac->shared->touch_input = wacom_wac->touch_input;
+	}
+
+	if (wacom_wac->has_mute_touch_switch)
+		wacom_wac->shared->has_mute_touch_switch = true;
+
+	if (wacom_wac->shared->has_mute_touch_switch &&
+	    wacom_wac->shared->touch_input) {
+		set_bit(EV_SW, wacom_wac->shared->touch_input->evbit);
+		input_set_capability(wacom_wac->shared->touch_input, EV_SW,
+				     SW_MUTE_DEVICE);
+	}
+}
+
 static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
 {
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
@@ -2118,7 +2202,7 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
 
 	if (!wireless) {
 		/* Note that if query fails it is not a hard failure */
-		wacom_query_tablet_data(hdev, features);
+		wacom_query_tablet_data(wacom);
 	}
 
 	/* touch only Bamboo doesn't support pen */
@@ -2139,13 +2223,7 @@ static int wacom_parse_and_register(struct wacom *wacom, bool wireless)
 	if (features->device_type & WACOM_DEVICETYPE_WL_MONITOR)
 		error = hid_hw_open(hdev);
 
-	if ((wacom_wac->features.type == INTUOSHT ||
-	     wacom_wac->features.type == INTUOSHT2) &&
-	    (wacom_wac->features.device_type & WACOM_DEVICETYPE_TOUCH)) {
-		wacom_wac->shared->type = wacom_wac->features.type;
-		wacom_wac->shared->touch_input = wacom_wac->touch_input;
-	}
-
+	wacom_set_shared_values(wacom_wac);
 	devres_close_group(&hdev->dev, wacom);
 
 	return 0;
@@ -2450,6 +2528,7 @@ static int wacom_probe(struct hid_device *hdev,
 	wacom->usbdev = dev;
 	wacom->intf = intf;
 	mutex_init(&wacom->lock);
+	INIT_DELAYED_WORK(&wacom->init_work, wacom_init_work);
 	INIT_WORK(&wacom->wireless_work, wacom_wireless_work);
 	INIT_WORK(&wacom->battery_work, wacom_battery_work);
 	INIT_WORK(&wacom->remote_work, wacom_remote_work);
@@ -2491,12 +2570,17 @@ static void wacom_remove(struct hid_device *hdev)
 
 	hid_hw_stop(hdev);
 
+	cancel_delayed_work_sync(&wacom->init_work);
 	cancel_work_sync(&wacom->wireless_work);
 	cancel_work_sync(&wacom->battery_work);
 	cancel_work_sync(&wacom->remote_work);
 	if (hdev->bus == BUS_BLUETOOTH)
 		device_remove_file(&hdev->dev, &dev_attr_speed);
 
+	/* make sure we don't trigger the LEDs */
+	wacom_led_groups_release(wacom);
+	wacom_release_resources(wacom);
+
 	hid_set_drvdata(hdev, NULL);
 }
 
@@ -2504,12 +2588,11 @@ static void wacom_remove(struct hid_device *hdev)
 static int wacom_resume(struct hid_device *hdev)
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
-	struct wacom_features *features = &wacom->wacom_wac.features;
 
 	mutex_lock(&wacom->lock);
 
 	/* switch to wacom mode first */
-	wacom_query_tablet_data(hdev, features);
+	_wacom_query_tablet_data(wacom);
 	wacom_led_control(wacom);
 
 	mutex_unlock(&wacom->lock);
@@ -2540,4 +2623,4 @@ module_hid_driver(wacom_driver);
 MODULE_VERSION(DRIVER_VERSION);
 MODULE_AUTHOR(DRIVER_AUTHOR);
 MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE(DRIVER_LICENSE);
+MODULE_LICENSE("GPL");
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 0884dc9554fd..4aa3de9f1163 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -43,6 +43,8 @@ static void wacom_report_numbered_buttons(struct input_dev *input_dev,
 
 static int wacom_numbered_button_to_key(int n);
 
+static void wacom_update_led(struct wacom *wacom, int button_count, int mask,
+			     int group);
 /*
  * Percent of battery capacity for Graphire.
  * 8th value means AC online and show 100% capacity.
@@ -166,19 +168,21 @@ static int wacom_pl_irq(struct wacom_wac *wacom)
 		wacom->id[0] = STYLUS_DEVICE_ID;
 	}
 
-	pressure = (signed char)((data[7] << 1) | ((data[4] >> 2) & 1));
-	if (features->pressure_max > 255)
-		pressure = (pressure << 1) | ((data[4] >> 6) & 1);
-	pressure += (features->pressure_max + 1) / 2;
+	if (prox) {
+		pressure = (signed char)((data[7] << 1) | ((data[4] >> 2) & 1));
+		if (features->pressure_max > 255)
+			pressure = (pressure << 1) | ((data[4] >> 6) & 1);
+		pressure += (features->pressure_max + 1) / 2;
 
-	input_report_abs(input, ABS_X, data[3] | (data[2] << 7) | ((data[1] & 0x03) << 14));
-	input_report_abs(input, ABS_Y, data[6] | (data[5] << 7) | ((data[4] & 0x03) << 14));
-	input_report_abs(input, ABS_PRESSURE, pressure);
+		input_report_abs(input, ABS_X, data[3] | (data[2] << 7) | ((data[1] & 0x03) << 14));
+		input_report_abs(input, ABS_Y, data[6] | (data[5] << 7) | ((data[4] & 0x03) << 14));
+		input_report_abs(input, ABS_PRESSURE, pressure);
 
-	input_report_key(input, BTN_TOUCH, data[4] & 0x08);
-	input_report_key(input, BTN_STYLUS, data[4] & 0x10);
-	/* Only allow the stylus2 button to be reported for the pen tool. */
-	input_report_key(input, BTN_STYLUS2, (wacom->tool[0] == BTN_TOOL_PEN) && (data[4] & 0x20));
+		input_report_key(input, BTN_TOUCH, data[4] & 0x08);
+		input_report_key(input, BTN_STYLUS, data[4] & 0x10);
+		/* Only allow the stylus2 button to be reported for the pen tool. */
+		input_report_key(input, BTN_STYLUS2, (wacom->tool[0] == BTN_TOOL_PEN) && (data[4] & 0x20));
+	}
 
 	if (!prox)
 		wacom->id[0] = 0;
@@ -1190,6 +1194,166 @@ static int wacom_wac_finger_count_touches(struct wacom_wac *wacom)
 	return count;
 }
 
+static void wacom_intuos_pro2_bt_pen(struct wacom_wac *wacom)
+{
+	const int pen_frame_len = 14;
+	const int pen_frames = 7;
+
+	struct input_dev *pen_input = wacom->pen_input;
+	unsigned char *data = wacom->data;
+	int i;
+
+	wacom->serial[0] = get_unaligned_le64(&data[99]);
+	wacom->id[0]     = get_unaligned_le16(&data[107]);
+	if (wacom->serial[0] >> 52 == 1) {
+		/* Add back in missing bits of ID for non-USI pens */
+		wacom->id[0] |= (wacom->serial[0] >> 32) & 0xFFFFF;
+	}
+	wacom->tool[0]   = wacom_intuos_get_tool_type(wacom_intuos_id_mangle(wacom->id[0]));
+
+	for (i = 0; i < pen_frames; i++) {
+		unsigned char *frame = &data[i*pen_frame_len + 1];
+		bool valid = frame[0] & 0x80;
+		bool prox = frame[0] & 0x40;
+		bool range = frame[0] & 0x20;
+
+		if (!valid)
+			continue;
+
+		if (range) {
+			input_report_abs(pen_input, ABS_X, get_unaligned_le16(&frame[1]));
+			input_report_abs(pen_input, ABS_Y, get_unaligned_le16(&frame[3]));
+			input_report_abs(pen_input, ABS_TILT_X, frame[7]);
+			input_report_abs(pen_input, ABS_TILT_Y, frame[8]);
+			input_report_abs(pen_input, ABS_Z, get_unaligned_le16(&frame[9]));
+			input_report_abs(pen_input, ABS_WHEEL, get_unaligned_le16(&frame[11]));
+		}
+		input_report_abs(pen_input, ABS_PRESSURE, get_unaligned_le16(&frame[5]));
+		input_report_abs(pen_input, ABS_DISTANCE, range ? frame[13] : wacom->features.distance_max);
+
+		input_report_key(pen_input, BTN_TOUCH, frame[0] & 0x01);
+		input_report_key(pen_input, BTN_STYLUS, frame[0] & 0x02);
+		input_report_key(pen_input, BTN_STYLUS2, frame[0] & 0x04);
+
+		input_report_key(pen_input, wacom->tool[0], prox);
+		input_event(pen_input, EV_MSC, MSC_SERIAL, wacom->serial[0]);
+		input_report_abs(pen_input, ABS_MISC,
+				 wacom_intuos_id_mangle(wacom->id[0])); /* report tool id */
+
+		wacom->shared->stylus_in_proximity = prox;
+
+		input_sync(pen_input);
+	}
+}
+
+static void wacom_intuos_pro2_bt_touch(struct wacom_wac *wacom)
+{
+	const int finger_touch_len = 8;
+	const int finger_frames = 4;
+	const int finger_frame_len = 43;
+
+	struct input_dev *touch_input = wacom->touch_input;
+	unsigned char *data = wacom->data;
+	int num_contacts_left = 5;
+	int i, j;
+
+	for (i = 0; i < finger_frames; i++) {
+		unsigned char *frame = &data[i*finger_frame_len + 109];
+		int current_num_contacts = frame[0] & 0x7F;
+		int contacts_to_send;
+
+		if (!(frame[0] & 0x80))
+			continue;
+
+		/*
+		 * First packet resets the counter since only the first
+		 * packet in series will have non-zero current_num_contacts.
+		 */
+		if (current_num_contacts)
+			wacom->num_contacts_left = current_num_contacts;
+
+		contacts_to_send = min(num_contacts_left, wacom->num_contacts_left);
+
+		for (j = 0; j < contacts_to_send; j++) {
+			unsigned char *touch = &frame[j*finger_touch_len + 1];
+			int slot = input_mt_get_slot_by_key(touch_input, touch[0]);
+			int x = get_unaligned_le16(&touch[2]);
+			int y = get_unaligned_le16(&touch[4]);
+			int w = touch[6] * input_abs_get_res(touch_input, ABS_MT_POSITION_X);
+			int h = touch[7] * input_abs_get_res(touch_input, ABS_MT_POSITION_Y);
+
+			if (slot < 0)
+				continue;
+
+			input_mt_slot(touch_input, slot);
+			input_mt_report_slot_state(touch_input, MT_TOOL_FINGER, touch[1] & 0x01);
+			input_report_abs(touch_input, ABS_MT_POSITION_X, x);
+			input_report_abs(touch_input, ABS_MT_POSITION_Y, y);
+			input_report_abs(touch_input, ABS_MT_TOUCH_MAJOR, max(w, h));
+			input_report_abs(touch_input, ABS_MT_TOUCH_MINOR, min(w, h));
+			input_report_abs(touch_input, ABS_MT_ORIENTATION, w > h);
+		}
+
+		input_mt_sync_frame(touch_input);
+
+		wacom->num_contacts_left -= contacts_to_send;
+		if (wacom->num_contacts_left <= 0) {
+			wacom->num_contacts_left = 0;
+			wacom->shared->touch_down = wacom_wac_finger_count_touches(wacom);
+		}
+	}
+
+	input_report_switch(touch_input, SW_MUTE_DEVICE, !(data[281] >> 7));
+	input_sync(touch_input);
+}
+
+static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom)
+{
+	struct input_dev *pad_input = wacom->pad_input;
+	unsigned char *data = wacom->data;
+
+	int buttons = (data[282] << 1) | ((data[281] >> 6) & 0x01);
+	int ring = data[285];
+	int prox = buttons | (ring & 0x80);
+
+	wacom_report_numbered_buttons(pad_input, 9, buttons);
+
+	input_report_abs(pad_input, ABS_WHEEL, (ring & 0x80) ? (ring & 0x7f) : 0);
+
+	input_report_key(pad_input, wacom->tool[1], prox ? 1 : 0);
+	input_report_abs(pad_input, ABS_MISC, prox ? PAD_DEVICE_ID : 0);
+	input_event(pad_input, EV_MSC, MSC_SERIAL, 0xffffffff);
+
+	input_sync(pad_input);
+}
+
+static void wacom_intuos_pro2_bt_battery(struct wacom_wac *wacom)
+{
+	unsigned char *data = wacom->data;
+
+	bool chg = data[284] & 0x80;
+	int battery_status = data[284] & 0x7F;
+
+	wacom_notify_battery(wacom, battery_status, chg, 1, chg);
+}
+
+static int wacom_intuos_pro2_bt_irq(struct wacom_wac *wacom, size_t len)
+{
+	unsigned char *data = wacom->data;
+
+	if (data[0] != 0x80) {
+		dev_dbg(wacom->pen_input->dev.parent,
+			"%s: received unknown report #%d\n", __func__, data[0]);
+		return 0;
+	}
+
+	wacom_intuos_pro2_bt_pen(wacom);
+	wacom_intuos_pro2_bt_touch(wacom);
+	wacom_intuos_pro2_bt_pad(wacom);
+	wacom_intuos_pro2_bt_battery(wacom);
+	return 0;
+}
+
 static int wacom_24hdt_irq(struct wacom_wac *wacom)
 {
 	struct input_dev *input = wacom->touch_input;
@@ -1444,7 +1608,7 @@ static int wacom_tpc_irq(struct wacom_wac *wacom, size_t len)
 	return 0;
 }
 
-static int wacom_equivalent_usage(int usage)
+int wacom_equivalent_usage(int usage)
 {
 	if ((usage & HID_USAGE_PAGE) == WACOM_HID_UP_WACOMDIGITIZER) {
 		int subpage = (usage & 0xFF00) << 8;
@@ -1471,6 +1635,16 @@ static int wacom_equivalent_usage(int usage)
 		return subpage | subusage;
 	}
 
+	if ((usage & HID_USAGE_PAGE) == WACOM_HID_UP_WACOMTOUCH) {
+		int subpage = (usage & 0xFF00) << 8;
+		int subusage = (usage & 0xFF);
+
+		if (subpage == HID_UP_UNDEFINED)
+			subpage = WACOM_HID_SP_DIGITIZER;
+
+		return subpage | subusage;
+	}
+
 	return usage;
 }
 
@@ -1550,12 +1724,14 @@ static void wacom_wac_pad_usage_mapping(struct hid_device *hdev,
 		wacom_map_usage(input, usage, field, EV_ABS, ABS_Z, 0);
 		features->device_type |= WACOM_DEVICETYPE_PAD;
 		break;
+	case WACOM_HID_WD_BUTTONCENTER:
+		wacom->generic_has_leds = true;
+		/* fall through */
 	case WACOM_HID_WD_BUTTONHOME:
 	case WACOM_HID_WD_BUTTONUP:
 	case WACOM_HID_WD_BUTTONDOWN:
 	case WACOM_HID_WD_BUTTONLEFT:
 	case WACOM_HID_WD_BUTTONRIGHT:
-	case WACOM_HID_WD_BUTTONCENTER:
 		wacom_map_usage(input, usage, field, EV_KEY,
 				wacom_numbered_button_to_key(features->numbered_buttons),
 				0);
@@ -1563,7 +1739,17 @@ static void wacom_wac_pad_usage_mapping(struct hid_device *hdev,
 		features->device_type |= WACOM_DEVICETYPE_PAD;
 		break;
 	case WACOM_HID_WD_TOUCHONOFF:
-		wacom_map_usage(input, usage, field, EV_SW, SW_MUTE_DEVICE, 0);
+		/*
+		 * This usage, which is used to mute touch events, comes
+		 * from the pad packet, but is reported on the touch
+		 * interface. Because the touch interface may not have
+		 * been created yet, we cannot call wacom_map_usage(). In
+		 * order to process this usage when we receive it, we set
+		 * the usage type and code directly.
+		 */
+		wacom_wac->has_mute_touch_switch = true;
+		usage->type = EV_SW;
+		usage->code = SW_MUTE_DEVICE;
 		features->device_type |= WACOM_DEVICETYPE_PAD;
 		break;
 	case WACOM_HID_WD_TOUCHSTRIP:
@@ -1578,6 +1764,10 @@ static void wacom_wac_pad_usage_mapping(struct hid_device *hdev,
 		wacom_map_usage(input, usage, field, EV_ABS, ABS_WHEEL, 0);
 		features->device_type |= WACOM_DEVICETYPE_PAD;
 		break;
+	case WACOM_HID_WD_TOUCHRINGSTATUS:
+		wacom_map_usage(input, usage, field, EV_ABS, ABS_WHEEL, 0);
+		features->device_type |= WACOM_DEVICETYPE_PAD;
+		break;
 	}
 
 	switch (equivalent_usage & 0xfffffff0) {
@@ -1620,17 +1810,40 @@ static void wacom_wac_pad_event(struct hid_device *hdev, struct hid_field *field
 	struct input_dev *input = wacom_wac->pad_input;
 	struct wacom_features *features = &wacom_wac->features;
 	unsigned equivalent_usage = wacom_equivalent_usage(usage->hid);
+	int i;
+
+	/*
+	 * Avoid reporting this event and setting inrange_state if this usage
+	 * hasn't been mapped.
+	 */
+	if (!usage->type)
+		return;
 
 	if (wacom_equivalent_usage(field->physical) == HID_DG_TABLETFUNCTIONKEY) {
-		wacom_wac->hid_data.inrange_state |= value;
+		if (usage->hid != WACOM_HID_WD_TOUCHRING)
+			wacom_wac->hid_data.inrange_state |= value;
 	}
 
 	switch (equivalent_usage) {
 	case WACOM_HID_WD_TOUCHRINGSTATUS:
+		if (!value)
+			input_event(input, usage->type, usage->code, 0);
+		break;
+
+	case WACOM_HID_WD_TOUCHONOFF:
+		if (wacom_wac->shared->touch_input) {
+			input_report_switch(wacom_wac->shared->touch_input,
+					    SW_MUTE_DEVICE, !value);
+			input_sync(wacom_wac->shared->touch_input);
+		}
 		break;
 
+	case WACOM_HID_WD_BUTTONCENTER:
+		for (i = 0; i < wacom->led.count; i++)
+			wacom_update_led(wacom, features->numbered_buttons,
+					 value, i);
+		 /* fall through*/
 	default:
-		features->input_event_flag = true;
 		input_event(input, usage->type, usage->code, value);
 		break;
 	}
@@ -1668,20 +1881,15 @@ static void wacom_wac_pad_report(struct hid_device *hdev,
 {
 	struct wacom *wacom = hid_get_drvdata(hdev);
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
-	struct wacom_features *features = &wacom_wac->features;
 	struct input_dev *input = wacom_wac->pad_input;
 	bool active = wacom_wac->hid_data.inrange_state != 0;
 
 	/* report prox for expresskey events */
 	if (wacom_equivalent_usage(report->field[0]->physical) == HID_DG_TABLETFUNCTIONKEY) {
-		features->input_event_flag = true;
 		input_event(input, EV_ABS, ABS_MISC, active ? PAD_DEVICE_ID : 0);
-	}
-
-	if (features->input_event_flag) {
-		features->input_event_flag = false;
 		input_sync(input);
 	}
+
 }
 
 static void wacom_wac_pen_usage_mapping(struct hid_device *hdev,
@@ -2056,8 +2264,10 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev,
 
 		for (j = 0; j < field->maxusage; j++) {
 			struct hid_usage *usage = &field->usage[j];
+			unsigned int equivalent_usage =
+				wacom_equivalent_usage(usage->hid);
 
-			switch (usage->hid) {
+			switch (equivalent_usage) {
 			case HID_GD_X:
 			case HID_GD_Y:
 			case HID_DG_WIDTH:
@@ -2066,7 +2276,7 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev,
 			case HID_DG_INRANGE:
 			case HID_DG_INVERT:
 			case HID_DG_TIPSWITCH:
-				hid_data->last_slot_field = usage->hid;
+				hid_data->last_slot_field = equivalent_usage;
 				break;
 			case HID_DG_CONTACTCOUNT:
 				hid_data->cc_report = report->id;
@@ -2121,8 +2331,8 @@ void wacom_wac_usage_mapping(struct hid_device *hdev,
 	struct wacom_wac *wacom_wac = &wacom->wacom_wac;
 	struct wacom_features *features = &wacom_wac->features;
 
-	/* currently, only direct devices have proper hid report descriptors */
-	features->device_type |= WACOM_DEVICETYPE_DIRECT;
+	if (WACOM_DIRECT_DEVICE(field))
+		features->device_type |= WACOM_DEVICETYPE_DIRECT;
 
 	if (WACOM_PAD_FIELD(field))
 		wacom_wac_pad_usage_mapping(hdev, field, usage);
@@ -2140,6 +2350,9 @@ void wacom_wac_event(struct hid_device *hdev, struct hid_field *field,
 	if (wacom->wacom_wac.features.type != HID_GENERIC)
 		return;
 
+	if (value > field->logical_maximum || value < field->logical_minimum)
+		return;
+
 	if (WACOM_PAD_FIELD(field)) {
 		wacom_wac_pad_battery_event(hdev, field, usage, value);
 		if (wacom->wacom_wac.pad_input)
@@ -2667,6 +2880,10 @@ void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len)
 			sync = wacom_intuos_irq(wacom_wac);
 		break;
 
+	case INTUOSP2_BT:
+		sync = wacom_intuos_pro2_bt_irq(wacom_wac, len);
+		break;
+
 	case TABLETPC:
 	case TABLETPCE:
 	case TABLETPC2FG:
@@ -2777,8 +2994,6 @@ void wacom_setup_device_quirks(struct wacom *wacom)
 	struct wacom_features *features = &wacom->wacom_wac.features;
 
 	/* The pen and pad share the same interface on most devices */
-	if (features->numbered_buttons > 0)
-		features->device_type |= WACOM_DEVICETYPE_PAD;
 	if (features->type == GRAPHIRE_BT || features->type == WACOM_G4 ||
 	    features->type == DTUS ||
 	    (features->type >= INTUOS3S && features->type <= WACOM_MO)) {
@@ -2838,6 +3053,13 @@ void wacom_setup_device_quirks(struct wacom *wacom)
 	if (features->type == REMOTE)
 		features->device_type = WACOM_DEVICETYPE_PAD;
 
+	if (features->type == INTUOSP2_BT) {
+		features->device_type |= WACOM_DEVICETYPE_PEN |
+					 WACOM_DEVICETYPE_PAD |
+					 WACOM_DEVICETYPE_TOUCH;
+		features->quirks |= WACOM_QUIRK_BATTERY;
+	}
+
 	switch (features->type) {
 	case PL:
 	case DTU:
@@ -2984,6 +3206,7 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev,
 	case INTUOSPL:
 	case INTUOS5S:
 	case INTUOSPS:
+	case INTUOSP2_BT:
 		input_set_abs_params(input_dev, ABS_DISTANCE, 0,
 				      features->distance_max,
 				      features->distance_fuzz, 0);
@@ -3092,6 +3315,27 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
 	}
 
 	switch (features->type) {
+	case INTUOSP2_BT:
+		input_dev->evbit[0] |= BIT_MASK(EV_SW);
+		__set_bit(SW_MUTE_DEVICE, input_dev->swbit);
+
+		if (wacom_wac->shared->touch->product == 0x361) {
+			input_set_abs_params(input_dev, ABS_MT_POSITION_X,
+					     0, 12440, 4, 0);
+			input_set_abs_params(input_dev, ABS_MT_POSITION_Y,
+					     0, 8640, 4, 0);
+		}
+		else if (wacom_wac->shared->touch->product == 0x360) {
+			input_set_abs_params(input_dev, ABS_MT_POSITION_X,
+					     0, 8960, 4, 0);
+			input_set_abs_params(input_dev, ABS_MT_POSITION_Y,
+					     0, 5920, 4, 0);
+		}
+		input_abs_set_res(input_dev, ABS_MT_POSITION_X, 40);
+		input_abs_set_res(input_dev, ABS_MT_POSITION_X, 40);
+
+		/* fall through */
+
 	case INTUOS5:
 	case INTUOS5L:
 	case INTUOSPM:
@@ -3288,6 +3532,9 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 {
 	struct wacom_features *features = &wacom_wac->features;
 
+	if ((features->type == HID_GENERIC) && features->numbered_buttons > 0)
+		features->device_type |= WACOM_DEVICETYPE_PAD;
+
 	if (!(features->device_type & WACOM_DEVICETYPE_PAD))
 		return -ENODEV;
 
@@ -3389,6 +3636,7 @@ int wacom_setup_pad_input_capabilities(struct input_dev *input_dev,
 	case INTUOSPL:
 	case INTUOS5S:
 	case INTUOSPS:
+	case INTUOSP2_BT:
 		input_set_abs_params(input_dev, ABS_WHEEL, 0, 71, 0, 0);
 		break;
 
@@ -3947,6 +4195,12 @@ static const struct wacom_features wacom_features_0x343 =
 	  DTUS, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 4,
 	  WACOM_DTU_OFFSET, WACOM_DTU_OFFSET,
 	  WACOM_DTU_OFFSET, WACOM_DTU_OFFSET };
+static const struct wacom_features wacom_features_0x360 =
+	{ "Wacom Intuos Pro M", 44800, 29600, 8191, 63,
+	  INTUOSP2_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 9, .touch_max = 10 };
+static const struct wacom_features wacom_features_0x361 =
+	{ "Wacom Intuos Pro L", 62200, 43200, 8191, 63,
+	  INTUOSP2_BT, WACOM_INTUOS_RES, WACOM_INTUOS_RES, 9, .touch_max = 10 };
 
 static const struct wacom_features wacom_features_HID_ANY_ID =
 	{ "Wacom HID", .type = HID_GENERIC, .oVid = HID_ANY_ID, .oPid = HID_ANY_ID };
@@ -4113,6 +4367,8 @@ const struct hid_device_id wacom_ids[] = {
 	{ USB_DEVICE_WACOM(0x33D) },
 	{ USB_DEVICE_WACOM(0x33E) },
 	{ USB_DEVICE_WACOM(0x343) },
+	{ BT_DEVICE_WACOM(0x360) },
+	{ BT_DEVICE_WACOM(0x361) },
 	{ USB_DEVICE_WACOM(0x4001) },
 	{ USB_DEVICE_WACOM(0x4004) },
 	{ USB_DEVICE_WACOM(0x5000) },
@@ -4121,6 +4377,7 @@ const struct hid_device_id wacom_ids[] = {
 
 	{ USB_DEVICE_WACOM(HID_ANY_ID) },
 	{ I2C_DEVICE_WACOM(HID_ANY_ID) },
+	{ BT_DEVICE_WACOM(HID_ANY_ID) },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, wacom_ids);
diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
index fb0e50acb10d..857ccee16f38 100644
--- a/drivers/hid/wacom_wac.h
+++ b/drivers/hid/wacom_wac.h
@@ -12,8 +12,8 @@
 #include <linux/types.h>
 #include <linux/hid.h>
 
-/* maximum packet length for USB devices */
-#define WACOM_PKGLEN_MAX	192
+/* maximum packet length for USB/BT devices */
+#define WACOM_PKGLEN_MAX	361
 
 #define WACOM_NAME_MAX		64
 #define WACOM_MAX_REMOTES	5
@@ -72,6 +72,17 @@
 #define WACOM_REPORT_REMOTE		17
 #define WACOM_REPORT_INTUOSHT2_ID	8
 
+/* wacom command report ids */
+#define WAC_CMD_WL_LED_CONTROL          0x03
+#define WAC_CMD_LED_CONTROL             0x20
+#define WAC_CMD_ICON_START              0x21
+#define WAC_CMD_ICON_XFER               0x23
+#define WAC_CMD_ICON_BT_XFER            0x26
+#define WAC_CMD_DELETE_PAIRING          0x20
+#define WAC_CMD_LED_CONTROL_GENERIC     0x32
+#define WAC_CMD_UNPAIR_ALL              0xFF
+#define WAC_CMD_WL_INTUOSP2             0x82
+
 /* device quirks */
 #define WACOM_QUIRK_BBTOUCH_LOWRES	0x0001
 #define WACOM_QUIRK_SENSE		0x0002
@@ -91,6 +102,7 @@
 #define WACOM_HID_SP_DIGITIZER          0x000d0000
 #define WACOM_HID_SP_DIGITIZERINFO      0x00100000
 #define WACOM_HID_WD_DIGITIZER          (WACOM_HID_UP_WACOMDIGITIZER | 0x01)
+#define WACOM_HID_WD_PEN                (WACOM_HID_UP_WACOMDIGITIZER | 0x02)
 #define WACOM_HID_WD_SENSE              (WACOM_HID_UP_WACOMDIGITIZER | 0x36)
 #define WACOM_HID_WD_DIGITIZERFNKEYS    (WACOM_HID_UP_WACOMDIGITIZER | 0x39)
 #define WACOM_HID_WD_SERIALHI           (WACOM_HID_UP_WACOMDIGITIZER | 0x5c)
@@ -104,6 +116,7 @@
 #define WACOM_HID_WD_ACCELEROMETER_Y    (WACOM_HID_UP_WACOMDIGITIZER | 0x0402)
 #define WACOM_HID_WD_ACCELEROMETER_Z    (WACOM_HID_UP_WACOMDIGITIZER | 0x0403)
 #define WACOM_HID_WD_BATTERY_CHARGING   (WACOM_HID_UP_WACOMDIGITIZER | 0x0404)
+#define WACOM_HID_WD_TOUCHONOFF         (WACOM_HID_UP_WACOMDIGITIZER | 0x0454)
 #define WACOM_HID_WD_BATTERY_LEVEL      (WACOM_HID_UP_WACOMDIGITIZER | 0x043b)
 #define WACOM_HID_WD_EXPRESSKEY00       (WACOM_HID_UP_WACOMDIGITIZER | 0x0910)
 #define WACOM_HID_WD_EXPRESSKEYCAP00    (WACOM_HID_UP_WACOMDIGITIZER | 0x0950)
@@ -113,7 +126,6 @@
 #define WACOM_HID_WD_BUTTONLEFT         (WACOM_HID_UP_WACOMDIGITIZER | 0x0993)
 #define WACOM_HID_WD_BUTTONRIGHT        (WACOM_HID_UP_WACOMDIGITIZER | 0x0994)
 #define WACOM_HID_WD_BUTTONCENTER       (WACOM_HID_UP_WACOMDIGITIZER | 0x0995)
-#define WACOM_HID_WD_TOUCHONOFF         (WACOM_HID_UP_WACOMDIGITIZER | 0x0996)
 #define WACOM_HID_WD_FINGERWHEEL        (WACOM_HID_UP_WACOMDIGITIZER | 0x0d03)
 #define WACOM_HID_WD_OFFSETLEFT         (WACOM_HID_UP_WACOMDIGITIZER | 0x0d30)
 #define WACOM_HID_WD_OFFSETTOP          (WACOM_HID_UP_WACOMDIGITIZER | 0x0d31)
@@ -127,6 +139,12 @@
 #define WACOM_HID_UP_G11                0xff110000
 #define WACOM_HID_G11_PEN               (WACOM_HID_UP_G11 | 0x02)
 #define WACOM_HID_G11_TOUCHSCREEN       (WACOM_HID_UP_G11 | 0x11)
+#define WACOM_HID_UP_WACOMTOUCH         0xff000000
+#define WACOM_HID_WT_TOUCHSCREEN        (WACOM_HID_UP_WACOMTOUCH | 0x04)
+#define WACOM_HID_WT_TOUCHPAD           (WACOM_HID_UP_WACOMTOUCH | 0x05)
+#define WACOM_HID_WT_CONTACTMAX         (WACOM_HID_UP_WACOMTOUCH | 0x55)
+#define WACOM_HID_WT_X                  (WACOM_HID_UP_WACOMTOUCH | 0x130)
+#define WACOM_HID_WT_Y                  (WACOM_HID_UP_WACOMTOUCH | 0x131)
 
 #define WACOM_PAD_FIELD(f)	(((f)->physical == HID_DG_TABLETFUNCTIONKEY) || \
 				 ((f)->physical == WACOM_HID_WD_DIGITIZERFNKEYS) || \
@@ -144,7 +162,14 @@
 				 ((f)->physical == HID_DG_FINGER) || \
 				 ((f)->application == HID_DG_TOUCHSCREEN) || \
 				 ((f)->application == WACOM_HID_G9_TOUCHSCREEN) || \
-				 ((f)->application == WACOM_HID_G11_TOUCHSCREEN))
+				 ((f)->application == WACOM_HID_G11_TOUCHSCREEN) || \
+				 ((f)->application == WACOM_HID_WT_TOUCHPAD) || \
+				 ((f)->application == HID_DG_TOUCHPAD))
+
+#define WACOM_DIRECT_DEVICE(f)	(((f)->application == HID_DG_TOUCHSCREEN) || \
+				 ((f)->application == WACOM_HID_WT_TOUCHSCREEN) || \
+				 ((f)->application == HID_DG_PEN) || \
+				 ((f)->application == WACOM_HID_WD_PEN))
 
 enum {
 	PENPARTNER = 0,
@@ -170,6 +195,7 @@ enum {
 	INTUOSPS,
 	INTUOSPM,
 	INTUOSPL,
+	INTUOSP2_BT,
 	WACOM_21UX2,
 	WACOM_22HD,
 	DTK,
@@ -232,7 +258,6 @@ struct wacom_features {
 	int pktlen;
 	bool check_for_hid_type;
 	int hid_type;
-	bool input_event_flag;
 };
 
 struct wacom_shared {
@@ -244,6 +269,7 @@ struct wacom_shared {
 	struct input_dev *touch_input;
 	struct hid_device *pen;
 	struct hid_device *touch;
+	bool has_mute_touch_switch;
 };
 
 struct hid_data {
@@ -300,6 +326,7 @@ struct wacom_wac {
 	int mode_report;
 	int mode_value;
 	struct hid_data hid_data;
+	bool has_mute_touch_switch;
 };
 
 #endif
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index cd49cb17eb7f..308dbda700eb 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -383,6 +383,7 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 		return ret;
 	}
 
+	init_cached_read_index(channel);
 	next_read_location = hv_get_next_read_location(inring_info);
 	next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc,
 						    sizeof(desc),
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 190d270b20a2..0649d53f3d16 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1459,6 +1459,16 @@ config SENSORS_SCH5636
 	  This driver can also be built as a module.  If so, the module
 	  will be called sch5636.
 
+config SENSORS_STTS751
+	tristate "ST Microelectronics STTS751"
+	depends on I2C
+	help
+	  If you say yes here you get support for STTS751
+	  temperature sensor chips.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called stts751.
+
 config SENSORS_SMM665
 	tristate "Summit Microelectronics SMM665"
 	depends on I2C
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index d2cb7e804a0f..5509edf6186a 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -148,6 +148,7 @@ obj-$(CONFIG_SENSORS_SMM665)	+= smm665.o
 obj-$(CONFIG_SENSORS_SMSC47B397)+= smsc47b397.o
 obj-$(CONFIG_SENSORS_SMSC47M1)	+= smsc47m1.o
 obj-$(CONFIG_SENSORS_SMSC47M192)+= smsc47m192.o
+obj-$(CONFIG_SENSORS_STTS751)	+= stts751.o
 obj-$(CONFIG_SENSORS_AMC6821)	+= amc6821.o
 obj-$(CONFIG_SENSORS_TC74)	+= tc74.o
 obj-$(CONFIG_SENSORS_THMC50)	+= thmc50.o
diff --git a/drivers/hwmon/adc128d818.c b/drivers/hwmon/adc128d818.c
index ad2b47e40345..bbe3a5c5b3f5 100644
--- a/drivers/hwmon/adc128d818.c
+++ b/drivers/hwmon/adc128d818.c
@@ -28,6 +28,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/mutex.h>
 #include <linux/bitops.h>
+#include <linux/of.h>
 
 /* Addresses to scan
  * The chip also supports addresses 0x35..0x37. Don't scan those addresses
@@ -58,15 +59,22 @@ static const unsigned short normal_i2c[] = {
 #define ADC128_REG_MAN_ID		0x3e
 #define ADC128_REG_DEV_ID		0x3f
 
+/* No. of voltage entries in adc128_attrs */
+#define ADC128_ATTR_NUM_VOLT		(8 * 4)
+
+/* Voltage inputs visible per operation mode */
+static const u8 num_inputs[] = { 7, 8, 4, 6 };
+
 struct adc128_data {
 	struct i2c_client *client;
 	struct regulator *regulator;
 	int vref;		/* Reference voltage in mV */
 	struct mutex update_lock;
+	u8 mode;		/* Operation mode */
 	bool valid;		/* true if following fields are valid */
 	unsigned long last_updated;	/* In jiffies */
 
-	u16 in[3][7];		/* Register value, normalized to 12 bit
+	u16 in[3][8];		/* Register value, normalized to 12 bit
 				 * 0: input voltage
 				 * 1: min limit
 				 * 2: max limit
@@ -87,7 +95,7 @@ static struct adc128_data *adc128_update_device(struct device *dev)
 	mutex_lock(&data->update_lock);
 
 	if (time_after(jiffies, data->last_updated + HZ) || !data->valid) {
-		for (i = 0; i < 7; i++) {
+		for (i = 0; i < num_inputs[data->mode]; i++) {
 			rv = i2c_smbus_read_word_swapped(client,
 							 ADC128_REG_IN(i));
 			if (rv < 0)
@@ -107,20 +115,25 @@ static struct adc128_data *adc128_update_device(struct device *dev)
 			data->in[2][i] = rv << 4;
 		}
 
-		rv = i2c_smbus_read_word_swapped(client, ADC128_REG_TEMP);
-		if (rv < 0)
-			goto abort;
-		data->temp[0] = rv >> 7;
+		if (data->mode != 1) {
+			rv = i2c_smbus_read_word_swapped(client,
+							 ADC128_REG_TEMP);
+			if (rv < 0)
+				goto abort;
+			data->temp[0] = rv >> 7;
 
-		rv = i2c_smbus_read_byte_data(client, ADC128_REG_TEMP_MAX);
-		if (rv < 0)
-			goto abort;
-		data->temp[1] = rv << 1;
+			rv = i2c_smbus_read_byte_data(client,
+						      ADC128_REG_TEMP_MAX);
+			if (rv < 0)
+				goto abort;
+			data->temp[1] = rv << 1;
 
-		rv = i2c_smbus_read_byte_data(client, ADC128_REG_TEMP_HYST);
-		if (rv < 0)
-			goto abort;
-		data->temp[2] = rv << 1;
+			rv = i2c_smbus_read_byte_data(client,
+						      ADC128_REG_TEMP_HYST);
+			if (rv < 0)
+				goto abort;
+			data->temp[2] = rv << 1;
+		}
 
 		rv = i2c_smbus_read_byte_data(client, ADC128_REG_ALARM);
 		if (rv < 0)
@@ -240,6 +253,25 @@ static ssize_t adc128_show_alarm(struct device *dev,
 	return sprintf(buf, "%u\n", !!(alarms & mask));
 }
 
+static umode_t adc128_is_visible(struct kobject *kobj,
+				 struct attribute *attr, int index)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct adc128_data *data = dev_get_drvdata(dev);
+
+	if (index < ADC128_ATTR_NUM_VOLT) {
+		/* Voltage, visible according to num_inputs[] */
+		if (index >= num_inputs[data->mode] * 4)
+			return 0;
+	} else {
+		/* Temperature, visible if not in mode 1 */
+		if (data->mode == 1)
+			return 0;
+	}
+
+	return attr->mode;
+}
+
 static SENSOR_DEVICE_ATTR_2(in0_input, S_IRUGO,
 			    adc128_show_in, NULL, 0, 0);
 static SENSOR_DEVICE_ATTR_2(in0_min, S_IWUSR | S_IRUGO,
@@ -289,6 +321,13 @@ static SENSOR_DEVICE_ATTR_2(in6_min, S_IWUSR | S_IRUGO,
 static SENSOR_DEVICE_ATTR_2(in6_max, S_IWUSR | S_IRUGO,
 			    adc128_show_in, adc128_set_in, 6, 2);
 
+static SENSOR_DEVICE_ATTR_2(in7_input, S_IRUGO,
+			    adc128_show_in, NULL, 7, 0);
+static SENSOR_DEVICE_ATTR_2(in7_min, S_IWUSR | S_IRUGO,
+			    adc128_show_in, adc128_set_in, 7, 1);
+static SENSOR_DEVICE_ATTR_2(in7_max, S_IWUSR | S_IRUGO,
+			    adc128_show_in, adc128_set_in, 7, 2);
+
 static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, adc128_show_temp, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO,
 			  adc128_show_temp, adc128_set_temp, 1);
@@ -302,44 +341,54 @@ static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, adc128_show_alarm, NULL, 3);
 static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, adc128_show_alarm, NULL, 4);
 static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, adc128_show_alarm, NULL, 5);
 static SENSOR_DEVICE_ATTR(in6_alarm, S_IRUGO, adc128_show_alarm, NULL, 6);
+static SENSOR_DEVICE_ATTR(in7_alarm, S_IRUGO, adc128_show_alarm, NULL, 7);
 static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, adc128_show_alarm, NULL, 7);
 
 static struct attribute *adc128_attrs[] = {
-	&sensor_dev_attr_in0_min.dev_attr.attr,
-	&sensor_dev_attr_in1_min.dev_attr.attr,
-	&sensor_dev_attr_in2_min.dev_attr.attr,
-	&sensor_dev_attr_in3_min.dev_attr.attr,
-	&sensor_dev_attr_in4_min.dev_attr.attr,
-	&sensor_dev_attr_in5_min.dev_attr.attr,
-	&sensor_dev_attr_in6_min.dev_attr.attr,
-	&sensor_dev_attr_in0_max.dev_attr.attr,
-	&sensor_dev_attr_in1_max.dev_attr.attr,
-	&sensor_dev_attr_in2_max.dev_attr.attr,
-	&sensor_dev_attr_in3_max.dev_attr.attr,
-	&sensor_dev_attr_in4_max.dev_attr.attr,
-	&sensor_dev_attr_in5_max.dev_attr.attr,
-	&sensor_dev_attr_in6_max.dev_attr.attr,
+	&sensor_dev_attr_in0_alarm.dev_attr.attr,
 	&sensor_dev_attr_in0_input.dev_attr.attr,
+	&sensor_dev_attr_in0_max.dev_attr.attr,
+	&sensor_dev_attr_in0_min.dev_attr.attr,
+	&sensor_dev_attr_in1_alarm.dev_attr.attr,
 	&sensor_dev_attr_in1_input.dev_attr.attr,
+	&sensor_dev_attr_in1_max.dev_attr.attr,
+	&sensor_dev_attr_in1_min.dev_attr.attr,
+	&sensor_dev_attr_in2_alarm.dev_attr.attr,
 	&sensor_dev_attr_in2_input.dev_attr.attr,
+	&sensor_dev_attr_in2_max.dev_attr.attr,
+	&sensor_dev_attr_in2_min.dev_attr.attr,
+	&sensor_dev_attr_in3_alarm.dev_attr.attr,
 	&sensor_dev_attr_in3_input.dev_attr.attr,
+	&sensor_dev_attr_in3_max.dev_attr.attr,
+	&sensor_dev_attr_in3_min.dev_attr.attr,
+	&sensor_dev_attr_in4_alarm.dev_attr.attr,
 	&sensor_dev_attr_in4_input.dev_attr.attr,
+	&sensor_dev_attr_in4_max.dev_attr.attr,
+	&sensor_dev_attr_in4_min.dev_attr.attr,
+	&sensor_dev_attr_in5_alarm.dev_attr.attr,
 	&sensor_dev_attr_in5_input.dev_attr.attr,
+	&sensor_dev_attr_in5_max.dev_attr.attr,
+	&sensor_dev_attr_in5_min.dev_attr.attr,
+	&sensor_dev_attr_in6_alarm.dev_attr.attr,
 	&sensor_dev_attr_in6_input.dev_attr.attr,
+	&sensor_dev_attr_in6_max.dev_attr.attr,
+	&sensor_dev_attr_in6_min.dev_attr.attr,
+	&sensor_dev_attr_in7_alarm.dev_attr.attr,
+	&sensor_dev_attr_in7_input.dev_attr.attr,
+	&sensor_dev_attr_in7_max.dev_attr.attr,
+	&sensor_dev_attr_in7_min.dev_attr.attr,
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
 	&sensor_dev_attr_temp1_max.dev_attr.attr,
-	&sensor_dev_attr_temp1_max_hyst.dev_attr.attr,
-	&sensor_dev_attr_in0_alarm.dev_attr.attr,
-	&sensor_dev_attr_in1_alarm.dev_attr.attr,
-	&sensor_dev_attr_in2_alarm.dev_attr.attr,
-	&sensor_dev_attr_in3_alarm.dev_attr.attr,
-	&sensor_dev_attr_in4_alarm.dev_attr.attr,
-	&sensor_dev_attr_in5_alarm.dev_attr.attr,
-	&sensor_dev_attr_in6_alarm.dev_attr.attr,
 	&sensor_dev_attr_temp1_max_alarm.dev_attr.attr,
+	&sensor_dev_attr_temp1_max_hyst.dev_attr.attr,
 	NULL
 };
-ATTRIBUTE_GROUPS(adc128);
+
+static struct attribute_group adc128_group = {
+	.attrs = adc128_attrs,
+	.is_visible = adc128_is_visible,
+};
+__ATTRIBUTE_GROUPS(adc128);
 
 static int adc128_detect(struct i2c_client *client, struct i2c_board_info *info)
 {
@@ -387,6 +436,15 @@ static int adc128_init_client(struct adc128_data *data)
 	if (err)
 		return err;
 
+	/* Set operation mode, if non-default */
+	if (data->mode != 0) {
+		err = i2c_smbus_write_byte_data(client,
+						ADC128_REG_CONFIG_ADV,
+						data->mode << 1);
+		if (err)
+			return err;
+	}
+
 	/* Start monitoring */
 	err = i2c_smbus_write_byte_data(client, ADC128_REG_CONFIG, 0x01);
 	if (err)
@@ -433,6 +491,21 @@ static int adc128_probe(struct i2c_client *client,
 		data->vref = 2560;	/* 2.56V, in mV */
 	}
 
+	/* Operation mode is optional. If unspecified, keep current mode */
+	if (of_property_read_u8(dev->of_node, "ti,mode", &data->mode) == 0) {
+		if (data->mode > 3) {
+			dev_err(dev, "invalid operation mode %d\n",
+				data->mode);
+			err = -EINVAL;
+			goto error;
+		}
+	} else {
+		err = i2c_smbus_read_byte_data(client, ADC128_REG_CONFIG_ADV);
+		if (err < 0)
+			goto error;
+		data->mode = (err >> 1) & ADC128_REG_MASK;
+	}
+
 	data->client = client;
 	i2c_set_clientdata(client, data);
 	mutex_init(&data->update_lock);
diff --git a/drivers/hwmon/adm1021.c b/drivers/hwmon/adm1021.c
index 1fdcc3e703b9..eacf10fadbc6 100644
--- a/drivers/hwmon/adm1021.c
+++ b/drivers/hwmon/adm1021.c
@@ -191,7 +191,7 @@ static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%u\n", (data->alarms >> index) & 1);
 }
 
-static ssize_t show_alarms(struct device *dev,
+static ssize_t alarms_show(struct device *dev,
 			   struct device_attribute *attr,
 			   char *buf)
 {
@@ -251,16 +251,16 @@ static ssize_t set_temp_min(struct device *dev,
 	return count;
 }
 
-static ssize_t show_low_power(struct device *dev,
+static ssize_t low_power_show(struct device *dev,
 			      struct device_attribute *devattr, char *buf)
 {
 	struct adm1021_data *data = adm1021_update_device(dev);
 	return sprintf(buf, "%d\n", data->low_power);
 }
 
-static ssize_t set_low_power(struct device *dev,
-			     struct device_attribute *devattr,
-			     const char *buf, size_t count)
+static ssize_t low_power_store(struct device *dev,
+			       struct device_attribute *devattr,
+			       const char *buf, size_t count)
 {
 	struct adm1021_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -303,8 +303,8 @@ static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 4);
 static SENSOR_DEVICE_ATTR(temp2_min_alarm, S_IRUGO, show_alarm, NULL, 3);
 static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 2);
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
-static DEVICE_ATTR(low_power, S_IWUSR | S_IRUGO, show_low_power, set_low_power);
+static DEVICE_ATTR_RO(alarms);
+static DEVICE_ATTR_RW(low_power);
 
 static struct attribute *adm1021_attributes[] = {
 	&sensor_dev_attr_temp1_max.dev_attr.attr,
diff --git a/drivers/hwmon/adm1025.c b/drivers/hwmon/adm1025.c
index 1abb4609b412..1e4dad36f5ef 100644
--- a/drivers/hwmon/adm1025.c
+++ b/drivers/hwmon/adm1025.c
@@ -333,12 +333,12 @@ set_temp(1);
 set_temp(2);
 
 static ssize_t
-show_alarms(struct device *dev, struct device_attribute *attr, char *buf)
+alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct adm1025_data *data = adm1025_update_device(dev);
 	return sprintf(buf, "%u\n", data->alarms);
 }
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t
 show_alarm(struct device *dev, struct device_attribute *attr, char *buf)
@@ -358,21 +358,21 @@ static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 4);
 static SENSOR_DEVICE_ATTR(temp1_fault, S_IRUGO, show_alarm, NULL, 14);
 
 static ssize_t
-show_vid(struct device *dev, struct device_attribute *attr, char *buf)
+cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct adm1025_data *data = adm1025_update_device(dev);
 	return sprintf(buf, "%u\n", vid_from_reg(data->vid, data->vrm));
 }
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 static ssize_t
-show_vrm(struct device *dev, struct device_attribute *attr, char *buf)
+vrm_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct adm1025_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%u\n", data->vrm);
 }
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
-		       const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct adm1025_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -388,7 +388,7 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 	data->vrm = val;
 	return count;
 }
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
+static DEVICE_ATTR_RW(vrm);
 
 /*
  * Real code
diff --git a/drivers/hwmon/adm1026.c b/drivers/hwmon/adm1026.c
index b2a5d9e5c590..e43f09a07cd0 100644
--- a/drivers/hwmon/adm1026.c
+++ b/drivers/hwmon/adm1026.c
@@ -1034,15 +1034,15 @@ temp_crit_reg(1);
 temp_crit_reg(2);
 temp_crit_reg(3);
 
-static ssize_t show_analog_out_reg(struct device *dev,
-				   struct device_attribute *attr, char *buf)
+static ssize_t analog_out_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", DAC_FROM_REG(data->analog_out));
 }
-static ssize_t set_analog_out_reg(struct device *dev,
-				  struct device_attribute *attr,
-				  const char *buf, size_t count)
+static ssize_t analog_out_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -1060,11 +1060,10 @@ static ssize_t set_analog_out_reg(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(analog_out, S_IRUGO | S_IWUSR, show_analog_out_reg,
-	set_analog_out_reg);
+static DEVICE_ATTR_RW(analog_out);
 
-static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr,
-			    char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	int vid = (data->gpio >> 11) & 0x1f;
@@ -1073,17 +1072,17 @@ static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", vid_from_reg(vid, data->vrm));
 }
 
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
-static ssize_t show_vrm_reg(struct device *dev, struct device_attribute *attr,
-			    char *buf)
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", data->vrm);
 }
 
-static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -1100,16 +1099,16 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
 
-static ssize_t show_alarms_reg(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%ld\n", data->alarms);
 }
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 			  char *buf)
@@ -1148,14 +1147,15 @@ static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 24);
 static SENSOR_DEVICE_ATTR(in10_alarm, S_IRUGO, show_alarm, NULL, 25);
 static SENSOR_DEVICE_ATTR(in8_alarm, S_IRUGO, show_alarm, NULL, 26);
 
-static ssize_t show_alarm_mask(struct device *dev,
+static ssize_t alarm_mask_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%ld\n", data->alarm_mask);
 }
-static ssize_t set_alarm_mask(struct device *dev, struct device_attribute *attr,
-			      const char *buf, size_t count)
+static ssize_t alarm_mask_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -1186,18 +1186,17 @@ static ssize_t set_alarm_mask(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(alarm_mask, S_IRUGO | S_IWUSR, show_alarm_mask,
-	set_alarm_mask);
+static DEVICE_ATTR_RW(alarm_mask);
 
 
-static ssize_t show_gpio(struct device *dev, struct device_attribute *attr,
+static ssize_t gpio_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%ld\n", data->gpio);
 }
-static ssize_t set_gpio(struct device *dev, struct device_attribute *attr,
-			const char *buf, size_t count)
+static ssize_t gpio_store(struct device *dev, struct device_attribute *attr,
+			  const char *buf, size_t count)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -1221,16 +1220,18 @@ static ssize_t set_gpio(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(gpio, S_IRUGO | S_IWUSR, show_gpio, set_gpio);
+static DEVICE_ATTR_RW(gpio);
 
-static ssize_t show_gpio_mask(struct device *dev, struct device_attribute *attr,
+static ssize_t gpio_mask_show(struct device *dev,
+			      struct device_attribute *attr,
 			      char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%ld\n", data->gpio_mask);
 }
-static ssize_t set_gpio_mask(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
+static ssize_t gpio_mask_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t count)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -1254,17 +1255,17 @@ static ssize_t set_gpio_mask(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(gpio_mask, S_IRUGO | S_IWUSR, show_gpio_mask, set_gpio_mask);
+static DEVICE_ATTR_RW(gpio_mask);
 
-static ssize_t show_pwm_reg(struct device *dev, struct device_attribute *attr,
-			    char *buf)
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", PWM_FROM_REG(data->pwm1.pwm));
 }
 
-static ssize_t set_pwm_reg(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr,
+			  const char *buf, size_t count)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -1285,16 +1286,17 @@ static ssize_t set_pwm_reg(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_auto_pwm_min(struct device *dev,
-				 struct device_attribute *attr, char *buf)
+static ssize_t temp1_auto_point1_pwm_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", data->pwm1.auto_pwm_min);
 }
 
-static ssize_t set_auto_pwm_min(struct device *dev,
-				struct device_attribute *attr, const char *buf,
-				size_t count)
+static ssize_t temp1_auto_point1_pwm_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t count)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -1316,21 +1318,23 @@ static ssize_t set_auto_pwm_min(struct device *dev,
 	return count;
 }
 
-static ssize_t show_auto_pwm_max(struct device *dev,
-				 struct device_attribute *attr, char *buf)
+static ssize_t temp1_auto_point2_pwm_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
 {
 	return sprintf(buf, "%d\n", ADM1026_PWM_MAX);
 }
 
-static ssize_t show_pwm_enable(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t pwm1_enable_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", data->pwm1.enable);
 }
 
-static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr,
-			      const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -1366,25 +1370,25 @@ static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr,
 }
 
 /* enable PWM fan control */
-static DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm_reg, set_pwm_reg);
-static DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, show_pwm_reg, set_pwm_reg);
-static DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, show_pwm_reg, set_pwm_reg);
-static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, show_pwm_enable,
-	set_pwm_enable);
-static DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR, show_pwm_enable,
-	set_pwm_enable);
-static DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR, show_pwm_enable,
-	set_pwm_enable);
-static DEVICE_ATTR(temp1_auto_point1_pwm, S_IRUGO | S_IWUSR,
-	show_auto_pwm_min, set_auto_pwm_min);
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, pwm1_show, pwm1_store);
+static DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, pwm1_show, pwm1_store);
+static DEVICE_ATTR_RW(pwm1_enable);
+static DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR, pwm1_enable_show,
+		   pwm1_enable_store);
+static DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR, pwm1_enable_show,
+		   pwm1_enable_store);
+static DEVICE_ATTR_RW(temp1_auto_point1_pwm);
 static DEVICE_ATTR(temp2_auto_point1_pwm, S_IRUGO | S_IWUSR,
-	show_auto_pwm_min, set_auto_pwm_min);
+	temp1_auto_point1_pwm_show, temp1_auto_point1_pwm_store);
 static DEVICE_ATTR(temp3_auto_point1_pwm, S_IRUGO | S_IWUSR,
-	show_auto_pwm_min, set_auto_pwm_min);
+	temp1_auto_point1_pwm_show, temp1_auto_point1_pwm_store);
 
-static DEVICE_ATTR(temp1_auto_point2_pwm, S_IRUGO, show_auto_pwm_max, NULL);
-static DEVICE_ATTR(temp2_auto_point2_pwm, S_IRUGO, show_auto_pwm_max, NULL);
-static DEVICE_ATTR(temp3_auto_point2_pwm, S_IRUGO, show_auto_pwm_max, NULL);
+static DEVICE_ATTR_RO(temp1_auto_point2_pwm);
+static DEVICE_ATTR(temp2_auto_point2_pwm, S_IRUGO, temp1_auto_point2_pwm_show,
+		   NULL);
+static DEVICE_ATTR(temp3_auto_point2_pwm, S_IRUGO, temp1_auto_point2_pwm_show,
+		   NULL);
 
 static struct attribute *adm1026_attributes[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/adm1031.c b/drivers/hwmon/adm1031.c
index a5818980dad7..bcf508269fd6 100644
--- a/drivers/hwmon/adm1031.c
+++ b/drivers/hwmon/adm1031.c
@@ -829,14 +829,14 @@ temp_reg(2);
 temp_reg(3);
 
 /* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct adm1031_data *data = adm1031_update_device(dev);
 	return sprintf(buf, "%d\n", data->alarm);
 }
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev,
 			  struct device_attribute *attr, char *buf)
@@ -867,7 +867,7 @@ static const unsigned int update_intervals[] = {
 	16000, 8000, 4000, 2000, 1000, 500, 250, 125,
 };
 
-static ssize_t show_update_interval(struct device *dev,
+static ssize_t update_interval_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
@@ -875,9 +875,9 @@ static ssize_t show_update_interval(struct device *dev,
 	return sprintf(buf, "%u\n", data->update_interval);
 }
 
-static ssize_t set_update_interval(struct device *dev,
-				   struct device_attribute *attr,
-				   const char *buf, size_t count)
+static ssize_t update_interval_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -912,8 +912,7 @@ static ssize_t set_update_interval(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, show_update_interval,
-		   set_update_interval);
+static DEVICE_ATTR_RW(update_interval);
 
 static struct attribute *adm1031_attributes[] = {
 	&sensor_dev_attr_fan1_input.dev_attr.attr,
diff --git a/drivers/hwmon/adm9240.c b/drivers/hwmon/adm9240.c
index 72bf2489511e..255413fdbde9 100644
--- a/drivers/hwmon/adm9240.c
+++ b/drivers/hwmon/adm9240.c
@@ -262,8 +262,8 @@ static struct adm9240_data *adm9240_update_device(struct device *dev)
 /*** sysfs accessors ***/
 
 /* temperature */
-static ssize_t show_temp(struct device *dev, struct device_attribute *dummy,
-		char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *dummy, char *buf)
 {
 	struct adm9240_data *data = adm9240_update_device(dev);
 	return sprintf(buf, "%d\n", data->temp / 128 * 500); /* 9-bit value */
@@ -298,7 +298,7 @@ static ssize_t set_max(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
+static DEVICE_ATTR_RO(temp1_input);
 static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO,
 		show_max, set_max, 0);
 static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IWUSR | S_IRUGO,
@@ -501,13 +501,13 @@ fan(1);
 fan(2);
 
 /* alarms */
-static ssize_t show_alarms(struct device *dev,
+static ssize_t alarms_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct adm9240_data *data = adm9240_update_device(dev);
 	return sprintf(buf, "%u\n", data->alarms);
 }
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -527,25 +527,25 @@ static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
 static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
 
 /* vid */
-static ssize_t show_vid(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct adm9240_data *data = adm9240_update_device(dev);
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 /* analog output */
-static ssize_t show_aout(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t aout_output_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct adm9240_data *data = adm9240_update_device(dev);
 	return sprintf(buf, "%d\n", AOUT_FROM_REG(data->aout));
 }
 
-static ssize_t set_aout(struct device *dev,
-		struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t aout_output_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct adm9240_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -562,7 +562,7 @@ static ssize_t set_aout(struct device *dev,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static DEVICE_ATTR(aout_output, S_IRUGO | S_IWUSR, show_aout, set_aout);
+static DEVICE_ATTR_RW(aout_output);
 
 static ssize_t chassis_clear(struct device *dev,
 		struct device_attribute *attr,
diff --git a/drivers/hwmon/adt7411.c b/drivers/hwmon/adt7411.c
index bdeaece9641d..b939f8a115ba 100644
--- a/drivers/hwmon/adt7411.c
+++ b/drivers/hwmon/adt7411.c
@@ -21,6 +21,21 @@
 #include <linux/hwmon-sysfs.h>
 #include <linux/slab.h>
 
+#define ADT7411_REG_STAT_1			0x00
+#define ADT7411_STAT_1_INT_TEMP_HIGH		BIT(0)
+#define ADT7411_STAT_1_INT_TEMP_LOW		BIT(1)
+#define ADT7411_STAT_1_EXT_TEMP_HIGH_AIN1	BIT(2)
+#define ADT7411_STAT_1_EXT_TEMP_LOW		BIT(3)
+#define ADT7411_STAT_1_EXT_TEMP_FAULT		BIT(4)
+#define ADT7411_STAT_1_AIN2			BIT(5)
+#define ADT7411_STAT_1_AIN3			BIT(6)
+#define ADT7411_STAT_1_AIN4			BIT(7)
+#define ADT7411_REG_STAT_2			0x01
+#define ADT7411_STAT_2_AIN5			BIT(0)
+#define ADT7411_STAT_2_AIN6			BIT(1)
+#define ADT7411_STAT_2_AIN7			BIT(2)
+#define ADT7411_STAT_2_AIN8			BIT(3)
+#define ADT7411_STAT_2_VDD			BIT(4)
 #define ADT7411_REG_INT_TEMP_VDD_LSB		0x03
 #define ADT7411_REG_EXT_TEMP_AIN14_LSB		0x04
 #define ADT7411_REG_VDD_MSB			0x06
@@ -28,20 +43,31 @@
 #define ADT7411_REG_EXT_TEMP_AIN1_MSB		0x08
 
 #define ADT7411_REG_CFG1			0x18
-#define ADT7411_CFG1_START_MONITOR		(1 << 0)
-#define ADT7411_CFG1_RESERVED_BIT1		(1 << 1)
-#define ADT7411_CFG1_EXT_TDM			(1 << 2)
-#define ADT7411_CFG1_RESERVED_BIT3		(1 << 3)
+#define ADT7411_CFG1_START_MONITOR		BIT(0)
+#define ADT7411_CFG1_RESERVED_BIT1		BIT(1)
+#define ADT7411_CFG1_EXT_TDM			BIT(2)
+#define ADT7411_CFG1_RESERVED_BIT3		BIT(3)
 
 #define ADT7411_REG_CFG2			0x19
-#define ADT7411_CFG2_DISABLE_AVG		(1 << 5)
+#define ADT7411_CFG2_DISABLE_AVG		BIT(5)
 
 #define ADT7411_REG_CFG3			0x1a
-#define ADT7411_CFG3_ADC_CLK_225		(1 << 0)
-#define ADT7411_CFG3_RESERVED_BIT1		(1 << 1)
-#define ADT7411_CFG3_RESERVED_BIT2		(1 << 2)
-#define ADT7411_CFG3_RESERVED_BIT3		(1 << 3)
-#define ADT7411_CFG3_REF_VDD			(1 << 4)
+#define ADT7411_CFG3_ADC_CLK_225		BIT(0)
+#define ADT7411_CFG3_RESERVED_BIT1		BIT(1)
+#define ADT7411_CFG3_RESERVED_BIT2		BIT(2)
+#define ADT7411_CFG3_RESERVED_BIT3		BIT(3)
+#define ADT7411_CFG3_REF_VDD			BIT(4)
+
+#define ADT7411_REG_VDD_HIGH			0x23
+#define ADT7411_REG_VDD_LOW			0x24
+#define ADT7411_REG_TEMP_HIGH(nr)		(0x25 + 2 * (nr))
+#define ADT7411_REG_TEMP_LOW(nr)		(0x26 + 2 * (nr))
+#define ADT7411_REG_IN_HIGH(nr)		((nr) > 1 \
+						  ? 0x2b + 2 * ((nr)-2) \
+						  : 0x27)
+#define ADT7411_REG_IN_LOW(nr)			((nr) > 1 \
+						  ? 0x2c + 2 * ((nr)-2) \
+						  : 0x28)
 
 #define ADT7411_REG_DEVICE_ID			0x4d
 #define ADT7411_REG_MANUFACTURER_ID		0x4e
@@ -51,6 +77,30 @@
 
 static const unsigned short normal_i2c[] = { 0x48, 0x4a, 0x4b, I2C_CLIENT_END };
 
+static const u8 adt7411_in_alarm_reg[] = {
+	ADT7411_REG_STAT_2,
+	ADT7411_REG_STAT_1,
+	ADT7411_REG_STAT_1,
+	ADT7411_REG_STAT_1,
+	ADT7411_REG_STAT_1,
+	ADT7411_REG_STAT_2,
+	ADT7411_REG_STAT_2,
+	ADT7411_REG_STAT_2,
+	ADT7411_REG_STAT_2,
+};
+
+static const u8 adt7411_in_alarm_bits[] = {
+	ADT7411_STAT_2_VDD,
+	ADT7411_STAT_1_EXT_TEMP_HIGH_AIN1,
+	ADT7411_STAT_1_AIN2,
+	ADT7411_STAT_1_AIN3,
+	ADT7411_STAT_1_AIN4,
+	ADT7411_STAT_2_AIN5,
+	ADT7411_STAT_2_AIN6,
+	ADT7411_STAT_2_AIN7,
+	ADT7411_STAT_2_AIN8,
+};
+
 struct adt7411_data {
 	struct mutex device_lock;	/* for "atomic" device accesses */
 	struct mutex update_lock;
@@ -165,6 +215,19 @@ static struct attribute *adt7411_attrs[] = {
 };
 ATTRIBUTE_GROUPS(adt7411);
 
+static int adt7411_read_in_alarm(struct device *dev, int channel, long *val)
+{
+	struct adt7411_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	int ret;
+
+	ret = i2c_smbus_read_byte_data(client, adt7411_in_alarm_reg[channel]);
+	if (ret < 0)
+		return ret;
+	*val = !!(ret & adt7411_in_alarm_bits[channel]);
+	return 0;
+}
+
 static int adt7411_read_in_vdd(struct device *dev, u32 attr, long *val)
 {
 	struct adt7411_data *data = dev_get_drvdata(dev);
@@ -179,32 +242,41 @@ static int adt7411_read_in_vdd(struct device *dev, u32 attr, long *val)
 			return ret;
 		*val = ret * 7000 / 1024;
 		return 0;
+	case hwmon_in_min:
+		ret = i2c_smbus_read_byte_data(client, ADT7411_REG_VDD_LOW);
+		if (ret < 0)
+			return ret;
+		*val = ret * 7000 / 256;
+		return 0;
+	case hwmon_in_max:
+		ret = i2c_smbus_read_byte_data(client, ADT7411_REG_VDD_HIGH);
+		if (ret < 0)
+			return ret;
+		*val = ret * 7000 / 256;
+		return 0;
+	case hwmon_in_alarm:
+		return adt7411_read_in_alarm(dev, 0, val);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
-static int adt7411_read_in_chan(struct device *dev, u32 attr, int channel,
-				long *val)
+static int adt7411_update_vref(struct device *dev)
 {
 	struct adt7411_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
+	int val;
 
-	int ret;
-	int lsb_reg, lsb_shift;
-	int nr = channel - 1;
-
-	mutex_lock(&data->update_lock);
 	if (time_after_eq(jiffies, data->next_update)) {
-		ret = i2c_smbus_read_byte_data(client, ADT7411_REG_CFG3);
-		if (ret < 0)
-			goto exit_unlock;
+		val = i2c_smbus_read_byte_data(client, ADT7411_REG_CFG3);
+		if (val < 0)
+			return val;
 
-		if (ret & ADT7411_CFG3_REF_VDD) {
-			ret = adt7411_read_in_vdd(dev, hwmon_in_input,
+		if (val & ADT7411_CFG3_REF_VDD) {
+			val = adt7411_read_in_vdd(dev, hwmon_in_input,
 						  &data->vref_cached);
-			if (ret < 0)
-				goto exit_unlock;
+			if (val < 0)
+				return val;
 		} else {
 			data->vref_cached = 2250;
 		}
@@ -212,6 +284,24 @@ static int adt7411_read_in_chan(struct device *dev, u32 attr, int channel,
 		data->next_update = jiffies + HZ;
 	}
 
+	return 0;
+}
+
+static int adt7411_read_in_chan(struct device *dev, u32 attr, int channel,
+				long *val)
+{
+	struct adt7411_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+
+	int ret;
+	int reg, lsb_reg, lsb_shift;
+	int nr = channel - 1;
+
+	mutex_lock(&data->update_lock);
+	ret = adt7411_update_vref(dev);
+	if (ret < 0)
+		goto exit_unlock;
+
 	switch (attr) {
 	case hwmon_in_input:
 		lsb_reg = ADT7411_REG_EXT_TEMP_AIN14_LSB + (nr >> 2);
@@ -224,6 +314,20 @@ static int adt7411_read_in_chan(struct device *dev, u32 attr, int channel,
 		*val = ret * data->vref_cached / 1024;
 		ret = 0;
 		break;
+	case hwmon_in_min:
+	case hwmon_in_max:
+		reg = (attr == hwmon_in_min)
+			? ADT7411_REG_IN_LOW(channel)
+			: ADT7411_REG_IN_HIGH(channel);
+		ret = i2c_smbus_read_byte_data(client, reg);
+		if (ret < 0)
+			goto exit_unlock;
+		*val = ret * data->vref_cached / 256;
+		ret = 0;
+		break;
+	case hwmon_in_alarm:
+		ret = adt7411_read_in_alarm(dev, channel, val);
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
@@ -242,12 +346,44 @@ static int adt7411_read_in(struct device *dev, u32 attr, int channel,
 		return adt7411_read_in_chan(dev, attr, channel, val);
 }
 
+
+static int adt7411_read_temp_alarm(struct device *dev, u32 attr, int channel,
+				   long *val)
+{
+	struct adt7411_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	int ret, bit;
+
+	ret = i2c_smbus_read_byte_data(client, ADT7411_REG_STAT_1);
+	if (ret < 0)
+		return ret;
+
+	switch (attr) {
+	case hwmon_temp_min_alarm:
+		bit = channel ? ADT7411_STAT_1_EXT_TEMP_LOW
+			      : ADT7411_STAT_1_INT_TEMP_LOW;
+		break;
+	case hwmon_temp_max_alarm:
+		bit = channel ? ADT7411_STAT_1_EXT_TEMP_HIGH_AIN1
+			      : ADT7411_STAT_1_INT_TEMP_HIGH;
+		break;
+	case hwmon_temp_fault:
+		bit = ADT7411_STAT_1_EXT_TEMP_FAULT;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	*val = !!(ret & bit);
+	return 0;
+}
+
 static int adt7411_read_temp(struct device *dev, u32 attr, int channel,
 			     long *val)
 {
 	struct adt7411_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
-	int ret, regl, regh;
+	int ret, reg, regl, regh;
 
 	switch (attr) {
 	case hwmon_temp_input:
@@ -261,6 +397,21 @@ static int adt7411_read_temp(struct device *dev, u32 attr, int channel,
 		ret = ret & 0x200 ? ret - 0x400 : ret; /* 10 bit signed */
 		*val = ret * 250;
 		return 0;
+	case hwmon_temp_min:
+	case hwmon_temp_max:
+		reg = (attr == hwmon_temp_min)
+			? ADT7411_REG_TEMP_LOW(channel)
+			: ADT7411_REG_TEMP_HIGH(channel);
+		ret = i2c_smbus_read_byte_data(client, reg);
+		if (ret < 0)
+			return ret;
+		ret = ret & 0x80 ? ret - 0x100 : ret; /* 8 bit signed */
+		*val = ret * 1000;
+		return 0;
+	case hwmon_temp_min_alarm:
+	case hwmon_temp_max_alarm:
+	case hwmon_temp_fault:
+		return adt7411_read_temp_alarm(dev, attr, channel, val);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -279,26 +430,143 @@ static int adt7411_read(struct device *dev, enum hwmon_sensor_types type,
 	}
 }
 
+static int adt7411_write_in_vdd(struct device *dev, u32 attr, long val)
+{
+	struct adt7411_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	int reg;
+
+	val = clamp_val(val, 0, 255 * 7000 / 256);
+	val = DIV_ROUND_CLOSEST(val * 256, 7000);
+
+	switch (attr) {
+	case hwmon_in_min:
+		reg = ADT7411_REG_VDD_LOW;
+		break;
+	case hwmon_in_max:
+		reg = ADT7411_REG_VDD_HIGH;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return i2c_smbus_write_byte_data(client, reg, val);
+}
+
+static int adt7411_write_in_chan(struct device *dev, u32 attr, int channel,
+				 long val)
+{
+	struct adt7411_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	int ret, reg;
+
+	mutex_lock(&data->update_lock);
+	ret = adt7411_update_vref(dev);
+	if (ret < 0)
+		goto exit_unlock;
+	val = clamp_val(val, 0, 255 * data->vref_cached / 256);
+	val = DIV_ROUND_CLOSEST(val * 256, data->vref_cached);
+
+	switch (attr) {
+	case hwmon_in_min:
+		reg = ADT7411_REG_IN_LOW(channel);
+		break;
+	case hwmon_in_max:
+		reg = ADT7411_REG_IN_HIGH(channel);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		goto exit_unlock;
+	}
+
+	ret = i2c_smbus_write_byte_data(client, reg, val);
+ exit_unlock:
+	mutex_unlock(&data->update_lock);
+	return ret;
+}
+
+static int adt7411_write_in(struct device *dev, u32 attr, int channel,
+			    long val)
+{
+	if (channel == 0)
+		return adt7411_write_in_vdd(dev, attr, val);
+	else
+		return adt7411_write_in_chan(dev, attr, channel, val);
+}
+
+static int adt7411_write_temp(struct device *dev, u32 attr, int channel,
+			      long val)
+{
+	struct adt7411_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	int reg;
+
+	val = clamp_val(val, -128000, 127000);
+	val = DIV_ROUND_CLOSEST(val, 1000);
+
+	switch (attr) {
+	case hwmon_temp_min:
+		reg = ADT7411_REG_TEMP_LOW(channel);
+		break;
+	case hwmon_temp_max:
+		reg = ADT7411_REG_TEMP_HIGH(channel);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return i2c_smbus_write_byte_data(client, reg, val);
+}
+
+static int adt7411_write(struct device *dev, enum hwmon_sensor_types type,
+			 u32 attr, int channel, long val)
+{
+	switch (type) {
+	case hwmon_in:
+		return adt7411_write_in(dev, attr, channel, val);
+	case hwmon_temp:
+		return adt7411_write_temp(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static umode_t adt7411_is_visible(const void *_data,
 				  enum hwmon_sensor_types type,
 				  u32 attr, int channel)
 {
 	const struct adt7411_data *data = _data;
+	bool visible;
 
 	switch (type) {
 	case hwmon_in:
-		if (channel > 0 && channel < 3)
-			return data->use_ext_temp ? 0 : S_IRUGO;
-		else
-			return S_IRUGO;
+		visible = channel == 0 || channel >= 3 || !data->use_ext_temp;
+		switch (attr) {
+		case hwmon_in_input:
+		case hwmon_in_alarm:
+			return visible ? S_IRUGO : 0;
+		case hwmon_in_min:
+		case hwmon_in_max:
+			return visible ? S_IRUGO | S_IWUSR : 0;
+		}
+		break;
 	case hwmon_temp:
-		if (channel == 1)
-			return data->use_ext_temp ? S_IRUGO : 0;
-		else
-			return S_IRUGO;
+		visible = channel == 0 || data->use_ext_temp;
+		switch (attr) {
+		case hwmon_temp_input:
+		case hwmon_temp_min_alarm:
+		case hwmon_temp_max_alarm:
+		case hwmon_temp_fault:
+			return visible ? S_IRUGO : 0;
+		case hwmon_temp_min:
+		case hwmon_temp_max:
+			return visible ? S_IRUGO | S_IWUSR : 0;
+		}
+		break;
 	default:
-		return 0;
+		break;
 	}
+	return 0;
 }
 
 static int adt7411_detect(struct i2c_client *client,
@@ -372,15 +640,15 @@ static int adt7411_init_device(struct adt7411_data *data)
 }
 
 static const u32 adt7411_in_config[] = {
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
+	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
 	0
 };
 
@@ -390,8 +658,10 @@ static const struct hwmon_channel_info adt7411_in = {
 };
 
 static const u32 adt7411_temp_config[] = {
-	HWMON_T_INPUT,
-	HWMON_T_INPUT,
+	HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MIN_ALARM |
+		HWMON_T_MAX | HWMON_T_MAX_ALARM,
+	HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MIN_ALARM |
+		HWMON_T_MAX | HWMON_T_MAX_ALARM | HWMON_T_FAULT,
 	0
 };
 
@@ -409,6 +679,7 @@ static const struct hwmon_channel_info *adt7411_info[] = {
 static const struct hwmon_ops adt7411_hwmon_ops = {
 	.is_visible = adt7411_is_visible,
 	.read = adt7411_read,
+	.write = adt7411_write,
 };
 
 static const struct hwmon_chip_info adt7411_chip_info = {
diff --git a/drivers/hwmon/adt7470.c b/drivers/hwmon/adt7470.c
index c9a1d9c25572..2cd920751441 100644
--- a/drivers/hwmon/adt7470.c
+++ b/drivers/hwmon/adt7470.c
@@ -403,7 +403,7 @@ out:
 	return data;
 }
 
-static ssize_t show_auto_update_interval(struct device *dev,
+static ssize_t auto_update_interval_show(struct device *dev,
 					 struct device_attribute *devattr,
 					 char *buf)
 {
@@ -411,10 +411,9 @@ static ssize_t show_auto_update_interval(struct device *dev,
 	return sprintf(buf, "%d\n", data->auto_update_interval);
 }
 
-static ssize_t set_auto_update_interval(struct device *dev,
-					struct device_attribute *devattr,
-					const char *buf,
-					size_t count)
+static ssize_t auto_update_interval_store(struct device *dev,
+					  struct device_attribute *devattr,
+					  const char *buf, size_t count)
 {
 	struct adt7470_data *data = dev_get_drvdata(dev);
 	long temp;
@@ -431,7 +430,7 @@ static ssize_t set_auto_update_interval(struct device *dev,
 	return count;
 }
 
-static ssize_t show_num_temp_sensors(struct device *dev,
+static ssize_t num_temp_sensors_show(struct device *dev,
 				     struct device_attribute *devattr,
 				     char *buf)
 {
@@ -439,10 +438,9 @@ static ssize_t show_num_temp_sensors(struct device *dev,
 	return sprintf(buf, "%d\n", data->num_temp_sensors);
 }
 
-static ssize_t set_num_temp_sensors(struct device *dev,
-				    struct device_attribute *devattr,
-				    const char *buf,
-				    size_t count)
+static ssize_t num_temp_sensors_store(struct device *dev,
+				      struct device_attribute *devattr,
+				      const char *buf, size_t count)
 {
 	struct adt7470_data *data = dev_get_drvdata(dev);
 	long temp;
@@ -537,7 +535,7 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *devattr,
 	return sprintf(buf, "%d\n", 1000 * data->temp[attr->index]);
 }
 
-static ssize_t show_alarm_mask(struct device *dev,
+static ssize_t alarm_mask_show(struct device *dev,
 			   struct device_attribute *devattr,
 			   char *buf)
 {
@@ -546,10 +544,9 @@ static ssize_t show_alarm_mask(struct device *dev,
 	return sprintf(buf, "%x\n", data->alarms_mask);
 }
 
-static ssize_t set_alarm_mask(struct device *dev,
-			      struct device_attribute *devattr,
-			      const char *buf,
-			      size_t count)
+static ssize_t alarm_mask_store(struct device *dev,
+				struct device_attribute *devattr,
+				const char *buf, size_t count)
 {
 	struct adt7470_data *data = dev_get_drvdata(dev);
 	long mask;
@@ -723,8 +720,8 @@ static const int adt7470_freq_map[] = {
 	11, 15, 22, 29, 35, 44, 59, 88, 1400, 22500
 };
 
-static ssize_t show_pwm_freq(struct device *dev,
-			     struct device_attribute *devattr, char *buf)
+static ssize_t pwm1_freq_show(struct device *dev,
+			      struct device_attribute *devattr, char *buf)
 {
 	struct adt7470_data *data = adt7470_update_device(dev);
 	unsigned char cfg_reg_1;
@@ -745,9 +742,9 @@ static ssize_t show_pwm_freq(struct device *dev,
 	return scnprintf(buf, PAGE_SIZE, "%d\n", adt7470_freq_map[index]);
 }
 
-static ssize_t set_pwm_freq(struct device *dev,
-			    struct device_attribute *devattr,
-			    const char *buf, size_t count)
+static ssize_t pwm1_freq_store(struct device *dev,
+			       struct device_attribute *devattr,
+			       const char *buf, size_t count)
 {
 	struct adt7470_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -1012,12 +1009,9 @@ static ssize_t show_alarm(struct device *dev,
 		return sprintf(buf, "0\n");
 }
 
-static DEVICE_ATTR(alarm_mask, S_IWUSR | S_IRUGO, show_alarm_mask,
-		   set_alarm_mask);
-static DEVICE_ATTR(num_temp_sensors, S_IWUSR | S_IRUGO, show_num_temp_sensors,
-		   set_num_temp_sensors);
-static DEVICE_ATTR(auto_update_interval, S_IWUSR | S_IRUGO,
-		   show_auto_update_interval, set_auto_update_interval);
+static DEVICE_ATTR_RW(alarm_mask);
+static DEVICE_ATTR_RW(num_temp_sensors);
+static DEVICE_ATTR_RW(auto_update_interval);
 
 static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_temp_max,
 		    set_temp_max, 0);
@@ -1133,7 +1127,7 @@ static SENSOR_DEVICE_ATTR(pwm2, S_IWUSR | S_IRUGO, show_pwm, set_pwm, 1);
 static SENSOR_DEVICE_ATTR(pwm3, S_IWUSR | S_IRUGO, show_pwm, set_pwm, 2);
 static SENSOR_DEVICE_ATTR(pwm4, S_IWUSR | S_IRUGO, show_pwm, set_pwm, 3);
 
-static DEVICE_ATTR(pwm1_freq, S_IWUSR | S_IRUGO, show_pwm_freq, set_pwm_freq);
+static DEVICE_ATTR_RW(pwm1_freq);
 
 static SENSOR_DEVICE_ATTR(pwm1_auto_point1_pwm, S_IWUSR | S_IRUGO,
 		    show_pwm_min, set_pwm_min, 0);
diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index 3cefd1aeb24f..c646670b9ea9 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -856,16 +856,17 @@ static ssize_t set_pwmfreq(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_pwm_at_crit(struct device *dev,
-				struct device_attribute *devattr, char *buf)
+static ssize_t pwm_use_point2_pwm_at_crit_show(struct device *dev,
+					struct device_attribute *devattr,
+					char *buf)
 {
 	struct adt7475_data *data = adt7475_update_device(dev);
 	return sprintf(buf, "%d\n", !!(data->config4 & CONFIG4_MAXDUTY));
 }
 
-static ssize_t set_pwm_at_crit(struct device *dev,
-			       struct device_attribute *devattr,
-			       const char *buf, size_t count)
+static ssize_t pwm_use_point2_pwm_at_crit_store(struct device *dev,
+					struct device_attribute *devattr,
+					const char *buf, size_t count)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adt7475_data *data = i2c_get_clientdata(client);
@@ -888,15 +889,15 @@ static ssize_t set_pwm_at_crit(struct device *dev,
 	return count;
 }
 
-static ssize_t show_vrm(struct device *dev, struct device_attribute *devattr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *devattr,
 			char *buf)
 {
 	struct adt7475_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", (int)data->vrm);
 }
 
-static ssize_t set_vrm(struct device *dev, struct device_attribute *devattr,
-		       const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *devattr,
+			 const char *buf, size_t count)
 {
 	struct adt7475_data *data = dev_get_drvdata(dev);
 	long val;
@@ -910,8 +911,8 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-static ssize_t show_vid(struct device *dev, struct device_attribute *devattr,
-			char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *devattr, char *buf)
 {
 	struct adt7475_data *data = adt7475_update_device(dev);
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
@@ -1057,11 +1058,10 @@ static SENSOR_DEVICE_ATTR_2(pwm3_auto_point2_pwm, S_IRUGO | S_IWUSR, show_pwm,
 			    set_pwm, MAX, 2);
 
 /* Non-standard name, might need revisiting */
-static DEVICE_ATTR(pwm_use_point2_pwm_at_crit, S_IWUSR | S_IRUGO,
-		   show_pwm_at_crit, set_pwm_at_crit);
+static DEVICE_ATTR_RW(pwm_use_point2_pwm_at_crit);
 
-static DEVICE_ATTR(vrm, S_IWUSR | S_IRUGO, show_vrm, set_vrm);
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RW(vrm);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 static struct attribute *adt7475_attrs[] = {
 	&sensor_dev_attr_in1_input.dev_attr.attr,
diff --git a/drivers/hwmon/adt7x10.c b/drivers/hwmon/adt7x10.c
index 98141f483165..0f538f8be6bf 100644
--- a/drivers/hwmon/adt7x10.c
+++ b/drivers/hwmon/adt7x10.c
@@ -331,9 +331,8 @@ static ssize_t adt7x10_show_alarm(struct device *dev,
 	return sprintf(buf, "%d\n", !!(ret & attr->index));
 }
 
-static ssize_t adt7x10_show_name(struct device *dev,
-				 struct device_attribute *da,
-				 char *buf)
+static ssize_t name_show(struct device *dev, struct device_attribute *da,
+			 char *buf)
 {
 	struct adt7x10_data *data = dev_get_drvdata(dev);
 
@@ -359,7 +358,7 @@ static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, adt7x10_show_alarm,
 			  NULL, ADT7X10_STAT_T_HIGH);
 static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, adt7x10_show_alarm,
 			  NULL, ADT7X10_STAT_T_CRIT);
-static DEVICE_ATTR(name, S_IRUGO, adt7x10_show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static struct attribute *adt7x10_attributes[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
diff --git a/drivers/hwmon/asb100.c b/drivers/hwmon/asb100.c
index 272fcc837ecc..62e191311139 100644
--- a/drivers/hwmon/asb100.c
+++ b/drivers/hwmon/asb100.c
@@ -483,25 +483,25 @@ sysfs_temp(3);
 sysfs_temp(4);
 
 /* VID */
-static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct asb100_data *data = asb100_update_device(dev);
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
 
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 /* VRM */
-static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
 	struct asb100_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", data->vrm);
 }
 
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct asb100_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -519,16 +519,16 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 }
 
 /* Alarms */
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
+static DEVICE_ATTR_RW(vrm);
 
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
 	struct asb100_data *data = asb100_update_device(dev);
 	return sprintf(buf, "%u\n", data->alarms);
 }
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 		char *buf)
@@ -550,15 +550,15 @@ static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5);
 static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 13);
 
 /* 1 PWM */
-static ssize_t show_pwm1(struct device *dev, struct device_attribute *attr,
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
 	struct asb100_data *data = asb100_update_device(dev);
 	return sprintf(buf, "%d\n", ASB100_PWM_FROM_REG(data->pwm & 0x0f));
 }
 
-static ssize_t set_pwm1(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr,
+			  const char *buf, size_t count)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct asb100_data *data = i2c_get_clientdata(client);
@@ -577,15 +577,16 @@ static ssize_t set_pwm1(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_pwm_enable1(struct device *dev,
+static ssize_t pwm1_enable_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct asb100_data *data = asb100_update_device(dev);
 	return sprintf(buf, "%d\n", (data->pwm & 0x80) ? 1 : 0);
 }
 
-static ssize_t set_pwm_enable1(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct asb100_data *data = i2c_get_clientdata(client);
@@ -604,9 +605,8 @@ static ssize_t set_pwm_enable1(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm1, set_pwm1);
-static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR,
-		show_pwm_enable1, set_pwm_enable1);
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR_RW(pwm1_enable);
 
 static struct attribute *asb100_attributes[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/atxp1.c b/drivers/hwmon/atxp1.c
index f2f2f2fc755a..b7eadb54c8cb 100644
--- a/drivers/hwmon/atxp1.c
+++ b/drivers/hwmon/atxp1.c
@@ -81,8 +81,8 @@ static struct atxp1_data *atxp1_update_device(struct device *dev)
 }
 
 /* sys file functions for cpu0_vid */
-static ssize_t atxp1_showvcore(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	int size;
 	struct atxp1_data *data;
@@ -95,9 +95,9 @@ static ssize_t atxp1_showvcore(struct device *dev,
 	return size;
 }
 
-static ssize_t atxp1_storevcore(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t count)
+static ssize_t cpu0_vid_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct atxp1_data *data = atxp1_update_device(dev);
 	struct i2c_client *client = data->client;
@@ -154,12 +154,11 @@ static ssize_t atxp1_storevcore(struct device *dev,
  * CPU core reference voltage
  * unit: millivolt
  */
-static DEVICE_ATTR(cpu0_vid, S_IRUGO | S_IWUSR, atxp1_showvcore,
-		   atxp1_storevcore);
+static DEVICE_ATTR_RW(cpu0_vid);
 
 /* sys file functions for GPIO1 */
-static ssize_t atxp1_showgpio1(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t gpio1_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
 {
 	int size;
 	struct atxp1_data *data;
@@ -171,9 +170,8 @@ static ssize_t atxp1_showgpio1(struct device *dev,
 	return size;
 }
 
-static ssize_t atxp1_storegpio1(struct device *dev,
-				struct device_attribute *attr, const char *buf,
-				size_t count)
+static ssize_t gpio1_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t count)
 {
 	struct atxp1_data *data = atxp1_update_device(dev);
 	struct i2c_client *client = data->client;
@@ -201,11 +199,11 @@ static ssize_t atxp1_storegpio1(struct device *dev,
  * GPIO1 data register
  * unit: Four bit as hex (e.g. 0x0f)
  */
-static DEVICE_ATTR(gpio1, S_IRUGO | S_IWUSR, atxp1_showgpio1, atxp1_storegpio1);
+static DEVICE_ATTR_RW(gpio1);
 
 /* sys file functions for GPIO2 */
-static ssize_t atxp1_showgpio2(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t gpio2_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
 {
 	int size;
 	struct atxp1_data *data;
@@ -217,9 +215,8 @@ static ssize_t atxp1_showgpio2(struct device *dev,
 	return size;
 }
 
-static ssize_t atxp1_storegpio2(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t count)
+static ssize_t gpio2_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t count)
 {
 	struct atxp1_data *data = atxp1_update_device(dev);
 	struct i2c_client *client = data->client;
@@ -246,7 +243,7 @@ static ssize_t atxp1_storegpio2(struct device *dev,
  * GPIO2 data register
  * unit: Eight bit as hex (e.g. 0xff)
  */
-static DEVICE_ATTR(gpio2, S_IRUGO | S_IWUSR, atxp1_showgpio2, atxp1_storegpio2);
+static DEVICE_ATTR_RW(gpio2);
 
 static struct attribute *atxp1_attrs[] = {
 	&dev_attr_gpio1.attr,
diff --git a/drivers/hwmon/dme1737.c b/drivers/hwmon/dme1737.c
index 8763c4a8280c..aa40a00ad689 100644
--- a/drivers/hwmon/dme1737.c
+++ b/drivers/hwmon/dme1737.c
@@ -279,7 +279,8 @@ static inline int IN_FROM_REG(int reg, int nominal, int res)
 
 static inline int IN_TO_REG(long val, int nominal)
 {
-	return clamp_val((val * 192 + nominal / 2) / nominal, 0, 255);
+	val = clamp_val(val, 0, 255 * nominal / 192);
+	return DIV_ROUND_CLOSEST(val * 192, nominal);
 }
 
 /*
@@ -295,7 +296,8 @@ static inline int TEMP_FROM_REG(int reg, int res)
 
 static inline int TEMP_TO_REG(long val)
 {
-	return clamp_val((val < 0 ? val - 500 : val + 500) / 1000, -128, 127);
+	val = clamp_val(val, -128000, 127000);
+	return DIV_ROUND_CLOSEST(val, 1000);
 }
 
 /* Temperature range */
@@ -331,9 +333,10 @@ static inline int TEMP_HYST_FROM_REG(int reg, int ix)
 	return (((ix == 1) ? reg : reg >> 4) & 0x0f) * 1000;
 }
 
-static inline int TEMP_HYST_TO_REG(long val, int ix, int reg)
+static inline int TEMP_HYST_TO_REG(int temp, long hyst, int ix, int reg)
 {
-	int hyst = clamp_val((val + 500) / 1000, 0, 15);
+	hyst = clamp_val(hyst, temp - 15000, temp);
+	hyst = DIV_ROUND_CLOSEST(temp - hyst, 1000);
 
 	return (ix == 1) ? (reg & 0xf0) | hyst : (reg & 0x0f) | (hyst << 4);
 }
@@ -1022,7 +1025,9 @@ static ssize_t set_zone(struct device *dev, struct device_attribute *attr,
 	int ix = sensor_attr_2->index;
 	int fn = sensor_attr_2->nr;
 	long val;
+	int temp;
 	int err;
+	u8 reg;
 
 	err = kstrtol(buf, 10, &val);
 	if (err)
@@ -1035,10 +1040,9 @@ static ssize_t set_zone(struct device *dev, struct device_attribute *attr,
 		data->zone_low[ix] = dme1737_read(data,
 						  DME1737_REG_ZONE_LOW(ix));
 		/* Modify the temp hyst value */
-		data->zone_hyst[ix == 2] = TEMP_HYST_TO_REG(
-					TEMP_FROM_REG(data->zone_low[ix], 8) -
-					val, ix, dme1737_read(data,
-					DME1737_REG_ZONE_HYST(ix == 2)));
+		temp = TEMP_FROM_REG(data->zone_low[ix], 8);
+		reg = dme1737_read(data, DME1737_REG_ZONE_HYST(ix == 2));
+		data->zone_hyst[ix == 2] = TEMP_HYST_TO_REG(temp, val, ix, reg);
 		dme1737_write(data, DME1737_REG_ZONE_HYST(ix == 2),
 			      data->zone_hyst[ix == 2]);
 		break;
@@ -1055,10 +1059,10 @@ static ssize_t set_zone(struct device *dev, struct device_attribute *attr,
 		 * Modify the temp range value (which is stored in the upper
 		 * nibble of the pwm_freq register)
 		 */
-		data->pwm_freq[ix] = TEMP_RANGE_TO_REG(val -
-					TEMP_FROM_REG(data->zone_low[ix], 8),
-					dme1737_read(data,
-					DME1737_REG_PWM_FREQ(ix)));
+		temp = TEMP_FROM_REG(data->zone_low[ix], 8);
+		val = clamp_val(val, temp, temp + 80000);
+		reg = dme1737_read(data, DME1737_REG_PWM_FREQ(ix));
+		data->pwm_freq[ix] = TEMP_RANGE_TO_REG(val - temp, reg);
 		dme1737_write(data, DME1737_REG_PWM_FREQ(ix),
 			      data->pwm_freq[ix]);
 		break;
@@ -1468,7 +1472,7 @@ exit:
  * Miscellaneous sysfs attributes
  * --------------------------------------------------------------------- */
 
-static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
 			char *buf)
 {
 	struct i2c_client *client = to_i2c_client(dev);
@@ -1477,8 +1481,8 @@ static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", data->vrm);
 }
 
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
-		       const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct dme1737_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -1495,15 +1499,15 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
-			char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct dme1737_data *data = dme1737_update_device(dev);
 
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
 
-static ssize_t show_name(struct device *dev, struct device_attribute *attr,
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
 	struct dme1737_data *data = dev_get_drvdata(dev);
@@ -1645,9 +1649,9 @@ SENSOR_DEVICE_ATTR_PWM_5TO6(6);
 
 /* Misc */
 
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);   /* for ISA devices */
+static DEVICE_ATTR_RW(vrm);
+static DEVICE_ATTR_RO(cpu0_vid);
+static DEVICE_ATTR_RO(name);   /* for ISA devices */
 
 /*
  * This struct holds all the attributes that are always present and need to be
diff --git a/drivers/hwmon/ds1621.c b/drivers/hwmon/ds1621.c
index 8890870309e4..5c317fc32a4a 100644
--- a/drivers/hwmon/ds1621.c
+++ b/drivers/hwmon/ds1621.c
@@ -263,7 +263,7 @@ static ssize_t set_temp(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-static ssize_t show_alarms(struct device *dev, struct device_attribute *da,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *da,
 			   char *buf)
 {
 	struct ds1621_data *data = ds1621_update_client(dev);
@@ -278,15 +278,16 @@ static ssize_t show_alarm(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%d\n", !!(data->conf & attr->index));
 }
 
-static ssize_t show_convrate(struct device *dev, struct device_attribute *da,
-			  char *buf)
+static ssize_t update_interval_show(struct device *dev,
+				    struct device_attribute *da, char *buf)
 {
 	struct ds1621_data *data = dev_get_drvdata(dev);
 	return scnprintf(buf, PAGE_SIZE, "%hu\n", data->update_interval);
 }
 
-static ssize_t set_convrate(struct device *dev, struct device_attribute *da,
-			    const char *buf, size_t count)
+static ssize_t update_interval_store(struct device *dev,
+				     struct device_attribute *da,
+				     const char *buf, size_t count)
 {
 	struct ds1621_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -315,9 +316,8 @@ static ssize_t set_convrate(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
-static DEVICE_ATTR(update_interval, S_IWUSR | S_IRUGO, show_convrate,
-		   set_convrate);
+static DEVICE_ATTR_RO(alarms);
+static DEVICE_ATTR_RW(update_interval);
 
 static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp1_min, S_IWUSR | S_IRUGO, show_temp, set_temp, 1);
diff --git a/drivers/hwmon/emc2103.c b/drivers/hwmon/emc2103.c
index 4b870ee9b0d3..1ed9a7aa953d 100644
--- a/drivers/hwmon/emc2103.c
+++ b/drivers/hwmon/emc2103.c
@@ -284,7 +284,7 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *da,
 }
 
 static ssize_t
-show_fan(struct device *dev, struct device_attribute *da, char *buf)
+fan1_input_show(struct device *dev, struct device_attribute *da, char *buf)
 {
 	struct emc2103_data *data = emc2103_update_device(dev);
 	int rpm = 0;
@@ -294,7 +294,7 @@ show_fan(struct device *dev, struct device_attribute *da, char *buf)
 }
 
 static ssize_t
-show_fan_div(struct device *dev, struct device_attribute *da, char *buf)
+fan1_div_show(struct device *dev, struct device_attribute *da, char *buf)
 {
 	struct emc2103_data *data = emc2103_update_device(dev);
 	int fan_div = 8 / data->fan_multiplier;
@@ -307,8 +307,8 @@ show_fan_div(struct device *dev, struct device_attribute *da, char *buf)
  * of least surprise; the user doesn't expect the fan target to change just
  * because the divider changed.
  */
-static ssize_t set_fan_div(struct device *dev, struct device_attribute *da,
-			   const char *buf, size_t count)
+static ssize_t fan1_div_store(struct device *dev, struct device_attribute *da,
+			      const char *buf, size_t count)
 {
 	struct emc2103_data *data = emc2103_update_device(dev);
 	struct i2c_client *client = data->client;
@@ -369,7 +369,7 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *da,
 }
 
 static ssize_t
-show_fan_target(struct device *dev, struct device_attribute *da, char *buf)
+fan1_target_show(struct device *dev, struct device_attribute *da, char *buf)
 {
 	struct emc2103_data *data = emc2103_update_device(dev);
 	int rpm = 0;
@@ -382,8 +382,9 @@ show_fan_target(struct device *dev, struct device_attribute *da, char *buf)
 	return sprintf(buf, "%d\n", rpm);
 }
 
-static ssize_t set_fan_target(struct device *dev, struct device_attribute *da,
-			      const char *buf, size_t count)
+static ssize_t fan1_target_store(struct device *dev,
+				 struct device_attribute *da, const char *buf,
+				 size_t count)
 {
 	struct emc2103_data *data = emc2103_update_device(dev);
 	struct i2c_client *client = data->client;
@@ -412,7 +413,7 @@ static ssize_t set_fan_target(struct device *dev, struct device_attribute *da,
 }
 
 static ssize_t
-show_fan_fault(struct device *dev, struct device_attribute *da, char *buf)
+fan1_fault_show(struct device *dev, struct device_attribute *da, char *buf)
 {
 	struct emc2103_data *data = emc2103_update_device(dev);
 	bool fault = ((data->fan_tach & 0x1fe0) == 0x1fe0);
@@ -420,14 +421,15 @@ show_fan_fault(struct device *dev, struct device_attribute *da, char *buf)
 }
 
 static ssize_t
-show_pwm_enable(struct device *dev, struct device_attribute *da, char *buf)
+pwm1_enable_show(struct device *dev, struct device_attribute *da, char *buf)
 {
 	struct emc2103_data *data = emc2103_update_device(dev);
 	return sprintf(buf, "%d\n", data->fan_rpm_control ? 3 : 0);
 }
 
-static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *da,
-			      const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+				 struct device_attribute *da, const char *buf,
+				 size_t count)
 {
 	struct emc2103_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -512,14 +514,12 @@ static SENSOR_DEVICE_ATTR(temp4_min_alarm, S_IRUGO, show_temp_min_alarm,
 static SENSOR_DEVICE_ATTR(temp4_max_alarm, S_IRUGO, show_temp_max_alarm,
 	NULL, 3);
 
-static DEVICE_ATTR(fan1_input, S_IRUGO, show_fan, NULL);
-static DEVICE_ATTR(fan1_div, S_IRUGO | S_IWUSR, show_fan_div, set_fan_div);
-static DEVICE_ATTR(fan1_target, S_IRUGO | S_IWUSR, show_fan_target,
-	set_fan_target);
-static DEVICE_ATTR(fan1_fault, S_IRUGO, show_fan_fault, NULL);
+static DEVICE_ATTR_RO(fan1_input);
+static DEVICE_ATTR_RW(fan1_div);
+static DEVICE_ATTR_RW(fan1_target);
+static DEVICE_ATTR_RO(fan1_fault);
 
-static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR, show_pwm_enable,
-	set_pwm_enable);
+static DEVICE_ATTR_RW(pwm1_enable);
 
 /* sensors present on all models */
 static struct attribute *emc2103_attributes[] = {
diff --git a/drivers/hwmon/f71805f.c b/drivers/hwmon/f71805f.c
index facd05cda26d..73c681162653 100644
--- a/drivers/hwmon/f71805f.c
+++ b/drivers/hwmon/f71805f.c
@@ -946,7 +946,7 @@ static ssize_t set_temp_hyst(struct device *dev, struct device_attribute
 	return count;
 }
 
-static ssize_t show_alarms_in(struct device *dev, struct device_attribute
+static ssize_t alarms_in_show(struct device *dev, struct device_attribute
 			      *devattr, char *buf)
 {
 	struct f71805f_data *data = f71805f_update_device(dev);
@@ -954,7 +954,7 @@ static ssize_t show_alarms_in(struct device *dev, struct device_attribute
 	return sprintf(buf, "%lu\n", data->alarms & 0x7ff);
 }
 
-static ssize_t show_alarms_fan(struct device *dev, struct device_attribute
+static ssize_t alarms_fan_show(struct device *dev, struct device_attribute
 			       *devattr, char *buf)
 {
 	struct f71805f_data *data = f71805f_update_device(dev);
@@ -962,7 +962,7 @@ static ssize_t show_alarms_fan(struct device *dev, struct device_attribute
 	return sprintf(buf, "%lu\n", (data->alarms >> 16) & 0x07);
 }
 
-static ssize_t show_alarms_temp(struct device *dev, struct device_attribute
+static ssize_t alarms_temp_show(struct device *dev, struct device_attribute
 				*devattr, char *buf)
 {
 	struct f71805f_data *data = f71805f_update_device(dev);
@@ -980,7 +980,7 @@ static ssize_t show_alarm(struct device *dev, struct device_attribute
 	return sprintf(buf, "%lu\n", (data->alarms >> bitnr) & 1);
 }
 
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
 			 *devattr, char *buf)
 {
 	struct f71805f_data *data = dev_get_drvdata(dev);
@@ -1176,11 +1176,11 @@ static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 13);
 static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 16);
 static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 17);
 static SENSOR_DEVICE_ATTR(fan3_alarm, S_IRUGO, show_alarm, NULL, 18);
-static DEVICE_ATTR(alarms_in, S_IRUGO, show_alarms_in, NULL);
-static DEVICE_ATTR(alarms_fan, S_IRUGO, show_alarms_fan, NULL);
-static DEVICE_ATTR(alarms_temp, S_IRUGO, show_alarms_temp, NULL);
+static DEVICE_ATTR_RO(alarms_in);
+static DEVICE_ATTR_RO(alarms_fan);
+static DEVICE_ATTR_RO(alarms_temp);
 
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static struct attribute *f71805f_attributes[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c
index cb28e4b4fb10..ca54ce5c8e10 100644
--- a/drivers/hwmon/f71882fg.c
+++ b/drivers/hwmon/f71882fg.c
@@ -390,7 +390,7 @@ static ssize_t show_pwm_auto_point_temp(struct device *dev,
 static ssize_t store_pwm_auto_point_temp(struct device *dev,
 	struct device_attribute *devattr, const char *buf, size_t count);
 /* Sysfs misc */
-static ssize_t show_name(struct device *dev, struct device_attribute *devattr,
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
 	char *buf);
 
 static int f71882fg_probe(struct platform_device *pdev);
@@ -404,7 +404,7 @@ static struct platform_driver f71882fg_driver = {
 	.remove		= f71882fg_remove,
 };
 
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 /*
  * Temp attr for the f71858fg, the f71858fg is special as it has its
@@ -2212,7 +2212,7 @@ static ssize_t store_pwm_auto_point_temp(struct device *dev,
 	return count;
 }
 
-static ssize_t show_name(struct device *dev, struct device_attribute *devattr,
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
 	char *buf)
 {
 	struct f71882fg_data *data = dev_get_drvdata(dev);
diff --git a/drivers/hwmon/fam15h_power.c b/drivers/hwmon/fam15h_power.c
index 15aa49d082c4..9545a346044f 100644
--- a/drivers/hwmon/fam15h_power.c
+++ b/drivers/hwmon/fam15h_power.c
@@ -83,8 +83,8 @@ static bool is_carrizo_or_later(void)
 	return boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model >= 0x60;
 }
 
-static ssize_t show_power(struct device *dev,
-			  struct device_attribute *attr, char *buf)
+static ssize_t power1_input_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
 {
 	u32 val, tdp_limit, running_avg_range;
 	s32 running_avg_capture;
@@ -136,16 +136,16 @@ static ssize_t show_power(struct device *dev,
 	curr_pwr_watts = (curr_pwr_watts * 15625) >> (10 + running_avg_range);
 	return sprintf(buf, "%u\n", (unsigned int) curr_pwr_watts);
 }
-static DEVICE_ATTR(power1_input, S_IRUGO, show_power, NULL);
+static DEVICE_ATTR_RO(power1_input);
 
-static ssize_t show_power_crit(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t power1_crit_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct fam15h_power_data *data = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", data->processor_pwr_watts);
 }
-static DEVICE_ATTR(power1_crit, S_IRUGO, show_power_crit, NULL);
+static DEVICE_ATTR_RO(power1_crit);
 
 static void do_read_registers_on_cu(void *_data)
 {
@@ -212,9 +212,8 @@ static int read_registers(struct fam15h_power_data *data)
 	return 0;
 }
 
-static ssize_t acc_show_power(struct device *dev,
-			      struct device_attribute *attr,
-			      char *buf)
+static ssize_t power1_average_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
 {
 	struct fam15h_power_data *data = dev_get_drvdata(dev);
 	u64 prev_cu_acc_power[MAX_CUS], prev_ptsc[MAX_CUS],
@@ -267,20 +266,20 @@ static ssize_t acc_show_power(struct device *dev,
 
 	return sprintf(buf, "%llu\n", (unsigned long long)avg_acc);
 }
-static DEVICE_ATTR(power1_average, S_IRUGO, acc_show_power, NULL);
+static DEVICE_ATTR_RO(power1_average);
 
-static ssize_t acc_show_power_period(struct device *dev,
-				     struct device_attribute *attr,
-				     char *buf)
+static ssize_t power1_average_interval_show(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
 {
 	struct fam15h_power_data *data = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%lu\n", data->power_period);
 }
 
-static ssize_t acc_set_power_period(struct device *dev,
-				    struct device_attribute *attr,
-				    const char *buf, size_t count)
+static ssize_t power1_average_interval_store(struct device *dev,
+					     struct device_attribute *attr,
+					     const char *buf, size_t count)
 {
 	struct fam15h_power_data *data = dev_get_drvdata(dev);
 	unsigned long temp;
@@ -301,8 +300,7 @@ static ssize_t acc_set_power_period(struct device *dev,
 
 	return count;
 }
-static DEVICE_ATTR(power1_average_interval, S_IRUGO | S_IWUSR,
-		   acc_show_power_period, acc_set_power_period);
+static DEVICE_ATTR_RW(power1_average_interval);
 
 static int fam15h_power_init_attrs(struct pci_dev *pdev,
 				   struct fam15h_power_data *data)
diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c
index d58abdc5a4cf..5e78229ade04 100644
--- a/drivers/hwmon/fschmd.c
+++ b/drivers/hwmon/fschmd.c
@@ -561,7 +561,7 @@ static ssize_t store_pwm_auto_point1_pwm(struct device *dev,
  * The FSC hwmon family has the ability to force an attached alert led to flash
  * from software, we export this as an alert_led sysfs attr
  */
-static ssize_t show_alert_led(struct device *dev,
+static ssize_t alert_led_show(struct device *dev,
 	struct device_attribute *devattr, char *buf)
 {
 	struct fschmd_data *data = fschmd_update_device(dev);
@@ -572,7 +572,7 @@ static ssize_t show_alert_led(struct device *dev,
 		return sprintf(buf, "0\n");
 }
 
-static ssize_t store_alert_led(struct device *dev,
+static ssize_t alert_led_store(struct device *dev,
 	struct device_attribute *devattr, const char *buf, size_t count)
 {
 	u8 reg;
@@ -602,7 +602,7 @@ static ssize_t store_alert_led(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(alert_led, 0644, show_alert_led, store_alert_led);
+static DEVICE_ATTR_RW(alert_led);
 
 static struct sensor_device_attribute fschmd_attr[] = {
 	SENSOR_ATTR(in0_input, 0444, show_in_value, NULL, 0),
diff --git a/drivers/hwmon/g760a.c b/drivers/hwmon/g760a.c
index ec6a77da411a..7be1371b2c3d 100644
--- a/drivers/hwmon/g760a.c
+++ b/drivers/hwmon/g760a.c
@@ -107,8 +107,8 @@ static struct g760a_data *g760a_update_client(struct device *dev)
 	return data;
 }
 
-static ssize_t show_fan(struct device *dev, struct device_attribute *da,
-			char *buf)
+static ssize_t fan1_input_show(struct device *dev,
+			       struct device_attribute *da, char *buf)
 {
 	struct g760a_data *data = g760a_update_client(dev);
 	unsigned int rpm = 0;
@@ -121,8 +121,8 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%d\n", rpm);
 }
 
-static ssize_t show_fan_alarm(struct device *dev, struct device_attribute *da,
-			      char *buf)
+static ssize_t fan1_alarm_show(struct device *dev,
+			       struct device_attribute *da, char *buf)
 {
 	struct g760a_data *data = g760a_update_client(dev);
 
@@ -131,16 +131,16 @@ static ssize_t show_fan_alarm(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%d\n", fan_alarm);
 }
 
-static ssize_t get_pwm(struct device *dev, struct device_attribute *da,
-		       char *buf)
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *da,
+			 char *buf)
 {
 	struct g760a_data *data = g760a_update_client(dev);
 
 	return sprintf(buf, "%d\n", PWM_FROM_CNT(data->set_cnt));
 }
 
-static ssize_t set_pwm(struct device *dev, struct device_attribute *da,
-		       const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *da,
+			  const char *buf, size_t count)
 {
 	struct g760a_data *data = g760a_update_client(dev);
 	struct i2c_client *client = data->client;
@@ -157,9 +157,9 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, get_pwm, set_pwm);
-static DEVICE_ATTR(fan1_input, S_IRUGO, show_fan, NULL);
-static DEVICE_ATTR(fan1_alarm, S_IRUGO, show_fan_alarm, NULL);
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR_RO(fan1_input);
+static DEVICE_ATTR_RO(fan1_alarm);
 
 static struct attribute *g760a_attrs[] = {
 	&dev_attr_pwm1.attr,
diff --git a/drivers/hwmon/g762.c b/drivers/hwmon/g762.c
index 628be9c95ff9..6dca2fd3d303 100644
--- a/drivers/hwmon/g762.c
+++ b/drivers/hwmon/g762.c
@@ -738,8 +738,8 @@ static int g762_pdata_prop_import(struct i2c_client *client)
  * Read function for fan1_input sysfs file. Return current fan RPM value, or
  * 0 if fan is out of control.
  */
-static ssize_t get_fan_rpm(struct device *dev, struct device_attribute *da,
-			   char *buf)
+static ssize_t fan1_input_show(struct device *dev,
+			       struct device_attribute *da, char *buf)
 {
 	struct g762_data *data = g762_update_client(dev);
 	unsigned int rpm = 0;
@@ -764,8 +764,8 @@ static ssize_t get_fan_rpm(struct device *dev, struct device_attribute *da,
  * Read and write functions for pwm1_mode sysfs file. Get and set fan speed
  * control mode i.e. PWM (1) or DC (0).
  */
-static ssize_t get_pwm_mode(struct device *dev, struct device_attribute *da,
-			    char *buf)
+static ssize_t pwm1_mode_show(struct device *dev, struct device_attribute *da,
+			      char *buf)
 {
 	struct g762_data *data = g762_update_client(dev);
 
@@ -776,8 +776,9 @@ static ssize_t get_pwm_mode(struct device *dev, struct device_attribute *da,
 		       !!(data->fan_cmd1 & G762_REG_FAN_CMD1_OUT_MODE));
 }
 
-static ssize_t set_pwm_mode(struct device *dev, struct device_attribute *da,
-			    const char *buf, size_t count)
+static ssize_t pwm1_mode_store(struct device *dev,
+			       struct device_attribute *da, const char *buf,
+			       size_t count)
 {
 	unsigned long val;
 	int ret;
@@ -796,8 +797,8 @@ static ssize_t set_pwm_mode(struct device *dev, struct device_attribute *da,
  * Read and write functions for fan1_div sysfs file. Get and set fan
  * controller prescaler value
  */
-static ssize_t get_fan_div(struct device *dev,
-			   struct device_attribute *da, char *buf)
+static ssize_t fan1_div_show(struct device *dev, struct device_attribute *da,
+			     char *buf)
 {
 	struct g762_data *data = g762_update_client(dev);
 
@@ -807,9 +808,8 @@ static ssize_t get_fan_div(struct device *dev,
 	return sprintf(buf, "%d\n", G762_CLKDIV_FROM_REG(data->fan_cmd1));
 }
 
-static ssize_t set_fan_div(struct device *dev,
-			   struct device_attribute *da,
-			   const char *buf, size_t count)
+static ssize_t fan1_div_store(struct device *dev, struct device_attribute *da,
+			      const char *buf, size_t count)
 {
 	unsigned long val;
 	int ret;
@@ -828,8 +828,8 @@ static ssize_t set_fan_div(struct device *dev,
  * Read and write functions for fan1_pulses sysfs file. Get and set number
  * of tachometer pulses per fan revolution.
  */
-static ssize_t get_fan_pulses(struct device *dev,
-			      struct device_attribute *da, char *buf)
+static ssize_t fan1_pulses_show(struct device *dev,
+				struct device_attribute *da, char *buf)
 {
 	struct g762_data *data = g762_update_client(dev);
 
@@ -839,9 +839,9 @@ static ssize_t get_fan_pulses(struct device *dev,
 	return sprintf(buf, "%d\n", G762_PULSE_FROM_REG(data->fan_cmd1));
 }
 
-static ssize_t set_fan_pulses(struct device *dev,
-			      struct device_attribute *da,
-			      const char *buf, size_t count)
+static ssize_t fan1_pulses_store(struct device *dev,
+				 struct device_attribute *da, const char *buf,
+				 size_t count)
 {
 	unsigned long val;
 	int ret;
@@ -870,8 +870,8 @@ static ssize_t set_fan_pulses(struct device *dev,
  * but we do not accept 0 as this mode is not natively supported by the chip
  * and it is not emulated by g762 driver. -EINVAL is returned in this case.
  */
-static ssize_t get_pwm_enable(struct device *dev,
-			      struct device_attribute *da, char *buf)
+static ssize_t pwm1_enable_show(struct device *dev,
+				struct device_attribute *da, char *buf)
 {
 	struct g762_data *data = g762_update_client(dev);
 
@@ -882,9 +882,9 @@ static ssize_t get_pwm_enable(struct device *dev,
 		       (!!(data->fan_cmd1 & G762_REG_FAN_CMD1_FAN_MODE)) + 1);
 }
 
-static ssize_t set_pwm_enable(struct device *dev,
-			      struct device_attribute *da,
-			      const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+				 struct device_attribute *da, const char *buf,
+				 size_t count)
 {
 	unsigned long val;
 	int ret;
@@ -904,8 +904,8 @@ static ssize_t set_pwm_enable(struct device *dev,
  * (which affects fan speed) in open-loop mode. 0 stops the fan and 255
  * makes it run at full speed.
  */
-static ssize_t get_pwm(struct device *dev, struct device_attribute *da,
-		       char *buf)
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *da,
+			 char *buf)
 {
 	struct g762_data *data = g762_update_client(dev);
 
@@ -915,8 +915,8 @@ static ssize_t get_pwm(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%d\n", data->set_out);
 }
 
-static ssize_t set_pwm(struct device *dev, struct device_attribute *da,
-		       const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *da,
+			  const char *buf, size_t count)
 {
 	unsigned long val;
 	int ret;
@@ -942,8 +942,8 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute *da,
  * Also note that due to rounding errors it is possible that you don't read
  * back exactly the value you have set.
  */
-static ssize_t get_fan_target(struct device *dev, struct device_attribute *da,
-			      char *buf)
+static ssize_t fan1_target_show(struct device *dev,
+				struct device_attribute *da, char *buf)
 {
 	struct g762_data *data = g762_update_client(dev);
 	unsigned int rpm;
@@ -961,8 +961,9 @@ static ssize_t get_fan_target(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%u\n", rpm);
 }
 
-static ssize_t set_fan_target(struct device *dev, struct device_attribute *da,
-			      const char *buf, size_t count)
+static ssize_t fan1_target_store(struct device *dev,
+				 struct device_attribute *da, const char *buf,
+				 size_t count)
 {
 	unsigned long val;
 	int ret;
@@ -978,7 +979,7 @@ static ssize_t set_fan_target(struct device *dev, struct device_attribute *da,
 }
 
 /* read function for fan1_fault sysfs file. */
-static ssize_t get_fan_failure(struct device *dev, struct device_attribute *da,
+static ssize_t fan1_fault_show(struct device *dev, struct device_attribute *da,
 			       char *buf)
 {
 	struct g762_data *data = g762_update_client(dev);
@@ -993,8 +994,8 @@ static ssize_t get_fan_failure(struct device *dev, struct device_attribute *da,
  * read function for fan1_alarm sysfs file. Note that OOC condition is
  * enabled low
  */
-static ssize_t get_fan_ooc(struct device *dev, struct device_attribute *da,
-			   char *buf)
+static ssize_t fan1_alarm_show(struct device *dev,
+			       struct device_attribute *da, char *buf)
 {
 	struct g762_data *data = g762_update_client(dev);
 
@@ -1004,18 +1005,15 @@ static ssize_t get_fan_ooc(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%u\n", !(data->fan_sta & G762_REG_FAN_STA_OOC));
 }
 
-static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, get_pwm, set_pwm);
-static DEVICE_ATTR(pwm1_mode, S_IWUSR | S_IRUGO, get_pwm_mode, set_pwm_mode);
-static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO,
-		   get_pwm_enable, set_pwm_enable);
-static DEVICE_ATTR(fan1_input, S_IRUGO, get_fan_rpm, NULL);
-static DEVICE_ATTR(fan1_alarm, S_IRUGO, get_fan_ooc, NULL);
-static DEVICE_ATTR(fan1_fault, S_IRUGO, get_fan_failure, NULL);
-static DEVICE_ATTR(fan1_target, S_IWUSR | S_IRUGO,
-		   get_fan_target, set_fan_target);
-static DEVICE_ATTR(fan1_div, S_IWUSR | S_IRUGO, get_fan_div, set_fan_div);
-static DEVICE_ATTR(fan1_pulses, S_IWUSR | S_IRUGO,
-		   get_fan_pulses, set_fan_pulses);
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR_RW(pwm1_mode);
+static DEVICE_ATTR_RW(pwm1_enable);
+static DEVICE_ATTR_RO(fan1_input);
+static DEVICE_ATTR_RO(fan1_alarm);
+static DEVICE_ATTR_RO(fan1_fault);
+static DEVICE_ATTR_RW(fan1_target);
+static DEVICE_ATTR_RW(fan1_div);
+static DEVICE_ATTR_RW(fan1_pulses);
 
 /* Driver data */
 static struct attribute *g762_attrs[] = {
diff --git a/drivers/hwmon/gl518sm.c b/drivers/hwmon/gl518sm.c
index 0212c8317bca..b267510daeb2 100644
--- a/drivers/hwmon/gl518sm.c
+++ b/drivers/hwmon/gl518sm.c
@@ -86,9 +86,8 @@ enum chips { gl518sm_r00, gl518sm_r80 };
 #define BOOL_FROM_REG(val)	((val) ? 0 : 1)
 #define BOOL_TO_REG(val)	((val) ? 0 : 1)
 
-#define TEMP_TO_REG(val)	clamp_val(((((val) < 0 ? \
-				(val) - 500 : \
-				(val) + 500) / 1000) + 119), 0, 255)
+#define TEMP_CLAMP(val)		clamp_val(val, -119000, 136000)
+#define TEMP_TO_REG(val)	(DIV_ROUND_CLOSEST(TEMP_CLAMP(val), 1000) + 119)
 #define TEMP_FROM_REG(val)	(((val) - 119) * 1000)
 
 static inline u8 FAN_TO_REG(long rpm, int div)
@@ -101,11 +100,13 @@ static inline u8 FAN_TO_REG(long rpm, int div)
 }
 #define FAN_FROM_REG(val, div)	((val) == 0 ? 0 : (480000 / ((val) * (div))))
 
-#define IN_TO_REG(val)		clamp_val((((val) + 9) / 19), 0, 255)
+#define IN_CLAMP(val)		clamp_val(val, 0, 255 * 19)
+#define IN_TO_REG(val)		DIV_ROUND_CLOSEST(IN_CLAMP(val), 19)
 #define IN_FROM_REG(val)	((val) * 19)
 
-#define VDD_TO_REG(val)		clamp_val((((val) * 4 + 47) / 95), 0, 255)
-#define VDD_FROM_REG(val)	(((val) * 95 + 2) / 4)
+#define VDD_CLAMP(val)		clamp_val(val, 0, 255 * 95 / 4)
+#define VDD_TO_REG(val)		DIV_ROUND_CLOSEST(VDD_CLAMP(val) * 4, 95)
+#define VDD_FROM_REG(val)	DIV_ROUND_CLOSEST((val) * 95, 4)
 
 #define DIV_FROM_REG(val)	(1 << (val))
 
diff --git a/drivers/hwmon/gl520sm.c b/drivers/hwmon/gl520sm.c
index dee93ec87d02..4ff32ee67fb6 100644
--- a/drivers/hwmon/gl520sm.c
+++ b/drivers/hwmon/gl520sm.c
@@ -200,19 +200,21 @@ static struct gl520_data *gl520_update_device(struct device *dev)
  * Sysfs stuff
  */
 
-static ssize_t get_cpu_vid(struct device *dev, struct device_attribute *attr,
-			   char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct gl520_data *data = gl520_update_device(dev);
 	return sprintf(buf, "%u\n", vid_from_reg(data->vid, data->vrm));
 }
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, get_cpu_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
-#define VDD_FROM_REG(val) (((val) * 95 + 2) / 4)
-#define VDD_TO_REG(val) clamp_val((((val) * 4 + 47) / 95), 0, 255)
+#define VDD_FROM_REG(val)	DIV_ROUND_CLOSEST((val) * 95, 4)
+#define VDD_CLAMP(val)		clamp_val(val, 0, 255 * 95 / 4)
+#define VDD_TO_REG(val)		DIV_ROUND_CLOSEST(VDD_CLAMP(val) * 4, 95)
 
-#define IN_FROM_REG(val) ((val) * 19)
-#define IN_TO_REG(val) clamp_val((((val) + 9) / 19), 0, 255)
+#define IN_FROM_REG(val)	((val) * 19)
+#define IN_CLAMP(val)		clamp_val(val, 0, 255 * 19)
+#define IN_TO_REG(val)		DIV_ROUND_CLOSEST(IN_CLAMP(val), 19)
 
 static ssize_t get_in_input(struct device *dev, struct device_attribute *attr,
 			    char *buf)
@@ -349,8 +351,13 @@ static SENSOR_DEVICE_ATTR(in4_max, S_IRUGO | S_IWUSR,
 
 #define DIV_FROM_REG(val) (1 << (val))
 #define FAN_FROM_REG(val, div) ((val) == 0 ? 0 : (480000 / ((val) << (div))))
-#define FAN_TO_REG(val, div) ((val) <= 0 ? 0 : \
-	clamp_val((480000 + ((val) << ((div)-1))) / ((val) << (div)), 1, 255))
+
+#define FAN_BASE(div)		(480000 >> (div))
+#define FAN_CLAMP(val, div)	clamp_val(val, FAN_BASE(div) / 255, \
+					  FAN_BASE(div))
+#define FAN_TO_REG(val, div)	((val) == 0 ? 0 : \
+				 DIV_ROUND_CLOSEST(480000, \
+						FAN_CLAMP(val, div) << (div)))
 
 static ssize_t get_fan_input(struct device *dev, struct device_attribute *attr,
 			     char *buf)
@@ -381,8 +388,8 @@ static ssize_t get_fan_div(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", DIV_FROM_REG(data->fan_div[n]));
 }
 
-static ssize_t get_fan_off(struct device *dev, struct device_attribute *attr,
-			   char *buf)
+static ssize_t fan1_off_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct gl520_data *data = gl520_update_device(dev);
 	return sprintf(buf, "%d\n", data->fan_off);
@@ -476,8 +483,9 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t set_fan_off(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t fan1_off_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct gl520_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -510,12 +518,11 @@ static SENSOR_DEVICE_ATTR(fan1_div, S_IRUGO | S_IWUSR,
 		get_fan_div, set_fan_div, 0);
 static SENSOR_DEVICE_ATTR(fan2_div, S_IRUGO | S_IWUSR,
 		get_fan_div, set_fan_div, 1);
-static DEVICE_ATTR(fan1_off, S_IRUGO | S_IWUSR,
-		get_fan_off, set_fan_off);
+static DEVICE_ATTR_RW(fan1_off);
 
-#define TEMP_FROM_REG(val) (((val) - 130) * 1000)
-#define TEMP_TO_REG(val) clamp_val(((((val) < 0 ? \
-			(val) - 500 : (val) + 500) / 1000) + 130), 0, 255)
+#define TEMP_FROM_REG(val)	(((val) - 130) * 1000)
+#define TEMP_CLAMP(val)		clamp_val(val, -130000, 125000)
+#define TEMP_TO_REG(val)	(DIV_ROUND_CLOSEST(TEMP_CLAMP(val), 1000) + 130)
 
 static ssize_t get_temp_input(struct device *dev, struct device_attribute *attr,
 			      char *buf)
@@ -596,29 +603,30 @@ static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR,
 static SENSOR_DEVICE_ATTR(temp2_max_hyst, S_IRUGO | S_IWUSR,
 		get_temp_max_hyst, set_temp_max_hyst, 1);
 
-static ssize_t get_alarms(struct device *dev, struct device_attribute *attr,
-			  char *buf)
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct gl520_data *data = gl520_update_device(dev);
 	return sprintf(buf, "%d\n", data->alarms);
 }
 
-static ssize_t get_beep_enable(struct device *dev, struct device_attribute
-			       *attr, char *buf)
+static ssize_t beep_enable_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct gl520_data *data = gl520_update_device(dev);
 	return sprintf(buf, "%d\n", data->beep_enable);
 }
 
-static ssize_t get_beep_mask(struct device *dev, struct device_attribute *attr,
-			     char *buf)
+static ssize_t beep_mask_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	struct gl520_data *data = gl520_update_device(dev);
 	return sprintf(buf, "%d\n", data->beep_mask);
 }
 
-static ssize_t set_beep_enable(struct device *dev, struct device_attribute
-			       *attr, const char *buf, size_t count)
+static ssize_t beep_enable_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct gl520_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -641,8 +649,9 @@ static ssize_t set_beep_enable(struct device *dev, struct device_attribute
 	return count;
 }
 
-static ssize_t set_beep_mask(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
+static ssize_t beep_mask_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t count)
 {
 	struct gl520_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -661,11 +670,9 @@ static ssize_t set_beep_mask(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(alarms, S_IRUGO, get_alarms, NULL);
-static DEVICE_ATTR(beep_enable, S_IRUGO | S_IWUSR,
-		get_beep_enable, set_beep_enable);
-static DEVICE_ATTR(beep_mask, S_IRUGO | S_IWUSR,
-		get_beep_mask, set_beep_mask);
+static DEVICE_ATTR_RO(alarms);
+static DEVICE_ATTR_RW(beep_enable);
+static DEVICE_ATTR_RW(beep_mask);
 
 static ssize_t get_alarm(struct device *dev, struct device_attribute *attr,
 			 char *buf)
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 685568b1236d..9c355b9d31c5 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -77,8 +77,8 @@ static irqreturn_t fan_alarm_irq_handler(int irq, void *dev_id)
 	return IRQ_NONE;
 }
 
-static ssize_t show_fan_alarm(struct device *dev,
-			      struct device_attribute *attr, char *buf)
+static ssize_t fan1_alarm_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 	struct gpio_fan_alarm *alarm = fan_data->alarm;
@@ -90,7 +90,7 @@ static ssize_t show_fan_alarm(struct device *dev,
 	return sprintf(buf, "%d\n", value);
 }
 
-static DEVICE_ATTR(fan1_alarm, S_IRUGO, show_fan_alarm, NULL);
+static DEVICE_ATTR_RO(fan1_alarm);
 
 static int fan_alarm_init(struct gpio_fan_data *fan_data,
 			  struct gpio_fan_alarm *alarm)
@@ -188,8 +188,8 @@ static int rpm_to_speed_index(struct gpio_fan_data *fan_data, unsigned long rpm)
 	return fan_data->num_speed - 1;
 }
 
-static ssize_t show_pwm(struct device *dev,
-			struct device_attribute *attr, char *buf)
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 	u8 pwm = fan_data->speed_index * 255 / (fan_data->num_speed - 1);
@@ -197,8 +197,8 @@ static ssize_t show_pwm(struct device *dev,
 	return sprintf(buf, "%d\n", pwm);
 }
 
-static ssize_t set_pwm(struct device *dev, struct device_attribute *attr,
-		       const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev, struct device_attribute *attr,
+			  const char *buf, size_t count)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 	unsigned long pwm;
@@ -224,16 +224,17 @@ exit_unlock:
 	return ret;
 }
 
-static ssize_t show_pwm_enable(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t pwm1_enable_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%d\n", fan_data->pwm_enable);
 }
 
-static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr,
-			      const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -257,22 +258,22 @@ static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_pwm_mode(struct device *dev,
-			     struct device_attribute *attr, char *buf)
+static ssize_t pwm1_mode_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "0\n");
 }
 
-static ssize_t show_rpm_min(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t fan1_min_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%d\n", fan_data->speed[0].rpm);
 }
 
-static ssize_t show_rpm_max(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t fan1_max_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 
@@ -280,8 +281,8 @@ static ssize_t show_rpm_max(struct device *dev,
 		       fan_data->speed[fan_data->num_speed - 1].rpm);
 }
 
-static ssize_t show_rpm(struct device *dev,
-			struct device_attribute *attr, char *buf)
+static ssize_t fan1_input_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	struct gpio_fan_data *fan_data = dev_get_drvdata(dev);
 
@@ -313,14 +314,13 @@ exit_unlock:
 	return ret;
 }
 
-static DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm, set_pwm);
-static DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR,
-		   show_pwm_enable, set_pwm_enable);
-static DEVICE_ATTR(pwm1_mode, S_IRUGO, show_pwm_mode, NULL);
-static DEVICE_ATTR(fan1_min, S_IRUGO, show_rpm_min, NULL);
-static DEVICE_ATTR(fan1_max, S_IRUGO, show_rpm_max, NULL);
-static DEVICE_ATTR(fan1_input, S_IRUGO, show_rpm, NULL);
-static DEVICE_ATTR(fan1_target, S_IRUGO | S_IWUSR, show_rpm, set_rpm);
+static DEVICE_ATTR_RW(pwm1);
+static DEVICE_ATTR_RW(pwm1_enable);
+static DEVICE_ATTR_RO(pwm1_mode);
+static DEVICE_ATTR_RO(fan1_min);
+static DEVICE_ATTR_RO(fan1_max);
+static DEVICE_ATTR_RO(fan1_input);
+static DEVICE_ATTR(fan1_target, S_IRUGO | S_IWUSR, fan1_input_show, set_rpm);
 
 static umode_t gpio_fan_is_visible(struct kobject *kobj,
 				   struct attribute *attr, int index)
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 3932f9276c07..28375d59cc36 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -63,11 +63,11 @@ struct hwmon_thermal_data {
 };
 
 static ssize_t
-show_name(struct device *dev, struct device_attribute *attr, char *buf)
+name_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%s\n", to_hwmon_device(dev)->name);
 }
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static struct attribute *hwmon_dev_attrs[] = {
 	&dev_attr_name.attr,
@@ -544,9 +544,11 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 	struct device *hdev;
 	int i, j, err, id;
 
-	/* Do not accept invalid characters in hwmon name attribute */
+	/* Complain about invalid characters in hwmon name attribute */
 	if (name && (!strlen(name) || strpbrk(name, "-* \t\n")))
-		return ERR_PTR(-EINVAL);
+		dev_warn(dev,
+			 "hwmon: '%s' is not a valid name attribute, please fix\n",
+			 name);
 
 	id = ida_simple_get(&hwmon_ida, 0, 0, GFP_KERNEL);
 	if (id < 0)
@@ -606,7 +608,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata,
 	if (err)
 		goto free_hwmon;
 
-	if (chip && chip->ops->read &&
+	if (dev && chip && chip->ops->read &&
 	    chip->info[0]->type == hwmon_chip &&
 	    (chip->info[0]->config[0] & HWMON_C_REGISTER_TZ)) {
 		const struct hwmon_channel_info **info = chip->info;
@@ -651,6 +653,9 @@ hwmon_device_register_with_groups(struct device *dev, const char *name,
 				  void *drvdata,
 				  const struct attribute_group **groups)
 {
+	if (!name)
+		return ERR_PTR(-EINVAL);
+
 	return __hwmon_device_register(dev, name, drvdata, NULL, groups);
 }
 EXPORT_SYMBOL_GPL(hwmon_device_register_with_groups);
@@ -674,6 +679,9 @@ hwmon_device_register_with_info(struct device *dev, const char *name,
 				const struct hwmon_chip_info *chip,
 				const struct attribute_group **extra_groups)
 {
+	if (!name)
+		return ERR_PTR(-EINVAL);
+
 	if (chip && (!chip->ops || !chip->ops->is_visible || !chip->info))
 		return ERR_PTR(-EINVAL);
 
@@ -695,7 +703,7 @@ struct device *hwmon_device_register(struct device *dev)
 	dev_warn(dev,
 		 "hwmon_device_register() is deprecated. Please convert the driver to use hwmon_device_register_with_info().\n");
 
-	return hwmon_device_register_with_groups(dev, NULL, NULL, NULL);
+	return __hwmon_device_register(dev, NULL, NULL, NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(hwmon_device_register);
 
diff --git a/drivers/hwmon/i5500_temp.c b/drivers/hwmon/i5500_temp.c
index 3e3ccbf18b4e..400e0675a90b 100644
--- a/drivers/hwmon/i5500_temp.c
+++ b/drivers/hwmon/i5500_temp.c
@@ -43,8 +43,8 @@
  */
 
 /* Sensor resolution : 0.5 degree C */
-static ssize_t show_temp(struct device *dev,
-			 struct device_attribute *devattr, char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *devattr, char *buf)
 {
 	struct pci_dev *pdev = to_pci_dev(dev->parent);
 	long temp;
@@ -83,7 +83,7 @@ static ssize_t show_alarm(struct device *dev,
 	return sprintf(buf, "%u\n", (unsigned int)ctsts & (1 << nr));
 }
 
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
+static DEVICE_ATTR_RO(temp1_input);
 static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_thresh, NULL, 0xE2);
 static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IRUGO, show_thresh, NULL, 0xEC);
 static SENSOR_DEVICE_ATTR(temp1_max, S_IRUGO, show_thresh, NULL, 0xEE);
diff --git a/drivers/hwmon/i5k_amb.c b/drivers/hwmon/i5k_amb.c
index 6b3d1972cef7..a5a9f457b7f7 100644
--- a/drivers/hwmon/i5k_amb.c
+++ b/drivers/hwmon/i5k_amb.c
@@ -114,14 +114,14 @@ struct i5k_amb_data {
 	unsigned int num_attrs;
 };
 
-static ssize_t show_name(struct device *dev, struct device_attribute *devattr,
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
 			 char *buf)
 {
 	return sprintf(buf, "%s\n", DRVNAME);
 }
 
 
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static struct platform_device *amb_pdev;
 
diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c
index ad82cb28d87a..efb01c247e2d 100644
--- a/drivers/hwmon/it87.c
+++ b/drivers/hwmon/it87.c
@@ -12,6 +12,7 @@
  *
  *  Supports: IT8603E  Super I/O chip w/LPC interface
  *            IT8620E  Super I/O chip w/LPC interface
+ *            IT8622E  Super I/O chip w/LPC interface
  *            IT8623E  Super I/O chip w/LPC interface
  *            IT8628E  Super I/O chip w/LPC interface
  *            IT8705F  Super I/O chip w/LPC interface
@@ -31,6 +32,7 @@
  *            IT8783E/F Super I/O chip w/LPC interface
  *            IT8786E  Super I/O chip w/LPC interface
  *            IT8790E  Super I/O chip w/LPC interface
+ *            IT8792E  Super I/O chip w/LPC interface
  *            Sis950   A clone of the IT8705F
  *
  *  Copyright (C) 2001 Chris Gauthron
@@ -69,8 +71,8 @@
 #define DRVNAME "it87"
 
 enum chips { it87, it8712, it8716, it8718, it8720, it8721, it8728, it8732,
-	     it8771, it8772, it8781, it8782, it8783, it8786, it8790, it8603,
-	     it8620, it8628 };
+	     it8771, it8772, it8781, it8782, it8783, it8786, it8790,
+	     it8792, it8603, it8620, it8622, it8628 };
 
 static unsigned short force_id;
 module_param(force_id, ushort, 0);
@@ -151,6 +153,7 @@ static inline void superio_exit(int ioreg)
 #define IT8726F_DEVID 0x8726
 #define IT8728F_DEVID 0x8728
 #define IT8732F_DEVID 0x8732
+#define IT8792E_DEVID 0x8733
 #define IT8771E_DEVID 0x8771
 #define IT8772E_DEVID 0x8772
 #define IT8781F_DEVID 0x8781
@@ -160,6 +163,7 @@ static inline void superio_exit(int ioreg)
 #define IT8790E_DEVID 0x8790
 #define IT8603E_DEVID 0x8603
 #define IT8620E_DEVID 0x8620
+#define IT8622E_DEVID 0x8622
 #define IT8623E_DEVID 0x8623
 #define IT8628E_DEVID 0x8628
 #define IT87_ACT_REG  0x30
@@ -293,9 +297,11 @@ struct it87_devices {
 #define FEAT_SIX_FANS		BIT(11)	/* Supports six fans */
 #define FEAT_10_9MV_ADC		BIT(12)
 #define FEAT_AVCC3		BIT(13)	/* Chip supports in9/AVCC3 */
-#define FEAT_SIX_PWM		BIT(14)	/* Chip supports 6 pwm chn */
-#define FEAT_PWM_FREQ2		BIT(15)	/* Separate pwm freq 2 */
-#define FEAT_SIX_TEMP		BIT(16)	/* Up to 6 temp sensors */
+#define FEAT_FIVE_PWM		BIT(14)	/* Chip supports 5 pwm chn */
+#define FEAT_SIX_PWM		BIT(15)	/* Chip supports 6 pwm chn */
+#define FEAT_PWM_FREQ2		BIT(16)	/* Separate pwm freq 2 */
+#define FEAT_SIX_TEMP		BIT(17)	/* Up to 6 temp sensors */
+#define FEAT_VIN3_5V		BIT(18)	/* VIN3 connected to +5V */
 
 static const struct it87_devices it87_devices[] = {
 	[it87] = {
@@ -419,6 +425,15 @@ static const struct it87_devices it87_devices[] = {
 		  | FEAT_PWM_FREQ2,
 		.peci_mask = 0x07,
 	},
+	[it8792] = {
+		.name = "it8792",
+		.suffix = "E",
+		.features = FEAT_NEWER_AUTOPWM | FEAT_16BIT_FANS
+		  | FEAT_TEMP_OFFSET | FEAT_TEMP_OLD_PECI | FEAT_TEMP_PECI
+		  | FEAT_10_9MV_ADC | FEAT_IN7_INTERNAL,
+		.peci_mask = 0x07,
+		.old_peci_mask = 0x02,	/* Actually reports PCH */
+	},
 	[it8603] = {
 		.name = "it8603",
 		.suffix = "E",
@@ -433,7 +448,16 @@ static const struct it87_devices it87_devices[] = {
 		.features = FEAT_NEWER_AUTOPWM | FEAT_12MV_ADC | FEAT_16BIT_FANS
 		  | FEAT_TEMP_OFFSET | FEAT_TEMP_PECI | FEAT_SIX_FANS
 		  | FEAT_IN7_INTERNAL | FEAT_SIX_PWM | FEAT_PWM_FREQ2
-		  | FEAT_SIX_TEMP,
+		  | FEAT_SIX_TEMP | FEAT_VIN3_5V,
+		.peci_mask = 0x07,
+	},
+	[it8622] = {
+		.name = "it8622",
+		.suffix = "E",
+		.features = FEAT_NEWER_AUTOPWM | FEAT_12MV_ADC | FEAT_16BIT_FANS
+		  | FEAT_TEMP_OFFSET | FEAT_TEMP_PECI | FEAT_FIVE_FANS
+		  | FEAT_FIVE_PWM | FEAT_IN7_INTERNAL | FEAT_PWM_FREQ2
+		  | FEAT_AVCC3 | FEAT_VIN3_5V,
 		.peci_mask = 0x07,
 	},
 	[it8628] = {
@@ -442,7 +466,7 @@ static const struct it87_devices it87_devices[] = {
 		.features = FEAT_NEWER_AUTOPWM | FEAT_12MV_ADC | FEAT_16BIT_FANS
 		  | FEAT_TEMP_OFFSET | FEAT_TEMP_PECI | FEAT_SIX_FANS
 		  | FEAT_IN7_INTERNAL | FEAT_SIX_PWM | FEAT_PWM_FREQ2
-		  | FEAT_SIX_TEMP,
+		  | FEAT_SIX_TEMP | FEAT_VIN3_5V,
 		.peci_mask = 0x07,
 	},
 };
@@ -465,9 +489,12 @@ static const struct it87_devices it87_devices[] = {
 #define has_in7_internal(data)	((data)->features & FEAT_IN7_INTERNAL)
 #define has_six_fans(data)	((data)->features & FEAT_SIX_FANS)
 #define has_avcc3(data)		((data)->features & FEAT_AVCC3)
+#define has_five_pwm(data)	((data)->features & (FEAT_FIVE_PWM \
+						     | FEAT_SIX_PWM))
 #define has_six_pwm(data)	((data)->features & FEAT_SIX_PWM)
 #define has_pwm_freq2(data)	((data)->features & FEAT_PWM_FREQ2)
 #define has_six_temp(data)	((data)->features & FEAT_SIX_TEMP)
+#define has_vin3_5v(data)	((data)->features & FEAT_VIN3_5V)
 
 struct it87_sio_data {
 	enum chips type;
@@ -1300,25 +1327,35 @@ static ssize_t set_pwm_enable(struct device *dev, struct device_attribute *attr,
 			it87_write_value(data, IT87_REG_FAN_MAIN_CTRL,
 					 data->fan_main_ctrl);
 		} else {
+			u8 ctrl;
+
 			/* No on/off mode, set maximum pwm value */
 			data->pwm_duty[nr] = pwm_to_reg(data, 0xff);
 			it87_write_value(data, IT87_REG_PWM_DUTY[nr],
 					 data->pwm_duty[nr]);
 			/* and set manual mode */
-			data->pwm_ctrl[nr] = has_newer_autopwm(data) ?
-					     data->pwm_temp_map[nr] :
-					     data->pwm_duty[nr];
-			it87_write_value(data, IT87_REG_PWM[nr],
-					 data->pwm_ctrl[nr]);
+			if (has_newer_autopwm(data)) {
+				ctrl = (data->pwm_ctrl[nr] & 0x7c) |
+					data->pwm_temp_map[nr];
+			} else {
+				ctrl = data->pwm_duty[nr];
+			}
+			data->pwm_ctrl[nr] = ctrl;
+			it87_write_value(data, IT87_REG_PWM[nr], ctrl);
 		}
 	} else {
-		if (val == 1)				/* Manual mode */
-			data->pwm_ctrl[nr] = has_newer_autopwm(data) ?
-					     data->pwm_temp_map[nr] :
-					     data->pwm_duty[nr];
-		else					/* Automatic mode */
-			data->pwm_ctrl[nr] = 0x80 | data->pwm_temp_map[nr];
-		it87_write_value(data, IT87_REG_PWM[nr], data->pwm_ctrl[nr]);
+		u8 ctrl;
+
+		if (has_newer_autopwm(data)) {
+			ctrl = (data->pwm_ctrl[nr] & 0x7c) |
+				data->pwm_temp_map[nr];
+			if (val != 1)
+				ctrl |= 0x80;
+		} else {
+			ctrl = (val == 1 ? data->pwm_duty[nr] : 0x80);
+		}
+		data->pwm_ctrl[nr] = ctrl;
+		it87_write_value(data, IT87_REG_PWM[nr], ctrl);
 
 		if (data->type != it8603 && nr < 3) {
 			/* set SmartGuardian mode */
@@ -1344,6 +1381,7 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 
 	mutex_lock(&data->update_lock);
+	it87_update_pwm_ctrl(data, nr);
 	if (has_newer_autopwm(data)) {
 		/*
 		 * If we are in automatic mode, the PWM duty cycle register
@@ -1456,13 +1494,15 @@ static ssize_t set_pwm_temp_map(struct device *dev,
 	}
 
 	mutex_lock(&data->update_lock);
+	it87_update_pwm_ctrl(data, nr);
 	data->pwm_temp_map[nr] = reg;
 	/*
 	 * If we are in automatic mode, write the temp mapping immediately;
 	 * otherwise, just store it for later use.
 	 */
 	if (data->pwm_ctrl[nr] & 0x80) {
-		data->pwm_ctrl[nr] = 0x80 | data->pwm_temp_map[nr];
+		data->pwm_ctrl[nr] = (data->pwm_ctrl[nr] & 0xfc) |
+						data->pwm_temp_map[nr];
 		it87_write_value(data, IT87_REG_PWM[nr], data->pwm_ctrl[nr]);
 	}
 	mutex_unlock(&data->update_lock);
@@ -1762,14 +1802,14 @@ static SENSOR_DEVICE_ATTR(pwm6_auto_slope, S_IRUGO | S_IWUSR,
 			  show_auto_pwm_slope, set_auto_pwm_slope, 5);
 
 /* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct it87_data *data = it87_update_device(dev);
 
 	return sprintf(buf, "%u\n", data->alarms);
 }
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 			  char *buf)
@@ -1877,16 +1917,16 @@ static SENSOR_DEVICE_ATTR(temp1_beep, S_IRUGO | S_IWUSR,
 static SENSOR_DEVICE_ATTR(temp2_beep, S_IRUGO, show_beep, NULL, 2);
 static SENSOR_DEVICE_ATTR(temp3_beep, S_IRUGO, show_beep, NULL, 2);
 
-static ssize_t show_vrm_reg(struct device *dev, struct device_attribute *attr,
-			    char *buf)
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	struct it87_data *data = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", data->vrm);
 }
 
-static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct it87_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -1898,16 +1938,16 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
 
 	return count;
 }
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
 
-static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr,
-			    char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct it87_data *data = it87_update_device(dev);
 
 	return sprintf(buf, "%ld\n", (long)vid_from_reg(data->vid, data->vrm));
 }
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 static ssize_t show_label(struct device *dev, struct device_attribute *attr,
 			  char *buf)
@@ -1916,17 +1956,21 @@ static ssize_t show_label(struct device *dev, struct device_attribute *attr,
 		"+5V",
 		"5VSB",
 		"Vbat",
+		"AVCC",
 	};
 	static const char * const labels_it8721[] = {
 		"+3.3V",
 		"3VSB",
 		"Vbat",
+		"+3.3V",
 	};
 	struct it87_data *data = dev_get_drvdata(dev);
 	int nr = to_sensor_dev_attr(attr)->index;
 	const char *label;
 
-	if (has_12mv_adc(data) || has_10_9mv_adc(data))
+	if (has_vin3_5v(data) && nr == 0)
+		label = labels[0];
+	else if (has_12mv_adc(data) || has_10_9mv_adc(data))
 		label = labels_it8721[nr];
 	else
 		label = labels[nr];
@@ -1937,7 +1981,7 @@ static SENSOR_DEVICE_ATTR(in3_label, S_IRUGO, show_label, NULL, 0);
 static SENSOR_DEVICE_ATTR(in7_label, S_IRUGO, show_label, NULL, 1);
 static SENSOR_DEVICE_ATTR(in8_label, S_IRUGO, show_label, NULL, 2);
 /* AVCC3 */
-static SENSOR_DEVICE_ATTR(in9_label, S_IRUGO, show_label, NULL, 0);
+static SENSOR_DEVICE_ATTR(in9_label, S_IRUGO, show_label, NULL, 3);
 
 static umode_t it87_in_is_visible(struct kobject *kobj,
 				  struct attribute *attr, int index)
@@ -2386,6 +2430,9 @@ static int __init it87_find(int sioaddr, unsigned short *address,
 	case IT8732F_DEVID:
 		sio_data->type = it8732;
 		break;
+	case IT8792E_DEVID:
+		sio_data->type = it8792;
+		break;
 	case IT8771E_DEVID:
 		sio_data->type = it8771;
 		break;
@@ -2414,6 +2461,9 @@ static int __init it87_find(int sioaddr, unsigned short *address,
 	case IT8620E_DEVID:
 		sio_data->type = it8620;
 		break;
+	case IT8622E_DEVID:
+		sio_data->type = it8622;
+		break;
 	case IT8628E_DEVID:
 		sio_data->type = it8628;
 		break;
@@ -2457,8 +2507,10 @@ static int __init it87_find(int sioaddr, unsigned short *address,
 	else
 		sio_data->skip_in |= BIT(9);
 
-	if (!has_six_pwm(config))
+	if (!has_five_pwm(config))
 		sio_data->skip_pwm |= BIT(3) | BIT(4) | BIT(5);
+	else if (!has_six_pwm(config))
+		sio_data->skip_pwm |= BIT(5);
 
 	if (!has_vid(config))
 		sio_data->skip_vid = 1;
@@ -2587,7 +2639,7 @@ static int __init it87_find(int sioaddr, unsigned short *address,
 
 		/* Check for pwm4 */
 		reg = superio_inb(sioaddr, IT87_SIO_GPIO4_REG);
-		if (!(reg & BIT(2)))
+		if (reg & BIT(2))
 			sio_data->skip_pwm |= BIT(3);
 
 		/* Check for pwm2, fan2 */
@@ -2602,6 +2654,50 @@ static int __init it87_find(int sioaddr, unsigned short *address,
 			sio_data->skip_fan |= BIT(5);
 		}
 
+		/* Check if AVCC is on VIN3 */
+		reg = superio_inb(sioaddr, IT87_SIO_PINX2_REG);
+		if (reg & BIT(0))
+			sio_data->internal |= BIT(0);
+		else
+			sio_data->skip_in |= BIT(9);
+
+		sio_data->beep_pin = superio_inb(sioaddr,
+						 IT87_SIO_BEEP_PIN_REG) & 0x3f;
+	} else if (sio_data->type == it8622) {
+		int reg;
+
+		superio_select(sioaddr, GPIO);
+
+		/* Check for pwm4, fan4 */
+		reg = superio_inb(sioaddr, IT87_SIO_GPIO1_REG);
+		if (reg & BIT(6))
+			sio_data->skip_fan |= BIT(3);
+		if (reg & BIT(5))
+			sio_data->skip_pwm |= BIT(3);
+
+		/* Check for pwm3, fan3, pwm5, fan5 */
+		reg = superio_inb(sioaddr, IT87_SIO_GPIO3_REG);
+		if (reg & BIT(6))
+			sio_data->skip_pwm |= BIT(2);
+		if (reg & BIT(7))
+			sio_data->skip_fan |= BIT(2);
+		if (reg & BIT(3))
+			sio_data->skip_pwm |= BIT(4);
+		if (reg & BIT(1))
+			sio_data->skip_fan |= BIT(4);
+
+		/* Check for pwm2, fan2 */
+		reg = superio_inb(sioaddr, IT87_SIO_GPIO5_REG);
+		if (reg & BIT(1))
+			sio_data->skip_pwm |= BIT(1);
+		if (reg & BIT(2))
+			sio_data->skip_fan |= BIT(1);
+
+		/* Check for AVCC */
+		reg = superio_inb(sioaddr, IT87_SIO_PINX2_REG);
+		if (!(reg & BIT(0)))
+			sio_data->skip_in |= BIT(9);
+
 		sio_data->beep_pin = superio_inb(sioaddr,
 						 IT87_SIO_BEEP_PIN_REG) & 0x3f;
 	} else {
diff --git a/drivers/hwmon/jz4740-hwmon.c b/drivers/hwmon/jz4740-hwmon.c
index 0621ee1b3c98..2d40a2e771d7 100644
--- a/drivers/hwmon/jz4740-hwmon.c
+++ b/drivers/hwmon/jz4740-hwmon.c
@@ -44,8 +44,8 @@ static irqreturn_t jz4740_hwmon_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static ssize_t jz4740_hwmon_read_adcin(struct device *dev,
-	struct device_attribute *dev_attr, char *buf)
+static ssize_t in0_input_show(struct device *dev,
+			      struct device_attribute *dev_attr, char *buf)
 {
 	struct jz4740_hwmon *hwmon = dev_get_drvdata(dev);
 	struct platform_device *pdev = hwmon->pdev;
@@ -79,7 +79,7 @@ static ssize_t jz4740_hwmon_read_adcin(struct device *dev,
 	return ret;
 }
 
-static DEVICE_ATTR(in0_input, S_IRUGO, jz4740_hwmon_read_adcin, NULL);
+static DEVICE_ATTR_RO(in0_input);
 
 static struct attribute *jz4740_attrs[] = {
 	&dev_attr_in0_input.attr,
diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 9cdfde6515ad..ce3b91f22e30 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -72,8 +72,8 @@ static void amd_nb_smu_index_read(struct pci_dev *pdev, unsigned int devfn,
 	mutex_unlock(&nb_smu_ind_mutex);
 }
 
-static ssize_t show_temp(struct device *dev,
-			 struct device_attribute *attr, char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	u32 regval;
 	struct pci_dev *pdev = dev_get_drvdata(dev);
@@ -88,8 +88,8 @@ static ssize_t show_temp(struct device *dev,
 	return sprintf(buf, "%u\n", (regval >> 21) * 125);
 }
 
-static ssize_t show_temp_max(struct device *dev,
-			     struct device_attribute *attr, char *buf)
+static ssize_t temp1_max_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%d\n", 70 * 1000);
 }
@@ -110,8 +110,8 @@ static ssize_t show_temp_crit(struct device *dev,
 	return sprintf(buf, "%d\n", value);
 }
 
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
-static DEVICE_ATTR(temp1_max, S_IRUGO, show_temp_max, NULL);
+static DEVICE_ATTR_RO(temp1_input);
+static DEVICE_ATTR_RO(temp1_max);
 static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp_crit, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IRUGO, show_temp_crit, NULL, 1);
 
diff --git a/drivers/hwmon/k8temp.c b/drivers/hwmon/k8temp.c
index 734d55d48cc8..5a632bcf869b 100644
--- a/drivers/hwmon/k8temp.c
+++ b/drivers/hwmon/k8temp.c
@@ -100,7 +100,7 @@ static struct k8temp_data *k8temp_update_device(struct device *dev)
  * Sysfs stuff
  */
 
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
 			 *devattr, char *buf)
 {
 	struct k8temp_data *data = dev_get_drvdata(dev);
@@ -133,7 +133,7 @@ static SENSOR_DEVICE_ATTR_2(temp1_input, S_IRUGO, show_temp, NULL, 0, 0);
 static SENSOR_DEVICE_ATTR_2(temp2_input, S_IRUGO, show_temp, NULL, 0, 1);
 static SENSOR_DEVICE_ATTR_2(temp3_input, S_IRUGO, show_temp, NULL, 1, 0);
 static SENSOR_DEVICE_ATTR_2(temp4_input, S_IRUGO, show_temp, NULL, 1, 1);
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static const struct pci_device_id k8temp_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
diff --git a/drivers/hwmon/lm63.c b/drivers/hwmon/lm63.c
index 33bfdb444138..2e1948699114 100644
--- a/drivers/hwmon/lm63.c
+++ b/drivers/hwmon/lm63.c
@@ -417,16 +417,16 @@ static ssize_t set_pwm1(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-static ssize_t show_pwm1_enable(struct device *dev,
+static ssize_t pwm1_enable_show(struct device *dev,
 				struct device_attribute *dummy, char *buf)
 {
 	struct lm63_data *data = lm63_update_device(dev);
 	return sprintf(buf, "%d\n", data->config_fan & 0x20 ? 1 : 2);
 }
 
-static ssize_t set_pwm1_enable(struct device *dev,
-			       struct device_attribute *dummy,
-			       const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+				 struct device_attribute *dummy,
+				 const char *buf, size_t count)
 {
 	struct lm63_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -600,7 +600,7 @@ static ssize_t set_temp11(struct device *dev, struct device_attribute *devattr,
  * Hysteresis register holds a relative value, while we want to present
  * an absolute to user-space
  */
-static ssize_t show_temp2_crit_hyst(struct device *dev,
+static ssize_t temp2_crit_hyst_show(struct device *dev,
 				    struct device_attribute *dummy, char *buf)
 {
 	struct lm63_data *data = lm63_update_device(dev);
@@ -624,9 +624,9 @@ static ssize_t show_lut_temp_hyst(struct device *dev,
  * And now the other way around, user-space provides an absolute
  * hysteresis value and we have to store a relative one
  */
-static ssize_t set_temp2_crit_hyst(struct device *dev,
-				   struct device_attribute *dummy,
-				   const char *buf, size_t count)
+static ssize_t temp2_crit_hyst_store(struct device *dev,
+				     struct device_attribute *dummy,
+				     const char *buf, size_t count)
 {
 	struct lm63_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -670,7 +670,7 @@ static void lm63_set_convrate(struct lm63_data *data, unsigned int interval)
 	data->update_interval = UPDATE_INTERVAL(data->max_convrate_hz, i);
 }
 
-static ssize_t show_update_interval(struct device *dev,
+static ssize_t update_interval_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct lm63_data *data = dev_get_drvdata(dev);
@@ -678,9 +678,9 @@ static ssize_t show_update_interval(struct device *dev,
 	return sprintf(buf, "%u\n", data->update_interval);
 }
 
-static ssize_t set_update_interval(struct device *dev,
-				   struct device_attribute *attr,
-				   const char *buf, size_t count)
+static ssize_t update_interval_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
 {
 	struct lm63_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -697,16 +697,17 @@ static ssize_t set_update_interval(struct device *dev,
 	return count;
 }
 
-static ssize_t show_type(struct device *dev, struct device_attribute *attr,
-			 char *buf)
+static ssize_t temp2_type_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	struct lm63_data *data = dev_get_drvdata(dev);
 
 	return sprintf(buf, data->trutherm ? "1\n" : "2\n");
 }
 
-static ssize_t set_type(struct device *dev, struct device_attribute *attr,
-			const char *buf, size_t count)
+static ssize_t temp2_type_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
 {
 	struct lm63_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -731,7 +732,7 @@ static ssize_t set_type(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_alarms(struct device *dev, struct device_attribute *dummy,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *dummy,
 			   char *buf)
 {
 	struct lm63_data *data = lm63_update_device(dev);
@@ -753,8 +754,7 @@ static SENSOR_DEVICE_ATTR(fan1_min, S_IWUSR | S_IRUGO, show_fan,
 	set_fan, 1);
 
 static SENSOR_DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, show_pwm1, set_pwm1, 0);
-static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO,
-	show_pwm1_enable, set_pwm1_enable);
+static DEVICE_ATTR_RW(pwm1_enable);
 static SENSOR_DEVICE_ATTR(pwm1_auto_point1_pwm, S_IWUSR | S_IRUGO,
 	show_pwm1, set_pwm1, 1);
 static SENSOR_DEVICE_ATTR(pwm1_auto_point1_temp, S_IWUSR | S_IRUGO,
@@ -841,10 +841,9 @@ static SENSOR_DEVICE_ATTR(temp2_offset, S_IWUSR | S_IRUGO, show_temp11,
 	set_temp11, 3);
 static SENSOR_DEVICE_ATTR(temp2_crit, S_IRUGO, show_remote_temp8,
 	set_temp8, 2);
-static DEVICE_ATTR(temp2_crit_hyst, S_IWUSR | S_IRUGO, show_temp2_crit_hyst,
-	set_temp2_crit_hyst);
+static DEVICE_ATTR_RW(temp2_crit_hyst);
 
-static DEVICE_ATTR(temp2_type, S_IWUSR | S_IRUGO, show_type, set_type);
+static DEVICE_ATTR_RW(temp2_type);
 
 /* Individual alarm files */
 static SENSOR_DEVICE_ATTR(fan1_min_alarm, S_IRUGO, show_alarm, NULL, 0);
@@ -854,10 +853,9 @@ static SENSOR_DEVICE_ATTR(temp2_min_alarm, S_IRUGO, show_alarm, NULL, 3);
 static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 4);
 static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 6);
 /* Raw alarm file for compatibility */
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
-static DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, show_update_interval,
-		   set_update_interval);
+static DEVICE_ATTR_RW(update_interval);
 
 static struct attribute *lm63_attributes[] = {
 	&sensor_dev_attr_pwm1.dev_attr.attr,
diff --git a/drivers/hwmon/lm70.c b/drivers/hwmon/lm70.c
index 583f883a4cfe..543556dc563b 100644
--- a/drivers/hwmon/lm70.c
+++ b/drivers/hwmon/lm70.c
@@ -46,6 +46,7 @@
 #define LM70_CHIP_TMP121	1	/* TI TMP121/TMP123 */
 #define LM70_CHIP_LM71		2	/* NS LM71 */
 #define LM70_CHIP_LM74		3	/* NS LM74 */
+#define LM70_CHIP_TMP122	4	/* TI TMP122/TMP124 */
 
 struct lm70 {
 	struct spi_device *spi;
@@ -54,8 +55,8 @@ struct lm70 {
 };
 
 /* sysfs hook function */
-static ssize_t lm70_sense_temp(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct lm70 *p_lm70 = dev_get_drvdata(dev);
 	struct spi_device *spi = p_lm70->spi;
@@ -72,7 +73,8 @@ static ssize_t lm70_sense_temp(struct device *dev,
 	 */
 	status = spi_write_then_read(spi, NULL, 0, &rxbuf[0], 2);
 	if (status < 0) {
-		pr_warn("spi_write_then_read failed with status %d\n", status);
+		dev_warn(dev, "spi_write_then_read failed with status %d\n",
+			 status);
 		goto out;
 	}
 	raw = (rxbuf[0] << 8) + rxbuf[1];
@@ -91,7 +93,7 @@ static ssize_t lm70_sense_temp(struct device *dev,
 	 * Celsius.
 	 * So it's equivalent to multiplying by 0.25 * 1000 = 250.
 	 *
-	 * LM74 and TMP121/TMP123:
+	 * LM74 and TMP121/TMP122/TMP123/TMP124:
 	 * 13 bits of 2's complement data, discard LSB 3 bits,
 	 * resolution 0.0625 degrees celsius.
 	 *
@@ -105,6 +107,7 @@ static ssize_t lm70_sense_temp(struct device *dev,
 		break;
 
 	case LM70_CHIP_TMP121:
+	case LM70_CHIP_TMP122:
 	case LM70_CHIP_LM74:
 		val = ((int)raw / 8) * 625 / 10;
 		break;
@@ -120,7 +123,7 @@ out:
 	return status;
 }
 
-static DEVICE_ATTR(temp1_input, S_IRUGO, lm70_sense_temp, NULL);
+static DEVICE_ATTR_RO(temp1_input);
 
 static struct attribute *lm70_attrs[] = {
 	&dev_attr_temp1_input.attr,
@@ -142,6 +145,10 @@ static const struct of_device_id lm70_of_ids[] = {
 		.data = (void *) LM70_CHIP_TMP121,
 	},
 	{
+		.compatible = "ti,tmp122",
+		.data = (void *) LM70_CHIP_TMP122,
+	},
+	{
 		.compatible = "ti,lm71",
 		.data = (void *) LM70_CHIP_LM71,
 	},
@@ -190,6 +197,7 @@ static int lm70_probe(struct spi_device *spi)
 static const struct spi_device_id lm70_ids[] = {
 	{ "lm70",   LM70_CHIP_LM70 },
 	{ "tmp121", LM70_CHIP_TMP121 },
+	{ "tmp122", LM70_CHIP_TMP122 },
 	{ "lm71",   LM70_CHIP_LM71 },
 	{ "lm74",   LM70_CHIP_LM74 },
 	{ },
diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c
index 539efe4ad991..0cb7ff613b80 100644
--- a/drivers/hwmon/lm78.c
+++ b/drivers/hwmon/lm78.c
@@ -236,22 +236,23 @@ show_in_offset(5);
 show_in_offset(6);
 
 /* Temperature */
-static ssize_t show_temp(struct device *dev, struct device_attribute *da,
-			 char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *da, char *buf)
 {
 	struct lm78_data *data = lm78_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp));
 }
 
-static ssize_t show_temp_over(struct device *dev, struct device_attribute *da,
+static ssize_t temp1_max_show(struct device *dev, struct device_attribute *da,
 			      char *buf)
 {
 	struct lm78_data *data = lm78_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_over));
 }
 
-static ssize_t set_temp_over(struct device *dev, struct device_attribute *da,
-			     const char *buf, size_t count)
+static ssize_t temp1_max_store(struct device *dev,
+			       struct device_attribute *da, const char *buf,
+			       size_t count)
 {
 	struct lm78_data *data = dev_get_drvdata(dev);
 	long val;
@@ -268,15 +269,16 @@ static ssize_t set_temp_over(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-static ssize_t show_temp_hyst(struct device *dev, struct device_attribute *da,
-			      char *buf)
+static ssize_t temp1_max_hyst_show(struct device *dev,
+				   struct device_attribute *da, char *buf)
 {
 	struct lm78_data *data = lm78_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_hyst));
 }
 
-static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *da,
-			     const char *buf, size_t count)
+static ssize_t temp1_max_hyst_store(struct device *dev,
+				    struct device_attribute *da,
+				    const char *buf, size_t count)
 {
 	struct lm78_data *data = dev_get_drvdata(dev);
 	long val;
@@ -293,11 +295,9 @@ static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
-static DEVICE_ATTR(temp1_max, S_IRUGO | S_IWUSR,
-		show_temp_over, set_temp_over);
-static DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR,
-		show_temp_hyst, set_temp_hyst);
+static DEVICE_ATTR_RO(temp1_input);
+static DEVICE_ATTR_RW(temp1_max);
+static DEVICE_ATTR_RW(temp1_max_hyst);
 
 /* 3 Fans */
 static ssize_t show_fan(struct device *dev, struct device_attribute *da,
@@ -431,22 +431,22 @@ static SENSOR_DEVICE_ATTR(fan2_div, S_IRUGO | S_IWUSR,
 static SENSOR_DEVICE_ATTR(fan3_div, S_IRUGO, show_fan_div, NULL, 2);
 
 /* VID */
-static ssize_t show_vid(struct device *dev, struct device_attribute *da,
-			char *buf)
+static ssize_t cpu0_vid_show(struct device *dev, struct device_attribute *da,
+			     char *buf)
 {
 	struct lm78_data *data = lm78_update_device(dev);
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, 82));
 }
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 /* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *da,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *da,
 			   char *buf)
 {
 	struct lm78_data *data = lm78_update_device(dev);
 	return sprintf(buf, "%u\n", data->alarms);
 }
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev, struct device_attribute *da,
 			  char *buf)
diff --git a/drivers/hwmon/lm80.c b/drivers/hwmon/lm80.c
index 4bcd9b882948..08e3945a6fbf 100644
--- a/drivers/hwmon/lm80.c
+++ b/drivers/hwmon/lm80.c
@@ -432,7 +432,7 @@ static ssize_t set_temp(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct lm80_data *data = lm80_update_device(dev);
@@ -505,7 +505,7 @@ static SENSOR_DEVICE_ATTR(temp1_crit, S_IWUSR | S_IRUGO, show_temp,
 		set_temp, t_os_max);
 static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IWUSR | S_IRUGO, show_temp,
 		set_temp, t_os_hyst);
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
 static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
 static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2);
diff --git a/drivers/hwmon/lm83.c b/drivers/hwmon/lm83.c
index 9e4d0e1d3c4b..cbfd0bb7f135 100644
--- a/drivers/hwmon/lm83.c
+++ b/drivers/hwmon/lm83.c
@@ -188,7 +188,7 @@ static ssize_t set_temp(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-static ssize_t show_alarms(struct device *dev, struct device_attribute *dummy,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *dummy,
 			   char *buf)
 {
 	struct lm83_data *data = lm83_update_device(dev);
@@ -236,7 +236,7 @@ static SENSOR_DEVICE_ATTR(temp4_max_alarm, S_IRUGO, show_alarm, NULL, 12);
 static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 13);
 static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 15);
 /* Raw alarm file for compatibility */
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static struct attribute *lm83_attributes[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index 29c8136ce9c5..691469ffa24e 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -604,8 +604,8 @@ show_fan_offset(4);
 
 /* vid, vrm, alarms */
 
-static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct lm85_data *data = lm85_update_device(dev);
 	int vid;
@@ -621,17 +621,17 @@ static ssize_t show_vid_reg(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", vid);
 }
 
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
-static ssize_t show_vrm_reg(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	struct lm85_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%ld\n", (long) data->vrm);
 }
 
-static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct lm85_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -648,16 +648,16 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
 
-static ssize_t show_alarms_reg(struct device *dev, struct device_attribute
-		*attr, char *buf)
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%u\n", data->alarms);
 }
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 		char *buf)
diff --git a/drivers/hwmon/lm87.c b/drivers/hwmon/lm87.c
index 13cca3606e06..e06faf9d3f0f 100644
--- a/drivers/hwmon/lm87.c
+++ b/drivers/hwmon/lm87.c
@@ -445,23 +445,23 @@ set_temp(1);
 set_temp(2);
 set_temp(3);
 
-static ssize_t show_temp_crit_int(struct device *dev,
-				  struct device_attribute *attr, char *buf)
+static ssize_t temp1_crit_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_crit_int));
 }
 
-static ssize_t show_temp_crit_ext(struct device *dev,
-				  struct device_attribute *attr, char *buf)
+static ssize_t temp2_crit_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_crit_ext));
 }
 
-static DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp_crit_int, NULL);
-static DEVICE_ATTR(temp2_crit, S_IRUGO, show_temp_crit_ext, NULL);
-static DEVICE_ATTR(temp3_crit, S_IRUGO, show_temp_crit_ext, NULL);
+static DEVICE_ATTR_RO(temp1_crit);
+static DEVICE_ATTR_RO(temp2_crit);
+static DEVICE_ATTR(temp3_crit, S_IRUGO, temp2_crit_show, NULL);
 
 static ssize_t show_fan_input(struct device *dev,
 			      struct device_attribute *attr, char *buf)
@@ -586,30 +586,30 @@ static SENSOR_DEVICE_ATTR(fan##offset##_div, S_IRUGO | S_IWUSR, \
 set_fan(1);
 set_fan(2);
 
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	return sprintf(buf, "%d\n", data->alarms);
 }
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
-static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
-			char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
-static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
 			char *buf)
 {
 	struct lm87_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", data->vrm);
 }
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
-		       const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct lm87_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -625,16 +625,17 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 	data->vrm = val;
 	return count;
 }
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
+static DEVICE_ATTR_RW(vrm);
 
-static ssize_t show_aout(struct device *dev, struct device_attribute *attr,
-			 char *buf)
+static ssize_t aout_output_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	return sprintf(buf, "%d\n", AOUT_FROM_REG(data->aout));
 }
-static ssize_t set_aout(struct device *dev, struct device_attribute *attr,
-			const char *buf, size_t count)
+static ssize_t aout_output_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct i2c_client *client = dev_get_drvdata(dev);
 	struct lm87_data *data = i2c_get_clientdata(client);
@@ -651,7 +652,7 @@ static ssize_t set_aout(struct device *dev, struct device_attribute *attr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static DEVICE_ATTR(aout_output, S_IRUGO | S_IWUSR, show_aout, set_aout);
+static DEVICE_ATTR_RW(aout_output);
 
 static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 			  char *buf)
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index 841f2428e84a..aff5297bc2bc 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -830,7 +830,7 @@ static u16 temp_to_u16_adt7461(struct lm90_data *data, long val)
 }
 
 /* pec used for ADM1032 only */
-static ssize_t show_pec(struct device *dev, struct device_attribute *dummy,
+static ssize_t pec_show(struct device *dev, struct device_attribute *dummy,
 			char *buf)
 {
 	struct i2c_client *client = to_i2c_client(dev);
@@ -838,8 +838,8 @@ static ssize_t show_pec(struct device *dev, struct device_attribute *dummy,
 	return sprintf(buf, "%d\n", !!(client->flags & I2C_CLIENT_PEC));
 }
 
-static ssize_t set_pec(struct device *dev, struct device_attribute *dummy,
-		       const char *buf, size_t count)
+static ssize_t pec_store(struct device *dev, struct device_attribute *dummy,
+			 const char *buf, size_t count)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	long val;
@@ -863,7 +863,7 @@ static ssize_t set_pec(struct device *dev, struct device_attribute *dummy,
 	return count;
 }
 
-static DEVICE_ATTR(pec, S_IWUSR | S_IRUGO, show_pec, set_pec);
+static DEVICE_ATTR_RW(pec);
 
 static int lm90_get_temp11(struct lm90_data *data, int index)
 {
diff --git a/drivers/hwmon/lm92.c b/drivers/hwmon/lm92.c
index cfaf70b9cba7..2a91974a10bb 100644
--- a/drivers/hwmon/lm92.c
+++ b/drivers/hwmon/lm92.c
@@ -181,8 +181,8 @@ static ssize_t show_temp_hyst(struct device *dev,
 		       - TEMP_FROM_REG(data->temp[t_hyst]));
 }
 
-static ssize_t show_temp_min_hyst(struct device *dev,
-				  struct device_attribute *attr, char *buf)
+static ssize_t temp1_min_hyst_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
 {
 	struct lm92_data *data = lm92_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp[t_min])
@@ -213,7 +213,7 @@ static ssize_t set_temp_hyst(struct device *dev,
 	return count;
 }
 
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct lm92_data *data = lm92_update_device(dev);
@@ -235,11 +235,11 @@ static SENSOR_DEVICE_ATTR(temp1_crit_hyst, S_IWUSR | S_IRUGO, show_temp_hyst,
 			  set_temp_hyst, t_crit);
 static SENSOR_DEVICE_ATTR(temp1_min, S_IWUSR | S_IRUGO, show_temp, set_temp,
 			  t_min);
-static DEVICE_ATTR(temp1_min_hyst, S_IRUGO, show_temp_min_hyst, NULL);
+static DEVICE_ATTR_RO(temp1_min_hyst);
 static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO, show_temp, set_temp,
 			  t_max);
 static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IRUGO, show_temp_hyst, NULL, t_max);
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, show_alarm, NULL, 2);
 static SENSOR_DEVICE_ATTR(temp1_min_alarm, S_IRUGO, show_alarm, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 1);
diff --git a/drivers/hwmon/lm93.c b/drivers/hwmon/lm93.c
index 90bb04858117..77a0a83399b3 100644
--- a/drivers/hwmon/lm93.c
+++ b/drivers/hwmon/lm93.c
@@ -2156,7 +2156,7 @@ static SENSOR_DEVICE_ATTR(pwm2_auto_spinup_time, S_IWUSR | S_IRUGO,
 			  show_pwm_auto_spinup_time,
 			  store_pwm_auto_spinup_time, 1);
 
-static ssize_t show_pwm_auto_prochot_ramp(struct device *dev,
+static ssize_t pwm_auto_prochot_ramp_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct lm93_data *data = lm93_update_device(dev);
@@ -2164,7 +2164,7 @@ static ssize_t show_pwm_auto_prochot_ramp(struct device *dev,
 		       LM93_RAMP_FROM_REG(data->pwm_ramp_ctl >> 4 & 0x0f));
 }
 
-static ssize_t store_pwm_auto_prochot_ramp(struct device *dev,
+static ssize_t pwm_auto_prochot_ramp_store(struct device *dev,
 						struct device_attribute *attr,
 						const char *buf, size_t count)
 {
@@ -2186,11 +2186,9 @@ static ssize_t store_pwm_auto_prochot_ramp(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(pwm_auto_prochot_ramp, S_IRUGO | S_IWUSR,
-			show_pwm_auto_prochot_ramp,
-			store_pwm_auto_prochot_ramp);
+static DEVICE_ATTR_RW(pwm_auto_prochot_ramp);
 
-static ssize_t show_pwm_auto_vrdhot_ramp(struct device *dev,
+static ssize_t pwm_auto_vrdhot_ramp_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct lm93_data *data = lm93_update_device(dev);
@@ -2198,7 +2196,7 @@ static ssize_t show_pwm_auto_vrdhot_ramp(struct device *dev,
 		       LM93_RAMP_FROM_REG(data->pwm_ramp_ctl & 0x0f));
 }
 
-static ssize_t store_pwm_auto_vrdhot_ramp(struct device *dev,
+static ssize_t pwm_auto_vrdhot_ramp_store(struct device *dev,
 						struct device_attribute *attr,
 						const char *buf, size_t count)
 {
@@ -2220,9 +2218,7 @@ static ssize_t store_pwm_auto_vrdhot_ramp(struct device *dev,
 	return 0;
 }
 
-static DEVICE_ATTR(pwm_auto_vrdhot_ramp, S_IRUGO | S_IWUSR,
-			show_pwm_auto_vrdhot_ramp,
-			store_pwm_auto_vrdhot_ramp);
+static DEVICE_ATTR_RW(pwm_auto_vrdhot_ramp);
 
 static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
 			char *buf)
@@ -2378,7 +2374,7 @@ static SENSOR_DEVICE_ATTR(prochot1_interval, S_IWUSR | S_IRUGO,
 static SENSOR_DEVICE_ATTR(prochot2_interval, S_IWUSR | S_IRUGO,
 			  show_prochot_interval, store_prochot_interval, 1);
 
-static ssize_t show_prochot_override_duty_cycle(struct device *dev,
+static ssize_t prochot_override_duty_cycle_show(struct device *dev,
 						struct device_attribute *attr,
 						char *buf)
 {
@@ -2386,7 +2382,7 @@ static ssize_t show_prochot_override_duty_cycle(struct device *dev,
 	return sprintf(buf, "%d\n", data->prochot_override & 0x0f);
 }
 
-static ssize_t store_prochot_override_duty_cycle(struct device *dev,
+static ssize_t prochot_override_duty_cycle_store(struct device *dev,
 						struct device_attribute *attr,
 						const char *buf, size_t count)
 {
@@ -2408,18 +2404,16 @@ static ssize_t store_prochot_override_duty_cycle(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(prochot_override_duty_cycle, S_IRUGO | S_IWUSR,
-			show_prochot_override_duty_cycle,
-			store_prochot_override_duty_cycle);
+static DEVICE_ATTR_RW(prochot_override_duty_cycle);
 
-static ssize_t show_prochot_short(struct device *dev,
+static ssize_t prochot_short_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct lm93_data *data = lm93_update_device(dev);
 	return sprintf(buf, "%d\n", (data->config & 0x10) ? 1 : 0);
 }
 
-static ssize_t store_prochot_short(struct device *dev,
+static ssize_t prochot_short_store(struct device *dev,
 					struct device_attribute *attr,
 					const char *buf, size_t count)
 {
@@ -2442,8 +2436,7 @@ static ssize_t store_prochot_short(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(prochot_short, S_IRUGO | S_IWUSR,
-		   show_prochot_short, store_prochot_short);
+static DEVICE_ATTR_RW(prochot_short);
 
 static ssize_t show_vrdhot(struct device *dev, struct device_attribute *attr,
 				char *buf)
@@ -2457,23 +2450,23 @@ static ssize_t show_vrdhot(struct device *dev, struct device_attribute *attr,
 static SENSOR_DEVICE_ATTR(vrdhot1, S_IRUGO, show_vrdhot, NULL, 0);
 static SENSOR_DEVICE_ATTR(vrdhot2, S_IRUGO, show_vrdhot, NULL, 1);
 
-static ssize_t show_gpio(struct device *dev, struct device_attribute *attr,
+static ssize_t gpio_show(struct device *dev, struct device_attribute *attr,
 				char *buf)
 {
 	struct lm93_data *data = lm93_update_device(dev);
 	return sprintf(buf, "%d\n", LM93_GPI_FROM_REG(data->gpi));
 }
 
-static DEVICE_ATTR(gpio, S_IRUGO, show_gpio, NULL);
+static DEVICE_ATTR_RO(gpio);
 
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 				char *buf)
 {
 	struct lm93_data *data = lm93_update_device(dev);
 	return sprintf(buf, "%d\n", LM93_ALARMS_FROM_REG(data->block1));
 }
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static struct attribute *lm93_attrs[] = {
 	&sensor_dev_attr_in1_input.dev_attr.attr,
diff --git a/drivers/hwmon/lm95234.c b/drivers/hwmon/lm95234.c
index 8796de39ff9b..c7fcc9e7f57a 100644
--- a/drivers/hwmon/lm95234.c
+++ b/drivers/hwmon/lm95234.c
@@ -450,8 +450,8 @@ static ssize_t set_offset(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_interval(struct device *dev, struct device_attribute *attr,
-			     char *buf)
+static ssize_t update_interval_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
 {
 	struct lm95234_data *data = dev_get_drvdata(dev);
 	int ret = lm95234_update_device(data);
@@ -463,8 +463,9 @@ static ssize_t show_interval(struct device *dev, struct device_attribute *attr,
 		       DIV_ROUND_CLOSEST(data->interval * 1000, HZ));
 }
 
-static ssize_t set_interval(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static ssize_t update_interval_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
 {
 	struct lm95234_data *data = dev_get_drvdata(dev);
 	int ret = lm95234_update_device(data);
@@ -566,8 +567,7 @@ static SENSOR_DEVICE_ATTR(temp4_offset, S_IWUSR | S_IRUGO, show_offset,
 static SENSOR_DEVICE_ATTR(temp5_offset, S_IWUSR | S_IRUGO, show_offset,
 			  set_offset, 3);
 
-static DEVICE_ATTR(update_interval, S_IWUSR | S_IRUGO, show_interval,
-		   set_interval);
+static DEVICE_ATTR_RW(update_interval);
 
 static struct attribute *lm95234_common_attrs[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
diff --git a/drivers/hwmon/ltc4151.c b/drivers/hwmon/ltc4151.c
index 8445c9fd946b..b904cb547ffb 100644
--- a/drivers/hwmon/ltc4151.c
+++ b/drivers/hwmon/ltc4151.c
@@ -215,6 +215,7 @@ static const struct of_device_id ltc4151_match[] = {
 	{ .compatible = "lltc,ltc4151" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, ltc4151_match);
 
 /* This is the driver that will be inserted */
 static struct i2c_driver ltc4151_driver = {
diff --git a/drivers/hwmon/max1111.c b/drivers/hwmon/max1111.c
index 303d0c9df907..8ddd4d690652 100644
--- a/drivers/hwmon/max1111.c
+++ b/drivers/hwmon/max1111.c
@@ -98,7 +98,7 @@ EXPORT_SYMBOL(max1111_read_channel);
  * likely to be used by hwmon applications to distinguish between
  * different devices, explicitly add a name attribute here.
  */
-static ssize_t show_name(struct device *dev,
+static ssize_t name_show(struct device *dev,
 			 struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%s\n", to_spi_device(dev)->modalias);
@@ -125,7 +125,7 @@ static ssize_t show_adc(struct device *dev,
 #define MAX1111_ADC_ATTR(_id)		\
 	SENSOR_DEVICE_ATTR(in##_id##_input, S_IRUGO, show_adc, NULL, _id)
 
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 static MAX1111_ADC_ATTR(0);
 static MAX1111_ADC_ATTR(1);
 static MAX1111_ADC_ATTR(2);
diff --git a/drivers/hwmon/max1619.c b/drivers/hwmon/max1619.c
index eda9cf599685..a18278938494 100644
--- a/drivers/hwmon/max1619.c
+++ b/drivers/hwmon/max1619.c
@@ -173,7 +173,7 @@ static ssize_t set_temp(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct max1619_data *data = max1619_update_device(dev);
@@ -199,7 +199,7 @@ static SENSOR_DEVICE_ATTR(temp2_crit, S_IWUSR | S_IRUGO, show_temp, set_temp,
 static SENSOR_DEVICE_ATTR(temp2_crit_hyst, S_IWUSR | S_IRUGO, show_temp,
 			  set_temp, t_hyst2);
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 static SENSOR_DEVICE_ATTR(temp2_crit_alarm, S_IRUGO, show_alarm, NULL, 1);
 static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 2);
 static SENSOR_DEVICE_ATTR(temp2_min_alarm, S_IRUGO, show_alarm, NULL, 3);
diff --git a/drivers/hwmon/max197.c b/drivers/hwmon/max197.c
index 07628569547a..638567fb7cd8 100644
--- a/drivers/hwmon/max197.c
+++ b/drivers/hwmon/max197.c
@@ -207,8 +207,8 @@ unlock:
 	return ret;
 }
 
-static ssize_t max197_show_name(struct device *dev,
-				struct device_attribute *attr, char *buf)
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	return sprintf(buf, "%s\n", pdev->name);
@@ -231,7 +231,7 @@ static ssize_t max197_show_name(struct device *dev,
 	&sensor_dev_attr_in##chan##_max.dev_attr.attr,			\
 	&sensor_dev_attr_in##chan##_min.dev_attr.attr
 
-static DEVICE_ATTR(name, S_IRUGO, max197_show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 MAX197_SENSOR_DEVICE_ATTR_CH(0);
 MAX197_SENSOR_DEVICE_ATTR_CH(1);
diff --git a/drivers/hwmon/max6650.c b/drivers/hwmon/max6650.c
index a993b44ed538..65be4b19fe47 100644
--- a/drivers/hwmon/max6650.c
+++ b/drivers/hwmon/max6650.c
@@ -270,8 +270,8 @@ static ssize_t get_fan(struct device *dev, struct device_attribute *devattr,
  * controlled.
  */
 
-static ssize_t get_target(struct device *dev, struct device_attribute *devattr,
-			 char *buf)
+static ssize_t fan1_target_show(struct device *dev,
+				struct device_attribute *devattr, char *buf)
 {
 	struct max6650_data *data = max6650_update_device(dev);
 	int kscale, ktach, rpm;
@@ -318,8 +318,9 @@ static int max6650_set_target(struct max6650_data *data, unsigned long rpm)
 					 data->speed);
 }
 
-static ssize_t set_target(struct device *dev, struct device_attribute *devattr,
-			 const char *buf, size_t count)
+static ssize_t fan1_target_store(struct device *dev,
+				 struct device_attribute *devattr,
+				 const char *buf, size_t count)
 {
 	struct max6650_data *data = dev_get_drvdata(dev);
 	unsigned long rpm;
@@ -350,8 +351,8 @@ static ssize_t set_target(struct device *dev, struct device_attribute *devattr,
  * back exactly the value you have set.
  */
 
-static ssize_t get_pwm(struct device *dev, struct device_attribute *devattr,
-		       char *buf)
+static ssize_t pwm1_show(struct device *dev, struct device_attribute *devattr,
+			 char *buf)
 {
 	int pwm;
 	struct max6650_data *data = max6650_update_device(dev);
@@ -371,8 +372,9 @@ static ssize_t get_pwm(struct device *dev, struct device_attribute *devattr,
 	return sprintf(buf, "%d\n", pwm);
 }
 
-static ssize_t set_pwm(struct device *dev, struct device_attribute *devattr,
-			const char *buf, size_t count)
+static ssize_t pwm1_store(struct device *dev,
+			  struct device_attribute *devattr, const char *buf,
+			  size_t count)
 {
 	struct max6650_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -406,8 +408,8 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute *devattr,
  * 2 = Closed loop, RPM for all fans regulated by fan1 tachometer
  * 3 = Fan off
  */
-static ssize_t get_enable(struct device *dev, struct device_attribute *devattr,
-			  char *buf)
+static ssize_t pwm1_enable_show(struct device *dev,
+				struct device_attribute *devattr, char *buf)
 {
 	struct max6650_data *data = max6650_update_device(dev);
 	int mode = (data->config & MAX6650_CFG_MODE_MASK) >> 4;
@@ -416,8 +418,9 @@ static ssize_t get_enable(struct device *dev, struct device_attribute *devattr,
 	return sprintf(buf, "%d\n", sysfs_modes[mode]);
 }
 
-static ssize_t set_enable(struct device *dev, struct device_attribute *devattr,
-			  const char *buf, size_t count)
+static ssize_t pwm1_enable_store(struct device *dev,
+				 struct device_attribute *devattr,
+				 const char *buf, size_t count)
 {
 	struct max6650_data *data = dev_get_drvdata(dev);
 	unsigned long mode;
@@ -458,16 +461,17 @@ static ssize_t set_enable(struct device *dev, struct device_attribute *devattr,
  * defined for that. See the data sheet for details.
  */
 
-static ssize_t get_div(struct device *dev, struct device_attribute *devattr,
-		       char *buf)
+static ssize_t fan1_div_show(struct device *dev,
+			     struct device_attribute *devattr, char *buf)
 {
 	struct max6650_data *data = max6650_update_device(dev);
 
 	return sprintf(buf, "%d\n", DIV_FROM_REG(data->count));
 }
 
-static ssize_t set_div(struct device *dev, struct device_attribute *devattr,
-		       const char *buf, size_t count)
+static ssize_t fan1_div_store(struct device *dev,
+			      struct device_attribute *devattr,
+			      const char *buf, size_t count)
 {
 	struct max6650_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -534,10 +538,10 @@ static SENSOR_DEVICE_ATTR(fan1_input, S_IRUGO, get_fan, NULL, 0);
 static SENSOR_DEVICE_ATTR(fan2_input, S_IRUGO, get_fan, NULL, 1);
 static SENSOR_DEVICE_ATTR(fan3_input, S_IRUGO, get_fan, NULL, 2);
 static SENSOR_DEVICE_ATTR(fan4_input, S_IRUGO, get_fan, NULL, 3);
-static DEVICE_ATTR(fan1_target, S_IWUSR | S_IRUGO, get_target, set_target);
-static DEVICE_ATTR(fan1_div, S_IWUSR | S_IRUGO, get_div, set_div);
-static DEVICE_ATTR(pwm1_enable, S_IWUSR | S_IRUGO, get_enable, set_enable);
-static DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, get_pwm, set_pwm);
+static DEVICE_ATTR_RW(fan1_target);
+static DEVICE_ATTR_RW(fan1_div);
+static DEVICE_ATTR_RW(pwm1_enable);
+static DEVICE_ATTR_RW(pwm1);
 static SENSOR_DEVICE_ATTR(fan1_max_alarm, S_IRUGO, get_alarm, NULL,
 			  MAX6650_ALRM_MAX);
 static SENSOR_DEVICE_ATTR(fan1_min_alarm, S_IRUGO, get_alarm, NULL,
diff --git a/drivers/hwmon/mc13783-adc.c b/drivers/hwmon/mc13783-adc.c
index 0c02f40eb0c1..960a1db6f269 100644
--- a/drivers/hwmon/mc13783-adc.c
+++ b/drivers/hwmon/mc13783-adc.c
@@ -40,8 +40,8 @@ struct mc13783_adc_priv {
 	char name[PLATFORM_NAME_SIZE];
 };
 
-static ssize_t mc13783_adc_show_name(struct device *dev, struct device_attribute
-			      *devattr, char *buf)
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
+			 char *buf)
 {
 	struct mc13783_adc_priv *priv = dev_get_drvdata(dev);
 
@@ -111,7 +111,7 @@ static ssize_t mc13783_adc_read_gp(struct device *dev,
 	return sprintf(buf, "%u\n", val);
 }
 
-static DEVICE_ATTR(name, S_IRUGO, mc13783_adc_show_name, NULL);
+static DEVICE_ATTR_RO(name);
 static SENSOR_DEVICE_ATTR(in2_input, S_IRUGO, mc13783_adc_read_bp, NULL, 2);
 static SENSOR_DEVICE_ATTR(in5_input, S_IRUGO, mc13783_adc_read_gp, NULL, 5);
 static SENSOR_DEVICE_ATTR(in6_input, S_IRUGO, mc13783_adc_read_gp, NULL, 6);
diff --git a/drivers/hwmon/mcp3021.c b/drivers/hwmon/mcp3021.c
index 1929734c3b1d..de886f82101b 100644
--- a/drivers/hwmon/mcp3021.c
+++ b/drivers/hwmon/mcp3021.c
@@ -86,8 +86,8 @@ static inline u16 volts_from_reg(struct mcp3021_data *data, u16 val)
 	return DIV_ROUND_CLOSEST(data->vdd * val, 1 << data->output_res);
 }
 
-static ssize_t show_in_input(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in0_input_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct mcp3021_data *data = i2c_get_clientdata(client);
@@ -102,7 +102,7 @@ static ssize_t show_in_input(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", in_input);
 }
 
-static DEVICE_ATTR(in0_input, 0444, show_in_input, NULL);
+static DEVICE_ATTR_RO(in0_input);
 
 static int mcp3021_probe(struct i2c_client *client,
 				const struct i2c_device_id *id)
diff --git a/drivers/hwmon/nct6683.c b/drivers/hwmon/nct6683.c
index 559c596b24f9..8b0bc4fc06e8 100644
--- a/drivers/hwmon/nct6683.c
+++ b/drivers/hwmon/nct6683.c
@@ -979,7 +979,7 @@ static const struct sensor_template_group nct6683_pwm_template_group = {
 };
 
 static ssize_t
-show_global_beep(struct device *dev, struct device_attribute *attr, char *buf)
+beep_enable_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct nct6683_data *data = dev_get_drvdata(dev);
 	int ret;
@@ -1004,7 +1004,7 @@ error:
 }
 
 static ssize_t
-store_global_beep(struct device *dev, struct device_attribute *attr,
+beep_enable_store(struct device *dev, struct device_attribute *attr,
 		  const char *buf, size_t count)
 {
 	struct nct6683_data *data = dev_get_drvdata(dev);
@@ -1039,7 +1039,8 @@ error:
 /* Case open detection */
 
 static ssize_t
-show_caseopen(struct device *dev, struct device_attribute *attr, char *buf)
+intrusion0_alarm_show(struct device *dev, struct device_attribute *attr,
+		      char *buf)
 {
 	struct nct6683_data *data = dev_get_drvdata(dev);
 	int ret;
@@ -1064,8 +1065,8 @@ error:
 }
 
 static ssize_t
-clear_caseopen(struct device *dev, struct device_attribute *attr,
-	       const char *buf, size_t count)
+intrusion0_alarm_store(struct device *dev, struct device_attribute *attr,
+		       const char *buf, size_t count)
 {
 	struct nct6683_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -1102,10 +1103,8 @@ error:
 	return count;
 }
 
-static DEVICE_ATTR(intrusion0_alarm, S_IWUSR | S_IRUGO, show_caseopen,
-		   clear_caseopen);
-static DEVICE_ATTR(beep_enable, S_IWUSR | S_IRUGO, show_global_beep,
-		   store_global_beep);
+static DEVICE_ATTR_RW(intrusion0_alarm);
+static DEVICE_ATTR_RW(beep_enable);
 
 static struct attribute *nct6683_attributes_other[] = {
 	&dev_attr_intrusion0_alarm.attr,
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index ce75dd4db7eb..2458b406f6aa 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -3127,14 +3127,14 @@ static const struct sensor_template_group nct6775_pwm_template_group = {
 };
 
 static ssize_t
-show_vid(struct device *dev, struct device_attribute *attr, char *buf)
+cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct nct6775_data *data = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
 
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 /* Case open detection */
 
diff --git a/drivers/hwmon/nsa320-hwmon.c b/drivers/hwmon/nsa320-hwmon.c
index 0517a265741f..5a16109cdea8 100644
--- a/drivers/hwmon/nsa320-hwmon.c
+++ b/drivers/hwmon/nsa320-hwmon.c
@@ -122,8 +122,8 @@ static ssize_t show_label(struct device *dev,
 	return sprintf(buf, "%s\n", nsa320_input_names[channel]);
 }
 
-static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
-			 char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	s32 mcu_data = nsa320_hwmon_update(dev);
 
@@ -133,8 +133,8 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", (mcu_data & 0xffff) * 100);
 }
 
-static ssize_t show_fan(struct device *dev, struct device_attribute *attr,
-			char *buf)
+static ssize_t fan1_input_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	s32 mcu_data = nsa320_hwmon_update(dev);
 
@@ -145,9 +145,9 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *attr,
 }
 
 static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, show_label, NULL, NSA320_TEMP);
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
+static DEVICE_ATTR_RO(temp1_input);
 static SENSOR_DEVICE_ATTR(fan1_label, S_IRUGO, show_label, NULL, NSA320_FAN);
-static DEVICE_ATTR(fan1_input, S_IRUGO, show_fan, NULL);
+static DEVICE_ATTR_RO(fan1_input);
 
 static struct attribute *nsa320_attrs[] = {
 	&sensor_dev_attr_temp1_label.dev_attr.attr,
diff --git a/drivers/hwmon/pc87360.c b/drivers/hwmon/pc87360.c
index d50fbf93a737..7e3697727537 100644
--- a/drivers/hwmon/pc87360.c
+++ b/drivers/hwmon/pc87360.c
@@ -589,22 +589,22 @@ static struct sensor_device_attribute in_max_alarm[] = {
 	&in_min_alarm[X].dev_attr.attr,	\
 	&in_max_alarm[X].dev_attr.attr
 
-static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
-			char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct pc87360_data *data = pc87360_update_device(dev);
 	return sprintf(buf, "%u\n", vid_from_reg(data->vid, data->vrm));
 }
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
-static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
 			char *buf)
 {
 	struct pc87360_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%u\n", data->vrm);
 }
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
-		       const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct pc87360_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -620,15 +620,15 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 	data->vrm = val;
 	return count;
 }
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
+static DEVICE_ATTR_RW(vrm);
 
-static ssize_t show_in_alarms(struct device *dev,
+static ssize_t alarms_in_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
 	struct pc87360_data *data = pc87360_update_device(dev);
 	return sprintf(buf, "%u\n", data->in_alarms);
 }
-static DEVICE_ATTR(alarms_in, S_IRUGO, show_in_alarms, NULL);
+static DEVICE_ATTR_RO(alarms_in);
 
 static struct attribute *pc8736x_vin_attr_array[] = {
 	VIN_UNIT_ATTRS(0),
@@ -1006,14 +1006,14 @@ static struct sensor_device_attribute temp_crit[] = {
 		    show_temp_crit, set_temp_crit, 2),
 };
 
-static ssize_t show_temp_alarms(struct device *dev,
+static ssize_t alarms_temp_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct pc87360_data *data = pc87360_update_device(dev);
 	return sprintf(buf, "%u\n", data->temp_alarms);
 }
 
-static DEVICE_ATTR(alarms_temp, S_IRUGO, show_temp_alarms, NULL);
+static DEVICE_ATTR_RO(alarms_temp);
 
 /*
  * show_temp_min/max_alarm() reads data from the per-channel status
@@ -1106,14 +1106,14 @@ static const struct attribute_group pc8736x_temp_attr_group[] = {
 	{ .attrs = pc8736x_temp_attr[2] }
 };
 
-static ssize_t show_name(struct device *dev,
+static ssize_t name_show(struct device *dev,
 			struct device_attribute *devattr, char *buf)
 {
 	struct pc87360_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%s\n", data->name);
 }
 
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 /*
  * Device detection, registration and update
diff --git a/drivers/hwmon/pc87427.c b/drivers/hwmon/pc87427.c
index cb9fdd37bd0d..dc5a9d5ada51 100644
--- a/drivers/hwmon/pc87427.c
+++ b/drivers/hwmon/pc87427.c
@@ -943,14 +943,14 @@ static const struct attribute_group pc87427_group_temp[6] = {
 	{ .attrs = pc87427_attributes_temp[5] },
 };
 
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
 			 *devattr, char *buf)
 {
 	struct pc87427_data *data = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%s\n", data->name);
 }
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 
 /*
diff --git a/drivers/hwmon/pcf8591.c b/drivers/hwmon/pcf8591.c
index 5740888c6242..60e25c85e71c 100644
--- a/drivers/hwmon/pcf8591.c
+++ b/drivers/hwmon/pcf8591.c
@@ -103,16 +103,16 @@ show_in_channel(1);
 show_in_channel(2);
 show_in_channel(3);
 
-static ssize_t show_out0_ouput(struct device *dev,
-			       struct device_attribute *attr, char *buf)
+static ssize_t out0_output_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct pcf8591_data *data = i2c_get_clientdata(to_i2c_client(dev));
 	return sprintf(buf, "%d\n", data->aout * 10);
 }
 
-static ssize_t set_out0_output(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t count)
+static ssize_t out0_output_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	unsigned long val;
 	struct i2c_client *client = to_i2c_client(dev);
@@ -132,19 +132,18 @@ static ssize_t set_out0_output(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(out0_output, S_IWUSR | S_IRUGO,
-		   show_out0_ouput, set_out0_output);
+static DEVICE_ATTR_RW(out0_output);
 
-static ssize_t show_out0_enable(struct device *dev,
+static ssize_t out0_enable_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	struct pcf8591_data *data = i2c_get_clientdata(to_i2c_client(dev));
 	return sprintf(buf, "%u\n", !(!(data->control & PCF8591_CONTROL_AOEF)));
 }
 
-static ssize_t set_out0_enable(struct device *dev,
-			       struct device_attribute *attr,
-			       const char *buf, size_t count)
+static ssize_t out0_enable_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct pcf8591_data *data = i2c_get_clientdata(client);
@@ -165,8 +164,7 @@ static ssize_t set_out0_enable(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(out0_enable, S_IWUSR | S_IRUGO,
-		   show_out0_enable, set_out0_enable);
+static DEVICE_ATTR_RW(out0_enable);
 
 static struct attribute *pcf8591_attributes[] = {
 	&dev_attr_out0_enable.attr,
diff --git a/drivers/hwmon/sch5627.c b/drivers/hwmon/sch5627.c
index 19f85c0da270..91544f2312e6 100644
--- a/drivers/hwmon/sch5627.c
+++ b/drivers/hwmon/sch5627.c
@@ -205,7 +205,7 @@ static int reg_to_rpm(u16 reg)
 	return 5400540 / reg;
 }
 
-static ssize_t show_name(struct device *dev, struct device_attribute *devattr,
+static ssize_t name_show(struct device *dev, struct device_attribute *devattr,
 	char *buf)
 {
 	return snprintf(buf, PAGE_SIZE, "%s\n", DEVNAME);
@@ -326,7 +326,7 @@ static ssize_t show_in_label(struct device *dev, struct device_attribute
 			SCH5627_IN_LABELS[attr->index]);
 }
 
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL, 0);
 static SENSOR_DEVICE_ATTR(temp2_input, S_IRUGO, show_temp, NULL, 1);
 static SENSOR_DEVICE_ATTR(temp3_input, S_IRUGO, show_temp, NULL, 2);
diff --git a/drivers/hwmon/sch56xx-common.c b/drivers/hwmon/sch56xx-common.c
index 68c350c704fb..bda3d5285586 100644
--- a/drivers/hwmon/sch56xx-common.c
+++ b/drivers/hwmon/sch56xx-common.c
@@ -28,7 +28,6 @@
 #include <linux/delay.h>
 #include <linux/fs.h>
 #include <linux/watchdog.h>
-#include <linux/miscdevice.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 #include "sch56xx-common.h"
diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c
index a2fdbb7d20ed..e4d642b673c6 100644
--- a/drivers/hwmon/sht15.c
+++ b/drivers/hwmon/sht15.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/atomic.h>
 #include <linux/bitrev.h>
+#include <linux/of_gpio.h>
 
 /* Commands */
 #define SHT15_MEASURE_TEMP		0x03
@@ -769,7 +770,7 @@ static ssize_t sht15_show_humidity(struct device *dev,
 	return ret ? ret : sprintf(buf, "%d\n", sht15_calc_humid(data));
 }
 
-static ssize_t show_name(struct device *dev,
+static ssize_t name_show(struct device *dev,
 			 struct device_attribute *attr,
 			 char *buf)
 {
@@ -787,7 +788,7 @@ static SENSOR_DEVICE_ATTR(humidity1_fault, S_IRUGO, sht15_show_status, NULL,
 			  SHT15_STATUS_LOW_BATTERY);
 static SENSOR_DEVICE_ATTR(heater_enable, S_IRUGO | S_IWUSR, sht15_show_status,
 			  sht15_store_heater, SHT15_STATUS_HEATER);
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 static struct attribute *sht15_attrs[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
 	&sensor_dev_attr_humidity1_input.dev_attr.attr,
@@ -911,6 +912,54 @@ static int sht15_invalidate_voltage(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id sht15_dt_match[] = {
+	{ .compatible = "sensirion,sht15" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, sht15_dt_match);
+
+/*
+ * This function returns NULL if pdev isn't a device instatiated by dt,
+ * a pointer to pdata if it could successfully get all information
+ * from dt or a negative ERR_PTR() on error.
+ */
+static struct sht15_platform_data *sht15_probe_dt(struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	struct sht15_platform_data *pdata;
+
+	/* no device tree device */
+	if (!np)
+		return NULL;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return ERR_PTR(-ENOMEM);
+
+	pdata->gpio_data = of_get_named_gpio(np, "data-gpios", 0);
+	if (pdata->gpio_data < 0) {
+		if (pdata->gpio_data != -EPROBE_DEFER)
+			dev_err(dev, "data-gpios not found\n");
+		return ERR_PTR(pdata->gpio_data);
+	}
+
+	pdata->gpio_sck = of_get_named_gpio(np, "clk-gpios", 0);
+	if (pdata->gpio_sck < 0) {
+		if (pdata->gpio_sck != -EPROBE_DEFER)
+			dev_err(dev, "clk-gpios not found\n");
+		return ERR_PTR(pdata->gpio_sck);
+	}
+
+	return pdata;
+}
+#else
+static inline struct sht15_platform_data *sht15_probe_dt(struct device *dev)
+{
+	return NULL;
+}
+#endif
+
 static int sht15_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -928,11 +977,17 @@ static int sht15_probe(struct platform_device *pdev)
 	data->dev = &pdev->dev;
 	init_waitqueue_head(&data->wait_queue);
 
-	if (dev_get_platdata(&pdev->dev) == NULL) {
-		dev_err(&pdev->dev, "no platform data supplied\n");
-		return -EINVAL;
+	data->pdata = sht15_probe_dt(&pdev->dev);
+	if (IS_ERR(data->pdata))
+		return PTR_ERR(data->pdata);
+	if (data->pdata == NULL) {
+		data->pdata = dev_get_platdata(&pdev->dev);
+		if (data->pdata == NULL) {
+			dev_err(&pdev->dev, "no platform data supplied\n");
+			return -EINVAL;
+		}
 	}
-	data->pdata = dev_get_platdata(&pdev->dev);
+
 	data->supply_uv = data->pdata->supply_mv * 1000;
 	if (data->pdata->checksum)
 		data->checksumming = true;
@@ -1075,6 +1130,7 @@ MODULE_DEVICE_TABLE(platform, sht15_device_ids);
 static struct platform_driver sht15_driver = {
 	.driver = {
 		.name = "sht15",
+		.of_match_table = of_match_ptr(sht15_dt_match),
 	},
 	.probe = sht15_probe,
 	.remove = sht15_remove,
diff --git a/drivers/hwmon/sht21.c b/drivers/hwmon/sht21.c
index 84cdb1cf0fb4..06706d288355 100644
--- a/drivers/hwmon/sht21.c
+++ b/drivers/hwmon/sht21.c
@@ -34,23 +34,29 @@
 /* I2C command bytes */
 #define SHT21_TRIG_T_MEASUREMENT_HM  0xe3
 #define SHT21_TRIG_RH_MEASUREMENT_HM 0xe5
+#define SHT21_READ_SNB_CMD1 0xFA
+#define SHT21_READ_SNB_CMD2 0x0F
+#define SHT21_READ_SNAC_CMD1 0xFC
+#define SHT21_READ_SNAC_CMD2 0xC9
 
 /**
  * struct sht21 - SHT21 device specific data
  * @hwmon_dev: device registered with hwmon
  * @lock: mutex to protect measurement values
- * @valid: only 0 before first measurement is taken
  * @last_update: time of last update (jiffies)
  * @temperature: cached temperature measurement value
  * @humidity: cached humidity measurement value
+ * @valid: only 0 before first measurement is taken
+ * @eic: cached electronic identification code text
  */
 struct sht21 {
 	struct i2c_client *client;
 	struct mutex lock;
-	char valid;
 	unsigned long last_update;
 	int temperature;
 	int humidity;
+	char valid;
+	char eic[18];
 };
 
 /**
@@ -165,15 +171,97 @@ static ssize_t sht21_show_humidity(struct device *dev,
 	return sprintf(buf, "%d\n", sht21->humidity);
 }
 
+static ssize_t eic_read(struct sht21 *sht21)
+{
+	struct i2c_client *client = sht21->client;
+	u8 tx[2];
+	u8 rx[8];
+	u8 eic[8];
+	struct i2c_msg msgs[2] = {
+		{
+			.addr = client->addr,
+			.flags = 0,
+			.len = 2,
+			.buf = tx,
+		},
+		{
+			.addr = client->addr,
+			.flags = I2C_M_RD,
+			.len = 8,
+			.buf = rx,
+		},
+	};
+	int ret;
+
+	tx[0] = SHT21_READ_SNB_CMD1;
+	tx[1] = SHT21_READ_SNB_CMD2;
+	ret = i2c_transfer(client->adapter, msgs, 2);
+	if (ret < 0)
+		goto out;
+	eic[2] = rx[0];
+	eic[3] = rx[2];
+	eic[4] = rx[4];
+	eic[5] = rx[6];
+
+	tx[0] = SHT21_READ_SNAC_CMD1;
+	tx[1] = SHT21_READ_SNAC_CMD2;
+	msgs[1].len = 6;
+	ret = i2c_transfer(client->adapter, msgs, 2);
+	if (ret < 0)
+		goto out;
+	eic[0] = rx[3];
+	eic[1] = rx[4];
+	eic[6] = rx[0];
+	eic[7] = rx[1];
+
+	ret = snprintf(sht21->eic, sizeof(sht21->eic),
+		       "%02x%02x%02x%02x%02x%02x%02x%02x\n",
+		       eic[0], eic[1], eic[2], eic[3],
+		       eic[4], eic[5], eic[6], eic[7]);
+out:
+	if (ret < 0)
+		sht21->eic[0] = 0;
+
+	return ret;
+}
+
+/**
+ * eic_show() - show Electronic Identification Code in sysfs
+ * @dev: device
+ * @attr: device attribute
+ * @buf: sysfs buffer (PAGE_SIZE) where EIC is written
+ *
+ * Will be called on read access to eic sysfs attribute.
+ * Returns number of bytes written into buffer, negative errno on error.
+ */
+static ssize_t eic_show(struct device *dev,
+	struct device_attribute *attr,
+	char *buf)
+{
+	struct sht21 *sht21 = dev_get_drvdata(dev);
+	int ret;
+
+	ret = sizeof(sht21->eic) - 1;
+	mutex_lock(&sht21->lock);
+	if (!sht21->eic[0])
+		ret = eic_read(sht21);
+	if (ret > 0)
+		memcpy(buf, sht21->eic, ret);
+	mutex_unlock(&sht21->lock);
+	return ret;
+}
+
 /* sysfs attributes */
 static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, sht21_show_temperature,
 	NULL, 0);
 static SENSOR_DEVICE_ATTR(humidity1_input, S_IRUGO, sht21_show_humidity,
 	NULL, 0);
+static DEVICE_ATTR_RO(eic);
 
 static struct attribute *sht21_attrs[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
 	&sensor_dev_attr_humidity1_input.dev_attr.attr,
+	&dev_attr_eic.attr,
 	NULL
 };
 
diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c
index 45a028fb8851..6d789aab54c9 100644
--- a/drivers/hwmon/sis5595.c
+++ b/drivers/hwmon/sis5595.c
@@ -304,22 +304,23 @@ show_in_offset(3);
 show_in_offset(4);
 
 /* Temperature */
-static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
-			 char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp));
 }
 
-static ssize_t show_temp_over(struct device *dev, struct device_attribute *attr,
+static ssize_t temp1_max_show(struct device *dev, struct device_attribute *attr,
 			      char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_over));
 }
 
-static ssize_t set_temp_over(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
+static ssize_t temp1_max_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t count)
 {
 	struct sis5595_data *data = dev_get_drvdata(dev);
 	long val;
@@ -336,15 +337,16 @@ static ssize_t set_temp_over(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_temp_hyst(struct device *dev, struct device_attribute *attr,
-			      char *buf)
+static ssize_t temp1_max_hyst_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_hyst));
 }
 
-static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
+static ssize_t temp1_max_hyst_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t count)
 {
 	struct sis5595_data *data = dev_get_drvdata(dev);
 	long val;
@@ -361,11 +363,9 @@ static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL);
-static DEVICE_ATTR(temp1_max, S_IRUGO | S_IWUSR,
-		show_temp_over, set_temp_over);
-static DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR,
-		show_temp_hyst, set_temp_hyst);
+static DEVICE_ATTR_RO(temp1_input);
+static DEVICE_ATTR_RW(temp1_max);
+static DEVICE_ATTR_RW(temp1_max_hyst);
 
 /* 2 Fans */
 static ssize_t show_fan(struct device *dev, struct device_attribute *da,
@@ -492,13 +492,13 @@ show_fan_offset(1);
 show_fan_offset(2);
 
 /* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
 	return sprintf(buf, "%d\n", data->alarms);
 }
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev, struct device_attribute *da,
 			  char *buf)
@@ -516,13 +516,13 @@ static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
 static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
 static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 15);
 
-static ssize_t show_name(struct device *dev, struct device_attribute *attr,
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
 	struct sis5595_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%s\n", data->name);
 }
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static struct attribute *sis5595_attributes[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/smsc47m1.c b/drivers/hwmon/smsc47m1.c
index 5d323186d2c1..c7b6a425e2c0 100644
--- a/drivers/hwmon/smsc47m1.c
+++ b/drivers/hwmon/smsc47m1.c
@@ -264,8 +264,8 @@ static ssize_t get_pwm_en(struct device *dev, struct device_attribute
 	return sprintf(buf, "%d\n", PWM_EN_FROM_REG(data->pwm[attr->index]));
 }
 
-static ssize_t get_alarms(struct device *dev, struct device_attribute
-			  *devattr, char *buf)
+static ssize_t alarms_show(struct device *dev,
+			   struct device_attribute *devattr, char *buf)
 {
 	struct smsc47m1_data *data = smsc47m1_update_device(dev, 0);
 	return sprintf(buf, "%d\n", data->alarms);
@@ -440,16 +440,16 @@ fan_present(1);
 fan_present(2);
 fan_present(3);
 
-static DEVICE_ATTR(alarms, S_IRUGO, get_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
 			 *devattr, char *buf)
 {
 	struct smsc47m1_data *data = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%s\n", data->name);
 }
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static struct attribute *smsc47m1_attributes_fan1[] = {
 	&sensor_dev_attr_fan1_input.dev_attr.attr,
diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c
index 15650f247679..6989408033ec 100644
--- a/drivers/hwmon/smsc47m192.c
+++ b/drivers/hwmon/smsc47m192.c
@@ -400,23 +400,23 @@ show_temp_index(2)
 show_temp_index(3)
 
 /* VID */
-static ssize_t show_vid(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct smsc47m192_data *data = smsc47m192_update_device(dev);
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
-static ssize_t show_vrm(struct device *dev, struct device_attribute *attr,
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
 	struct smsc47m192_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", data->vrm);
 }
 
-static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct smsc47m192_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -431,7 +431,7 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr,
 	data->vrm = val;
 	return count;
 }
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm);
+static DEVICE_ATTR_RW(vrm);
 
 /* Alarms */
 static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
diff --git a/drivers/hwmon/stts751.c b/drivers/hwmon/stts751.c
new file mode 100644
index 000000000000..55450680fb58
--- /dev/null
+++ b/drivers/hwmon/stts751.c
@@ -0,0 +1,834 @@
+/*
+ * STTS751 sensor driver
+ *
+ * Copyright (C) 2016-2017 Istituto Italiano di Tecnologia - RBCS - EDL
+ * Robotics, Brain and Cognitive Sciences department
+ * Electronic Design Laboratory
+ *
+ * Written by Andrea Merello <andrea.merello@gmail.com>
+ *
+ * Based on  LM95241 driver and LM90 driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/err.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/property.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+#include <linux/util_macros.h>
+
+#define DEVNAME "stts751"
+
+static const unsigned short normal_i2c[] = {
+	0x48, 0x49, 0x38, 0x39,  /* STTS751-0 */
+	0x4A, 0x4B, 0x3A, 0x3B,  /* STTS751-1 */
+	I2C_CLIENT_END };
+
+#define STTS751_REG_TEMP_H	0x00
+#define STTS751_REG_STATUS	0x01
+#define STTS751_STATUS_TRIPT	BIT(0)
+#define STTS751_STATUS_TRIPL	BIT(5)
+#define STTS751_STATUS_TRIPH	BIT(6)
+#define STTS751_REG_TEMP_L	0x02
+#define STTS751_REG_CONF	0x03
+#define STTS751_CONF_RES_MASK	0x0C
+#define STTS751_CONF_RES_SHIFT  2
+#define STTS751_CONF_EVENT_DIS  BIT(7)
+#define STTS751_CONF_STOP	BIT(6)
+#define STTS751_REG_RATE	0x04
+#define STTS751_REG_HLIM_H	0x05
+#define STTS751_REG_HLIM_L	0x06
+#define STTS751_REG_LLIM_H	0x07
+#define STTS751_REG_LLIM_L	0x08
+#define STTS751_REG_TLIM	0x20
+#define STTS751_REG_HYST	0x21
+#define STTS751_REG_SMBUS_TO	0x22
+
+#define STTS751_REG_PROD_ID	0xFD
+#define STTS751_REG_MAN_ID	0xFE
+#define STTS751_REG_REV_ID	0xFF
+
+#define STTS751_0_PROD_ID	0x00
+#define STTS751_1_PROD_ID	0x01
+#define ST_MAN_ID		0x53
+
+/*
+ * Possible update intervals are (in mS):
+ * 16000, 8000, 4000, 2000, 1000, 500, 250, 125, 62.5, 31.25
+ * However we are not going to complicate things too much and we stick to the
+ * approx value in mS.
+ */
+static const int stts751_intervals[] = {
+	16000, 8000, 4000, 2000, 1000, 500, 250, 125, 63, 31
+};
+
+static const struct i2c_device_id stts751_id[] = {
+	{ "stts751", 0 },
+	{ }
+};
+
+struct stts751_priv {
+	struct device *dev;
+	struct i2c_client *client;
+	struct mutex access_lock;
+	u8 interval;
+	int res;
+	int event_max, event_min;
+	int therm;
+	int hyst;
+	bool smbus_timeout;
+	int temp;
+	unsigned long last_update, last_alert_update;
+	u8 config;
+	bool min_alert, max_alert, therm_trip;
+	bool data_valid, alert_valid;
+	bool notify_max, notify_min;
+};
+
+/*
+ * These functions converts temperature from HW format to integer format and
+ * vice-vers. They are (mostly) taken from lm90 driver. Unit is in mC.
+ */
+static int stts751_to_deg(s16 hw_val)
+{
+	return hw_val * 125 / 32;
+}
+
+static s32 stts751_to_hw(int val)
+{
+	return DIV_ROUND_CLOSEST(val, 125) * 32;
+}
+
+static int stts751_adjust_resolution(struct stts751_priv *priv)
+{
+	u8 res;
+
+	switch (priv->interval) {
+	case 9:
+		/* 10 bits */
+		res = 0;
+		break;
+	case 8:
+		/* 11 bits */
+		res = 1;
+		break;
+	default:
+		/* 12 bits */
+		res = 3;
+		break;
+	}
+
+	if (priv->res == res)
+		return 0;
+
+	priv->config &= ~STTS751_CONF_RES_MASK;
+	priv->config |= res << STTS751_CONF_RES_SHIFT;
+	dev_dbg(&priv->client->dev, "setting res %d. config %x",
+		res, priv->config);
+	priv->res = res;
+
+	return i2c_smbus_write_byte_data(priv->client,
+				STTS751_REG_CONF, priv->config);
+}
+
+static int stts751_update_temp(struct stts751_priv *priv)
+{
+	s32 integer1, integer2, frac;
+
+	/*
+	 * There is a trick here, like in the lm90 driver. We have to read two
+	 * registers to get the sensor temperature, but we have to beware a
+	 * conversion could occur between the readings. We could use the
+	 * one-shot conversion register, but we don't want to do this (disables
+	 * hardware monitoring). So the solution used here is to read the high
+	 * byte once, then the low byte, then the high byte again. If the new
+	 * high byte matches the old one, then we have a valid reading. Else we
+	 * have to read the low byte again, and now we believe we have a correct
+	 * reading.
+	 */
+	integer1 = i2c_smbus_read_byte_data(priv->client, STTS751_REG_TEMP_H);
+	if (integer1 < 0) {
+		dev_dbg(&priv->client->dev,
+			"I2C read failed (temp H). ret: %x\n", integer1);
+		return integer1;
+	}
+
+	frac = i2c_smbus_read_byte_data(priv->client, STTS751_REG_TEMP_L);
+	if (frac < 0) {
+		dev_dbg(&priv->client->dev,
+			"I2C read failed (temp L). ret: %x\n", frac);
+		return frac;
+	}
+
+	integer2 = i2c_smbus_read_byte_data(priv->client, STTS751_REG_TEMP_H);
+	if (integer2 < 0) {
+		dev_dbg(&priv->client->dev,
+			"I2C 2nd read failed (temp H). ret: %x\n", integer2);
+		return integer2;
+	}
+
+	if (integer1 != integer2) {
+		frac = i2c_smbus_read_byte_data(priv->client,
+						STTS751_REG_TEMP_L);
+		if (frac < 0) {
+			dev_dbg(&priv->client->dev,
+				"I2C 2nd read failed (temp L). ret: %x\n",
+				frac);
+			return frac;
+		}
+	}
+
+	priv->temp = stts751_to_deg((integer1 << 8) | frac);
+	return 0;
+}
+
+static int stts751_set_temp_reg16(struct stts751_priv *priv, int temp,
+				  u8 hreg, u8 lreg)
+{
+	s32 hwval;
+	int ret;
+
+	hwval = stts751_to_hw(temp);
+
+	ret = i2c_smbus_write_byte_data(priv->client, hreg, hwval >> 8);
+	if (ret)
+		return ret;
+
+	return i2c_smbus_write_byte_data(priv->client, lreg, hwval & 0xff);
+}
+
+static int stts751_set_temp_reg8(struct stts751_priv *priv, int temp, u8 reg)
+{
+	s32 hwval;
+
+	hwval = stts751_to_hw(temp);
+	return i2c_smbus_write_byte_data(priv->client, reg, hwval >> 8);
+}
+
+static int stts751_read_reg16(struct stts751_priv *priv, int *temp,
+			      u8 hreg, u8 lreg)
+{
+	int integer, frac;
+
+	integer = i2c_smbus_read_byte_data(priv->client, hreg);
+	if (integer < 0)
+		return integer;
+
+	frac = i2c_smbus_read_byte_data(priv->client, lreg);
+	if (frac < 0)
+		return frac;
+
+	*temp = stts751_to_deg((integer << 8) | frac);
+
+	return 0;
+}
+
+static int stts751_read_reg8(struct stts751_priv *priv, int *temp, u8 reg)
+{
+	int integer;
+
+	integer = i2c_smbus_read_byte_data(priv->client, reg);
+	if (integer < 0)
+		return integer;
+
+	*temp = stts751_to_deg(integer << 8);
+
+	return 0;
+}
+
+/*
+ * Update alert flags without waiting for cache to expire. We detects alerts
+ * immediately for the sake of the alert handler; we still need to deal with
+ * caching to workaround the fact that alarm flags int the status register,
+ * despite what the datasheet claims, gets always cleared on read.
+ */
+static int stts751_update_alert(struct stts751_priv *priv)
+{
+	int ret;
+	bool conv_done;
+	int cache_time = msecs_to_jiffies(stts751_intervals[priv->interval]);
+
+	/*
+	 * Add another 10% because if we run faster than the HW conversion
+	 * rate we will end up in reporting incorrectly alarms.
+	 */
+	cache_time += cache_time / 10;
+
+	ret = i2c_smbus_read_byte_data(priv->client, STTS751_REG_STATUS);
+	if (ret < 0)
+		return ret;
+
+	dev_dbg(&priv->client->dev, "status reg %x\n", ret);
+	conv_done = ret & (STTS751_STATUS_TRIPH | STTS751_STATUS_TRIPL);
+	/*
+	 * Reset the cache if the cache time expired, or if we are sure
+	 * we have valid data from a device conversion, or if we know
+	 * our cache has been never written.
+	 *
+	 * Note that when the cache has been never written the point is
+	 * to correctly initialize the timestamp, rather than clearing
+	 * the cache values.
+	 *
+	 * Note that updating the cache timestamp when we get an alarm flag
+	 * is required, otherwise we could incorrectly report alarms to be zero.
+	 */
+	if (time_after(jiffies,	priv->last_alert_update + cache_time) ||
+	    conv_done || !priv->alert_valid) {
+		priv->max_alert = false;
+		priv->min_alert = false;
+		priv->alert_valid = true;
+		priv->last_alert_update = jiffies;
+		dev_dbg(&priv->client->dev, "invalidating alert cache\n");
+	}
+
+	priv->max_alert |= !!(ret & STTS751_STATUS_TRIPH);
+	priv->min_alert |= !!(ret & STTS751_STATUS_TRIPL);
+	priv->therm_trip = !!(ret & STTS751_STATUS_TRIPT);
+
+	dev_dbg(&priv->client->dev, "max_alert: %d, min_alert: %d, therm_trip: %d\n",
+		priv->max_alert, priv->min_alert, priv->therm_trip);
+
+	return 0;
+}
+
+static void stts751_alert(struct i2c_client *client,
+			  enum i2c_alert_protocol type, unsigned int data)
+{
+	int ret;
+	struct stts751_priv *priv = i2c_get_clientdata(client);
+
+	if (type != I2C_PROTOCOL_SMBUS_ALERT)
+		return;
+
+	dev_dbg(&client->dev, "alert!");
+
+	mutex_lock(&priv->access_lock);
+	ret = stts751_update_alert(priv);
+	if (ret < 0) {
+		/* default to worst case */
+		priv->max_alert = true;
+		priv->min_alert = true;
+
+		dev_warn(priv->dev,
+			 "Alert received, but can't communicate to the device. Triggering all alarms!");
+	}
+
+	if (priv->max_alert) {
+		if (priv->notify_max)
+			dev_notice(priv->dev, "got alert for HIGH temperature");
+		priv->notify_max = false;
+
+		/* unblock alert poll */
+		sysfs_notify(&priv->dev->kobj, NULL, "temp1_max_alarm");
+	}
+
+	if (priv->min_alert) {
+		if (priv->notify_min)
+			dev_notice(priv->dev, "got alert for LOW temperature");
+		priv->notify_min = false;
+
+		/* unblock alert poll */
+		sysfs_notify(&priv->dev->kobj, NULL, "temp1_min_alarm");
+	}
+
+	if (priv->min_alert || priv->max_alert)
+		kobject_uevent(&priv->dev->kobj, KOBJ_CHANGE);
+
+	mutex_unlock(&priv->access_lock);
+}
+
+static int stts751_update(struct stts751_priv *priv)
+{
+	int ret;
+	int cache_time = msecs_to_jiffies(stts751_intervals[priv->interval]);
+
+	if (time_after(jiffies,	priv->last_update + cache_time) ||
+	    !priv->data_valid) {
+		ret = stts751_update_temp(priv);
+		if (ret)
+			return ret;
+
+		ret = stts751_update_alert(priv);
+		if (ret)
+			return ret;
+		priv->data_valid = true;
+		priv->last_update = jiffies;
+	}
+
+	return 0;
+}
+
+static ssize_t show_max_alarm(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	int ret;
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	mutex_lock(&priv->access_lock);
+	ret = stts751_update(priv);
+	if (!ret)
+		priv->notify_max = true;
+	mutex_unlock(&priv->access_lock);
+	if (ret < 0)
+		return ret;
+
+	return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->max_alert);
+}
+
+static ssize_t show_min_alarm(struct device *dev, struct device_attribute *attr,
+			      char *buf)
+{
+	int ret;
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	mutex_lock(&priv->access_lock);
+	ret = stts751_update(priv);
+	if (!ret)
+		priv->notify_min = true;
+	mutex_unlock(&priv->access_lock);
+	if (ret < 0)
+		return ret;
+
+	return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->min_alert);
+}
+
+static ssize_t show_input(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	int ret;
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	mutex_lock(&priv->access_lock);
+	ret = stts751_update(priv);
+	mutex_unlock(&priv->access_lock);
+	if (ret < 0)
+		return ret;
+
+	return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->temp);
+}
+
+static ssize_t show_therm(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->therm);
+}
+
+static ssize_t set_therm(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
+{
+	int ret;
+	long temp;
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	if (kstrtol(buf, 10, &temp) < 0)
+		return -EINVAL;
+
+	/* HW works in range -64C to +127.937C */
+	temp = clamp_val(temp, -64000, 127937);
+	mutex_lock(&priv->access_lock);
+	ret = stts751_set_temp_reg8(priv, temp, STTS751_REG_TLIM);
+	if (ret)
+		goto exit;
+
+	dev_dbg(&priv->client->dev, "setting therm %ld", temp);
+
+	/*
+	 * hysteresis reg is relative to therm, so the HW does not need to be
+	 * adjusted, we need to update our local copy only.
+	 */
+	priv->hyst = temp - (priv->therm - priv->hyst);
+	priv->therm = temp;
+
+exit:
+	mutex_unlock(&priv->access_lock);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static ssize_t show_hyst(struct device *dev, struct device_attribute *attr,
+			 char *buf)
+{
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->hyst);
+}
+
+static ssize_t set_hyst(struct device *dev, struct device_attribute *attr,
+			const char *buf, size_t count)
+{
+	int ret;
+	long temp;
+
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	if (kstrtol(buf, 10, &temp) < 0)
+		return -EINVAL;
+
+	mutex_lock(&priv->access_lock);
+	/* HW works in range -64C to +127.937C */
+	temp = clamp_val(temp, -64000, priv->therm);
+	priv->hyst = temp;
+	dev_dbg(&priv->client->dev, "setting hyst %ld", temp);
+	temp = priv->therm - temp;
+	ret = stts751_set_temp_reg8(priv, temp, STTS751_REG_HYST);
+	mutex_unlock(&priv->access_lock);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static ssize_t show_therm_trip(struct device *dev,
+			       struct device_attribute *attr, char *buf)
+{
+	int ret;
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	mutex_lock(&priv->access_lock);
+	ret = stts751_update(priv);
+	mutex_unlock(&priv->access_lock);
+	if (ret < 0)
+		return ret;
+
+	return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->therm_trip);
+}
+
+static ssize_t show_max(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->event_max);
+}
+
+static ssize_t set_max(struct device *dev, struct device_attribute *attr,
+		       const char *buf, size_t count)
+{
+	int ret;
+	long temp;
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	if (kstrtol(buf, 10, &temp) < 0)
+		return -EINVAL;
+
+	mutex_lock(&priv->access_lock);
+	/* HW works in range -64C to +127.937C */
+	temp = clamp_val(temp, priv->event_min, 127937);
+	ret = stts751_set_temp_reg16(priv, temp,
+				     STTS751_REG_HLIM_H, STTS751_REG_HLIM_L);
+	if (ret)
+		goto exit;
+
+	dev_dbg(&priv->client->dev, "setting event max %ld", temp);
+	priv->event_max = temp;
+	ret = count;
+exit:
+	mutex_unlock(&priv->access_lock);
+	return ret;
+}
+
+static ssize_t show_min(struct device *dev, struct device_attribute *attr,
+			char *buf)
+{
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE - 1, "%d\n", priv->event_min);
+}
+
+static ssize_t set_min(struct device *dev, struct device_attribute *attr,
+		       const char *buf, size_t count)
+{
+	int ret;
+	long temp;
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	if (kstrtol(buf, 10, &temp) < 0)
+		return -EINVAL;
+
+	mutex_lock(&priv->access_lock);
+	/* HW works in range -64C to +127.937C */
+	temp = clamp_val(temp, -64000, priv->event_max);
+	ret = stts751_set_temp_reg16(priv, temp,
+				     STTS751_REG_LLIM_H, STTS751_REG_LLIM_L);
+	if (ret)
+		goto exit;
+
+	dev_dbg(&priv->client->dev, "setting event min %ld", temp);
+	priv->event_min = temp;
+	ret = count;
+exit:
+	mutex_unlock(&priv->access_lock);
+	return ret;
+}
+
+static ssize_t show_interval(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE - 1, "%d\n",
+			stts751_intervals[priv->interval]);
+}
+
+static ssize_t set_interval(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	unsigned long val;
+	int idx;
+	int ret = count;
+	struct stts751_priv *priv = dev_get_drvdata(dev);
+
+	if (kstrtoul(buf, 10, &val) < 0)
+		return -EINVAL;
+
+	idx = find_closest_descending(val, stts751_intervals,
+				      ARRAY_SIZE(stts751_intervals));
+
+	dev_dbg(&priv->client->dev, "setting interval. req:%lu, idx: %d, val: %d",
+		val, idx, stts751_intervals[idx]);
+
+	mutex_lock(&priv->access_lock);
+	if (priv->interval == idx)
+		goto exit;
+
+	/*
+	 * In early development stages I've become suspicious about the chip
+	 * starting to misbehave if I ever set, even briefly, an invalid
+	 * configuration. While I'm not sure this is really needed, be
+	 * conservative and set rate/resolution in such an order that avoids
+	 * passing through an invalid configuration.
+	 */
+
+	/* speed up: lower the resolution, then modify convrate */
+	if (priv->interval < idx) {
+		dev_dbg(&priv->client->dev, "lower resolution, then modify convrate");
+		priv->interval = idx;
+		ret = stts751_adjust_resolution(priv);
+		if (ret)
+			goto exit;
+	}
+
+	ret = i2c_smbus_write_byte_data(priv->client, STTS751_REG_RATE, idx);
+	if (ret)
+		goto exit;
+	/* slow down: modify convrate, then raise resolution */
+	if (priv->interval != idx) {
+		dev_dbg(&priv->client->dev, "modify convrate, then raise resolution");
+		priv->interval = idx;
+		ret = stts751_adjust_resolution(priv);
+		if (ret)
+			goto exit;
+	}
+	ret = count;
+exit:
+	mutex_unlock(&priv->access_lock);
+
+	return ret;
+}
+
+static int stts751_detect(struct i2c_client *new_client,
+			  struct i2c_board_info *info)
+{
+	struct i2c_adapter *adapter = new_client->adapter;
+	const char *name;
+	int tmp;
+
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
+		return -ENODEV;
+
+	tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_MAN_ID);
+	if (tmp != ST_MAN_ID)
+		return -ENODEV;
+
+	/* lower temperaure registers always have bits 0-3 set to zero */
+	tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_TEMP_L);
+	if (tmp & 0xf)
+		return -ENODEV;
+
+	tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_HLIM_L);
+	if (tmp & 0xf)
+		return -ENODEV;
+
+	tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_LLIM_L);
+	if (tmp & 0xf)
+		return -ENODEV;
+
+	/* smbus timeout register always have bits 0-7 set to zero */
+	tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_SMBUS_TO);
+	if (tmp & 0x7f)
+		return -ENODEV;
+
+	tmp = i2c_smbus_read_byte_data(new_client, STTS751_REG_PROD_ID);
+
+	switch (tmp) {
+	case STTS751_0_PROD_ID:
+		name = "STTS751-0";
+		break;
+	case STTS751_1_PROD_ID:
+		name = "STTS751-1";
+		break;
+	default:
+		return -ENODEV;
+	}
+	dev_dbg(&new_client->dev, "Chip %s detected", name);
+
+	strlcpy(info->type, stts751_id[0].name, I2C_NAME_SIZE);
+	return 0;
+}
+
+static int stts751_read_chip_config(struct stts751_priv *priv)
+{
+	int ret;
+	int tmp;
+
+	ret = i2c_smbus_read_byte_data(priv->client, STTS751_REG_CONF);
+	if (ret < 0)
+		return ret;
+	priv->config = ret;
+	priv->res = (ret & STTS751_CONF_RES_MASK) >> STTS751_CONF_RES_SHIFT;
+
+	ret = i2c_smbus_read_byte_data(priv->client, STTS751_REG_RATE);
+	if (ret < 0)
+		return ret;
+	priv->interval = ret;
+
+	ret = stts751_read_reg16(priv, &priv->event_max,
+				 STTS751_REG_HLIM_H, STTS751_REG_HLIM_L);
+	if (ret)
+		return ret;
+
+	ret = stts751_read_reg16(priv, &priv->event_min,
+				 STTS751_REG_LLIM_H, STTS751_REG_LLIM_L);
+	if (ret)
+		return ret;
+
+	ret = stts751_read_reg8(priv, &priv->therm, STTS751_REG_TLIM);
+	if (ret)
+		return ret;
+
+	ret = stts751_read_reg8(priv, &tmp, STTS751_REG_HYST);
+	if (ret)
+		return ret;
+	priv->hyst = priv->therm - tmp;
+
+	return 0;
+}
+
+static SENSOR_DEVICE_ATTR(temp1_input, 0444, show_input, NULL, 0);
+static SENSOR_DEVICE_ATTR(temp1_min, 0644, show_min, set_min, 0);
+static SENSOR_DEVICE_ATTR(temp1_max, 0644, show_max, set_max, 0);
+static SENSOR_DEVICE_ATTR(temp1_min_alarm, 0444, show_min_alarm, NULL, 0);
+static SENSOR_DEVICE_ATTR(temp1_max_alarm, 0444, show_max_alarm, NULL, 0);
+static SENSOR_DEVICE_ATTR(temp1_crit, 0644, show_therm,	set_therm, 0);
+static SENSOR_DEVICE_ATTR(temp1_crit_hyst, 0644, show_hyst, set_hyst, 0);
+static SENSOR_DEVICE_ATTR(temp1_crit_alarm, 0444, show_therm_trip, NULL, 0);
+static SENSOR_DEVICE_ATTR(update_interval, 0644,
+			  show_interval, set_interval, 0);
+
+static struct attribute *stts751_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	&sensor_dev_attr_temp1_min.dev_attr.attr,
+	&sensor_dev_attr_temp1_max.dev_attr.attr,
+	&sensor_dev_attr_temp1_min_alarm.dev_attr.attr,
+	&sensor_dev_attr_temp1_max_alarm.dev_attr.attr,
+	&sensor_dev_attr_temp1_crit.dev_attr.attr,
+	&sensor_dev_attr_temp1_crit_hyst.dev_attr.attr,
+	&sensor_dev_attr_temp1_crit_alarm.dev_attr.attr,
+	&sensor_dev_attr_update_interval.dev_attr.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(stts751);
+
+static int stts751_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	struct stts751_priv *priv;
+	int ret;
+	bool smbus_nto;
+	int rev_id;
+
+	priv = devm_kzalloc(&client->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->client = client;
+	priv->notify_max = true;
+	priv->notify_min = true;
+	i2c_set_clientdata(client, priv);
+	mutex_init(&priv->access_lock);
+
+	if (device_property_present(&client->dev,
+				    "smbus-timeout-disable")) {
+		smbus_nto = device_property_read_bool(&client->dev,
+						      "smbus-timeout-disable");
+
+		ret = i2c_smbus_write_byte_data(client,	STTS751_REG_SMBUS_TO,
+						smbus_nto ? 0 : 0x80);
+		if (ret)
+			return ret;
+	}
+
+	rev_id = i2c_smbus_read_byte_data(client, STTS751_REG_REV_ID);
+	if (rev_id < 0)
+		return -ENODEV;
+	if (rev_id != 0x1) {
+		dev_dbg(&client->dev, "Chip revision 0x%x is untested\n",
+			rev_id);
+	}
+
+	ret = stts751_read_chip_config(priv);
+	if (ret)
+		return ret;
+
+	priv->config &= ~(STTS751_CONF_STOP | STTS751_CONF_EVENT_DIS);
+	ret = i2c_smbus_write_byte_data(client,	STTS751_REG_CONF, priv->config);
+	if (ret)
+		return ret;
+
+	priv->dev = devm_hwmon_device_register_with_groups(&client->dev,
+							client->name, priv,
+							stts751_groups);
+	return PTR_ERR_OR_ZERO(priv->dev);
+}
+
+MODULE_DEVICE_TABLE(i2c, stts751_id);
+
+static struct i2c_driver stts751_driver = {
+	.class		= I2C_CLASS_HWMON,
+	.driver = {
+		.name	= DEVNAME,
+	},
+	.probe		= stts751_probe,
+	.id_table	= stts751_id,
+	.detect		= stts751_detect,
+	.alert		= stts751_alert,
+	.address_list	= normal_i2c,
+};
+
+module_i2c_driver(stts751_driver);
+
+MODULE_AUTHOR("Andrea Merello <andrea.merello@gmail.com>");
+MODULE_DESCRIPTION("STTS751 sensor driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/tmp401.c b/drivers/hwmon/tmp401.c
index eeeed2c7d081..1f2d13dc9439 100644
--- a/drivers/hwmon/tmp401.c
+++ b/drivers/hwmon/tmp401.c
@@ -82,16 +82,6 @@ static const u8 TMP401_TEMP_MSB_WRITE[7][2] = {
 	{ 0, 0x11 },	/* offset */
 };
 
-static const u8 TMP401_TEMP_LSB[7][2] = {
-	{ 0x15, 0x10 },	/* temp */
-	{ 0x17, 0x14 },	/* low limit */
-	{ 0x16, 0x13 },	/* high limit */
-	{ 0, 0 },	/* therm (crit) limit (unused) */
-	{ 0x31, 0x35 },	/* lowest */
-	{ 0x33, 0x37 },	/* highest */
-	{ 0, 0x12 },	/* offset */
-};
-
 static const u8 TMP432_TEMP_MSB_READ[4][3] = {
 	{ 0x00, 0x01, 0x23 },	/* temp */
 	{ 0x06, 0x08, 0x16 },	/* low limit */
@@ -106,12 +96,6 @@ static const u8 TMP432_TEMP_MSB_WRITE[4][3] = {
 	{ 0x20, 0x19, 0x1A },	/* therm (crit) limit */
 };
 
-static const u8 TMP432_TEMP_LSB[3][3] = {
-	{ 0x29, 0x10, 0x24 },	/* temp */
-	{ 0x3E, 0x14, 0x18 },	/* low limit */
-	{ 0x3D, 0x13, 0x17 },	/* high limit */
-};
-
 /* [0] = fault, [1] = low, [2] = high, [3] = therm/crit */
 static const u8 TMP432_STATUS_REG[] = {
 	0x1b, 0x36, 0x35, 0x37 };
@@ -213,25 +197,20 @@ static int tmp401_update_device_reg16(struct i2c_client *client,
 	for (i = 0; i < num_sensors; i++) {		/* local / r1 / r2 */
 		for (j = 0; j < num_regs; j++) {	/* temp / low / ... */
 			u8 regaddr;
-			/*
-			 * High byte must be read first immediately followed
-			 * by the low byte
-			 */
+
 			regaddr = data->kind == tmp432 ?
 						TMP432_TEMP_MSB_READ[j][i] :
 						TMP401_TEMP_MSB_READ[j][i];
-			val = i2c_smbus_read_byte_data(client, regaddr);
-			if (val < 0)
-				return val;
-			data->temp[j][i] = val << 8;
-			if (j == 3)		/* crit is msb only */
-				continue;
-			regaddr = data->kind == tmp432 ? TMP432_TEMP_LSB[j][i]
-						       : TMP401_TEMP_LSB[j][i];
-			val = i2c_smbus_read_byte_data(client, regaddr);
+			if (j == 3) { /* crit is msb only */
+				val = i2c_smbus_read_byte_data(client, regaddr);
+			} else {
+				val = i2c_smbus_read_word_swapped(client,
+								  regaddr);
+			}
 			if (val < 0)
 				return val;
-			data->temp[j][i] |= val;
+
+			data->temp[j][i] = j == 3 ? val << 8 : val;
 		}
 	}
 	return 0;
@@ -373,11 +352,11 @@ static ssize_t store_temp(struct device *dev, struct device_attribute *devattr,
 
 	regaddr = data->kind == tmp432 ? TMP432_TEMP_MSB_WRITE[nr][index]
 				       : TMP401_TEMP_MSB_WRITE[nr][index];
-	i2c_smbus_write_byte_data(client, regaddr, reg >> 8);
-	if (nr != 3) {
-		regaddr = data->kind == tmp432 ? TMP432_TEMP_LSB[nr][index]
-					       : TMP401_TEMP_LSB[nr][index];
-		i2c_smbus_write_byte_data(client, regaddr, reg & 0xFF);
+	if (nr == 3) { /* crit is msb only */
+		i2c_smbus_write_byte_data(client, regaddr, reg >> 8);
+	} else {
+		/* Hardware expects big endian data --> use _swapped */
+		i2c_smbus_write_word_swapped(client, regaddr, reg);
 	}
 	data->temp[nr][index] = reg;
 
@@ -449,7 +428,7 @@ static ssize_t reset_temp_history(struct device *dev,
 	return count;
 }
 
-static ssize_t show_update_interval(struct device *dev,
+static ssize_t update_interval_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct tmp401_data *data = dev_get_drvdata(dev);
@@ -457,9 +436,9 @@ static ssize_t show_update_interval(struct device *dev,
 	return sprintf(buf, "%u\n", data->update_interval);
 }
 
-static ssize_t set_update_interval(struct device *dev,
-				   struct device_attribute *attr,
-				   const char *buf, size_t count)
+static ssize_t update_interval_store(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
 {
 	struct tmp401_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -521,8 +500,7 @@ static SENSOR_DEVICE_ATTR_2(temp2_max_alarm, S_IRUGO, show_status, NULL,
 static SENSOR_DEVICE_ATTR_2(temp2_crit_alarm, S_IRUGO, show_status, NULL,
 			    3, TMP432_STATUS_REMOTE1);
 
-static DEVICE_ATTR(update_interval, S_IRUGO | S_IWUSR, show_update_interval,
-		   set_update_interval);
+static DEVICE_ATTR_RW(update_interval);
 
 static struct attribute *tmp401_attributes[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
diff --git a/drivers/hwmon/via-cputemp.c b/drivers/hwmon/via-cputemp.c
index d1f209a5feac..07a0cb0a1f28 100644
--- a/drivers/hwmon/via-cputemp.c
+++ b/drivers/hwmon/via-cputemp.c
@@ -88,8 +88,8 @@ static ssize_t show_temp(struct device *dev,
 	return sprintf(buf, "%lu\n", ((unsigned long)eax & 0xffffff) * 1000);
 }
 
-static ssize_t show_cpu_vid(struct device *dev,
-			    struct device_attribute *devattr, char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *devattr, char *buf)
 {
 	struct via_cputemp_data *data = dev_get_drvdata(dev);
 	u32 eax, edx;
@@ -119,7 +119,7 @@ static const struct attribute_group via_cputemp_group = {
 };
 
 /* Optional attributes */
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_cpu_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 static int via_cputemp_probe(struct platform_device *pdev)
 {
diff --git a/drivers/hwmon/via686a.c b/drivers/hwmon/via686a.c
index 40dd93c8f9f4..81f35e3a06b8 100644
--- a/drivers/hwmon/via686a.c
+++ b/drivers/hwmon/via686a.c
@@ -580,14 +580,14 @@ show_fan_offset(1);
 show_fan_offset(2);
 
 /* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct via686a_data *data = via686a_update_device(dev);
 	return sprintf(buf, "%u\n", data->alarms);
 }
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 			  char *buf)
@@ -607,13 +607,13 @@ static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 15);
 static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
 static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
 
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
 			 *devattr, char *buf)
 {
 	struct via686a_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%s\n", data->name);
 }
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static struct attribute *via686a_attributes[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/vt8231.c b/drivers/hwmon/vt8231.c
index cb69a8c2ed5b..367b5eb53fb6 100644
--- a/drivers/hwmon/vt8231.c
+++ b/drivers/hwmon/vt8231.c
@@ -263,8 +263,8 @@ static ssize_t set_in_max(struct device *dev, struct device_attribute *attr,
 }
 
 /* Special case for input 5 as this has 3.3V scaling built into the chip */
-static ssize_t show_in5(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in5_input_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	struct vt8231_data *data = vt8231_update_device(dev);
 
@@ -272,7 +272,7 @@ static ssize_t show_in5(struct device *dev, struct device_attribute *attr,
 		(((data->in[5] - 3) * 10000 * 54) / (958 * 34)));
 }
 
-static ssize_t show_in5_min(struct device *dev, struct device_attribute *attr,
+static ssize_t in5_min_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
 	struct vt8231_data *data = vt8231_update_device(dev);
@@ -281,7 +281,7 @@ static ssize_t show_in5_min(struct device *dev, struct device_attribute *attr,
 		(((data->in_min[5] - 3) * 10000 * 54) / (958 * 34)));
 }
 
-static ssize_t show_in5_max(struct device *dev, struct device_attribute *attr,
+static ssize_t in5_max_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
 	struct vt8231_data *data = vt8231_update_device(dev);
@@ -290,8 +290,9 @@ static ssize_t show_in5_max(struct device *dev, struct device_attribute *attr,
 		(((data->in_max[5] - 3) * 10000 * 54) / (958 * 34)));
 }
 
-static ssize_t set_in5_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t in5_min_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct vt8231_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -309,8 +310,9 @@ static ssize_t set_in5_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t set_in5_max(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t in5_max_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct vt8231_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -342,34 +344,35 @@ define_voltage_sysfs(2);
 define_voltage_sysfs(3);
 define_voltage_sysfs(4);
 
-static DEVICE_ATTR(in5_input, S_IRUGO, show_in5, NULL);
-static DEVICE_ATTR(in5_min, S_IRUGO | S_IWUSR, show_in5_min, set_in5_min);
-static DEVICE_ATTR(in5_max, S_IRUGO | S_IWUSR, show_in5_max, set_in5_max);
+static DEVICE_ATTR_RO(in5_input);
+static DEVICE_ATTR_RW(in5_min);
+static DEVICE_ATTR_RW(in5_max);
 
 /* Temperatures */
-static ssize_t show_temp0(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp1_input_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct vt8231_data *data = vt8231_update_device(dev);
 	return sprintf(buf, "%d\n", data->temp[0] * 250);
 }
 
-static ssize_t show_temp0_max(struct device *dev, struct device_attribute *attr,
+static ssize_t temp1_max_show(struct device *dev, struct device_attribute *attr,
 		char *buf)
 {
 	struct vt8231_data *data = vt8231_update_device(dev);
 	return sprintf(buf, "%d\n", data->temp_max[0] * 1000);
 }
 
-static ssize_t show_temp0_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp1_max_hyst_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
 {
 	struct vt8231_data *data = vt8231_update_device(dev);
 	return sprintf(buf, "%d\n", data->temp_min[0] * 1000);
 }
 
-static ssize_t set_temp0_max(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp1_max_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t count)
 {
 	struct vt8231_data *data = dev_get_drvdata(dev);
 	long val;
@@ -385,8 +388,9 @@ static ssize_t set_temp0_max(struct device *dev, struct device_attribute *attr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t set_temp0_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp1_max_hyst_store(struct device *dev,
+				    struct device_attribute *attr,
+				    const char *buf, size_t count)
 {
 	struct vt8231_data *data = dev_get_drvdata(dev);
 	long val;
@@ -481,10 +485,9 @@ static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IRUGO | S_IWUSR,	\
 static SENSOR_DEVICE_ATTR(temp##offset##_max_hyst, S_IRUGO | S_IWUSR,	\
 		show_temp_min, set_temp_min, offset - 1)
 
-static DEVICE_ATTR(temp1_input, S_IRUGO, show_temp0, NULL);
-static DEVICE_ATTR(temp1_max, S_IRUGO | S_IWUSR, show_temp0_max, set_temp0_max);
-static DEVICE_ATTR(temp1_max_hyst, S_IRUGO | S_IWUSR, show_temp0_min,
-		   set_temp0_min);
+static DEVICE_ATTR_RO(temp1_input);
+static DEVICE_ATTR_RW(temp1_max);
+static DEVICE_ATTR_RW(temp1_max_hyst);
 
 define_temperature_sysfs(2);
 define_temperature_sysfs(3);
@@ -603,13 +606,13 @@ define_fan_sysfs(1);
 define_fan_sysfs(2);
 
 /* Alarms */
-static ssize_t show_alarms(struct device *dev, struct device_attribute *attr,
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
 {
 	struct vt8231_data *data = vt8231_update_device(dev);
 	return sprintf(buf, "%d\n", data->alarms);
 }
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 			  char *buf)
@@ -633,13 +636,13 @@ static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 2);
 static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
 static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
 
-static ssize_t show_name(struct device *dev, struct device_attribute
+static ssize_t name_show(struct device *dev, struct device_attribute
 			 *devattr, char *buf)
 {
 	struct vt8231_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%s\n", data->name);
 }
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static struct attribute *vt8231_attributes_temps[6][5] = {
 	{
diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c
index 697007afb99c..ab346ed142de 100644
--- a/drivers/hwmon/w83627ehf.c
+++ b/drivers/hwmon/w83627ehf.c
@@ -1687,14 +1687,14 @@ store_##reg(struct device *dev, struct device_attribute *attr, \
 
 fan_time_functions(fan_stop_time, FAN_STOP_TIME)
 
-static ssize_t show_name(struct device *dev, struct device_attribute *attr,
+static ssize_t name_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
 	struct w83627ehf_data *data = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%s\n", data->name);
 }
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static struct sensor_device_attribute sda_sf3_arrays_fan4[] = {
 	SENSOR_ATTR(pwm4_stop_time, S_IWUSR | S_IRUGO, show_fan_stop_time,
@@ -1754,12 +1754,12 @@ static struct sensor_device_attribute sda_sf3_max_step_arrays[] = {
 };
 
 static ssize_t
-show_vid(struct device *dev, struct device_attribute *attr, char *buf)
+cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83627ehf_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 
 /* Case open detection */
diff --git a/drivers/hwmon/w83627hf.c b/drivers/hwmon/w83627hf.c
index 721295b9a051..8ac89d0781cc 100644
--- a/drivers/hwmon/w83627hf.c
+++ b/drivers/hwmon/w83627hf.c
@@ -575,26 +575,30 @@ static ssize_t show_in_0(struct w83627hf_data *data, char *buf, u8 reg)
 	return sprintf(buf,"%ld\n", in0);
 }
 
-static ssize_t show_regs_in_0(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t in0_input_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	return show_in_0(data, buf, data->in[0]);
 }
 
-static ssize_t show_regs_in_min0(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t in0_min_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	return show_in_0(data, buf, data->in_min[0]);
 }
 
-static ssize_t show_regs_in_max0(struct device *dev, struct device_attribute *attr, char *buf)
+static ssize_t in0_max_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	return show_in_0(data, buf, data->in_max[0]);
 }
 
-static ssize_t store_regs_in_min0(struct device *dev, struct device_attribute *attr,
-	const char *buf, size_t count)
+static ssize_t in0_min_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct w83627hf_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -622,8 +626,9 @@ static ssize_t store_regs_in_min0(struct device *dev, struct device_attribute *a
 	return count;
 }
 
-static ssize_t store_regs_in_max0(struct device *dev, struct device_attribute *attr,
-	const char *buf, size_t count)
+static ssize_t in0_max_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct w83627hf_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -651,11 +656,9 @@ static ssize_t store_regs_in_max0(struct device *dev, struct device_attribute *a
 	return count;
 }
 
-static DEVICE_ATTR(in0_input, S_IRUGO, show_regs_in_0, NULL);
-static DEVICE_ATTR(in0_min, S_IRUGO | S_IWUSR,
-	show_regs_in_min0, store_regs_in_min0);
-static DEVICE_ATTR(in0_max, S_IRUGO | S_IWUSR,
-	show_regs_in_max0, store_regs_in_max0);
+static DEVICE_ATTR_RO(in0_input);
+static DEVICE_ATTR_RW(in0_min);
+static DEVICE_ATTR_RW(in0_max);
 
 static ssize_t
 show_fan_input(struct device *dev, struct device_attribute *devattr, char *buf)
@@ -796,21 +799,22 @@ sysfs_temp_decl(2);
 sysfs_temp_decl(3);
 
 static ssize_t
-show_vid_reg(struct device *dev, struct device_attribute *attr, char *buf)
+cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	return sprintf(buf, "%ld\n", (long) vid_from_reg(data->vid, data->vrm));
 }
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 static ssize_t
-show_vrm_reg(struct device *dev, struct device_attribute *attr, char *buf)
+vrm_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83627hf_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%ld\n", (long) data->vrm);
 }
 static ssize_t
-store_vrm_reg(struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
+vrm_store(struct device *dev, struct device_attribute *attr, const char *buf,
+	  size_t count)
 {
 	struct w83627hf_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -826,15 +830,15 @@ store_vrm_reg(struct device *dev, struct device_attribute *attr, const char *buf
 
 	return count;
 }
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
 
 static ssize_t
-show_alarms_reg(struct device *dev, struct device_attribute *attr, char *buf)
+alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	return sprintf(buf, "%ld\n", (long) data->alarms);
 }
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t
 show_alarm(struct device *dev, struct device_attribute *attr, char *buf)
@@ -860,7 +864,7 @@ static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5);
 static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 13);
 
 static ssize_t
-show_beep_mask(struct device *dev, struct device_attribute *attr, char *buf)
+beep_mask_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	return sprintf(buf, "%ld\n",
@@ -868,7 +872,7 @@ show_beep_mask(struct device *dev, struct device_attribute *attr, char *buf)
 }
 
 static ssize_t
-store_beep_mask(struct device *dev, struct device_attribute *attr,
+beep_mask_store(struct device *dev, struct device_attribute *attr,
 		const char *buf, size_t count)
 {
 	struct w83627hf_data *data = dev_get_drvdata(dev);
@@ -895,8 +899,7 @@ store_beep_mask(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(beep_mask, S_IRUGO | S_IWUSR,
-		   show_beep_mask, store_beep_mask);
+static DEVICE_ATTR_RW(beep_mask);
 
 static ssize_t
 show_beep(struct device *dev, struct device_attribute *attr, char *buf)
@@ -1264,13 +1267,13 @@ sysfs_temp_type(2);
 sysfs_temp_type(3);
 
 static ssize_t
-show_name(struct device *dev, struct device_attribute *devattr, char *buf)
+name_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	struct w83627hf_data *data = dev_get_drvdata(dev);
 
 	return sprintf(buf, "%s\n", data->name);
 }
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static int __init w83627hf_find(int sioaddr, unsigned short *addr,
 				struct w83627hf_sio_data *sio_data)
diff --git a/drivers/hwmon/w83781d.c b/drivers/hwmon/w83781d.c
index 54848fdd181e..246fb2365126 100644
--- a/drivers/hwmon/w83781d.c
+++ b/drivers/hwmon/w83781d.c
@@ -416,24 +416,24 @@ sysfs_temp_offsets(2);
 sysfs_temp_offsets(3);
 
 static ssize_t
-show_vid_reg(struct device *dev, struct device_attribute *attr, char *buf)
+cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83781d_data *data = w83781d_update_device(dev);
 	return sprintf(buf, "%ld\n", (long) vid_from_reg(data->vid, data->vrm));
 }
 
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
 static ssize_t
-show_vrm_reg(struct device *dev, struct device_attribute *attr, char *buf)
+vrm_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83781d_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%ld\n", (long) data->vrm);
 }
 
 static ssize_t
-store_vrm_reg(struct device *dev, struct device_attribute *attr,
-	      const char *buf, size_t count)
+vrm_store(struct device *dev, struct device_attribute *attr, const char *buf,
+	  size_t count)
 {
 	struct w83781d_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -447,16 +447,16 @@ store_vrm_reg(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
 
 static ssize_t
-show_alarms_reg(struct device *dev, struct device_attribute *attr, char *buf)
+alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83781d_data *data = w83781d_update_device(dev);
 	return sprintf(buf, "%u\n", data->alarms);
 }
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 		char *buf)
@@ -491,7 +491,7 @@ static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 4);
 static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5);
 static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_temp3_alarm, NULL, 0);
 
-static ssize_t show_beep_mask(struct device *dev,
+static ssize_t beep_mask_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	struct w83781d_data *data = w83781d_update_device(dev);
@@ -500,7 +500,7 @@ static ssize_t show_beep_mask(struct device *dev,
 }
 
 static ssize_t
-store_beep_mask(struct device *dev, struct device_attribute *attr,
+beep_mask_store(struct device *dev, struct device_attribute *attr,
 		const char *buf, size_t count)
 {
 	struct w83781d_data *data = dev_get_drvdata(dev);
@@ -527,8 +527,7 @@ store_beep_mask(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static DEVICE_ATTR(beep_mask, S_IRUGO | S_IWUSR,
-		show_beep_mask, store_beep_mask);
+static DEVICE_ATTR_RW(beep_mask);
 
 static ssize_t show_beep(struct device *dev, struct device_attribute *attr,
 		char *buf)
@@ -708,7 +707,7 @@ show_pwm(struct device *dev, struct device_attribute *da, char *buf)
 }
 
 static ssize_t
-show_pwm2_enable(struct device *dev, struct device_attribute *da, char *buf)
+pwm2_enable_show(struct device *dev, struct device_attribute *da, char *buf)
 {
 	struct w83781d_data *data = w83781d_update_device(dev);
 	return sprintf(buf, "%d\n", (int)data->pwm2_enable);
@@ -736,7 +735,7 @@ store_pwm(struct device *dev, struct device_attribute *da, const char *buf,
 }
 
 static ssize_t
-store_pwm2_enable(struct device *dev, struct device_attribute *da,
+pwm2_enable_store(struct device *dev, struct device_attribute *da,
 		const char *buf, size_t count)
 {
 	struct w83781d_data *data = dev_get_drvdata(dev);
@@ -778,8 +777,7 @@ static SENSOR_DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 1);
 static SENSOR_DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 2);
 static SENSOR_DEVICE_ATTR(pwm4, S_IRUGO | S_IWUSR, show_pwm, store_pwm, 3);
 /* only PWM2 can be enabled/disabled */
-static DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR,
-		show_pwm2_enable, store_pwm2_enable);
+static DEVICE_ATTR_RW(pwm2_enable);
 
 static ssize_t
 show_sensor(struct device *dev, struct device_attribute *da, char *buf)
@@ -1616,12 +1614,12 @@ static unsigned short isa_address = 0x290;
  * we must create it by ourselves.
  */
 static ssize_t
-show_name(struct device *dev, struct device_attribute *devattr, char *buf)
+name_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	struct w83781d_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%s\n", data->name);
 }
-static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+static DEVICE_ATTR_RO(name);
 
 static struct w83781d_data *w83781d_data_if_isa(void)
 {
diff --git a/drivers/hwmon/w83791d.c b/drivers/hwmon/w83791d.c
index 001df856913f..8af6081b4ab4 100644
--- a/drivers/hwmon/w83791d.c
+++ b/drivers/hwmon/w83791d.c
@@ -1041,14 +1041,14 @@ static struct sensor_device_attribute sda_temp_alarm[] = {
 };
 
 /* get realtime status of all sensors items: voltage, temp, fan */
-static ssize_t show_alarms_reg(struct device *dev,
-				struct device_attribute *attr, char *buf)
+static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct w83791d_data *data = w83791d_update_device(dev);
 	return sprintf(buf, "%u\n", data->alarms);
 }
 
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
 
 /* Beep control */
 
@@ -1147,25 +1147,24 @@ static struct sensor_device_attribute sda_beep_ctrl[] = {
 };
 
 /* cpu voltage regulation information */
-static ssize_t show_vid_reg(struct device *dev,
-				struct device_attribute *attr, char *buf)
+static ssize_t cpu0_vid_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct w83791d_data *data = w83791d_update_device(dev);
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
 
-static DEVICE_ATTR(cpu0_vid, S_IRUGO, show_vid_reg, NULL);
+static DEVICE_ATTR_RO(cpu0_vid);
 
-static ssize_t show_vrm_reg(struct device *dev,
-				struct device_attribute *attr, char *buf)
+static ssize_t vrm_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	struct w83791d_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", data->vrm);
 }
 
-static ssize_t store_vrm_reg(struct device *dev,
-				struct device_attribute *attr,
-				const char *buf, size_t count)
+static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct w83791d_data *data = dev_get_drvdata(dev);
 	unsigned long val;
@@ -1188,7 +1187,7 @@ static ssize_t store_vrm_reg(struct device *dev,
 	return count;
 }
 
-static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm_reg, store_vrm_reg);
+static DEVICE_ATTR_RW(vrm);
 
 #define IN_UNIT_ATTRS(X) \
 	&sda_in_input[X].dev_attr.attr,	\
diff --git a/drivers/hwmon/w83792d.c b/drivers/hwmon/w83792d.c
index 0a8bce726b4b..d764602d70db 100644
--- a/drivers/hwmon/w83792d.c
+++ b/drivers/hwmon/w83792d.c
@@ -578,7 +578,7 @@ static ssize_t store_temp23(struct device *dev, struct device_attribute *attr,
 
 /* get realtime status of all sensors items: voltage, temp, fan */
 static ssize_t
-show_alarms_reg(struct device *dev, struct device_attribute *attr, char *buf)
+alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83792d_data *data = w83792d_update_device(dev);
 	return sprintf(buf, "%d\n", data->alarms);
@@ -735,16 +735,16 @@ store_pwm_mode(struct device *dev, struct device_attribute *attr,
 }
 
 static ssize_t
-show_chassis_clear(struct device *dev, struct device_attribute *attr,
-			char *buf)
+intrusion0_alarm_show(struct device *dev, struct device_attribute *attr,
+		      char *buf)
 {
 	struct w83792d_data *data = w83792d_update_device(dev);
 	return sprintf(buf, "%d\n", data->chassis);
 }
 
 static ssize_t
-store_chassis_clear(struct device *dev, struct device_attribute *attr,
-			const char *buf, size_t count)
+intrusion0_alarm_store(struct device *dev, struct device_attribute *attr,
+		       const char *buf, size_t count)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct w83792d_data *data = i2c_get_clientdata(client);
@@ -1047,7 +1047,7 @@ static SENSOR_DEVICE_ATTR_2(temp2_max_hyst, S_IRUGO | S_IWUSR,
 			show_temp23, store_temp23, 0, 4);
 static SENSOR_DEVICE_ATTR_2(temp3_max_hyst, S_IRUGO | S_IWUSR,
 			show_temp23, store_temp23, 1, 4);
-static DEVICE_ATTR(alarms, S_IRUGO, show_alarms_reg, NULL);
+static DEVICE_ATTR_RO(alarms);
 static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
 static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
 static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 2);
@@ -1067,8 +1067,7 @@ static SENSOR_DEVICE_ATTR(in8_alarm, S_IRUGO, show_alarm, NULL, 20);
 static SENSOR_DEVICE_ATTR(fan4_alarm, S_IRUGO, show_alarm, NULL, 21);
 static SENSOR_DEVICE_ATTR(fan5_alarm, S_IRUGO, show_alarm, NULL, 22);
 static SENSOR_DEVICE_ATTR(fan6_alarm, S_IRUGO, show_alarm, NULL, 23);
-static DEVICE_ATTR(intrusion0_alarm, S_IRUGO | S_IWUSR,
-			show_chassis_clear, store_chassis_clear);
+static DEVICE_ATTR_RW(intrusion0_alarm);
 static SENSOR_DEVICE_ATTR(pwm1, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 0);
 static SENSOR_DEVICE_ATTR(pwm2, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 1);
 static SENSOR_DEVICE_ATTR(pwm3, S_IWUSR | S_IRUGO, show_pwm, store_pwm, 2);
diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c
index 816aa6caf5d5..dab5c515d5a3 100644
--- a/drivers/hwmon/w83793.c
+++ b/drivers/hwmon/w83793.c
@@ -324,7 +324,7 @@ static struct i2c_driver w83793_driver = {
 };
 
 static ssize_t
-show_vrm(struct device *dev, struct device_attribute *attr, char *buf)
+vrm_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83793_data *data = dev_get_drvdata(dev);
 	return sprintf(buf, "%d\n", data->vrm);
@@ -342,7 +342,7 @@ show_vid(struct device *dev, struct device_attribute *attr, char *buf)
 }
 
 static ssize_t
-store_vrm(struct device *dev, struct device_attribute *attr,
+vrm_store(struct device *dev, struct device_attribute *attr,
 	  const char *buf, size_t count)
 {
 	struct w83793_data *data = dev_get_drvdata(dev);
@@ -1169,7 +1169,7 @@ static struct sensor_device_attribute_2 w83793_vid[] = {
 	SENSOR_ATTR_2(cpu0_vid, S_IRUGO, show_vid, NULL, NOT_USED, 0),
 	SENSOR_ATTR_2(cpu1_vid, S_IRUGO, show_vid, NULL, NOT_USED, 1),
 };
-static DEVICE_ATTR(vrm, S_IWUSR | S_IRUGO, show_vrm, store_vrm);
+static DEVICE_ATTR_RW(vrm);
 
 static struct sensor_device_attribute_2 sda_single_files[] = {
 	SENSOR_ATTR_2(intrusion0_alarm, S_IWUSR | S_IRUGO, show_alarm_beep,
diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c
index 686971263bef..45d6771fac8c 100644
--- a/drivers/i2c/busses/i2c-cadence.c
+++ b/drivers/i2c/busses/i2c-cadence.c
@@ -962,10 +962,6 @@ static int cdns_i2c_probe(struct platform_device *pdev)
 		goto err_clk_dis;
 	}
 
-	ret = i2c_add_adapter(&id->adap);
-	if (ret < 0)
-		goto err_clk_dis;
-
 	/*
 	 * Cadence I2C controller has a bug wherein it generates
 	 * invalid read transaction after HW timeout in master receiver mode.
@@ -975,6 +971,10 @@ static int cdns_i2c_probe(struct platform_device *pdev)
 	 */
 	cdns_i2c_writereg(CDNS_I2C_TIMEOUT_MAX, CDNS_I2C_TIME_OUT_OFFSET);
 
+	ret = i2c_add_adapter(&id->adap);
+	if (ret < 0)
+		goto err_clk_dis;
+
 	dev_info(&pdev->dev, "%u kHz mmio %08lx irq %d\n",
 		 id->i2c_clk / 1000, (unsigned long)r_mem->start, id->irq);
 
diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c
index 6d81c56184d3..e9db857c6226 100644
--- a/drivers/i2c/busses/i2c-designware-core.c
+++ b/drivers/i2c/busses/i2c-designware-core.c
@@ -475,30 +475,28 @@ static int i2c_dw_wait_bus_not_busy(struct dw_i2c_dev *dev)
 static void i2c_dw_xfer_init(struct dw_i2c_dev *dev)
 {
 	struct i2c_msg *msgs = dev->msgs;
-	u32 ic_tar = 0;
+	u32 ic_con, ic_tar = 0;
 
 	/* Disable the adapter */
 	__i2c_dw_enable_and_wait(dev, false);
 
 	/* if the slave address is ten bit address, enable 10BITADDR */
-	if (dev->dynamic_tar_update_enabled) {
+	ic_con = dw_readl(dev, DW_IC_CON);
+	if (msgs[dev->msg_write_idx].flags & I2C_M_TEN) {
+		ic_con |= DW_IC_CON_10BITADDR_MASTER;
 		/*
 		 * If I2C_DYNAMIC_TAR_UPDATE is set, the 10-bit addressing
-		 * mode has to be enabled via bit 12 of IC_TAR register,
-		 * otherwise bit 4 of IC_CON is used.
+		 * mode has to be enabled via bit 12 of IC_TAR register.
+		 * We set it always as I2C_DYNAMIC_TAR_UPDATE can't be
+		 * detected from registers.
 		 */
-		if (msgs[dev->msg_write_idx].flags & I2C_M_TEN)
-			ic_tar = DW_IC_TAR_10BITADDR_MASTER;
+		ic_tar = DW_IC_TAR_10BITADDR_MASTER;
 	} else {
-		u32 ic_con = dw_readl(dev, DW_IC_CON);
-
-		if (msgs[dev->msg_write_idx].flags & I2C_M_TEN)
-			ic_con |= DW_IC_CON_10BITADDR_MASTER;
-		else
-			ic_con &= ~DW_IC_CON_10BITADDR_MASTER;
-		dw_writel(dev, ic_con, DW_IC_CON);
+		ic_con &= ~DW_IC_CON_10BITADDR_MASTER;
 	}
 
+	dw_writel(dev, ic_con, DW_IC_CON);
+
 	/*
 	 * Set the slave (target) address and enable 10-bit addressing mode
 	 * if applicable.
@@ -963,7 +961,6 @@ int i2c_dw_probe(struct dw_i2c_dev *dev)
 {
 	struct i2c_adapter *adap = &dev->adapter;
 	int r;
-	u32 reg;
 
 	init_completion(&dev->cmd_complete);
 
@@ -971,26 +968,6 @@ int i2c_dw_probe(struct dw_i2c_dev *dev)
 	if (r)
 		return r;
 
-	r = i2c_dw_acquire_lock(dev);
-	if (r)
-		return r;
-
-	/*
-	 * Test if dynamic TAR update is enabled in this controller by writing
-	 * to IC_10BITADDR_MASTER field in IC_CON: when it is enabled this
-	 * field is read-only so it should not succeed
-	 */
-	reg = dw_readl(dev, DW_IC_CON);
-	dw_writel(dev, reg ^ DW_IC_CON_10BITADDR_MASTER, DW_IC_CON);
-
-	if ((dw_readl(dev, DW_IC_CON) & DW_IC_CON_10BITADDR_MASTER) ==
-	    (reg & DW_IC_CON_10BITADDR_MASTER)) {
-		dev->dynamic_tar_update_enabled = true;
-		dev_dbg(dev->dev, "Dynamic TAR update enabled");
-	}
-
-	i2c_dw_release_lock(dev);
-
 	snprintf(adap->name, sizeof(adap->name),
 		 "Synopsys DesignWare I2C adapter");
 	adap->retries = 3;
diff --git a/drivers/i2c/busses/i2c-designware-core.h b/drivers/i2c/busses/i2c-designware-core.h
index 26250b425e2f..c1db3a5a340f 100644
--- a/drivers/i2c/busses/i2c-designware-core.h
+++ b/drivers/i2c/busses/i2c-designware-core.h
@@ -125,7 +125,6 @@ struct dw_i2c_dev {
 	int			(*acquire_lock)(struct dw_i2c_dev *dev);
 	void			(*release_lock)(struct dw_i2c_dev *dev);
 	bool			pm_runtime_disabled;
-	bool			dynamic_tar_update_enabled;
 };
 
 #define ACCESS_SWAP		0x00000001
diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c
index c62b7cd475f8..3310f2e0dbd3 100644
--- a/drivers/i2c/busses/i2c-imx-lpi2c.c
+++ b/drivers/i2c/busses/i2c-imx-lpi2c.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -636,12 +637,31 @@ static int lpi2c_imx_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int lpi2c_imx_suspend(struct device *dev)
+{
+	pinctrl_pm_select_sleep_state(dev);
+
+	return 0;
+}
+
+static int lpi2c_imx_resume(struct device *dev)
+{
+	pinctrl_pm_select_default_state(dev);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(imx_lpi2c_pm, lpi2c_imx_suspend, lpi2c_imx_resume);
+
 static struct platform_driver lpi2c_imx_driver = {
 	.probe = lpi2c_imx_probe,
 	.remove = lpi2c_imx_remove,
 	.driver = {
 		.name = DRIVER_NAME,
 		.of_match_table = lpi2c_imx_of_match,
+		.pm = &imx_lpi2c_pm,
 	},
 };
 
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index e34d82e79b98..c21ca7bf2efe 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -58,7 +58,7 @@
 #define SMBSLVDAT	(0xC + piix4_smba)
 
 /* count for request_region */
-#define SMBIOSIZE	8
+#define SMBIOSIZE	9
 
 /* PCI Address Constants */
 #define SMBBA		0x090
@@ -592,6 +592,8 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr,
 	u8 port;
 	int retval;
 
+	mutex_lock(&piix4_mutex_sb800);
+
 	/* Request the SMBUS semaphore, avoid conflicts with the IMC */
 	smbslvcnt  = inb_p(SMBSLVCNT);
 	do {
@@ -605,10 +607,10 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr,
 		usleep_range(1000, 2000);
 	} while (--retries);
 	/* SMBus is still owned by the IMC, we give up */
-	if (!retries)
+	if (!retries) {
+		mutex_unlock(&piix4_mutex_sb800);
 		return -EBUSY;
-
-	mutex_lock(&piix4_mutex_sb800);
+	}
 
 	outb_p(piix4_port_sel_sb800, SB800_PIIX4_SMB_IDX);
 	smba_en_lo = inb_p(SB800_PIIX4_SMB_IDX + 1);
@@ -623,11 +625,11 @@ static s32 piix4_access_sb800(struct i2c_adapter *adap, u16 addr,
 
 	outb_p(smba_en_lo, SB800_PIIX4_SMB_IDX + 1);
 
-	mutex_unlock(&piix4_mutex_sb800);
-
 	/* Release the semaphore */
 	outb_p(smbslvcnt | 0x20, SMBSLVCNT);
 
+	mutex_unlock(&piix4_mutex_sb800);
+
 	return retval;
 }
 
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 583e95042a21..bfb6ba7cac00 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -221,7 +221,8 @@ static int i2c_acpi_get_info(struct acpi_device *adev,
 
 	acpi_dev_free_resource_list(&resource_list);
 
-	strlcpy(info->type, dev_name(&adev->dev), sizeof(info->type));
+	acpi_set_modalias(adev, dev_name(&adev->dev), info->type,
+			  sizeof(info->type));
 
 	return 0;
 }
@@ -1335,15 +1336,29 @@ i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
 	client->dev.fwnode = info->fwnode;
 
 	i2c_dev_set_name(adap, client);
+
+	if (info->properties) {
+		status = device_add_properties(&client->dev, info->properties);
+		if (status) {
+			dev_err(&adap->dev,
+				"Failed to add properties to client %s: %d\n",
+				client->name, status);
+			goto out_err;
+		}
+	}
+
 	status = device_register(&client->dev);
 	if (status)
-		goto out_err;
+		goto out_free_props;
 
 	dev_dbg(&adap->dev, "client [%s] registered with bus id %s\n",
 		client->name, dev_name(&client->dev));
 
 	return client;
 
+out_free_props:
+	if (info->properties)
+		device_remove_properties(&client->dev);
 out_err:
 	dev_err(&adap->dev,
 		"Failed to register i2c client %s at 0x%02x (%d)\n",
diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig
index 39ea67f9b066..c99a25c075bc 100644
--- a/drivers/ide/Kconfig
+++ b/drivers/ide/Kconfig
@@ -10,6 +10,7 @@ menuconfig IDE
 	tristate "ATA/ATAPI/MFM/RLL support (DEPRECATED)"
 	depends on HAVE_IDE
 	depends on BLOCK
+	select BLK_SCSI_REQUEST
 	---help---
 	  If you say Y here, your kernel will be able to manage ATA/(E)IDE and
 	  ATAPI units. The most common cases are IDE hard drives and ATAPI
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index f90ea221f7f2..feb30061123b 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -92,8 +92,9 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 	struct request *rq;
 	int error;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->special = (char *)pc;
 
 	if (buf && bufflen) {
@@ -103,9 +104,9 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 			goto put_req;
 	}
 
-	memcpy(rq->cmd, pc->c, 12);
+	memcpy(scsi_req(rq)->cmd, pc->c, 12);
 	if (drive->media == ide_tape)
-		rq->cmd[13] = REQ_IDETAPE_PC1;
+		scsi_req(rq)->cmd[13] = REQ_IDETAPE_PC1;
 	error = blk_execute_rq(drive->queue, disk, rq, 0);
 put_req:
 	blk_put_request(rq);
@@ -171,7 +172,8 @@ EXPORT_SYMBOL_GPL(ide_create_request_sense_cmd);
 void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 {
 	struct request_sense *sense = &drive->sense_data;
-	struct request *sense_rq = &drive->sense_rq;
+	struct request *sense_rq = drive->sense_rq;
+	struct scsi_request *req = scsi_req(sense_rq);
 	unsigned int cmd_len, sense_len;
 	int err;
 
@@ -191,12 +193,13 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 
 	BUG_ON(sense_len > sizeof(*sense));
 
-	if (rq->cmd_type == REQ_TYPE_ATA_SENSE || drive->sense_rq_armed)
+	if (ata_sense_request(rq) || drive->sense_rq_armed)
 		return;
 
 	memset(sense, 0, sizeof(*sense));
 
 	blk_rq_init(rq->q, sense_rq);
+	scsi_req_init(sense_rq);
 
 	err = blk_rq_map_kern(drive->queue, sense_rq, sense, sense_len,
 			      GFP_NOIO);
@@ -208,13 +211,14 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 	}
 
 	sense_rq->rq_disk = rq->rq_disk;
-	sense_rq->cmd[0] = GPCMD_REQUEST_SENSE;
-	sense_rq->cmd[4] = cmd_len;
-	sense_rq->cmd_type = REQ_TYPE_ATA_SENSE;
+	sense_rq->cmd_flags = REQ_OP_DRV_IN;
+	ide_req(sense_rq)->type = ATA_PRIV_SENSE;
 	sense_rq->rq_flags |= RQF_PREEMPT;
 
+	req->cmd[0] = GPCMD_REQUEST_SENSE;
+	req->cmd[4] = cmd_len;
 	if (drive->media == ide_tape)
-		sense_rq->cmd[13] = REQ_IDETAPE_PC1;
+		req->cmd[13] = REQ_IDETAPE_PC1;
 
 	drive->sense_rq_armed = true;
 }
@@ -229,12 +233,12 @@ int ide_queue_sense_rq(ide_drive_t *drive, void *special)
 		return -ENOMEM;
 	}
 
-	drive->sense_rq.special = special;
+	drive->sense_rq->special = special;
 	drive->sense_rq_armed = false;
 
 	drive->hwif->rq = NULL;
 
-	elv_add_request(drive->queue, &drive->sense_rq, ELEVATOR_INSERT_FRONT);
+	elv_add_request(drive->queue, drive->sense_rq, ELEVATOR_INSERT_FRONT);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
@@ -247,14 +251,14 @@ EXPORT_SYMBOL_GPL(ide_queue_sense_rq);
 void ide_retry_pc(ide_drive_t *drive)
 {
 	struct request *failed_rq = drive->hwif->rq;
-	struct request *sense_rq = &drive->sense_rq;
+	struct request *sense_rq = drive->sense_rq;
 	struct ide_atapi_pc *pc = &drive->request_sense_pc;
 
 	(void)ide_read_error(drive);
 
 	/* init pc from sense_rq */
 	ide_init_pc(pc);
-	memcpy(pc->c, sense_rq->cmd, 12);
+	memcpy(pc->c, scsi_req(sense_rq)->cmd, 12);
 
 	if (drive->media == ide_tape)
 		drive->atapi_flags |= IDE_AFLAG_IGNORE_DSC;
@@ -286,7 +290,7 @@ int ide_cd_expiry(ide_drive_t *drive)
 	 * commands/drives support that. Let ide_timer_expiry keep polling us
 	 * for these.
 	 */
-	switch (rq->cmd[0]) {
+	switch (scsi_req(rq)->cmd[0]) {
 	case GPCMD_BLANK:
 	case GPCMD_FORMAT_UNIT:
 	case GPCMD_RESERVE_RZONE_TRACK:
@@ -297,7 +301,7 @@ int ide_cd_expiry(ide_drive_t *drive)
 	default:
 		if (!(rq->rq_flags & RQF_QUIET))
 			printk(KERN_INFO PFX "cmd 0x%x timed out\n",
-					 rq->cmd[0]);
+					 scsi_req(rq)->cmd[0]);
 		wait = 0;
 		break;
 	}
@@ -307,15 +311,21 @@ EXPORT_SYMBOL_GPL(ide_cd_expiry);
 
 int ide_cd_get_xferlen(struct request *rq)
 {
-	switch (rq->cmd_type) {
-	case REQ_TYPE_FS:
+	switch (req_op(rq)) {
+	default:
 		return 32768;
-	case REQ_TYPE_ATA_SENSE:
-	case REQ_TYPE_BLOCK_PC:
-	case REQ_TYPE_ATA_PC:
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
 		return blk_rq_bytes(rq);
-	default:
-		return 0;
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+		switch (ide_req(rq)->type) {
+		case ATA_PRIV_PC:
+		case ATA_PRIV_SENSE:
+			return blk_rq_bytes(rq);
+		default:
+			return 0;
+		}
 	}
 }
 EXPORT_SYMBOL_GPL(ide_cd_get_xferlen);
@@ -374,7 +384,7 @@ int ide_check_ireason(ide_drive_t *drive, struct request *rq, int len,
 				drive->name, __func__, ireason);
 	}
 
-	if (dev_is_idecd(drive) && rq->cmd_type == REQ_TYPE_ATA_PC)
+	if (dev_is_idecd(drive) && ata_pc_request(rq))
 		rq->rq_flags |= RQF_FAILED;
 
 	return 1;
@@ -420,7 +430,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 						     ? "write" : "read");
 			pc->flags |= PC_FLAG_DMA_ERROR;
 		} else
-			rq->resid_len = 0;
+			scsi_req(rq)->resid_len = 0;
 		debug_log("%s: DMA finished\n", drive->name);
 	}
 
@@ -436,7 +446,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 		local_irq_enable_in_hardirq();
 
 		if (drive->media == ide_tape &&
-		    (stat & ATA_ERR) && rq->cmd[0] == REQUEST_SENSE)
+		    (stat & ATA_ERR) && scsi_req(rq)->cmd[0] == REQUEST_SENSE)
 			stat &= ~ATA_ERR;
 
 		if ((stat & ATA_ERR) || (pc->flags & PC_FLAG_DMA_ERROR)) {
@@ -446,7 +456,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 			if (drive->media != ide_tape)
 				pc->rq->errors++;
 
-			if (rq->cmd[0] == REQUEST_SENSE) {
+			if (scsi_req(rq)->cmd[0] == REQUEST_SENSE) {
 				printk(KERN_ERR PFX "%s: I/O error in request "
 						"sense command\n", drive->name);
 				return ide_do_reset(drive);
@@ -477,12 +487,12 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 		if (uptodate == 0)
 			drive->failed_pc = NULL;
 
-		if (rq->cmd_type == REQ_TYPE_DRV_PRIV) {
+		if (ata_misc_request(rq)) {
 			rq->errors = 0;
 			error = 0;
 		} else {
 
-			if (rq->cmd_type != REQ_TYPE_FS && uptodate <= 0) {
+			if (blk_rq_is_passthrough(rq) && uptodate <= 0) {
 				if (rq->errors == 0)
 					rq->errors = -EIO;
 			}
@@ -512,7 +522,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 	ide_pio_bytes(drive, cmd, write, done);
 
 	/* Update transferred byte count */
-	rq->resid_len -= done;
+	scsi_req(rq)->resid_len -= done;
 
 	bcount -= done;
 
@@ -520,7 +530,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 		ide_pad_transfer(drive, write, bcount);
 
 	debug_log("[cmd %x] transferred %d bytes, padded %d bytes, resid: %u\n",
-		  rq->cmd[0], done, bcount, rq->resid_len);
+		  rq->cmd[0], done, bcount, scsi_req(rq)->resid_len);
 
 	/* And set the interrupt handler again */
 	ide_set_handler(drive, ide_pc_intr, timeout);
@@ -603,7 +613,7 @@ static ide_startstop_t ide_transfer_pc(ide_drive_t *drive)
 
 	if (dev_is_idecd(drive)) {
 		/* ATAPI commands get padded out to 12 bytes minimum */
-		cmd_len = COMMAND_SIZE(rq->cmd[0]);
+		cmd_len = COMMAND_SIZE(scsi_req(rq)->cmd[0]);
 		if (cmd_len < ATAPI_MIN_CDB_BYTES)
 			cmd_len = ATAPI_MIN_CDB_BYTES;
 
@@ -650,7 +660,7 @@ static ide_startstop_t ide_transfer_pc(ide_drive_t *drive)
 
 	/* Send the actual packet */
 	if ((drive->atapi_flags & IDE_AFLAG_ZIP_DRIVE) == 0)
-		hwif->tp_ops->output_data(drive, NULL, rq->cmd, cmd_len);
+		hwif->tp_ops->output_data(drive, NULL, scsi_req(rq)->cmd, cmd_len);
 
 	/* Begin DMA, if necessary */
 	if (dev_is_idecd(drive)) {
@@ -695,7 +705,7 @@ ide_startstop_t ide_issue_pc(ide_drive_t *drive, struct ide_cmd *cmd)
 							     bytes, 63 * 1024));
 
 		/* We haven't transferred any data yet */
-		rq->resid_len = bcount;
+		scsi_req(rq)->resid_len = bcount;
 
 		if (pc->flags & PC_FLAG_DMA_ERROR) {
 			pc->flags &= ~PC_FLAG_DMA_ERROR;
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 9cbd217bc0c9..aef00511ca86 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -121,7 +121,7 @@ static int cdrom_log_sense(ide_drive_t *drive, struct request *rq)
 		 * don't log START_STOP unit with LoEj set, since we cannot
 		 * reliably check if drive can auto-close
 		 */
-		if (rq->cmd[0] == GPCMD_START_STOP_UNIT && sense->asc == 0x24)
+		if (scsi_req(rq)->cmd[0] == GPCMD_START_STOP_UNIT && sense->asc == 0x24)
 			break;
 		log = 1;
 		break;
@@ -163,7 +163,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 	 * toc has not been recorded yet, it will fail with 05/24/00 (which is a
 	 * confusing error)
 	 */
-	if (failed_command && failed_command->cmd[0] == GPCMD_READ_TOC_PMA_ATIP)
+	if (failed_command && scsi_req(failed_command)->cmd[0] == GPCMD_READ_TOC_PMA_ATIP)
 		if (sense->sense_key == 0x05 && sense->asc == 0x24)
 			return;
 
@@ -176,7 +176,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 			if (!sense->valid)
 				break;
 			if (failed_command == NULL ||
-			    failed_command->cmd_type != REQ_TYPE_FS)
+			    blk_rq_is_passthrough(failed_command))
 				break;
 			sector = (sense->information[0] << 24) |
 				 (sense->information[1] << 16) |
@@ -210,7 +210,7 @@ static void cdrom_analyze_sense_data(ide_drive_t *drive,
 static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
 {
 	/*
-	 * For REQ_TYPE_ATA_SENSE, "rq->special" points to the original
+	 * For ATA_PRIV_SENSE, "rq->special" points to the original
 	 * failed request.  Also, the sense data should be read
 	 * directly from rq which might be different from the original
 	 * sense buffer if it got copied during mapping.
@@ -219,15 +219,12 @@ static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
 	void *sense = bio_data(rq->bio);
 
 	if (failed) {
-		if (failed->sense) {
-			/*
-			 * Sense is always read into drive->sense_data.
-			 * Copy back if the failed request has its
-			 * sense pointer set.
-			 */
-			memcpy(failed->sense, sense, 18);
-			failed->sense_len = rq->sense_len;
-		}
+		/*
+		 * Sense is always read into drive->sense_data, copy back to the
+		 * original request.
+		 */
+		memcpy(scsi_req(failed)->sense, sense, 18);
+		scsi_req(failed)->sense_len = scsi_req(rq)->sense_len;
 		cdrom_analyze_sense_data(drive, failed);
 
 		if (ide_end_rq(drive, failed, -EIO, blk_rq_bytes(failed)))
@@ -285,7 +282,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 				  "stat 0x%x",
 				  rq->cmd[0], rq->cmd_type, err, stat);
 
-	if (rq->cmd_type == REQ_TYPE_ATA_SENSE) {
+	if (ata_sense_request(rq)) {
 		/*
 		 * We got an error trying to get sense info from the drive
 		 * (probably while trying to recover from a former error).
@@ -296,7 +293,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 	}
 
 	/* if we have an error, pass CHECK_CONDITION as the SCSI status byte */
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC && !rq->errors)
+	if (blk_rq_is_scsi(rq) && !rq->errors)
 		rq->errors = SAM_STAT_CHECK_CONDITION;
 
 	if (blk_noretry_request(rq))
@@ -304,13 +301,13 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 
 	switch (sense_key) {
 	case NOT_READY:
-		if (rq->cmd_type == REQ_TYPE_FS && rq_data_dir(rq) == WRITE) {
+		if (req_op(rq) == REQ_OP_WRITE) {
 			if (ide_cd_breathe(drive, rq))
 				return 1;
 		} else {
 			cdrom_saw_media_change(drive);
 
-			if (rq->cmd_type == REQ_TYPE_FS &&
+			if (!blk_rq_is_passthrough(rq) &&
 			    !(rq->rq_flags & RQF_QUIET))
 				printk(KERN_ERR PFX "%s: tray open\n",
 					drive->name);
@@ -320,7 +317,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 	case UNIT_ATTENTION:
 		cdrom_saw_media_change(drive);
 
-		if (rq->cmd_type != REQ_TYPE_FS)
+		if (blk_rq_is_passthrough(rq))
 			return 0;
 
 		/*
@@ -338,7 +335,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 		 *
 		 * cdrom_log_sense() knows this!
 		 */
-		if (rq->cmd[0] == GPCMD_START_STOP_UNIT)
+		if (scsi_req(rq)->cmd[0] == GPCMD_START_STOP_UNIT)
 			break;
 		/* fall-through */
 	case DATA_PROTECT:
@@ -368,7 +365,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 		do_end_request = 1;
 		break;
 	default:
-		if (rq->cmd_type != REQ_TYPE_FS)
+		if (blk_rq_is_passthrough(rq))
 			break;
 		if (err & ~ATA_ABORTED) {
 			/* go to the default handler for other errors */
@@ -379,7 +376,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 			do_end_request = 1;
 	}
 
-	if (rq->cmd_type != REQ_TYPE_FS) {
+	if (blk_rq_is_passthrough(rq)) {
 		rq->rq_flags |= RQF_FAILED;
 		do_end_request = 1;
 	}
@@ -414,7 +411,7 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd)
 	 * Some of the trailing request sense fields are optional,
 	 * and some drives don't send them.  Sigh.
 	 */
-	if (rq->cmd[0] == GPCMD_REQUEST_SENSE &&
+	if (scsi_req(rq)->cmd[0] == GPCMD_REQUEST_SENSE &&
 	    cmd->nleft > 0 && cmd->nleft <= 5)
 		cmd->nleft = 0;
 }
@@ -425,12 +422,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		    req_flags_t rq_flags)
 {
 	struct cdrom_info *info = drive->driver_data;
-	struct request_sense local_sense;
 	int retries = 10;
-	req_flags_t flags = 0;
-
-	if (!sense)
-		sense = &local_sense;
+	bool failed;
 
 	ide_debug_log(IDE_DBG_PC, "cmd[0]: 0x%x, write: 0x%x, timeout: %d, "
 				  "rq_flags: 0x%x",
@@ -440,12 +433,13 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 	do {
 		struct request *rq;
 		int error;
+		bool delay = false;
 
-		rq = blk_get_request(drive->queue, write, __GFP_RECLAIM);
-
-		memcpy(rq->cmd, cmd, BLK_MAX_CDB);
-		rq->cmd_type = REQ_TYPE_ATA_PC;
-		rq->sense = sense;
+		rq = blk_get_request(drive->queue,
+			write ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN,  __GFP_RECLAIM);
+		scsi_req_init(rq);
+		memcpy(scsi_req(rq)->cmd, cmd, BLK_MAX_CDB);
+		ide_req(rq)->type = ATA_PRIV_PC;
 		rq->rq_flags |= rq_flags;
 		rq->timeout = timeout;
 		if (buffer) {
@@ -460,21 +454,21 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		error = blk_execute_rq(drive->queue, info->disk, rq, 0);
 
 		if (buffer)
-			*bufflen = rq->resid_len;
-
-		flags = rq->rq_flags;
-		blk_put_request(rq);
+			*bufflen = scsi_req(rq)->resid_len;
+		if (sense)
+			memcpy(sense, scsi_req(rq)->sense, sizeof(*sense));
 
 		/*
 		 * FIXME: we should probably abort/retry or something in case of
 		 * failure.
 		 */
-		if (flags & RQF_FAILED) {
+		failed = (rq->rq_flags & RQF_FAILED) != 0;
+		if (failed) {
 			/*
 			 * The request failed.  Retry if it was due to a unit
 			 * attention status (usually means media was changed).
 			 */
-			struct request_sense *reqbuf = sense;
+			struct request_sense *reqbuf = scsi_req(rq)->sense;
 
 			if (reqbuf->sense_key == UNIT_ATTENTION)
 				cdrom_saw_media_change(drive);
@@ -485,19 +479,20 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 				 * a disk.  Retry, but wait a little to give
 				 * the drive time to complete the load.
 				 */
-				ssleep(2);
+				delay = true;
 			} else {
 				/* otherwise, don't retry */
 				retries = 0;
 			}
 			--retries;
 		}
-
-		/* end of retry loop */
-	} while ((flags & RQF_FAILED) && retries >= 0);
+		blk_put_request(rq);
+		if (delay)
+			ssleep(2);
+	} while (failed && retries >= 0);
 
 	/* return an error if the command failed */
-	return (flags & RQF_FAILED) ? -EIO : 0;
+	return failed ? -EIO : 0;
 }
 
 /*
@@ -526,7 +521,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 	ide_expiry_t *expiry = NULL;
 	int dma_error = 0, dma, thislen, uptodate = 0;
 	int write = (rq_data_dir(rq) == WRITE) ? 1 : 0, rc = 0;
-	int sense = (rq->cmd_type == REQ_TYPE_ATA_SENSE);
+	int sense = ata_sense_request(rq);
 	unsigned int timeout;
 	u16 len;
 	u8 ireason, stat;
@@ -569,7 +564,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 
 	ide_read_bcount_and_ireason(drive, &len, &ireason);
 
-	thislen = (rq->cmd_type == REQ_TYPE_FS) ? len : cmd->nleft;
+	thislen = !blk_rq_is_passthrough(rq) ? len : cmd->nleft;
 	if (thislen > len)
 		thislen = len;
 
@@ -578,7 +573,8 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 
 	/* If DRQ is clear, the command has completed. */
 	if ((stat & ATA_DRQ) == 0) {
-		if (rq->cmd_type == REQ_TYPE_FS) {
+		switch (req_op(rq)) {
+		default:
 			/*
 			 * If we're not done reading/writing, complain.
 			 * Otherwise, complete the command normally.
@@ -592,7 +588,9 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 					rq->rq_flags |= RQF_FAILED;
 				uptodate = 0;
 			}
-		} else if (rq->cmd_type != REQ_TYPE_BLOCK_PC) {
+			goto out_end;
+		case REQ_OP_DRV_IN:
+		case REQ_OP_DRV_OUT:
 			ide_cd_request_sense_fixup(drive, cmd);
 
 			uptodate = cmd->nleft ? 0 : 1;
@@ -608,8 +606,11 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 
 			if (!uptodate)
 				rq->rq_flags |= RQF_FAILED;
+			goto out_end;
+		case REQ_OP_SCSI_IN:
+		case REQ_OP_SCSI_OUT:
+			goto out_end;
 		}
-		goto out_end;
 	}
 
 	rc = ide_check_ireason(drive, rq, len, ireason, write);
@@ -636,12 +637,12 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 		len -= blen;
 
 		if (sense && write == 0)
-			rq->sense_len += blen;
+			scsi_req(rq)->sense_len += blen;
 	}
 
 	/* pad, if necessary */
 	if (len > 0) {
-		if (rq->cmd_type != REQ_TYPE_FS || write == 0)
+		if (blk_rq_is_passthrough(rq) || write == 0)
 			ide_pad_transfer(drive, write, len);
 		else {
 			printk(KERN_ERR PFX "%s: confused, missing data\n",
@@ -650,12 +651,18 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 		}
 	}
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
+	switch (req_op(rq)) {
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
 		timeout = rq->timeout;
-	} else {
+		break;
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+		expiry = ide_cd_expiry;
+		/*FALLTHRU*/
+	default:
 		timeout = ATAPI_WAIT_PC;
-		if (rq->cmd_type != REQ_TYPE_FS)
-			expiry = ide_cd_expiry;
+		break;
 	}
 
 	hwif->expiry = expiry;
@@ -663,15 +670,15 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 	return ide_started;
 
 out_end:
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC && rc == 0) {
-		rq->resid_len = 0;
+	if (blk_rq_is_scsi(rq) && rc == 0) {
+		scsi_req(rq)->resid_len = 0;
 		blk_end_request_all(rq, 0);
 		hwif->rq = NULL;
 	} else {
 		if (sense && uptodate)
 			ide_cd_complete_failed_rq(drive, rq);
 
-		if (rq->cmd_type == REQ_TYPE_FS) {
+		if (!blk_rq_is_passthrough(rq)) {
 			if (cmd->nleft == 0)
 				uptodate = 1;
 		} else {
@@ -684,10 +691,10 @@ out_end:
 				return ide_stopped;
 
 		/* make sure it's fully ended */
-		if (rq->cmd_type != REQ_TYPE_FS) {
-			rq->resid_len -= cmd->nbytes - cmd->nleft;
+		if (blk_rq_is_passthrough(rq)) {
+			scsi_req(rq)->resid_len -= cmd->nbytes - cmd->nleft;
 			if (uptodate == 0 && (cmd->tf_flags & IDE_TFLAG_WRITE))
-				rq->resid_len += cmd->last_xfer_len;
+				scsi_req(rq)->resid_len += cmd->last_xfer_len;
 		}
 
 		ide_complete_rq(drive, uptodate ? 0 : -EIO, blk_rq_bytes(rq));
@@ -744,7 +751,7 @@ static void cdrom_do_block_pc(ide_drive_t *drive, struct request *rq)
 	ide_debug_log(IDE_DBG_PC, "rq->cmd[0]: 0x%x, rq->cmd_type: 0x%x",
 				  rq->cmd[0], rq->cmd_type);
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
+	if (blk_rq_is_scsi(rq))
 		rq->rq_flags |= RQF_QUIET;
 	else
 		rq->rq_flags &= ~RQF_FAILED;
@@ -786,25 +793,31 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 	if (drive->debug_mask & IDE_DBG_RQ)
 		blk_dump_rq_flags(rq, "ide_cd_do_request");
 
-	switch (rq->cmd_type) {
-	case REQ_TYPE_FS:
+	switch (req_op(rq)) {
+	default:
 		if (cdrom_start_rw(drive, rq) == ide_stopped)
 			goto out_end;
 		break;
-	case REQ_TYPE_ATA_SENSE:
-	case REQ_TYPE_BLOCK_PC:
-	case REQ_TYPE_ATA_PC:
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
+	handle_pc:
 		if (!rq->timeout)
 			rq->timeout = ATAPI_WAIT_PC;
-
 		cdrom_do_block_pc(drive, rq);
 		break;
-	case REQ_TYPE_DRV_PRIV:
-		/* right now this can only be a reset... */
-		uptodate = 1;
-		goto out_end;
-	default:
-		BUG();
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+		switch (ide_req(rq)->type) {
+		case ATA_PRIV_MISC:
+			/* right now this can only be a reset... */
+			uptodate = 1;
+			goto out_end;
+		case ATA_PRIV_SENSE:
+		case ATA_PRIV_PC:
+			goto handle_pc;
+		default:
+			BUG();
+		}
 	}
 
 	/* prepare sense request for this command */
@@ -817,7 +830,7 @@ static ide_startstop_t ide_cd_do_request(ide_drive_t *drive, struct request *rq,
 
 	cmd.rq = rq;
 
-	if (rq->cmd_type == REQ_TYPE_FS || blk_rq_bytes(rq)) {
+	if (!blk_rq_is_passthrough(rq) || blk_rq_bytes(rq)) {
 		ide_init_sg_cmd(&cmd, blk_rq_bytes(rq));
 		ide_map_sg(drive, &cmd);
 	}
@@ -1166,7 +1179,7 @@ void ide_cdrom_update_speed(ide_drive_t *drive, u8 *buf)
 	 CDC_CD_RW | CDC_DVD | CDC_DVD_R | CDC_DVD_RAM | CDC_GENERIC_PACKET | \
 	 CDC_MO_DRIVE | CDC_MRW | CDC_MRW_W | CDC_RAM)
 
-static struct cdrom_device_ops ide_cdrom_dops = {
+static const struct cdrom_device_ops ide_cdrom_dops = {
 	.open			= ide_cdrom_open_real,
 	.release		= ide_cdrom_release_real,
 	.drive_status		= ide_cdrom_drive_status,
@@ -1312,28 +1325,29 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
 	int hard_sect = queue_logical_block_size(q);
 	long block = (long)blk_rq_pos(rq) / (hard_sect >> 9);
 	unsigned long blocks = blk_rq_sectors(rq) / (hard_sect >> 9);
+	struct scsi_request *req = scsi_req(rq);
 
-	memset(rq->cmd, 0, BLK_MAX_CDB);
+	memset(req->cmd, 0, BLK_MAX_CDB);
 
 	if (rq_data_dir(rq) == READ)
-		rq->cmd[0] = GPCMD_READ_10;
+		req->cmd[0] = GPCMD_READ_10;
 	else
-		rq->cmd[0] = GPCMD_WRITE_10;
+		req->cmd[0] = GPCMD_WRITE_10;
 
 	/*
 	 * fill in lba
 	 */
-	rq->cmd[2] = (block >> 24) & 0xff;
-	rq->cmd[3] = (block >> 16) & 0xff;
-	rq->cmd[4] = (block >>  8) & 0xff;
-	rq->cmd[5] = block & 0xff;
+	req->cmd[2] = (block >> 24) & 0xff;
+	req->cmd[3] = (block >> 16) & 0xff;
+	req->cmd[4] = (block >>  8) & 0xff;
+	req->cmd[5] = block & 0xff;
 
 	/*
 	 * and transfer length
 	 */
-	rq->cmd[7] = (blocks >> 8) & 0xff;
-	rq->cmd[8] = blocks & 0xff;
-	rq->cmd_len = 10;
+	req->cmd[7] = (blocks >> 8) & 0xff;
+	req->cmd[8] = blocks & 0xff;
+	req->cmd_len = 10;
 	return BLKPREP_OK;
 }
 
@@ -1343,7 +1357,7 @@ static int ide_cdrom_prep_fs(struct request_queue *q, struct request *rq)
  */
 static int ide_cdrom_prep_pc(struct request *rq)
 {
-	u8 *c = rq->cmd;
+	u8 *c = scsi_req(rq)->cmd;
 
 	/* transform 6-byte read/write commands to the 10-byte version */
 	if (c[0] == READ_6 || c[0] == WRITE_6) {
@@ -1354,7 +1368,7 @@ static int ide_cdrom_prep_pc(struct request *rq)
 		c[2] = 0;
 		c[1] &= 0xe0;
 		c[0] += (READ_10 - READ_6);
-		rq->cmd_len = 10;
+		scsi_req(rq)->cmd_len = 10;
 		return BLKPREP_OK;
 	}
 
@@ -1373,9 +1387,9 @@ static int ide_cdrom_prep_pc(struct request *rq)
 
 static int ide_cdrom_prep_fn(struct request_queue *q, struct request *rq)
 {
-	if (rq->cmd_type == REQ_TYPE_FS)
+	if (!blk_rq_is_passthrough(rq))
 		return ide_cdrom_prep_fs(q, rq);
-	else if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
+	else if (blk_rq_is_scsi(rq))
 		return ide_cdrom_prep_pc(rq);
 
 	return 0;
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index f085e3a2e1d6..9fcefbc8425e 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -303,8 +303,9 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	struct request *rq;
 	int ret;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->rq_flags = RQF_QUIET;
 	ret = blk_execute_rq(drive->queue, cd->disk, rq, 0);
 	blk_put_request(rq);
diff --git a/drivers/ide/ide-cd_verbose.c b/drivers/ide/ide-cd_verbose.c
index f079ca2f260b..58a6feb74c02 100644
--- a/drivers/ide/ide-cd_verbose.c
+++ b/drivers/ide/ide-cd_verbose.c
@@ -315,12 +315,12 @@ void ide_cd_log_error(const char *name, struct request *failed_command,
 		while (hi > lo) {
 			mid = (lo + hi) / 2;
 			if (packet_command_texts[mid].packet_command ==
-			    failed_command->cmd[0]) {
+			    scsi_req(failed_command)->cmd[0]) {
 				s = packet_command_texts[mid].text;
 				break;
 			}
 			if (packet_command_texts[mid].packet_command >
-			    failed_command->cmd[0])
+			    scsi_req(failed_command)->cmd[0])
 				hi = mid;
 			else
 				lo = mid + 1;
@@ -329,7 +329,7 @@ void ide_cd_log_error(const char *name, struct request *failed_command,
 		printk(KERN_ERR "  The failed \"%s\" packet command "
 				"was: \n  \"", s);
 		for (i = 0; i < BLK_MAX_CDB; i++)
-			printk(KERN_CONT "%02x ", failed_command->cmd[i]);
+			printk(KERN_CONT "%02x ", scsi_req(failed_command)->cmd[i]);
 		printk(KERN_CONT "\"\n");
 	}
 
diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c
index 0dd43b4fcec6..a45dda5386e4 100644
--- a/drivers/ide/ide-devsets.c
+++ b/drivers/ide/ide-devsets.c
@@ -165,11 +165,12 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 	if (!(setting->flags & DS_SYNC))
 		return setting->set(drive, arg);
 
-	rq = blk_get_request(q, READ, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
-	rq->cmd_len = 5;
-	rq->cmd[0] = REQ_DEVSET_EXEC;
-	*(int *)&rq->cmd[1] = arg;
+	rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_MISC;
+	scsi_req(rq)->cmd_len = 5;
+	scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC;
+	*(int *)&scsi_req(rq)->cmd[1] = arg;
 	rq->special = setting->set;
 
 	if (blk_execute_rq(q, NULL, rq, 0))
@@ -183,7 +184,7 @@ ide_startstop_t ide_do_devset(ide_drive_t *drive, struct request *rq)
 {
 	int err, (*setfunc)(ide_drive_t *, int) = rq->special;
 
-	err = setfunc(drive, *(int *)&rq->cmd[1]);
+	err = setfunc(drive, *(int *)&scsi_req(rq)->cmd[1]);
 	if (err)
 		rq->errors = err;
 	ide_complete_rq(drive, err, blk_rq_bytes(rq));
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 5ceace542b77..186159715b71 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -184,7 +184,7 @@ static ide_startstop_t ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
 	ide_hwif_t *hwif = drive->hwif;
 
 	BUG_ON(drive->dev_flags & IDE_DFLAG_BLOCKED);
-	BUG_ON(rq->cmd_type != REQ_TYPE_FS);
+	BUG_ON(blk_rq_is_passthrough(rq));
 
 	ledtrig_disk_activity();
 
@@ -452,8 +452,9 @@ static int idedisk_prep_fn(struct request_queue *q, struct request *rq)
 	cmd->valid.out.tf = IDE_VALID_OUT_TF | IDE_VALID_DEVICE;
 	cmd->tf_flags = IDE_TFLAG_DYN;
 	cmd->protocol = ATA_PROT_NODATA;
-
-	rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
+	rq->cmd_flags &= ~REQ_OP_MASK;
+	rq->cmd_flags |= REQ_OP_DRV_OUT;
+	ide_req(rq)->type = ATA_PRIV_TASKFILE;
 	rq->special = cmd;
 	cmd->rq = rq;
 
@@ -477,8 +478,9 @@ static int set_multcount(ide_drive_t *drive, int arg)
 	if (drive->special_flags & IDE_SFLAG_SET_MULTMODE)
 		return -EBUSY;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_TASKFILE;
 
 	drive->mult_req = arg;
 	drive->special_flags |= IDE_SFLAG_SET_MULTMODE;
diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c
index d6da011299f5..cf3af6840368 100644
--- a/drivers/ide/ide-eh.c
+++ b/drivers/ide/ide-eh.c
@@ -123,8 +123,8 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
 		return ide_stopped;
 
 	/* retry only "normal" I/O: */
-	if (rq->cmd_type != REQ_TYPE_FS) {
-		if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE) {
+	if (blk_rq_is_passthrough(rq)) {
+		if (ata_taskfile_request(rq)) {
 			struct ide_cmd *cmd = rq->special;
 
 			if (cmd)
@@ -147,8 +147,8 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
 {
 	struct request *rq = drive->hwif->rq;
 
-	if (rq && rq->cmd_type == REQ_TYPE_DRV_PRIV &&
-	    rq->cmd[0] == REQ_DRIVE_RESET) {
+	if (rq && ata_misc_request(rq) &&
+	    scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) {
 		if (err <= 0 && rq->errors == 0)
 			rq->errors = -EIO;
 		ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq));
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index f079d8d1d856..a69e8013f1df 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -72,7 +72,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc)
 		drive->failed_pc = NULL;
 
 	if (pc->c[0] == GPCMD_READ_10 || pc->c[0] == GPCMD_WRITE_10 ||
-	    rq->cmd_type == REQ_TYPE_BLOCK_PC)
+	    (req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT))
 		uptodate = 1; /* FIXME */
 	else if (pc->c[0] == GPCMD_REQUEST_SENSE) {
 
@@ -97,7 +97,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc)
 			       "Aborting request!\n");
 	}
 
-	if (rq->cmd_type == REQ_TYPE_DRV_PRIV)
+	if (ata_misc_request(rq))
 		rq->errors = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
 
 	return uptodate;
@@ -203,7 +203,7 @@ static void idefloppy_create_rw_cmd(ide_drive_t *drive,
 	put_unaligned(cpu_to_be16(blocks), (unsigned short *)&pc->c[7]);
 	put_unaligned(cpu_to_be32(block), (unsigned int *) &pc->c[2]);
 
-	memcpy(rq->cmd, pc->c, 12);
+	memcpy(scsi_req(rq)->cmd, pc->c, 12);
 
 	pc->rq = rq;
 	if (cmd == WRITE)
@@ -216,7 +216,7 @@ static void idefloppy_blockpc_cmd(struct ide_disk_obj *floppy,
 		struct ide_atapi_pc *pc, struct request *rq)
 {
 	ide_init_pc(pc);
-	memcpy(pc->c, rq->cmd, sizeof(pc->c));
+	memcpy(pc->c, scsi_req(rq)->cmd, sizeof(pc->c));
 	pc->rq = rq;
 	if (blk_rq_bytes(rq)) {
 		pc->flags |= PC_FLAG_DMA_OK;
@@ -246,7 +246,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 		} else
 			printk(KERN_ERR PFX "%s: I/O error\n", drive->name);
 
-		if (rq->cmd_type == REQ_TYPE_DRV_PRIV) {
+		if (ata_misc_request(rq)) {
 			rq->errors = 0;
 			ide_complete_rq(drive, 0, blk_rq_bytes(rq));
 			return ide_stopped;
@@ -254,8 +254,8 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 			goto out_end;
 	}
 
-	switch (rq->cmd_type) {
-	case REQ_TYPE_FS:
+	switch (req_op(rq)) {
+	default:
 		if (((long)blk_rq_pos(rq) % floppy->bs_factor) ||
 		    (blk_rq_sectors(rq) % floppy->bs_factor)) {
 			printk(KERN_ERR PFX "%s: unsupported r/w rq size\n",
@@ -265,16 +265,21 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 		pc = &floppy->queued_pc;
 		idefloppy_create_rw_cmd(drive, pc, rq, (unsigned long)block);
 		break;
-	case REQ_TYPE_DRV_PRIV:
-	case REQ_TYPE_ATA_SENSE:
-		pc = (struct ide_atapi_pc *)rq->special;
-		break;
-	case REQ_TYPE_BLOCK_PC:
+	case REQ_OP_SCSI_IN:
+	case REQ_OP_SCSI_OUT:
 		pc = &floppy->queued_pc;
 		idefloppy_blockpc_cmd(floppy, pc, rq);
 		break;
-	default:
-		BUG();
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+		switch (ide_req(rq)->type) {
+		case ATA_PRIV_MISC:
+		case ATA_PRIV_SENSE:
+			pc = (struct ide_atapi_pc *)rq->special;
+			break;
+		default:
+			BUG();
+		}
 	}
 
 	ide_prep_sense(drive, rq);
@@ -286,7 +291,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 
 	cmd.rq = rq;
 
-	if (rq->cmd_type == REQ_TYPE_FS || blk_rq_bytes(rq)) {
+	if (!blk_rq_is_passthrough(rq) || blk_rq_bytes(rq)) {
 		ide_init_sg_cmd(&cmd, blk_rq_bytes(rq));
 		ide_map_sg(drive, &cmd);
 	}
@@ -296,7 +301,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 	return ide_floppy_issue_pc(drive, &cmd, pc);
 out_end:
 	drive->failed_pc = NULL;
-	if (rq->cmd_type != REQ_TYPE_FS && rq->errors == 0)
+	if (blk_rq_is_passthrough(rq) && rq->errors == 0)
 		rq->errors = -EIO;
 	ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
 	return ide_stopped;
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 201e43fcbc94..043b1fb963cb 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -102,7 +102,7 @@ void ide_complete_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat, u8 err)
 			drive->dev_flags |= IDE_DFLAG_PARKED;
 	}
 
-	if (rq && rq->cmd_type == REQ_TYPE_ATA_TASKFILE) {
+	if (rq && ata_taskfile_request(rq)) {
 		struct ide_cmd *orig_cmd = rq->special;
 
 		if (cmd->tf_flags & IDE_TFLAG_DYN)
@@ -135,7 +135,7 @@ EXPORT_SYMBOL(ide_complete_rq);
 
 void ide_kill_rq(ide_drive_t *drive, struct request *rq)
 {
-	u8 drv_req = (rq->cmd_type == REQ_TYPE_DRV_PRIV) && rq->rq_disk;
+	u8 drv_req = ata_misc_request(rq) && rq->rq_disk;
 	u8 media = drive->media;
 
 	drive->failed_pc = NULL;
@@ -145,7 +145,7 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq)
 	} else {
 		if (media == ide_tape)
 			rq->errors = IDE_DRV_ERROR_GENERAL;
-		else if (rq->cmd_type != REQ_TYPE_FS && rq->errors == 0)
+		else if (blk_rq_is_passthrough(rq) && rq->errors == 0)
 			rq->errors = -EIO;
 	}
 
@@ -279,7 +279,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
 
 static ide_startstop_t ide_special_rq(ide_drive_t *drive, struct request *rq)
 {
-	u8 cmd = rq->cmd[0];
+	u8 cmd = scsi_req(rq)->cmd[0];
 
 	switch (cmd) {
 	case REQ_PARK_HEADS:
@@ -340,7 +340,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 		if (drive->current_speed == 0xff)
 			ide_config_drive_speed(drive, drive->desired_speed);
 
-		if (rq->cmd_type == REQ_TYPE_ATA_TASKFILE)
+		if (ata_taskfile_request(rq))
 			return execute_drive_cmd(drive, rq);
 		else if (ata_pm_request(rq)) {
 			struct ide_pm_state *pm = rq->special;
@@ -353,7 +353,7 @@ static ide_startstop_t start_request (ide_drive_t *drive, struct request *rq)
 			    pm->pm_step == IDE_PM_COMPLETED)
 				ide_complete_pm_rq(drive, rq);
 			return startstop;
-		} else if (!rq->rq_disk && rq->cmd_type == REQ_TYPE_DRV_PRIV)
+		} else if (!rq->rq_disk && ata_misc_request(rq))
 			/*
 			 * TODO: Once all ULDs have been modified to
 			 * check for specific op codes rather than
@@ -545,6 +545,7 @@ repeat:
 			goto plug_device;
 		}
 
+		scsi_req(rq)->resid_len = blk_rq_bytes(rq);
 		hwif->rq = rq;
 
 		spin_unlock_irq(&hwif->lock);
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index d05db2469209..248a3e0ceb46 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -125,8 +125,9 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
 	if (NULL == (void *) arg) {
 		struct request *rq;
 
-		rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
-		rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
+		rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+		scsi_req_init(rq);
+		ide_req(rq)->type = ATA_PRIV_TASKFILE;
 		err = blk_execute_rq(drive->queue, NULL, rq, 0);
 		blk_put_request(rq);
 
@@ -221,10 +222,11 @@ static int generic_drive_reset(ide_drive_t *drive)
 	struct request *rq;
 	int ret = 0;
 
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
-	rq->cmd_len = 1;
-	rq->cmd[0] = REQ_DRIVE_RESET;
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_MISC;
+	scsi_req(rq)->cmd_len = 1;
+	scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;
 	if (blk_execute_rq(drive->queue, NULL, rq, 1))
 		ret = rq->errors;
 	blk_put_request(rq);
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index 2d7dca56dd24..101aed9a61ca 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -31,10 +31,11 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	}
 	spin_unlock_irq(&hwif->lock);
 
-	rq = blk_get_request(q, READ, __GFP_RECLAIM);
-	rq->cmd[0] = REQ_PARK_HEADS;
-	rq->cmd_len = 1;
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	scsi_req(rq)->cmd[0] = REQ_PARK_HEADS;
+	scsi_req(rq)->cmd_len = 1;
+	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->special = &timeout;
 	rc = blk_execute_rq(q, NULL, rq, 1);
 	blk_put_request(rq);
@@ -45,13 +46,14 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	 * Make sure that *some* command is sent to the drive after the
 	 * timeout has expired, so power management will be reenabled.
 	 */
-	rq = blk_get_request(q, READ, GFP_NOWAIT);
+	rq = blk_get_request(q, REQ_OP_DRV_IN, GFP_NOWAIT);
+	scsi_req_init(rq);
 	if (IS_ERR(rq))
 		goto out;
 
-	rq->cmd[0] = REQ_UNPARK_HEADS;
-	rq->cmd_len = 1;
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
+	scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS;
+	scsi_req(rq)->cmd_len = 1;
+	ide_req(rq)->type = ATA_PRIV_MISC;
 	elv_add_request(q, rq, ELEVATOR_INSERT_FRONT);
 
 out:
@@ -64,7 +66,7 @@ ide_startstop_t ide_do_park_unpark(ide_drive_t *drive, struct request *rq)
 	struct ide_taskfile *tf = &cmd.tf;
 
 	memset(&cmd, 0, sizeof(cmd));
-	if (rq->cmd[0] == REQ_PARK_HEADS) {
+	if (scsi_req(rq)->cmd[0] == REQ_PARK_HEADS) {
 		drive->sleep = *(unsigned long *)rq->special;
 		drive->dev_flags |= IDE_DFLAG_SLEEPING;
 		tf->command = ATA_CMD_IDLEIMMEDIATE;
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index a015acdffb39..ec951be4b0c8 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -18,8 +18,9 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_ATA_PM_SUSPEND;
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_PM_SUSPEND;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_SUSPEND;
 	if (mesg.event == PM_EVENT_PRETHAW)
@@ -88,8 +89,9 @@ int generic_ide_resume(struct device *dev)
 	}
 
 	memset(&rqpm, 0, sizeof(rqpm));
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_ATA_PM_RESUME;
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_PM_RESUME;
 	rq->rq_flags |= RQF_PREEMPT;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_RESUME;
@@ -221,10 +223,10 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 
 #ifdef DEBUG_PM
 	printk("%s: completing PM request, %s\n", drive->name,
-	       (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND) ? "suspend" : "resume");
+	       (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND) ? "suspend" : "resume");
 #endif
 	spin_lock_irqsave(q->queue_lock, flags);
-	if (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND)
+	if (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND)
 		blk_stop_queue(q);
 	else
 		drive->dev_flags &= ~IDE_DFLAG_BLOCKED;
@@ -240,11 +242,13 @@ void ide_check_pm_state(ide_drive_t *drive, struct request *rq)
 {
 	struct ide_pm_state *pm = rq->special;
 
-	if (rq->cmd_type == REQ_TYPE_ATA_PM_SUSPEND &&
+	if (blk_rq_is_private(rq) &&
+	    ide_req(rq)->type == ATA_PRIV_PM_SUSPEND &&
 	    pm->pm_step == IDE_PM_START_SUSPEND)
 		/* Mark drive blocked when starting the suspend sequence. */
 		drive->dev_flags |= IDE_DFLAG_BLOCKED;
-	else if (rq->cmd_type == REQ_TYPE_ATA_PM_RESUME &&
+	else if (blk_rq_is_private(rq) &&
+	         ide_req(rq)->type == ATA_PRIV_PM_RESUME &&
 		 pm->pm_step == IDE_PM_START_RESUME) {
 		/*
 		 * The first thing we do on wakeup is to wait for BSY bit to
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 330e319419e6..a74ae8df4bb8 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -741,6 +741,14 @@ static void ide_port_tune_devices(ide_hwif_t *hwif)
 	}
 }
 
+static int ide_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
+{
+	struct ide_request *req = blk_mq_rq_to_pdu(rq);
+
+	req->sreq.sense = req->sense;
+	return 0;
+}
+
 /*
  * init request queue
  */
@@ -758,11 +766,18 @@ static int ide_init_queue(ide_drive_t *drive)
 	 *	limits and LBA48 we could raise it but as yet
 	 *	do not.
 	 */
-
-	q = blk_init_queue_node(do_ide_request, NULL, hwif_to_node(hwif));
+	q = blk_alloc_queue_node(GFP_KERNEL, hwif_to_node(hwif));
 	if (!q)
 		return 1;
 
+	q->request_fn = do_ide_request;
+	q->init_rq_fn = ide_init_rq;
+	q->cmd_size = sizeof(struct ide_request);
+	if (blk_init_allocated_queue(q) < 0) {
+		blk_cleanup_queue(q);
+		return 1;
+	}
+
 	q->queuedata = drive;
 	blk_queue_segment_boundary(q, 0xffff);
 
@@ -1131,10 +1146,12 @@ static void ide_port_init_devices_data(ide_hwif_t *hwif)
 	ide_port_for_each_dev(i, drive, hwif) {
 		u8 j = (hwif->index * MAX_DRIVES) + i;
 		u16 *saved_id = drive->id;
+		struct request *saved_sense_rq = drive->sense_rq;
 
 		memset(drive, 0, sizeof(*drive));
 		memset(saved_id, 0, SECTOR_SIZE);
 		drive->id = saved_id;
+		drive->sense_rq = saved_sense_rq;
 
 		drive->media			= ide_disk;
 		drive->select			= (i << 4) | ATA_DEVICE_OBS;
@@ -1241,6 +1258,7 @@ static void ide_port_free_devices(ide_hwif_t *hwif)
 	int i;
 
 	ide_port_for_each_dev(i, drive, hwif) {
+		kfree(drive->sense_rq);
 		kfree(drive->id);
 		kfree(drive);
 	}
@@ -1248,11 +1266,10 @@ static void ide_port_free_devices(ide_hwif_t *hwif)
 
 static int ide_port_alloc_devices(ide_hwif_t *hwif, int node)
 {
+	ide_drive_t *drive;
 	int i;
 
 	for (i = 0; i < MAX_DRIVES; i++) {
-		ide_drive_t *drive;
-
 		drive = kzalloc_node(sizeof(*drive), GFP_KERNEL, node);
 		if (drive == NULL)
 			goto out_nomem;
@@ -1267,12 +1284,21 @@ static int ide_port_alloc_devices(ide_hwif_t *hwif, int node)
 		 */
 		drive->id = kzalloc_node(SECTOR_SIZE, GFP_KERNEL, node);
 		if (drive->id == NULL)
-			goto out_nomem;
+			goto out_free_drive;
+
+		drive->sense_rq = kmalloc(sizeof(struct request) +
+				sizeof(struct ide_request), GFP_KERNEL);
+		if (!drive->sense_rq)
+			goto out_free_id;
 
 		hwif->devices[i] = drive;
 	}
 	return 0;
 
+out_free_id:
+	kfree(drive->id);
+out_free_drive:
+	kfree(drive);
 out_nomem:
 	ide_port_free_devices(hwif);
 	return -ENOMEM;
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 9ecf4e35adcd..3c1b7974d66d 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -282,7 +282,7 @@ static void idetape_analyze_error(ide_drive_t *drive)
 
 	/* correct remaining bytes to transfer */
 	if (pc->flags & PC_FLAG_DMA_ERROR)
-		rq->resid_len = tape->blk_size * get_unaligned_be32(&sense[3]);
+		scsi_req(rq)->resid_len = tape->blk_size * get_unaligned_be32(&sense[3]);
 
 	/*
 	 * If error was the result of a zero-length read or write command,
@@ -316,7 +316,7 @@ static void idetape_analyze_error(ide_drive_t *drive)
 			pc->flags |= PC_FLAG_ABORT;
 		}
 		if (!(pc->flags & PC_FLAG_ABORT) &&
-		    (blk_rq_bytes(rq) - rq->resid_len))
+		    (blk_rq_bytes(rq) - scsi_req(rq)->resid_len))
 			pc->retries = IDETAPE_MAX_PC_RETRIES + 1;
 	}
 }
@@ -348,7 +348,7 @@ static int ide_tape_callback(ide_drive_t *drive, int dsc)
 					"itself - Aborting request!\n");
 	} else if (pc->c[0] == READ_6 || pc->c[0] == WRITE_6) {
 		unsigned int blocks =
-			(blk_rq_bytes(rq) - rq->resid_len) / tape->blk_size;
+			(blk_rq_bytes(rq) - scsi_req(rq)->resid_len) / tape->blk_size;
 
 		tape->avg_size += blocks * tape->blk_size;
 
@@ -560,7 +560,7 @@ static void ide_tape_create_rw_cmd(idetape_tape_t *tape,
 		pc->flags |= PC_FLAG_WRITING;
 	}
 
-	memcpy(rq->cmd, pc->c, 12);
+	memcpy(scsi_req(rq)->cmd, pc->c, 12);
 }
 
 static ide_startstop_t idetape_do_request(ide_drive_t *drive,
@@ -570,14 +570,16 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 	idetape_tape_t *tape = drive->driver_data;
 	struct ide_atapi_pc *pc = NULL;
 	struct ide_cmd cmd;
+	struct scsi_request *req = scsi_req(rq);
 	u8 stat;
 
 	ide_debug_log(IDE_DBG_RQ, "cmd: 0x%x, sector: %llu, nr_sectors: %u",
-		      rq->cmd[0], (unsigned long long)blk_rq_pos(rq),
+		      req->cmd[0], (unsigned long long)blk_rq_pos(rq),
 		      blk_rq_sectors(rq));
 
-	BUG_ON(!(rq->cmd_type == REQ_TYPE_DRV_PRIV ||
-		 rq->cmd_type == REQ_TYPE_ATA_SENSE));
+	BUG_ON(!blk_rq_is_private(rq));
+	BUG_ON(ide_req(rq)->type != ATA_PRIV_MISC &&
+	       ide_req(rq)->type != ATA_PRIV_SENSE);
 
 	/* Retry a failed packet command */
 	if (drive->failed_pc && drive->pc->c[0] == REQUEST_SENSE) {
@@ -592,7 +594,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 	stat = hwif->tp_ops->read_status(hwif);
 
 	if ((drive->dev_flags & IDE_DFLAG_DSC_OVERLAP) == 0 &&
-	    (rq->cmd[13] & REQ_IDETAPE_PC2) == 0)
+	    (req->cmd[13] & REQ_IDETAPE_PC2) == 0)
 		drive->atapi_flags |= IDE_AFLAG_IGNORE_DSC;
 
 	if (drive->dev_flags & IDE_DFLAG_POST_RESET) {
@@ -609,7 +611,7 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 		} else if (time_after(jiffies, tape->dsc_timeout)) {
 			printk(KERN_ERR "ide-tape: %s: DSC timeout\n",
 				tape->name);
-			if (rq->cmd[13] & REQ_IDETAPE_PC2) {
+			if (req->cmd[13] & REQ_IDETAPE_PC2) {
 				idetape_media_access_finished(drive);
 				return ide_stopped;
 			} else {
@@ -626,23 +628,23 @@ static ide_startstop_t idetape_do_request(ide_drive_t *drive,
 		tape->postponed_rq = false;
 	}
 
-	if (rq->cmd[13] & REQ_IDETAPE_READ) {
+	if (req->cmd[13] & REQ_IDETAPE_READ) {
 		pc = &tape->queued_pc;
 		ide_tape_create_rw_cmd(tape, pc, rq, READ_6);
 		goto out;
 	}
-	if (rq->cmd[13] & REQ_IDETAPE_WRITE) {
+	if (req->cmd[13] & REQ_IDETAPE_WRITE) {
 		pc = &tape->queued_pc;
 		ide_tape_create_rw_cmd(tape, pc, rq, WRITE_6);
 		goto out;
 	}
-	if (rq->cmd[13] & REQ_IDETAPE_PC1) {
+	if (req->cmd[13] & REQ_IDETAPE_PC1) {
 		pc = (struct ide_atapi_pc *)rq->special;
-		rq->cmd[13] &= ~(REQ_IDETAPE_PC1);
-		rq->cmd[13] |= REQ_IDETAPE_PC2;
+		req->cmd[13] &= ~(REQ_IDETAPE_PC1);
+		req->cmd[13] |= REQ_IDETAPE_PC2;
 		goto out;
 	}
-	if (rq->cmd[13] & REQ_IDETAPE_PC2) {
+	if (req->cmd[13] & REQ_IDETAPE_PC2) {
 		idetape_media_access_finished(drive);
 		return ide_stopped;
 	}
@@ -852,9 +854,10 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	BUG_ON(cmd != REQ_IDETAPE_READ && cmd != REQ_IDETAPE_WRITE);
 	BUG_ON(size < 0 || size % tape->blk_size);
 
-	rq = blk_get_request(drive->queue, READ, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_DRV_PRIV;
-	rq->cmd[13] = cmd;
+	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_MISC;
+	scsi_req(rq)->cmd[13] = cmd;
 	rq->rq_disk = tape->disk;
 	rq->__sector = tape->first_frame;
 
@@ -868,7 +871,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	blk_execute_rq(drive->queue, tape->disk, rq, 0);
 
 	/* calculate the number of transferred bytes and update buffer state */
-	size -= rq->resid_len;
+	size -= scsi_req(rq)->resid_len;
 	tape->cur = tape->buf;
 	if (cmd == REQ_IDETAPE_READ)
 		tape->valid = size;
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index a716693417a3..247b9faccce1 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -428,10 +428,12 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 {
 	struct request *rq;
 	int error;
-	int rw = !(cmd->tf_flags & IDE_TFLAG_WRITE) ? READ : WRITE;
 
-	rq = blk_get_request(drive->queue, rw, __GFP_RECLAIM);
-	rq->cmd_type = REQ_TYPE_ATA_TASKFILE;
+	rq = blk_get_request(drive->queue,
+		(cmd->tf_flags & IDE_TFLAG_WRITE) ?
+			REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM);
+	scsi_req_init(rq);
+	ide_req(rq)->type = ATA_PRIV_TASKFILE;
 
 	/*
 	 * (ks) We transfer currently only whole sectors.
diff --git a/drivers/ide/sis5513.c b/drivers/ide/sis5513.c
index 247853ea1368..c3062b53056f 100644
--- a/drivers/ide/sis5513.c
+++ b/drivers/ide/sis5513.c
@@ -54,7 +54,7 @@
 #define DRV_NAME "sis5513"
 
 /* registers layout and init values are chipset family dependent */
-
+#undef ATA_16
 #define ATA_16		0x01
 #define ATA_33		0x02
 #define ATA_66		0x03
diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c
index 2bbf0c521beb..7d61b566e148 100644
--- a/drivers/iio/adc/palmas_gpadc.c
+++ b/drivers/iio/adc/palmas_gpadc.c
@@ -775,7 +775,7 @@ static int palmas_adc_wakeup_reset(struct palmas_gpadc *adc)
 
 static int palmas_gpadc_suspend(struct device *dev)
 {
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct iio_dev *indio_dev = dev_get_drvdata(dev);
 	struct palmas_gpadc *adc = iio_priv(indio_dev);
 	int wakeup = adc->wakeup1_enable || adc->wakeup2_enable;
 	int ret;
@@ -798,7 +798,7 @@ static int palmas_gpadc_suspend(struct device *dev)
 
 static int palmas_gpadc_resume(struct device *dev)
 {
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct iio_dev *indio_dev = dev_get_drvdata(dev);
 	struct palmas_gpadc *adc = iio_priv(indio_dev);
 	int wakeup = adc->wakeup1_enable || adc->wakeup2_enable;
 	int ret;
diff --git a/drivers/iio/health/afe4403.c b/drivers/iio/health/afe4403.c
index 9a081465c42f..6bb23a49e81e 100644
--- a/drivers/iio/health/afe4403.c
+++ b/drivers/iio/health/afe4403.c
@@ -422,7 +422,7 @@ MODULE_DEVICE_TABLE(of, afe4403_of_match);
 
 static int __maybe_unused afe4403_suspend(struct device *dev)
 {
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct iio_dev *indio_dev = spi_get_drvdata(to_spi_device(dev));
 	struct afe4403_data *afe = iio_priv(indio_dev);
 	int ret;
 
@@ -443,7 +443,7 @@ static int __maybe_unused afe4403_suspend(struct device *dev)
 
 static int __maybe_unused afe4403_resume(struct device *dev)
 {
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct iio_dev *indio_dev = spi_get_drvdata(to_spi_device(dev));
 	struct afe4403_data *afe = iio_priv(indio_dev);
 	int ret;
 
diff --git a/drivers/iio/health/afe4404.c b/drivers/iio/health/afe4404.c
index 45266404f7e3..964f5231a831 100644
--- a/drivers/iio/health/afe4404.c
+++ b/drivers/iio/health/afe4404.c
@@ -428,7 +428,7 @@ MODULE_DEVICE_TABLE(of, afe4404_of_match);
 
 static int __maybe_unused afe4404_suspend(struct device *dev)
 {
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct iio_dev *indio_dev = i2c_get_clientdata(to_i2c_client(dev));
 	struct afe4404_data *afe = iio_priv(indio_dev);
 	int ret;
 
@@ -449,7 +449,7 @@ static int __maybe_unused afe4404_suspend(struct device *dev)
 
 static int __maybe_unused afe4404_resume(struct device *dev)
 {
-	struct iio_dev *indio_dev = dev_to_iio_dev(dev);
+	struct iio_dev *indio_dev = i2c_get_clientdata(to_i2c_client(dev));
 	struct afe4404_data *afe = iio_priv(indio_dev);
 	int ret;
 
diff --git a/drivers/iio/health/max30100.c b/drivers/iio/health/max30100.c
index 90ab8a2d2846..183c14329d6e 100644
--- a/drivers/iio/health/max30100.c
+++ b/drivers/iio/health/max30100.c
@@ -238,7 +238,7 @@ static irqreturn_t max30100_interrupt_handler(int irq, void *private)
 
 	mutex_lock(&data->lock);
 
-	while (cnt || (cnt = max30100_fifo_count(data) > 0)) {
+	while (cnt || (cnt = max30100_fifo_count(data)) > 0) {
 		ret = max30100_read_measurement(data);
 		if (ret)
 			break;
diff --git a/drivers/iio/humidity/dht11.c b/drivers/iio/humidity/dht11.c
index 9c47bc98f3ac..2a22ad920333 100644
--- a/drivers/iio/humidity/dht11.c
+++ b/drivers/iio/humidity/dht11.c
@@ -71,7 +71,8 @@
  * a) select an implementation using busy loop polling on those systems
  * b) use the checksum to do some probabilistic decoding
  */
-#define DHT11_START_TRANSMISSION	18  /* ms */
+#define DHT11_START_TRANSMISSION_MIN	18000  /* us */
+#define DHT11_START_TRANSMISSION_MAX	20000  /* us */
 #define DHT11_MIN_TIMERES	34000  /* ns */
 #define DHT11_THRESHOLD		49000  /* ns */
 #define DHT11_AMBIG_LOW		23000  /* ns */
@@ -228,7 +229,8 @@ static int dht11_read_raw(struct iio_dev *iio_dev,
 		ret = gpio_direction_output(dht11->gpio, 0);
 		if (ret)
 			goto err;
-		msleep(DHT11_START_TRANSMISSION);
+		usleep_range(DHT11_START_TRANSMISSION_MIN,
+			     DHT11_START_TRANSMISSION_MAX);
 		ret = gpio_direction_input(dht11->gpio);
 		if (ret)
 			goto err;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index e7dcfac877ca..3e70a9c5d79d 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2811,7 +2811,8 @@ static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
 	if (!src_addr || !src_addr->sa_family) {
 		src_addr = (struct sockaddr *) &id->route.addr.src_addr;
 		src_addr->sa_family = dst_addr->sa_family;
-		if (dst_addr->sa_family == AF_INET6) {
+		if (IS_ENABLED(CONFIG_IPV6) &&
+		    dst_addr->sa_family == AF_INET6) {
 			struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *) src_addr;
 			struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *) dst_addr;
 			src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id;
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 1e62a5f0cb28..4609b921f899 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -134,6 +134,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 		 IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
 
 	if (access & IB_ACCESS_ON_DEMAND) {
+		put_pid(umem->pid);
 		ret = ib_umem_odp_get(context, umem);
 		if (ret) {
 			kfree(umem);
@@ -149,6 +150,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 
 	page_list = (struct page **) __get_free_page(GFP_KERNEL);
 	if (!page_list) {
+		put_pid(umem->pid);
 		kfree(umem);
 		return ERR_PTR(-ENOMEM);
 	}
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.h b/drivers/infiniband/hw/cxgb3/iwch_cm.h
index b9efadfffb4f..e66e75921797 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.h
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.h
@@ -55,14 +55,14 @@
 
 #define put_ep(ep) { \
 	PDBG("put_ep (via %s:%u) ep %p refcnt %d\n", __func__, __LINE__,  \
-	     ep, atomic_read(&((ep)->kref.refcount))); \
-	WARN_ON(atomic_read(&((ep)->kref.refcount)) < 1); \
+	     ep, kref_read(&((ep)->kref))); \
+	WARN_ON(kref_read(&((ep)->kref)) < 1); \
 	kref_put(&((ep)->kref), __free_ep); \
 }
 
 #define get_ep(ep) { \
 	PDBG("get_ep (via %s:%u) ep %p, refcnt %d\n", __func__, __LINE__, \
-	     ep, atomic_read(&((ep)->kref.refcount))); \
+	     ep, kref_read(&((ep)->kref))); \
 	kref_get(&((ep)->kref));  \
 }
 
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index 9d5fe1853da4..6262dc035f3c 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -1135,16 +1135,7 @@ static int iwch_query_port(struct ib_device *ibdev,
 
 	memset(props, 0, sizeof(struct ib_port_attr));
 	props->max_mtu = IB_MTU_4096;
-	if (netdev->mtu >= 4096)
-		props->active_mtu = IB_MTU_4096;
-	else if (netdev->mtu >= 2048)
-		props->active_mtu = IB_MTU_2048;
-	else if (netdev->mtu >= 1024)
-		props->active_mtu = IB_MTU_1024;
-	else if (netdev->mtu >= 512)
-		props->active_mtu = IB_MTU_512;
-	else
-		props->active_mtu = IB_MTU_256;
+	props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
 
 	if (!netif_carrier_ok(netdev))
 		props->state = IB_PORT_DOWN;
diff --git a/drivers/infiniband/hw/cxgb3/iwch_qp.c b/drivers/infiniband/hw/cxgb3/iwch_qp.c
index d939980a708f..a9194db7f9b8 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_qp.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_qp.c
@@ -961,7 +961,7 @@ int iwch_modify_qp(struct iwch_dev *rhp, struct iwch_qp *qhp,
 	case IWCH_QP_STATE_RTS:
 		switch (attrs->next_state) {
 		case IWCH_QP_STATE_CLOSING:
-			BUG_ON(atomic_read(&qhp->ep->com.kref.refcount) < 2);
+			BUG_ON(kref_read(&qhp->ep->com.kref) < 2);
 			qhp->attr.state = IWCH_QP_STATE_CLOSING;
 			if (!internal) {
 				abort=0;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index f1510cc76d2d..9398143d7c5e 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1804,20 +1804,21 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb)
 	skb_trim(skb, dlen);
 	mutex_lock(&ep->com.mutex);
 
-	/* update RX credits */
-	update_rx_credits(ep, dlen);
-
 	switch (ep->com.state) {
 	case MPA_REQ_SENT:
+		update_rx_credits(ep, dlen);
 		ep->rcv_seq += dlen;
 		disconnect = process_mpa_reply(ep, skb);
 		break;
 	case MPA_REQ_WAIT:
+		update_rx_credits(ep, dlen);
 		ep->rcv_seq += dlen;
 		disconnect = process_mpa_request(ep, skb);
 		break;
 	case FPDU_MODE: {
 		struct c4iw_qp_attributes attrs;
+
+		update_rx_credits(ep, dlen);
 		BUG_ON(!ep->com.qp);
 		if (status)
 			pr_err("%s Unexpected streaming data." \
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index 19c6477af19f..bec82a600d77 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -505,6 +505,15 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
 	}
 
 	/*
+	 * Special cqe for drain WR completions...
+	 */
+	if (CQE_OPCODE(hw_cqe) == C4IW_DRAIN_OPCODE) {
+		*cookie = CQE_DRAIN_COOKIE(hw_cqe);
+		*cqe = *hw_cqe;
+		goto skip_cqe;
+	}
+
+	/*
 	 * Gotta tweak READ completions:
 	 *	1) the cqe doesn't contain the sq_wptr from the wr.
 	 *	2) opcode not reflected from the wr.
@@ -753,6 +762,9 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 				c4iw_invalidate_mr(qhp->rhp,
 						   CQE_WRID_FR_STAG(&cqe));
 			break;
+		case C4IW_DRAIN_OPCODE:
+			wc->opcode = IB_WC_SEND;
+			break;
 		default:
 			printk(KERN_ERR MOD "Unexpected opcode %d "
 			       "in the CQE received for QPID=0x%0x\n",
@@ -817,15 +829,8 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 		}
 	}
 out:
-	if (wq) {
-		if (unlikely(qhp->attr.state != C4IW_QP_STATE_RTS)) {
-			if (t4_sq_empty(wq))
-				complete(&qhp->sq_drained);
-			if (t4_rq_empty(wq))
-				complete(&qhp->rq_drained);
-		}
+	if (wq)
 		spin_unlock(&qhp->lock);
-	}
 	return ret;
 }
 
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 516b0ae6dc3f..40c0e7b9fc6e 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -846,9 +846,17 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 		}
 	}
 
+	rdev->free_workq = create_singlethread_workqueue("iw_cxgb4_free");
+	if (!rdev->free_workq) {
+		err = -ENOMEM;
+		goto err_free_status_page;
+	}
+
 	rdev->status_page->db_off = 0;
 
 	return 0;
+err_free_status_page:
+	free_page((unsigned long)rdev->status_page);
 destroy_ocqp_pool:
 	c4iw_ocqp_pool_destroy(rdev);
 destroy_rqtpool:
@@ -862,6 +870,7 @@ destroy_resource:
 
 static void c4iw_rdev_close(struct c4iw_rdev *rdev)
 {
+	destroy_workqueue(rdev->free_workq);
 	kfree(rdev->wr_log);
 	free_page((unsigned long)rdev->status_page);
 	c4iw_pblpool_destroy(rdev);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 4788e1a46fde..d19662f635b1 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -45,6 +45,7 @@
 #include <linux/kref.h>
 #include <linux/timer.h>
 #include <linux/io.h>
+#include <linux/workqueue.h>
 
 #include <asm/byteorder.h>
 
@@ -107,6 +108,7 @@ struct c4iw_dev_ucontext {
 	struct list_head qpids;
 	struct list_head cqids;
 	struct mutex lock;
+	struct kref kref;
 };
 
 enum c4iw_rdev_flags {
@@ -183,6 +185,7 @@ struct c4iw_rdev {
 	atomic_t wr_log_idx;
 	struct wr_log_entry *wr_log;
 	int wr_log_size;
+	struct workqueue_struct *free_workq;
 };
 
 static inline int c4iw_fatal_error(struct c4iw_rdev *rdev)
@@ -480,8 +483,8 @@ struct c4iw_qp {
 	wait_queue_head_t wait;
 	struct timer_list timer;
 	int sq_sig_all;
-	struct completion rq_drained;
-	struct completion sq_drained;
+	struct work_struct free_work;
+	struct c4iw_ucontext *ucontext;
 };
 
 static inline struct c4iw_qp *to_c4iw_qp(struct ib_qp *ibqp)
@@ -495,6 +498,7 @@ struct c4iw_ucontext {
 	u32 key;
 	spinlock_t mmap_lock;
 	struct list_head mmaps;
+	struct kref kref;
 };
 
 static inline struct c4iw_ucontext *to_c4iw_ucontext(struct ib_ucontext *c)
@@ -502,6 +506,18 @@ static inline struct c4iw_ucontext *to_c4iw_ucontext(struct ib_ucontext *c)
 	return container_of(c, struct c4iw_ucontext, ibucontext);
 }
 
+void _c4iw_free_ucontext(struct kref *kref);
+
+static inline void c4iw_put_ucontext(struct c4iw_ucontext *ucontext)
+{
+	kref_put(&ucontext->kref, _c4iw_free_ucontext);
+}
+
+static inline void c4iw_get_ucontext(struct c4iw_ucontext *ucontext)
+{
+	kref_get(&ucontext->kref);
+}
+
 struct c4iw_mm_entry {
 	struct list_head entry;
 	u64 addr;
@@ -615,6 +631,8 @@ static inline int to_ib_qp_state(int c4iw_qp_state)
 	return IB_QPS_ERR;
 }
 
+#define C4IW_DRAIN_OPCODE FW_RI_SGE_EC_CR_RETURN
+
 static inline u32 c4iw_ib_to_tpt_access(int a)
 {
 	return (a & IB_ACCESS_REMOTE_WRITE ? FW_RI_MEM_ACCESS_REM_WRITE : 0) |
@@ -654,14 +672,14 @@ enum c4iw_mmid_state {
 
 #define c4iw_put_ep(ep) { \
 	PDBG("put_ep (via %s:%u) ep %p refcnt %d\n", __func__, __LINE__,  \
-	     ep, atomic_read(&((ep)->kref.refcount))); \
-	WARN_ON(atomic_read(&((ep)->kref.refcount)) < 1); \
+	     ep, kref_read(&((ep)->kref))); \
+	WARN_ON(kref_read(&((ep)->kref)) < 1); \
 	kref_put(&((ep)->kref), _c4iw_free_ep); \
 }
 
 #define c4iw_get_ep(ep) { \
 	PDBG("get_ep (via %s:%u) ep %p, refcnt %d\n", __func__, __LINE__, \
-	     ep, atomic_read(&((ep)->kref.refcount))); \
+	     ep, kref_read(&((ep)->kref))); \
 	kref_get(&((ep)->kref));  \
 }
 void _c4iw_free_ep(struct kref *kref);
@@ -997,8 +1015,6 @@ extern int c4iw_wr_log;
 extern int db_fc_threshold;
 extern int db_coalescing_threshold;
 extern int use_dsgl;
-void c4iw_drain_rq(struct ib_qp *qp);
-void c4iw_drain_sq(struct ib_qp *qp);
 void c4iw_invalidate_mr(struct c4iw_dev *rhp, u32 rkey);
 
 #endif
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 49b51b7e0fd7..3345e1c312f7 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -93,17 +93,28 @@ static int c4iw_process_mad(struct ib_device *ibdev, int mad_flags,
 	return -ENOSYS;
 }
 
-static int c4iw_dealloc_ucontext(struct ib_ucontext *context)
+void _c4iw_free_ucontext(struct kref *kref)
 {
-	struct c4iw_dev *rhp = to_c4iw_dev(context->device);
-	struct c4iw_ucontext *ucontext = to_c4iw_ucontext(context);
+	struct c4iw_ucontext *ucontext;
+	struct c4iw_dev *rhp;
 	struct c4iw_mm_entry *mm, *tmp;
 
-	PDBG("%s context %p\n", __func__, context);
+	ucontext = container_of(kref, struct c4iw_ucontext, kref);
+	rhp = to_c4iw_dev(ucontext->ibucontext.device);
+
+	PDBG("%s ucontext %p\n", __func__, ucontext);
 	list_for_each_entry_safe(mm, tmp, &ucontext->mmaps, entry)
 		kfree(mm);
 	c4iw_release_dev_ucontext(&rhp->rdev, &ucontext->uctx);
 	kfree(ucontext);
+}
+
+static int c4iw_dealloc_ucontext(struct ib_ucontext *context)
+{
+	struct c4iw_ucontext *ucontext = to_c4iw_ucontext(context);
+
+	PDBG("%s context %p\n", __func__, context);
+	c4iw_put_ucontext(ucontext);
 	return 0;
 }
 
@@ -127,6 +138,7 @@ static struct ib_ucontext *c4iw_alloc_ucontext(struct ib_device *ibdev,
 	c4iw_init_dev_ucontext(&rhp->rdev, &context->uctx);
 	INIT_LIST_HEAD(&context->mmaps);
 	spin_lock_init(&context->mmap_lock);
+	kref_init(&context->kref);
 
 	if (udata->outlen < sizeof(uresp) - sizeof(uresp.reserved)) {
 		if (!warned++)
@@ -361,16 +373,7 @@ static int c4iw_query_port(struct ib_device *ibdev, u8 port,
 
 	memset(props, 0, sizeof(struct ib_port_attr));
 	props->max_mtu = IB_MTU_4096;
-	if (netdev->mtu >= 4096)
-		props->active_mtu = IB_MTU_4096;
-	else if (netdev->mtu >= 2048)
-		props->active_mtu = IB_MTU_2048;
-	else if (netdev->mtu >= 1024)
-		props->active_mtu = IB_MTU_1024;
-	else if (netdev->mtu >= 512)
-		props->active_mtu = IB_MTU_512;
-	else
-		props->active_mtu = IB_MTU_256;
+	props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
 
 	if (!netif_carrier_ok(netdev))
 		props->state = IB_PORT_DOWN;
@@ -607,8 +610,6 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION;
 	dev->ibdev.get_port_immutable = c4iw_port_immutable;
 	dev->ibdev.get_dev_fw_str = get_dev_fw_str;
-	dev->ibdev.drain_sq = c4iw_drain_sq;
-	dev->ibdev.drain_rq = c4iw_drain_rq;
 
 	dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL);
 	if (!dev->ibdev.iwcm)
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index cda5542e13a2..d4fd2f5c8326 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -715,13 +715,32 @@ static int build_inv_stag(union t4_wr *wqe, struct ib_send_wr *wr, u8 *len16)
 	return 0;
 }
 
-static void _free_qp(struct kref *kref)
+static void free_qp_work(struct work_struct *work)
+{
+	struct c4iw_ucontext *ucontext;
+	struct c4iw_qp *qhp;
+	struct c4iw_dev *rhp;
+
+	qhp = container_of(work, struct c4iw_qp, free_work);
+	ucontext = qhp->ucontext;
+	rhp = qhp->rhp;
+
+	PDBG("%s qhp %p ucontext %p\n", __func__, qhp, ucontext);
+	destroy_qp(&rhp->rdev, &qhp->wq,
+		   ucontext ? &ucontext->uctx : &rhp->rdev.uctx);
+
+	if (ucontext)
+		c4iw_put_ucontext(ucontext);
+	kfree(qhp);
+}
+
+static void queue_qp_free(struct kref *kref)
 {
 	struct c4iw_qp *qhp;
 
 	qhp = container_of(kref, struct c4iw_qp, kref);
 	PDBG("%s qhp %p\n", __func__, qhp);
-	kfree(qhp);
+	queue_work(qhp->rhp->rdev.free_workq, &qhp->free_work);
 }
 
 void c4iw_qp_add_ref(struct ib_qp *qp)
@@ -733,7 +752,7 @@ void c4iw_qp_add_ref(struct ib_qp *qp)
 void c4iw_qp_rem_ref(struct ib_qp *qp)
 {
 	PDBG("%s ib_qp %p\n", __func__, qp);
-	kref_put(&to_c4iw_qp(qp)->kref, _free_qp);
+	kref_put(&to_c4iw_qp(qp)->kref, queue_qp_free);
 }
 
 static void add_to_fc_list(struct list_head *head, struct list_head *entry)
@@ -776,6 +795,64 @@ static int ring_kernel_rq_db(struct c4iw_qp *qhp, u16 inc)
 	return 0;
 }
 
+static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr)
+{
+	struct t4_cqe cqe = {};
+	struct c4iw_cq *schp;
+	unsigned long flag;
+	struct t4_cq *cq;
+
+	schp = to_c4iw_cq(qhp->ibqp.send_cq);
+	cq = &schp->cq;
+
+	cqe.u.drain_cookie = wr->wr_id;
+	cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) |
+				 CQE_OPCODE_V(C4IW_DRAIN_OPCODE) |
+				 CQE_TYPE_V(1) |
+				 CQE_SWCQE_V(1) |
+				 CQE_QPID_V(qhp->wq.sq.qid));
+
+	spin_lock_irqsave(&schp->lock, flag);
+	cqe.bits_type_ts = cpu_to_be64(CQE_GENBIT_V((u64)cq->gen));
+	cq->sw_queue[cq->sw_pidx] = cqe;
+	t4_swcq_produce(cq);
+	spin_unlock_irqrestore(&schp->lock, flag);
+
+	spin_lock_irqsave(&schp->comp_handler_lock, flag);
+	(*schp->ibcq.comp_handler)(&schp->ibcq,
+				   schp->ibcq.cq_context);
+	spin_unlock_irqrestore(&schp->comp_handler_lock, flag);
+}
+
+static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr)
+{
+	struct t4_cqe cqe = {};
+	struct c4iw_cq *rchp;
+	unsigned long flag;
+	struct t4_cq *cq;
+
+	rchp = to_c4iw_cq(qhp->ibqp.recv_cq);
+	cq = &rchp->cq;
+
+	cqe.u.drain_cookie = wr->wr_id;
+	cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) |
+				 CQE_OPCODE_V(C4IW_DRAIN_OPCODE) |
+				 CQE_TYPE_V(0) |
+				 CQE_SWCQE_V(1) |
+				 CQE_QPID_V(qhp->wq.sq.qid));
+
+	spin_lock_irqsave(&rchp->lock, flag);
+	cqe.bits_type_ts = cpu_to_be64(CQE_GENBIT_V((u64)cq->gen));
+	cq->sw_queue[cq->sw_pidx] = cqe;
+	t4_swcq_produce(cq);
+	spin_unlock_irqrestore(&rchp->lock, flag);
+
+	spin_lock_irqsave(&rchp->comp_handler_lock, flag);
+	(*rchp->ibcq.comp_handler)(&rchp->ibcq,
+				   rchp->ibcq.cq_context);
+	spin_unlock_irqrestore(&rchp->comp_handler_lock, flag);
+}
+
 int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		   struct ib_send_wr **bad_wr)
 {
@@ -794,8 +871,8 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	spin_lock_irqsave(&qhp->lock, flag);
 	if (t4_wq_in_error(&qhp->wq)) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
-		*bad_wr = wr;
-		return -EINVAL;
+		complete_sq_drain_wr(qhp, wr);
+		return err;
 	}
 	num_wrs = t4_sq_avail(&qhp->wq);
 	if (num_wrs == 0) {
@@ -937,8 +1014,8 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 	spin_lock_irqsave(&qhp->lock, flag);
 	if (t4_wq_in_error(&qhp->wq)) {
 		spin_unlock_irqrestore(&qhp->lock, flag);
-		*bad_wr = wr;
-		return -EINVAL;
+		complete_rq_drain_wr(qhp, wr);
+		return err;
 	}
 	num_wrs = t4_rq_avail(&qhp->wq);
 	if (num_wrs == 0) {
@@ -1503,7 +1580,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 	case C4IW_QP_STATE_RTS:
 		switch (attrs->next_state) {
 		case C4IW_QP_STATE_CLOSING:
-			BUG_ON(atomic_read(&qhp->ep->com.kref.refcount) < 2);
+			BUG_ON(kref_read(&qhp->ep->com.kref) < 2);
 			t4_set_wq_in_error(&qhp->wq);
 			set_state(qhp, C4IW_QP_STATE_CLOSING);
 			ep = qhp->ep;
@@ -1550,7 +1627,12 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 		}
 		break;
 	case C4IW_QP_STATE_CLOSING:
-		if (!internal) {
+
+		/*
+		 * Allow kernel users to move to ERROR for qp draining.
+		 */
+		if (!internal && (qhp->ibqp.uobject || attrs->next_state !=
+				  C4IW_QP_STATE_ERROR)) {
 			ret = -EINVAL;
 			goto out;
 		}
@@ -1643,7 +1725,6 @@ int c4iw_destroy_qp(struct ib_qp *ib_qp)
 	struct c4iw_dev *rhp;
 	struct c4iw_qp *qhp;
 	struct c4iw_qp_attributes attrs;
-	struct c4iw_ucontext *ucontext;
 
 	qhp = to_c4iw_qp(ib_qp);
 	rhp = qhp->rhp;
@@ -1663,11 +1744,6 @@ int c4iw_destroy_qp(struct ib_qp *ib_qp)
 	spin_unlock_irq(&rhp->lock);
 	free_ird(rhp, qhp->attr.max_ird);
 
-	ucontext = ib_qp->uobject ?
-		   to_c4iw_ucontext(ib_qp->uobject->context) : NULL;
-	destroy_qp(&rhp->rdev, &qhp->wq,
-		   ucontext ? &ucontext->uctx : &rhp->rdev.uctx);
-
 	c4iw_qp_rem_ref(ib_qp);
 
 	PDBG("%s ib_qp %p qpid 0x%0x\n", __func__, ib_qp, qhp->wq.sq.qid);
@@ -1763,11 +1839,10 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 	qhp->attr.max_ird = 0;
 	qhp->sq_sig_all = attrs->sq_sig_type == IB_SIGNAL_ALL_WR;
 	spin_lock_init(&qhp->lock);
-	init_completion(&qhp->sq_drained);
-	init_completion(&qhp->rq_drained);
 	mutex_init(&qhp->mutex);
 	init_waitqueue_head(&qhp->wait);
 	kref_init(&qhp->kref);
+	INIT_WORK(&qhp->free_work, free_qp_work);
 
 	ret = insert_handle(rhp, &rhp->qpidr, qhp, qhp->wq.sq.qid);
 	if (ret)
@@ -1854,6 +1929,9 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 			ma_sync_key_mm->len = PAGE_SIZE;
 			insert_mmap(ucontext, ma_sync_key_mm);
 		}
+
+		c4iw_get_ucontext(ucontext);
+		qhp->ucontext = ucontext;
 	}
 	qhp->ibqp.qp_num = qhp->wq.sq.qid;
 	init_timer(&(qhp->timer));
@@ -1958,40 +2036,3 @@ int c4iw_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	init_attr->sq_sig_type = qhp->sq_sig_all ? IB_SIGNAL_ALL_WR : 0;
 	return 0;
 }
-
-static void move_qp_to_err(struct c4iw_qp *qp)
-{
-	struct c4iw_qp_attributes attrs = { .next_state = C4IW_QP_STATE_ERROR };
-
-	(void)c4iw_modify_qp(qp->rhp, qp, C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
-}
-
-void c4iw_drain_sq(struct ib_qp *ibqp)
-{
-	struct c4iw_qp *qp = to_c4iw_qp(ibqp);
-	unsigned long flag;
-	bool need_to_wait;
-
-	move_qp_to_err(qp);
-	spin_lock_irqsave(&qp->lock, flag);
-	need_to_wait = !t4_sq_empty(&qp->wq);
-	spin_unlock_irqrestore(&qp->lock, flag);
-
-	if (need_to_wait)
-		wait_for_completion(&qp->sq_drained);
-}
-
-void c4iw_drain_rq(struct ib_qp *ibqp)
-{
-	struct c4iw_qp *qp = to_c4iw_qp(ibqp);
-	unsigned long flag;
-	bool need_to_wait;
-
-	move_qp_to_err(qp);
-	spin_lock_irqsave(&qp->lock, flag);
-	need_to_wait = !t4_rq_empty(&qp->wq);
-	spin_unlock_irqrestore(&qp->lock, flag);
-
-	if (need_to_wait)
-		wait_for_completion(&qp->rq_drained);
-}
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index 862381aa83c8..640d22148a3e 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -179,6 +179,7 @@ struct t4_cqe {
 			__be32 wrid_hi;
 			__be32 wrid_low;
 		} gen;
+		u64 drain_cookie;
 	} u;
 	__be64 reserved;
 	__be64 bits_type_ts;
@@ -238,6 +239,7 @@ struct t4_cqe {
 /* generic accessor macros */
 #define CQE_WRID_HI(x)		(be32_to_cpu((x)->u.gen.wrid_hi))
 #define CQE_WRID_LOW(x)		(be32_to_cpu((x)->u.gen.wrid_low))
+#define CQE_DRAIN_COOKIE(x)	((x)->u.drain_cookie)
 
 /* macros for flit 3 of the cqe */
 #define CQE_GENBIT_S	63
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 29e97df9e1a7..4c000d60d5c6 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -100,16 +100,7 @@ static int i40iw_query_port(struct ib_device *ibdev,
 	memset(props, 0, sizeof(*props));
 
 	props->max_mtu = IB_MTU_4096;
-	if (netdev->mtu >= 4096)
-		props->active_mtu = IB_MTU_4096;
-	else if (netdev->mtu >= 2048)
-		props->active_mtu = IB_MTU_2048;
-	else if (netdev->mtu >= 1024)
-		props->active_mtu = IB_MTU_1024;
-	else if (netdev->mtu >= 512)
-		props->active_mtu = IB_MTU_512;
-	else
-		props->active_mtu = IB_MTU_256;
+	props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
 
 	props->lid = 1;
 	if (netif_carrier_ok(iwdev->netdev))
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index aff9fb14768b..5a31f3c6a421 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -478,17 +478,7 @@ static int nes_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr
 	memset(props, 0, sizeof(*props));
 
 	props->max_mtu = IB_MTU_4096;
-
-	if (netdev->mtu  >= 4096)
-		props->active_mtu = IB_MTU_4096;
-	else if (netdev->mtu  >= 2048)
-		props->active_mtu = IB_MTU_2048;
-	else if (netdev->mtu  >= 1024)
-		props->active_mtu = IB_MTU_1024;
-	else if (netdev->mtu  >= 512)
-		props->active_mtu = IB_MTU_512;
-	else
-		props->active_mtu = IB_MTU_256;
+	props->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
 
 	props->lid = 1;
 	props->lmc = 0;
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 7b74d09a8217..3ac8aa5ef37d 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -576,8 +576,7 @@ static int qedr_set_device_attr(struct qedr_dev *dev)
 	return 0;
 }
 
-void qedr_unaffiliated_event(void *context,
-			     u8 event_code)
+void qedr_unaffiliated_event(void *context, u8 event_code)
 {
 	pr_err("unaffiliated event not implemented yet\n");
 }
@@ -792,6 +791,9 @@ static struct qedr_dev *qedr_add(struct qed_dev *cdev, struct pci_dev *pdev,
 		if (device_create_file(&dev->ibdev.dev, qedr_attributes[i]))
 			goto sysfs_err;
 
+	if (!test_and_set_bit(QEDR_ENET_STATE_BIT, &dev->enet_state))
+		qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ACTIVE);
+
 	DP_DEBUG(dev, QEDR_MSG_INIT, "qedr driver loaded successfully\n");
 	return dev;
 
@@ -824,11 +826,10 @@ static void qedr_remove(struct qedr_dev *dev)
 	ib_dealloc_device(&dev->ibdev);
 }
 
-static int qedr_close(struct qedr_dev *dev)
+static void qedr_close(struct qedr_dev *dev)
 {
-	qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ERR);
-
-	return 0;
+	if (test_and_clear_bit(QEDR_ENET_STATE_BIT, &dev->enet_state))
+		qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ERR);
 }
 
 static void qedr_shutdown(struct qedr_dev *dev)
@@ -837,6 +838,12 @@ static void qedr_shutdown(struct qedr_dev *dev)
 	qedr_remove(dev);
 }
 
+static void qedr_open(struct qedr_dev *dev)
+{
+	if (!test_and_set_bit(QEDR_ENET_STATE_BIT, &dev->enet_state))
+		qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_PORT_ACTIVE);
+}
+
 static void qedr_mac_address_change(struct qedr_dev *dev)
 {
 	union ib_gid *sgid = &dev->sgid_tbl[0];
@@ -863,7 +870,7 @@ static void qedr_mac_address_change(struct qedr_dev *dev)
 
 	ether_addr_copy(dev->gsi_ll2_mac_address, dev->ndev->dev_addr);
 
-	qedr_ib_dispatch_event(dev, 1, IB_EVENT_GID_CHANGE);
+	qedr_ib_dispatch_event(dev, QEDR_PORT, IB_EVENT_GID_CHANGE);
 
 	if (rc)
 		DP_ERR(dev, "Error updating mac filter\n");
@@ -877,7 +884,7 @@ static void qedr_notify(struct qedr_dev *dev, enum qede_roce_event event)
 {
 	switch (event) {
 	case QEDE_UP:
-		qedr_ib_dispatch_event(dev, 1, IB_EVENT_PORT_ACTIVE);
+		qedr_open(dev);
 		break;
 	case QEDE_DOWN:
 		qedr_close(dev);
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index 620badd7d4fb..bb32e4792ec9 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -113,6 +113,8 @@ struct qedr_device_attr {
 	struct qed_rdma_events events;
 };
 
+#define QEDR_ENET_STATE_BIT	(0)
+
 struct qedr_dev {
 	struct ib_device	ibdev;
 	struct qed_dev		*cdev;
@@ -153,6 +155,8 @@ struct qedr_dev {
 	struct qedr_cq		*gsi_sqcq;
 	struct qedr_cq		*gsi_rqcq;
 	struct qedr_qp		*gsi_qp;
+
+	unsigned long enet_state;
 };
 
 #define QEDR_MAX_SQ_PBL			(0x8000)
@@ -188,6 +192,7 @@ struct qedr_dev {
 #define QEDR_ROCE_MAX_CNQ_SIZE		(0x4000)
 
 #define QEDR_MAX_PORT			(1)
+#define QEDR_PORT			(1)
 
 #define QEDR_UVERBS(CMD_NAME) (1ull << IB_USER_VERBS_CMD_##CMD_NAME)
 
@@ -251,9 +256,6 @@ struct qedr_cq {
 
 	u16 icid;
 
-	/* Lock to protect completion handler */
-	spinlock_t comp_handler_lock;
-
 	/* Lock to protect multiplem CQ's */
 	spinlock_t cq_lock;
 	u8 arm_flags;
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c
index 63890ebb72bd..a9a8d8745d2e 100644
--- a/drivers/infiniband/hw/qedr/qedr_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_cm.c
@@ -87,11 +87,8 @@ void qedr_ll2_tx_cb(void *_qdev, struct qed_roce_ll2_packet *pkt)
 	qedr_inc_sw_gsi_cons(&qp->sq);
 	spin_unlock_irqrestore(&qp->q_lock, flags);
 
-	if (cq->ibcq.comp_handler) {
-		spin_lock_irqsave(&cq->comp_handler_lock, flags);
+	if (cq->ibcq.comp_handler)
 		(*cq->ibcq.comp_handler) (&cq->ibcq, cq->ibcq.cq_context);
-		spin_unlock_irqrestore(&cq->comp_handler_lock, flags);
-	}
 }
 
 void qedr_ll2_rx_cb(void *_dev, struct qed_roce_ll2_packet *pkt,
@@ -113,11 +110,8 @@ void qedr_ll2_rx_cb(void *_dev, struct qed_roce_ll2_packet *pkt,
 
 	spin_unlock_irqrestore(&qp->q_lock, flags);
 
-	if (cq->ibcq.comp_handler) {
-		spin_lock_irqsave(&cq->comp_handler_lock, flags);
+	if (cq->ibcq.comp_handler)
 		(*cq->ibcq.comp_handler) (&cq->ibcq, cq->ibcq.cq_context);
-		spin_unlock_irqrestore(&cq->comp_handler_lock, flags);
-	}
 }
 
 static void qedr_destroy_gsi_cq(struct qedr_dev *dev,
@@ -404,9 +398,9 @@ static inline int qedr_gsi_build_packet(struct qedr_dev *dev,
 	}
 
 	if (ether_addr_equal(udh.eth.smac_h, udh.eth.dmac_h))
-		packet->tx_dest = QED_ROCE_LL2_TX_DEST_NW;
-	else
 		packet->tx_dest = QED_ROCE_LL2_TX_DEST_LB;
+	else
+		packet->tx_dest = QED_ROCE_LL2_TX_DEST_NW;
 
 	packet->roce_mode = roce_mode;
 	memcpy(packet->header.vaddr, ud_header_buffer, header_size);
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 57c8de208077..c7d6c9a783bd 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -471,8 +471,6 @@ struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev,
 			    struct ib_ucontext *context, struct ib_udata *udata)
 {
 	struct qedr_dev *dev = get_qedr_dev(ibdev);
-	struct qedr_ucontext *uctx = NULL;
-	struct qedr_alloc_pd_uresp uresp;
 	struct qedr_pd *pd;
 	u16 pd_id;
 	int rc;
@@ -489,21 +487,33 @@ struct ib_pd *qedr_alloc_pd(struct ib_device *ibdev,
 	if (!pd)
 		return ERR_PTR(-ENOMEM);
 
-	dev->ops->rdma_alloc_pd(dev->rdma_ctx, &pd_id);
+	rc = dev->ops->rdma_alloc_pd(dev->rdma_ctx, &pd_id);
+	if (rc)
+		goto err;
 
-	uresp.pd_id = pd_id;
 	pd->pd_id = pd_id;
 
 	if (udata && context) {
+		struct qedr_alloc_pd_uresp uresp;
+
+		uresp.pd_id = pd_id;
+
 		rc = ib_copy_to_udata(udata, &uresp, sizeof(uresp));
-		if (rc)
+		if (rc) {
 			DP_ERR(dev, "copy error pd_id=0x%x.\n", pd_id);
-		uctx = get_qedr_ucontext(context);
-		uctx->pd = pd;
-		pd->uctx = uctx;
+			dev->ops->rdma_dealloc_pd(dev->rdma_ctx, pd_id);
+			goto err;
+		}
+
+		pd->uctx = get_qedr_ucontext(context);
+		pd->uctx->pd = pd;
 	}
 
 	return &pd->ibpd;
+
+err:
+	kfree(pd);
+	return ERR_PTR(rc);
 }
 
 int qedr_dealloc_pd(struct ib_pd *ibpd)
@@ -1600,7 +1610,7 @@ err0:
 	return ERR_PTR(-EFAULT);
 }
 
-enum ib_qp_state qedr_get_ibqp_state(enum qed_roce_qp_state qp_state)
+static enum ib_qp_state qedr_get_ibqp_state(enum qed_roce_qp_state qp_state)
 {
 	switch (qp_state) {
 	case QED_ROCE_QP_STATE_RESET:
@@ -1621,7 +1631,8 @@ enum ib_qp_state qedr_get_ibqp_state(enum qed_roce_qp_state qp_state)
 	return IB_QPS_ERR;
 }
 
-enum qed_roce_qp_state qedr_get_state_from_ibqp(enum ib_qp_state qp_state)
+static enum qed_roce_qp_state qedr_get_state_from_ibqp(
+					enum ib_qp_state qp_state)
 {
 	switch (qp_state) {
 	case IB_QPS_RESET:
@@ -1657,7 +1668,7 @@ static int qedr_update_qp_state(struct qedr_dev *dev,
 	int status = 0;
 
 	if (new_state == qp->state)
-		return 1;
+		return 0;
 
 	switch (qp->state) {
 	case QED_ROCE_QP_STATE_RESET:
@@ -1733,6 +1744,14 @@ static int qedr_update_qp_state(struct qedr_dev *dev,
 		/* ERR->XXX */
 		switch (new_state) {
 		case QED_ROCE_QP_STATE_RESET:
+			if ((qp->rq.prod != qp->rq.cons) ||
+			    (qp->sq.prod != qp->sq.cons)) {
+				DP_NOTICE(dev,
+					  "Error->Reset with rq/sq not empty rq.prod=%x rq.cons=%x sq.prod=%x sq.cons=%x\n",
+					  qp->rq.prod, qp->rq.cons, qp->sq.prod,
+					  qp->sq.cons);
+				status = -EINVAL;
+			}
 			break;
 		default:
 			status = -EINVAL;
@@ -1865,7 +1884,6 @@ int qedr_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 			 qp_params.sgid.dwords[2], qp_params.sgid.dwords[3]);
 		DP_DEBUG(dev, QEDR_MSG_QP, "remote_mac=[%pM]\n",
 			 qp_params.remote_mac_addr);
-;
 
 		qp_params.mtu = qp->mtu;
 		qp_params.lb_indication = false;
@@ -2016,7 +2034,7 @@ int qedr_query_qp(struct ib_qp *ibqp,
 
 	qp_attr->qp_state = qedr_get_ibqp_state(params.state);
 	qp_attr->cur_qp_state = qedr_get_ibqp_state(params.state);
-	qp_attr->path_mtu = iboe_get_mtu(params.mtu);
+	qp_attr->path_mtu = ib_mtu_int_to_enum(params.mtu);
 	qp_attr->path_mig_state = IB_MIG_MIGRATED;
 	qp_attr->rq_psn = params.rq_psn;
 	qp_attr->sq_psn = params.sq_psn;
@@ -2028,7 +2046,7 @@ int qedr_query_qp(struct ib_qp *ibqp,
 	qp_attr->cap.max_recv_wr = qp->rq.max_wr;
 	qp_attr->cap.max_send_sge = qp->sq.max_sges;
 	qp_attr->cap.max_recv_sge = qp->rq.max_sges;
-	qp_attr->cap.max_inline_data = qp->max_inline_data;
+	qp_attr->cap.max_inline_data = ROCE_REQ_MAX_INLINE_DATA_SIZE;
 	qp_init_attr->cap = qp_attr->cap;
 
 	memcpy(&qp_attr->ah_attr.grh.dgid.raw[0], &params.dgid.bytes[0],
@@ -2302,7 +2320,8 @@ int qedr_dereg_mr(struct ib_mr *ib_mr)
 	return rc;
 }
 
-struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd, int max_page_list_len)
+static struct qedr_mr *__qedr_alloc_mr(struct ib_pd *ibpd,
+				       int max_page_list_len)
 {
 	struct qedr_pd *pd = get_qedr_pd(ibpd);
 	struct qedr_dev *dev = get_qedr_dev(ibpd->device);
@@ -2704,7 +2723,7 @@ static int qedr_prepare_reg(struct qedr_qp *qp,
 	return 0;
 }
 
-enum ib_wc_opcode qedr_ib_to_wc_opcode(enum ib_wr_opcode opcode)
+static enum ib_wc_opcode qedr_ib_to_wc_opcode(enum ib_wr_opcode opcode)
 {
 	switch (opcode) {
 	case IB_WR_RDMA_WRITE:
@@ -2729,7 +2748,7 @@ enum ib_wc_opcode qedr_ib_to_wc_opcode(enum ib_wr_opcode opcode)
 	}
 }
 
-inline bool qedr_can_post_send(struct qedr_qp *qp, struct ib_send_wr *wr)
+static inline bool qedr_can_post_send(struct qedr_qp *qp, struct ib_send_wr *wr)
 {
 	int wq_is_full, err_wr, pbl_is_full;
 	struct qedr_dev *dev = qp->dev;
@@ -2766,7 +2785,7 @@ inline bool qedr_can_post_send(struct qedr_qp *qp, struct ib_send_wr *wr)
 	return true;
 }
 
-int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
+static int __qedr_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		     struct ib_send_wr **bad_wr)
 {
 	struct qedr_dev *dev = get_qedr_dev(ibqp->device);
@@ -3234,9 +3253,10 @@ static int qedr_poll_cq_req(struct qedr_dev *dev,
 				  IB_WC_SUCCESS, 0);
 		break;
 	case RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR:
-		DP_ERR(dev,
-		       "Error: POLL CQ with RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR. CQ icid=0x%x, QP icid=0x%x\n",
-		       cq->icid, qp->icid);
+		if (qp->state != QED_ROCE_QP_STATE_ERR)
+			DP_ERR(dev,
+			       "Error: POLL CQ with RDMA_CQE_REQ_STS_WORK_REQUEST_FLUSHED_ERR. CQ icid=0x%x, QP icid=0x%x\n",
+			       cq->icid, qp->icid);
 		cnt = process_req(dev, qp, cq, num_entries, wc, req->sq_cons,
 				  IB_WC_WR_FLUSH_ERR, 1);
 		break;
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c
index 80ef3f8998c8..04443242e258 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_sysfs.c
@@ -80,7 +80,7 @@ usnic_ib_show_config(struct device *device, struct device_attribute *attr,
 	left = PAGE_SIZE;
 
 	mutex_lock(&us_ibdev->usdev_lock);
-	if (atomic_read(&us_ibdev->vf_cnt.refcount) > 0) {
+	if (kref_read(&us_ibdev->vf_cnt) > 0) {
 		char *busname;
 
 		/*
@@ -99,7 +99,7 @@ usnic_ib_show_config(struct device *device, struct device_attribute *attr,
 			PCI_FUNC(us_ibdev->pdev->devfn),
 			netdev_name(us_ibdev->netdev),
 			us_ibdev->ufdev->mac,
-			atomic_read(&us_ibdev->vf_cnt.refcount));
+			kref_read(&us_ibdev->vf_cnt));
 		UPDATE_PTR_LEFT(n, ptr, left);
 
 		for (res_type = USNIC_VNIC_RES_TYPE_EOL;
@@ -147,7 +147,7 @@ usnic_ib_show_max_vf(struct device *device, struct device_attribute *attr,
 	us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev);
 
 	return scnprintf(buf, PAGE_SIZE, "%u\n",
-			atomic_read(&us_ibdev->vf_cnt.refcount));
+			kref_read(&us_ibdev->vf_cnt));
 }
 
 static ssize_t
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index 74819a7951e2..69df8e353123 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -291,11 +291,11 @@ int usnic_ib_query_device(struct ib_device *ibdev,
 	qp_per_vf = max(us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_WQ],
 			us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_RQ]);
 	props->max_qp = qp_per_vf *
-		atomic_read(&us_ibdev->vf_cnt.refcount);
+		kref_read(&us_ibdev->vf_cnt);
 	props->device_cap_flags = IB_DEVICE_PORT_ACTIVE_EVENT |
 		IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
 	props->max_cq = us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_CQ] *
-		atomic_read(&us_ibdev->vf_cnt.refcount);
+		kref_read(&us_ibdev->vf_cnt);
 	props->max_pd = USNIC_UIOM_MAX_PD_CNT;
 	props->max_mr = USNIC_UIOM_MAX_MR_CNT;
 	props->local_ca_ack_delay = 0;
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index 231a1ce1f4be..bd8fbd3d2032 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -1029,7 +1029,7 @@ static int pvrdma_pci_probe(struct pci_dev *pdev,
 	if (ret) {
 		dev_err(&pdev->dev, "failed to allocate interrupts\n");
 		ret = -ENOMEM;
-		goto err_netdevice;
+		goto err_free_cq_ring;
 	}
 
 	/* Allocate UAR table. */
@@ -1092,8 +1092,6 @@ err_free_uar_table:
 err_free_intrs:
 	pvrdma_free_irq(dev);
 	pvrdma_disable_msi_all(dev);
-err_netdevice:
-	unregister_netdevice_notifier(&dev->nb_netdev);
 err_free_cq_ring:
 	pvrdma_page_dir_cleanup(dev, &dev->cq_pdir);
 err_free_async_ring:
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
index 54891370d18a..c2aa52638dcb 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_verbs.c
@@ -306,7 +306,7 @@ struct ib_ucontext *pvrdma_alloc_ucontext(struct ib_device *ibdev,
 	union pvrdma_cmd_resp rsp;
 	struct pvrdma_cmd_create_uc *cmd = &req.create_uc;
 	struct pvrdma_cmd_create_uc_resp *resp = &rsp.create_uc_resp;
-	struct pvrdma_alloc_ucontext_resp uresp;
+	struct pvrdma_alloc_ucontext_resp uresp = {0};
 	int ret;
 	void *ptr;
 
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index d0faca294006..86a6585b847d 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -59,9 +59,11 @@ int mem_check_range(struct rxe_mem *mem, u64 iova, size_t length)
 
 	case RXE_MEM_TYPE_MR:
 	case RXE_MEM_TYPE_FMR:
-		return ((iova < mem->iova) ||
-			((iova + length) > (mem->iova + mem->length))) ?
-			-EFAULT : 0;
+		if (iova < mem->iova ||
+		    length > mem->length ||
+		    iova > mem->iova + mem->length - length)
+			return -EFAULT;
+		return 0;
 
 	default:
 		return -EFAULT;
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 342e78163613..4abdeb359fb4 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -555,7 +555,7 @@ struct rxe_dev *rxe_net_add(struct net_device *ndev)
 	}
 
 	spin_lock_bh(&dev_list_lock);
-	list_add_tail(&rxe_dev_list, &rxe->list);
+	list_add_tail(&rxe->list, &rxe_dev_list);
 	spin_unlock_bh(&dev_list_lock);
 	return rxe;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c
index 486d576e55bc..44b2108253bd 100644
--- a/drivers/infiniband/sw/rxe/rxe_qp.c
+++ b/drivers/infiniband/sw/rxe/rxe_qp.c
@@ -813,8 +813,7 @@ void rxe_qp_destroy(struct rxe_qp *qp)
 	del_timer_sync(&qp->rnr_nak_timer);
 
 	rxe_cleanup_task(&qp->req.task);
-	if (qp_type(qp) == IB_QPT_RC)
-		rxe_cleanup_task(&qp->comp.task);
+	rxe_cleanup_task(&qp->comp.task);
 
 	/* flush out any receive wr's or pending requests */
 	__rxe_do_task(&qp->req.task);
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index 3435efff8799..5bcf07328972 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -479,7 +479,7 @@ static enum resp_states check_rkey(struct rxe_qp *qp,
 				goto err2;
 			}
 
-			resid = mtu;
+			qp->resp.resid = mtu;
 		} else {
 			if (pktlen != resid) {
 				state = RESPST_ERR_LENGTH;
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 9104e6b8cac9..30a6985909e0 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -651,13 +651,6 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep,
 						   SHOST_DIX_GUARD_CRC);
 		}
 
-		/*
-		 * Limit the sg_tablesize and max_sectors based on the device
-		 * max fastreg page list length.
-		 */
-		shost->sg_tablesize = min_t(unsigned short, shost->sg_tablesize,
-			ib_conn->device->ib_device->attrs.max_fast_reg_page_list_len);
-
 		if (iscsi_host_add(shost,
 				   ib_conn->device->ib_device->dma_device)) {
 			mutex_unlock(&iser_conn->state_mutex);
@@ -679,6 +672,10 @@ iscsi_iser_session_create(struct iscsi_endpoint *ep,
 	max_fr_sectors = ((shost->sg_tablesize - 1) * PAGE_SIZE) >> 9;
 	shost->max_sectors = min(iser_max_sectors, max_fr_sectors);
 
+	iser_dbg("iser_conn %p, sg_tablesize %u, max_sectors %u\n",
+		 iser_conn, shost->sg_tablesize,
+		 shost->max_sectors);
+
 	if (cmds_max > max_cmds) {
 		iser_info("cmds_max changed from %u to %u\n",
 			  cmds_max, max_cmds);
@@ -997,6 +994,7 @@ static struct scsi_host_template iscsi_iser_sht = {
 	.change_queue_depth	= scsi_change_queue_depth,
 	.sg_tablesize           = ISCSI_ISER_DEF_SG_TABLESIZE,
 	.cmd_per_lun            = ISER_DEF_CMD_PER_LUN,
+	.eh_timed_out		= iscsi_eh_cmd_timed_out,
 	.eh_abort_handler       = iscsi_eh_abort,
 	.eh_device_reset_handler= iscsi_eh_device_reset,
 	.eh_target_reset_handler = iscsi_eh_recover_target,
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 0be6a7c5ddb5..9d0b22ad58c1 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -496,7 +496,6 @@ struct ib_conn {
  * @rx_descs:         rx buffers array (cyclic buffer)
  * @num_rx_descs:     number of rx descriptors
  * @scsi_sg_tablesize: scsi host sg_tablesize
- * @scsi_max_sectors: scsi host max sectors
  */
 struct iser_conn {
 	struct ib_conn		     ib_conn;
@@ -519,7 +518,6 @@ struct iser_conn {
 	struct iser_rx_desc	     *rx_descs;
 	u32                          num_rx_descs;
 	unsigned short               scsi_sg_tablesize;
-	unsigned int                 scsi_max_sectors;
 	bool			     snd_w_inv;
 };
 
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 8ae7a3beddb7..6a9d1cb548ee 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -707,18 +707,7 @@ iser_calc_scsi_params(struct iser_conn *iser_conn,
 	sup_sg_tablesize = min_t(unsigned, ISCSI_ISER_MAX_SG_TABLESIZE,
 				 device->ib_device->attrs.max_fast_reg_page_list_len);
 
-	if (sg_tablesize > sup_sg_tablesize) {
-		sg_tablesize = sup_sg_tablesize;
-		iser_conn->scsi_max_sectors = sg_tablesize * SIZE_4K / 512;
-	} else {
-		iser_conn->scsi_max_sectors = max_sectors;
-	}
-
-	iser_conn->scsi_sg_tablesize = sg_tablesize;
-
-	iser_dbg("iser_conn %p, sg_tablesize %u, max_sectors %u\n",
-		 iser_conn, iser_conn->scsi_sg_tablesize,
-		 iser_conn->scsi_max_sectors);
+	iser_conn->scsi_sg_tablesize = min(sg_tablesize, sup_sg_tablesize);
 }
 
 /**
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 8ddc07123193..36529e390e48 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -371,6 +371,7 @@ static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device,
 	struct srp_fr_desc *d;
 	struct ib_mr *mr;
 	int i, ret = -EINVAL;
+	enum ib_mr_type mr_type;
 
 	if (pool_size <= 0)
 		goto err;
@@ -384,9 +385,13 @@ static struct srp_fr_pool *srp_create_fr_pool(struct ib_device *device,
 	spin_lock_init(&pool->lock);
 	INIT_LIST_HEAD(&pool->free_list);
 
+	if (device->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG)
+		mr_type = IB_MR_TYPE_SG_GAPS;
+	else
+		mr_type = IB_MR_TYPE_MEM_REG;
+
 	for (i = 0, d = &pool->desc[0]; i < pool->size; i++, d++) {
-		mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG,
-				 max_page_list_len);
+		mr = ib_alloc_mr(pd, mr_type, max_page_list_len);
 		if (IS_ERR(mr)) {
 			ret = PTR_ERR(mr);
 			if (ret == -ENOMEM)
@@ -2864,6 +2869,7 @@ static struct scsi_host_template srp_template = {
 	.info				= srp_target_info,
 	.queuecommand			= srp_queuecommand,
 	.change_queue_depth             = srp_change_queue_depth,
+	.eh_timed_out			= srp_timed_out,
 	.eh_abort_handler		= srp_abort,
 	.eh_device_reset_handler	= srp_reset_device,
 	.eh_host_reset_handler		= srp_reset_host,
@@ -3694,6 +3700,12 @@ static int __init srp_init_module(void)
 		indirect_sg_entries = cmd_sg_entries;
 	}
 
+	if (indirect_sg_entries > SG_MAX_SEGMENTS) {
+		pr_warn("Clamping indirect_sg_entries to %u\n",
+			SG_MAX_SEGMENTS);
+		indirect_sg_entries = SG_MAX_SEGMENTS;
+	}
+
 	srp_remove_wq = create_workqueue("srp_remove");
 	if (!srp_remove_wq) {
 		ret = -ENOMEM;
diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
index 92595b98e7ed..022be0e22eba 100644
--- a/drivers/input/misc/uinput.c
+++ b/drivers/input/misc/uinput.c
@@ -263,13 +263,21 @@ static int uinput_create_device(struct uinput_device *udev)
 		return -EINVAL;
 	}
 
-	if (test_bit(ABS_MT_SLOT, dev->absbit)) {
-		nslot = input_abs_get_max(dev, ABS_MT_SLOT) + 1;
-		error = input_mt_init_slots(dev, nslot, 0);
-		if (error)
+	if (test_bit(EV_ABS, dev->evbit)) {
+		input_alloc_absinfo(dev);
+		if (!dev->absinfo) {
+			error = -EINVAL;
 			goto fail1;
-	} else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) {
-		input_set_events_per_packet(dev, 60);
+		}
+
+		if (test_bit(ABS_MT_SLOT, dev->absbit)) {
+			nslot = input_abs_get_max(dev, ABS_MT_SLOT) + 1;
+			error = input_mt_init_slots(dev, nslot, 0);
+			if (error)
+				goto fail1;
+		} else if (test_bit(ABS_MT_POSITION_X, dev->absbit)) {
+			input_set_events_per_packet(dev, 60);
+		}
 	}
 
 	if (test_bit(EV_FF, dev->evbit) && !udev->ff_effects_max) {
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index fa598f7f4372..1e1d0ad406f2 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -1231,6 +1231,7 @@ static const struct acpi_device_id elan_acpi_id[] = {
 	{ "ELAN0000", 0 },
 	{ "ELAN0100", 0 },
 	{ "ELAN0600", 0 },
+	{ "ELAN0605", 0 },
 	{ "ELAN1000", 0 },
 	{ }
 };
diff --git a/drivers/input/rmi4/Kconfig b/drivers/input/rmi4/Kconfig
index 8993983e3fe4..bb7762bf2879 100644
--- a/drivers/input/rmi4/Kconfig
+++ b/drivers/input/rmi4/Kconfig
@@ -42,13 +42,19 @@ config RMI4_SMB
 config RMI4_F03
         bool "RMI4 Function 03 (PS2 Guest)"
 	depends on RMI4_CORE
-	depends on SERIO=y || RMI4_CORE=SERIO
         help
           Say Y here if you want to add support for RMI4 function 03.
 
           Function 03 provides PS2 guest support for RMI4 devices. This
           includes support for TrackPoints on TouchPads.
 
+config RMI4_F03_SERIO
+	tristate
+	depends on RMI4_CORE
+	depends on RMI4_F03
+	default RMI4_CORE
+	select SERIO
+
 config RMI4_2D_SENSOR
 	bool
 	depends on RMI4_CORE
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index 11447ab1055c..bf5c36e229ba 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -901,7 +901,7 @@ void rmi_enable_irq(struct rmi_device *rmi_dev, bool clear_wake)
 	data->enabled = true;
 	if (clear_wake && device_may_wakeup(rmi_dev->xport->dev)) {
 		retval = disable_irq_wake(irq);
-		if (!retval)
+		if (retval)
 			dev_warn(&rmi_dev->dev,
 				 "Failed to disable irq for wake: %d\n",
 				 retval);
@@ -936,7 +936,7 @@ void rmi_disable_irq(struct rmi_device *rmi_dev, bool enable_wake)
 	disable_irq(irq);
 	if (enable_wake && device_may_wakeup(rmi_dev->xport->dev)) {
 		retval = enable_irq_wake(irq);
-		if (!retval)
+		if (retval)
 			dev_warn(&rmi_dev->dev,
 				 "Failed to enable irq for wake: %d\n",
 				 retval);
diff --git a/drivers/input/touchscreen/wm97xx-core.c b/drivers/input/touchscreen/wm97xx-core.c
index 83cf11312fd9..c9d1c91e1887 100644
--- a/drivers/input/touchscreen/wm97xx-core.c
+++ b/drivers/input/touchscreen/wm97xx-core.c
@@ -682,7 +682,7 @@ static int wm97xx_probe(struct device *dev)
 	}
 	platform_set_drvdata(wm->battery_dev, wm);
 	wm->battery_dev->dev.parent = dev;
-	wm->battery_dev->dev.platform_data = pdata->batt_pdata;
+	wm->battery_dev->dev.platform_data = pdata ? pdata->batt_pdata : NULL;
 	ret = platform_device_add(wm->battery_dev);
 	if (ret < 0)
 		goto batt_reg_err;
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 8ee54d71c7eb..37e204f3d9be 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -352,9 +352,6 @@ config MTK_IOMMU_V1
 	select IOMMU_API
 	select MEMORY
 	select MTK_SMI
-	select COMMON_CLK_MT2701_MMSYS
-	select COMMON_CLK_MT2701_IMGSYS
-	select COMMON_CLK_MT2701_VDECSYS
 	help
 	  Support for the M4U on certain Mediatek SoCs. M4U generation 1 HW is
 	  Multimedia Memory Managememt Unit. This option enables remapping of
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 3ef0f42984f2..1b5b8c5361c5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -112,7 +112,7 @@ static struct timer_list queue_timer;
  * Domain for untranslated devices - only allocated
  * if iommu=pt passed on kernel cmd line.
  */
-static const struct iommu_ops amd_iommu_ops;
+const struct iommu_ops amd_iommu_ops;
 
 static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
 int amd_iommu_max_glx_val = -1;
@@ -445,6 +445,7 @@ static void init_iommu_group(struct device *dev)
 static int iommu_init_device(struct device *dev)
 {
 	struct iommu_dev_data *dev_data;
+	struct amd_iommu *iommu;
 	int devid;
 
 	if (dev->archdata.iommu)
@@ -454,6 +455,8 @@ static int iommu_init_device(struct device *dev)
 	if (devid < 0)
 		return devid;
 
+	iommu = amd_iommu_rlookup_table[devid];
+
 	dev_data = find_dev_data(devid);
 	if (!dev_data)
 		return -ENOMEM;
@@ -469,8 +472,7 @@ static int iommu_init_device(struct device *dev)
 
 	dev->archdata.iommu = dev_data;
 
-	iommu_device_link(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev,
-			  dev);
+	iommu_device_link(&iommu->iommu, dev);
 
 	return 0;
 }
@@ -495,13 +497,16 @@ static void iommu_ignore_device(struct device *dev)
 
 static void iommu_uninit_device(struct device *dev)
 {
-	int devid;
 	struct iommu_dev_data *dev_data;
+	struct amd_iommu *iommu;
+	int devid;
 
 	devid = get_device_id(dev);
 	if (devid < 0)
 		return;
 
+	iommu = amd_iommu_rlookup_table[devid];
+
 	dev_data = search_dev_data(devid);
 	if (!dev_data)
 		return;
@@ -509,8 +514,7 @@ static void iommu_uninit_device(struct device *dev)
 	if (dev_data->domain)
 		detach_device(dev);
 
-	iommu_device_unlink(amd_iommu_rlookup_table[dev_data->devid]->iommu_dev,
-			    dev);
+	iommu_device_unlink(&iommu->iommu, dev);
 
 	iommu_group_remove_device(dev);
 
@@ -3161,9 +3165,10 @@ static bool amd_iommu_capable(enum iommu_cap cap)
 	return false;
 }
 
-static void amd_iommu_get_dm_regions(struct device *dev,
-				     struct list_head *head)
+static void amd_iommu_get_resv_regions(struct device *dev,
+				       struct list_head *head)
 {
+	struct iommu_resv_region *region;
 	struct unity_map_entry *entry;
 	int devid;
 
@@ -3172,41 +3177,56 @@ static void amd_iommu_get_dm_regions(struct device *dev,
 		return;
 
 	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
-		struct iommu_dm_region *region;
+		size_t length;
+		int prot = 0;
 
 		if (devid < entry->devid_start || devid > entry->devid_end)
 			continue;
 
-		region = kzalloc(sizeof(*region), GFP_KERNEL);
+		length = entry->address_end - entry->address_start;
+		if (entry->prot & IOMMU_PROT_IR)
+			prot |= IOMMU_READ;
+		if (entry->prot & IOMMU_PROT_IW)
+			prot |= IOMMU_WRITE;
+
+		region = iommu_alloc_resv_region(entry->address_start,
+						 length, prot,
+						 IOMMU_RESV_DIRECT);
 		if (!region) {
 			pr_err("Out of memory allocating dm-regions for %s\n",
 				dev_name(dev));
 			return;
 		}
-
-		region->start = entry->address_start;
-		region->length = entry->address_end - entry->address_start;
-		if (entry->prot & IOMMU_PROT_IR)
-			region->prot |= IOMMU_READ;
-		if (entry->prot & IOMMU_PROT_IW)
-			region->prot |= IOMMU_WRITE;
-
 		list_add_tail(&region->list, head);
 	}
+
+	region = iommu_alloc_resv_region(MSI_RANGE_START,
+					 MSI_RANGE_END - MSI_RANGE_START + 1,
+					 0, IOMMU_RESV_RESERVED);
+	if (!region)
+		return;
+	list_add_tail(&region->list, head);
+
+	region = iommu_alloc_resv_region(HT_RANGE_START,
+					 HT_RANGE_END - HT_RANGE_START + 1,
+					 0, IOMMU_RESV_RESERVED);
+	if (!region)
+		return;
+	list_add_tail(&region->list, head);
 }
 
-static void amd_iommu_put_dm_regions(struct device *dev,
+static void amd_iommu_put_resv_regions(struct device *dev,
 				     struct list_head *head)
 {
-	struct iommu_dm_region *entry, *next;
+	struct iommu_resv_region *entry, *next;
 
 	list_for_each_entry_safe(entry, next, head, list)
 		kfree(entry);
 }
 
-static void amd_iommu_apply_dm_region(struct device *dev,
+static void amd_iommu_apply_resv_region(struct device *dev,
 				      struct iommu_domain *domain,
-				      struct iommu_dm_region *region)
+				      struct iommu_resv_region *region)
 {
 	struct dma_ops_domain *dma_dom = to_dma_ops_domain(to_pdomain(domain));
 	unsigned long start, end;
@@ -3217,7 +3237,7 @@ static void amd_iommu_apply_dm_region(struct device *dev,
 	WARN_ON_ONCE(reserve_iova(&dma_dom->iovad, start, end) == NULL);
 }
 
-static const struct iommu_ops amd_iommu_ops = {
+const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
 	.domain_free  = amd_iommu_domain_free,
@@ -3230,9 +3250,9 @@ static const struct iommu_ops amd_iommu_ops = {
 	.add_device = amd_iommu_add_device,
 	.remove_device = amd_iommu_remove_device,
 	.device_group = amd_iommu_device_group,
-	.get_dm_regions = amd_iommu_get_dm_regions,
-	.put_dm_regions = amd_iommu_put_dm_regions,
-	.apply_dm_region = amd_iommu_apply_dm_region,
+	.get_resv_regions = amd_iommu_get_resv_regions,
+	.put_resv_regions = amd_iommu_put_resv_regions,
+	.apply_resv_region = amd_iommu_apply_resv_region,
 	.pgsize_bitmap	= AMD_IOMMU_PGSIZES,
 };
 
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 6799cf9713f7..04cdac7ab3e3 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -94,6 +94,8 @@
  * out of it.
  */
 
+extern const struct iommu_ops amd_iommu_ops;
+
 /*
  * structure describing one IOMMU in the ACPI table. Typically followed by one
  * or more ivhd_entrys.
@@ -1635,9 +1637,10 @@ static int iommu_init_pci(struct amd_iommu *iommu)
 	amd_iommu_erratum_746_workaround(iommu);
 	amd_iommu_ats_write_check_workaround(iommu);
 
-	iommu->iommu_dev = iommu_device_create(&iommu->dev->dev, iommu,
-					       amd_iommu_groups, "ivhd%d",
-					       iommu->index);
+	iommu_device_sysfs_add(&iommu->iommu, &iommu->dev->dev,
+			       amd_iommu_groups, "ivhd%d", iommu->index);
+	iommu_device_set_ops(&iommu->iommu, &amd_iommu_ops);
+	iommu_device_register(&iommu->iommu);
 
 	return pci_enable_device(iommu->dev);
 }
@@ -2230,7 +2233,7 @@ static int __init early_amd_iommu_init(void)
 	 */
 	ret = check_ivrs_checksum(ivrs_base);
 	if (ret)
-		return ret;
+		goto out;
 
 	amd_iommu_target_ivhd_type = get_highest_supported_ivhd_type(ivrs_base);
 	DUMP_printk("Using IVHD type %#x\n", amd_iommu_target_ivhd_type);
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index 0d91785ebdc3..af00f381a7b1 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -535,8 +535,8 @@ struct amd_iommu {
 	/* if one, we need to send a completion wait command */
 	bool need_sync;
 
-	/* IOMMU sysfs device */
-	struct device *iommu_dev;
+	/* Handle for IOMMU core code */
+	struct iommu_device iommu;
 
 	/*
 	 * We can't rely on the BIOS to restore all values on reinit, so we
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 4d6ec444a9d6..5806a6acc94e 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -269,9 +269,6 @@
 #define STRTAB_STE_1_SHCFG_INCOMING	1UL
 #define STRTAB_STE_1_SHCFG_SHIFT	44
 
-#define STRTAB_STE_1_PRIVCFG_UNPRIV	2UL
-#define STRTAB_STE_1_PRIVCFG_SHIFT	48
-
 #define STRTAB_STE_2_S2VMID_SHIFT	0
 #define STRTAB_STE_2_S2VMID_MASK	0xffffUL
 #define STRTAB_STE_2_VTCR_SHIFT		32
@@ -412,6 +409,9 @@
 /* High-level queue structures */
 #define ARM_SMMU_POLL_TIMEOUT_US	100
 
+#define MSI_IOVA_BASE			0x8000000
+#define MSI_IOVA_LENGTH			0x100000
+
 static bool disable_bypass;
 module_param_named(disable_bypass, disable_bypass, bool, S_IRUGO);
 MODULE_PARM_DESC(disable_bypass,
@@ -616,6 +616,9 @@ struct arm_smmu_device {
 	unsigned int			sid_bits;
 
 	struct arm_smmu_strtab_cfg	strtab_cfg;
+
+	/* IOMMU core code handle */
+	struct iommu_device		iommu;
 };
 
 /* SMMU private data for each master */
@@ -1042,13 +1045,8 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 		}
 	}
 
-	/* Nuke the existing Config, as we're going to rewrite it */
-	val &= ~(STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT);
-
-	if (ste->valid)
-		val |= STRTAB_STE_0_V;
-	else
-		val &= ~STRTAB_STE_0_V;
+	/* Nuke the existing STE_0 value, as we're going to rewrite it */
+	val = ste->valid ? STRTAB_STE_0_V : 0;
 
 	if (ste->bypass) {
 		val |= disable_bypass ? STRTAB_STE_0_CFG_ABORT
@@ -1073,9 +1071,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 #ifdef CONFIG_PCI_ATS
 			 STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT |
 #endif
-			 STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT |
-			 STRTAB_STE_1_PRIVCFG_UNPRIV <<
-			 STRTAB_STE_1_PRIVCFG_SHIFT);
+			 STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT);
 
 		if (smmu->features & ARM_SMMU_FEAT_STALLS)
 			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
@@ -1083,7 +1079,6 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid,
 		val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK
 		        << STRTAB_STE_0_S1CTXPTR_SHIFT) |
 			STRTAB_STE_0_CFG_S1_TRANS;
-
 	}
 
 	if (ste->s2_cfg) {
@@ -1372,8 +1367,6 @@ static bool arm_smmu_capable(enum iommu_cap cap)
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
 		return true;
-	case IOMMU_CAP_INTR_REMAP:
-		return true; /* MSIs are just memory writes */
 	case IOMMU_CAP_NOEXEC:
 		return true;
 	default:
@@ -1795,8 +1788,10 @@ static int arm_smmu_add_device(struct device *dev)
 	}
 
 	group = iommu_group_get_for_dev(dev);
-	if (!IS_ERR(group))
+	if (!IS_ERR(group)) {
 		iommu_group_put(group);
+		iommu_device_link(&smmu->iommu, dev);
+	}
 
 	return PTR_ERR_OR_ZERO(group);
 }
@@ -1805,14 +1800,17 @@ static void arm_smmu_remove_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
 	struct arm_smmu_master_data *master;
+	struct arm_smmu_device *smmu;
 
 	if (!fwspec || fwspec->ops != &arm_smmu_ops)
 		return;
 
 	master = fwspec->iommu_priv;
+	smmu = master->smmu;
 	if (master && master->ste.valid)
 		arm_smmu_detach_dev(dev);
 	iommu_group_remove_device(dev);
+	iommu_device_unlink(&smmu->iommu, dev);
 	kfree(master);
 	iommu_fwspec_free(dev);
 }
@@ -1883,6 +1881,29 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	return iommu_fwspec_add_ids(dev, args->args, 1);
 }
 
+static void arm_smmu_get_resv_regions(struct device *dev,
+				      struct list_head *head)
+{
+	struct iommu_resv_region *region;
+	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+	region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
+					 prot, IOMMU_RESV_MSI);
+	if (!region)
+		return;
+
+	list_add_tail(&region->list, head);
+}
+
+static void arm_smmu_put_resv_regions(struct device *dev,
+				      struct list_head *head)
+{
+	struct iommu_resv_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, head, list)
+		kfree(entry);
+}
+
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
@@ -1898,6 +1919,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.domain_get_attr	= arm_smmu_domain_get_attr,
 	.domain_set_attr	= arm_smmu_domain_set_attr,
 	.of_xlate		= arm_smmu_of_xlate,
+	.get_resv_regions	= arm_smmu_get_resv_regions,
+	.put_resv_regions	= arm_smmu_put_resv_regions,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
@@ -1983,17 +2006,9 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu)
 	u32 size, l1size;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
 
-	/*
-	 * If we can resolve everything with a single L2 table, then we
-	 * just need a single L1 descriptor. Otherwise, calculate the L1
-	 * size, capped to the SIDSIZE.
-	 */
-	if (smmu->sid_bits < STRTAB_SPLIT) {
-		size = 0;
-	} else {
-		size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
-		size = min(size, smmu->sid_bits - STRTAB_SPLIT);
-	}
+	/* Calculate the L1 size, capped to the SIDSIZE. */
+	size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
+	size = min(size, smmu->sid_bits - STRTAB_SPLIT);
 	cfg->num_l1_ents = 1 << size;
 
 	size += STRTAB_SPLIT;
@@ -2504,6 +2519,13 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu)
 	smmu->ssid_bits = reg >> IDR1_SSID_SHIFT & IDR1_SSID_MASK;
 	smmu->sid_bits = reg >> IDR1_SID_SHIFT & IDR1_SID_MASK;
 
+	/*
+	 * If the SMMU supports fewer bits than would fill a single L2 stream
+	 * table, use a linear table instead.
+	 */
+	if (smmu->sid_bits <= STRTAB_SPLIT)
+		smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB;
+
 	/* IDR5 */
 	reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
 
@@ -2613,6 +2635,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 {
 	int irq, ret;
 	struct resource *res;
+	resource_size_t ioaddr;
 	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
 	bool bypass;
@@ -2630,6 +2653,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		dev_err(dev, "MMIO region too small (%pr)\n", res);
 		return -EINVAL;
 	}
+	ioaddr = res->start;
 
 	smmu->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(smmu->base))
@@ -2682,7 +2706,15 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		return ret;
 
 	/* And we're up. Go go go! */
-	iommu_register_instance(dev->fwnode, &arm_smmu_ops);
+	ret = iommu_device_sysfs_add(&smmu->iommu, dev, NULL,
+				     "smmu3.%pa", &ioaddr);
+	if (ret)
+		return ret;
+
+	iommu_device_set_ops(&smmu->iommu, &arm_smmu_ops);
+	iommu_device_set_fwnode(&smmu->iommu, dev->fwnode);
+
+	ret = iommu_device_register(&smmu->iommu);
 
 #ifdef CONFIG_PCI
 	if (pci_bus_type.iommu_ops != &arm_smmu_ops) {
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index a60cded8a6ed..abf6496843a6 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -24,6 +24,7 @@
  *	- v7/v8 long-descriptor format
  *	- Non-secure access to the SMMU
  *	- Context fault reporting
+ *	- Extended Stream ID (16 bit)
  */
 
 #define pr_fmt(fmt) "arm-smmu: " fmt
@@ -87,6 +88,7 @@
 #define sCR0_CLIENTPD			(1 << 0)
 #define sCR0_GFRE			(1 << 1)
 #define sCR0_GFIE			(1 << 2)
+#define sCR0_EXIDENABLE			(1 << 3)
 #define sCR0_GCFGFRE			(1 << 4)
 #define sCR0_GCFGFIE			(1 << 5)
 #define sCR0_USFCFG			(1 << 10)
@@ -126,6 +128,7 @@
 #define ID0_NUMIRPT_MASK		0xff
 #define ID0_NUMSIDB_SHIFT		9
 #define ID0_NUMSIDB_MASK		0xf
+#define ID0_EXIDS			(1 << 8)
 #define ID0_NUMSMRG_SHIFT		0
 #define ID0_NUMSMRG_MASK		0xff
 
@@ -169,6 +172,7 @@
 #define ARM_SMMU_GR0_S2CR(n)		(0xc00 + ((n) << 2))
 #define S2CR_CBNDX_SHIFT		0
 #define S2CR_CBNDX_MASK			0xff
+#define S2CR_EXIDVALID			(1 << 10)
 #define S2CR_TYPE_SHIFT			16
 #define S2CR_TYPE_MASK			0x3
 enum arm_smmu_s2cr_type {
@@ -260,6 +264,7 @@ enum arm_smmu_s2cr_privcfg {
 
 #define TTBCR2_SEP_SHIFT		15
 #define TTBCR2_SEP_UPSTREAM		(0x7 << TTBCR2_SEP_SHIFT)
+#define TTBCR2_AS			(1 << 4)
 
 #define TTBRn_ASID_SHIFT		48
 
@@ -281,6 +286,9 @@ enum arm_smmu_s2cr_privcfg {
 
 #define FSYNR0_WNR			(1 << 4)
 
+#define MSI_IOVA_BASE			0x8000000
+#define MSI_IOVA_LENGTH			0x100000
+
 static int force_stage;
 module_param(force_stage, int, S_IRUGO);
 MODULE_PARM_DESC(force_stage,
@@ -351,6 +359,7 @@ struct arm_smmu_device {
 #define ARM_SMMU_FEAT_FMT_AARCH64_64K	(1 << 9)
 #define ARM_SMMU_FEAT_FMT_AARCH32_L	(1 << 10)
 #define ARM_SMMU_FEAT_FMT_AARCH32_S	(1 << 11)
+#define ARM_SMMU_FEAT_EXIDS		(1 << 12)
 	u32				features;
 
 #define ARM_SMMU_OPT_SECURE_CFG_ACCESS (1 << 0)
@@ -380,6 +389,9 @@ struct arm_smmu_device {
 	unsigned int			*irqs;
 
 	u32				cavium_id_base; /* Specific to Cavium */
+
+	/* IOMMU core code handle */
+	struct iommu_device		iommu;
 };
 
 enum arm_smmu_context_fmt {
@@ -778,6 +790,8 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain,
 			reg = pgtbl_cfg->arm_lpae_s1_cfg.tcr;
 			reg2 = pgtbl_cfg->arm_lpae_s1_cfg.tcr >> 32;
 			reg2 |= TTBCR2_SEP_UPSTREAM;
+			if (cfg->fmt == ARM_SMMU_CTX_FMT_AARCH64)
+				reg2 |= TTBCR2_AS;
 		}
 		if (smmu->version > ARM_SMMU_V1)
 			writel_relaxed(reg2, cb_base + ARM_SMMU_CB_TTBCR2);
@@ -1048,7 +1062,7 @@ static void arm_smmu_write_smr(struct arm_smmu_device *smmu, int idx)
 	struct arm_smmu_smr *smr = smmu->smrs + idx;
 	u32 reg = smr->id << SMR_ID_SHIFT | smr->mask << SMR_MASK_SHIFT;
 
-	if (smr->valid)
+	if (!(smmu->features & ARM_SMMU_FEAT_EXIDS) && smr->valid)
 		reg |= SMR_VALID;
 	writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_SMR(idx));
 }
@@ -1060,6 +1074,9 @@ static void arm_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx)
 		  (s2cr->cbndx & S2CR_CBNDX_MASK) << S2CR_CBNDX_SHIFT |
 		  (s2cr->privcfg & S2CR_PRIVCFG_MASK) << S2CR_PRIVCFG_SHIFT;
 
+	if (smmu->features & ARM_SMMU_FEAT_EXIDS && smmu->smrs &&
+	    smmu->smrs[idx].valid)
+		reg |= S2CR_EXIDVALID;
 	writel_relaxed(reg, ARM_SMMU_GR0(smmu) + ARM_SMMU_GR0_S2CR(idx));
 }
 
@@ -1070,6 +1087,34 @@ static void arm_smmu_write_sme(struct arm_smmu_device *smmu, int idx)
 		arm_smmu_write_smr(smmu, idx);
 }
 
+/*
+ * The width of SMR's mask field depends on sCR0_EXIDENABLE, so this function
+ * should be called after sCR0 is written.
+ */
+static void arm_smmu_test_smr_masks(struct arm_smmu_device *smmu)
+{
+	void __iomem *gr0_base = ARM_SMMU_GR0(smmu);
+	u32 smr;
+
+	if (!smmu->smrs)
+		return;
+
+	/*
+	 * SMR.ID bits may not be preserved if the corresponding MASK
+	 * bits are set, so check each one separately. We can reject
+	 * masters later if they try to claim IDs outside these masks.
+	 */
+	smr = smmu->streamid_mask << SMR_ID_SHIFT;
+	writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
+	smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
+	smmu->streamid_mask = smr >> SMR_ID_SHIFT;
+
+	smr = smmu->streamid_mask << SMR_MASK_SHIFT;
+	writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
+	smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
+	smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT;
+}
+
 static int arm_smmu_find_sme(struct arm_smmu_device *smmu, u16 id, u16 mask)
 {
 	struct arm_smmu_smr *smrs = smmu->smrs;
@@ -1214,7 +1259,7 @@ static int arm_smmu_domain_add_master(struct arm_smmu_domain *smmu_domain,
 			continue;
 
 		s2cr[idx].type = type;
-		s2cr[idx].privcfg = S2CR_PRIVCFG_UNPRIV;
+		s2cr[idx].privcfg = S2CR_PRIVCFG_DEFAULT;
 		s2cr[idx].cbndx = cbndx;
 		arm_smmu_write_s2cr(smmu, idx);
 	}
@@ -1371,8 +1416,6 @@ static bool arm_smmu_capable(enum iommu_cap cap)
 		 * requests.
 		 */
 		return true;
-	case IOMMU_CAP_INTR_REMAP:
-		return true; /* MSIs are just memory writes */
 	case IOMMU_CAP_NOEXEC:
 		return true;
 	default:
@@ -1444,6 +1487,8 @@ static int arm_smmu_add_device(struct device *dev)
 	if (ret)
 		goto out_free;
 
+	iommu_device_link(&smmu->iommu, dev);
+
 	return 0;
 
 out_free:
@@ -1456,10 +1501,17 @@ out_free:
 static void arm_smmu_remove_device(struct device *dev)
 {
 	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
+	struct arm_smmu_master_cfg *cfg;
+	struct arm_smmu_device *smmu;
+
 
 	if (!fwspec || fwspec->ops != &arm_smmu_ops)
 		return;
 
+	cfg  = fwspec->iommu_priv;
+	smmu = cfg->smmu;
+
+	iommu_device_unlink(&smmu->iommu, dev);
 	arm_smmu_master_free_smes(fwspec);
 	iommu_group_remove_device(dev);
 	kfree(fwspec->iommu_priv);
@@ -1549,6 +1601,29 @@ static int arm_smmu_of_xlate(struct device *dev, struct of_phandle_args *args)
 	return iommu_fwspec_add_ids(dev, &fwid, 1);
 }
 
+static void arm_smmu_get_resv_regions(struct device *dev,
+				      struct list_head *head)
+{
+	struct iommu_resv_region *region;
+	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+
+	region = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
+					 prot, IOMMU_RESV_MSI);
+	if (!region)
+		return;
+
+	list_add_tail(&region->list, head);
+}
+
+static void arm_smmu_put_resv_regions(struct device *dev,
+				      struct list_head *head)
+{
+	struct iommu_resv_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, head, list)
+		kfree(entry);
+}
+
 static struct iommu_ops arm_smmu_ops = {
 	.capable		= arm_smmu_capable,
 	.domain_alloc		= arm_smmu_domain_alloc,
@@ -1564,6 +1639,8 @@ static struct iommu_ops arm_smmu_ops = {
 	.domain_get_attr	= arm_smmu_domain_get_attr,
 	.domain_set_attr	= arm_smmu_domain_set_attr,
 	.of_xlate		= arm_smmu_of_xlate,
+	.get_resv_regions	= arm_smmu_get_resv_regions,
+	.put_resv_regions	= arm_smmu_put_resv_regions,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
@@ -1648,6 +1725,9 @@ static void arm_smmu_device_reset(struct arm_smmu_device *smmu)
 	if (smmu->features & ARM_SMMU_FEAT_VMID16)
 		reg |= sCR0_VMID16EN;
 
+	if (smmu->features & ARM_SMMU_FEAT_EXIDS)
+		reg |= sCR0_EXIDENABLE;
+
 	/* Push the button */
 	__arm_smmu_tlb_sync(smmu);
 	writel(reg, ARM_SMMU_GR0_NS(smmu) + ARM_SMMU_GR0_sCR0);
@@ -1735,11 +1815,14 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 			   "\t(IDR0.CTTW overridden by FW configuration)\n");
 
 	/* Max. number of entries we have for stream matching/indexing */
-	size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK);
+	if (smmu->version == ARM_SMMU_V2 && id & ID0_EXIDS) {
+		smmu->features |= ARM_SMMU_FEAT_EXIDS;
+		size = 1 << 16;
+	} else {
+		size = 1 << ((id >> ID0_NUMSIDB_SHIFT) & ID0_NUMSIDB_MASK);
+	}
 	smmu->streamid_mask = size - 1;
 	if (id & ID0_SMS) {
-		u32 smr;
-
 		smmu->features |= ARM_SMMU_FEAT_STREAM_MATCH;
 		size = (id >> ID0_NUMSMRG_SHIFT) & ID0_NUMSMRG_MASK;
 		if (size == 0) {
@@ -1748,21 +1831,6 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 			return -ENODEV;
 		}
 
-		/*
-		 * SMR.ID bits may not be preserved if the corresponding MASK
-		 * bits are set, so check each one separately. We can reject
-		 * masters later if they try to claim IDs outside these masks.
-		 */
-		smr = smmu->streamid_mask << SMR_ID_SHIFT;
-		writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
-		smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
-		smmu->streamid_mask = smr >> SMR_ID_SHIFT;
-
-		smr = smmu->streamid_mask << SMR_MASK_SHIFT;
-		writel_relaxed(smr, gr0_base + ARM_SMMU_GR0_SMR(0));
-		smr = readl_relaxed(gr0_base + ARM_SMMU_GR0_SMR(0));
-		smmu->smr_mask_mask = smr >> SMR_MASK_SHIFT;
-
 		/* Zero-initialised to mark as invalid */
 		smmu->smrs = devm_kcalloc(smmu->dev, size, sizeof(*smmu->smrs),
 					  GFP_KERNEL);
@@ -1770,8 +1838,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 			return -ENOMEM;
 
 		dev_notice(smmu->dev,
-			   "\tstream matching with %lu register groups, mask 0x%x",
-			   size, smmu->smr_mask_mask);
+			   "\tstream matching with %lu register groups", size);
 	}
 	/* s2cr->type == 0 means translation, so initialise explicitly */
 	smmu->s2crs = devm_kmalloc_array(smmu->dev, size, sizeof(*smmu->s2crs),
@@ -2011,6 +2078,7 @@ static int arm_smmu_device_dt_probe(struct platform_device *pdev,
 static int arm_smmu_device_probe(struct platform_device *pdev)
 {
 	struct resource *res;
+	resource_size_t ioaddr;
 	struct arm_smmu_device *smmu;
 	struct device *dev = &pdev->dev;
 	int num_irqs, i, err;
@@ -2031,6 +2099,7 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		return err;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ioaddr = res->start;
 	smmu->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(smmu->base))
 		return PTR_ERR(smmu->base);
@@ -2091,9 +2160,25 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
 		}
 	}
 
-	iommu_register_instance(dev->fwnode, &arm_smmu_ops);
+	err = iommu_device_sysfs_add(&smmu->iommu, smmu->dev, NULL,
+				     "smmu.%pa", &ioaddr);
+	if (err) {
+		dev_err(dev, "Failed to register iommu in sysfs\n");
+		return err;
+	}
+
+	iommu_device_set_ops(&smmu->iommu, &arm_smmu_ops);
+	iommu_device_set_fwnode(&smmu->iommu, dev->fwnode);
+
+	err = iommu_device_register(&smmu->iommu);
+	if (err) {
+		dev_err(dev, "Failed to register iommu\n");
+		return err;
+	}
+
 	platform_set_drvdata(pdev, smmu);
 	arm_smmu_device_reset(smmu);
+	arm_smmu_test_smr_masks(smmu);
 
 	/* Oh, for a proper bus abstraction */
 	if (!iommu_present(&platform_bus_type))
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 2db0d641cf45..48d36ce59efb 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -37,15 +37,50 @@ struct iommu_dma_msi_page {
 	phys_addr_t		phys;
 };
 
+enum iommu_dma_cookie_type {
+	IOMMU_DMA_IOVA_COOKIE,
+	IOMMU_DMA_MSI_COOKIE,
+};
+
 struct iommu_dma_cookie {
-	struct iova_domain	iovad;
-	struct list_head	msi_page_list;
-	spinlock_t		msi_lock;
+	enum iommu_dma_cookie_type	type;
+	union {
+		/* Full allocator for IOMMU_DMA_IOVA_COOKIE */
+		struct iova_domain	iovad;
+		/* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */
+		dma_addr_t		msi_iova;
+	};
+	struct list_head		msi_page_list;
+	spinlock_t			msi_lock;
 };
 
+static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie)
+{
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
+		return cookie->iovad.granule;
+	return PAGE_SIZE;
+}
+
 static inline struct iova_domain *cookie_iovad(struct iommu_domain *domain)
 {
-	return &((struct iommu_dma_cookie *)domain->iova_cookie)->iovad;
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE)
+		return &cookie->iovad;
+	return NULL;
+}
+
+static struct iommu_dma_cookie *cookie_alloc(enum iommu_dma_cookie_type type)
+{
+	struct iommu_dma_cookie *cookie;
+
+	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
+	if (cookie) {
+		spin_lock_init(&cookie->msi_lock);
+		INIT_LIST_HEAD(&cookie->msi_page_list);
+		cookie->type = type;
+	}
+	return cookie;
 }
 
 int iommu_dma_init(void)
@@ -62,25 +97,53 @@ int iommu_dma_init(void)
  */
 int iommu_get_dma_cookie(struct iommu_domain *domain)
 {
+	if (domain->iova_cookie)
+		return -EEXIST;
+
+	domain->iova_cookie = cookie_alloc(IOMMU_DMA_IOVA_COOKIE);
+	if (!domain->iova_cookie)
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL(iommu_get_dma_cookie);
+
+/**
+ * iommu_get_msi_cookie - Acquire just MSI remapping resources
+ * @domain: IOMMU domain to prepare
+ * @base: Start address of IOVA region for MSI mappings
+ *
+ * Users who manage their own IOVA allocation and do not want DMA API support,
+ * but would still like to take advantage of automatic MSI remapping, can use
+ * this to initialise their own domain appropriately. Users should reserve a
+ * contiguous IOVA region, starting at @base, large enough to accommodate the
+ * number of PAGE_SIZE mappings necessary to cover every MSI doorbell address
+ * used by the devices attached to @domain.
+ */
+int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
+{
 	struct iommu_dma_cookie *cookie;
 
+	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
+		return -EINVAL;
+
 	if (domain->iova_cookie)
 		return -EEXIST;
 
-	cookie = kzalloc(sizeof(*cookie), GFP_KERNEL);
+	cookie = cookie_alloc(IOMMU_DMA_MSI_COOKIE);
 	if (!cookie)
 		return -ENOMEM;
 
-	spin_lock_init(&cookie->msi_lock);
-	INIT_LIST_HEAD(&cookie->msi_page_list);
+	cookie->msi_iova = base;
 	domain->iova_cookie = cookie;
 	return 0;
 }
-EXPORT_SYMBOL(iommu_get_dma_cookie);
+EXPORT_SYMBOL(iommu_get_msi_cookie);
 
 /**
  * iommu_put_dma_cookie - Release a domain's DMA mapping resources
- * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie()
+ * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() or
+ *          iommu_get_msi_cookie()
  *
  * IOMMU drivers should normally call this from their domain_free callback.
  */
@@ -92,7 +155,7 @@ void iommu_put_dma_cookie(struct iommu_domain *domain)
 	if (!cookie)
 		return;
 
-	if (cookie->iovad.granule)
+	if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule)
 		put_iova_domain(&cookie->iovad);
 
 	list_for_each_entry_safe(msi, tmp, &cookie->msi_page_list, list) {
@@ -137,11 +200,13 @@ static void iova_reserve_pci_windows(struct pci_dev *dev,
 int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		u64 size, struct device *dev)
 {
-	struct iova_domain *iovad = cookie_iovad(domain);
+	struct iommu_dma_cookie *cookie = domain->iova_cookie;
+	struct iova_domain *iovad = &cookie->iovad;
 	unsigned long order, base_pfn, end_pfn;
+	bool pci = dev && dev_is_pci(dev);
 
-	if (!iovad)
-		return -ENODEV;
+	if (!cookie || cookie->type != IOMMU_DMA_IOVA_COOKIE)
+		return -EINVAL;
 
 	/* Use the smallest supported page size for IOVA granularity */
 	order = __ffs(domain->pgsize_bitmap);
@@ -161,19 +226,31 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		end_pfn = min_t(unsigned long, end_pfn,
 				domain->geometry.aperture_end >> order);
 	}
+	/*
+	 * PCI devices may have larger DMA masks, but still prefer allocating
+	 * within a 32-bit mask to avoid DAC addressing. Such limitations don't
+	 * apply to the typical platform device, so for those we may as well
+	 * leave the cache limit at the top of their range to save an rb_last()
+	 * traversal on every allocation.
+	 */
+	if (pci)
+		end_pfn &= DMA_BIT_MASK(32) >> order;
 
-	/* All we can safely do with an existing domain is enlarge it */
+	/* start_pfn is always nonzero for an already-initialised domain */
 	if (iovad->start_pfn) {
 		if (1UL << order != iovad->granule ||
-		    base_pfn != iovad->start_pfn ||
-		    end_pfn < iovad->dma_32bit_pfn) {
+		    base_pfn != iovad->start_pfn) {
 			pr_warn("Incompatible range for DMA domain\n");
 			return -EFAULT;
 		}
-		iovad->dma_32bit_pfn = end_pfn;
+		/*
+		 * If we have devices with different DMA masks, move the free
+		 * area cache limit down for the benefit of the smaller one.
+		 */
+		iovad->dma_32bit_pfn = min(end_pfn, iovad->dma_32bit_pfn);
 	} else {
 		init_iova_domain(iovad, 1UL << order, base_pfn, end_pfn);
-		if (dev && dev_is_pci(dev))
+		if (pci)
 			iova_reserve_pci_windows(to_pci_dev(dev), iovad);
 	}
 	return 0;
@@ -181,16 +258,22 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 EXPORT_SYMBOL(iommu_dma_init_domain);
 
 /**
- * dma_direction_to_prot - Translate DMA API directions to IOMMU API page flags
+ * dma_info_to_prot - Translate DMA API directions and attributes to IOMMU API
+ *                    page flags.
  * @dir: Direction of DMA transfer
  * @coherent: Is the DMA master cache-coherent?
+ * @attrs: DMA attributes for the mapping
  *
  * Return: corresponding IOMMU API page protection flags
  */
-int dma_direction_to_prot(enum dma_data_direction dir, bool coherent)
+int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
+		     unsigned long attrs)
 {
 	int prot = coherent ? IOMMU_CACHE : 0;
 
+	if (attrs & DMA_ATTR_PRIVILEGED)
+		prot |= IOMMU_PRIV;
+
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
 		return prot | IOMMU_READ | IOMMU_WRITE;
@@ -204,19 +287,28 @@ int dma_direction_to_prot(enum dma_data_direction dir, bool coherent)
 }
 
 static struct iova *__alloc_iova(struct iommu_domain *domain, size_t size,
-		dma_addr_t dma_limit)
+		dma_addr_t dma_limit, struct device *dev)
 {
 	struct iova_domain *iovad = cookie_iovad(domain);
 	unsigned long shift = iova_shift(iovad);
 	unsigned long length = iova_align(iovad, size) >> shift;
+	struct iova *iova = NULL;
 
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, domain->geometry.aperture_end);
+
+	/* Try to get PCI devices a SAC address */
+	if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
+		iova = alloc_iova(iovad, length, DMA_BIT_MASK(32) >> shift,
+				  true);
 	/*
 	 * Enforce size-alignment to be safe - there could perhaps be an
 	 * attribute to control this per-device, or at least per-domain...
 	 */
-	return alloc_iova(iovad, length, dma_limit >> shift, true);
+	if (!iova)
+		iova = alloc_iova(iovad, length, dma_limit >> shift, true);
+
+	return iova;
 }
 
 /* The IOVA allocator knows what we mapped, so just unmap whatever that was */
@@ -369,7 +461,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp,
 	if (!pages)
 		return NULL;
 
-	iova = __alloc_iova(domain, size, dev->coherent_dma_mask);
+	iova = __alloc_iova(domain, size, dev->coherent_dma_mask, dev);
 	if (!iova)
 		goto out_free_pages;
 
@@ -440,7 +532,7 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 	struct iova_domain *iovad = cookie_iovad(domain);
 	size_t iova_off = iova_offset(iovad, phys);
 	size_t len = iova_align(iovad, size + iova_off);
-	struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev));
+	struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev), dev);
 
 	if (!iova)
 		return DMA_ERROR_CODE;
@@ -598,7 +690,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		prev = s;
 	}
 
-	iova = __alloc_iova(domain, iova_len, dma_get_mask(dev));
+	iova = __alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
 	if (!iova)
 		goto out_restore_sg;
 
@@ -633,7 +725,7 @@ dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	return __iommu_dma_map(dev, phys, size,
-			dma_direction_to_prot(dir, false) | IOMMU_MMIO);
+			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO);
 }
 
 void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
@@ -642,16 +734,6 @@ void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 	__iommu_dma_unmap(iommu_get_domain_for_dev(dev), handle);
 }
 
-int iommu_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * 'Special' IOMMUs which don't have the same addressing capability
-	 * as the CPU will have to wait until we have some way to query that
-	 * before they'll be able to use this framework.
-	 */
-	return 1;
-}
-
 int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	return dma_addr == DMA_ERROR_CODE;
@@ -662,11 +744,12 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 {
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iommu_dma_msi_page *msi_page;
-	struct iova_domain *iovad = &cookie->iovad;
+	struct iova_domain *iovad = cookie_iovad(domain);
 	struct iova *iova;
 	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;
+	size_t size = cookie_msi_granule(cookie);
 
-	msi_addr &= ~(phys_addr_t)iova_mask(iovad);
+	msi_addr &= ~(phys_addr_t)(size - 1);
 	list_for_each_entry(msi_page, &cookie->msi_page_list, list)
 		if (msi_page->phys == msi_addr)
 			return msi_page;
@@ -675,13 +758,18 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	if (!msi_page)
 		return NULL;
 
-	iova = __alloc_iova(domain, iovad->granule, dma_get_mask(dev));
-	if (!iova)
-		goto out_free_page;
-
 	msi_page->phys = msi_addr;
-	msi_page->iova = iova_dma_addr(iovad, iova);
-	if (iommu_map(domain, msi_page->iova, msi_addr, iovad->granule, prot))
+	if (iovad) {
+		iova = __alloc_iova(domain, size, dma_get_mask(dev), dev);
+		if (!iova)
+			goto out_free_page;
+		msi_page->iova = iova_dma_addr(iovad, iova);
+	} else {
+		msi_page->iova = cookie->msi_iova;
+		cookie->msi_iova += size;
+	}
+
+	if (iommu_map(domain, msi_page->iova, msi_addr, size, prot))
 		goto out_free_iova;
 
 	INIT_LIST_HEAD(&msi_page->list);
@@ -689,7 +777,10 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	return msi_page;
 
 out_free_iova:
-	__free_iova(iovad, iova);
+	if (iovad)
+		__free_iova(iovad, iova);
+	else
+		cookie->msi_iova -= size;
 out_free_page:
 	kfree(msi_page);
 	return NULL;
@@ -730,7 +821,7 @@ void iommu_dma_map_msi_msg(int irq, struct msi_msg *msg)
 		msg->data = ~0U;
 	} else {
 		msg->address_hi = upper_32_bits(msi_page->iova);
-		msg->address_lo &= iova_mask(&cookie->iovad);
+		msg->address_lo &= cookie_msi_granule(cookie) - 1;
 		msg->address_lo += lower_32_bits(msi_page->iova);
 	}
 }
diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
index 8ccbd7023194..d9c0decfc91a 100644
--- a/drivers/iommu/dmar.c
+++ b/drivers/iommu/dmar.c
@@ -74,6 +74,8 @@ static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];
 static int alloc_iommu(struct dmar_drhd_unit *drhd);
 static void free_iommu(struct intel_iommu *iommu);
 
+extern const struct iommu_ops intel_iommu_ops;
+
 static void dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 {
 	/*
@@ -1078,14 +1080,17 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
 	raw_spin_lock_init(&iommu->register_lock);
 
 	if (intel_iommu_enabled) {
-		iommu->iommu_dev = iommu_device_create(NULL, iommu,
-						       intel_iommu_groups,
-						       "%s", iommu->name);
+		err = iommu_device_sysfs_add(&iommu->iommu, NULL,
+					     intel_iommu_groups,
+					     "%s", iommu->name);
+		if (err)
+			goto err_unmap;
 
-		if (IS_ERR(iommu->iommu_dev)) {
-			err = PTR_ERR(iommu->iommu_dev);
+		iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops);
+
+		err = iommu_device_register(&iommu->iommu);
+		if (err)
 			goto err_unmap;
-		}
 	}
 
 	drhd->iommu = iommu;
@@ -1103,7 +1108,8 @@ error:
 
 static void free_iommu(struct intel_iommu *iommu)
 {
-	iommu_device_destroy(iommu->iommu_dev);
+	iommu_device_sysfs_remove(&iommu->iommu);
+	iommu_device_unregister(&iommu->iommu);
 
 	if (iommu->irq) {
 		if (iommu->pr_irq) {
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 57ba0d3091ea..a7e0821c9967 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -276,6 +276,8 @@ struct sysmmu_drvdata {
 	struct list_head owner_node;	/* node for owner controllers list */
 	phys_addr_t pgtable;		/* assigned page table structure */
 	unsigned int version;		/* our version */
+
+	struct iommu_device iommu;	/* IOMMU core handle */
 };
 
 static struct exynos_iommu_domain *to_exynos_domain(struct iommu_domain *dom)
@@ -381,13 +383,14 @@ static void show_fault_information(struct sysmmu_drvdata *data,
 {
 	sysmmu_pte_t *ent;
 
-	dev_err(data->sysmmu, "%s FAULT occurred at %#x (page table base: %pa)\n",
-		finfo->name, fault_addr, &data->pgtable);
+	dev_err(data->sysmmu, "%s: %s FAULT occurred at %#x\n",
+		dev_name(data->master), finfo->name, fault_addr);
+	dev_dbg(data->sysmmu, "Page table base: %pa\n", &data->pgtable);
 	ent = section_entry(phys_to_virt(data->pgtable), fault_addr);
-	dev_err(data->sysmmu, "\tLv1 entry: %#x\n", *ent);
+	dev_dbg(data->sysmmu, "\tLv1 entry: %#x\n", *ent);
 	if (lv1ent_page(ent)) {
 		ent = page_entry(ent, fault_addr);
-		dev_err(data->sysmmu, "\t Lv2 entry: %#x\n", *ent);
+		dev_dbg(data->sysmmu, "\t Lv2 entry: %#x\n", *ent);
 	}
 }
 
@@ -611,6 +614,18 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 	data->sysmmu = dev;
 	spin_lock_init(&data->lock);
 
+	ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL,
+				     dev_name(data->sysmmu));
+	if (ret)
+		return ret;
+
+	iommu_device_set_ops(&data->iommu, &exynos_iommu_ops);
+	iommu_device_set_fwnode(&data->iommu, &dev->of_node->fwnode);
+
+	ret = iommu_device_register(&data->iommu);
+	if (ret)
+		return ret;
+
 	platform_set_drvdata(pdev, data);
 
 	__sysmmu_get_version(data);
@@ -628,8 +643,6 @@ static int __init exynos_sysmmu_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(dev);
 
-	of_iommu_set_ops(dev->of_node, &exynos_iommu_ops);
-
 	return 0;
 }
 
@@ -743,6 +756,8 @@ static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
 				DMA_TO_DEVICE);
 	/* For mapping page table entries we rely on dma == phys */
 	BUG_ON(handle != virt_to_phys(domain->pgtable));
+	if (dma_mapping_error(dma_dev, handle))
+		goto err_lv2ent;
 
 	spin_lock_init(&domain->lock);
 	spin_lock_init(&domain->pgtablelock);
@@ -754,6 +769,8 @@ static struct iommu_domain *exynos_iommu_domain_alloc(unsigned type)
 
 	return &domain->domain;
 
+err_lv2ent:
+	free_pages((unsigned long)domain->lv2entcnt, 1);
 err_counter:
 	free_pages((unsigned long)domain->pgtable, 2);
 err_dma_cookie:
@@ -897,6 +914,7 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
 	}
 
 	if (lv1ent_fault(sent)) {
+		dma_addr_t handle;
 		sysmmu_pte_t *pent;
 		bool need_flush_flpd_cache = lv1ent_zero(sent);
 
@@ -908,7 +926,12 @@ static sysmmu_pte_t *alloc_lv2entry(struct exynos_iommu_domain *domain,
 		update_pte(sent, mk_lv1ent_page(virt_to_phys(pent)));
 		kmemleak_ignore(pent);
 		*pgcounter = NUM_LV2ENTRIES;
-		dma_map_single(dma_dev, pent, LV2TABLE_SIZE, DMA_TO_DEVICE);
+		handle = dma_map_single(dma_dev, pent, LV2TABLE_SIZE,
+					DMA_TO_DEVICE);
+		if (dma_mapping_error(dma_dev, handle)) {
+			kmem_cache_free(lv2table_kmem_cache, pent);
+			return ERR_PTR(-EADDRINUSE);
+		}
 
 		/*
 		 * If pre-fetched SLPD is a faulty SLPD in zero_l2_table,
@@ -1231,9 +1254,21 @@ static int exynos_iommu_add_device(struct device *dev)
 
 static void exynos_iommu_remove_device(struct device *dev)
 {
+	struct exynos_iommu_owner *owner = dev->archdata.iommu;
+
 	if (!has_sysmmu(dev))
 		return;
 
+	if (owner->domain) {
+		struct iommu_group *group = iommu_group_get(dev);
+
+		if (group) {
+			WARN_ON(owner->domain !=
+				iommu_group_default_domain(group));
+			exynos_iommu_detach_device(owner->domain, dev);
+			iommu_group_put(group);
+		}
+	}
 	iommu_group_remove_device(dev);
 }
 
@@ -1242,7 +1277,7 @@ static int exynos_iommu_of_xlate(struct device *dev,
 {
 	struct exynos_iommu_owner *owner = dev->archdata.iommu;
 	struct platform_device *sysmmu = of_find_device_by_node(spec->np);
-	struct sysmmu_drvdata *data;
+	struct sysmmu_drvdata *data, *entry;
 
 	if (!sysmmu)
 		return -ENODEV;
@@ -1261,6 +1296,10 @@ static int exynos_iommu_of_xlate(struct device *dev,
 		dev->archdata.iommu = owner;
 	}
 
+	list_for_each_entry(entry, &owner->controllers, owner_node)
+		if (entry == data)
+			return 0;
+
 	list_add_tail(&data->owner_node, &owner->controllers);
 	data->master = dev;
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 8a185250ae5a..f5e02f8e7371 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -440,6 +440,7 @@ struct dmar_rmrr_unit {
 	u64	end_address;		/* reserved end address */
 	struct dmar_dev_scope *devices;	/* target devices */
 	int	devices_cnt;		/* target device count */
+	struct iommu_resv_region *resv; /* reserved region handle */
 };
 
 struct dmar_atsr_unit {
@@ -547,7 +548,7 @@ EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
 static DEFINE_SPINLOCK(device_domain_lock);
 static LIST_HEAD(device_domain_list);
 
-static const struct iommu_ops intel_iommu_ops;
+const struct iommu_ops intel_iommu_ops;
 
 static bool translation_pre_enabled(struct intel_iommu *iommu)
 {
@@ -1144,7 +1145,7 @@ static void dma_pte_free_level(struct dmar_domain *domain, int level,
 		if (!dma_pte_present(pte) || dma_pte_superpage(pte))
 			goto next;
 
-		level_pfn = pfn & level_mask(level - 1);
+		level_pfn = pfn & level_mask(level);
 		level_pte = phys_to_virt(dma_pte_addr(pte));
 
 		if (level > 2)
@@ -3325,13 +3326,14 @@ static int __init init_dmars(void)
 	iommu_identity_mapping |= IDENTMAP_GFX;
 #endif
 
+	check_tylersburg_isoch();
+
 	if (iommu_identity_mapping) {
 		ret = si_domain_init(hw_pass_through);
 		if (ret)
 			goto free_iommu;
 	}
 
-	check_tylersburg_isoch();
 
 	/*
 	 * If we copied translations from a previous kernel in the kdump
@@ -4246,27 +4248,40 @@ static inline void init_iommu_pm_ops(void) {}
 int __init dmar_parse_one_rmrr(struct acpi_dmar_header *header, void *arg)
 {
 	struct acpi_dmar_reserved_memory *rmrr;
+	int prot = DMA_PTE_READ|DMA_PTE_WRITE;
 	struct dmar_rmrr_unit *rmrru;
+	size_t length;
 
 	rmrru = kzalloc(sizeof(*rmrru), GFP_KERNEL);
 	if (!rmrru)
-		return -ENOMEM;
+		goto out;
 
 	rmrru->hdr = header;
 	rmrr = (struct acpi_dmar_reserved_memory *)header;
 	rmrru->base_address = rmrr->base_address;
 	rmrru->end_address = rmrr->end_address;
+
+	length = rmrr->end_address - rmrr->base_address + 1;
+	rmrru->resv = iommu_alloc_resv_region(rmrr->base_address, length, prot,
+					      IOMMU_RESV_DIRECT);
+	if (!rmrru->resv)
+		goto free_rmrru;
+
 	rmrru->devices = dmar_alloc_dev_scope((void *)(rmrr + 1),
 				((void *)rmrr) + rmrr->header.length,
 				&rmrru->devices_cnt);
-	if (rmrru->devices_cnt && rmrru->devices == NULL) {
-		kfree(rmrru);
-		return -ENOMEM;
-	}
+	if (rmrru->devices_cnt && rmrru->devices == NULL)
+		goto free_all;
 
 	list_add(&rmrru->list, &dmar_rmrr_units);
 
 	return 0;
+free_all:
+	kfree(rmrru->resv);
+free_rmrru:
+	kfree(rmrru);
+out:
+	return -ENOMEM;
 }
 
 static struct dmar_atsr_unit *dmar_find_atsr(struct acpi_dmar_atsr *atsr)
@@ -4480,6 +4495,7 @@ static void intel_iommu_free_dmars(void)
 	list_for_each_entry_safe(rmrru, rmrr_n, &dmar_rmrr_units, list) {
 		list_del(&rmrru->list);
 		dmar_free_dev_scope(&rmrru->devices, &rmrru->devices_cnt);
+		kfree(rmrru->resv);
 		kfree(rmrru);
 	}
 
@@ -4853,10 +4869,13 @@ int __init intel_iommu_init(void)
 
 	init_iommu_pm_ops();
 
-	for_each_active_iommu(iommu, drhd)
-		iommu->iommu_dev = iommu_device_create(NULL, iommu,
-						       intel_iommu_groups,
-						       "%s", iommu->name);
+	for_each_active_iommu(iommu, drhd) {
+		iommu_device_sysfs_add(&iommu->iommu, NULL,
+				       intel_iommu_groups,
+				       "%s", iommu->name);
+		iommu_device_set_ops(&iommu->iommu, &intel_iommu_ops);
+		iommu_device_register(&iommu->iommu);
+	}
 
 	bus_set_iommu(&pci_bus_type, &intel_iommu_ops);
 	bus_register_notifier(&pci_bus_type, &device_nb);
@@ -5178,7 +5197,7 @@ static int intel_iommu_add_device(struct device *dev)
 	if (!iommu)
 		return -ENODEV;
 
-	iommu_device_link(iommu->iommu_dev, dev);
+	iommu_device_link(&iommu->iommu, dev);
 
 	group = iommu_group_get_for_dev(dev);
 
@@ -5200,7 +5219,46 @@ static void intel_iommu_remove_device(struct device *dev)
 
 	iommu_group_remove_device(dev);
 
-	iommu_device_unlink(iommu->iommu_dev, dev);
+	iommu_device_unlink(&iommu->iommu, dev);
+}
+
+static void intel_iommu_get_resv_regions(struct device *device,
+					 struct list_head *head)
+{
+	struct iommu_resv_region *reg;
+	struct dmar_rmrr_unit *rmrr;
+	struct device *i_dev;
+	int i;
+
+	rcu_read_lock();
+	for_each_rmrr_units(rmrr) {
+		for_each_active_dev_scope(rmrr->devices, rmrr->devices_cnt,
+					  i, i_dev) {
+			if (i_dev != device)
+				continue;
+
+			list_add_tail(&rmrr->resv->list, head);
+		}
+	}
+	rcu_read_unlock();
+
+	reg = iommu_alloc_resv_region(IOAPIC_RANGE_START,
+				      IOAPIC_RANGE_END - IOAPIC_RANGE_START + 1,
+				      0, IOMMU_RESV_RESERVED);
+	if (!reg)
+		return;
+	list_add_tail(&reg->list, head);
+}
+
+static void intel_iommu_put_resv_regions(struct device *dev,
+					 struct list_head *head)
+{
+	struct iommu_resv_region *entry, *next;
+
+	list_for_each_entry_safe(entry, next, head, list) {
+		if (entry->type == IOMMU_RESV_RESERVED)
+			kfree(entry);
+	}
 }
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
@@ -5332,20 +5390,22 @@ struct intel_iommu *intel_svm_device_to_iommu(struct device *dev)
 }
 #endif /* CONFIG_INTEL_IOMMU_SVM */
 
-static const struct iommu_ops intel_iommu_ops = {
-	.capable	= intel_iommu_capable,
-	.domain_alloc	= intel_iommu_domain_alloc,
-	.domain_free	= intel_iommu_domain_free,
-	.attach_dev	= intel_iommu_attach_device,
-	.detach_dev	= intel_iommu_detach_device,
-	.map		= intel_iommu_map,
-	.unmap		= intel_iommu_unmap,
-	.map_sg		= default_iommu_map_sg,
-	.iova_to_phys	= intel_iommu_iova_to_phys,
-	.add_device	= intel_iommu_add_device,
-	.remove_device	= intel_iommu_remove_device,
-	.device_group   = pci_device_group,
-	.pgsize_bitmap	= INTEL_IOMMU_PGSIZES,
+const struct iommu_ops intel_iommu_ops = {
+	.capable		= intel_iommu_capable,
+	.domain_alloc		= intel_iommu_domain_alloc,
+	.domain_free		= intel_iommu_domain_free,
+	.attach_dev		= intel_iommu_attach_device,
+	.detach_dev		= intel_iommu_detach_device,
+	.map			= intel_iommu_map,
+	.unmap			= intel_iommu_unmap,
+	.map_sg			= default_iommu_map_sg,
+	.iova_to_phys		= intel_iommu_iova_to_phys,
+	.add_device		= intel_iommu_add_device,
+	.remove_device		= intel_iommu_remove_device,
+	.get_resv_regions	= intel_iommu_get_resv_regions,
+	.put_resv_regions	= intel_iommu_put_resv_regions,
+	.device_group		= pci_device_group,
+	.pgsize_bitmap		= INTEL_IOMMU_PGSIZES,
 };
 
 static void quirk_iommu_g4x_gfx(struct pci_dev *dev)
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 0769276c0537..1c049e2e12bf 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -265,7 +265,9 @@ static arm_v7s_iopte arm_v7s_prot_to_pte(int prot, int lvl,
 	if (!(prot & IOMMU_MMIO))
 		pte |= ARM_V7S_ATTR_TEX(1);
 	if (ap) {
-		pte |= ARM_V7S_PTE_AF | ARM_V7S_PTE_AP_UNPRIV;
+		pte |= ARM_V7S_PTE_AF;
+		if (!(prot & IOMMU_PRIV))
+			pte |= ARM_V7S_PTE_AP_UNPRIV;
 		if (!(prot & IOMMU_WRITE))
 			pte |= ARM_V7S_PTE_AP_RDONLY;
 	}
@@ -288,6 +290,8 @@ static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int lvl)
 
 	if (!(attr & ARM_V7S_PTE_AP_RDONLY))
 		prot |= IOMMU_WRITE;
+	if (!(attr & ARM_V7S_PTE_AP_UNPRIV))
+		prot |= IOMMU_PRIV;
 	if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0)
 		prot |= IOMMU_MMIO;
 	else if (pte & ARM_V7S_ATTR_C)
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index a40ce3406fef..feacc54bec68 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -350,11 +350,14 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 
 	if (data->iop.fmt == ARM_64_LPAE_S1 ||
 	    data->iop.fmt == ARM_32_LPAE_S1) {
-		pte = ARM_LPAE_PTE_AP_UNPRIV | ARM_LPAE_PTE_nG;
+		pte = ARM_LPAE_PTE_nG;
 
 		if (!(prot & IOMMU_WRITE) && (prot & IOMMU_READ))
 			pte |= ARM_LPAE_PTE_AP_RDONLY;
 
+		if (!(prot & IOMMU_PRIV))
+			pte |= ARM_LPAE_PTE_AP_UNPRIV;
+
 		if (prot & IOMMU_MMIO)
 			pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
diff --git a/drivers/iommu/iommu-sysfs.c b/drivers/iommu/iommu-sysfs.c
index 39b2d9127dbf..c58351ed61c1 100644
--- a/drivers/iommu/iommu-sysfs.c
+++ b/drivers/iommu/iommu-sysfs.c
@@ -50,85 +50,76 @@ static int __init iommu_dev_init(void)
 postcore_initcall(iommu_dev_init);
 
 /*
- * Create an IOMMU device and return a pointer to it.  IOMMU specific
- * attributes can be provided as an attribute group, allowing a unique
- * namespace per IOMMU type.
+ * Init the struct device for the IOMMU. IOMMU specific attributes can
+ * be provided as an attribute group, allowing a unique namespace per
+ * IOMMU type.
  */
-struct device *iommu_device_create(struct device *parent, void *drvdata,
-				   const struct attribute_group **groups,
-				   const char *fmt, ...)
+int iommu_device_sysfs_add(struct iommu_device *iommu,
+			   struct device *parent,
+			   const struct attribute_group **groups,
+			   const char *fmt, ...)
 {
-	struct device *dev;
 	va_list vargs;
 	int ret;
 
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return ERR_PTR(-ENOMEM);
+	device_initialize(&iommu->dev);
 
-	device_initialize(dev);
-
-	dev->class = &iommu_class;
-	dev->parent = parent;
-	dev->groups = groups;
-	dev_set_drvdata(dev, drvdata);
+	iommu->dev.class = &iommu_class;
+	iommu->dev.parent = parent;
+	iommu->dev.groups = groups;
 
 	va_start(vargs, fmt);
-	ret = kobject_set_name_vargs(&dev->kobj, fmt, vargs);
+	ret = kobject_set_name_vargs(&iommu->dev.kobj, fmt, vargs);
 	va_end(vargs);
 	if (ret)
 		goto error;
 
-	ret = device_add(dev);
+	ret = device_add(&iommu->dev);
 	if (ret)
 		goto error;
 
-	return dev;
+	return 0;
 
 error:
-	put_device(dev);
-	return ERR_PTR(ret);
+	put_device(&iommu->dev);
+	return ret;
 }
 
-void iommu_device_destroy(struct device *dev)
+void iommu_device_sysfs_remove(struct iommu_device *iommu)
 {
-	if (!dev || IS_ERR(dev))
-		return;
-
-	device_unregister(dev);
+	device_unregister(&iommu->dev);
 }
-
 /*
  * IOMMU drivers can indicate a device is managed by a given IOMMU using
  * this interface.  A link to the device will be created in the "devices"
  * directory of the IOMMU device in sysfs and an "iommu" link will be
  * created under the linked device, pointing back at the IOMMU device.
  */
-int iommu_device_link(struct device *dev, struct device *link)
+int iommu_device_link(struct iommu_device *iommu, struct device *link)
 {
 	int ret;
 
-	if (!dev || IS_ERR(dev))
+	if (!iommu || IS_ERR(iommu))
 		return -ENODEV;
 
-	ret = sysfs_add_link_to_group(&dev->kobj, "devices",
+	ret = sysfs_add_link_to_group(&iommu->dev.kobj, "devices",
 				      &link->kobj, dev_name(link));
 	if (ret)
 		return ret;
 
-	ret = sysfs_create_link_nowarn(&link->kobj, &dev->kobj, "iommu");
+	ret = sysfs_create_link_nowarn(&link->kobj, &iommu->dev.kobj, "iommu");
 	if (ret)
-		sysfs_remove_link_from_group(&dev->kobj, "devices",
+		sysfs_remove_link_from_group(&iommu->dev.kobj, "devices",
 					     dev_name(link));
 
 	return ret;
 }
 
-void iommu_device_unlink(struct device *dev, struct device *link)
+void iommu_device_unlink(struct iommu_device *iommu, struct device *link)
 {
-	if (!dev || IS_ERR(dev))
+	if (!iommu || IS_ERR(iommu))
 		return;
 
 	sysfs_remove_link(&link->kobj, "iommu");
-	sysfs_remove_link_from_group(&dev->kobj, "devices", dev_name(link));
+	sysfs_remove_link_from_group(&iommu->dev.kobj, "devices", dev_name(link));
 }
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index dbe7f653bb7c..8ea14f41a979 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -55,7 +55,7 @@ struct iommu_group {
 	struct iommu_domain *domain;
 };
 
-struct iommu_device {
+struct group_device {
 	struct list_head list;
 	struct device *dev;
 	char *name;
@@ -68,6 +68,12 @@ struct iommu_group_attribute {
 			 const char *buf, size_t count);
 };
 
+static const char * const iommu_group_resv_type_string[] = {
+	[IOMMU_RESV_DIRECT]	= "direct",
+	[IOMMU_RESV_RESERVED]	= "reserved",
+	[IOMMU_RESV_MSI]	= "msi",
+};
+
 #define IOMMU_GROUP_ATTR(_name, _mode, _show, _store)		\
 struct iommu_group_attribute iommu_group_attr_##_name =		\
 	__ATTR(_name, _mode, _show, _store)
@@ -77,6 +83,25 @@ struct iommu_group_attribute iommu_group_attr_##_name =		\
 #define to_iommu_group(_kobj)		\
 	container_of(_kobj, struct iommu_group, kobj)
 
+static LIST_HEAD(iommu_device_list);
+static DEFINE_SPINLOCK(iommu_device_lock);
+
+int iommu_device_register(struct iommu_device *iommu)
+{
+	spin_lock(&iommu_device_lock);
+	list_add_tail(&iommu->list, &iommu_device_list);
+	spin_unlock(&iommu_device_lock);
+
+	return 0;
+}
+
+void iommu_device_unregister(struct iommu_device *iommu)
+{
+	spin_lock(&iommu_device_lock);
+	list_del(&iommu->list);
+	spin_unlock(&iommu_device_lock);
+}
+
 static struct iommu_domain *__iommu_domain_alloc(struct bus_type *bus,
 						 unsigned type);
 static int __iommu_attach_device(struct iommu_domain *domain,
@@ -133,8 +158,131 @@ static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf)
 	return sprintf(buf, "%s\n", group->name);
 }
 
+/**
+ * iommu_insert_resv_region - Insert a new region in the
+ * list of reserved regions.
+ * @new: new region to insert
+ * @regions: list of regions
+ *
+ * The new element is sorted by address with respect to the other
+ * regions of the same type. In case it overlaps with another
+ * region of the same type, regions are merged. In case it
+ * overlaps with another region of different type, regions are
+ * not merged.
+ */
+static int iommu_insert_resv_region(struct iommu_resv_region *new,
+				    struct list_head *regions)
+{
+	struct iommu_resv_region *region;
+	phys_addr_t start = new->start;
+	phys_addr_t end = new->start + new->length - 1;
+	struct list_head *pos = regions->next;
+
+	while (pos != regions) {
+		struct iommu_resv_region *entry =
+			list_entry(pos, struct iommu_resv_region, list);
+		phys_addr_t a = entry->start;
+		phys_addr_t b = entry->start + entry->length - 1;
+		int type = entry->type;
+
+		if (end < a) {
+			goto insert;
+		} else if (start > b) {
+			pos = pos->next;
+		} else if ((start >= a) && (end <= b)) {
+			if (new->type == type)
+				goto done;
+			else
+				pos = pos->next;
+		} else {
+			if (new->type == type) {
+				phys_addr_t new_start = min(a, start);
+				phys_addr_t new_end = max(b, end);
+
+				list_del(&entry->list);
+				entry->start = new_start;
+				entry->length = new_end - new_start + 1;
+				iommu_insert_resv_region(entry, regions);
+			} else {
+				pos = pos->next;
+			}
+		}
+	}
+insert:
+	region = iommu_alloc_resv_region(new->start, new->length,
+					 new->prot, new->type);
+	if (!region)
+		return -ENOMEM;
+
+	list_add_tail(&region->list, pos);
+done:
+	return 0;
+}
+
+static int
+iommu_insert_device_resv_regions(struct list_head *dev_resv_regions,
+				 struct list_head *group_resv_regions)
+{
+	struct iommu_resv_region *entry;
+	int ret = 0;
+
+	list_for_each_entry(entry, dev_resv_regions, list) {
+		ret = iommu_insert_resv_region(entry, group_resv_regions);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+int iommu_get_group_resv_regions(struct iommu_group *group,
+				 struct list_head *head)
+{
+	struct group_device *device;
+	int ret = 0;
+
+	mutex_lock(&group->mutex);
+	list_for_each_entry(device, &group->devices, list) {
+		struct list_head dev_resv_regions;
+
+		INIT_LIST_HEAD(&dev_resv_regions);
+		iommu_get_resv_regions(device->dev, &dev_resv_regions);
+		ret = iommu_insert_device_resv_regions(&dev_resv_regions, head);
+		iommu_put_resv_regions(device->dev, &dev_resv_regions);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&group->mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_get_group_resv_regions);
+
+static ssize_t iommu_group_show_resv_regions(struct iommu_group *group,
+					     char *buf)
+{
+	struct iommu_resv_region *region, *next;
+	struct list_head group_resv_regions;
+	char *str = buf;
+
+	INIT_LIST_HEAD(&group_resv_regions);
+	iommu_get_group_resv_regions(group, &group_resv_regions);
+
+	list_for_each_entry_safe(region, next, &group_resv_regions, list) {
+		str += sprintf(str, "0x%016llx 0x%016llx %s\n",
+			       (long long int)region->start,
+			       (long long int)(region->start +
+						region->length - 1),
+			       iommu_group_resv_type_string[region->type]);
+		kfree(region);
+	}
+
+	return (str - buf);
+}
+
 static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL);
 
+static IOMMU_GROUP_ATTR(reserved_regions, 0444,
+			iommu_group_show_resv_regions, NULL);
+
 static void iommu_group_release(struct kobject *kobj)
 {
 	struct iommu_group *group = to_iommu_group(kobj);
@@ -212,6 +360,11 @@ struct iommu_group *iommu_group_alloc(void)
 	 */
 	kobject_put(&group->kobj);
 
+	ret = iommu_group_create_file(group,
+				      &iommu_group_attr_reserved_regions);
+	if (ret)
+		return ERR_PTR(ret);
+
 	pr_debug("Allocated group %d\n", group->id);
 
 	return group;
@@ -318,7 +471,7 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
 					      struct device *dev)
 {
 	struct iommu_domain *domain = group->default_domain;
-	struct iommu_dm_region *entry;
+	struct iommu_resv_region *entry;
 	struct list_head mappings;
 	unsigned long pg_size;
 	int ret = 0;
@@ -331,18 +484,21 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
 	pg_size = 1UL << __ffs(domain->pgsize_bitmap);
 	INIT_LIST_HEAD(&mappings);
 
-	iommu_get_dm_regions(dev, &mappings);
+	iommu_get_resv_regions(dev, &mappings);
 
 	/* We need to consider overlapping regions for different devices */
 	list_for_each_entry(entry, &mappings, list) {
 		dma_addr_t start, end, addr;
 
-		if (domain->ops->apply_dm_region)
-			domain->ops->apply_dm_region(dev, domain, entry);
+		if (domain->ops->apply_resv_region)
+			domain->ops->apply_resv_region(dev, domain, entry);
 
 		start = ALIGN(entry->start, pg_size);
 		end   = ALIGN(entry->start + entry->length, pg_size);
 
+		if (entry->type != IOMMU_RESV_DIRECT)
+			continue;
+
 		for (addr = start; addr < end; addr += pg_size) {
 			phys_addr_t phys_addr;
 
@@ -358,7 +514,7 @@ static int iommu_group_create_direct_mappings(struct iommu_group *group,
 	}
 
 out:
-	iommu_put_dm_regions(dev, &mappings);
+	iommu_put_resv_regions(dev, &mappings);
 
 	return ret;
 }
@@ -374,7 +530,7 @@ out:
 int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 {
 	int ret, i = 0;
-	struct iommu_device *device;
+	struct group_device *device;
 
 	device = kzalloc(sizeof(*device), GFP_KERNEL);
 	if (!device)
@@ -383,36 +539,30 @@ int iommu_group_add_device(struct iommu_group *group, struct device *dev)
 	device->dev = dev;
 
 	ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group");
-	if (ret) {
-		kfree(device);
-		return ret;
-	}
+	if (ret)
+		goto err_free_device;
 
 	device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj));
 rename:
 	if (!device->name) {
-		sysfs_remove_link(&dev->kobj, "iommu_group");
-		kfree(device);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_remove_link;
 	}
 
 	ret = sysfs_create_link_nowarn(group->devices_kobj,
 				       &dev->kobj, device->name);
 	if (ret) {
-		kfree(device->name);
 		if (ret == -EEXIST && i >= 0) {
 			/*
 			 * Account for the slim chance of collision
 			 * and append an instance to the name.
 			 */
+			kfree(device->name);
 			device->name = kasprintf(GFP_KERNEL, "%s.%d",
 						 kobject_name(&dev->kobj), i++);
 			goto rename;
 		}
-
-		sysfs_remove_link(&dev->kobj, "iommu_group");
-		kfree(device);
-		return ret;
+		goto err_free_name;
 	}
 
 	kobject_get(group->devices_kobj);
@@ -424,8 +574,10 @@ rename:
 	mutex_lock(&group->mutex);
 	list_add_tail(&device->list, &group->devices);
 	if (group->domain)
-		__iommu_attach_device(group->domain, dev);
+		ret = __iommu_attach_device(group->domain, dev);
 	mutex_unlock(&group->mutex);
+	if (ret)
+		goto err_put_group;
 
 	/* Notify any listeners about change to group. */
 	blocking_notifier_call_chain(&group->notifier,
@@ -436,6 +588,21 @@ rename:
 	pr_info("Adding device %s to group %d\n", dev_name(dev), group->id);
 
 	return 0;
+
+err_put_group:
+	mutex_lock(&group->mutex);
+	list_del(&device->list);
+	mutex_unlock(&group->mutex);
+	dev->iommu_group = NULL;
+	kobject_put(group->devices_kobj);
+err_free_name:
+	kfree(device->name);
+err_remove_link:
+	sysfs_remove_link(&dev->kobj, "iommu_group");
+err_free_device:
+	kfree(device);
+	pr_err("Failed to add device %s to group %d: %d\n", dev_name(dev), group->id, ret);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(iommu_group_add_device);
 
@@ -449,7 +616,7 @@ EXPORT_SYMBOL_GPL(iommu_group_add_device);
 void iommu_group_remove_device(struct device *dev)
 {
 	struct iommu_group *group = dev->iommu_group;
-	struct iommu_device *tmp_device, *device = NULL;
+	struct group_device *tmp_device, *device = NULL;
 
 	pr_info("Removing device %s from group %d\n", dev_name(dev), group->id);
 
@@ -484,7 +651,7 @@ EXPORT_SYMBOL_GPL(iommu_group_remove_device);
 
 static int iommu_group_device_count(struct iommu_group *group)
 {
-	struct iommu_device *entry;
+	struct group_device *entry;
 	int ret = 0;
 
 	list_for_each_entry(entry, &group->devices, list)
@@ -507,7 +674,7 @@ static int iommu_group_device_count(struct iommu_group *group)
 static int __iommu_group_for_each_dev(struct iommu_group *group, void *data,
 				      int (*fn)(struct device *, void *))
 {
-	struct iommu_device *device;
+	struct group_device *device;
 	int ret = 0;
 
 	list_for_each_entry(device, &group->devices, list) {
@@ -1559,20 +1726,38 @@ int iommu_domain_set_attr(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_domain_set_attr);
 
-void iommu_get_dm_regions(struct device *dev, struct list_head *list)
+void iommu_get_resv_regions(struct device *dev, struct list_head *list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
 
-	if (ops && ops->get_dm_regions)
-		ops->get_dm_regions(dev, list);
+	if (ops && ops->get_resv_regions)
+		ops->get_resv_regions(dev, list);
 }
 
-void iommu_put_dm_regions(struct device *dev, struct list_head *list)
+void iommu_put_resv_regions(struct device *dev, struct list_head *list)
 {
 	const struct iommu_ops *ops = dev->bus->iommu_ops;
 
-	if (ops && ops->put_dm_regions)
-		ops->put_dm_regions(dev, list);
+	if (ops && ops->put_resv_regions)
+		ops->put_resv_regions(dev, list);
+}
+
+struct iommu_resv_region *iommu_alloc_resv_region(phys_addr_t start,
+						  size_t length,
+						  int prot, int type)
+{
+	struct iommu_resv_region *region;
+
+	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	if (!region)
+		return NULL;
+
+	INIT_LIST_HEAD(&region->list);
+	region->start = start;
+	region->length = length;
+	region->prot = prot;
+	region->type = type;
+	return region;
 }
 
 /* Request that a device is direct mapped by the IOMMU */
@@ -1628,43 +1813,18 @@ out:
 	return ret;
 }
 
-struct iommu_instance {
-	struct list_head list;
-	struct fwnode_handle *fwnode;
-	const struct iommu_ops *ops;
-};
-static LIST_HEAD(iommu_instance_list);
-static DEFINE_SPINLOCK(iommu_instance_lock);
-
-void iommu_register_instance(struct fwnode_handle *fwnode,
-			     const struct iommu_ops *ops)
+const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
 {
-	struct iommu_instance *iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
-
-	if (WARN_ON(!iommu))
-		return;
-
-	of_node_get(to_of_node(fwnode));
-	INIT_LIST_HEAD(&iommu->list);
-	iommu->fwnode = fwnode;
-	iommu->ops = ops;
-	spin_lock(&iommu_instance_lock);
-	list_add_tail(&iommu->list, &iommu_instance_list);
-	spin_unlock(&iommu_instance_lock);
-}
-
-const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode)
-{
-	struct iommu_instance *instance;
 	const struct iommu_ops *ops = NULL;
+	struct iommu_device *iommu;
 
-	spin_lock(&iommu_instance_lock);
-	list_for_each_entry(instance, &iommu_instance_list, list)
-		if (instance->fwnode == fwnode) {
-			ops = instance->ops;
+	spin_lock(&iommu_device_lock);
+	list_for_each_entry(iommu, &iommu_device_list, list)
+		if (iommu->fwnode == fwnode) {
+			ops = iommu->ops;
 			break;
 		}
-	spin_unlock(&iommu_instance_lock);
+	spin_unlock(&iommu_device_lock);
 	return ops;
 }
 
@@ -1714,13 +1874,14 @@ int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids)
 		fwspec = krealloc(dev->iommu_fwspec, size, GFP_KERNEL);
 		if (!fwspec)
 			return -ENOMEM;
+
+		dev->iommu_fwspec = fwspec;
 	}
 
 	for (i = 0; i < num_ids; i++)
 		fwspec->ids[fwspec->num_ids + i] = ids[i];
 
 	fwspec->num_ids += num_ids;
-	dev->iommu_fwspec = fwspec;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(iommu_fwspec_add_ids);
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 080beca0197d..b7268a14184f 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -62,7 +62,7 @@ __get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
 	else {
 		struct rb_node *prev_node = rb_prev(iovad->cached32_node);
 		struct iova *curr_iova =
-			container_of(iovad->cached32_node, struct iova, node);
+			rb_entry(iovad->cached32_node, struct iova, node);
 		*limit_pfn = curr_iova->pfn_lo - 1;
 		return prev_node;
 	}
@@ -86,11 +86,11 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 	if (!iovad->cached32_node)
 		return;
 	curr = iovad->cached32_node;
-	cached_iova = container_of(curr, struct iova, node);
+	cached_iova = rb_entry(curr, struct iova, node);
 
 	if (free->pfn_lo >= cached_iova->pfn_lo) {
 		struct rb_node *node = rb_next(&free->node);
-		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *iova = rb_entry(node, struct iova, node);
 
 		/* only cache if it's below 32bit pfn */
 		if (node && iova->pfn_lo < iovad->dma_32bit_pfn)
@@ -125,7 +125,7 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 	curr = __get_cached_rbnode(iovad, &limit_pfn);
 	prev = curr;
 	while (curr) {
-		struct iova *curr_iova = container_of(curr, struct iova, node);
+		struct iova *curr_iova = rb_entry(curr, struct iova, node);
 
 		if (limit_pfn < curr_iova->pfn_lo)
 			goto move_left;
@@ -171,8 +171,7 @@ move_left:
 
 		/* Figure out where to put new node */
 		while (*entry) {
-			struct iova *this = container_of(*entry,
-							struct iova, node);
+			struct iova *this = rb_entry(*entry, struct iova, node);
 			parent = *entry;
 
 			if (new->pfn_lo < this->pfn_lo)
@@ -201,7 +200,7 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova)
 	struct rb_node **new = &(root->rb_node), *parent = NULL;
 	/* Figure out where to put new node */
 	while (*new) {
-		struct iova *this = container_of(*new, struct iova, node);
+		struct iova *this = rb_entry(*new, struct iova, node);
 
 		parent = *new;
 
@@ -311,7 +310,7 @@ private_find_iova(struct iova_domain *iovad, unsigned long pfn)
 	assert_spin_locked(&iovad->iova_rbtree_lock);
 
 	while (node) {
-		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *iova = rb_entry(node, struct iova, node);
 
 		/* If pfn falls within iova's range, return iova */
 		if ((pfn >= iova->pfn_lo) && (pfn <= iova->pfn_hi)) {
@@ -463,7 +462,7 @@ void put_iova_domain(struct iova_domain *iovad)
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
 	node = rb_first(&iovad->rbroot);
 	while (node) {
-		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *iova = rb_entry(node, struct iova, node);
 
 		rb_erase(node, &iovad->rbroot);
 		free_iova_mem(iova);
@@ -477,7 +476,7 @@ static int
 __is_range_overlap(struct rb_node *node,
 	unsigned long pfn_lo, unsigned long pfn_hi)
 {
-	struct iova *iova = container_of(node, struct iova, node);
+	struct iova *iova = rb_entry(node, struct iova, node);
 
 	if ((pfn_lo <= iova->pfn_hi) && (pfn_hi >= iova->pfn_lo))
 		return 1;
@@ -541,7 +540,7 @@ reserve_iova(struct iova_domain *iovad,
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
 	for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
 		if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
-			iova = container_of(node, struct iova, node);
+			iova = rb_entry(node, struct iova, node);
 			__adjust_overlap_range(iova, &pfn_lo, &pfn_hi);
 			if ((pfn_lo >= iova->pfn_lo) &&
 				(pfn_hi <= iova->pfn_hi))
@@ -578,7 +577,7 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 
 	spin_lock_irqsave(&from->iova_rbtree_lock, flags);
 	for (node = rb_first(&from->rbroot); node; node = rb_next(node)) {
-		struct iova *iova = container_of(node, struct iova, node);
+		struct iova *iova = rb_entry(node, struct iova, node);
 		struct iova *new_iova;
 
 		new_iova = reserve_iova(to, iova->pfn_lo, iova->pfn_hi);
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index ace331da6459..b7e14ee863f9 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -313,6 +313,8 @@ static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
 	domain->cfg.ias = 32;
 	domain->cfg.oas = 40;
 	domain->cfg.tlb = &ipmmu_gather_ops;
+	domain->io_domain.geometry.aperture_end = DMA_BIT_MASK(32);
+	domain->io_domain.geometry.force_aperture = true;
 	/*
 	 * TODO: Add support for coherent walk through CCI with DVM and remove
 	 * cache handling. For now, delegate it to the io-pgtable code.
diff --git a/drivers/iommu/msm_iommu.c b/drivers/iommu/msm_iommu.c
index b09692bb5b0a..d0448353d501 100644
--- a/drivers/iommu/msm_iommu.c
+++ b/drivers/iommu/msm_iommu.c
@@ -371,6 +371,58 @@ static int msm_iommu_domain_config(struct msm_priv *priv)
 	return 0;
 }
 
+/* Must be called under msm_iommu_lock */
+static struct msm_iommu_dev *find_iommu_for_dev(struct device *dev)
+{
+	struct msm_iommu_dev *iommu, *ret = NULL;
+	struct msm_iommu_ctx_dev *master;
+
+	list_for_each_entry(iommu, &qcom_iommu_devices, dev_node) {
+		master = list_first_entry(&iommu->ctx_list,
+					  struct msm_iommu_ctx_dev,
+					  list);
+		if (master->of_node == dev->of_node) {
+			ret = iommu;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static int msm_iommu_add_device(struct device *dev)
+{
+	struct msm_iommu_dev *iommu;
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	iommu = find_iommu_for_dev(dev);
+	if (iommu)
+		iommu_device_link(&iommu->iommu, dev);
+	else
+		ret = -ENODEV;
+
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+
+	return ret;
+}
+
+static void msm_iommu_remove_device(struct device *dev)
+{
+	struct msm_iommu_dev *iommu;
+	unsigned long flags;
+
+	spin_lock_irqsave(&msm_iommu_lock, flags);
+
+	iommu = find_iommu_for_dev(dev);
+	if (iommu)
+		iommu_device_unlink(&iommu->iommu, dev);
+
+	spin_unlock_irqrestore(&msm_iommu_lock, flags);
+}
+
 static int msm_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
 {
 	int ret = 0;
@@ -646,6 +698,8 @@ static struct iommu_ops msm_iommu_ops = {
 	.unmap = msm_iommu_unmap,
 	.map_sg = default_iommu_map_sg,
 	.iova_to_phys = msm_iommu_iova_to_phys,
+	.add_device = msm_iommu_add_device,
+	.remove_device = msm_iommu_remove_device,
 	.pgsize_bitmap = MSM_IOMMU_PGSIZES,
 	.of_xlate = qcom_iommu_of_xlate,
 };
@@ -653,6 +707,7 @@ static struct iommu_ops msm_iommu_ops = {
 static int msm_iommu_probe(struct platform_device *pdev)
 {
 	struct resource *r;
+	resource_size_t ioaddr;
 	struct msm_iommu_dev *iommu;
 	int ret, par, val;
 
@@ -696,6 +751,7 @@ static int msm_iommu_probe(struct platform_device *pdev)
 		ret = PTR_ERR(iommu->base);
 		goto fail;
 	}
+	ioaddr = r->start;
 
 	iommu->irq = platform_get_irq(pdev, 0);
 	if (iommu->irq < 0) {
@@ -737,7 +793,22 @@ static int msm_iommu_probe(struct platform_device *pdev)
 	}
 
 	list_add(&iommu->dev_node, &qcom_iommu_devices);
-	of_iommu_set_ops(pdev->dev.of_node, &msm_iommu_ops);
+
+	ret = iommu_device_sysfs_add(&iommu->iommu, iommu->dev, NULL,
+				     "msm-smmu.%pa", &ioaddr);
+	if (ret) {
+		pr_err("Could not add msm-smmu at %pa to sysfs\n", &ioaddr);
+		goto fail;
+	}
+
+	iommu_device_set_ops(&iommu->iommu, &msm_iommu_ops);
+	iommu_device_set_fwnode(&iommu->iommu, &pdev->dev.of_node->fwnode);
+
+	ret = iommu_device_register(&iommu->iommu);
+	if (ret) {
+		pr_err("Could not register msm-smmu at %pa\n", &ioaddr);
+		goto fail;
+	}
 
 	pr_info("device mapped at %p, irq %d with %d ctx banks\n",
 		iommu->base, iommu->irq, iommu->ncb);
diff --git a/drivers/iommu/msm_iommu.h b/drivers/iommu/msm_iommu.h
index 4ca25d50d679..ae92d2779c42 100644
--- a/drivers/iommu/msm_iommu.h
+++ b/drivers/iommu/msm_iommu.h
@@ -19,6 +19,7 @@
 #define MSM_IOMMU_H
 
 #include <linux/interrupt.h>
+#include <linux/iommu.h>
 #include <linux/clk.h>
 
 /* Sharability attributes of MSM IOMMU mappings */
@@ -68,6 +69,8 @@ struct msm_iommu_dev {
 	struct list_head dom_node;
 	struct list_head ctx_list;
 	DECLARE_BITMAP(context_map, IOMMU_MAX_CBS);
+
+	struct iommu_device iommu;
 };
 
 /**
diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c
index 1479c76ece9e..5d14cd15198d 100644
--- a/drivers/iommu/mtk_iommu.c
+++ b/drivers/iommu/mtk_iommu.c
@@ -360,11 +360,15 @@ static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
 
 static int mtk_iommu_add_device(struct device *dev)
 {
+	struct mtk_iommu_data *data;
 	struct iommu_group *group;
 
 	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
 		return -ENODEV; /* Not a iommu client device */
 
+	data = dev->iommu_fwspec->iommu_priv;
+	iommu_device_link(&data->iommu, dev);
+
 	group = iommu_group_get_for_dev(dev);
 	if (IS_ERR(group))
 		return PTR_ERR(group);
@@ -375,9 +379,14 @@ static int mtk_iommu_add_device(struct device *dev)
 
 static void mtk_iommu_remove_device(struct device *dev)
 {
+	struct mtk_iommu_data *data;
+
 	if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops)
 		return;
 
+	data = dev->iommu_fwspec->iommu_priv;
+	iommu_device_unlink(&data->iommu, dev);
+
 	iommu_group_remove_device(dev);
 	iommu_fwspec_free(dev);
 }
@@ -497,6 +506,7 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	struct mtk_iommu_data   *data;
 	struct device           *dev = &pdev->dev;
 	struct resource         *res;
+	resource_size_t		ioaddr;
 	struct component_match  *match = NULL;
 	void                    *protect;
 	int                     i, larb_nr, ret;
@@ -519,6 +529,7 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	data->base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(data->base))
 		return PTR_ERR(data->base);
+	ioaddr = res->start;
 
 	data->irq = platform_get_irq(pdev, 0);
 	if (data->irq < 0)
@@ -567,6 +578,18 @@ static int mtk_iommu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
+				     "mtk-iommu.%pa", &ioaddr);
+	if (ret)
+		return ret;
+
+	iommu_device_set_ops(&data->iommu, &mtk_iommu_ops);
+	iommu_device_set_fwnode(&data->iommu, &pdev->dev.of_node->fwnode);
+
+	ret = iommu_device_register(&data->iommu);
+	if (ret)
+		return ret;
+
 	if (!iommu_present(&platform_bus_type))
 		bus_set_iommu(&platform_bus_type, &mtk_iommu_ops);
 
@@ -577,6 +600,9 @@ static int mtk_iommu_remove(struct platform_device *pdev)
 {
 	struct mtk_iommu_data *data = platform_get_drvdata(pdev);
 
+	iommu_device_sysfs_remove(&data->iommu);
+	iommu_device_unregister(&data->iommu);
+
 	if (iommu_present(&platform_bus_type))
 		bus_set_iommu(&platform_bus_type, NULL);
 
@@ -655,7 +681,6 @@ static int mtk_iommu_init_fn(struct device_node *np)
 		return ret;
 	}
 
-	of_iommu_set_ops(np, &mtk_iommu_ops);
 	return 0;
 }
 
diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h
index 50177f738e4e..2a28eadeea0e 100644
--- a/drivers/iommu/mtk_iommu.h
+++ b/drivers/iommu/mtk_iommu.h
@@ -47,6 +47,8 @@ struct mtk_iommu_data {
 	struct iommu_group		*m4u_group;
 	struct mtk_smi_iommu		smi_imu;      /* SMI larb iommu info */
 	bool                            enable_4GB;
+
+	struct iommu_device		iommu;
 };
 
 static inline int compare_of(struct device *dev, void *data)
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 0f57ddc4ecc2..2683e9fc0dcf 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -127,7 +127,7 @@ static const struct iommu_ops
 			   "iommu-map-mask", &iommu_spec.np, iommu_spec.args))
 		return NULL;
 
-	ops = of_iommu_get_ops(iommu_spec.np);
+	ops = iommu_ops_from_fwnode(&iommu_spec.np->fwnode);
 	if (!ops || !ops->of_xlate ||
 	    iommu_fwspec_init(&pdev->dev, &iommu_spec.np->fwnode, ops) ||
 	    ops->of_xlate(&pdev->dev, &iommu_spec))
@@ -157,7 +157,7 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
 					   "#iommu-cells", idx,
 					   &iommu_spec)) {
 		np = iommu_spec.np;
-		ops = of_iommu_get_ops(np);
+		ops = iommu_ops_from_fwnode(&np->fwnode);
 
 		if (!ops || !ops->of_xlate ||
 		    iommu_fwspec_init(dev, &np->fwnode, ops) ||
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index ae96731cd2fb..125528f39e92 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -283,3 +283,12 @@ config EZNPS_GIC
 config STM32_EXTI
 	bool
 	select IRQ_DOMAIN
+
+config QCOM_IRQ_COMBINER
+	bool "QCOM IRQ combiner support"
+	depends on ARCH_QCOM && ACPI
+	select IRQ_DOMAIN
+	select IRQ_DOMAIN_HIERARCHY
+	help
+	  Say yes here to add support for the IRQ combiner devices embedded
+	  in Qualcomm Technologies chips.
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 0e55d94065bf..152bc40b6762 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_ATH79)			+= irq-ath79-misc.o
 obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2835.o
 obj-$(CONFIG_ARCH_BCM2835)		+= irq-bcm2836.o
 obj-$(CONFIG_ARCH_EXYNOS)		+= exynos-combiner.o
+obj-$(CONFIG_ARCH_GEMINI)		+= irq-gemini.o
 obj-$(CONFIG_ARCH_HIP04)		+= irq-hip04.o
 obj-$(CONFIG_ARCH_LPC32XX)		+= irq-lpc32xx.o
 obj-$(CONFIG_ARCH_MMP)			+= irq-mmp.o
@@ -75,3 +76,4 @@ obj-$(CONFIG_LS_SCFG_MSI)		+= irq-ls-scfg-msi.o
 obj-$(CONFIG_EZNPS_GIC)			+= irq-eznps.o
 obj-$(CONFIG_ARCH_ASPEED)		+= irq-aspeed-vic.o
 obj-$(CONFIG_STM32_EXTI) 		+= irq-stm32-exti.o
+obj-$(CONFIG_QCOM_IRQ_COMBINER)		+= qcom-irq-combiner.o
diff --git a/drivers/irqchip/irq-gemini.c b/drivers/irqchip/irq-gemini.c
new file mode 100644
index 000000000000..495224c743ee
--- /dev/null
+++ b/drivers/irqchip/irq-gemini.c
@@ -0,0 +1,185 @@
+/*
+ * irqchip for the Cortina Systems Gemini Copyright (C) 2017 Linus
+ * Walleij <linus.walleij@linaro.org>
+ *
+ * Based on arch/arm/mach-gemini/irq.c
+ * Copyright (C) 2001-2006 Storlink, Corp.
+ * Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
+ */
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/versatile-fpga.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/cpu.h>
+
+#include <asm/exception.h>
+#include <asm/mach/irq.h>
+
+#define GEMINI_NUM_IRQS 32
+
+#define GEMINI_IRQ_SOURCE(base_addr)	(base_addr + 0x00)
+#define GEMINI_IRQ_MASK(base_addr)	(base_addr + 0x04)
+#define GEMINI_IRQ_CLEAR(base_addr)	(base_addr + 0x08)
+#define GEMINI_IRQ_MODE(base_addr)	(base_addr + 0x0C)
+#define GEMINI_IRQ_POLARITY(base_addr)	(base_addr + 0x10)
+#define GEMINI_IRQ_STATUS(base_addr)	(base_addr + 0x14)
+#define GEMINI_FIQ_SOURCE(base_addr)	(base_addr + 0x20)
+#define GEMINI_FIQ_MASK(base_addr)	(base_addr + 0x24)
+#define GEMINI_FIQ_CLEAR(base_addr)	(base_addr + 0x28)
+#define GEMINI_FIQ_MODE(base_addr)	(base_addr + 0x2C)
+#define GEMINI_FIQ_POLARITY(base_addr)	(base_addr + 0x30)
+#define GEMINI_FIQ_STATUS(base_addr)	(base_addr + 0x34)
+
+/**
+ * struct gemini_irq_data - irq data container for the Gemini IRQ controller
+ * @base: memory offset in virtual memory
+ * @chip: chip container for this instance
+ * @domain: IRQ domain for this instance
+ */
+struct gemini_irq_data {
+	void __iomem *base;
+	struct irq_chip chip;
+	struct irq_domain *domain;
+};
+
+static void gemini_irq_mask(struct irq_data *d)
+{
+	struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
+	unsigned int mask;
+
+	mask = readl(GEMINI_IRQ_MASK(g->base));
+	mask &= ~BIT(irqd_to_hwirq(d));
+	writel(mask, GEMINI_IRQ_MASK(g->base));
+}
+
+static void gemini_irq_unmask(struct irq_data *d)
+{
+	struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
+	unsigned int mask;
+
+	mask = readl(GEMINI_IRQ_MASK(g->base));
+	mask |= BIT(irqd_to_hwirq(d));
+	writel(mask, GEMINI_IRQ_MASK(g->base));
+}
+
+static void gemini_irq_ack(struct irq_data *d)
+{
+	struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
+
+	writel(BIT(irqd_to_hwirq(d)), GEMINI_IRQ_CLEAR(g->base));
+}
+
+static int gemini_irq_set_type(struct irq_data *d, unsigned int trigger)
+{
+	struct gemini_irq_data *g = irq_data_get_irq_chip_data(d);
+	int offset = irqd_to_hwirq(d);
+	u32 mode, polarity;
+
+	mode = readl(GEMINI_IRQ_MODE(g->base));
+	polarity = readl(GEMINI_IRQ_POLARITY(g->base));
+
+	if (trigger & (IRQ_TYPE_LEVEL_HIGH)) {
+		irq_set_handler_locked(d, handle_level_irq);
+		/* Disable edge detection */
+		mode &= ~BIT(offset);
+		polarity &= ~BIT(offset);
+	} else if (trigger & IRQ_TYPE_EDGE_RISING) {
+		irq_set_handler_locked(d, handle_edge_irq);
+		mode |= BIT(offset);
+		polarity |= BIT(offset);
+	} else if (trigger & IRQ_TYPE_EDGE_FALLING) {
+		irq_set_handler_locked(d, handle_edge_irq);
+		mode |= BIT(offset);
+		polarity &= ~BIT(offset);
+	} else {
+		irq_set_handler_locked(d, handle_bad_irq);
+		pr_warn("GEMINI IRQ: no supported trigger selected for line %d\n",
+			offset);
+	}
+
+	writel(mode, GEMINI_IRQ_MODE(g->base));
+	writel(polarity, GEMINI_IRQ_POLARITY(g->base));
+
+	return 0;
+}
+
+static struct irq_chip gemini_irq_chip = {
+	.name		= "GEMINI",
+	.irq_ack	= gemini_irq_ack,
+	.irq_mask	= gemini_irq_mask,
+	.irq_unmask	= gemini_irq_unmask,
+	.irq_set_type	= gemini_irq_set_type,
+};
+
+/* Local static for the IRQ entry call */
+static struct gemini_irq_data girq;
+
+asmlinkage void __exception_irq_entry gemini_irqchip_handle_irq(struct pt_regs *regs)
+{
+	struct gemini_irq_data *g = &girq;
+	int irq;
+	u32 status;
+
+	while ((status = readl(GEMINI_IRQ_STATUS(g->base)))) {
+		irq = ffs(status) - 1;
+		handle_domain_irq(g->domain, irq, regs);
+	}
+}
+
+static int gemini_irqdomain_map(struct irq_domain *d, unsigned int irq,
+				irq_hw_number_t hwirq)
+{
+	struct gemini_irq_data *g = d->host_data;
+
+	irq_set_chip_data(irq, g);
+	/* All IRQs should set up their type, flags as bad by default */
+	irq_set_chip_and_handler(irq, &gemini_irq_chip, handle_bad_irq);
+	irq_set_probe(irq);
+
+	return 0;
+}
+
+static void gemini_irqdomain_unmap(struct irq_domain *d, unsigned int irq)
+{
+	irq_set_chip_and_handler(irq, NULL, NULL);
+	irq_set_chip_data(irq, NULL);
+}
+
+static const struct irq_domain_ops gemini_irqdomain_ops = {
+	.map = gemini_irqdomain_map,
+	.unmap = gemini_irqdomain_unmap,
+	.xlate = irq_domain_xlate_onetwocell,
+};
+
+int __init gemini_of_init_irq(struct device_node *node,
+			      struct device_node *parent)
+{
+	struct gemini_irq_data *g = &girq;
+
+	/*
+	 * Disable the idle handler by default since it is buggy
+	 * For more info see arch/arm/mach-gemini/idle.c
+	 */
+	cpu_idle_poll_ctrl(true);
+
+	g->base = of_iomap(node, 0);
+	WARN(!g->base, "unable to map gemini irq registers\n");
+
+	/* Disable all interrupts */
+	writel(0, GEMINI_IRQ_MASK(g->base));
+	writel(0, GEMINI_FIQ_MASK(g->base));
+
+	g->domain = irq_domain_add_simple(node, GEMINI_NUM_IRQS, 0,
+					  &gemini_irqdomain_ops, g);
+	set_handle_irq(gemini_irqchip_handle_irq);
+
+	return 0;
+}
+IRQCHIP_DECLARE(gemini, "cortina,gemini-interrupt-controller",
+		gemini_of_init_irq);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 69b040f47d56..23201004fd7a 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -161,7 +161,7 @@ struct its_cmd_desc {
 			struct its_device *dev;
 			u32 phys_id;
 			u32 event_id;
-		} its_mapvi_cmd;
+		} its_mapti_cmd;
 
 		struct {
 			struct its_device *dev;
@@ -193,58 +193,56 @@ struct its_cmd_block {
 typedef struct its_collection *(*its_cmd_builder_t)(struct its_cmd_block *,
 						    struct its_cmd_desc *);
 
+static void its_mask_encode(u64 *raw_cmd, u64 val, int h, int l)
+{
+	u64 mask = GENMASK_ULL(h, l);
+	*raw_cmd &= ~mask;
+	*raw_cmd |= (val << l) & mask;
+}
+
 static void its_encode_cmd(struct its_cmd_block *cmd, u8 cmd_nr)
 {
-	cmd->raw_cmd[0] &= ~0xffULL;
-	cmd->raw_cmd[0] |= cmd_nr;
+	its_mask_encode(&cmd->raw_cmd[0], cmd_nr, 7, 0);
 }
 
 static void its_encode_devid(struct its_cmd_block *cmd, u32 devid)
 {
-	cmd->raw_cmd[0] &= BIT_ULL(32) - 1;
-	cmd->raw_cmd[0] |= ((u64)devid) << 32;
+	its_mask_encode(&cmd->raw_cmd[0], devid, 63, 32);
 }
 
 static void its_encode_event_id(struct its_cmd_block *cmd, u32 id)
 {
-	cmd->raw_cmd[1] &= ~0xffffffffULL;
-	cmd->raw_cmd[1] |= id;
+	its_mask_encode(&cmd->raw_cmd[1], id, 31, 0);
 }
 
 static void its_encode_phys_id(struct its_cmd_block *cmd, u32 phys_id)
 {
-	cmd->raw_cmd[1] &= 0xffffffffULL;
-	cmd->raw_cmd[1] |= ((u64)phys_id) << 32;
+	its_mask_encode(&cmd->raw_cmd[1], phys_id, 63, 32);
 }
 
 static void its_encode_size(struct its_cmd_block *cmd, u8 size)
 {
-	cmd->raw_cmd[1] &= ~0x1fULL;
-	cmd->raw_cmd[1] |= size & 0x1f;
+	its_mask_encode(&cmd->raw_cmd[1], size, 4, 0);
 }
 
 static void its_encode_itt(struct its_cmd_block *cmd, u64 itt_addr)
 {
-	cmd->raw_cmd[2] &= ~0xffffffffffffULL;
-	cmd->raw_cmd[2] |= itt_addr & 0xffffffffff00ULL;
+	its_mask_encode(&cmd->raw_cmd[2], itt_addr >> 8, 50, 8);
 }
 
 static void its_encode_valid(struct its_cmd_block *cmd, int valid)
 {
-	cmd->raw_cmd[2] &= ~(1ULL << 63);
-	cmd->raw_cmd[2] |= ((u64)!!valid) << 63;
+	its_mask_encode(&cmd->raw_cmd[2], !!valid, 63, 63);
 }
 
 static void its_encode_target(struct its_cmd_block *cmd, u64 target_addr)
 {
-	cmd->raw_cmd[2] &= ~(0xffffffffULL << 16);
-	cmd->raw_cmd[2] |= (target_addr & (0xffffffffULL << 16));
+	its_mask_encode(&cmd->raw_cmd[2], target_addr >> 16, 50, 16);
 }
 
 static void its_encode_collection(struct its_cmd_block *cmd, u16 col)
 {
-	cmd->raw_cmd[2] &= ~0xffffULL;
-	cmd->raw_cmd[2] |= col;
+	its_mask_encode(&cmd->raw_cmd[2], col, 15, 0);
 }
 
 static inline void its_fixup_cmd(struct its_cmd_block *cmd)
@@ -289,18 +287,18 @@ static struct its_collection *its_build_mapc_cmd(struct its_cmd_block *cmd,
 	return desc->its_mapc_cmd.col;
 }
 
-static struct its_collection *its_build_mapvi_cmd(struct its_cmd_block *cmd,
+static struct its_collection *its_build_mapti_cmd(struct its_cmd_block *cmd,
 						  struct its_cmd_desc *desc)
 {
 	struct its_collection *col;
 
-	col = dev_event_to_col(desc->its_mapvi_cmd.dev,
-			       desc->its_mapvi_cmd.event_id);
+	col = dev_event_to_col(desc->its_mapti_cmd.dev,
+			       desc->its_mapti_cmd.event_id);
 
-	its_encode_cmd(cmd, GITS_CMD_MAPVI);
-	its_encode_devid(cmd, desc->its_mapvi_cmd.dev->device_id);
-	its_encode_event_id(cmd, desc->its_mapvi_cmd.event_id);
-	its_encode_phys_id(cmd, desc->its_mapvi_cmd.phys_id);
+	its_encode_cmd(cmd, GITS_CMD_MAPTI);
+	its_encode_devid(cmd, desc->its_mapti_cmd.dev->device_id);
+	its_encode_event_id(cmd, desc->its_mapti_cmd.event_id);
+	its_encode_phys_id(cmd, desc->its_mapti_cmd.phys_id);
 	its_encode_collection(cmd, col->col_id);
 
 	its_fixup_cmd(cmd);
@@ -413,6 +411,12 @@ static struct its_cmd_block *its_allocate_entry(struct its_node *its)
 	if (its->cmd_write == (its->cmd_base + ITS_CMD_QUEUE_NR_ENTRIES))
 		its->cmd_write = its->cmd_base;
 
+	/* Clear command  */
+	cmd->raw_cmd[0] = 0;
+	cmd->raw_cmd[1] = 0;
+	cmd->raw_cmd[2] = 0;
+	cmd->raw_cmd[3] = 0;
+
 	return cmd;
 }
 
@@ -531,15 +535,15 @@ static void its_send_mapc(struct its_node *its, struct its_collection *col,
 	its_send_single_command(its, its_build_mapc_cmd, &desc);
 }
 
-static void its_send_mapvi(struct its_device *dev, u32 irq_id, u32 id)
+static void its_send_mapti(struct its_device *dev, u32 irq_id, u32 id)
 {
 	struct its_cmd_desc desc;
 
-	desc.its_mapvi_cmd.dev = dev;
-	desc.its_mapvi_cmd.phys_id = irq_id;
-	desc.its_mapvi_cmd.event_id = id;
+	desc.its_mapti_cmd.dev = dev;
+	desc.its_mapti_cmd.phys_id = irq_id;
+	desc.its_mapti_cmd.event_id = id;
 
-	its_send_single_command(dev->its, its_build_mapvi_cmd, &desc);
+	its_send_single_command(dev->its, its_build_mapti_cmd, &desc);
 }
 
 static void its_send_movi(struct its_device *dev,
@@ -824,7 +828,7 @@ static int __init its_alloc_lpi_tables(void)
 static const char *its_base_type_string[] = {
 	[GITS_BASER_TYPE_DEVICE]	= "Devices",
 	[GITS_BASER_TYPE_VCPU]		= "Virtual CPUs",
-	[GITS_BASER_TYPE_CPU]		= "Physical CPUs",
+	[GITS_BASER_TYPE_RESERVED3]	= "Reserved (3)",
 	[GITS_BASER_TYPE_COLLECTION]	= "Interrupt Collections",
 	[GITS_BASER_TYPE_RESERVED5] 	= "Reserved (5)",
 	[GITS_BASER_TYPE_RESERVED6] 	= "Reserved (6)",
@@ -960,7 +964,7 @@ static bool its_parse_baser_device(struct its_node *its, struct its_baser *baser
 				   u32 psz, u32 *order)
 {
 	u64 esz = GITS_BASER_ENTRY_SIZE(its_read_baser(its, baser));
-	u64 val = GITS_BASER_InnerShareable | GITS_BASER_WaWb;
+	u64 val = GITS_BASER_InnerShareable | GITS_BASER_RaWaWb;
 	u32 ids = its->device_ids;
 	u32 new_order = *order;
 	bool indirect = false;
@@ -1025,7 +1029,7 @@ static int its_alloc_tables(struct its_node *its)
 	u64 typer = gic_read_typer(its->base + GITS_TYPER);
 	u32 ids = GITS_TYPER_DEVBITS(typer);
 	u64 shr = GITS_BASER_InnerShareable;
-	u64 cache = GITS_BASER_WaWb;
+	u64 cache = GITS_BASER_RaWaWb;
 	u32 psz = SZ_64K;
 	int err, i;
 
@@ -1122,7 +1126,7 @@ static void its_cpu_init_lpis(void)
 	/* set PROPBASE */
 	val = (page_to_phys(gic_rdists->prop_page) |
 	       GICR_PROPBASER_InnerShareable |
-	       GICR_PROPBASER_WaWb |
+	       GICR_PROPBASER_RaWaWb |
 	       ((LPI_NRBITS - 1) & GICR_PROPBASER_IDBITS_MASK));
 
 	gicr_write_propbaser(val, rbase + GICR_PROPBASER);
@@ -1147,7 +1151,7 @@ static void its_cpu_init_lpis(void)
 	/* set PENDBASE */
 	val = (page_to_phys(pend_page) |
 	       GICR_PENDBASER_InnerShareable |
-	       GICR_PENDBASER_WaWb);
+	       GICR_PENDBASER_RaWaWb);
 
 	gicr_write_pendbaser(val, rbase + GICR_PENDBASER);
 	tmp = gicr_read_pendbaser(rbase + GICR_PENDBASER);
@@ -1498,7 +1502,7 @@ static void its_irq_domain_activate(struct irq_domain *domain,
 	its_dev->event_map.col_map[event] = cpumask_first(cpu_mask);
 
 	/* Map the GIC IRQ and event to the device */
-	its_send_mapvi(its_dev, d->hwirq, event);
+	its_send_mapti(its_dev, d->hwirq, event);
 }
 
 static void its_irq_domain_deactivate(struct irq_domain *domain,
@@ -1642,6 +1646,7 @@ static int its_init_domain(struct fwnode_handle *handle, struct its_node *its)
 
 	inner_domain->parent = its_parent;
 	inner_domain->bus_token = DOMAIN_BUS_NEXUS;
+	inner_domain->flags |= IRQ_DOMAIN_FLAG_MSI_REMAP;
 	info->ops = &its_msi_domain_ops;
 	info->data = its;
 	inner_domain->host_data = info;
@@ -1693,7 +1698,8 @@ static int __init its_probe_one(struct resource *res,
 	its->ite_size = ((gic_read_typer(its_base + GITS_TYPER) >> 4) & 0xf) + 1;
 	its->numa_node = numa_node;
 
-	its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL);
+	its->cmd_base = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						get_order(ITS_CMD_QUEUE_SZ));
 	if (!its->cmd_base) {
 		err = -ENOMEM;
 		goto out_free_its;
@@ -1711,7 +1717,7 @@ static int __init its_probe_one(struct resource *res,
 		goto out_free_tables;
 
 	baser = (virt_to_phys(its->cmd_base)	|
-		 GITS_CBASER_WaWb		|
+		 GITS_CBASER_RaWaWb		|
 		 GITS_CBASER_InnerShareable	|
 		 (ITS_CMD_QUEUE_SZ / SZ_4K - 1)	|
 		 GITS_CBASER_VALID);
@@ -1751,7 +1757,7 @@ static int __init its_probe_one(struct resource *res,
 out_free_tables:
 	its_free_tables(its);
 out_free_cmd:
-	kfree(its->cmd_base);
+	free_pages((unsigned long)its->cmd_base, get_order(ITS_CMD_QUEUE_SZ));
 out_free_its:
 	kfree(its);
 out_unmap:
diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c
index 54a5e870a8f5..efbcf8435185 100644
--- a/drivers/irqchip/irq-keystone.c
+++ b/drivers/irqchip/irq-keystone.c
@@ -19,9 +19,9 @@
 #include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include <linux/irqchip/chained_irq.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
 #include <linux/mfd/syscon.h>
@@ -39,6 +39,7 @@ struct keystone_irq_device {
 	struct irq_domain	*irqd;
 	struct regmap		*devctrl_regs;
 	u32			devctrl_offset;
+	raw_spinlock_t		wa_lock;
 };
 
 static inline u32 keystone_irq_readl(struct keystone_irq_device *kirq)
@@ -83,17 +84,15 @@ static void keystone_irq_ack(struct irq_data *d)
 	/* nothing to do here */
 }
 
-static void keystone_irq_handler(struct irq_desc *desc)
+static irqreturn_t keystone_irq_handler(int irq, void *keystone_irq)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
-	struct keystone_irq_device *kirq = irq_desc_get_handler_data(desc);
+	struct keystone_irq_device *kirq = keystone_irq;
+	unsigned long wa_lock_flags;
 	unsigned long pending;
 	int src, virq;
 
 	dev_dbg(kirq->dev, "start irq %d\n", irq);
 
-	chained_irq_enter(irq_desc_get_chip(desc), desc);
-
 	pending = keystone_irq_readl(kirq);
 	keystone_irq_writel(kirq, pending);
 
@@ -111,13 +110,15 @@ static void keystone_irq_handler(struct irq_desc *desc)
 			if (!virq)
 				dev_warn(kirq->dev, "spurious irq detected hwirq %d, virq %d\n",
 					 src, virq);
+			raw_spin_lock_irqsave(&kirq->wa_lock, wa_lock_flags);
 			generic_handle_irq(virq);
+			raw_spin_unlock_irqrestore(&kirq->wa_lock,
+						   wa_lock_flags);
 		}
 	}
 
-	chained_irq_exit(irq_desc_get_chip(desc), desc);
-
 	dev_dbg(kirq->dev, "end irq %d\n", irq);
+	return IRQ_HANDLED;
 }
 
 static int keystone_irq_map(struct irq_domain *h, unsigned int virq,
@@ -182,9 +183,16 @@ static int keystone_irq_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+	raw_spin_lock_init(&kirq->wa_lock);
+
 	platform_set_drvdata(pdev, kirq);
 
-	irq_set_chained_handler_and_data(kirq->irq, keystone_irq_handler, kirq);
+	ret = request_irq(kirq->irq, keystone_irq_handler,
+			  0, dev_name(dev), kirq);
+	if (ret) {
+		irq_domain_remove(kirq->irqd);
+		return ret;
+	}
 
 	/* clear all source bits */
 	keystone_irq_writel(kirq, ~0x0);
@@ -199,6 +207,8 @@ static int keystone_irq_remove(struct platform_device *pdev)
 	struct keystone_irq_device *kirq = platform_get_drvdata(pdev);
 	int hwirq;
 
+	free_irq(kirq->irq, kirq);
+
 	for (hwirq = 0; hwirq < KEYSTONE_N_IRQ; hwirq++)
 		irq_dispose_mapping(irq_find_mapping(kirq->irqd, hwirq));
 
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index c01c09e9916d..11d12bccc4e7 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -968,6 +968,34 @@ static struct irq_domain_ops gic_ipi_domain_ops = {
 	.match = gic_ipi_domain_match,
 };
 
+static void __init gic_map_single_int(struct device_node *node,
+				      unsigned int irq)
+{
+	unsigned int linux_irq;
+	struct irq_fwspec local_int_fwspec = {
+		.fwnode         = &node->fwnode,
+		.param_count    = 3,
+		.param          = {
+			[0]     = GIC_LOCAL,
+			[1]     = irq,
+			[2]     = IRQ_TYPE_NONE,
+		},
+	};
+
+	if (!gic_local_irq_is_routable(irq))
+		return;
+
+	linux_irq = irq_create_fwspec_mapping(&local_int_fwspec);
+	WARN_ON(!linux_irq);
+}
+
+static void __init gic_map_interrupts(struct device_node *node)
+{
+	gic_map_single_int(node, GIC_LOCAL_INT_TIMER);
+	gic_map_single_int(node, GIC_LOCAL_INT_PERFCTR);
+	gic_map_single_int(node, GIC_LOCAL_INT_FDC);
+}
+
 static void __init __gic_init(unsigned long gic_base_addr,
 			      unsigned long gic_addrspace_size,
 			      unsigned int cpu_vec, unsigned int irqbase,
@@ -1067,6 +1095,7 @@ static void __init __gic_init(unsigned long gic_base_addr,
 	}
 
 	gic_basic_init();
+	gic_map_interrupts(node);
 }
 
 void __init gic_init(unsigned long gic_base_addr,
diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c
index 17304705f2cf..05fa9f7af53c 100644
--- a/drivers/irqchip/irq-mxs.c
+++ b/drivers/irqchip/irq-mxs.c
@@ -131,12 +131,16 @@ static struct irq_chip mxs_icoll_chip = {
 	.irq_ack = icoll_ack_irq,
 	.irq_mask = icoll_mask_irq,
 	.irq_unmask = icoll_unmask_irq,
+	.flags = IRQCHIP_MASK_ON_SUSPEND |
+		 IRQCHIP_SKIP_SET_WAKE,
 };
 
 static struct irq_chip asm9260_icoll_chip = {
 	.irq_ack = icoll_ack_irq,
 	.irq_mask = asm9260_mask_irq,
 	.irq_unmask = asm9260_unmask_irq,
+	.flags = IRQCHIP_MASK_ON_SUSPEND |
+		 IRQCHIP_SKIP_SET_WAKE,
 };
 
 asmlinkage void __exception_irq_entry icoll_handle_irq(struct pt_regs *regs)
diff --git a/drivers/irqchip/qcom-irq-combiner.c b/drivers/irqchip/qcom-irq-combiner.c
new file mode 100644
index 000000000000..226558698344
--- /dev/null
+++ b/drivers/irqchip/qcom-irq-combiner.c
@@ -0,0 +1,296 @@
+/* Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * Driver for interrupt combiners in the Top-level Control and Status
+ * Registers (TCSR) hardware block in Qualcomm Technologies chips.
+ * An interrupt combiner in this block combines a set of interrupts by
+ * OR'ing the individual interrupt signals into a summary interrupt
+ * signal routed to a parent interrupt controller, and provides read-
+ * only, 32-bit registers to query the status of individual interrupts.
+ * The status bit for IRQ n is bit (n % 32) within register (n / 32)
+ * of the given combiner. Thus, each combiner can be described as a set
+ * of register offsets and the number of IRQs managed.
+ */
+
+#define pr_fmt(fmt) "QCOM80B1:" fmt
+
+#include <linux/acpi.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/platform_device.h>
+
+#define REG_SIZE 32
+
+struct combiner_reg {
+	void __iomem *addr;
+	unsigned long enabled;
+};
+
+struct combiner {
+	struct irq_domain   *domain;
+	int                 parent_irq;
+	u32                 nirqs;
+	u32                 nregs;
+	struct combiner_reg regs[0];
+};
+
+static inline int irq_nr(u32 reg, u32 bit)
+{
+	return reg * REG_SIZE + bit;
+}
+
+/*
+ * Handler for the cascaded IRQ.
+ */
+static void combiner_handle_irq(struct irq_desc *desc)
+{
+	struct combiner *combiner = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	u32 reg;
+
+	chained_irq_enter(chip, desc);
+
+	for (reg = 0; reg < combiner->nregs; reg++) {
+		int virq;
+		int hwirq;
+		u32 bit;
+		u32 status;
+
+		bit = readl_relaxed(combiner->regs[reg].addr);
+		status = bit & combiner->regs[reg].enabled;
+		if (!status)
+			pr_warn_ratelimited("Unexpected IRQ on CPU%d: (%08x %08lx %p)\n",
+					    smp_processor_id(), bit,
+					    combiner->regs[reg].enabled,
+					    combiner->regs[reg].addr);
+
+		while (status) {
+			bit = __ffs(status);
+			status &= ~(1 << bit);
+			hwirq = irq_nr(reg, bit);
+			virq = irq_find_mapping(combiner->domain, hwirq);
+			if (virq > 0)
+				generic_handle_irq(virq);
+
+		}
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static void combiner_irq_chip_mask_irq(struct irq_data *data)
+{
+	struct combiner *combiner = irq_data_get_irq_chip_data(data);
+	struct combiner_reg *reg = combiner->regs + data->hwirq / REG_SIZE;
+
+	clear_bit(data->hwirq % REG_SIZE, &reg->enabled);
+}
+
+static void combiner_irq_chip_unmask_irq(struct irq_data *data)
+{
+	struct combiner *combiner = irq_data_get_irq_chip_data(data);
+	struct combiner_reg *reg = combiner->regs + data->hwirq / REG_SIZE;
+
+	set_bit(data->hwirq % REG_SIZE, &reg->enabled);
+}
+
+static struct irq_chip irq_chip = {
+	.irq_mask = combiner_irq_chip_mask_irq,
+	.irq_unmask = combiner_irq_chip_unmask_irq,
+	.name = "qcom-irq-combiner"
+};
+
+static int combiner_irq_map(struct irq_domain *domain, unsigned int irq,
+				   irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &irq_chip, handle_level_irq);
+	irq_set_chip_data(irq, domain->host_data);
+	irq_set_noprobe(irq);
+	return 0;
+}
+
+static void combiner_irq_unmap(struct irq_domain *domain, unsigned int irq)
+{
+	irq_domain_reset_irq_data(irq_get_irq_data(irq));
+}
+
+static int combiner_irq_translate(struct irq_domain *d, struct irq_fwspec *fws,
+				  unsigned long *hwirq, unsigned int *type)
+{
+	struct combiner *combiner = d->host_data;
+
+	if (is_acpi_node(fws->fwnode)) {
+		if (WARN_ON((fws->param_count != 2) ||
+			    (fws->param[0] >= combiner->nirqs) ||
+			    (fws->param[1] & IORESOURCE_IRQ_LOWEDGE) ||
+			    (fws->param[1] & IORESOURCE_IRQ_HIGHEDGE)))
+			return -EINVAL;
+
+		*hwirq = fws->param[0];
+		*type = fws->param[1];
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static const struct irq_domain_ops domain_ops = {
+	.map = combiner_irq_map,
+	.unmap = combiner_irq_unmap,
+	.translate = combiner_irq_translate
+};
+
+static acpi_status count_registers_cb(struct acpi_resource *ares, void *context)
+{
+	int *count = context;
+
+	if (ares->type == ACPI_RESOURCE_TYPE_GENERIC_REGISTER)
+		++(*count);
+	return AE_OK;
+}
+
+static int count_registers(struct platform_device *pdev)
+{
+	acpi_handle ahandle = ACPI_HANDLE(&pdev->dev);
+	acpi_status status;
+	int count = 0;
+
+	if (!acpi_has_method(ahandle, METHOD_NAME__CRS))
+		return -EINVAL;
+
+	status = acpi_walk_resources(ahandle, METHOD_NAME__CRS,
+				     count_registers_cb, &count);
+	if (ACPI_FAILURE(status))
+		return -EINVAL;
+	return count;
+}
+
+struct get_registers_context {
+	struct device *dev;
+	struct combiner *combiner;
+	int err;
+};
+
+static acpi_status get_registers_cb(struct acpi_resource *ares, void *context)
+{
+	struct get_registers_context *ctx = context;
+	struct acpi_resource_generic_register *reg;
+	phys_addr_t paddr;
+	void __iomem *vaddr;
+
+	if (ares->type != ACPI_RESOURCE_TYPE_GENERIC_REGISTER)
+		return AE_OK;
+
+	reg = &ares->data.generic_reg;
+	paddr = reg->address;
+	if ((reg->space_id != ACPI_SPACE_MEM) ||
+	    (reg->bit_offset != 0) ||
+	    (reg->bit_width > REG_SIZE)) {
+		dev_err(ctx->dev, "Bad register resource @%pa\n", &paddr);
+		ctx->err = -EINVAL;
+		return AE_ERROR;
+	}
+
+	vaddr = devm_ioremap(ctx->dev, reg->address, REG_SIZE);
+	if (!vaddr) {
+		dev_err(ctx->dev, "Can't map register @%pa\n", &paddr);
+		ctx->err = -ENOMEM;
+		return AE_ERROR;
+	}
+
+	ctx->combiner->regs[ctx->combiner->nregs].addr = vaddr;
+	ctx->combiner->nirqs += reg->bit_width;
+	ctx->combiner->nregs++;
+	return AE_OK;
+}
+
+static int get_registers(struct platform_device *pdev, struct combiner *comb)
+{
+	acpi_handle ahandle = ACPI_HANDLE(&pdev->dev);
+	acpi_status status;
+	struct get_registers_context ctx;
+
+	if (!acpi_has_method(ahandle, METHOD_NAME__CRS))
+		return -EINVAL;
+
+	ctx.dev = &pdev->dev;
+	ctx.combiner = comb;
+	ctx.err = 0;
+
+	status = acpi_walk_resources(ahandle, METHOD_NAME__CRS,
+				     get_registers_cb, &ctx);
+	if (ACPI_FAILURE(status))
+		return ctx.err;
+	return 0;
+}
+
+static int __init combiner_probe(struct platform_device *pdev)
+{
+	struct combiner *combiner;
+	size_t alloc_sz;
+	u32 nregs;
+	int err;
+
+	nregs = count_registers(pdev);
+	if (nregs <= 0) {
+		dev_err(&pdev->dev, "Error reading register resources\n");
+		return -EINVAL;
+	}
+
+	alloc_sz = sizeof(*combiner) + sizeof(struct combiner_reg) * nregs;
+	combiner = devm_kzalloc(&pdev->dev, alloc_sz, GFP_KERNEL);
+	if (!combiner)
+		return -ENOMEM;
+
+	err = get_registers(pdev, combiner);
+	if (err < 0)
+		return err;
+
+	combiner->parent_irq = platform_get_irq(pdev, 0);
+	if (combiner->parent_irq <= 0) {
+		dev_err(&pdev->dev, "Error getting IRQ resource\n");
+		return -EPROBE_DEFER;
+	}
+
+	combiner->domain = irq_domain_create_linear(pdev->dev.fwnode, combiner->nirqs,
+						    &domain_ops, combiner);
+	if (!combiner->domain)
+		/* Errors printed by irq_domain_create_linear */
+		return -ENODEV;
+
+	irq_set_chained_handler_and_data(combiner->parent_irq,
+					 combiner_handle_irq, combiner);
+
+	dev_info(&pdev->dev, "Initialized with [p=%d,n=%d,r=%p]\n",
+		 combiner->parent_irq, combiner->nirqs, combiner->regs[0].addr);
+	return 0;
+}
+
+static const struct acpi_device_id qcom_irq_combiner_ids[] = {
+	{ "QCOM80B1", },
+	{ }
+};
+
+static struct platform_driver qcom_irq_combiner_probe = {
+	.driver = {
+		.name = "qcom-irq-combiner",
+		.acpi_match_table = ACPI_PTR(qcom_irq_combiner_ids),
+	},
+	.probe = combiner_probe,
+};
+
+static int __init register_qcom_irq_combiner(void)
+{
+	return platform_driver_register(&qcom_irq_combiner_probe);
+}
+device_initcall(register_qcom_irq_combiner);
diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c
index 1a1d99704fe6..296f1411fe84 100644
--- a/drivers/isdn/hardware/eicon/message.c
+++ b/drivers/isdn/hardware/eicon/message.c
@@ -11297,7 +11297,8 @@ static void mixer_notify_update(PLCI *plci, byte others)
 				((CAPI_MSG *) msg)->header.ncci = 0;
 				((CAPI_MSG *) msg)->info.facility_req.Selector = SELECTOR_LINE_INTERCONNECT;
 				((CAPI_MSG *) msg)->info.facility_req.structs[0] = 3;
-				PUT_WORD(&(((CAPI_MSG *) msg)->info.facility_req.structs[1]), LI_REQ_SILENT_UPDATE);
+				((CAPI_MSG *) msg)->info.facility_req.structs[1] = LI_REQ_SILENT_UPDATE & 0xff;
+				((CAPI_MSG *) msg)->info.facility_req.structs[2] = LI_REQ_SILENT_UPDATE >> 8;
 				((CAPI_MSG *) msg)->info.facility_req.structs[3] = 0;
 				w = api_put(notify_plci->appl, (CAPI_MSG *) msg);
 				if (w != _QUEUE_FULL)
diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c
index 9cb4b621fbc3..b324474c0c12 100644
--- a/drivers/isdn/mISDN/stack.c
+++ b/drivers/isdn/mISDN/stack.c
@@ -203,7 +203,7 @@ mISDNStackd(void *data)
 {
 	struct mISDNstack *st = data;
 #ifdef MISDN_MSG_STATS
-	cputime_t utime, stime;
+	u64 utime, stime;
 #endif
 	int err = 0;
 
@@ -308,7 +308,7 @@ mISDNStackd(void *data)
 	       st->stopped_cnt);
 	task_cputime(st->thread, &utime, &stime);
 	printk(KERN_DEBUG
-	       "mISDNStackd daemon for %s utime(%ld) stime(%ld)\n",
+	       "mISDNStackd daemon for %s utime(%llu) stime(%llu)\n",
 	       dev_name(&st->dev->dev), utime, stime);
 	printk(KERN_DEBUG
 	       "mISDNStackd daemon for %s nvcsw(%ld) nivcsw(%ld)\n",
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index c621cbbb5768..275f467956ee 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -29,6 +29,15 @@ config LEDS_CLASS_FLASH
 	  for the flash related features of a LED device. It can be built
 	  as a module.
 
+config LEDS_BRIGHTNESS_HW_CHANGED
+	bool "LED Class brightness_hw_changed attribute support"
+	depends on LEDS_CLASS
+	help
+	  This option enables support for the brightness_hw_changed attribute
+	  for led sysfs class devices under /sys/class/leds.
+
+	  See Documentation/ABI/testing/sysfs-class-led for details.
+
 comment "LED drivers"
 
 config LEDS_88PM860X
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 326ee6e925a2..f2b0a80a62b4 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -103,6 +103,68 @@ static const struct attribute_group *led_groups[] = {
 	NULL,
 };
 
+#ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED
+static ssize_t brightness_hw_changed_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+
+	if (led_cdev->brightness_hw_changed == -1)
+		return -ENODATA;
+
+	return sprintf(buf, "%u\n", led_cdev->brightness_hw_changed);
+}
+
+static DEVICE_ATTR_RO(brightness_hw_changed);
+
+static int led_add_brightness_hw_changed(struct led_classdev *led_cdev)
+{
+	struct device *dev = led_cdev->dev;
+	int ret;
+
+	ret = device_create_file(dev, &dev_attr_brightness_hw_changed);
+	if (ret) {
+		dev_err(dev, "Error creating brightness_hw_changed\n");
+		return ret;
+	}
+
+	led_cdev->brightness_hw_changed_kn =
+		sysfs_get_dirent(dev->kobj.sd, "brightness_hw_changed");
+	if (!led_cdev->brightness_hw_changed_kn) {
+		dev_err(dev, "Error getting brightness_hw_changed kn\n");
+		device_remove_file(dev, &dev_attr_brightness_hw_changed);
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static void led_remove_brightness_hw_changed(struct led_classdev *led_cdev)
+{
+	sysfs_put(led_cdev->brightness_hw_changed_kn);
+	device_remove_file(led_cdev->dev, &dev_attr_brightness_hw_changed);
+}
+
+void led_classdev_notify_brightness_hw_changed(struct led_classdev *led_cdev,
+					       enum led_brightness brightness)
+{
+	if (WARN_ON(!led_cdev->brightness_hw_changed_kn))
+		return;
+
+	led_cdev->brightness_hw_changed = brightness;
+	sysfs_notify_dirent(led_cdev->brightness_hw_changed_kn);
+}
+EXPORT_SYMBOL_GPL(led_classdev_notify_brightness_hw_changed);
+#else
+static int led_add_brightness_hw_changed(struct led_classdev *led_cdev)
+{
+	return 0;
+}
+static void led_remove_brightness_hw_changed(struct led_classdev *led_cdev)
+{
+}
+#endif
+
 /**
  * led_classdev_suspend - suspend an led_classdev.
  * @led_cdev: the led_classdev to suspend.
@@ -204,10 +266,21 @@ int led_classdev_register(struct device *parent, struct led_classdev *led_cdev)
 		dev_warn(parent, "Led %s renamed to %s due to name collision",
 				led_cdev->name, dev_name(led_cdev->dev));
 
+	if (led_cdev->flags & LED_BRIGHT_HW_CHANGED) {
+		ret = led_add_brightness_hw_changed(led_cdev);
+		if (ret) {
+			device_unregister(led_cdev->dev);
+			return ret;
+		}
+	}
+
 	led_cdev->work_flags = 0;
 #ifdef CONFIG_LEDS_TRIGGERS
 	init_rwsem(&led_cdev->trigger_lock);
 #endif
+#ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED
+	led_cdev->brightness_hw_changed = -1;
+#endif
 	mutex_init(&led_cdev->led_access);
 	/* add to the list of leds */
 	down_write(&leds_list_lock);
@@ -256,6 +329,9 @@ void led_classdev_unregister(struct led_classdev *led_cdev)
 
 	flush_work(&led_cdev->set_brightness_work);
 
+	if (led_cdev->flags & LED_BRIGHT_HW_CHANGED)
+		led_remove_brightness_hw_changed(led_cdev);
+
 	device_unregister(led_cdev->dev);
 
 	down_write(&leds_list_lock);
diff --git a/drivers/leds/leds-ktd2692.c b/drivers/leds/leds-ktd2692.c
index bf23ba191ad0..45296aaca9da 100644
--- a/drivers/leds/leds-ktd2692.c
+++ b/drivers/leds/leds-ktd2692.c
@@ -270,15 +270,15 @@ static int ktd2692_parse_dt(struct ktd2692_context *led, struct device *dev,
 		return -ENXIO;
 
 	led->ctrl_gpio = devm_gpiod_get(dev, "ctrl", GPIOD_ASIS);
-	if (IS_ERR(led->ctrl_gpio)) {
-		ret = PTR_ERR(led->ctrl_gpio);
+	ret = PTR_ERR_OR_ZERO(led->ctrl_gpio);
+	if (ret) {
 		dev_err(dev, "cannot get ctrl-gpios %d\n", ret);
 		return ret;
 	}
 
 	led->aux_gpio = devm_gpiod_get(dev, "aux", GPIOD_ASIS);
-	if (IS_ERR(led->aux_gpio)) {
-		ret = PTR_ERR(led->aux_gpio);
+	ret = PTR_ERR_OR_ZERO(led->aux_gpio);
+	if (ret) {
 		dev_err(dev, "cannot get aux-gpios %d\n", ret);
 		return ret;
 	}
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index c9f386213e9e..e6f2f8b9f09a 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -43,6 +43,9 @@ static void led_heartbeat_function(unsigned long data)
 		return;
 	}
 
+	if (test_and_clear_bit(LED_BLINK_BRIGHTNESS_CHANGE, &led_cdev->work_flags))
+		led_cdev->blink_brightness = led_cdev->new_blink_brightness;
+
 	/* acts like an actual heart beat -- ie thump-thump-pause... */
 	switch (heartbeat_data->phase) {
 	case 0:
@@ -59,26 +62,26 @@ static void led_heartbeat_function(unsigned long data)
 		delay = msecs_to_jiffies(70);
 		heartbeat_data->phase++;
 		if (!heartbeat_data->invert)
-			brightness = led_cdev->max_brightness;
+			brightness = led_cdev->blink_brightness;
 		break;
 	case 1:
 		delay = heartbeat_data->period / 4 - msecs_to_jiffies(70);
 		heartbeat_data->phase++;
 		if (heartbeat_data->invert)
-			brightness = led_cdev->max_brightness;
+			brightness = led_cdev->blink_brightness;
 		break;
 	case 2:
 		delay = msecs_to_jiffies(70);
 		heartbeat_data->phase++;
 		if (!heartbeat_data->invert)
-			brightness = led_cdev->max_brightness;
+			brightness = led_cdev->blink_brightness;
 		break;
 	default:
 		delay = heartbeat_data->period - heartbeat_data->period / 4 -
 			msecs_to_jiffies(70);
 		heartbeat_data->phase = 0;
 		if (heartbeat_data->invert)
-			brightness = led_cdev->max_brightness;
+			brightness = led_cdev->blink_brightness;
 		break;
 	}
 
@@ -133,7 +136,10 @@ static void heartbeat_trig_activate(struct led_classdev *led_cdev)
 	setup_timer(&heartbeat_data->timer,
 		    led_heartbeat_function, (unsigned long) led_cdev);
 	heartbeat_data->phase = 0;
+	if (!led_cdev->blink_brightness)
+		led_cdev->blink_brightness = led_cdev->max_brightness;
 	led_heartbeat_function(heartbeat_data->timer.data);
+	set_bit(LED_BLINK_SW, &led_cdev->work_flags);
 	led_cdev->activated = true;
 }
 
@@ -145,6 +151,7 @@ static void heartbeat_trig_deactivate(struct led_classdev *led_cdev)
 		del_timer_sync(&heartbeat_data->timer);
 		device_remove_file(led_cdev->dev, &dev_attr_invert);
 		kfree(heartbeat_data);
+		clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
 		led_cdev->activated = false;
 	}
 }
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 2f5d5f4a4c75..052714106b7b 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -26,15 +26,6 @@ config NVM_DEBUG
 
 	It is required to create/remove targets without IOCTLs.
 
-config NVM_GENNVM
-	tristate "General Non-Volatile Memory Manager for Open-Channel SSDs"
-	---help---
-	Non-volatile memory media manager for Open-Channel SSDs that implements
-	physical media metadata management and block provisioning API.
-
-	This is the standard media manager for using Open-Channel SSDs, and
-	required for targets to be instantiated.
-
 config NVM_RRPC
 	tristate "Round-robin Hybrid Open-Channel SSD target"
 	---help---
diff --git a/drivers/lightnvm/Makefile b/drivers/lightnvm/Makefile
index a7a0a22cf1a5..b2a39e2d2895 100644
--- a/drivers/lightnvm/Makefile
+++ b/drivers/lightnvm/Makefile
@@ -2,6 +2,5 @@
 # Makefile for Open-Channel SSDs.
 #
 
-obj-$(CONFIG_NVM)		:= core.o sysblk.o
-obj-$(CONFIG_NVM_GENNVM) 	+= gennvm.o
+obj-$(CONFIG_NVM)		:= core.o
 obj-$(CONFIG_NVM_RRPC)		+= rrpc.o
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 02240a0b39c9..5262ba66a7a7 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -29,10 +29,483 @@
 
 static LIST_HEAD(nvm_tgt_types);
 static DECLARE_RWSEM(nvm_tgtt_lock);
-static LIST_HEAD(nvm_mgrs);
 static LIST_HEAD(nvm_devices);
 static DECLARE_RWSEM(nvm_lock);
 
+/* Map between virtual and physical channel and lun */
+struct nvm_ch_map {
+	int ch_off;
+	int nr_luns;
+	int *lun_offs;
+};
+
+struct nvm_dev_map {
+	struct nvm_ch_map *chnls;
+	int nr_chnls;
+};
+
+struct nvm_area {
+	struct list_head list;
+	sector_t begin;
+	sector_t end;	/* end is excluded */
+};
+
+static struct nvm_target *nvm_find_target(struct nvm_dev *dev, const char *name)
+{
+	struct nvm_target *tgt;
+
+	list_for_each_entry(tgt, &dev->targets, list)
+		if (!strcmp(name, tgt->disk->disk_name))
+			return tgt;
+
+	return NULL;
+}
+
+static int nvm_reserve_luns(struct nvm_dev *dev, int lun_begin, int lun_end)
+{
+	int i;
+
+	for (i = lun_begin; i <= lun_end; i++) {
+		if (test_and_set_bit(i, dev->lun_map)) {
+			pr_err("nvm: lun %d already allocated\n", i);
+			goto err;
+		}
+	}
+
+	return 0;
+err:
+	while (--i > lun_begin)
+		clear_bit(i, dev->lun_map);
+
+	return -EBUSY;
+}
+
+static void nvm_release_luns_err(struct nvm_dev *dev, int lun_begin,
+				 int lun_end)
+{
+	int i;
+
+	for (i = lun_begin; i <= lun_end; i++)
+		WARN_ON(!test_and_clear_bit(i, dev->lun_map));
+}
+
+static void nvm_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev)
+{
+	struct nvm_dev *dev = tgt_dev->parent;
+	struct nvm_dev_map *dev_map = tgt_dev->map;
+	int i, j;
+
+	for (i = 0; i < dev_map->nr_chnls; i++) {
+		struct nvm_ch_map *ch_map = &dev_map->chnls[i];
+		int *lun_offs = ch_map->lun_offs;
+		int ch = i + ch_map->ch_off;
+
+		for (j = 0; j < ch_map->nr_luns; j++) {
+			int lun = j + lun_offs[j];
+			int lunid = (ch * dev->geo.luns_per_chnl) + lun;
+
+			WARN_ON(!test_and_clear_bit(lunid, dev->lun_map));
+		}
+
+		kfree(ch_map->lun_offs);
+	}
+
+	kfree(dev_map->chnls);
+	kfree(dev_map);
+
+	kfree(tgt_dev->luns);
+	kfree(tgt_dev);
+}
+
+static struct nvm_tgt_dev *nvm_create_tgt_dev(struct nvm_dev *dev,
+					      int lun_begin, int lun_end)
+{
+	struct nvm_tgt_dev *tgt_dev = NULL;
+	struct nvm_dev_map *dev_rmap = dev->rmap;
+	struct nvm_dev_map *dev_map;
+	struct ppa_addr *luns;
+	int nr_luns = lun_end - lun_begin + 1;
+	int luns_left = nr_luns;
+	int nr_chnls = nr_luns / dev->geo.luns_per_chnl;
+	int nr_chnls_mod = nr_luns % dev->geo.luns_per_chnl;
+	int bch = lun_begin / dev->geo.luns_per_chnl;
+	int blun = lun_begin % dev->geo.luns_per_chnl;
+	int lunid = 0;
+	int lun_balanced = 1;
+	int prev_nr_luns;
+	int i, j;
+
+	nr_chnls = nr_luns / dev->geo.luns_per_chnl;
+	nr_chnls = (nr_chnls_mod == 0) ? nr_chnls : nr_chnls + 1;
+
+	dev_map = kmalloc(sizeof(struct nvm_dev_map), GFP_KERNEL);
+	if (!dev_map)
+		goto err_dev;
+
+	dev_map->chnls = kcalloc(nr_chnls, sizeof(struct nvm_ch_map),
+								GFP_KERNEL);
+	if (!dev_map->chnls)
+		goto err_chnls;
+
+	luns = kcalloc(nr_luns, sizeof(struct ppa_addr), GFP_KERNEL);
+	if (!luns)
+		goto err_luns;
+
+	prev_nr_luns = (luns_left > dev->geo.luns_per_chnl) ?
+					dev->geo.luns_per_chnl : luns_left;
+	for (i = 0; i < nr_chnls; i++) {
+		struct nvm_ch_map *ch_rmap = &dev_rmap->chnls[i + bch];
+		int *lun_roffs = ch_rmap->lun_offs;
+		struct nvm_ch_map *ch_map = &dev_map->chnls[i];
+		int *lun_offs;
+		int luns_in_chnl = (luns_left > dev->geo.luns_per_chnl) ?
+					dev->geo.luns_per_chnl : luns_left;
+
+		if (lun_balanced && prev_nr_luns != luns_in_chnl)
+			lun_balanced = 0;
+
+		ch_map->ch_off = ch_rmap->ch_off = bch;
+		ch_map->nr_luns = luns_in_chnl;
+
+		lun_offs = kcalloc(luns_in_chnl, sizeof(int), GFP_KERNEL);
+		if (!lun_offs)
+			goto err_ch;
+
+		for (j = 0; j < luns_in_chnl; j++) {
+			luns[lunid].ppa = 0;
+			luns[lunid].g.ch = i;
+			luns[lunid++].g.lun = j;
+
+			lun_offs[j] = blun;
+			lun_roffs[j + blun] = blun;
+		}
+
+		ch_map->lun_offs = lun_offs;
+
+		/* when starting a new channel, lun offset is reset */
+		blun = 0;
+		luns_left -= luns_in_chnl;
+	}
+
+	dev_map->nr_chnls = nr_chnls;
+
+	tgt_dev = kmalloc(sizeof(struct nvm_tgt_dev), GFP_KERNEL);
+	if (!tgt_dev)
+		goto err_ch;
+
+	memcpy(&tgt_dev->geo, &dev->geo, sizeof(struct nvm_geo));
+	/* Target device only owns a portion of the physical device */
+	tgt_dev->geo.nr_chnls = nr_chnls;
+	tgt_dev->geo.nr_luns = nr_luns;
+	tgt_dev->geo.luns_per_chnl = (lun_balanced) ? prev_nr_luns : -1;
+	tgt_dev->total_secs = nr_luns * tgt_dev->geo.sec_per_lun;
+	tgt_dev->q = dev->q;
+	tgt_dev->map = dev_map;
+	tgt_dev->luns = luns;
+	memcpy(&tgt_dev->identity, &dev->identity, sizeof(struct nvm_id));
+
+	tgt_dev->parent = dev;
+
+	return tgt_dev;
+err_ch:
+	while (--i > 0)
+		kfree(dev_map->chnls[i].lun_offs);
+	kfree(luns);
+err_luns:
+	kfree(dev_map->chnls);
+err_chnls:
+	kfree(dev_map);
+err_dev:
+	return tgt_dev;
+}
+
+static const struct block_device_operations nvm_fops = {
+	.owner		= THIS_MODULE,
+};
+
+static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
+{
+	struct nvm_ioctl_create_simple *s = &create->conf.s;
+	struct request_queue *tqueue;
+	struct gendisk *tdisk;
+	struct nvm_tgt_type *tt;
+	struct nvm_target *t;
+	struct nvm_tgt_dev *tgt_dev;
+	void *targetdata;
+
+	tt = nvm_find_target_type(create->tgttype, 1);
+	if (!tt) {
+		pr_err("nvm: target type %s not found\n", create->tgttype);
+		return -EINVAL;
+	}
+
+	mutex_lock(&dev->mlock);
+	t = nvm_find_target(dev, create->tgtname);
+	if (t) {
+		pr_err("nvm: target name already exists.\n");
+		mutex_unlock(&dev->mlock);
+		return -EINVAL;
+	}
+	mutex_unlock(&dev->mlock);
+
+	if (nvm_reserve_luns(dev, s->lun_begin, s->lun_end))
+		return -ENOMEM;
+
+	t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL);
+	if (!t)
+		goto err_reserve;
+
+	tgt_dev = nvm_create_tgt_dev(dev, s->lun_begin, s->lun_end);
+	if (!tgt_dev) {
+		pr_err("nvm: could not create target device\n");
+		goto err_t;
+	}
+
+	tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
+	if (!tqueue)
+		goto err_dev;
+	blk_queue_make_request(tqueue, tt->make_rq);
+
+	tdisk = alloc_disk(0);
+	if (!tdisk)
+		goto err_queue;
+
+	sprintf(tdisk->disk_name, "%s", create->tgtname);
+	tdisk->flags = GENHD_FL_EXT_DEVT;
+	tdisk->major = 0;
+	tdisk->first_minor = 0;
+	tdisk->fops = &nvm_fops;
+	tdisk->queue = tqueue;
+
+	targetdata = tt->init(tgt_dev, tdisk);
+	if (IS_ERR(targetdata))
+		goto err_init;
+
+	tdisk->private_data = targetdata;
+	tqueue->queuedata = targetdata;
+
+	blk_queue_max_hw_sectors(tqueue, 8 * dev->ops->max_phys_sect);
+
+	set_capacity(tdisk, tt->capacity(targetdata));
+	add_disk(tdisk);
+
+	if (tt->sysfs_init && tt->sysfs_init(tdisk))
+		goto err_sysfs;
+
+	t->type = tt;
+	t->disk = tdisk;
+	t->dev = tgt_dev;
+
+	mutex_lock(&dev->mlock);
+	list_add_tail(&t->list, &dev->targets);
+	mutex_unlock(&dev->mlock);
+
+	return 0;
+err_sysfs:
+	if (tt->exit)
+		tt->exit(targetdata);
+err_init:
+	put_disk(tdisk);
+err_queue:
+	blk_cleanup_queue(tqueue);
+err_dev:
+	nvm_remove_tgt_dev(tgt_dev);
+err_t:
+	kfree(t);
+err_reserve:
+	nvm_release_luns_err(dev, s->lun_begin, s->lun_end);
+	return -ENOMEM;
+}
+
+static void __nvm_remove_target(struct nvm_target *t)
+{
+	struct nvm_tgt_type *tt = t->type;
+	struct gendisk *tdisk = t->disk;
+	struct request_queue *q = tdisk->queue;
+
+	del_gendisk(tdisk);
+	blk_cleanup_queue(q);
+
+	if (tt->sysfs_exit)
+		tt->sysfs_exit(tdisk);
+
+	if (tt->exit)
+		tt->exit(tdisk->private_data);
+
+	nvm_remove_tgt_dev(t->dev);
+	put_disk(tdisk);
+
+	list_del(&t->list);
+	kfree(t);
+}
+
+/**
+ * nvm_remove_tgt - Removes a target from the media manager
+ * @dev:	device
+ * @remove:	ioctl structure with target name to remove.
+ *
+ * Returns:
+ * 0: on success
+ * 1: on not found
+ * <0: on error
+ */
+static int nvm_remove_tgt(struct nvm_dev *dev, struct nvm_ioctl_remove *remove)
+{
+	struct nvm_target *t;
+
+	mutex_lock(&dev->mlock);
+	t = nvm_find_target(dev, remove->tgtname);
+	if (!t) {
+		mutex_unlock(&dev->mlock);
+		return 1;
+	}
+	__nvm_remove_target(t);
+	mutex_unlock(&dev->mlock);
+
+	return 0;
+}
+
+static int nvm_register_map(struct nvm_dev *dev)
+{
+	struct nvm_dev_map *rmap;
+	int i, j;
+
+	rmap = kmalloc(sizeof(struct nvm_dev_map), GFP_KERNEL);
+	if (!rmap)
+		goto err_rmap;
+
+	rmap->chnls = kcalloc(dev->geo.nr_chnls, sizeof(struct nvm_ch_map),
+								GFP_KERNEL);
+	if (!rmap->chnls)
+		goto err_chnls;
+
+	for (i = 0; i < dev->geo.nr_chnls; i++) {
+		struct nvm_ch_map *ch_rmap;
+		int *lun_roffs;
+		int luns_in_chnl = dev->geo.luns_per_chnl;
+
+		ch_rmap = &rmap->chnls[i];
+
+		ch_rmap->ch_off = -1;
+		ch_rmap->nr_luns = luns_in_chnl;
+
+		lun_roffs = kcalloc(luns_in_chnl, sizeof(int), GFP_KERNEL);
+		if (!lun_roffs)
+			goto err_ch;
+
+		for (j = 0; j < luns_in_chnl; j++)
+			lun_roffs[j] = -1;
+
+		ch_rmap->lun_offs = lun_roffs;
+	}
+
+	dev->rmap = rmap;
+
+	return 0;
+err_ch:
+	while (--i >= 0)
+		kfree(rmap->chnls[i].lun_offs);
+err_chnls:
+	kfree(rmap);
+err_rmap:
+	return -ENOMEM;
+}
+
+static void nvm_map_to_dev(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p)
+{
+	struct nvm_dev_map *dev_map = tgt_dev->map;
+	struct nvm_ch_map *ch_map = &dev_map->chnls[p->g.ch];
+	int lun_off = ch_map->lun_offs[p->g.lun];
+
+	p->g.ch += ch_map->ch_off;
+	p->g.lun += lun_off;
+}
+
+static void nvm_map_to_tgt(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p)
+{
+	struct nvm_dev *dev = tgt_dev->parent;
+	struct nvm_dev_map *dev_rmap = dev->rmap;
+	struct nvm_ch_map *ch_rmap = &dev_rmap->chnls[p->g.ch];
+	int lun_roff = ch_rmap->lun_offs[p->g.lun];
+
+	p->g.ch -= ch_rmap->ch_off;
+	p->g.lun -= lun_roff;
+}
+
+static void nvm_ppa_tgt_to_dev(struct nvm_tgt_dev *tgt_dev,
+				struct ppa_addr *ppa_list, int nr_ppas)
+{
+	int i;
+
+	for (i = 0; i < nr_ppas; i++) {
+		nvm_map_to_dev(tgt_dev, &ppa_list[i]);
+		ppa_list[i] = generic_to_dev_addr(tgt_dev, ppa_list[i]);
+	}
+}
+
+static void nvm_ppa_dev_to_tgt(struct nvm_tgt_dev *tgt_dev,
+				struct ppa_addr *ppa_list, int nr_ppas)
+{
+	int i;
+
+	for (i = 0; i < nr_ppas; i++) {
+		ppa_list[i] = dev_to_generic_addr(tgt_dev, ppa_list[i]);
+		nvm_map_to_tgt(tgt_dev, &ppa_list[i]);
+	}
+}
+
+static void nvm_rq_tgt_to_dev(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
+{
+	if (rqd->nr_ppas == 1) {
+		nvm_ppa_tgt_to_dev(tgt_dev, &rqd->ppa_addr, 1);
+		return;
+	}
+
+	nvm_ppa_tgt_to_dev(tgt_dev, rqd->ppa_list, rqd->nr_ppas);
+}
+
+static void nvm_rq_dev_to_tgt(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
+{
+	if (rqd->nr_ppas == 1) {
+		nvm_ppa_dev_to_tgt(tgt_dev, &rqd->ppa_addr, 1);
+		return;
+	}
+
+	nvm_ppa_dev_to_tgt(tgt_dev, rqd->ppa_list, rqd->nr_ppas);
+}
+
+void nvm_part_to_tgt(struct nvm_dev *dev, sector_t *entries,
+		     int len)
+{
+	struct nvm_geo *geo = &dev->geo;
+	struct nvm_dev_map *dev_rmap = dev->rmap;
+	u64 i;
+
+	for (i = 0; i < len; i++) {
+		struct nvm_ch_map *ch_rmap;
+		int *lun_roffs;
+		struct ppa_addr gaddr;
+		u64 pba = le64_to_cpu(entries[i]);
+		int off;
+		u64 diff;
+
+		if (!pba)
+			continue;
+
+		gaddr = linear_to_generic_addr(geo, pba);
+		ch_rmap = &dev_rmap->chnls[gaddr.g.ch];
+		lun_roffs = ch_rmap->lun_offs;
+
+		off = gaddr.g.ch * geo->luns_per_chnl + gaddr.g.lun;
+
+		diff = ((ch_rmap->ch_off * geo->luns_per_chnl) +
+				(lun_roffs[gaddr.g.lun])) * geo->sec_per_lun;
+
+		entries[i] -= cpu_to_le64(diff);
+	}
+}
+EXPORT_SYMBOL(nvm_part_to_tgt);
+
 struct nvm_tgt_type *nvm_find_target_type(const char *name, int lock)
 {
 	struct nvm_tgt_type *tmp, *tt = NULL;
@@ -92,78 +565,6 @@ void nvm_dev_dma_free(struct nvm_dev *dev, void *addr, dma_addr_t dma_handler)
 }
 EXPORT_SYMBOL(nvm_dev_dma_free);
 
-static struct nvmm_type *nvm_find_mgr_type(const char *name)
-{
-	struct nvmm_type *mt;
-
-	list_for_each_entry(mt, &nvm_mgrs, list)
-		if (!strcmp(name, mt->name))
-			return mt;
-
-	return NULL;
-}
-
-static struct nvmm_type *nvm_init_mgr(struct nvm_dev *dev)
-{
-	struct nvmm_type *mt;
-	int ret;
-
-	lockdep_assert_held(&nvm_lock);
-
-	list_for_each_entry(mt, &nvm_mgrs, list) {
-		if (strncmp(dev->sb.mmtype, mt->name, NVM_MMTYPE_LEN))
-			continue;
-
-		ret = mt->register_mgr(dev);
-		if (ret < 0) {
-			pr_err("nvm: media mgr failed to init (%d) on dev %s\n",
-								ret, dev->name);
-			return NULL; /* initialization failed */
-		} else if (ret > 0)
-			return mt;
-	}
-
-	return NULL;
-}
-
-int nvm_register_mgr(struct nvmm_type *mt)
-{
-	struct nvm_dev *dev;
-	int ret = 0;
-
-	down_write(&nvm_lock);
-	if (nvm_find_mgr_type(mt->name)) {
-		ret = -EEXIST;
-		goto finish;
-	} else {
-		list_add(&mt->list, &nvm_mgrs);
-	}
-
-	/* try to register media mgr if any device have none configured */
-	list_for_each_entry(dev, &nvm_devices, devices) {
-		if (dev->mt)
-			continue;
-
-		dev->mt = nvm_init_mgr(dev);
-	}
-finish:
-	up_write(&nvm_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL(nvm_register_mgr);
-
-void nvm_unregister_mgr(struct nvmm_type *mt)
-{
-	if (!mt)
-		return;
-
-	down_write(&nvm_lock);
-	list_del(&mt->list);
-	up_write(&nvm_lock);
-}
-EXPORT_SYMBOL(nvm_unregister_mgr);
-
 static struct nvm_dev *nvm_find_nvm_dev(const char *name)
 {
 	struct nvm_dev *dev;
@@ -175,53 +576,6 @@ static struct nvm_dev *nvm_find_nvm_dev(const char *name)
 	return NULL;
 }
 
-static void nvm_tgt_generic_to_addr_mode(struct nvm_tgt_dev *tgt_dev,
-					 struct nvm_rq *rqd)
-{
-	struct nvm_dev *dev = tgt_dev->parent;
-	int i;
-
-	if (rqd->nr_ppas > 1) {
-		for (i = 0; i < rqd->nr_ppas; i++) {
-			rqd->ppa_list[i] = dev->mt->trans_ppa(tgt_dev,
-					rqd->ppa_list[i], TRANS_TGT_TO_DEV);
-			rqd->ppa_list[i] = generic_to_dev_addr(dev,
-							rqd->ppa_list[i]);
-		}
-	} else {
-		rqd->ppa_addr = dev->mt->trans_ppa(tgt_dev, rqd->ppa_addr,
-						TRANS_TGT_TO_DEV);
-		rqd->ppa_addr = generic_to_dev_addr(dev, rqd->ppa_addr);
-	}
-}
-
-int nvm_set_bb_tbl(struct nvm_dev *dev, struct ppa_addr *ppas, int nr_ppas,
-								int type)
-{
-	struct nvm_rq rqd;
-	int ret;
-
-	if (nr_ppas > dev->ops->max_phys_sect) {
-		pr_err("nvm: unable to update all sysblocks atomically\n");
-		return -EINVAL;
-	}
-
-	memset(&rqd, 0, sizeof(struct nvm_rq));
-
-	nvm_set_rqd_ppalist(dev, &rqd, ppas, nr_ppas, 1);
-	nvm_generic_to_addr_mode(dev, &rqd);
-
-	ret = dev->ops->set_bb_tbl(dev, &rqd.ppa_addr, rqd.nr_ppas, type);
-	nvm_free_rqd_ppalist(dev, &rqd);
-	if (ret) {
-		pr_err("nvm: sysblk failed bb mark\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(nvm_set_bb_tbl);
-
 int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas,
 		       int nr_ppas, int type)
 {
@@ -237,12 +591,12 @@ int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas,
 	memset(&rqd, 0, sizeof(struct nvm_rq));
 
 	nvm_set_rqd_ppalist(dev, &rqd, ppas, nr_ppas, 1);
-	nvm_tgt_generic_to_addr_mode(tgt_dev, &rqd);
+	nvm_rq_tgt_to_dev(tgt_dev, &rqd);
 
 	ret = dev->ops->set_bb_tbl(dev, &rqd.ppa_addr, rqd.nr_ppas, type);
 	nvm_free_rqd_ppalist(dev, &rqd);
 	if (ret) {
-		pr_err("nvm: sysblk failed bb mark\n");
+		pr_err("nvm: failed bb mark\n");
 		return -EINVAL;
 	}
 
@@ -262,15 +616,42 @@ int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
 {
 	struct nvm_dev *dev = tgt_dev->parent;
 
-	return dev->mt->submit_io(tgt_dev, rqd);
+	if (!dev->ops->submit_io)
+		return -ENODEV;
+
+	nvm_rq_tgt_to_dev(tgt_dev, rqd);
+
+	rqd->dev = tgt_dev;
+	return dev->ops->submit_io(dev, rqd);
 }
 EXPORT_SYMBOL(nvm_submit_io);
 
-int nvm_erase_blk(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p, int flags)
+int nvm_erase_blk(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas, int flags)
 {
 	struct nvm_dev *dev = tgt_dev->parent;
+	struct nvm_rq rqd;
+	int ret;
+
+	if (!dev->ops->erase_block)
+		return 0;
+
+	nvm_map_to_dev(tgt_dev, ppas);
+
+	memset(&rqd, 0, sizeof(struct nvm_rq));
+
+	ret = nvm_set_rqd_ppalist(dev, &rqd, ppas, 1, 1);
+	if (ret)
+		return ret;
+
+	nvm_rq_tgt_to_dev(tgt_dev, &rqd);
+
+	rqd.flags = flags;
+
+	ret = dev->ops->erase_block(dev, &rqd);
 
-	return dev->mt->erase_blk(tgt_dev, p, flags);
+	nvm_free_rqd_ppalist(dev, &rqd);
+
+	return ret;
 }
 EXPORT_SYMBOL(nvm_erase_blk);
 
@@ -289,46 +670,67 @@ EXPORT_SYMBOL(nvm_get_l2p_tbl);
 int nvm_get_area(struct nvm_tgt_dev *tgt_dev, sector_t *lba, sector_t len)
 {
 	struct nvm_dev *dev = tgt_dev->parent;
+	struct nvm_geo *geo = &dev->geo;
+	struct nvm_area *area, *prev, *next;
+	sector_t begin = 0;
+	sector_t max_sectors = (geo->sec_size * dev->total_secs) >> 9;
 
-	return dev->mt->get_area(dev, lba, len);
-}
-EXPORT_SYMBOL(nvm_get_area);
+	if (len > max_sectors)
+		return -EINVAL;
 
-void nvm_put_area(struct nvm_tgt_dev *tgt_dev, sector_t lba)
-{
-	struct nvm_dev *dev = tgt_dev->parent;
+	area = kmalloc(sizeof(struct nvm_area), GFP_KERNEL);
+	if (!area)
+		return -ENOMEM;
 
-	dev->mt->put_area(dev, lba);
-}
-EXPORT_SYMBOL(nvm_put_area);
+	prev = NULL;
 
-void nvm_addr_to_generic_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
-{
-	int i;
+	spin_lock(&dev->lock);
+	list_for_each_entry(next, &dev->area_list, list) {
+		if (begin + len > next->begin) {
+			begin = next->end;
+			prev = next;
+			continue;
+		}
+		break;
+	}
 
-	if (rqd->nr_ppas > 1) {
-		for (i = 0; i < rqd->nr_ppas; i++)
-			rqd->ppa_list[i] = dev_to_generic_addr(dev,
-							rqd->ppa_list[i]);
-	} else {
-		rqd->ppa_addr = dev_to_generic_addr(dev, rqd->ppa_addr);
+	if ((begin + len) > max_sectors) {
+		spin_unlock(&dev->lock);
+		kfree(area);
+		return -EINVAL;
 	}
+
+	area->begin = *lba = begin;
+	area->end = begin + len;
+
+	if (prev) /* insert into sorted order */
+		list_add(&area->list, &prev->list);
+	else
+		list_add(&area->list, &dev->area_list);
+	spin_unlock(&dev->lock);
+
+	return 0;
 }
-EXPORT_SYMBOL(nvm_addr_to_generic_mode);
+EXPORT_SYMBOL(nvm_get_area);
 
-void nvm_generic_to_addr_mode(struct nvm_dev *dev, struct nvm_rq *rqd)
+void nvm_put_area(struct nvm_tgt_dev *tgt_dev, sector_t begin)
 {
-	int i;
+	struct nvm_dev *dev = tgt_dev->parent;
+	struct nvm_area *area;
 
-	if (rqd->nr_ppas > 1) {
-		for (i = 0; i < rqd->nr_ppas; i++)
-			rqd->ppa_list[i] = generic_to_dev_addr(dev,
-							rqd->ppa_list[i]);
-	} else {
-		rqd->ppa_addr = generic_to_dev_addr(dev, rqd->ppa_addr);
+	spin_lock(&dev->lock);
+	list_for_each_entry(area, &dev->area_list, list) {
+		if (area->begin != begin)
+			continue;
+
+		list_del(&area->list);
+		spin_unlock(&dev->lock);
+		kfree(area);
+		return;
 	}
+	spin_unlock(&dev->lock);
 }
-EXPORT_SYMBOL(nvm_generic_to_addr_mode);
+EXPORT_SYMBOL(nvm_put_area);
 
 int nvm_set_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd,
 			const struct ppa_addr *ppas, int nr_ppas, int vblk)
@@ -380,149 +782,19 @@ void nvm_free_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd)
 }
 EXPORT_SYMBOL(nvm_free_rqd_ppalist);
 
-int nvm_erase_ppa(struct nvm_dev *dev, struct ppa_addr *ppas, int nr_ppas,
-								int flags)
+void nvm_end_io(struct nvm_rq *rqd)
 {
-	struct nvm_rq rqd;
-	int ret;
+	struct nvm_tgt_dev *tgt_dev = rqd->dev;
 
-	if (!dev->ops->erase_block)
-		return 0;
+	/* Convert address space */
+	if (tgt_dev)
+		nvm_rq_dev_to_tgt(tgt_dev, rqd);
 
-	memset(&rqd, 0, sizeof(struct nvm_rq));
-
-	ret = nvm_set_rqd_ppalist(dev, &rqd, ppas, nr_ppas, 1);
-	if (ret)
-		return ret;
-
-	nvm_generic_to_addr_mode(dev, &rqd);
-
-	rqd.flags = flags;
-
-	ret = dev->ops->erase_block(dev, &rqd);
-
-	nvm_free_rqd_ppalist(dev, &rqd);
-
-	return ret;
-}
-EXPORT_SYMBOL(nvm_erase_ppa);
-
-void nvm_end_io(struct nvm_rq *rqd, int error)
-{
-	rqd->error = error;
-	rqd->end_io(rqd);
+	if (rqd->end_io)
+		rqd->end_io(rqd);
 }
 EXPORT_SYMBOL(nvm_end_io);
 
-static void nvm_end_io_sync(struct nvm_rq *rqd)
-{
-	struct completion *waiting = rqd->wait;
-
-	rqd->wait = NULL;
-
-	complete(waiting);
-}
-
-static int __nvm_submit_ppa(struct nvm_dev *dev, struct nvm_rq *rqd, int opcode,
-						int flags, void *buf, int len)
-{
-	DECLARE_COMPLETION_ONSTACK(wait);
-	struct bio *bio;
-	int ret;
-	unsigned long hang_check;
-
-	bio = bio_map_kern(dev->q, buf, len, GFP_KERNEL);
-	if (IS_ERR_OR_NULL(bio))
-		return -ENOMEM;
-
-	nvm_generic_to_addr_mode(dev, rqd);
-
-	rqd->dev = NULL;
-	rqd->opcode = opcode;
-	rqd->flags = flags;
-	rqd->bio = bio;
-	rqd->wait = &wait;
-	rqd->end_io = nvm_end_io_sync;
-
-	ret = dev->ops->submit_io(dev, rqd);
-	if (ret) {
-		bio_put(bio);
-		return ret;
-	}
-
-	/* Prevent hang_check timer from firing at us during very long I/O */
-	hang_check = sysctl_hung_task_timeout_secs;
-	if (hang_check)
-		while (!wait_for_completion_io_timeout(&wait,
-							hang_check * (HZ/2)))
-			;
-	else
-		wait_for_completion_io(&wait);
-
-	return rqd->error;
-}
-
-/**
- * nvm_submit_ppa_list - submit user-defined ppa list to device. The user must
- *			 take to free ppa list if necessary.
- * @dev:	device
- * @ppa_list:	user created ppa_list
- * @nr_ppas:	length of ppa_list
- * @opcode:	device opcode
- * @flags:	device flags
- * @buf:	data buffer
- * @len:	data buffer length
- */
-int nvm_submit_ppa_list(struct nvm_dev *dev, struct ppa_addr *ppa_list,
-			int nr_ppas, int opcode, int flags, void *buf, int len)
-{
-	struct nvm_rq rqd;
-
-	if (dev->ops->max_phys_sect < nr_ppas)
-		return -EINVAL;
-
-	memset(&rqd, 0, sizeof(struct nvm_rq));
-
-	rqd.nr_ppas = nr_ppas;
-	if (nr_ppas > 1)
-		rqd.ppa_list = ppa_list;
-	else
-		rqd.ppa_addr = ppa_list[0];
-
-	return __nvm_submit_ppa(dev, &rqd, opcode, flags, buf, len);
-}
-EXPORT_SYMBOL(nvm_submit_ppa_list);
-
-/**
- * nvm_submit_ppa - submit PPAs to device. PPAs will automatically be unfolded
- *		    as single, dual, quad plane PPAs depending on device type.
- * @dev:	device
- * @ppa:	user created ppa_list
- * @nr_ppas:	length of ppa_list
- * @opcode:	device opcode
- * @flags:	device flags
- * @buf:	data buffer
- * @len:	data buffer length
- */
-int nvm_submit_ppa(struct nvm_dev *dev, struct ppa_addr *ppa, int nr_ppas,
-				int opcode, int flags, void *buf, int len)
-{
-	struct nvm_rq rqd;
-	int ret;
-
-	memset(&rqd, 0, sizeof(struct nvm_rq));
-	ret = nvm_set_rqd_ppalist(dev, &rqd, ppa, nr_ppas, 1);
-	if (ret)
-		return ret;
-
-	ret = __nvm_submit_ppa(dev, &rqd, opcode, flags, buf, len);
-
-	nvm_free_rqd_ppalist(dev, &rqd);
-
-	return ret;
-}
-EXPORT_SYMBOL(nvm_submit_ppa);
-
 /*
  * folds a bad block list from its plane representation to its virtual
  * block representation. The fold is done in place and reduced size is
@@ -559,21 +831,14 @@ int nvm_bb_tbl_fold(struct nvm_dev *dev, u8 *blks, int nr_blks)
 }
 EXPORT_SYMBOL(nvm_bb_tbl_fold);
 
-int nvm_get_bb_tbl(struct nvm_dev *dev, struct ppa_addr ppa, u8 *blks)
-{
-	ppa = generic_to_dev_addr(dev, ppa);
-
-	return dev->ops->get_bb_tbl(dev, ppa, blks);
-}
-EXPORT_SYMBOL(nvm_get_bb_tbl);
-
 int nvm_get_tgt_bb_tbl(struct nvm_tgt_dev *tgt_dev, struct ppa_addr ppa,
 		       u8 *blks)
 {
 	struct nvm_dev *dev = tgt_dev->parent;
 
-	ppa = dev->mt->trans_ppa(tgt_dev, ppa, TRANS_TGT_TO_DEV);
-	return nvm_get_bb_tbl(dev, ppa, blks);
+	nvm_ppa_tgt_to_dev(tgt_dev, &ppa, 1);
+
+	return dev->ops->get_bb_tbl(dev, ppa, blks);
 }
 EXPORT_SYMBOL(nvm_get_tgt_bb_tbl);
 
@@ -627,7 +892,7 @@ static int nvm_init_mlc_tbl(struct nvm_dev *dev, struct nvm_id_group *grp)
 static int nvm_core_init(struct nvm_dev *dev)
 {
 	struct nvm_id *id = &dev->identity;
-	struct nvm_id_group *grp = &id->groups[0];
+	struct nvm_id_group *grp = &id->grp;
 	struct nvm_geo *geo = &dev->geo;
 	int ret;
 
@@ -691,36 +956,31 @@ static int nvm_core_init(struct nvm_dev *dev)
 		goto err_fmtype;
 	}
 
+	INIT_LIST_HEAD(&dev->area_list);
+	INIT_LIST_HEAD(&dev->targets);
 	mutex_init(&dev->mlock);
 	spin_lock_init(&dev->lock);
 
-	blk_queue_logical_block_size(dev->q, geo->sec_size);
+	ret = nvm_register_map(dev);
+	if (ret)
+		goto err_fmtype;
 
+	blk_queue_logical_block_size(dev->q, geo->sec_size);
 	return 0;
 err_fmtype:
 	kfree(dev->lun_map);
 	return ret;
 }
 
-static void nvm_free_mgr(struct nvm_dev *dev)
-{
-	if (!dev->mt)
-		return;
-
-	dev->mt->unregister_mgr(dev);
-	dev->mt = NULL;
-}
-
 void nvm_free(struct nvm_dev *dev)
 {
 	if (!dev)
 		return;
 
-	nvm_free_mgr(dev);
-
 	if (dev->dma_pool)
 		dev->ops->destroy_dma_pool(dev->dma_pool);
 
+	kfree(dev->rmap);
 	kfree(dev->lptbl);
 	kfree(dev->lun_map);
 	kfree(dev);
@@ -731,28 +991,19 @@ static int nvm_init(struct nvm_dev *dev)
 	struct nvm_geo *geo = &dev->geo;
 	int ret = -EINVAL;
 
-	if (!dev->q || !dev->ops)
-		return ret;
-
 	if (dev->ops->identity(dev, &dev->identity)) {
 		pr_err("nvm: device could not be identified\n");
 		goto err;
 	}
 
-	pr_debug("nvm: ver:%x nvm_vendor:%x groups:%u\n",
-			dev->identity.ver_id, dev->identity.vmnt,
-							dev->identity.cgrps);
+	pr_debug("nvm: ver:%x nvm_vendor:%x\n",
+			dev->identity.ver_id, dev->identity.vmnt);
 
 	if (dev->identity.ver_id != 1) {
 		pr_err("nvm: device not supported by kernel.");
 		goto err;
 	}
 
-	if (dev->identity.cgrps != 1) {
-		pr_err("nvm: only one group configuration supported.");
-		goto err;
-	}
-
 	ret = nvm_core_init(dev);
 	if (ret) {
 		pr_err("nvm: could not initialize core structures.\n");
@@ -779,49 +1030,50 @@ int nvm_register(struct nvm_dev *dev)
 {
 	int ret;
 
-	ret = nvm_init(dev);
-	if (ret)
-		goto err_init;
+	if (!dev->q || !dev->ops)
+		return -EINVAL;
 
 	if (dev->ops->max_phys_sect > 256) {
 		pr_info("nvm: max sectors supported is 256.\n");
-		ret = -EINVAL;
-		goto err_init;
+		return -EINVAL;
 	}
 
 	if (dev->ops->max_phys_sect > 1) {
 		dev->dma_pool = dev->ops->create_dma_pool(dev, "ppalist");
 		if (!dev->dma_pool) {
 			pr_err("nvm: could not create dma pool\n");
-			ret = -ENOMEM;
-			goto err_init;
+			return -ENOMEM;
 		}
 	}
 
-	if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) {
-		ret = nvm_get_sysblock(dev, &dev->sb);
-		if (!ret)
-			pr_err("nvm: device not initialized.\n");
-		else if (ret < 0)
-			pr_err("nvm: err (%d) on device initialization\n", ret);
-	}
+	ret = nvm_init(dev);
+	if (ret)
+		goto err_init;
 
 	/* register device with a supported media manager */
 	down_write(&nvm_lock);
-	if (ret > 0)
-		dev->mt = nvm_init_mgr(dev);
 	list_add(&dev->devices, &nvm_devices);
 	up_write(&nvm_lock);
 
 	return 0;
 err_init:
-	kfree(dev->lun_map);
+	dev->ops->destroy_dma_pool(dev->dma_pool);
 	return ret;
 }
 EXPORT_SYMBOL(nvm_register);
 
 void nvm_unregister(struct nvm_dev *dev)
 {
+	struct nvm_target *t, *tmp;
+
+	mutex_lock(&dev->mlock);
+	list_for_each_entry_safe(t, tmp, &dev->targets, list) {
+		if (t->dev->parent != dev)
+			continue;
+		__nvm_remove_target(t);
+	}
+	mutex_unlock(&dev->mlock);
+
 	down_write(&nvm_lock);
 	list_del(&dev->devices);
 	up_write(&nvm_lock);
@@ -844,24 +1096,24 @@ static int __nvm_configure_create(struct nvm_ioctl_create *create)
 		return -EINVAL;
 	}
 
-	if (!dev->mt) {
-		pr_info("nvm: device has no media manager registered.\n");
-		return -ENODEV;
-	}
-
 	if (create->conf.type != NVM_CONFIG_TYPE_SIMPLE) {
 		pr_err("nvm: config type not valid\n");
 		return -EINVAL;
 	}
 	s = &create->conf.s;
 
-	if (s->lun_begin > s->lun_end || s->lun_end > dev->geo.nr_luns) {
+	if (s->lun_begin == -1 && s->lun_end == -1) {
+		s->lun_begin = 0;
+		s->lun_end = dev->geo.nr_luns - 1;
+	}
+
+	if (s->lun_begin > s->lun_end || s->lun_end >= dev->geo.nr_luns) {
 		pr_err("nvm: lun out of bound (%u:%u > %u)\n",
-			s->lun_begin, s->lun_end, dev->geo.nr_luns);
+			s->lun_begin, s->lun_end, dev->geo.nr_luns - 1);
 		return -EINVAL;
 	}
 
-	return dev->mt->create_tgt(dev, create);
+	return nvm_create_tgt(dev, create);
 }
 
 static long nvm_ioctl_info(struct file *file, void __user *arg)
@@ -923,16 +1175,14 @@ static long nvm_ioctl_get_devices(struct file *file, void __user *arg)
 		struct nvm_ioctl_device_info *info = &devices->info[i];
 
 		sprintf(info->devname, "%s", dev->name);
-		if (dev->mt) {
-			info->bmversion[0] = dev->mt->version[0];
-			info->bmversion[1] = dev->mt->version[1];
-			info->bmversion[2] = dev->mt->version[2];
-			sprintf(info->bmname, "%s", dev->mt->name);
-		} else {
-			sprintf(info->bmname, "none");
-		}
 
+		/* kept for compatibility */
+		info->bmversion[0] = 1;
+		info->bmversion[1] = 0;
+		info->bmversion[2] = 0;
+		sprintf(info->bmname, "%s", "gennvm");
 		i++;
+
 		if (i > 31) {
 			pr_err("nvm: max 31 devices can be reported.\n");
 			break;
@@ -994,7 +1244,7 @@ static long nvm_ioctl_dev_remove(struct file *file, void __user *arg)
 	}
 
 	list_for_each_entry(dev, &nvm_devices, devices) {
-		ret = dev->mt->remove_tgt(dev, &remove);
+		ret = nvm_remove_tgt(dev, &remove);
 		if (!ret)
 			break;
 	}
@@ -1002,47 +1252,7 @@ static long nvm_ioctl_dev_remove(struct file *file, void __user *arg)
 	return ret;
 }
 
-static void nvm_setup_nvm_sb_info(struct nvm_sb_info *info)
-{
-	info->seqnr = 1;
-	info->erase_cnt = 0;
-	info->version = 1;
-}
-
-static long __nvm_ioctl_dev_init(struct nvm_ioctl_dev_init *init)
-{
-	struct nvm_dev *dev;
-	struct nvm_sb_info info;
-	int ret;
-
-	down_write(&nvm_lock);
-	dev = nvm_find_nvm_dev(init->dev);
-	up_write(&nvm_lock);
-	if (!dev) {
-		pr_err("nvm: device not found\n");
-		return -EINVAL;
-	}
-
-	nvm_setup_nvm_sb_info(&info);
-
-	strncpy(info.mmtype, init->mmtype, NVM_MMTYPE_LEN);
-	info.fs_ppa.ppa = -1;
-
-	if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) {
-		ret = nvm_init_sysblock(dev, &info);
-		if (ret)
-			return ret;
-	}
-
-	memcpy(&dev->sb, &info, sizeof(struct nvm_sb_info));
-
-	down_write(&nvm_lock);
-	dev->mt = nvm_init_mgr(dev);
-	up_write(&nvm_lock);
-
-	return 0;
-}
-
+/* kept for compatibility reasons */
 static long nvm_ioctl_dev_init(struct file *file, void __user *arg)
 {
 	struct nvm_ioctl_dev_init init;
@@ -1058,15 +1268,13 @@ static long nvm_ioctl_dev_init(struct file *file, void __user *arg)
 		return -EINVAL;
 	}
 
-	init.dev[DISK_NAME_LEN - 1] = '\0';
-
-	return __nvm_ioctl_dev_init(&init);
+	return 0;
 }
 
+/* Kept for compatibility reasons */
 static long nvm_ioctl_dev_factory(struct file *file, void __user *arg)
 {
 	struct nvm_ioctl_dev_factory fact;
-	struct nvm_dev *dev;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1079,19 +1287,6 @@ static long nvm_ioctl_dev_factory(struct file *file, void __user *arg)
 	if (fact.flags & ~(NVM_FACTORY_NR_BITS - 1))
 		return -EINVAL;
 
-	down_write(&nvm_lock);
-	dev = nvm_find_nvm_dev(fact.dev);
-	up_write(&nvm_lock);
-	if (!dev) {
-		pr_err("nvm: device not found\n");
-		return -EINVAL;
-	}
-
-	nvm_free_mgr(dev);
-
-	if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT)
-		return nvm_dev_factory(dev, fact.flags);
-
 	return 0;
 }
 
diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c
deleted file mode 100644
index ca7880082d80..000000000000
--- a/drivers/lightnvm/gennvm.c
+++ /dev/null
@@ -1,657 +0,0 @@
-/*
- * Copyright (C) 2015 Matias Bjorling <m@bjorling.me>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING.  If not, write to
- * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
- * USA.
- *
- * Implementation of a general nvm manager for Open-Channel SSDs.
- */
-
-#include "gennvm.h"
-
-static struct nvm_target *gen_find_target(struct gen_dev *gn, const char *name)
-{
-	struct nvm_target *tgt;
-
-	list_for_each_entry(tgt, &gn->targets, list)
-		if (!strcmp(name, tgt->disk->disk_name))
-			return tgt;
-
-	return NULL;
-}
-
-static const struct block_device_operations gen_fops = {
-	.owner		= THIS_MODULE,
-};
-
-static int gen_reserve_luns(struct nvm_dev *dev, struct nvm_target *t,
-			    int lun_begin, int lun_end)
-{
-	int i;
-
-	for (i = lun_begin; i <= lun_end; i++) {
-		if (test_and_set_bit(i, dev->lun_map)) {
-			pr_err("nvm: lun %d already allocated\n", i);
-			goto err;
-		}
-	}
-
-	return 0;
-
-err:
-	while (--i > lun_begin)
-		clear_bit(i, dev->lun_map);
-
-	return -EBUSY;
-}
-
-static void gen_release_luns_err(struct nvm_dev *dev, int lun_begin,
-				 int lun_end)
-{
-	int i;
-
-	for (i = lun_begin; i <= lun_end; i++)
-		WARN_ON(!test_and_clear_bit(i, dev->lun_map));
-}
-
-static void gen_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev)
-{
-	struct nvm_dev *dev = tgt_dev->parent;
-	struct gen_dev_map *dev_map = tgt_dev->map;
-	int i, j;
-
-	for (i = 0; i < dev_map->nr_chnls; i++) {
-		struct gen_ch_map *ch_map = &dev_map->chnls[i];
-		int *lun_offs = ch_map->lun_offs;
-		int ch = i + ch_map->ch_off;
-
-		for (j = 0; j < ch_map->nr_luns; j++) {
-			int lun = j + lun_offs[j];
-			int lunid = (ch * dev->geo.luns_per_chnl) + lun;
-
-			WARN_ON(!test_and_clear_bit(lunid, dev->lun_map));
-		}
-
-		kfree(ch_map->lun_offs);
-	}
-
-	kfree(dev_map->chnls);
-	kfree(dev_map);
-	kfree(tgt_dev->luns);
-	kfree(tgt_dev);
-}
-
-static struct nvm_tgt_dev *gen_create_tgt_dev(struct nvm_dev *dev,
-					      int lun_begin, int lun_end)
-{
-	struct nvm_tgt_dev *tgt_dev = NULL;
-	struct gen_dev_map *dev_rmap = dev->rmap;
-	struct gen_dev_map *dev_map;
-	struct ppa_addr *luns;
-	int nr_luns = lun_end - lun_begin + 1;
-	int luns_left = nr_luns;
-	int nr_chnls = nr_luns / dev->geo.luns_per_chnl;
-	int nr_chnls_mod = nr_luns % dev->geo.luns_per_chnl;
-	int bch = lun_begin / dev->geo.luns_per_chnl;
-	int blun = lun_begin % dev->geo.luns_per_chnl;
-	int lunid = 0;
-	int lun_balanced = 1;
-	int prev_nr_luns;
-	int i, j;
-
-	nr_chnls = nr_luns / dev->geo.luns_per_chnl;
-	nr_chnls = (nr_chnls_mod == 0) ? nr_chnls : nr_chnls + 1;
-
-	dev_map = kmalloc(sizeof(struct gen_dev_map), GFP_KERNEL);
-	if (!dev_map)
-		goto err_dev;
-
-	dev_map->chnls = kcalloc(nr_chnls, sizeof(struct gen_ch_map),
-								GFP_KERNEL);
-	if (!dev_map->chnls)
-		goto err_chnls;
-
-	luns = kcalloc(nr_luns, sizeof(struct ppa_addr), GFP_KERNEL);
-	if (!luns)
-		goto err_luns;
-
-	prev_nr_luns = (luns_left > dev->geo.luns_per_chnl) ?
-					dev->geo.luns_per_chnl : luns_left;
-	for (i = 0; i < nr_chnls; i++) {
-		struct gen_ch_map *ch_rmap = &dev_rmap->chnls[i + bch];
-		int *lun_roffs = ch_rmap->lun_offs;
-		struct gen_ch_map *ch_map = &dev_map->chnls[i];
-		int *lun_offs;
-		int luns_in_chnl = (luns_left > dev->geo.luns_per_chnl) ?
-					dev->geo.luns_per_chnl : luns_left;
-
-		if (lun_balanced && prev_nr_luns != luns_in_chnl)
-			lun_balanced = 0;
-
-		ch_map->ch_off = ch_rmap->ch_off = bch;
-		ch_map->nr_luns = luns_in_chnl;
-
-		lun_offs = kcalloc(luns_in_chnl, sizeof(int), GFP_KERNEL);
-		if (!lun_offs)
-			goto err_ch;
-
-		for (j = 0; j < luns_in_chnl; j++) {
-			luns[lunid].ppa = 0;
-			luns[lunid].g.ch = i;
-			luns[lunid++].g.lun = j;
-
-			lun_offs[j] = blun;
-			lun_roffs[j + blun] = blun;
-		}
-
-		ch_map->lun_offs = lun_offs;
-
-		/* when starting a new channel, lun offset is reset */
-		blun = 0;
-		luns_left -= luns_in_chnl;
-	}
-
-	dev_map->nr_chnls = nr_chnls;
-
-	tgt_dev = kmalloc(sizeof(struct nvm_tgt_dev), GFP_KERNEL);
-	if (!tgt_dev)
-		goto err_ch;
-
-	memcpy(&tgt_dev->geo, &dev->geo, sizeof(struct nvm_geo));
-	/* Target device only owns a portion of the physical device */
-	tgt_dev->geo.nr_chnls = nr_chnls;
-	tgt_dev->geo.nr_luns = nr_luns;
-	tgt_dev->geo.luns_per_chnl = (lun_balanced) ? prev_nr_luns : -1;
-	tgt_dev->total_secs = nr_luns * tgt_dev->geo.sec_per_lun;
-	tgt_dev->q = dev->q;
-	tgt_dev->map = dev_map;
-	tgt_dev->luns = luns;
-	memcpy(&tgt_dev->identity, &dev->identity, sizeof(struct nvm_id));
-
-	tgt_dev->parent = dev;
-
-	return tgt_dev;
-err_ch:
-	while (--i > 0)
-		kfree(dev_map->chnls[i].lun_offs);
-	kfree(luns);
-err_luns:
-	kfree(dev_map->chnls);
-err_chnls:
-	kfree(dev_map);
-err_dev:
-	return tgt_dev;
-}
-
-static int gen_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
-{
-	struct gen_dev *gn = dev->mp;
-	struct nvm_ioctl_create_simple *s = &create->conf.s;
-	struct request_queue *tqueue;
-	struct gendisk *tdisk;
-	struct nvm_tgt_type *tt;
-	struct nvm_target *t;
-	struct nvm_tgt_dev *tgt_dev;
-	void *targetdata;
-
-	tt = nvm_find_target_type(create->tgttype, 1);
-	if (!tt) {
-		pr_err("nvm: target type %s not found\n", create->tgttype);
-		return -EINVAL;
-	}
-
-	mutex_lock(&gn->lock);
-	t = gen_find_target(gn, create->tgtname);
-	if (t) {
-		pr_err("nvm: target name already exists.\n");
-		mutex_unlock(&gn->lock);
-		return -EINVAL;
-	}
-	mutex_unlock(&gn->lock);
-
-	t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL);
-	if (!t)
-		return -ENOMEM;
-
-	if (gen_reserve_luns(dev, t, s->lun_begin, s->lun_end))
-		goto err_t;
-
-	tgt_dev = gen_create_tgt_dev(dev, s->lun_begin, s->lun_end);
-	if (!tgt_dev) {
-		pr_err("nvm: could not create target device\n");
-		goto err_reserve;
-	}
-
-	tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
-	if (!tqueue)
-		goto err_dev;
-	blk_queue_make_request(tqueue, tt->make_rq);
-
-	tdisk = alloc_disk(0);
-	if (!tdisk)
-		goto err_queue;
-
-	sprintf(tdisk->disk_name, "%s", create->tgtname);
-	tdisk->flags = GENHD_FL_EXT_DEVT;
-	tdisk->major = 0;
-	tdisk->first_minor = 0;
-	tdisk->fops = &gen_fops;
-	tdisk->queue = tqueue;
-
-	targetdata = tt->init(tgt_dev, tdisk);
-	if (IS_ERR(targetdata))
-		goto err_init;
-
-	tdisk->private_data = targetdata;
-	tqueue->queuedata = targetdata;
-
-	blk_queue_max_hw_sectors(tqueue, 8 * dev->ops->max_phys_sect);
-
-	set_capacity(tdisk, tt->capacity(targetdata));
-	add_disk(tdisk);
-
-	t->type = tt;
-	t->disk = tdisk;
-	t->dev = tgt_dev;
-
-	mutex_lock(&gn->lock);
-	list_add_tail(&t->list, &gn->targets);
-	mutex_unlock(&gn->lock);
-
-	return 0;
-err_init:
-	put_disk(tdisk);
-err_queue:
-	blk_cleanup_queue(tqueue);
-err_dev:
-	kfree(tgt_dev);
-err_reserve:
-	gen_release_luns_err(dev, s->lun_begin, s->lun_end);
-err_t:
-	kfree(t);
-	return -ENOMEM;
-}
-
-static void __gen_remove_target(struct nvm_target *t)
-{
-	struct nvm_tgt_type *tt = t->type;
-	struct gendisk *tdisk = t->disk;
-	struct request_queue *q = tdisk->queue;
-
-	del_gendisk(tdisk);
-	blk_cleanup_queue(q);
-
-	if (tt->exit)
-		tt->exit(tdisk->private_data);
-
-	gen_remove_tgt_dev(t->dev);
-	put_disk(tdisk);
-
-	list_del(&t->list);
-	kfree(t);
-}
-
-/**
- * gen_remove_tgt - Removes a target from the media manager
- * @dev:	device
- * @remove:	ioctl structure with target name to remove.
- *
- * Returns:
- * 0: on success
- * 1: on not found
- * <0: on error
- */
-static int gen_remove_tgt(struct nvm_dev *dev, struct nvm_ioctl_remove *remove)
-{
-	struct gen_dev *gn = dev->mp;
-	struct nvm_target *t;
-
-	if (!gn)
-		return 1;
-
-	mutex_lock(&gn->lock);
-	t = gen_find_target(gn, remove->tgtname);
-	if (!t) {
-		mutex_unlock(&gn->lock);
-		return 1;
-	}
-	__gen_remove_target(t);
-	mutex_unlock(&gn->lock);
-
-	return 0;
-}
-
-static int gen_get_area(struct nvm_dev *dev, sector_t *lba, sector_t len)
-{
-	struct nvm_geo *geo = &dev->geo;
-	struct gen_dev *gn = dev->mp;
-	struct gen_area *area, *prev, *next;
-	sector_t begin = 0;
-	sector_t max_sectors = (geo->sec_size * dev->total_secs) >> 9;
-
-	if (len > max_sectors)
-		return -EINVAL;
-
-	area = kmalloc(sizeof(struct gen_area), GFP_KERNEL);
-	if (!area)
-		return -ENOMEM;
-
-	prev = NULL;
-
-	spin_lock(&dev->lock);
-	list_for_each_entry(next, &gn->area_list, list) {
-		if (begin + len > next->begin) {
-			begin = next->end;
-			prev = next;
-			continue;
-		}
-		break;
-	}
-
-	if ((begin + len) > max_sectors) {
-		spin_unlock(&dev->lock);
-		kfree(area);
-		return -EINVAL;
-	}
-
-	area->begin = *lba = begin;
-	area->end = begin + len;
-
-	if (prev) /* insert into sorted order */
-		list_add(&area->list, &prev->list);
-	else
-		list_add(&area->list, &gn->area_list);
-	spin_unlock(&dev->lock);
-
-	return 0;
-}
-
-static void gen_put_area(struct nvm_dev *dev, sector_t begin)
-{
-	struct gen_dev *gn = dev->mp;
-	struct gen_area *area;
-
-	spin_lock(&dev->lock);
-	list_for_each_entry(area, &gn->area_list, list) {
-		if (area->begin != begin)
-			continue;
-
-		list_del(&area->list);
-		spin_unlock(&dev->lock);
-		kfree(area);
-		return;
-	}
-	spin_unlock(&dev->lock);
-}
-
-static void gen_free(struct nvm_dev *dev)
-{
-	kfree(dev->mp);
-	kfree(dev->rmap);
-	dev->mp = NULL;
-}
-
-static int gen_register(struct nvm_dev *dev)
-{
-	struct gen_dev *gn;
-	struct gen_dev_map *dev_rmap;
-	int i, j;
-
-	if (!try_module_get(THIS_MODULE))
-		return -ENODEV;
-
-	gn = kzalloc(sizeof(struct gen_dev), GFP_KERNEL);
-	if (!gn)
-		goto err_gn;
-
-	dev_rmap = kmalloc(sizeof(struct gen_dev_map), GFP_KERNEL);
-	if (!dev_rmap)
-		goto err_rmap;
-
-	dev_rmap->chnls = kcalloc(dev->geo.nr_chnls, sizeof(struct gen_ch_map),
-								GFP_KERNEL);
-	if (!dev_rmap->chnls)
-		goto err_chnls;
-
-	for (i = 0; i < dev->geo.nr_chnls; i++) {
-		struct gen_ch_map *ch_rmap;
-		int *lun_roffs;
-		int luns_in_chnl = dev->geo.luns_per_chnl;
-
-		ch_rmap = &dev_rmap->chnls[i];
-
-		ch_rmap->ch_off = -1;
-		ch_rmap->nr_luns = luns_in_chnl;
-
-		lun_roffs = kcalloc(luns_in_chnl, sizeof(int), GFP_KERNEL);
-		if (!lun_roffs)
-			goto err_ch;
-
-		for (j = 0; j < luns_in_chnl; j++)
-			lun_roffs[j] = -1;
-
-		ch_rmap->lun_offs = lun_roffs;
-	}
-
-	gn->dev = dev;
-	gn->nr_luns = dev->geo.nr_luns;
-	INIT_LIST_HEAD(&gn->area_list);
-	mutex_init(&gn->lock);
-	INIT_LIST_HEAD(&gn->targets);
-	dev->mp = gn;
-	dev->rmap = dev_rmap;
-
-	return 1;
-err_ch:
-	while (--i >= 0)
-		kfree(dev_rmap->chnls[i].lun_offs);
-err_chnls:
-	kfree(dev_rmap);
-err_rmap:
-	gen_free(dev);
-err_gn:
-	module_put(THIS_MODULE);
-	return -ENOMEM;
-}
-
-static void gen_unregister(struct nvm_dev *dev)
-{
-	struct gen_dev *gn = dev->mp;
-	struct nvm_target *t, *tmp;
-
-	mutex_lock(&gn->lock);
-	list_for_each_entry_safe(t, tmp, &gn->targets, list) {
-		if (t->dev->parent != dev)
-			continue;
-		__gen_remove_target(t);
-	}
-	mutex_unlock(&gn->lock);
-
-	gen_free(dev);
-	module_put(THIS_MODULE);
-}
-
-static int gen_map_to_dev(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p)
-{
-	struct gen_dev_map *dev_map = tgt_dev->map;
-	struct gen_ch_map *ch_map = &dev_map->chnls[p->g.ch];
-	int lun_off = ch_map->lun_offs[p->g.lun];
-	struct nvm_dev *dev = tgt_dev->parent;
-	struct gen_dev_map *dev_rmap = dev->rmap;
-	struct gen_ch_map *ch_rmap;
-	int lun_roff;
-
-	p->g.ch += ch_map->ch_off;
-	p->g.lun += lun_off;
-
-	ch_rmap = &dev_rmap->chnls[p->g.ch];
-	lun_roff = ch_rmap->lun_offs[p->g.lun];
-
-	if (unlikely(ch_rmap->ch_off < 0 || lun_roff < 0)) {
-		pr_err("nvm: corrupted device partition table\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int gen_map_to_tgt(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p)
-{
-	struct nvm_dev *dev = tgt_dev->parent;
-	struct gen_dev_map *dev_rmap = dev->rmap;
-	struct gen_ch_map *ch_rmap = &dev_rmap->chnls[p->g.ch];
-	int lun_roff = ch_rmap->lun_offs[p->g.lun];
-
-	p->g.ch -= ch_rmap->ch_off;
-	p->g.lun -= lun_roff;
-
-	return 0;
-}
-
-static int gen_trans_rq(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd,
-			int flag)
-{
-	gen_trans_fn *f;
-	int i;
-	int ret = 0;
-
-	f = (flag == TRANS_TGT_TO_DEV) ? gen_map_to_dev : gen_map_to_tgt;
-
-	if (rqd->nr_ppas == 1)
-		return f(tgt_dev, &rqd->ppa_addr);
-
-	for (i = 0; i < rqd->nr_ppas; i++) {
-		ret = f(tgt_dev, &rqd->ppa_list[i]);
-		if (ret)
-			goto out;
-	}
-
-out:
-	return ret;
-}
-
-static void gen_end_io(struct nvm_rq *rqd)
-{
-	struct nvm_tgt_dev *tgt_dev = rqd->dev;
-	struct nvm_tgt_instance *ins = rqd->ins;
-
-	/* Convert address space */
-	if (tgt_dev)
-		gen_trans_rq(tgt_dev, rqd, TRANS_DEV_TO_TGT);
-
-	ins->tt->end_io(rqd);
-}
-
-static int gen_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
-{
-	struct nvm_dev *dev = tgt_dev->parent;
-
-	if (!dev->ops->submit_io)
-		return -ENODEV;
-
-	/* Convert address space */
-	gen_trans_rq(tgt_dev, rqd, TRANS_TGT_TO_DEV);
-	nvm_generic_to_addr_mode(dev, rqd);
-
-	rqd->dev = tgt_dev;
-	rqd->end_io = gen_end_io;
-	return dev->ops->submit_io(dev, rqd);
-}
-
-static int gen_erase_blk(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p,
-			 int flags)
-{
-	/* Convert address space */
-	gen_map_to_dev(tgt_dev, p);
-
-	return nvm_erase_ppa(tgt_dev->parent, p, 1, flags);
-}
-
-static struct ppa_addr gen_trans_ppa(struct nvm_tgt_dev *tgt_dev,
-				     struct ppa_addr p, int direction)
-{
-	gen_trans_fn *f;
-	struct ppa_addr ppa = p;
-
-	f = (direction == TRANS_TGT_TO_DEV) ? gen_map_to_dev : gen_map_to_tgt;
-	f(tgt_dev, &ppa);
-
-	return ppa;
-}
-
-static void gen_part_to_tgt(struct nvm_dev *dev, sector_t *entries,
-			       int len)
-{
-	struct nvm_geo *geo = &dev->geo;
-	struct gen_dev_map *dev_rmap = dev->rmap;
-	u64 i;
-
-	for (i = 0; i < len; i++) {
-		struct gen_ch_map *ch_rmap;
-		int *lun_roffs;
-		struct ppa_addr gaddr;
-		u64 pba = le64_to_cpu(entries[i]);
-		int off;
-		u64 diff;
-
-		if (!pba)
-			continue;
-
-		gaddr = linear_to_generic_addr(geo, pba);
-		ch_rmap = &dev_rmap->chnls[gaddr.g.ch];
-		lun_roffs = ch_rmap->lun_offs;
-
-		off = gaddr.g.ch * geo->luns_per_chnl + gaddr.g.lun;
-
-		diff = ((ch_rmap->ch_off * geo->luns_per_chnl) +
-				(lun_roffs[gaddr.g.lun])) * geo->sec_per_lun;
-
-		entries[i] -= cpu_to_le64(diff);
-	}
-}
-
-static struct nvmm_type gen = {
-	.name			= "gennvm",
-	.version		= {0, 1, 0},
-
-	.register_mgr		= gen_register,
-	.unregister_mgr		= gen_unregister,
-
-	.create_tgt		= gen_create_tgt,
-	.remove_tgt		= gen_remove_tgt,
-
-	.submit_io		= gen_submit_io,
-	.erase_blk		= gen_erase_blk,
-
-	.get_area		= gen_get_area,
-	.put_area		= gen_put_area,
-
-	.trans_ppa		= gen_trans_ppa,
-	.part_to_tgt		= gen_part_to_tgt,
-};
-
-static int __init gen_module_init(void)
-{
-	return nvm_register_mgr(&gen);
-}
-
-static void gen_module_exit(void)
-{
-	nvm_unregister_mgr(&gen);
-}
-
-module_init(gen_module_init);
-module_exit(gen_module_exit);
-MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("General media manager for Open-Channel SSDs");
diff --git a/drivers/lightnvm/gennvm.h b/drivers/lightnvm/gennvm.h
deleted file mode 100644
index 6a4b3f368848..000000000000
--- a/drivers/lightnvm/gennvm.h
+++ /dev/null
@@ -1,62 +0,0 @@
-/*
- * Copyright: Matias Bjorling <mb@bjorling.me>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- */
-
-#ifndef GENNVM_H_
-#define GENNVM_H_
-
-#include <linux/module.h>
-#include <linux/vmalloc.h>
-
-#include <linux/lightnvm.h>
-
-struct gen_dev {
-	struct nvm_dev *dev;
-
-	int nr_luns;
-	struct list_head area_list;
-
-	struct mutex lock;
-	struct list_head targets;
-};
-
-/* Map between virtual and physical channel and lun */
-struct gen_ch_map {
-	int ch_off;
-	int nr_luns;
-	int *lun_offs;
-};
-
-struct gen_dev_map {
-	struct gen_ch_map *chnls;
-	int nr_chnls;
-};
-
-struct gen_area {
-	struct list_head list;
-	sector_t begin;
-	sector_t end;	/* end is excluded */
-};
-
-static inline void *ch_map_to_lun_offs(struct gen_ch_map *ch_map)
-{
-	return ch_map + 1;
-}
-
-typedef int (gen_trans_fn)(struct nvm_tgt_dev *, struct ppa_addr *);
-
-#define gen_for_each_lun(bm, lun, i) \
-		for ((i) = 0, lun = &(bm)->luns[0]; \
-			(i) < (bm)->nr_luns; (i)++, lun = &(bm)->luns[(i)])
-
-#endif /* GENNVM_H_ */
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index 9fb7de395915..e00b1d7b976f 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -779,7 +779,7 @@ static void rrpc_end_io_write(struct rrpc *rrpc, struct rrpc_rq *rrqd,
 
 static void rrpc_end_io(struct nvm_rq *rqd)
 {
-	struct rrpc *rrpc = container_of(rqd->ins, struct rrpc, instance);
+	struct rrpc *rrpc = rqd->private;
 	struct nvm_tgt_dev *dev = rrpc->dev;
 	struct rrpc_rq *rrqd = nvm_rq_to_pdu(rqd);
 	uint8_t npages = rqd->nr_ppas;
@@ -972,8 +972,9 @@ static int rrpc_submit_io(struct rrpc *rrpc, struct bio *bio,
 
 	bio_get(bio);
 	rqd->bio = bio;
-	rqd->ins = &rrpc->instance;
+	rqd->private = rrpc;
 	rqd->nr_ppas = nr_pages;
+	rqd->end_io = rrpc_end_io;
 	rrq->flags = flags;
 
 	err = nvm_submit_io(dev, rqd);
@@ -1532,7 +1533,6 @@ static void *rrpc_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk)
 	if (!rrpc)
 		return ERR_PTR(-ENOMEM);
 
-	rrpc->instance.tt = &tt_rrpc;
 	rrpc->dev = dev;
 	rrpc->disk = tdisk;
 
@@ -1611,7 +1611,6 @@ static struct nvm_tgt_type tt_rrpc = {
 
 	.make_rq	= rrpc_make_rq,
 	.capacity	= rrpc_capacity,
-	.end_io		= rrpc_end_io,
 
 	.init		= rrpc_init,
 	.exit		= rrpc_exit,
diff --git a/drivers/lightnvm/rrpc.h b/drivers/lightnvm/rrpc.h
index 94e4d73116b2..fdb6ff902903 100644
--- a/drivers/lightnvm/rrpc.h
+++ b/drivers/lightnvm/rrpc.h
@@ -102,9 +102,6 @@ struct rrpc_lun {
 };
 
 struct rrpc {
-	/* instance must be kept in top to resolve rrpc in unprep */
-	struct nvm_tgt_instance instance;
-
 	struct nvm_tgt_dev *dev;
 	struct gendisk *disk;
 
diff --git a/drivers/lightnvm/sysblk.c b/drivers/lightnvm/sysblk.c
deleted file mode 100644
index 12002bf4efc2..000000000000
--- a/drivers/lightnvm/sysblk.c
+++ /dev/null
@@ -1,733 +0,0 @@
-/*
- * Copyright (C) 2015 Matias Bjorling. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; see the file COPYING.  If not, write to
- * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
- * USA.
- *
- */
-
-#include <linux/lightnvm.h>
-
-#define MAX_SYSBLKS 3	/* remember to update mapping scheme on change */
-#define MAX_BLKS_PR_SYSBLK 2 /* 2 blks with 256 pages and 3000 erases
-			      * enables ~1.5M updates per sysblk unit
-			      */
-
-struct sysblk_scan {
-	/* A row is a collection of flash blocks for a system block. */
-	int nr_rows;
-	int row;
-	int act_blk[MAX_SYSBLKS];
-
-	int nr_ppas;
-	struct ppa_addr ppas[MAX_SYSBLKS * MAX_BLKS_PR_SYSBLK];/* all sysblks */
-};
-
-static inline int scan_ppa_idx(int row, int blkid)
-{
-	return (row * MAX_BLKS_PR_SYSBLK) + blkid;
-}
-
-static void nvm_sysblk_to_cpu(struct nvm_sb_info *info,
-			      struct nvm_system_block *sb)
-{
-	info->seqnr = be32_to_cpu(sb->seqnr);
-	info->erase_cnt = be32_to_cpu(sb->erase_cnt);
-	info->version = be16_to_cpu(sb->version);
-	strncpy(info->mmtype, sb->mmtype, NVM_MMTYPE_LEN);
-	info->fs_ppa.ppa = be64_to_cpu(sb->fs_ppa);
-}
-
-static void nvm_cpu_to_sysblk(struct nvm_system_block *sb,
-			      struct nvm_sb_info *info)
-{
-	sb->magic = cpu_to_be32(NVM_SYSBLK_MAGIC);
-	sb->seqnr = cpu_to_be32(info->seqnr);
-	sb->erase_cnt = cpu_to_be32(info->erase_cnt);
-	sb->version = cpu_to_be16(info->version);
-	strncpy(sb->mmtype, info->mmtype, NVM_MMTYPE_LEN);
-	sb->fs_ppa = cpu_to_be64(info->fs_ppa.ppa);
-}
-
-static int nvm_setup_sysblks(struct nvm_dev *dev, struct ppa_addr *sysblk_ppas)
-{
-	struct nvm_geo *geo = &dev->geo;
-	int nr_rows = min_t(int, MAX_SYSBLKS, geo->nr_chnls);
-	int i;
-
-	for (i = 0; i < nr_rows; i++)
-		sysblk_ppas[i].ppa = 0;
-
-	/* if possible, place sysblk at first channel, middle channel and last
-	 * channel of the device. If not, create only one or two sys blocks
-	 */
-	switch (geo->nr_chnls) {
-	case 2:
-		sysblk_ppas[1].g.ch = 1;
-		/* fall-through */
-	case 1:
-		sysblk_ppas[0].g.ch = 0;
-		break;
-	default:
-		sysblk_ppas[0].g.ch = 0;
-		sysblk_ppas[1].g.ch = geo->nr_chnls / 2;
-		sysblk_ppas[2].g.ch = geo->nr_chnls - 1;
-		break;
-	}
-
-	return nr_rows;
-}
-
-static void nvm_setup_sysblk_scan(struct nvm_dev *dev, struct sysblk_scan *s,
-						struct ppa_addr *sysblk_ppas)
-{
-	memset(s, 0, sizeof(struct sysblk_scan));
-	s->nr_rows = nvm_setup_sysblks(dev, sysblk_ppas);
-}
-
-static int sysblk_get_free_blks(struct nvm_dev *dev, struct ppa_addr ppa,
-					u8 *blks, int nr_blks,
-					struct sysblk_scan *s)
-{
-	struct ppa_addr *sppa;
-	int i, blkid = 0;
-
-	nr_blks = nvm_bb_tbl_fold(dev, blks, nr_blks);
-	if (nr_blks < 0)
-		return nr_blks;
-
-	for (i = 0; i < nr_blks; i++) {
-		if (blks[i] == NVM_BLK_T_HOST)
-			return -EEXIST;
-
-		if (blks[i] != NVM_BLK_T_FREE)
-			continue;
-
-		sppa = &s->ppas[scan_ppa_idx(s->row, blkid)];
-		sppa->g.ch = ppa.g.ch;
-		sppa->g.lun = ppa.g.lun;
-		sppa->g.blk = i;
-		s->nr_ppas++;
-		blkid++;
-
-		pr_debug("nvm: use (%u %u %u) as sysblk\n",
-					sppa->g.ch, sppa->g.lun, sppa->g.blk);
-		if (blkid > MAX_BLKS_PR_SYSBLK - 1)
-			return 0;
-	}
-
-	pr_err("nvm: sysblk failed get sysblk\n");
-	return -EINVAL;
-}
-
-static int sysblk_get_host_blks(struct nvm_dev *dev, struct ppa_addr ppa,
-					u8 *blks, int nr_blks,
-					struct sysblk_scan *s)
-{
-	int i, nr_sysblk = 0;
-
-	nr_blks = nvm_bb_tbl_fold(dev, blks, nr_blks);
-	if (nr_blks < 0)
-		return nr_blks;
-
-	for (i = 0; i < nr_blks; i++) {
-		if (blks[i] != NVM_BLK_T_HOST)
-			continue;
-
-		if (s->nr_ppas == MAX_BLKS_PR_SYSBLK * MAX_SYSBLKS) {
-			pr_err("nvm: too many host blks\n");
-			return -EINVAL;
-		}
-
-		ppa.g.blk = i;
-
-		s->ppas[scan_ppa_idx(s->row, nr_sysblk)] = ppa;
-		s->nr_ppas++;
-		nr_sysblk++;
-	}
-
-	return 0;
-}
-
-static int nvm_get_all_sysblks(struct nvm_dev *dev, struct sysblk_scan *s,
-				struct ppa_addr *ppas, int get_free)
-{
-	struct nvm_geo *geo = &dev->geo;
-	int i, nr_blks, ret = 0;
-	u8 *blks;
-
-	s->nr_ppas = 0;
-	nr_blks = geo->blks_per_lun * geo->plane_mode;
-
-	blks = kmalloc(nr_blks, GFP_KERNEL);
-	if (!blks)
-		return -ENOMEM;
-
-	for (i = 0; i < s->nr_rows; i++) {
-		s->row = i;
-
-		ret = nvm_get_bb_tbl(dev, ppas[i], blks);
-		if (ret) {
-			pr_err("nvm: failed bb tbl for ppa (%u %u)\n",
-							ppas[i].g.ch,
-							ppas[i].g.blk);
-			goto err_get;
-		}
-
-		if (get_free)
-			ret = sysblk_get_free_blks(dev, ppas[i], blks, nr_blks,
-									s);
-		else
-			ret = sysblk_get_host_blks(dev, ppas[i], blks, nr_blks,
-									s);
-
-		if (ret)
-			goto err_get;
-	}
-
-err_get:
-	kfree(blks);
-	return ret;
-}
-
-/*
- * scans a block for latest sysblk.
- * Returns:
- *	0 - newer sysblk not found. PPA is updated to latest page.
- *	1 - newer sysblk found and stored in *cur. PPA is updated to
- *	    next valid page.
- *	<0- error.
- */
-static int nvm_scan_block(struct nvm_dev *dev, struct ppa_addr *ppa,
-						struct nvm_system_block *sblk)
-{
-	struct nvm_geo *geo = &dev->geo;
-	struct nvm_system_block *cur;
-	int pg, ret, found = 0;
-
-	/* the full buffer for a flash page is allocated. Only the first of it
-	 * contains the system block information
-	 */
-	cur = kmalloc(geo->pfpg_size, GFP_KERNEL);
-	if (!cur)
-		return -ENOMEM;
-
-	/* perform linear scan through the block */
-	for (pg = 0; pg < dev->lps_per_blk; pg++) {
-		ppa->g.pg = ppa_to_slc(dev, pg);
-
-		ret = nvm_submit_ppa(dev, ppa, 1, NVM_OP_PREAD, NVM_IO_SLC_MODE,
-							cur, geo->pfpg_size);
-		if (ret) {
-			if (ret == NVM_RSP_ERR_EMPTYPAGE) {
-				pr_debug("nvm: sysblk scan empty ppa (%u %u %u %u)\n",
-							ppa->g.ch,
-							ppa->g.lun,
-							ppa->g.blk,
-							ppa->g.pg);
-				break;
-			}
-			pr_err("nvm: read failed (%x) for ppa (%u %u %u %u)",
-							ret,
-							ppa->g.ch,
-							ppa->g.lun,
-							ppa->g.blk,
-							ppa->g.pg);
-			break; /* if we can't read a page, continue to the
-				* next blk
-				*/
-		}
-
-		if (be32_to_cpu(cur->magic) != NVM_SYSBLK_MAGIC) {
-			pr_debug("nvm: scan break for ppa (%u %u %u %u)\n",
-							ppa->g.ch,
-							ppa->g.lun,
-							ppa->g.blk,
-							ppa->g.pg);
-			break; /* last valid page already found */
-		}
-
-		if (be32_to_cpu(cur->seqnr) < be32_to_cpu(sblk->seqnr))
-			continue;
-
-		memcpy(sblk, cur, sizeof(struct nvm_system_block));
-		found = 1;
-	}
-
-	kfree(cur);
-
-	return found;
-}
-
-static int nvm_sysblk_set_bb_tbl(struct nvm_dev *dev, struct sysblk_scan *s,
-								int type)
-{
-	return nvm_set_bb_tbl(dev, s->ppas, s->nr_ppas, type);
-}
-
-static int nvm_write_and_verify(struct nvm_dev *dev, struct nvm_sb_info *info,
-							struct sysblk_scan *s)
-{
-	struct nvm_geo *geo = &dev->geo;
-	struct nvm_system_block nvmsb;
-	void *buf;
-	int i, sect, ret = 0;
-	struct ppa_addr *ppas;
-
-	nvm_cpu_to_sysblk(&nvmsb, info);
-
-	buf = kzalloc(geo->pfpg_size, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-	memcpy(buf, &nvmsb, sizeof(struct nvm_system_block));
-
-	ppas = kcalloc(geo->sec_per_pg, sizeof(struct ppa_addr), GFP_KERNEL);
-	if (!ppas) {
-		ret = -ENOMEM;
-		goto err;
-	}
-
-	/* Write and verify */
-	for (i = 0; i < s->nr_rows; i++) {
-		ppas[0] = s->ppas[scan_ppa_idx(i, s->act_blk[i])];
-
-		pr_debug("nvm: writing sysblk to ppa (%u %u %u %u)\n",
-							ppas[0].g.ch,
-							ppas[0].g.lun,
-							ppas[0].g.blk,
-							ppas[0].g.pg);
-
-		/* Expand to all sectors within a flash page */
-		if (geo->sec_per_pg > 1) {
-			for (sect = 1; sect < geo->sec_per_pg; sect++) {
-				ppas[sect].ppa = ppas[0].ppa;
-				ppas[sect].g.sec = sect;
-			}
-		}
-
-		ret = nvm_submit_ppa(dev, ppas, geo->sec_per_pg, NVM_OP_PWRITE,
-					NVM_IO_SLC_MODE, buf, geo->pfpg_size);
-		if (ret) {
-			pr_err("nvm: sysblk failed program (%u %u %u)\n",
-							ppas[0].g.ch,
-							ppas[0].g.lun,
-							ppas[0].g.blk);
-			break;
-		}
-
-		ret = nvm_submit_ppa(dev, ppas, geo->sec_per_pg, NVM_OP_PREAD,
-					NVM_IO_SLC_MODE, buf, geo->pfpg_size);
-		if (ret) {
-			pr_err("nvm: sysblk failed read (%u %u %u)\n",
-							ppas[0].g.ch,
-							ppas[0].g.lun,
-							ppas[0].g.blk);
-			break;
-		}
-
-		if (memcmp(buf, &nvmsb, sizeof(struct nvm_system_block))) {
-			pr_err("nvm: sysblk failed verify (%u %u %u)\n",
-							ppas[0].g.ch,
-							ppas[0].g.lun,
-							ppas[0].g.blk);
-			ret = -EINVAL;
-			break;
-		}
-	}
-
-	kfree(ppas);
-err:
-	kfree(buf);
-
-	return ret;
-}
-
-static int nvm_prepare_new_sysblks(struct nvm_dev *dev, struct sysblk_scan *s)
-{
-	int i, ret;
-	unsigned long nxt_blk;
-	struct ppa_addr *ppa;
-
-	for (i = 0; i < s->nr_rows; i++) {
-		nxt_blk = (s->act_blk[i] + 1) % MAX_BLKS_PR_SYSBLK;
-		ppa = &s->ppas[scan_ppa_idx(i, nxt_blk)];
-		ppa->g.pg = ppa_to_slc(dev, 0);
-
-		ret = nvm_erase_ppa(dev, ppa, 1, 0);
-		if (ret)
-			return ret;
-
-		s->act_blk[i] = nxt_blk;
-	}
-
-	return 0;
-}
-
-int nvm_get_sysblock(struct nvm_dev *dev, struct nvm_sb_info *info)
-{
-	struct ppa_addr sysblk_ppas[MAX_SYSBLKS];
-	struct sysblk_scan s;
-	struct nvm_system_block *cur;
-	int i, j, found = 0;
-	int ret = -ENOMEM;
-
-	/*
-	 * 1. setup sysblk locations
-	 * 2. get bad block list
-	 * 3. filter on host-specific (type 3)
-	 * 4. iterate through all and find the highest seq nr.
-	 * 5. return superblock information
-	 */
-
-	if (!dev->ops->get_bb_tbl)
-		return -EINVAL;
-
-	nvm_setup_sysblk_scan(dev, &s, sysblk_ppas);
-
-	mutex_lock(&dev->mlock);
-	ret = nvm_get_all_sysblks(dev, &s, sysblk_ppas, 0);
-	if (ret)
-		goto err_sysblk;
-
-	/* no sysblocks initialized */
-	if (!s.nr_ppas)
-		goto err_sysblk;
-
-	cur = kzalloc(sizeof(struct nvm_system_block), GFP_KERNEL);
-	if (!cur)
-		goto err_sysblk;
-
-	/* find the latest block across all sysblocks */
-	for (i = 0; i < s.nr_rows; i++) {
-		for (j = 0; j < MAX_BLKS_PR_SYSBLK; j++) {
-			struct ppa_addr ppa = s.ppas[scan_ppa_idx(i, j)];
-
-			ret = nvm_scan_block(dev, &ppa, cur);
-			if (ret > 0)
-				found = 1;
-			else if (ret < 0)
-				break;
-		}
-	}
-
-	nvm_sysblk_to_cpu(info, cur);
-
-	kfree(cur);
-err_sysblk:
-	mutex_unlock(&dev->mlock);
-
-	if (found)
-		return 1;
-	return ret;
-}
-
-int nvm_update_sysblock(struct nvm_dev *dev, struct nvm_sb_info *new)
-{
-	/* 1. for each latest superblock
-	 * 2. if room
-	 *    a. write new flash page entry with the updated information
-	 * 3. if no room
-	 *    a. find next available block on lun (linear search)
-	 *       if none, continue to next lun
-	 *       if none at all, report error. also report that it wasn't
-	 *       possible to write to all superblocks.
-	 *    c. write data to block.
-	 */
-	struct ppa_addr sysblk_ppas[MAX_SYSBLKS];
-	struct sysblk_scan s;
-	struct nvm_system_block *cur;
-	int i, j, ppaidx, found = 0;
-	int ret = -ENOMEM;
-
-	if (!dev->ops->get_bb_tbl)
-		return -EINVAL;
-
-	nvm_setup_sysblk_scan(dev, &s, sysblk_ppas);
-
-	mutex_lock(&dev->mlock);
-	ret = nvm_get_all_sysblks(dev, &s, sysblk_ppas, 0);
-	if (ret)
-		goto err_sysblk;
-
-	cur = kzalloc(sizeof(struct nvm_system_block), GFP_KERNEL);
-	if (!cur)
-		goto err_sysblk;
-
-	/* Get the latest sysblk for each sysblk row */
-	for (i = 0; i < s.nr_rows; i++) {
-		found = 0;
-		for (j = 0; j < MAX_BLKS_PR_SYSBLK; j++) {
-			ppaidx = scan_ppa_idx(i, j);
-			ret = nvm_scan_block(dev, &s.ppas[ppaidx], cur);
-			if (ret > 0) {
-				s.act_blk[i] = j;
-				found = 1;
-			} else if (ret < 0)
-				break;
-		}
-	}
-
-	if (!found) {
-		pr_err("nvm: no valid sysblks found to update\n");
-		ret = -EINVAL;
-		goto err_cur;
-	}
-
-	/*
-	 * All sysblocks found. Check that they have same page id in their flash
-	 * blocks
-	 */
-	for (i = 1; i < s.nr_rows; i++) {
-		struct ppa_addr l = s.ppas[scan_ppa_idx(0, s.act_blk[0])];
-		struct ppa_addr r = s.ppas[scan_ppa_idx(i, s.act_blk[i])];
-
-		if (l.g.pg != r.g.pg) {
-			pr_err("nvm: sysblks not on same page. Previous update failed.\n");
-			ret = -EINVAL;
-			goto err_cur;
-		}
-	}
-
-	/*
-	 * Check that there haven't been another update to the seqnr since we
-	 * began
-	 */
-	if ((new->seqnr - 1) != be32_to_cpu(cur->seqnr)) {
-		pr_err("nvm: seq is not sequential\n");
-		ret = -EINVAL;
-		goto err_cur;
-	}
-
-	/*
-	 * When all pages in a block has been written, a new block is selected
-	 * and writing is performed on the new block.
-	 */
-	if (s.ppas[scan_ppa_idx(0, s.act_blk[0])].g.pg ==
-						dev->lps_per_blk - 1) {
-		ret = nvm_prepare_new_sysblks(dev, &s);
-		if (ret)
-			goto err_cur;
-	}
-
-	ret = nvm_write_and_verify(dev, new, &s);
-err_cur:
-	kfree(cur);
-err_sysblk:
-	mutex_unlock(&dev->mlock);
-
-	return ret;
-}
-
-int nvm_init_sysblock(struct nvm_dev *dev, struct nvm_sb_info *info)
-{
-	struct nvm_geo *geo = &dev->geo;
-	struct ppa_addr sysblk_ppas[MAX_SYSBLKS];
-	struct sysblk_scan s;
-	int ret;
-
-	/*
-	 * 1. select master blocks and select first available blks
-	 * 2. get bad block list
-	 * 3. mark MAX_SYSBLKS block as host-based device allocated.
-	 * 4. write and verify data to block
-	 */
-
-	if (!dev->ops->get_bb_tbl || !dev->ops->set_bb_tbl)
-		return -EINVAL;
-
-	if (!(geo->mccap & NVM_ID_CAP_SLC) || !dev->lps_per_blk) {
-		pr_err("nvm: memory does not support SLC access\n");
-		return -EINVAL;
-	}
-
-	/* Index all sysblocks and mark them as host-driven */
-	nvm_setup_sysblk_scan(dev, &s, sysblk_ppas);
-
-	mutex_lock(&dev->mlock);
-	ret = nvm_get_all_sysblks(dev, &s, sysblk_ppas, 1);
-	if (ret)
-		goto err_mark;
-
-	ret = nvm_sysblk_set_bb_tbl(dev, &s, NVM_BLK_T_HOST);
-	if (ret)
-		goto err_mark;
-
-	/* Write to the first block of each row */
-	ret = nvm_write_and_verify(dev, info, &s);
-err_mark:
-	mutex_unlock(&dev->mlock);
-	return ret;
-}
-
-static int factory_nblks(int nblks)
-{
-	/* Round up to nearest BITS_PER_LONG */
-	return (nblks + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1);
-}
-
-static unsigned int factory_blk_offset(struct nvm_geo *geo, struct ppa_addr ppa)
-{
-	int nblks = factory_nblks(geo->blks_per_lun);
-
-	return ((ppa.g.ch * geo->luns_per_chnl * nblks) + (ppa.g.lun * nblks)) /
-								BITS_PER_LONG;
-}
-
-static int nvm_factory_blks(struct nvm_dev *dev, struct ppa_addr ppa,
-					u8 *blks, int nr_blks,
-					unsigned long *blk_bitmap, int flags)
-{
-	int i, lunoff;
-
-	nr_blks = nvm_bb_tbl_fold(dev, blks, nr_blks);
-	if (nr_blks < 0)
-		return nr_blks;
-
-	lunoff = factory_blk_offset(&dev->geo, ppa);
-
-	/* non-set bits correspond to the block must be erased */
-	for (i = 0; i < nr_blks; i++) {
-		switch (blks[i]) {
-		case NVM_BLK_T_FREE:
-			if (flags & NVM_FACTORY_ERASE_ONLY_USER)
-				set_bit(i, &blk_bitmap[lunoff]);
-			break;
-		case NVM_BLK_T_HOST:
-			if (!(flags & NVM_FACTORY_RESET_HOST_BLKS))
-				set_bit(i, &blk_bitmap[lunoff]);
-			break;
-		case NVM_BLK_T_GRWN_BAD:
-			if (!(flags & NVM_FACTORY_RESET_GRWN_BBLKS))
-				set_bit(i, &blk_bitmap[lunoff]);
-			break;
-		default:
-			set_bit(i, &blk_bitmap[lunoff]);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-static int nvm_fact_get_blks(struct nvm_dev *dev, struct ppa_addr *erase_list,
-					int max_ppas, unsigned long *blk_bitmap)
-{
-	struct nvm_geo *geo = &dev->geo;
-	struct ppa_addr ppa;
-	int ch, lun, blkid, idx, done = 0, ppa_cnt = 0;
-	unsigned long *offset;
-
-	while (!done) {
-		done = 1;
-		nvm_for_each_lun_ppa(geo, ppa, ch, lun) {
-			idx = factory_blk_offset(geo, ppa);
-			offset = &blk_bitmap[idx];
-
-			blkid = find_first_zero_bit(offset, geo->blks_per_lun);
-			if (blkid >= geo->blks_per_lun)
-				continue;
-			set_bit(blkid, offset);
-
-			ppa.g.blk = blkid;
-			pr_debug("nvm: erase ppa (%u %u %u)\n",
-							ppa.g.ch,
-							ppa.g.lun,
-							ppa.g.blk);
-
-			erase_list[ppa_cnt] = ppa;
-			ppa_cnt++;
-			done = 0;
-
-			if (ppa_cnt == max_ppas)
-				return ppa_cnt;
-		}
-	}
-
-	return ppa_cnt;
-}
-
-static int nvm_fact_select_blks(struct nvm_dev *dev, unsigned long *blk_bitmap,
-								int flags)
-{
-	struct nvm_geo *geo = &dev->geo;
-	struct ppa_addr ppa;
-	int ch, lun, nr_blks, ret = 0;
-	u8 *blks;
-
-	nr_blks = geo->blks_per_lun * geo->plane_mode;
-	blks = kmalloc(nr_blks, GFP_KERNEL);
-	if (!blks)
-		return -ENOMEM;
-
-	nvm_for_each_lun_ppa(geo, ppa, ch, lun) {
-		ret = nvm_get_bb_tbl(dev, ppa, blks);
-		if (ret)
-			pr_err("nvm: failed bb tbl for ch%u lun%u\n",
-							ppa.g.ch, ppa.g.blk);
-
-		ret = nvm_factory_blks(dev, ppa, blks, nr_blks, blk_bitmap,
-									flags);
-		if (ret)
-			break;
-	}
-
-	kfree(blks);
-	return ret;
-}
-
-int nvm_dev_factory(struct nvm_dev *dev, int flags)
-{
-	struct nvm_geo *geo = &dev->geo;
-	struct ppa_addr *ppas;
-	int ppa_cnt, ret = -ENOMEM;
-	int max_ppas = dev->ops->max_phys_sect / geo->nr_planes;
-	struct ppa_addr sysblk_ppas[MAX_SYSBLKS];
-	struct sysblk_scan s;
-	unsigned long *blk_bitmap;
-
-	blk_bitmap = kzalloc(factory_nblks(geo->blks_per_lun) * geo->nr_luns,
-								GFP_KERNEL);
-	if (!blk_bitmap)
-		return ret;
-
-	ppas = kcalloc(max_ppas, sizeof(struct ppa_addr), GFP_KERNEL);
-	if (!ppas)
-		goto err_blks;
-
-	/* create list of blks to be erased */
-	ret = nvm_fact_select_blks(dev, blk_bitmap, flags);
-	if (ret)
-		goto err_ppas;
-
-	/* continue to erase until list of blks until empty */
-	while ((ppa_cnt =
-			nvm_fact_get_blks(dev, ppas, max_ppas, blk_bitmap)) > 0)
-		nvm_erase_ppa(dev, ppas, ppa_cnt, 0);
-
-	/* mark host reserved blocks free */
-	if (flags & NVM_FACTORY_RESET_HOST_BLKS) {
-		nvm_setup_sysblk_scan(dev, &s, sysblk_ppas);
-		mutex_lock(&dev->mlock);
-		ret = nvm_get_all_sysblks(dev, &s, sysblk_ppas, 0);
-		if (!ret)
-			ret = nvm_sysblk_set_bb_tbl(dev, &s, NVM_BLK_T_FREE);
-		mutex_unlock(&dev->mlock);
-	}
-err_ppas:
-	kfree(ppas);
-err_blks:
-	kfree(blk_bitmap);
-	return ret;
-}
-EXPORT_SYMBOL(nvm_dev_factory);
diff --git a/drivers/macintosh/rack-meter.c b/drivers/macintosh/rack-meter.c
index 775527135b93..e199fd6c71ce 100644
--- a/drivers/macintosh/rack-meter.c
+++ b/drivers/macintosh/rack-meter.c
@@ -52,8 +52,8 @@ struct rackmeter_dma {
 struct rackmeter_cpu {
 	struct delayed_work	sniffer;
 	struct rackmeter	*rm;
-	cputime64_t		prev_wall;
-	cputime64_t		prev_idle;
+	u64			prev_wall;
+	u64			prev_idle;
 	int			zero;
 } ____cacheline_aligned;
 
@@ -81,7 +81,7 @@ static int rackmeter_ignore_nice;
 /* This is copied from cpufreq_ondemand, maybe we should put it in
  * a common header somewhere
  */
-static inline cputime64_t get_cpu_idle_time(unsigned int cpu)
+static inline u64 get_cpu_idle_time(unsigned int cpu)
 {
 	u64 retval;
 
@@ -217,23 +217,23 @@ static void rackmeter_do_timer(struct work_struct *work)
 		container_of(work, struct rackmeter_cpu, sniffer.work);
 	struct rackmeter *rm = rcpu->rm;
 	unsigned int cpu = smp_processor_id();
-	cputime64_t cur_jiffies, total_idle_ticks;
-	unsigned int total_ticks, idle_ticks;
+	u64 cur_nsecs, total_idle_nsecs;
+	u64 total_nsecs, idle_nsecs;
 	int i, offset, load, cumm, pause;
 
-	cur_jiffies = jiffies64_to_cputime64(get_jiffies_64());
-	total_ticks = (unsigned int) (cur_jiffies - rcpu->prev_wall);
-	rcpu->prev_wall = cur_jiffies;
+	cur_nsecs = jiffies64_to_nsecs(get_jiffies_64());
+	total_nsecs = cur_nsecs - rcpu->prev_wall;
+	rcpu->prev_wall = cur_nsecs;
 
-	total_idle_ticks = get_cpu_idle_time(cpu);
-	idle_ticks = (unsigned int) (total_idle_ticks - rcpu->prev_idle);
-	idle_ticks = min(idle_ticks, total_ticks);
-	rcpu->prev_idle = total_idle_ticks;
+	total_idle_nsecs = get_cpu_idle_time(cpu);
+	idle_nsecs = total_idle_nsecs - rcpu->prev_idle;
+	idle_nsecs = min(idle_nsecs, total_nsecs);
+	rcpu->prev_idle = total_idle_nsecs;
 
 	/* We do a very dumb calculation to update the LEDs for now,
 	 * we'll do better once we have actual PWM implemented
 	 */
-	load = (9 * (total_ticks - idle_ticks)) / total_ticks;
+	load = div64_u64(9 * (total_nsecs - idle_nsecs), total_nsecs);
 
 	offset = cpu << 3;
 	cumm = 0;
@@ -278,7 +278,7 @@ static void rackmeter_init_cpu_sniffer(struct rackmeter *rm)
 			continue;
 		rcpu = &rm->cpu[cpu];
 		rcpu->prev_idle = get_cpu_idle_time(cpu);
-		rcpu->prev_wall = jiffies64_to_cputime64(get_jiffies_64());
+		rcpu->prev_wall = jiffies64_to_nsecs(get_jiffies_64());
 		schedule_delayed_work_on(cpu, &rm->cpu[cpu].sniffer,
 					 msecs_to_jiffies(CPU_SAMPLING_RATE));
 	}
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 76d20875503c..709c9cc34369 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -666,7 +666,7 @@ static inline struct search *search_alloc(struct bio *bio,
 	s->iop.write_prio	= 0;
 	s->iop.error		= 0;
 	s->iop.flags		= 0;
-	s->iop.flush_journal	= (bio->bi_opf & (REQ_PREFLUSH|REQ_FUA)) != 0;
+	s->iop.flush_journal	= op_is_flush(bio->bi_opf);
 	s->iop.wq		= bcache_wq;
 
 	return s;
@@ -1009,7 +1009,7 @@ static int cached_dev_congested(void *data, int bits)
 	struct request_queue *q = bdev_get_queue(dc->bdev);
 	int ret = 0;
 
-	if (bdi_congested(&q->backing_dev_info, bits))
+	if (bdi_congested(q->backing_dev_info, bits))
 		return 1;
 
 	if (cached_dev_get(dc)) {
@@ -1018,7 +1018,7 @@ static int cached_dev_congested(void *data, int bits)
 
 		for_each_cache(ca, d->c, i) {
 			q = bdev_get_queue(ca->bdev);
-			ret |= bdi_congested(&q->backing_dev_info, bits);
+			ret |= bdi_congested(q->backing_dev_info, bits);
 		}
 
 		cached_dev_put(dc);
@@ -1032,7 +1032,7 @@ void bch_cached_dev_request_init(struct cached_dev *dc)
 	struct gendisk *g = dc->disk.disk;
 
 	g->queue->make_request_fn		= cached_dev_make_request;
-	g->queue->backing_dev_info.congested_fn = cached_dev_congested;
+	g->queue->backing_dev_info->congested_fn = cached_dev_congested;
 	dc->disk.cache_miss			= cached_dev_cache_miss;
 	dc->disk.ioctl				= cached_dev_ioctl;
 }
@@ -1125,7 +1125,7 @@ static int flash_dev_congested(void *data, int bits)
 
 	for_each_cache(ca, d->c, i) {
 		q = bdev_get_queue(ca->bdev);
-		ret |= bdi_congested(&q->backing_dev_info, bits);
+		ret |= bdi_congested(q->backing_dev_info, bits);
 	}
 
 	return ret;
@@ -1136,7 +1136,7 @@ void bch_flash_dev_request_init(struct bcache_device *d)
 	struct gendisk *g = d->disk;
 
 	g->queue->make_request_fn		= flash_dev_make_request;
-	g->queue->backing_dev_info.congested_fn = flash_dev_congested;
+	g->queue->backing_dev_info->congested_fn = flash_dev_congested;
 	d->cache_miss				= flash_dev_cache_miss;
 	d->ioctl				= flash_dev_ioctl;
 }
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 3a19cbc8b230..85e3f21c2514 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -807,7 +807,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	blk_queue_make_request(q, NULL);
 	d->disk->queue			= q;
 	q->queuedata			= d;
-	q->backing_dev_info.congested_data = d;
+	q->backing_dev_info->congested_data = d;
 	q->limits.max_hw_sectors	= UINT_MAX;
 	q->limits.max_sectors		= UINT_MAX;
 	q->limits.max_segment_size	= UINT_MAX;
@@ -1132,9 +1132,9 @@ static int cached_dev_init(struct cached_dev *dc, unsigned block_size)
 	set_capacity(dc->disk.disk,
 		     dc->bdev->bd_part->nr_sects - dc->sb.data_offset);
 
-	dc->disk.disk->queue->backing_dev_info.ra_pages =
-		max(dc->disk.disk->queue->backing_dev_info.ra_pages,
-		    q->backing_dev_info.ra_pages);
+	dc->disk.disk->queue->backing_dev_info->ra_pages =
+		max(dc->disk.disk->queue->backing_dev_info->ra_pages,
+		    q->backing_dev_info->ra_pages);
 
 	bch_cached_dev_request_init(dc);
 	bch_cached_dev_writeback_init(dc);
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 84d2f0e4c754..d36d427a9efb 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -794,7 +794,7 @@ static void __wait_for_free_buffer(struct dm_bufio_client *c)
 	DECLARE_WAITQUEUE(wait, current);
 
 	add_wait_queue(&c->free_buffer_wait, &wait);
-	set_task_state(current, TASK_UNINTERRUPTIBLE);
+	set_current_state(TASK_UNINTERRUPTIBLE);
 	dm_bufio_unlock(c);
 
 	io_schedule();
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 5813d2a7eefe..9c689b34e6e7 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -788,8 +788,7 @@ static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio)
 	struct per_bio_data *pb = get_per_bio_data(bio, pb_data_size);
 
 	spin_lock_irqsave(&cache->lock, flags);
-	if (cache->need_tick_bio &&
-	    !(bio->bi_opf & (REQ_FUA | REQ_PREFLUSH)) &&
+	if (cache->need_tick_bio && !op_is_flush(bio->bi_opf) &&
 	    bio_op(bio) != REQ_OP_DISCARD) {
 		pb->tick = true;
 		cache->need_tick_bio = false;
@@ -829,11 +828,6 @@ static dm_oblock_t get_bio_block(struct cache *cache, struct bio *bio)
 	return to_oblock(block_nr);
 }
 
-static int bio_triggers_commit(struct cache *cache, struct bio *bio)
-{
-	return bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
-}
-
 /*
  * You must increment the deferred set whilst the prison cell is held.  To
  * encourage this, we ask for 'cell' to be passed in.
@@ -885,7 +879,7 @@ static void issue(struct cache *cache, struct bio *bio)
 {
 	unsigned long flags;
 
-	if (!bio_triggers_commit(cache, bio)) {
+	if (!op_is_flush(bio->bi_opf)) {
 		accounted_request(cache, bio);
 		return;
 	}
@@ -1070,8 +1064,7 @@ static void dec_io_migrations(struct cache *cache)
 
 static bool discard_or_flush(struct bio *bio)
 {
-	return bio_op(bio) == REQ_OP_DISCARD ||
-	       bio->bi_opf & (REQ_PREFLUSH | REQ_FUA);
+	return bio_op(bio) == REQ_OP_DISCARD || op_is_flush(bio->bi_opf);
 }
 
 static void __cell_defer(struct cache *cache, struct dm_bio_prison_cell *cell)
@@ -2292,7 +2285,7 @@ static void do_waker(struct work_struct *ws)
 static int is_congested(struct dm_dev *dev, int bdi_bits)
 {
 	struct request_queue *q = bdev_get_queue(dev->bdev);
-	return bdi_congested(&q->backing_dev_info, bdi_bits);
+	return bdi_congested(q->backing_dev_info, bdi_bits);
 }
 
 static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 40ceba1fe8be..136fda3ff9e5 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -92,7 +92,6 @@ struct mapped_device {
 	 * io objects are allocated from here.
 	 */
 	mempool_t *io_pool;
-	mempool_t *rq_pool;
 
 	struct bio_set *bs;
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 7c6c57216bf2..1cb2ca9dfae3 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1210,14 +1210,14 @@ continue_locked:
 		spin_unlock_irq(&cc->write_thread_wait.lock);
 
 		if (unlikely(kthread_should_stop())) {
-			set_task_state(current, TASK_RUNNING);
+			set_current_state(TASK_RUNNING);
 			remove_wait_queue(&cc->write_thread_wait, &wait);
 			break;
 		}
 
 		schedule();
 
-		set_task_state(current, TASK_RUNNING);
+		set_current_state(TASK_RUNNING);
 		spin_lock_irq(&cc->write_thread_wait.lock);
 		__remove_wait_queue(&cc->write_thread_wait, &wait);
 		goto continue_locked;
@@ -1534,18 +1534,18 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 		return PTR_ERR(key);
 	}
 
-	rcu_read_lock();
+	down_read(&key->sem);
 
 	ukp = user_key_payload(key);
 	if (!ukp) {
-		rcu_read_unlock();
+		up_read(&key->sem);
 		key_put(key);
 		kzfree(new_key_string);
 		return -EKEYREVOKED;
 	}
 
 	if (cc->key_size != ukp->datalen) {
-		rcu_read_unlock();
+		up_read(&key->sem);
 		key_put(key);
 		kzfree(new_key_string);
 		return -EINVAL;
@@ -1553,7 +1553,7 @@ static int crypt_set_keyring_key(struct crypt_config *cc, const char *key_string
 
 	memcpy(cc->key, ukp->data, cc->key_size);
 
-	rcu_read_unlock();
+	up_read(&key->sem);
 	key_put(key);
 
 	/* clear the flag since following operations may invalidate previously valid key */
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index bf2b2676cb8a..9fab33b113c4 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1379,7 +1379,7 @@ static void stop_worker(struct era *era)
 static int dev_is_congested(struct dm_dev *dev, int bdi_bits)
 {
 	struct request_queue *q = bdev_get_queue(dev->bdev);
-	return bdi_congested(&q->backing_dev_info, bdi_bits);
+	return bdi_congested(q->backing_dev_info, bdi_bits);
 }
 
 static int era_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 6400cffb986d..7f223dbed49f 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -92,12 +92,6 @@ struct multipath {
 
 	unsigned queue_mode;
 
-	/*
-	 * We must use a mempool of dm_mpath_io structs so that we
-	 * can resubmit bios on error.
-	 */
-	mempool_t *mpio_pool;
-
 	struct mutex work_mutex;
 	struct work_struct trigger_event;
 
@@ -115,8 +109,6 @@ struct dm_mpath_io {
 
 typedef int (*action_fn) (struct pgpath *pgpath);
 
-static struct kmem_cache *_mpio_cache;
-
 static struct workqueue_struct *kmultipathd, *kmpath_handlerd;
 static void trigger_event(struct work_struct *work);
 static void activate_path(struct work_struct *work);
@@ -209,7 +201,6 @@ static struct multipath *alloc_multipath(struct dm_target *ti)
 		init_waitqueue_head(&m->pg_init_wait);
 		mutex_init(&m->work_mutex);
 
-		m->mpio_pool = NULL;
 		m->queue_mode = DM_TYPE_NONE;
 
 		m->ti = ti;
@@ -229,16 +220,7 @@ static int alloc_multipath_stage2(struct dm_target *ti, struct multipath *m)
 			m->queue_mode = DM_TYPE_MQ_REQUEST_BASED;
 		else
 			m->queue_mode = DM_TYPE_REQUEST_BASED;
-	}
-
-	if (m->queue_mode == DM_TYPE_REQUEST_BASED) {
-		unsigned min_ios = dm_get_reserved_rq_based_ios();
-
-		m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
-		if (!m->mpio_pool)
-			return -ENOMEM;
-	}
-	else if (m->queue_mode == DM_TYPE_BIO_BASED) {
+	} else if (m->queue_mode == DM_TYPE_BIO_BASED) {
 		INIT_WORK(&m->process_queued_bios, process_queued_bios);
 		/*
 		 * bio-based doesn't support any direct scsi_dh management;
@@ -263,7 +245,6 @@ static void free_multipath(struct multipath *m)
 
 	kfree(m->hw_handler_name);
 	kfree(m->hw_handler_params);
-	mempool_destroy(m->mpio_pool);
 	kfree(m);
 }
 
@@ -272,38 +253,6 @@ static struct dm_mpath_io *get_mpio(union map_info *info)
 	return info->ptr;
 }
 
-static struct dm_mpath_io *set_mpio(struct multipath *m, union map_info *info)
-{
-	struct dm_mpath_io *mpio;
-
-	if (!m->mpio_pool) {
-		/* Use blk-mq pdu memory requested via per_io_data_size */
-		mpio = get_mpio(info);
-		memset(mpio, 0, sizeof(*mpio));
-		return mpio;
-	}
-
-	mpio = mempool_alloc(m->mpio_pool, GFP_ATOMIC);
-	if (!mpio)
-		return NULL;
-
-	memset(mpio, 0, sizeof(*mpio));
-	info->ptr = mpio;
-
-	return mpio;
-}
-
-static void clear_request_fn_mpio(struct multipath *m, union map_info *info)
-{
-	/* Only needed for non blk-mq (.request_fn) multipath */
-	if (m->mpio_pool) {
-		struct dm_mpath_io *mpio = info->ptr;
-
-		info->ptr = NULL;
-		mempool_free(mpio, m->mpio_pool);
-	}
-}
-
 static size_t multipath_per_bio_data_size(void)
 {
 	return sizeof(struct dm_mpath_io) + sizeof(struct dm_bio_details);
@@ -427,7 +376,7 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
 	unsigned long flags;
 	struct priority_group *pg;
 	struct pgpath *pgpath;
-	bool bypassed = true;
+	unsigned bypassed = 1;
 
 	if (!atomic_read(&m->nr_valid_paths)) {
 		clear_bit(MPATHF_QUEUE_IO, &m->flags);
@@ -466,7 +415,7 @@ check_current_pg:
 	 */
 	do {
 		list_for_each_entry(pg, &m->priority_groups, list) {
-			if (pg->bypassed == bypassed)
+			if (pg->bypassed == !!bypassed)
 				continue;
 			pgpath = choose_path_in_pg(m, pg, nr_bytes);
 			if (!IS_ERR_OR_NULL(pgpath)) {
@@ -530,16 +479,17 @@ static bool must_push_back_bio(struct multipath *m)
 /*
  * Map cloned requests (request-based multipath)
  */
-static int __multipath_map(struct dm_target *ti, struct request *clone,
-			   union map_info *map_context,
-			   struct request *rq, struct request **__clone)
+static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
+				   union map_info *map_context,
+				   struct request **__clone)
 {
 	struct multipath *m = ti->private;
 	int r = DM_MAPIO_REQUEUE;
-	size_t nr_bytes = clone ? blk_rq_bytes(clone) : blk_rq_bytes(rq);
+	size_t nr_bytes = blk_rq_bytes(rq);
 	struct pgpath *pgpath;
 	struct block_device *bdev;
-	struct dm_mpath_io *mpio;
+	struct dm_mpath_io *mpio = get_mpio(map_context);
+	struct request *clone;
 
 	/* Do we need to select a new pgpath? */
 	pgpath = lockless_dereference(m->current_pgpath);
@@ -556,42 +506,23 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 		return r;
 	}
 
-	mpio = set_mpio(m, map_context);
-	if (!mpio)
-		/* ENOMEM, requeue */
-		return r;
-
+	memset(mpio, 0, sizeof(*mpio));
 	mpio->pgpath = pgpath;
 	mpio->nr_bytes = nr_bytes;
 
 	bdev = pgpath->path.dev->bdev;
 
-	if (clone) {
-		/*
-		 * Old request-based interface: allocated clone is passed in.
-		 * Used by: .request_fn stacked on .request_fn path(s).
-		 */
-		clone->q = bdev_get_queue(bdev);
-		clone->rq_disk = bdev->bd_disk;
-		clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-	} else {
-		/*
-		 * blk-mq request-based interface; used by both:
-		 * .request_fn stacked on blk-mq path(s) and
-		 * blk-mq stacked on blk-mq path(s).
-		 */
-		clone = blk_mq_alloc_request(bdev_get_queue(bdev),
-					     rq_data_dir(rq), BLK_MQ_REQ_NOWAIT);
-		if (IS_ERR(clone)) {
-			/* EBUSY, ENODEV or EWOULDBLOCK: requeue */
-			clear_request_fn_mpio(m, map_context);
-			return r;
-		}
-		clone->bio = clone->biotail = NULL;
-		clone->rq_disk = bdev->bd_disk;
-		clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
-		*__clone = clone;
+	clone = blk_get_request(bdev_get_queue(bdev),
+			rq->cmd_flags | REQ_NOMERGE,
+			GFP_ATOMIC);
+	if (IS_ERR(clone)) {
+		/* EBUSY, ENODEV or EWOULDBLOCK: requeue */
+		return r;
 	}
+	clone->bio = clone->biotail = NULL;
+	clone->rq_disk = bdev->bd_disk;
+	clone->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+	*__clone = clone;
 
 	if (pgpath->pg->ps.type->start_io)
 		pgpath->pg->ps.type->start_io(&pgpath->pg->ps,
@@ -600,22 +531,9 @@ static int __multipath_map(struct dm_target *ti, struct request *clone,
 	return DM_MAPIO_REMAPPED;
 }
 
-static int multipath_map(struct dm_target *ti, struct request *clone,
-			 union map_info *map_context)
-{
-	return __multipath_map(ti, clone, map_context, NULL, NULL);
-}
-
-static int multipath_clone_and_map(struct dm_target *ti, struct request *rq,
-				   union map_info *map_context,
-				   struct request **clone)
-{
-	return __multipath_map(ti, NULL, map_context, rq, clone);
-}
-
 static void multipath_release_clone(struct request *clone)
 {
-	blk_mq_free_request(clone);
+	blk_put_request(clone);
 }
 
 /*
@@ -1187,7 +1105,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->num_write_same_bios = 1;
 	if (m->queue_mode == DM_TYPE_BIO_BASED)
 		ti->per_io_data_size = multipath_per_bio_data_size();
-	else if (m->queue_mode == DM_TYPE_MQ_REQUEST_BASED)
+	else
 		ti->per_io_data_size = sizeof(struct dm_mpath_io);
 
 	return 0;
@@ -1610,7 +1528,6 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 		if (ps->type->end_io)
 			ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
 	}
-	clear_request_fn_mpio(m, map_context);
 
 	return r;
 }
@@ -2060,7 +1977,6 @@ static struct target_type multipath_target = {
 	.module = THIS_MODULE,
 	.ctr = multipath_ctr,
 	.dtr = multipath_dtr,
-	.map_rq = multipath_map,
 	.clone_and_map_rq = multipath_clone_and_map,
 	.release_clone_rq = multipath_release_clone,
 	.rq_end_io = multipath_end_io,
@@ -2080,11 +1996,6 @@ static int __init dm_multipath_init(void)
 {
 	int r;
 
-	/* allocate a slab for the dm_mpath_ios */
-	_mpio_cache = KMEM_CACHE(dm_mpath_io, 0);
-	if (!_mpio_cache)
-		return -ENOMEM;
-
 	r = dm_register_target(&multipath_target);
 	if (r < 0) {
 		DMERR("request-based register failed %d", r);
@@ -2120,8 +2031,6 @@ bad_alloc_kmpath_handlerd:
 bad_alloc_kmultipathd:
 	dm_unregister_target(&multipath_target);
 bad_register_target:
-	kmem_cache_destroy(_mpio_cache);
-
 	return r;
 }
 
@@ -2131,7 +2040,6 @@ static void __exit dm_multipath_exit(void)
 	destroy_workqueue(kmultipathd);
 
 	dm_unregister_target(&multipath_target);
-	kmem_cache_destroy(_mpio_cache);
 }
 
 module_init(dm_multipath_init);
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 9d7275fb541a..67d76f21fecd 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -109,28 +109,6 @@ void dm_stop_queue(struct request_queue *q)
 		dm_mq_stop_queue(q);
 }
 
-static struct dm_rq_target_io *alloc_old_rq_tio(struct mapped_device *md,
-						gfp_t gfp_mask)
-{
-	return mempool_alloc(md->io_pool, gfp_mask);
-}
-
-static void free_old_rq_tio(struct dm_rq_target_io *tio)
-{
-	mempool_free(tio, tio->md->io_pool);
-}
-
-static struct request *alloc_old_clone_request(struct mapped_device *md,
-					       gfp_t gfp_mask)
-{
-	return mempool_alloc(md->rq_pool, gfp_mask);
-}
-
-static void free_old_clone_request(struct mapped_device *md, struct request *rq)
-{
-	mempool_free(rq, md->rq_pool);
-}
-
 /*
  * Partial completion handling for request-based dm
  */
@@ -185,7 +163,7 @@ static void end_clone_bio(struct bio *clone)
 
 static struct dm_rq_target_io *tio_from_request(struct request *rq)
 {
-	return (rq->q->mq_ops ? blk_mq_rq_to_pdu(rq) : rq->special);
+	return blk_mq_rq_to_pdu(rq);
 }
 
 static void rq_end_stats(struct mapped_device *md, struct request *orig)
@@ -233,31 +211,6 @@ static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
 	dm_put(md);
 }
 
-static void free_rq_clone(struct request *clone)
-{
-	struct dm_rq_target_io *tio = clone->end_io_data;
-	struct mapped_device *md = tio->md;
-
-	blk_rq_unprep_clone(clone);
-
-	/*
-	 * It is possible for a clone_old_rq() allocated clone to
-	 * get passed in -- it may not yet have a request_queue.
-	 * This is known to occur if the error target replaces
-	 * a multipath target that has a request_fn queue stacked
-	 * on blk-mq queue(s).
-	 */
-	if (clone->q && clone->q->mq_ops)
-		/* stacked on blk-mq queue(s) */
-		tio->ti->type->release_clone_rq(clone);
-	else if (!md->queue->mq_ops)
-		/* request_fn queue stacked on request_fn queue(s) */
-		free_old_clone_request(md, clone);
-
-	if (!md->queue->mq_ops)
-		free_old_rq_tio(tio);
-}
-
 /*
  * Complete the clone and the original request.
  * Must be called without clone's queue lock held,
@@ -270,20 +223,9 @@ static void dm_end_request(struct request *clone, int error)
 	struct mapped_device *md = tio->md;
 	struct request *rq = tio->orig;
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
-		rq->errors = clone->errors;
-		rq->resid_len = clone->resid_len;
-
-		if (rq->sense)
-			/*
-			 * We are using the sense buffer of the original
-			 * request.
-			 * So setting the length of the sense data is enough.
-			 */
-			rq->sense_len = clone->sense_len;
-	}
+	blk_rq_unprep_clone(clone);
+	tio->ti->type->release_clone_rq(clone);
 
-	free_rq_clone(clone);
 	rq_end_stats(md, rq);
 	if (!rq->q->mq_ops)
 		blk_end_request_all(rq, error);
@@ -292,22 +234,6 @@ static void dm_end_request(struct request *clone, int error)
 	rq_completed(md, rw, true);
 }
 
-static void dm_unprep_request(struct request *rq)
-{
-	struct dm_rq_target_io *tio = tio_from_request(rq);
-	struct request *clone = tio->clone;
-
-	if (!rq->q->mq_ops) {
-		rq->special = NULL;
-		rq->rq_flags &= ~RQF_DONTPREP;
-	}
-
-	if (clone)
-		free_rq_clone(clone);
-	else if (!tio->md->queue->mq_ops)
-		free_old_rq_tio(tio);
-}
-
 /*
  * Requeue the original request of a clone.
  */
@@ -346,7 +272,10 @@ static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_
 	int rw = rq_data_dir(rq);
 
 	rq_end_stats(md, rq);
-	dm_unprep_request(rq);
+	if (tio->clone) {
+		blk_rq_unprep_clone(tio->clone);
+		tio->ti->type->release_clone_rq(tio->clone);
+	}
 
 	if (!rq->q->mq_ops)
 		dm_old_requeue_request(rq);
@@ -401,14 +330,11 @@ static void dm_softirq_done(struct request *rq)
 	if (!clone) {
 		rq_end_stats(tio->md, rq);
 		rw = rq_data_dir(rq);
-		if (!rq->q->mq_ops) {
+		if (!rq->q->mq_ops)
 			blk_end_request_all(rq, tio->error);
-			rq_completed(tio->md, rw, false);
-			free_old_rq_tio(tio);
-		} else {
+		else
 			blk_mq_end_request(rq, tio->error);
-			rq_completed(tio->md, rw, false);
-		}
+		rq_completed(tio->md, rw, false);
 		return;
 	}
 
@@ -452,16 +378,6 @@ static void end_clone_request(struct request *clone, int error)
 {
 	struct dm_rq_target_io *tio = clone->end_io_data;
 
-	if (!clone->q->mq_ops) {
-		/*
-		 * For just cleaning up the information of the queue in which
-		 * the clone was dispatched.
-		 * The clone is *NOT* freed actually here because it is alloced
-		 * from dm own mempool (RQF_ALLOCED isn't set).
-		 */
-		__blk_put_request(clone->q, clone);
-	}
-
 	/*
 	 * Actual request completion is done in a softirq context which doesn't
 	 * hold the clone's queue lock.  Otherwise, deadlock could occur because:
@@ -511,9 +427,6 @@ static int setup_clone(struct request *clone, struct request *rq,
 	if (r)
 		return r;
 
-	clone->cmd = rq->cmd;
-	clone->cmd_len = rq->cmd_len;
-	clone->sense = rq->sense;
 	clone->end_io = end_clone_request;
 	clone->end_io_data = tio;
 
@@ -522,28 +435,6 @@ static int setup_clone(struct request *clone, struct request *rq,
 	return 0;
 }
 
-static struct request *clone_old_rq(struct request *rq, struct mapped_device *md,
-				    struct dm_rq_target_io *tio, gfp_t gfp_mask)
-{
-	/*
-	 * Create clone for use with .request_fn request_queue
-	 */
-	struct request *clone;
-
-	clone = alloc_old_clone_request(md, gfp_mask);
-	if (!clone)
-		return NULL;
-
-	blk_rq_init(NULL, clone);
-	if (setup_clone(clone, rq, tio, gfp_mask)) {
-		/* -ENOMEM */
-		free_old_clone_request(md, clone);
-		return NULL;
-	}
-
-	return clone;
-}
-
 static void map_tio_request(struct kthread_work *work);
 
 static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
@@ -565,60 +456,6 @@ static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
 		kthread_init_work(&tio->work, map_tio_request);
 }
 
-static struct dm_rq_target_io *dm_old_prep_tio(struct request *rq,
-					       struct mapped_device *md,
-					       gfp_t gfp_mask)
-{
-	struct dm_rq_target_io *tio;
-	int srcu_idx;
-	struct dm_table *table;
-
-	tio = alloc_old_rq_tio(md, gfp_mask);
-	if (!tio)
-		return NULL;
-
-	init_tio(tio, rq, md);
-
-	table = dm_get_live_table(md, &srcu_idx);
-	/*
-	 * Must clone a request if this .request_fn DM device
-	 * is stacked on .request_fn device(s).
-	 */
-	if (!dm_table_all_blk_mq_devices(table)) {
-		if (!clone_old_rq(rq, md, tio, gfp_mask)) {
-			dm_put_live_table(md, srcu_idx);
-			free_old_rq_tio(tio);
-			return NULL;
-		}
-	}
-	dm_put_live_table(md, srcu_idx);
-
-	return tio;
-}
-
-/*
- * Called with the queue lock held.
- */
-static int dm_old_prep_fn(struct request_queue *q, struct request *rq)
-{
-	struct mapped_device *md = q->queuedata;
-	struct dm_rq_target_io *tio;
-
-	if (unlikely(rq->special)) {
-		DMWARN("Already has something in rq->special.");
-		return BLKPREP_KILL;
-	}
-
-	tio = dm_old_prep_tio(rq, md, GFP_ATOMIC);
-	if (!tio)
-		return BLKPREP_DEFER;
-
-	rq->special = tio;
-	rq->rq_flags |= RQF_DONTPREP;
-
-	return BLKPREP_OK;
-}
-
 /*
  * Returns:
  * DM_MAPIO_*       : the request has been processed as indicated
@@ -633,31 +470,18 @@ static int map_request(struct dm_rq_target_io *tio)
 	struct request *rq = tio->orig;
 	struct request *clone = NULL;
 
-	if (tio->clone) {
-		clone = tio->clone;
-		r = ti->type->map_rq(ti, clone, &tio->info);
-		if (r == DM_MAPIO_DELAY_REQUEUE)
-			return DM_MAPIO_REQUEUE; /* .request_fn requeue is always immediate */
-	} else {
-		r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
-		if (r < 0) {
-			/* The target wants to complete the I/O */
-			dm_kill_unmapped_request(rq, r);
-			return r;
-		}
-		if (r == DM_MAPIO_REMAPPED &&
-		    setup_clone(clone, rq, tio, GFP_ATOMIC)) {
-			/* -ENOMEM */
-			ti->type->release_clone_rq(clone);
-			return DM_MAPIO_REQUEUE;
-		}
-	}
-
+	r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
 	switch (r) {
 	case DM_MAPIO_SUBMITTED:
 		/* The target has taken the I/O to submit by itself later */
 		break;
 	case DM_MAPIO_REMAPPED:
+		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
+			/* -ENOMEM */
+			ti->type->release_clone_rq(clone);
+			return DM_MAPIO_REQUEUE;
+		}
+
 		/* The target has remapped the I/O so dispatch it */
 		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
 				     blk_rq_pos(rq));
@@ -716,6 +540,29 @@ static void dm_start_request(struct mapped_device *md, struct request *orig)
 	dm_get(md);
 }
 
+static int __dm_rq_init_rq(struct mapped_device *md, struct request *rq)
+{
+	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
+
+	/*
+	 * Must initialize md member of tio, otherwise it won't
+	 * be available in dm_mq_queue_rq.
+	 */
+	tio->md = md;
+
+	if (md->init_tio_pdu) {
+		/* target-specific per-io data is immediately after the tio */
+		tio->info.ptr = tio + 1;
+	}
+
+	return 0;
+}
+
+static int dm_rq_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
+{
+	return __dm_rq_init_rq(q->rq_alloc_data, rq);
+}
+
 static void map_tio_request(struct kthread_work *work)
 {
 	struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);
@@ -779,6 +626,10 @@ static void dm_old_request_fn(struct request_queue *q)
 		int srcu_idx;
 		struct dm_table *map = dm_get_live_table(md, &srcu_idx);
 
+		if (unlikely(!map)) {
+			dm_put_live_table(md, srcu_idx);
+			return;
+		}
 		ti = dm_table_find_target(map, pos);
 		dm_put_live_table(md, srcu_idx);
 	}
@@ -810,6 +661,7 @@ static void dm_old_request_fn(struct request_queue *q)
 		dm_start_request(md, rq);
 
 		tio = tio_from_request(rq);
+		init_tio(tio, rq, md);
 		/* Establish tio->ti before queuing work (map_tio_request) */
 		tio->ti = ti;
 		kthread_queue_work(&md->kworker, &tio->work);
@@ -820,10 +672,23 @@ static void dm_old_request_fn(struct request_queue *q)
 /*
  * Fully initialize a .request_fn request-based queue.
  */
-int dm_old_init_request_queue(struct mapped_device *md)
+int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t)
 {
+	struct dm_target *immutable_tgt;
+
 	/* Fully initialize the queue */
-	if (!blk_init_allocated_queue(md->queue, dm_old_request_fn, NULL))
+	md->queue->cmd_size = sizeof(struct dm_rq_target_io);
+	md->queue->rq_alloc_data = md;
+	md->queue->request_fn = dm_old_request_fn;
+	md->queue->init_rq_fn = dm_rq_init_rq;
+
+	immutable_tgt = dm_table_get_immutable_target(t);
+	if (immutable_tgt && immutable_tgt->per_io_data_size) {
+		/* any target-specific per-io data is immediately after the tio */
+		md->queue->cmd_size += immutable_tgt->per_io_data_size;
+		md->init_tio_pdu = true;
+	}
+	if (blk_init_allocated_queue(md->queue) < 0)
 		return -EINVAL;
 
 	/* disable dm_old_request_fn's merge heuristic by default */
@@ -831,7 +696,6 @@ int dm_old_init_request_queue(struct mapped_device *md)
 
 	dm_init_normal_md_queue(md);
 	blk_queue_softirq_done(md->queue, dm_softirq_done);
-	blk_queue_prep_rq(md->queue, dm_old_prep_fn);
 
 	/* Initialize the request-based DM worker thread */
 	kthread_init_worker(&md->kworker);
@@ -852,21 +716,7 @@ static int dm_mq_init_request(void *data, struct request *rq,
 		       unsigned int hctx_idx, unsigned int request_idx,
 		       unsigned int numa_node)
 {
-	struct mapped_device *md = data;
-	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
-
-	/*
-	 * Must initialize md member of tio, otherwise it won't
-	 * be available in dm_mq_queue_rq.
-	 */
-	tio->md = md;
-
-	if (md->init_tio_pdu) {
-		/* target-specific per-io data is immediately after the tio */
-		tio->info.ptr = tio + 1;
-	}
-
-	return 0;
+	return __dm_rq_init_rq(data, rq);
 }
 
 static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
diff --git a/drivers/md/dm-rq.h b/drivers/md/dm-rq.h
index 4da06cae7bad..f0020d21b95f 100644
--- a/drivers/md/dm-rq.h
+++ b/drivers/md/dm-rq.h
@@ -48,7 +48,7 @@ struct dm_rq_clone_bio_info {
 bool dm_use_blk_mq_default(void);
 bool dm_use_blk_mq(struct mapped_device *md);
 
-int dm_old_init_request_queue(struct mapped_device *md);
+int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t);
 int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t);
 void dm_mq_cleanup_mapped_device(struct mapped_device *md);
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 0a427de23ed2..3ad16d9c9d5a 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1750,7 +1750,7 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 		char b[BDEVNAME_SIZE];
 
 		if (likely(q))
-			r |= bdi_congested(&q->backing_dev_info, bdi_bits);
+			r |= bdi_congested(q->backing_dev_info, bdi_bits);
 		else
 			DMWARN_LIMIT("%s: any_congested: nonexistent device %s",
 				     dm_device_name(t->md),
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 710ae28fd618..43d3445b121d 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -131,12 +131,6 @@ static int io_err_map(struct dm_target *tt, struct bio *bio)
 	return -EIO;
 }
 
-static int io_err_map_rq(struct dm_target *ti, struct request *clone,
-			 union map_info *map_context)
-{
-	return -EIO;
-}
-
 static int io_err_clone_and_map_rq(struct dm_target *ti, struct request *rq,
 				   union map_info *map_context,
 				   struct request **clone)
@@ -161,7 +155,6 @@ static struct target_type error_target = {
 	.ctr  = io_err_ctr,
 	.dtr  = io_err_dtr,
 	.map  = io_err_map,
-	.map_rq = io_err_map_rq,
 	.clone_and_map_rq = io_err_clone_and_map_rq,
 	.release_clone_rq = io_err_release_clone_rq,
 	.direct_access = io_err_direct_access,
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index d1c05c12a9db..2b266a2b5035 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -699,7 +699,7 @@ static void remap_to_origin(struct thin_c *tc, struct bio *bio)
 
 static int bio_triggers_commit(struct thin_c *tc, struct bio *bio)
 {
-	return (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA)) &&
+	return op_is_flush(bio->bi_opf) &&
 		dm_thin_changed_this_transaction(tc->td);
 }
 
@@ -870,8 +870,7 @@ static void __inc_remap_and_issue_cell(void *context,
 	struct bio *bio;
 
 	while ((bio = bio_list_pop(&cell->bios))) {
-		if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) ||
-		    bio_op(bio) == REQ_OP_DISCARD)
+		if (op_is_flush(bio->bi_opf) || bio_op(bio) == REQ_OP_DISCARD)
 			bio_list_add(&info->defer_bios, bio);
 		else {
 			inc_all_io_entry(info->tc->pool, bio);
@@ -1716,9 +1715,8 @@ static void __remap_and_issue_shared_cell(void *context,
 	struct bio *bio;
 
 	while ((bio = bio_list_pop(&cell->bios))) {
-		if ((bio_data_dir(bio) == WRITE) ||
-		    (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) ||
-		     bio_op(bio) == REQ_OP_DISCARD))
+		if (bio_data_dir(bio) == WRITE || op_is_flush(bio->bi_opf) ||
+		    bio_op(bio) == REQ_OP_DISCARD)
 			bio_list_add(&info->defer_bios, bio);
 		else {
 			struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));;
@@ -2635,8 +2633,7 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_SUBMITTED;
 	}
 
-	if (bio->bi_opf & (REQ_PREFLUSH | REQ_FUA) ||
-	    bio_op(bio) == REQ_OP_DISCARD) {
+	if (op_is_flush(bio->bi_opf) || bio_op(bio) == REQ_OP_DISCARD) {
 		thin_defer_bio_with_throttle(tc, bio);
 		return DM_MAPIO_SUBMITTED;
 	}
@@ -2714,7 +2711,7 @@ static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
 		return 1;
 
 	q = bdev_get_queue(pt->data_dev->bdev);
-	return bdi_congested(&q->backing_dev_info, bdi_bits);
+	return bdi_congested(q->backing_dev_info, bdi_bits);
 }
 
 static void requeue_bios(struct pool *pool)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 0ff5469c03d2..9f37d7fc2786 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -91,7 +91,6 @@ static int dm_numa_node = DM_NUMA_NODE;
  */
 struct dm_md_mempools {
 	mempool_t *io_pool;
-	mempool_t *rq_pool;
 	struct bio_set *bs;
 };
 
@@ -466,13 +465,16 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 
 	if (r > 0) {
 		/*
-		 * Target determined this ioctl is being issued against
-		 * a logical partition of the parent bdev; so extra
-		 * validation is needed.
+		 * Target determined this ioctl is being issued against a
+		 * subset of the parent bdev; require extra privileges.
 		 */
-		r = scsi_verify_blk_ioctl(NULL, cmd);
-		if (r)
+		if (!capable(CAP_SYS_RAWIO)) {
+			DMWARN_LIMIT(
+	"%s: sending ioctl %x to DM device without required privilege.",
+				current->comm, cmd);
+			r = -ENOIOCTLCMD;
 			goto out;
+		}
 	}
 
 	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
@@ -1369,7 +1371,7 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 			 * With request-based DM we only need to check the
 			 * top-level queue for congestion.
 			 */
-			r = md->queue->backing_dev_info.wb.state & bdi_bits;
+			r = md->queue->backing_dev_info->wb.state & bdi_bits;
 		} else {
 			map = dm_get_live_table_fast(md);
 			if (map)
@@ -1452,7 +1454,7 @@ void dm_init_md_queue(struct mapped_device *md)
 	 * - must do so here (in alloc_dev callchain) before queue is used
 	 */
 	md->queue->queuedata = md;
-	md->queue->backing_dev_info.congested_data = md;
+	md->queue->backing_dev_info->congested_data = md;
 }
 
 void dm_init_normal_md_queue(struct mapped_device *md)
@@ -1463,7 +1465,7 @@ void dm_init_normal_md_queue(struct mapped_device *md)
 	/*
 	 * Initialize aspects of queue that aren't relevant for blk-mq
 	 */
-	md->queue->backing_dev_info.congested_fn = dm_any_congested;
+	md->queue->backing_dev_info->congested_fn = dm_any_congested;
 	blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
 }
 
@@ -1474,7 +1476,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	if (md->kworker_task)
 		kthread_stop(md->kworker_task);
 	mempool_destroy(md->io_pool);
-	mempool_destroy(md->rq_pool);
 	if (md->bs)
 		bioset_free(md->bs);
 
@@ -1650,12 +1651,10 @@ static void __bind_mempools(struct mapped_device *md, struct dm_table *t)
 		goto out;
 	}
 
-	BUG_ON(!p || md->io_pool || md->rq_pool || md->bs);
+	BUG_ON(!p || md->io_pool || md->bs);
 
 	md->io_pool = p->io_pool;
 	p->io_pool = NULL;
-	md->rq_pool = p->rq_pool;
-	p->rq_pool = NULL;
 	md->bs = p->bs;
 	p->bs = NULL;
 
@@ -1832,7 +1831,7 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 
 	switch (type) {
 	case DM_TYPE_REQUEST_BASED:
-		r = dm_old_init_request_queue(md);
+		r = dm_old_init_request_queue(md, t);
 		if (r) {
 			DMERR("Cannot initialize queue for request-based mapped device");
 			return r;
@@ -2548,7 +2547,6 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 					    unsigned integrity, unsigned per_io_data_size)
 {
 	struct dm_md_mempools *pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id);
-	struct kmem_cache *cachep = NULL;
 	unsigned int pool_size = 0;
 	unsigned int front_pad;
 
@@ -2558,20 +2556,16 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 	switch (type) {
 	case DM_TYPE_BIO_BASED:
 	case DM_TYPE_DAX_BIO_BASED:
-		cachep = _io_cache;
 		pool_size = dm_get_reserved_bio_based_ios();
 		front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
+	
+		pools->io_pool = mempool_create_slab_pool(pool_size, _io_cache);
+		if (!pools->io_pool)
+			goto out;
 		break;
 	case DM_TYPE_REQUEST_BASED:
-		cachep = _rq_tio_cache;
-		pool_size = dm_get_reserved_rq_based_ios();
-		pools->rq_pool = mempool_create_slab_pool(pool_size, _rq_cache);
-		if (!pools->rq_pool)
-			goto out;
-		/* fall through to setup remaining rq-based pools */
 	case DM_TYPE_MQ_REQUEST_BASED:
-		if (!pool_size)
-			pool_size = dm_get_reserved_rq_based_ios();
+		pool_size = dm_get_reserved_rq_based_ios();
 		front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
 		/* per_io_data_size is used for blk-mq pdu at queue allocation */
 		break;
@@ -2579,12 +2573,6 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned t
 		BUG();
 	}
 
-	if (cachep) {
-		pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
-		if (!pools->io_pool)
-			goto out;
-	}
-
 	pools->bs = bioset_create_nobvec(pool_size, front_pad);
 	if (!pools->bs)
 		goto out;
@@ -2606,7 +2594,6 @@ void dm_free_md_mempools(struct dm_md_mempools *pools)
 		return;
 
 	mempool_destroy(pools->io_pool);
-	mempool_destroy(pools->rq_pool);
 
 	if (pools->bs)
 		bioset_free(pools->bs);
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index f0aad08b9654..f298b01f7ab3 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -95,8 +95,7 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
 /*
  * To check whether the target type is request-based or not (bio-based).
  */
-#define dm_target_request_based(t) (((t)->type->map_rq != NULL) || \
-				    ((t)->type->clone_and_map_rq != NULL))
+#define dm_target_request_based(t) ((t)->type->clone_and_map_rq != NULL)
 
 /*
  * To check whether the target type is a hybrid (capable of being
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 5975c9915684..f1c7bbac31a5 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -62,7 +62,7 @@ static int linear_congested(struct mddev *mddev, int bits)
 
 	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
-		ret |= bdi_congested(&q->backing_dev_info, bits);
+		ret |= bdi_congested(q->backing_dev_info, bits);
 	}
 
 	return ret;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 82821ee0d57f..ba485dcf1064 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5291,6 +5291,11 @@ int md_run(struct mddev *mddev)
 	if (start_readonly && mddev->ro == 0)
 		mddev->ro = 2; /* read-only, but switch on first write */
 
+	/*
+	 * NOTE: some pers->run(), for example r5l_recovery_log(), wakes
+	 * up mddev->thread. It is important to initialize critical
+	 * resources for mddev->thread BEFORE calling pers->run().
+	 */
 	err = pers->run(mddev);
 	if (err)
 		pr_warn("md: pers->run() failed ...\n");
@@ -5341,8 +5346,8 @@ int md_run(struct mddev *mddev)
 			queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mddev->queue);
 		else
 			queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, mddev->queue);
-		mddev->queue->backing_dev_info.congested_data = mddev;
-		mddev->queue->backing_dev_info.congested_fn = md_congested;
+		mddev->queue->backing_dev_info->congested_data = mddev;
+		mddev->queue->backing_dev_info->congested_fn = md_congested;
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -5699,7 +5704,7 @@ static int do_md_stop(struct mddev *mddev, int mode,
 
 		__md_stop_writes(mddev);
 		__md_stop(mddev);
-		mddev->queue->backing_dev_info.congested_fn = NULL;
+		mddev->queue->backing_dev_info->congested_fn = NULL;
 
 		/* tell userspace to handle 'inactive' */
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index aa8c4e5c1ee2..d457afa672d5 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -169,7 +169,7 @@ static int multipath_congested(struct mddev *mddev, int bits)
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
 
-			ret |= bdi_congested(&q->backing_dev_info, bits);
+			ret |= bdi_congested(q->backing_dev_info, bits);
 			/* Just like multipath_map, we just check the
 			 * first available device
 			 */
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 8212f14214f1..0863905dee02 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -120,7 +120,7 @@ static int __check_holder(struct block_lock *lock)
 static void __wait(struct waiter *w)
 {
 	for (;;) {
-		set_task_state(current, TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE);
 
 		if (!w->task)
 			break;
@@ -128,7 +128,7 @@ static void __wait(struct waiter *w)
 		schedule();
 	}
 
-	set_task_state(current, TASK_RUNNING);
+	set_current_state(TASK_RUNNING);
 }
 
 static void __wake_waiter(struct waiter *w)
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 848365d474f3..d6585239bff2 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -41,7 +41,7 @@ static int raid0_congested(struct mddev *mddev, int bits)
 	for (i = 0; i < raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
 
-		ret |= bdi_congested(&q->backing_dev_info, bits);
+		ret |= bdi_congested(q->backing_dev_info, bits);
 	}
 	return ret;
 }
@@ -420,8 +420,8 @@ static int raid0_run(struct mddev *mddev)
 		 */
 		int stripe = mddev->raid_disks *
 			(mddev->chunk_sectors << 9) / PAGE_SIZE;
-		if (mddev->queue->backing_dev_info.ra_pages < 2* stripe)
-			mddev->queue->backing_dev_info.ra_pages = 2* stripe;
+		if (mddev->queue->backing_dev_info->ra_pages < 2* stripe)
+			mddev->queue->backing_dev_info->ra_pages = 2* stripe;
 	}
 
 	dump_zones(mddev);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 7b0f647bcccb..830ff2b20346 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -744,9 +744,9 @@ static int raid1_congested(struct mddev *mddev, int bits)
 			 * non-congested targets, it can be removed
 			 */
 			if ((bits & (1 << WB_async_congested)) || 1)
-				ret |= bdi_congested(&q->backing_dev_info, bits);
+				ret |= bdi_congested(q->backing_dev_info, bits);
 			else
-				ret &= bdi_congested(&q->backing_dev_info, bits);
+				ret &= bdi_congested(q->backing_dev_info, bits);
 		}
 	}
 	rcu_read_unlock();
@@ -1170,10 +1170,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	int i, disks;
 	struct bitmap *bitmap = mddev->bitmap;
 	unsigned long flags;
-	const int op = bio_op(bio);
-	const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
-	const unsigned long do_flush_fua = (bio->bi_opf &
-						(REQ_PREFLUSH | REQ_FUA));
 	struct md_rdev *blocked_rdev;
 	struct blk_plug_cb *cb;
 	struct raid1_plug_cb *plug = NULL;
@@ -1389,7 +1385,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				   conf->mirrors[i].rdev->data_offset);
 		mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
 		mbio->bi_end_io	= raid1_end_write_request;
-		bio_set_op_attrs(mbio, op, do_flush_fua | do_sync);
+		mbio->bi_opf = bio_op(bio) |
+			(bio->bi_opf & (REQ_SYNC | REQ_PREFLUSH | REQ_FUA));
 		if (test_bit(FailFast, &conf->mirrors[i].rdev->flags) &&
 		    !test_bit(WriteMostly, &conf->mirrors[i].rdev->flags) &&
 		    conf->raid_disks - mddev->degraded > 1)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 1920756828df..6bc5c2a85160 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -860,7 +860,7 @@ static int raid10_congested(struct mddev *mddev, int bits)
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
 
-			ret |= bdi_congested(&q->backing_dev_info, bits);
+			ret |= bdi_congested(q->backing_dev_info, bits);
 		}
 	}
 	rcu_read_unlock();
@@ -3841,8 +3841,8 @@ static int raid10_run(struct mddev *mddev)
 		 * maybe...
 		 */
 		stripe /= conf->geo.near_copies;
-		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+		if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
+			mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 	}
 
 	if (md_integrity_register(mddev))
@@ -4643,8 +4643,8 @@ static void end_reshape(struct r10conf *conf)
 		int stripe = conf->geo.raid_disks *
 			((conf->mddev->chunk_sectors << 9) / PAGE_SIZE);
 		stripe /= conf->geo.near_copies;
-		if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
-			conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+		if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
+			conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 	}
 	conf->fullsync = 0;
 }
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 0e8ed2c327b0..302dea3296ba 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -162,6 +162,8 @@ struct r5l_log {
 
 	/* to submit async io_units, to fulfill ordering of flush */
 	struct work_struct deferred_io_work;
+	/* to disable write back during in degraded mode */
+	struct work_struct disable_writeback_work;
 };
 
 /*
@@ -611,6 +613,21 @@ static void r5l_submit_io_async(struct work_struct *work)
 		r5l_do_submit_io(log, io);
 }
 
+static void r5c_disable_writeback_async(struct work_struct *work)
+{
+	struct r5l_log *log = container_of(work, struct r5l_log,
+					   disable_writeback_work);
+	struct mddev *mddev = log->rdev->mddev;
+
+	if (log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH)
+		return;
+	pr_info("md/raid:%s: Disabling writeback cache for degraded array.\n",
+		mdname(mddev));
+	mddev_suspend(mddev);
+	log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
+	mddev_resume(mddev);
+}
+
 static void r5l_submit_current_io(struct r5l_log *log)
 {
 	struct r5l_io_unit *io = log->current_io;
@@ -1393,8 +1410,6 @@ static void r5l_do_reclaim(struct r5l_log *log)
 	next_checkpoint = r5c_calculate_new_cp(conf);
 	spin_unlock_irq(&log->io_list_lock);
 
-	BUG_ON(reclaimable < 0);
-
 	if (reclaimable == 0 || !write_super)
 		return;
 
@@ -2062,7 +2077,7 @@ static int
 r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
 				       struct r5l_recovery_ctx *ctx)
 {
-	struct stripe_head *sh, *next;
+	struct stripe_head *sh;
 	struct mddev *mddev = log->rdev->mddev;
 	struct page *page;
 	sector_t next_checkpoint = MaxSector;
@@ -2076,7 +2091,7 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
 
 	WARN_ON(list_empty(&ctx->cached_list));
 
-	list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
+	list_for_each_entry(sh, &ctx->cached_list, lru) {
 		struct r5l_meta_block *mb;
 		int i;
 		int offset;
@@ -2126,14 +2141,39 @@ r5c_recovery_rewrite_data_only_stripes(struct r5l_log *log,
 		ctx->pos = write_pos;
 		ctx->seq += 1;
 		next_checkpoint = sh->log_start;
-		list_del_init(&sh->lru);
-		raid5_release_stripe(sh);
 	}
 	log->next_checkpoint = next_checkpoint;
 	__free_page(page);
 	return 0;
 }
 
+static void r5c_recovery_flush_data_only_stripes(struct r5l_log *log,
+						 struct r5l_recovery_ctx *ctx)
+{
+	struct mddev *mddev = log->rdev->mddev;
+	struct r5conf *conf = mddev->private;
+	struct stripe_head *sh, *next;
+
+	if (ctx->data_only_stripes == 0)
+		return;
+
+	log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_BACK;
+
+	list_for_each_entry_safe(sh, next, &ctx->cached_list, lru) {
+		r5c_make_stripe_write_out(sh);
+		set_bit(STRIPE_HANDLE, &sh->state);
+		list_del_init(&sh->lru);
+		raid5_release_stripe(sh);
+	}
+
+	md_wakeup_thread(conf->mddev->thread);
+	/* reuse conf->wait_for_quiescent in recovery */
+	wait_event(conf->wait_for_quiescent,
+		   atomic_read(&conf->active_stripes) == 0);
+
+	log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
+}
+
 static int r5l_recovery_log(struct r5l_log *log)
 {
 	struct mddev *mddev = log->rdev->mddev;
@@ -2160,32 +2200,31 @@ static int r5l_recovery_log(struct r5l_log *log)
 	pos = ctx.pos;
 	ctx.seq += 10000;
 
-	if (ctx.data_only_stripes == 0) {
-		log->next_checkpoint = ctx.pos;
-		r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++);
-		ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
-	}
 
 	if ((ctx.data_only_stripes == 0) && (ctx.data_parity_stripes == 0))
 		pr_debug("md/raid:%s: starting from clean shutdown\n",
 			 mdname(mddev));
-	else {
+	else
 		pr_debug("md/raid:%s: recovering %d data-only stripes and %d data-parity stripes\n",
 			 mdname(mddev), ctx.data_only_stripes,
 			 ctx.data_parity_stripes);
 
-		if (ctx.data_only_stripes > 0)
-			if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) {
-				pr_err("md/raid:%s: failed to rewrite stripes to journal\n",
-				       mdname(mddev));
-				return -EIO;
-			}
+	if (ctx.data_only_stripes == 0) {
+		log->next_checkpoint = ctx.pos;
+		r5l_log_write_empty_meta_block(log, ctx.pos, ctx.seq++);
+		ctx.pos = r5l_ring_add(log, ctx.pos, BLOCK_SECTORS);
+	} else if (r5c_recovery_rewrite_data_only_stripes(log, &ctx)) {
+		pr_err("md/raid:%s: failed to rewrite stripes to journal\n",
+		       mdname(mddev));
+		return -EIO;
 	}
 
 	log->log_start = ctx.pos;
 	log->seq = ctx.seq;
 	log->last_checkpoint = pos;
 	r5l_write_super(log, pos);
+
+	r5c_recovery_flush_data_only_stripes(log, &ctx);
 	return 0;
 }
 
@@ -2247,6 +2286,10 @@ static ssize_t r5c_journal_mode_store(struct mddev *mddev,
 	    val > R5C_JOURNAL_MODE_WRITE_BACK)
 		return -EINVAL;
 
+	if (raid5_calc_degraded(conf) > 0 &&
+	    val == R5C_JOURNAL_MODE_WRITE_BACK)
+		return -EINVAL;
+
 	mddev_suspend(mddev);
 	conf->log->r5c_journal_mode = val;
 	mddev_resume(mddev);
@@ -2301,6 +2344,16 @@ int r5c_try_caching_write(struct r5conf *conf,
 		set_bit(STRIPE_R5C_CACHING, &sh->state);
 	}
 
+	/*
+	 * When run in degraded mode, array is set to write-through mode.
+	 * This check helps drain pending write safely in the transition to
+	 * write-through mode.
+	 */
+	if (s->failed) {
+		r5c_make_stripe_write_out(sh);
+		return -EAGAIN;
+	}
+
 	for (i = disks; i--; ) {
 		dev = &sh->dev[i];
 		/* if non-overwrite, use writing-out phase */
@@ -2351,6 +2404,8 @@ void r5c_release_extra_page(struct stripe_head *sh)
 			struct page *p = sh->dev[i].orig_page;
 
 			sh->dev[i].orig_page = sh->dev[i].page;
+			clear_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags);
+
 			if (!using_disk_info_extra_page)
 				put_page(p);
 		}
@@ -2555,6 +2610,19 @@ ioerr:
 	return ret;
 }
 
+void r5c_update_on_rdev_error(struct mddev *mddev)
+{
+	struct r5conf *conf = mddev->private;
+	struct r5l_log *log = conf->log;
+
+	if (!log)
+		return;
+
+	if (raid5_calc_degraded(conf) > 0 &&
+	    conf->log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_BACK)
+		schedule_work(&log->disable_writeback_work);
+}
+
 int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 {
 	struct request_queue *q = bdev_get_queue(rdev->bdev);
@@ -2627,6 +2695,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)
 	spin_lock_init(&log->no_space_stripes_lock);
 
 	INIT_WORK(&log->deferred_io_work, r5l_submit_io_async);
+	INIT_WORK(&log->disable_writeback_work, r5c_disable_writeback_async);
 
 	log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH;
 	INIT_LIST_HEAD(&log->stripe_in_journal_list);
@@ -2659,6 +2728,7 @@ io_kc:
 
 void r5l_exit_log(struct r5l_log *log)
 {
+	flush_work(&log->disable_writeback_work);
 	md_unregister_thread(&log->reclaim_thread);
 	mempool_destroy(log->meta_pool);
 	bioset_free(log->bs);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 36c13e4be9c9..6214e699342c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -556,7 +556,7 @@ static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector,
  * of the two sections, and some non-in_sync devices may
  * be insync in the section most affected by failed devices.
  */
-static int calc_degraded(struct r5conf *conf)
+int raid5_calc_degraded(struct r5conf *conf)
 {
 	int degraded, degraded2;
 	int i;
@@ -619,7 +619,7 @@ static int has_failed(struct r5conf *conf)
 	if (conf->mddev->reshape_position == MaxSector)
 		return conf->mddev->degraded > conf->max_degraded;
 
-	degraded = calc_degraded(conf);
+	degraded = raid5_calc_degraded(conf);
 	if (degraded > conf->max_degraded)
 		return 1;
 	return 0;
@@ -1015,7 +1015,17 @@ again:
 
 			if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
 				WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
-			sh->dev[i].vec.bv_page = sh->dev[i].page;
+
+			if (!op_is_write(op) &&
+			    test_bit(R5_InJournal, &sh->dev[i].flags))
+				/*
+				 * issuing read for a page in journal, this
+				 * must be preparing for prexor in rmw; read
+				 * the data into orig_page
+				 */
+				sh->dev[i].vec.bv_page = sh->dev[i].orig_page;
+			else
+				sh->dev[i].vec.bv_page = sh->dev[i].page;
 			bi->bi_vcnt = 1;
 			bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
 			bi->bi_io_vec[0].bv_offset = 0;
@@ -2380,6 +2390,13 @@ static void raid5_end_read_request(struct bio * bi)
 		} else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
 			clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
 
+		if (test_bit(R5_InJournal, &sh->dev[i].flags))
+			/*
+			 * end read for a page in journal, this
+			 * must be preparing for prexor in rmw
+			 */
+			set_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags);
+
 		if (atomic_read(&rdev->read_errors))
 			atomic_set(&rdev->read_errors, 0);
 	} else {
@@ -2538,7 +2555,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
 
 	spin_lock_irqsave(&conf->device_lock, flags);
 	clear_bit(In_sync, &rdev->flags);
-	mddev->degraded = calc_degraded(conf);
+	mddev->degraded = raid5_calc_degraded(conf);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 
@@ -2552,6 +2569,7 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
 		bdevname(rdev->bdev, b),
 		mdname(mddev),
 		conf->raid_disks - mddev->degraded);
+	r5c_update_on_rdev_error(mddev);
 }
 
 /*
@@ -2880,6 +2898,30 @@ sector_t raid5_compute_blocknr(struct stripe_head *sh, int i, int previous)
 	return r_sector;
 }
 
+/*
+ * There are cases where we want handle_stripe_dirtying() and
+ * schedule_reconstruction() to delay towrite to some dev of a stripe.
+ *
+ * This function checks whether we want to delay the towrite. Specifically,
+ * we delay the towrite when:
+ *
+ *   1. degraded stripe has a non-overwrite to the missing dev, AND this
+ *      stripe has data in journal (for other devices).
+ *
+ *      In this case, when reading data for the non-overwrite dev, it is
+ *      necessary to handle complex rmw of write back cache (prexor with
+ *      orig_page, and xor with page). To keep read path simple, we would
+ *      like to flush data in journal to RAID disks first, so complex rmw
+ *      is handled in the write patch (handle_stripe_dirtying).
+ *
+ */
+static inline bool delay_towrite(struct r5dev *dev,
+				   struct stripe_head_state *s)
+{
+	return !test_bit(R5_OVERWRITE, &dev->flags) &&
+		!test_bit(R5_Insync, &dev->flags) && s->injournal;
+}
+
 static void
 schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
 			 int rcw, int expand)
@@ -2900,7 +2942,7 @@ schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
 
-			if (dev->towrite) {
+			if (dev->towrite && !delay_towrite(dev, s)) {
 				set_bit(R5_LOCKED, &dev->flags);
 				set_bit(R5_Wantdrain, &dev->flags);
 				if (!expand)
@@ -3295,13 +3337,6 @@ static int want_replace(struct stripe_head *sh, int disk_idx)
 	return rv;
 }
 
-/* fetch_block - checks the given member device to see if its data needs
- * to be read or computed to satisfy a request.
- *
- * Returns 1 when no more member devices need to be checked, otherwise returns
- * 0 to tell the loop in handle_stripe_fill to continue
- */
-
 static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 			   int disk_idx, int disks)
 {
@@ -3392,6 +3427,12 @@ static int need_this_block(struct stripe_head *sh, struct stripe_head_state *s,
 	return 0;
 }
 
+/* fetch_block - checks the given member device to see if its data needs
+ * to be read or computed to satisfy a request.
+ *
+ * Returns 1 when no more member devices need to be checked, otherwise returns
+ * 0 to tell the loop in handle_stripe_fill to continue
+ */
 static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
 		       int disk_idx, int disks)
 {
@@ -3478,10 +3519,26 @@ static void handle_stripe_fill(struct stripe_head *sh,
 	 * midst of changing due to a write
 	 */
 	if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
-	    !sh->reconstruct_state)
+	    !sh->reconstruct_state) {
+
+		/*
+		 * For degraded stripe with data in journal, do not handle
+		 * read requests yet, instead, flush the stripe to raid
+		 * disks first, this avoids handling complex rmw of write
+		 * back cache (prexor with orig_page, and then xor with
+		 * page) in the read path
+		 */
+		if (s->injournal && s->failed) {
+			if (test_bit(STRIPE_R5C_CACHING, &sh->state))
+				r5c_make_stripe_write_out(sh);
+			goto out;
+		}
+
 		for (i = disks; i--; )
 			if (fetch_block(sh, s, i, disks))
 				break;
+	}
+out:
 	set_bit(STRIPE_HANDLE, &sh->state);
 }
 
@@ -3594,6 +3651,21 @@ unhash:
 		break_stripe_batch_list(head_sh, STRIPE_EXPAND_SYNC_FLAGS);
 }
 
+/*
+ * For RMW in write back cache, we need extra page in prexor to store the
+ * old data. This page is stored in dev->orig_page.
+ *
+ * This function checks whether we have data for prexor. The exact logic
+ * is:
+ *       R5_UPTODATE && (!R5_InJournal || R5_OrigPageUPTDODATE)
+ */
+static inline bool uptodate_for_rmw(struct r5dev *dev)
+{
+	return (test_bit(R5_UPTODATE, &dev->flags)) &&
+		(!test_bit(R5_InJournal, &dev->flags) ||
+		 test_bit(R5_OrigPageUPTDODATE, &dev->flags));
+}
+
 static int handle_stripe_dirtying(struct r5conf *conf,
 				  struct stripe_head *sh,
 				  struct stripe_head_state *s,
@@ -3622,12 +3694,11 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 	} else for (i = disks; i--; ) {
 		/* would I have to read this buffer for read_modify_write */
 		struct r5dev *dev = &sh->dev[i];
-		if ((dev->towrite || i == sh->pd_idx || i == sh->qd_idx ||
+		if (((dev->towrite && !delay_towrite(dev, s)) ||
+		     i == sh->pd_idx || i == sh->qd_idx ||
 		     test_bit(R5_InJournal, &dev->flags)) &&
 		    !test_bit(R5_LOCKED, &dev->flags) &&
-		    !((test_bit(R5_UPTODATE, &dev->flags) &&
-		       (!test_bit(R5_InJournal, &dev->flags) ||
-			dev->page != dev->orig_page)) ||
+		    !(uptodate_for_rmw(dev) ||
 		      test_bit(R5_Wantcompute, &dev->flags))) {
 			if (test_bit(R5_Insync, &dev->flags))
 				rmw++;
@@ -3639,7 +3710,6 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 		    i != sh->pd_idx && i != sh->qd_idx &&
 		    !test_bit(R5_LOCKED, &dev->flags) &&
 		    !(test_bit(R5_UPTODATE, &dev->flags) ||
-		      test_bit(R5_InJournal, &dev->flags) ||
 		      test_bit(R5_Wantcompute, &dev->flags))) {
 			if (test_bit(R5_Insync, &dev->flags))
 				rcw++;
@@ -3689,13 +3759,11 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
-			if ((dev->towrite ||
+			if (((dev->towrite && !delay_towrite(dev, s)) ||
 			     i == sh->pd_idx || i == sh->qd_idx ||
 			     test_bit(R5_InJournal, &dev->flags)) &&
 			    !test_bit(R5_LOCKED, &dev->flags) &&
-			    !((test_bit(R5_UPTODATE, &dev->flags) &&
-			       (!test_bit(R5_InJournal, &dev->flags) ||
-				dev->page != dev->orig_page)) ||
+			    !(uptodate_for_rmw(dev) ||
 			      test_bit(R5_Wantcompute, &dev->flags)) &&
 			    test_bit(R5_Insync, &dev->flags)) {
 				if (test_bit(STRIPE_PREREAD_ACTIVE,
@@ -3722,7 +3790,6 @@ static int handle_stripe_dirtying(struct r5conf *conf,
 			    i != sh->pd_idx && i != sh->qd_idx &&
 			    !test_bit(R5_LOCKED, &dev->flags) &&
 			    !(test_bit(R5_UPTODATE, &dev->flags) ||
-			      test_bit(R5_InJournal, &dev->flags) ||
 			      test_bit(R5_Wantcompute, &dev->flags))) {
 				rcw++;
 				if (test_bit(R5_Insync, &dev->flags) &&
@@ -6264,10 +6331,10 @@ raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
 		mddev_suspend(mddev);
 		conf->skip_copy = new;
 		if (new)
-			mddev->queue->backing_dev_info.capabilities |=
+			mddev->queue->backing_dev_info->capabilities |=
 				BDI_CAP_STABLE_WRITES;
 		else
-			mddev->queue->backing_dev_info.capabilities &=
+			mddev->queue->backing_dev_info->capabilities &=
 				~BDI_CAP_STABLE_WRITES;
 		mddev_resume(mddev);
 	}
@@ -7025,7 +7092,7 @@ static int raid5_run(struct mddev *mddev)
 	/*
 	 * 0 for a fully functional array, 1 or 2 for a degraded array.
 	 */
-	mddev->degraded = calc_degraded(conf);
+	mddev->degraded = raid5_calc_degraded(conf);
 
 	if (has_failed(conf)) {
 		pr_crit("md/raid:%s: not enough operational devices (%d/%d failed)\n",
@@ -7086,8 +7153,8 @@ static int raid5_run(struct mddev *mddev)
 		int data_disks = conf->previous_raid_disks - conf->max_degraded;
 		int stripe = data_disks *
 			((mddev->chunk_sectors << 9) / PAGE_SIZE);
-		if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
-			mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+		if (mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
+			mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 
 		chunk_size = mddev->chunk_sectors << 9;
 		blk_queue_io_min(mddev->queue, chunk_size);
@@ -7272,7 +7339,7 @@ static int raid5_spare_active(struct mddev *mddev)
 		}
 	}
 	spin_lock_irqsave(&conf->device_lock, flags);
-	mddev->degraded = calc_degraded(conf);
+	mddev->degraded = raid5_calc_degraded(conf);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 	print_raid5_conf(conf);
 	return count;
@@ -7632,7 +7699,7 @@ static int raid5_start_reshape(struct mddev *mddev)
 		 * pre and post number of devices.
 		 */
 		spin_lock_irqsave(&conf->device_lock, flags);
-		mddev->degraded = calc_degraded(conf);
+		mddev->degraded = raid5_calc_degraded(conf);
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
 	mddev->raid_disks = conf->raid_disks;
@@ -7696,8 +7763,8 @@ static void end_reshape(struct r5conf *conf)
 			int data_disks = conf->raid_disks - conf->max_degraded;
 			int stripe = data_disks * ((conf->chunk_sectors << 9)
 						   / PAGE_SIZE);
-			if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
-				conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
+			if (conf->mddev->queue->backing_dev_info->ra_pages < 2 * stripe)
+				conf->mddev->queue->backing_dev_info->ra_pages = 2 * stripe;
 		}
 	}
 }
@@ -7720,7 +7787,7 @@ static void raid5_finish_reshape(struct mddev *mddev)
 		} else {
 			int d;
 			spin_lock_irq(&conf->device_lock);
-			mddev->degraded = calc_degraded(conf);
+			mddev->degraded = raid5_calc_degraded(conf);
 			spin_unlock_irq(&conf->device_lock);
 			for (d = conf->raid_disks ;
 			     d < conf->raid_disks - mddev->delta_disks;
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index ed8e1362ab36..1440fa26e296 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -322,6 +322,11 @@ enum r5dev_flags {
 			 * data and parity being written are in the journal
 			 * device
 			 */
+	R5_OrigPageUPTDODATE,	/* with write back cache, we read old data into
+				 * dev->orig_page for prexor. When this flag is
+				 * set, orig_page contains latest data in the
+				 * raid disk.
+				 */
 };
 
 /*
@@ -753,6 +758,7 @@ extern sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
 extern struct stripe_head *
 raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
 			int previous, int noblock, int noquiesce);
+extern int raid5_calc_degraded(struct r5conf *conf);
 extern int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev);
 extern void r5l_exit_log(struct r5l_log *log);
 extern int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh);
@@ -781,4 +787,5 @@ extern void r5c_flush_cache(struct r5conf *conf, int num);
 extern void r5c_check_stripe_cache_usage(struct r5conf *conf);
 extern void r5c_check_cached_full_stripe(struct r5conf *conf);
 extern struct md_sysfs_entry r5c_journal_mode;
+extern void r5c_update_on_rdev_error(struct mddev *mddev);
 #endif
diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index 0ea4efb3de66..ccda41c2c9e4 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -30,8 +30,9 @@
 
 #include "cec-priv.h"
 
-static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx);
-static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx);
+static void cec_fill_msg_report_features(struct cec_adapter *adap,
+					 struct cec_msg *msg,
+					 unsigned int la_idx);
 
 /*
  * 400 ms is the time it takes for one 16 byte message to be
@@ -288,10 +289,10 @@ static void cec_data_cancel(struct cec_data *data)
 
 	/* Mark it as an error */
 	data->msg.tx_ts = ktime_get_ns();
-	data->msg.tx_status = CEC_TX_STATUS_ERROR |
-			      CEC_TX_STATUS_MAX_RETRIES;
+	data->msg.tx_status |= CEC_TX_STATUS_ERROR |
+			       CEC_TX_STATUS_MAX_RETRIES;
+	data->msg.tx_error_cnt++;
 	data->attempts = 0;
-	data->msg.tx_error_cnt = 1;
 	/* Queue transmitted message for monitoring purposes */
 	cec_queue_msg_monitor(data->adap, &data->msg, 1);
 
@@ -611,8 +612,7 @@ int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg,
 	}
 	memset(msg->msg + msg->len, 0, sizeof(msg->msg) - msg->len);
 	if (msg->len == 1) {
-		if (cec_msg_initiator(msg) != 0xf ||
-		    cec_msg_destination(msg) == 0xf) {
+		if (cec_msg_destination(msg) == 0xf) {
 			dprintk(1, "cec_transmit_msg: invalid poll message\n");
 			return -EINVAL;
 		}
@@ -637,7 +637,7 @@ int cec_transmit_msg_fh(struct cec_adapter *adap, struct cec_msg *msg,
 		dprintk(1, "cec_transmit_msg: destination is the adapter itself\n");
 		return -EINVAL;
 	}
-	if (cec_msg_initiator(msg) != 0xf &&
+	if (msg->len > 1 && adap->is_configured &&
 	    !cec_has_log_addr(adap, cec_msg_initiator(msg))) {
 		dprintk(1, "cec_transmit_msg: initiator has unknown logical address %d\n",
 			cec_msg_initiator(msg));
@@ -851,7 +851,7 @@ static const u8 cec_msg_size[256] = {
 	[CEC_MSG_REQUEST_ARC_TERMINATION] = 2 | DIRECTED,
 	[CEC_MSG_TERMINATE_ARC] = 2 | DIRECTED,
 	[CEC_MSG_REQUEST_CURRENT_LATENCY] = 4 | BCAST,
-	[CEC_MSG_REPORT_CURRENT_LATENCY] = 7 | BCAST,
+	[CEC_MSG_REPORT_CURRENT_LATENCY] = 6 | BCAST,
 	[CEC_MSG_CDC_MESSAGE] = 2 | BCAST,
 };
 
@@ -1071,7 +1071,7 @@ static int cec_config_log_addr(struct cec_adapter *adap,
 
 	/* Send poll message */
 	msg.len = 1;
-	msg.msg[0] = 0xf0 | log_addr;
+	msg.msg[0] = (log_addr << 4) | log_addr;
 	err = cec_transmit_msg_fh(adap, &msg, NULL, true);
 
 	/*
@@ -1205,7 +1205,7 @@ static int cec_config_thread_func(void *arg)
 		las->log_addr[i] = CEC_LOG_ADDR_INVALID;
 		if (last_la == CEC_LOG_ADDR_INVALID ||
 		    last_la == CEC_LOG_ADDR_UNREGISTERED ||
-		    !(last_la & type2mask[type]))
+		    !((1 << last_la) & type2mask[type]))
 			last_la = la_list[0];
 
 		err = cec_config_log_addr(adap, i, last_la);
@@ -1250,30 +1250,49 @@ configured:
 		for (i = 1; i < las->num_log_addrs; i++)
 			las->log_addr[i] = CEC_LOG_ADDR_INVALID;
 	}
+	for (i = las->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++)
+		las->log_addr[i] = CEC_LOG_ADDR_INVALID;
 	adap->is_configured = true;
 	adap->is_configuring = false;
 	cec_post_state_event(adap);
-	mutex_unlock(&adap->lock);
 
+	/*
+	 * Now post the Report Features and Report Physical Address broadcast
+	 * messages. Note that these are non-blocking transmits, meaning that
+	 * they are just queued up and once adap->lock is unlocked the main
+	 * thread will kick in and start transmitting these.
+	 *
+	 * If after this function is done (but before one or more of these
+	 * messages are actually transmitted) the CEC adapter is unconfigured,
+	 * then any remaining messages will be dropped by the main thread.
+	 */
 	for (i = 0; i < las->num_log_addrs; i++) {
+		struct cec_msg msg = {};
+
 		if (las->log_addr[i] == CEC_LOG_ADDR_INVALID ||
 		    (las->flags & CEC_LOG_ADDRS_FL_CDC_ONLY))
 			continue;
 
-		/*
-		 * Report Features must come first according
-		 * to CEC 2.0
-		 */
-		if (las->log_addr[i] != CEC_LOG_ADDR_UNREGISTERED)
-			cec_report_features(adap, i);
-		cec_report_phys_addr(adap, i);
+		msg.msg[0] = (las->log_addr[i] << 4) | 0x0f;
+
+		/* Report Features must come first according to CEC 2.0 */
+		if (las->log_addr[i] != CEC_LOG_ADDR_UNREGISTERED &&
+		    adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0) {
+			cec_fill_msg_report_features(adap, &msg, i);
+			cec_transmit_msg_fh(adap, &msg, NULL, false);
+		}
+
+		/* Report Physical Address */
+		cec_msg_report_physical_addr(&msg, adap->phys_addr,
+					     las->primary_device_type[i]);
+		dprintk(2, "config: la %d pa %x.%x.%x.%x\n",
+			las->log_addr[i],
+			cec_phys_addr_exp(adap->phys_addr));
+		cec_transmit_msg_fh(adap, &msg, NULL, false);
 	}
-	for (i = las->num_log_addrs; i < CEC_MAX_LOG_ADDRS; i++)
-		las->log_addr[i] = CEC_LOG_ADDR_INVALID;
-	mutex_lock(&adap->lock);
 	adap->kthread_config = NULL;
-	mutex_unlock(&adap->lock);
 	complete(&adap->config_completion);
+	mutex_unlock(&adap->lock);
 	return 0;
 
 unconfigure:
@@ -1526,52 +1545,32 @@ EXPORT_SYMBOL_GPL(cec_s_log_addrs);
 
 /* High-level core CEC message handling */
 
-/* Transmit the Report Features message */
-static int cec_report_features(struct cec_adapter *adap, unsigned int la_idx)
+/* Fill in the Report Features message */
+static void cec_fill_msg_report_features(struct cec_adapter *adap,
+					 struct cec_msg *msg,
+					 unsigned int la_idx)
 {
-	struct cec_msg msg = { };
 	const struct cec_log_addrs *las = &adap->log_addrs;
 	const u8 *features = las->features[la_idx];
 	bool op_is_dev_features = false;
 	unsigned int idx;
 
-	/* This is 2.0 and up only */
-	if (adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0)
-		return 0;
-
 	/* Report Features */
-	msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f;
-	msg.len = 4;
-	msg.msg[1] = CEC_MSG_REPORT_FEATURES;
-	msg.msg[2] = adap->log_addrs.cec_version;
-	msg.msg[3] = las->all_device_types[la_idx];
+	msg->msg[0] = (las->log_addr[la_idx] << 4) | 0x0f;
+	msg->len = 4;
+	msg->msg[1] = CEC_MSG_REPORT_FEATURES;
+	msg->msg[2] = adap->log_addrs.cec_version;
+	msg->msg[3] = las->all_device_types[la_idx];
 
 	/* Write RC Profiles first, then Device Features */
 	for (idx = 0; idx < ARRAY_SIZE(las->features[0]); idx++) {
-		msg.msg[msg.len++] = features[idx];
+		msg->msg[msg->len++] = features[idx];
 		if ((features[idx] & CEC_OP_FEAT_EXT) == 0) {
 			if (op_is_dev_features)
 				break;
 			op_is_dev_features = true;
 		}
 	}
-	return cec_transmit_msg(adap, &msg, false);
-}
-
-/* Transmit the Report Physical Address message */
-static int cec_report_phys_addr(struct cec_adapter *adap, unsigned int la_idx)
-{
-	const struct cec_log_addrs *las = &adap->log_addrs;
-	struct cec_msg msg = { };
-
-	/* Report Physical Address */
-	msg.msg[0] = (las->log_addr[la_idx] << 4) | 0x0f;
-	cec_msg_report_physical_addr(&msg, adap->phys_addr,
-				     las->primary_device_type[la_idx]);
-	dprintk(2, "config: la %d pa %x.%x.%x.%x\n",
-		las->log_addr[la_idx],
-			cec_phys_addr_exp(adap->phys_addr));
-	return cec_transmit_msg(adap, &msg, false);
 }
 
 /* Transmit the Feature Abort message */
@@ -1777,9 +1776,10 @@ static int cec_receive_notify(struct cec_adapter *adap, struct cec_msg *msg,
 	}
 
 	case CEC_MSG_GIVE_FEATURES:
-		if (adap->log_addrs.cec_version >= CEC_OP_CEC_VERSION_2_0)
-			return cec_report_features(adap, la_idx);
-		return 0;
+		if (adap->log_addrs.cec_version < CEC_OP_CEC_VERSION_2_0)
+			return cec_feature_abort(adap, msg);
+		cec_fill_msg_report_features(adap, &tx_cec_msg, la_idx);
+		return cec_transmit_msg(adap, &tx_cec_msg, false);
 
 	default:
 		/*
diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c
index bc5e8cfe7ca2..8f11d7e45993 100644
--- a/drivers/media/dvb-core/dvb_net.c
+++ b/drivers/media/dvb-core/dvb_net.c
@@ -719,6 +719,9 @@ static void dvb_net_ule_check_crc(struct dvb_net_ule_handle *h,
 		skb_copy_from_linear_data(h->priv->ule_skb, dest_addr,
 					  ETH_ALEN);
 		skb_pull(h->priv->ule_skb, ETH_ALEN);
+	} else {
+		/* dest_addr buffer is only valid if h->priv->ule_dbit == 0 */
+		eth_zero_addr(dest_addr);
 	}
 
 	/* Handle ULE Extension Headers. */
@@ -750,16 +753,8 @@ static void dvb_net_ule_check_crc(struct dvb_net_ule_handle *h,
 	if (!h->priv->ule_bridged) {
 		skb_push(h->priv->ule_skb, ETH_HLEN);
 		h->ethh = (struct ethhdr *)h->priv->ule_skb->data;
-		if (!h->priv->ule_dbit) {
-			/*
-			 * dest_addr buffer is only valid if
-			 * h->priv->ule_dbit == 0
-			 */
-			memcpy(h->ethh->h_dest, dest_addr, ETH_ALEN);
-			eth_zero_addr(h->ethh->h_source);
-		} else /* zeroize source and dest */
-			memset(h->ethh, 0, ETH_ALEN * 2);
-
+		memcpy(h->ethh->h_dest, dest_addr, ETH_ALEN);
+		eth_zero_addr(h->ethh->h_source);
 		h->ethh->h_proto = htons(h->priv->ule_sndu_type);
 	}
 	/* else:  skb is in correct state; nothing to do. */
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index b31fa6fae009..b979ea148251 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -655,6 +655,7 @@ config VIDEO_S5K6A3
 config VIDEO_S5K4ECGX
         tristate "Samsung S5K4ECGX sensor support"
         depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	select CRC32
         ---help---
           This is a V4L2 sensor-level driver for Samsung S5K4ECGX 5M
           camera sensor with an embedded SoC image signal processor.
diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index 59872b31f832..f4e92bdfe192 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -2741,9 +2741,7 @@ static const struct v4l2_subdev_internal_ops smiapp_internal_ops = {
  * I2C Driver
  */
 
-#ifdef CONFIG_PM
-
-static int smiapp_suspend(struct device *dev)
+static int __maybe_unused smiapp_suspend(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct v4l2_subdev *subdev = i2c_get_clientdata(client);
@@ -2768,7 +2766,7 @@ static int smiapp_suspend(struct device *dev)
 	return 0;
 }
 
-static int smiapp_resume(struct device *dev)
+static int __maybe_unused smiapp_resume(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct v4l2_subdev *subdev = i2c_get_clientdata(client);
@@ -2783,13 +2781,6 @@ static int smiapp_resume(struct device *dev)
 	return rval;
 }
 
-#else
-
-#define smiapp_suspend	NULL
-#define smiapp_resume	NULL
-
-#endif /* CONFIG_PM */
-
 static struct smiapp_hwconfig *smiapp_get_hwconfig(struct device *dev)
 {
 	struct smiapp_hwconfig *hwcfg;
@@ -2913,13 +2904,9 @@ static int smiapp_probe(struct i2c_client *client,
 	if (IS_ERR(sensor->xshutdown))
 		return PTR_ERR(sensor->xshutdown);
 
-	pm_runtime_enable(&client->dev);
-
-	rval = pm_runtime_get_sync(&client->dev);
-	if (rval < 0) {
-		rval = -ENODEV;
-		goto out_power_off;
-	}
+	rval = smiapp_power_on(&client->dev);
+	if (rval < 0)
+		return rval;
 
 	rval = smiapp_identify_module(sensor);
 	if (rval) {
@@ -3100,6 +3087,9 @@ static int smiapp_probe(struct i2c_client *client,
 	if (rval < 0)
 		goto out_media_entity_cleanup;
 
+	pm_runtime_set_active(&client->dev);
+	pm_runtime_get_noresume(&client->dev);
+	pm_runtime_enable(&client->dev);
 	pm_runtime_set_autosuspend_delay(&client->dev, 1000);
 	pm_runtime_use_autosuspend(&client->dev);
 	pm_runtime_put_autosuspend(&client->dev);
@@ -3113,8 +3103,7 @@ out_cleanup:
 	smiapp_cleanup(sensor);
 
 out_power_off:
-	pm_runtime_put(&client->dev);
-	pm_runtime_disable(&client->dev);
+	smiapp_power_off(&client->dev);
 
 	return rval;
 }
@@ -3127,8 +3116,10 @@ static int smiapp_remove(struct i2c_client *client)
 
 	v4l2_async_unregister_subdev(subdev);
 
-	pm_runtime_suspend(&client->dev);
 	pm_runtime_disable(&client->dev);
+	if (!pm_runtime_status_suspended(&client->dev))
+		smiapp_power_off(&client->dev);
+	pm_runtime_set_suspended(&client->dev);
 
 	for (i = 0; i < sensor->ssds_used; i++) {
 		v4l2_device_unregister_subdev(&sensor->ssds[i].sd);
diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c
index 3a0fe8cc64e9..48646a7f3fb0 100644
--- a/drivers/media/i2c/tvp5150.c
+++ b/drivers/media/i2c/tvp5150.c
@@ -291,8 +291,12 @@ static void tvp5150_selmux(struct v4l2_subdev *sd)
 	tvp5150_write(sd, TVP5150_OP_MODE_CTL, opmode);
 	tvp5150_write(sd, TVP5150_VD_IN_SRC_SEL_1, input);
 
-	/* Svideo should enable YCrCb output and disable GPCL output
-	 * For Composite and TV, it should be the reverse
+	/*
+	 * Setup the FID/GLCO/VLK/HVLK and INTREQ/GPCL/VBLK output signals. For
+	 * S-Video we output the vertical lock (VLK) signal on FID/GLCO/VLK/HVLK
+	 * and set INTREQ/GPCL/VBLK to logic 0. For composite we output the
+	 * field indicator (FID) signal on FID/GLCO/VLK/HVLK and set
+	 * INTREQ/GPCL/VBLK to logic 1.
 	 */
 	val = tvp5150_read(sd, TVP5150_MISC_CTL);
 	if (val < 0) {
@@ -301,9 +305,9 @@ static void tvp5150_selmux(struct v4l2_subdev *sd)
 	}
 
 	if (decoder->input == TVP5150_SVIDEO)
-		val = (val & ~0x40) | 0x10;
+		val = (val & ~TVP5150_MISC_CTL_GPCL) | TVP5150_MISC_CTL_HVLK;
 	else
-		val = (val & ~0x10) | 0x40;
+		val = (val & ~TVP5150_MISC_CTL_HVLK) | TVP5150_MISC_CTL_GPCL;
 	tvp5150_write(sd, TVP5150_MISC_CTL, val);
 };
 
@@ -455,7 +459,12 @@ static const struct i2c_reg_value tvp5150_init_enable[] = {
 	},{	/* Automatic offset and AGC enabled */
 		TVP5150_ANAL_CHL_CTL, 0x15
 	},{	/* Activate YCrCb output 0x9 or 0xd ? */
-		TVP5150_MISC_CTL, 0x6f
+		TVP5150_MISC_CTL, TVP5150_MISC_CTL_GPCL |
+				  TVP5150_MISC_CTL_INTREQ_OE |
+				  TVP5150_MISC_CTL_YCBCR_OE |
+				  TVP5150_MISC_CTL_SYNC_OE |
+				  TVP5150_MISC_CTL_VBLANK |
+				  TVP5150_MISC_CTL_CLOCK_OE,
 	},{	/* Activates video std autodetection for all standards */
 		TVP5150_AUTOSW_MSK, 0x0
 	},{	/* Default format: 0x47. For 4:2:2: 0x40 */
@@ -861,8 +870,6 @@ static int tvp5150_fill_fmt(struct v4l2_subdev *sd,
 
 	f = &format->format;
 
-	tvp5150_reset(sd, 0);
-
 	f->width = decoder->rect.width;
 	f->height = decoder->rect.height / 2;
 
@@ -1051,21 +1058,27 @@ static const struct media_entity_operations tvp5150_sd_media_ops = {
 static int tvp5150_s_stream(struct v4l2_subdev *sd, int enable)
 {
 	struct tvp5150 *decoder = to_tvp5150(sd);
-	/* Output format: 8-bit ITU-R BT.656 with embedded syncs */
-	int val = 0x09;
-
-	/* Output format: 8-bit 4:2:2 YUV with discrete sync */
-	if (decoder->mbus_type == V4L2_MBUS_PARALLEL)
-		val = 0x0d;
+	int val;
 
-	/* Initializes TVP5150 to its default values */
-	/* # set PCLK (27MHz) */
-	tvp5150_write(sd, TVP5150_CONF_SHARED_PIN, 0x00);
+	/* Enable or disable the video output signals. */
+	val = tvp5150_read(sd, TVP5150_MISC_CTL);
+	if (val < 0)
+		return val;
+
+	val &= ~(TVP5150_MISC_CTL_YCBCR_OE | TVP5150_MISC_CTL_SYNC_OE |
+		 TVP5150_MISC_CTL_CLOCK_OE);
+
+	if (enable) {
+		/*
+		 * Enable the YCbCr and clock outputs. In discrete sync mode
+		 * (non-BT.656) additionally enable the the sync outputs.
+		 */
+		val |= TVP5150_MISC_CTL_YCBCR_OE | TVP5150_MISC_CTL_CLOCK_OE;
+		if (decoder->mbus_type == V4L2_MBUS_PARALLEL)
+			val |= TVP5150_MISC_CTL_SYNC_OE;
+	}
 
-	if (enable)
-		tvp5150_write(sd, TVP5150_MISC_CTL, val);
-	else
-		tvp5150_write(sd, TVP5150_MISC_CTL, 0x00);
+	tvp5150_write(sd, TVP5150_MISC_CTL, val);
 
 	return 0;
 }
@@ -1524,7 +1537,6 @@ static int tvp5150_probe(struct i2c_client *c,
 		res = core->hdl.error;
 		goto err;
 	}
-	v4l2_ctrl_handler_setup(&core->hdl);
 
 	/* Default is no cropping */
 	core->rect.top = 0;
@@ -1535,6 +1547,8 @@ static int tvp5150_probe(struct i2c_client *c,
 	core->rect.left = 0;
 	core->rect.width = TVP5150_H_MAX;
 
+	tvp5150_reset(sd, 0);	/* Calls v4l2_ctrl_handler_setup() */
+
 	res = v4l2_async_register_subdev(sd);
 	if (res < 0)
 		goto err;
diff --git a/drivers/media/i2c/tvp5150_reg.h b/drivers/media/i2c/tvp5150_reg.h
index 25a994944918..30a48c28d05a 100644
--- a/drivers/media/i2c/tvp5150_reg.h
+++ b/drivers/media/i2c/tvp5150_reg.h
@@ -9,6 +9,15 @@
 #define TVP5150_ANAL_CHL_CTL         0x01 /* Analog channel controls */
 #define TVP5150_OP_MODE_CTL          0x02 /* Operation mode controls */
 #define TVP5150_MISC_CTL             0x03 /* Miscellaneous controls */
+#define TVP5150_MISC_CTL_VBLK_GPCL	BIT(7)
+#define TVP5150_MISC_CTL_GPCL		BIT(6)
+#define TVP5150_MISC_CTL_INTREQ_OE	BIT(5)
+#define TVP5150_MISC_CTL_HVLK		BIT(4)
+#define TVP5150_MISC_CTL_YCBCR_OE	BIT(3)
+#define TVP5150_MISC_CTL_SYNC_OE	BIT(2)
+#define TVP5150_MISC_CTL_VBLANK		BIT(1)
+#define TVP5150_MISC_CTL_CLOCK_OE	BIT(0)
+
 #define TVP5150_AUTOSW_MSK           0x04 /* Autoswitch mask: TVP5150A / TVP5150AM */
 
 /* Reserved 05h */
diff --git a/drivers/media/pci/cobalt/cobalt-driver.c b/drivers/media/pci/cobalt/cobalt-driver.c
index 979634000597..d5c911c09e2b 100644
--- a/drivers/media/pci/cobalt/cobalt-driver.c
+++ b/drivers/media/pci/cobalt/cobalt-driver.c
@@ -308,9 +308,7 @@ static void cobalt_pci_iounmap(struct cobalt *cobalt, struct pci_dev *pci_dev)
 static void cobalt_free_msi(struct cobalt *cobalt, struct pci_dev *pci_dev)
 {
 	free_irq(pci_dev->irq, (void *)cobalt);
-
-	if (cobalt->msi_enabled)
-		pci_disable_msi(pci_dev);
+	pci_free_irq_vectors(pci_dev);
 }
 
 static int cobalt_setup_pci(struct cobalt *cobalt, struct pci_dev *pci_dev,
@@ -387,14 +385,12 @@ static int cobalt_setup_pci(struct cobalt *cobalt, struct pci_dev *pci_dev,
 	   from being generated. */
 	cobalt_set_interrupt(cobalt, false);
 
-	if (pci_enable_msi_range(pci_dev, 1, 1) < 1) {
+	if (pci_alloc_irq_vectors(pci_dev, 1, 1, PCI_IRQ_MSI) < 1) {
 		cobalt_err("Could not enable MSI\n");
-		cobalt->msi_enabled = false;
 		ret = -EIO;
 		goto err_release;
 	}
 	msi_config_show(cobalt, pci_dev);
-	cobalt->msi_enabled = true;
 
 	/* Register IRQ */
 	if (request_irq(pci_dev->irq, cobalt_irq_handler, IRQF_SHARED,
diff --git a/drivers/media/pci/cobalt/cobalt-driver.h b/drivers/media/pci/cobalt/cobalt-driver.h
index ed00dc9d9399..00f773ec359a 100644
--- a/drivers/media/pci/cobalt/cobalt-driver.h
+++ b/drivers/media/pci/cobalt/cobalt-driver.h
@@ -287,8 +287,6 @@ struct cobalt {
 	u32 irq_none;
 	u32 irq_full_fifo;
 
-	bool msi_enabled;
-
 	/* omnitek dma */
 	int dma_channels;
 	int first_fifo_channel;
diff --git a/drivers/media/usb/dvb-usb/pctv452e.c b/drivers/media/usb/dvb-usb/pctv452e.c
index 07fa08be9e99..d54ebe7e0215 100644
--- a/drivers/media/usb/dvb-usb/pctv452e.c
+++ b/drivers/media/usb/dvb-usb/pctv452e.c
@@ -97,14 +97,13 @@ struct pctv452e_state {
 	u8 c;	   /* transaction counter, wraps around...  */
 	u8 initialized; /* set to 1 if 0x15 has been sent */
 	u16 last_rc_key;
-
-	unsigned char data[80];
 };
 
 static int tt3650_ci_msg(struct dvb_usb_device *d, u8 cmd, u8 *data,
 			 unsigned int write_len, unsigned int read_len)
 {
 	struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
+	u8 *buf;
 	u8 id;
 	unsigned int rlen;
 	int ret;
@@ -114,36 +113,39 @@ static int tt3650_ci_msg(struct dvb_usb_device *d, u8 cmd, u8 *data,
 		return -EIO;
 	}
 
-	mutex_lock(&state->ca_mutex);
+	buf = kmalloc(64, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
 	id = state->c++;
 
-	state->data[0] = SYNC_BYTE_OUT;
-	state->data[1] = id;
-	state->data[2] = cmd;
-	state->data[3] = write_len;
+	buf[0] = SYNC_BYTE_OUT;
+	buf[1] = id;
+	buf[2] = cmd;
+	buf[3] = write_len;
 
-	memcpy(state->data + 4, data, write_len);
+	memcpy(buf + 4, data, write_len);
 
 	rlen = (read_len > 0) ? 64 : 0;
-	ret = dvb_usb_generic_rw(d, state->data, 4 + write_len,
-				  state->data, rlen, /* delay_ms */ 0);
+	ret = dvb_usb_generic_rw(d, buf, 4 + write_len,
+				  buf, rlen, /* delay_ms */ 0);
 	if (0 != ret)
 		goto failed;
 
 	ret = -EIO;
-	if (SYNC_BYTE_IN != state->data[0] || id != state->data[1])
+	if (SYNC_BYTE_IN != buf[0] || id != buf[1])
 		goto failed;
 
-	memcpy(data, state->data + 4, read_len);
+	memcpy(data, buf + 4, read_len);
 
-	mutex_unlock(&state->ca_mutex);
+	kfree(buf);
 	return 0;
 
 failed:
 	err("CI error %d; %02X %02X %02X -> %*ph.",
-	     ret, SYNC_BYTE_OUT, id, cmd, 3, state->data);
+	     ret, SYNC_BYTE_OUT, id, cmd, 3, buf);
 
-	mutex_unlock(&state->ca_mutex);
+	kfree(buf);
 	return ret;
 }
 
@@ -410,53 +412,57 @@ static int pctv452e_i2c_msg(struct dvb_usb_device *d, u8 addr,
 				u8 *rcv_buf, u8 rcv_len)
 {
 	struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
+	u8 *buf;
 	u8 id;
 	int ret;
 
-	mutex_lock(&state->ca_mutex);
+	buf = kmalloc(64, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
 	id = state->c++;
 
 	ret = -EINVAL;
 	if (snd_len > 64 - 7 || rcv_len > 64 - 7)
 		goto failed;
 
-	state->data[0] = SYNC_BYTE_OUT;
-	state->data[1] = id;
-	state->data[2] = PCTV_CMD_I2C;
-	state->data[3] = snd_len + 3;
-	state->data[4] = addr << 1;
-	state->data[5] = snd_len;
-	state->data[6] = rcv_len;
+	buf[0] = SYNC_BYTE_OUT;
+	buf[1] = id;
+	buf[2] = PCTV_CMD_I2C;
+	buf[3] = snd_len + 3;
+	buf[4] = addr << 1;
+	buf[5] = snd_len;
+	buf[6] = rcv_len;
 
-	memcpy(state->data + 7, snd_buf, snd_len);
+	memcpy(buf + 7, snd_buf, snd_len);
 
-	ret = dvb_usb_generic_rw(d, state->data, 7 + snd_len,
-				  state->data, /* rcv_len */ 64,
+	ret = dvb_usb_generic_rw(d, buf, 7 + snd_len,
+				  buf, /* rcv_len */ 64,
 				  /* delay_ms */ 0);
 	if (ret < 0)
 		goto failed;
 
 	/* TT USB protocol error. */
 	ret = -EIO;
-	if (SYNC_BYTE_IN != state->data[0] || id != state->data[1])
+	if (SYNC_BYTE_IN != buf[0] || id != buf[1])
 		goto failed;
 
 	/* I2C device didn't respond as expected. */
 	ret = -EREMOTEIO;
-	if (state->data[5] < snd_len || state->data[6] < rcv_len)
+	if (buf[5] < snd_len || buf[6] < rcv_len)
 		goto failed;
 
-	memcpy(rcv_buf, state->data + 7, rcv_len);
-	mutex_unlock(&state->ca_mutex);
+	memcpy(rcv_buf, buf + 7, rcv_len);
 
+	kfree(buf);
 	return rcv_len;
 
 failed:
 	err("I2C error %d; %02X %02X  %02X %02X %02X -> %*ph",
 	     ret, SYNC_BYTE_OUT, id, addr << 1, snd_len, rcv_len,
-	     7, state->data);
+	     7, buf);
 
-	mutex_unlock(&state->ca_mutex);
+	kfree(buf);
 	return ret;
 }
 
@@ -505,7 +511,7 @@ static u32 pctv452e_i2c_func(struct i2c_adapter *adapter)
 static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i)
 {
 	struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
-	u8 *rx;
+	u8 *b0, *rx;
 	int ret;
 
 	info("%s: %d\n", __func__, i);
@@ -516,11 +522,12 @@ static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i)
 	if (state->initialized)
 		return 0;
 
-	rx = kmalloc(PCTV_ANSWER_LEN, GFP_KERNEL);
-	if (!rx)
+	b0 = kmalloc(5 + PCTV_ANSWER_LEN, GFP_KERNEL);
+	if (!b0)
 		return -ENOMEM;
 
-	mutex_lock(&state->ca_mutex);
+	rx = b0 + 5;
+
 	/* hmm where shoud this should go? */
 	ret = usb_set_interface(d->udev, 0, ISOC_INTERFACE_ALTERNATIVE);
 	if (ret != 0)
@@ -528,66 +535,70 @@ static int pctv452e_power_ctrl(struct dvb_usb_device *d, int i)
 			__func__, ret);
 
 	/* this is a one-time initialization, dont know where to put */
-	state->data[0] = 0xaa;
-	state->data[1] = state->c++;
-	state->data[2] = PCTV_CMD_RESET;
-	state->data[3] = 1;
-	state->data[4] = 0;
+	b0[0] = 0xaa;
+	b0[1] = state->c++;
+	b0[2] = PCTV_CMD_RESET;
+	b0[3] = 1;
+	b0[4] = 0;
 	/* reset board */
-	ret = dvb_usb_generic_rw(d, state->data, 5, rx, PCTV_ANSWER_LEN, 0);
+	ret = dvb_usb_generic_rw(d, b0, 5, rx, PCTV_ANSWER_LEN, 0);
 	if (ret)
 		goto ret;
 
-	state->data[1] = state->c++;
-	state->data[4] = 1;
+	b0[1] = state->c++;
+	b0[4] = 1;
 	/* reset board (again?) */
-	ret = dvb_usb_generic_rw(d, state->data, 5, rx, PCTV_ANSWER_LEN, 0);
+	ret = dvb_usb_generic_rw(d, b0, 5, rx, PCTV_ANSWER_LEN, 0);
 	if (ret)
 		goto ret;
 
 	state->initialized = 1;
 
 ret:
-	mutex_unlock(&state->ca_mutex);
-	kfree(rx);
+	kfree(b0);
 	return ret;
 }
 
 static int pctv452e_rc_query(struct dvb_usb_device *d)
 {
 	struct pctv452e_state *state = (struct pctv452e_state *)d->priv;
+	u8 *b, *rx;
 	int ret, i;
 	u8 id;
 
-	mutex_lock(&state->ca_mutex);
+	b = kmalloc(CMD_BUFFER_SIZE + PCTV_ANSWER_LEN, GFP_KERNEL);
+	if (!b)
+		return -ENOMEM;
+
+	rx = b + CMD_BUFFER_SIZE;
+
 	id = state->c++;
 
 	/* prepare command header  */
-	state->data[0] = SYNC_BYTE_OUT;
-	state->data[1] = id;
-	state->data[2] = PCTV_CMD_IR;
-	state->data[3] = 0;
+	b[0] = SYNC_BYTE_OUT;
+	b[1] = id;
+	b[2] = PCTV_CMD_IR;
+	b[3] = 0;
 
 	/* send ir request */
-	ret = dvb_usb_generic_rw(d, state->data, 4,
-				 state->data, PCTV_ANSWER_LEN, 0);
+	ret = dvb_usb_generic_rw(d, b, 4, rx, PCTV_ANSWER_LEN, 0);
 	if (ret != 0)
 		goto ret;
 
 	if (debug > 3) {
-		info("%s: read: %2d: %*ph: ", __func__, ret, 3, state->data);
-		for (i = 0; (i < state->data[3]) && ((i + 3) < PCTV_ANSWER_LEN); i++)
-			info(" %02x", state->data[i + 3]);
+		info("%s: read: %2d: %*ph: ", __func__, ret, 3, rx);
+		for (i = 0; (i < rx[3]) && ((i+3) < PCTV_ANSWER_LEN); i++)
+			info(" %02x", rx[i+3]);
 
 		info("\n");
 	}
 
-	if ((state->data[3] == 9) &&  (state->data[12] & 0x01)) {
+	if ((rx[3] == 9) &&  (rx[12] & 0x01)) {
 		/* got a "press" event */
-		state->last_rc_key = RC_SCANCODE_RC5(state->data[7], state->data[6]);
+		state->last_rc_key = RC_SCANCODE_RC5(rx[7], rx[6]);
 		if (debug > 2)
 			info("%s: cmd=0x%02x sys=0x%02x\n",
-				__func__, state->data[6], state->data[7]);
+				__func__, rx[6], rx[7]);
 
 		rc_keydown(d->rc_dev, RC_TYPE_RC5, state->last_rc_key, 0);
 	} else if (state->last_rc_key) {
@@ -595,7 +606,7 @@ static int pctv452e_rc_query(struct dvb_usb_device *d)
 		state->last_rc_key = 0;
 	}
 ret:
-	mutex_unlock(&state->ca_mutex);
+	kfree(b);
 	return ret;
 }
 
diff --git a/drivers/media/usb/siano/smsusb.c b/drivers/media/usb/siano/smsusb.c
index a4dcaec31d02..8c1f926567ec 100644
--- a/drivers/media/usb/siano/smsusb.c
+++ b/drivers/media/usb/siano/smsusb.c
@@ -218,22 +218,30 @@ static int smsusb_start_streaming(struct smsusb_device_t *dev)
 static int smsusb_sendrequest(void *context, void *buffer, size_t size)
 {
 	struct smsusb_device_t *dev = (struct smsusb_device_t *) context;
-	struct sms_msg_hdr *phdr = (struct sms_msg_hdr *) buffer;
-	int dummy;
+	struct sms_msg_hdr *phdr;
+	int dummy, ret;
 
 	if (dev->state != SMSUSB_ACTIVE) {
 		pr_debug("Device not active yet\n");
 		return -ENOENT;
 	}
 
+	phdr = kmalloc(size, GFP_KERNEL);
+	if (!phdr)
+		return -ENOMEM;
+	memcpy(phdr, buffer, size);
+
 	pr_debug("sending %s(%d) size: %d\n",
 		  smscore_translate_msg(phdr->msg_type), phdr->msg_type,
 		  phdr->msg_length);
 
 	smsendian_handle_tx_message((struct sms_msg_data *) phdr);
-	smsendian_handle_message_header((struct sms_msg_hdr *)buffer);
-	return usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2),
-			    buffer, size, &dummy, 1000);
+	smsendian_handle_message_header((struct sms_msg_hdr *)phdr);
+	ret = usb_bulk_msg(dev->udev, usb_sndbulkpipe(dev->udev, 2),
+			    phdr, size, &dummy, 1000);
+
+	kfree(phdr);
+	return ret;
 }
 
 static char *smsusb1_fw_lkup[] = {
diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c
index a0547dbf9806..76382c858c35 100644
--- a/drivers/memstick/core/memstick.c
+++ b/drivers/memstick/core/memstick.c
@@ -330,7 +330,7 @@ static int h_memstick_read_dev_id(struct memstick_dev *card,
 	struct ms_id_register id_reg;
 
 	if (!(*mrq)) {
-		memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, NULL,
+		memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, &id_reg,
 				  sizeof(struct ms_id_register));
 		*mrq = &card->current_mrq;
 		return 0;
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index f3512404bc52..99e651c27fb7 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -2000,16 +2000,6 @@ static int msb_bd_getgeo(struct block_device *bdev,
 	return 0;
 }
 
-static int msb_prepare_req(struct request_queue *q, struct request *req)
-{
-	if (req->cmd_type != REQ_TYPE_FS) {
-		blk_dump_rq_flags(req, "MS unsupported request");
-		return BLKPREP_KILL;
-	}
-	req->rq_flags |= RQF_DONTPREP;
-	return BLKPREP_OK;
-}
-
 static void msb_submit_req(struct request_queue *q)
 {
 	struct memstick_dev *card = q->queuedata;
@@ -2132,7 +2122,6 @@ static int msb_init_disk(struct memstick_dev *card)
 	}
 
 	msb->queue->queuedata = card;
-	blk_queue_prep_rq(msb->queue, msb_prepare_req);
 
 	blk_queue_bounce_limit(msb->queue, limit);
 	blk_queue_max_hw_sectors(msb->queue, MS_BLOCK_MAX_PAGES);
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index fa0746d182ff..c00d8a266878 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -827,18 +827,6 @@ static void mspro_block_start(struct memstick_dev *card)
 	spin_unlock_irqrestore(&msb->q_lock, flags);
 }
 
-static int mspro_block_prepare_req(struct request_queue *q, struct request *req)
-{
-	if (req->cmd_type != REQ_TYPE_FS) {
-		blk_dump_rq_flags(req, "MSPro unsupported request");
-		return BLKPREP_KILL;
-	}
-
-	req->rq_flags |= RQF_DONTPREP;
-
-	return BLKPREP_OK;
-}
-
 static void mspro_block_submit_req(struct request_queue *q)
 {
 	struct memstick_dev *card = q->queuedata;
@@ -1228,7 +1216,6 @@ static int mspro_block_init_disk(struct memstick_dev *card)
 	}
 
 	msb->queue->queuedata = card;
-	blk_queue_prep_rq(msb->queue, mspro_block_prepare_req);
 
 	blk_queue_bounce_limit(msb->queue, limit);
 	blk_queue_max_hw_sectors(msb->queue, MSPRO_BLOCK_MAX_PAGES);
diff --git a/drivers/message/fusion/mptfc.c b/drivers/message/fusion/mptfc.c
index add6a3a6ef0d..98eafae78576 100644
--- a/drivers/message/fusion/mptfc.c
+++ b/drivers/message/fusion/mptfc.c
@@ -119,6 +119,7 @@ static struct scsi_host_template mptfc_driver_template = {
 	.target_destroy			= mptfc_target_destroy,
 	.slave_destroy			= mptscsih_slave_destroy,
 	.change_queue_depth 		= mptscsih_change_queue_depth,
+	.eh_timed_out			= fc_eh_timed_out,
 	.eh_abort_handler		= mptfc_abort,
 	.eh_device_reset_handler	= mptfc_dev_reset,
 	.eh_bus_reset_handler		= mptfc_bus_reset,
diff --git a/drivers/message/fusion/mptlan.h b/drivers/message/fusion/mptlan.h
index 8946e19dbfc8..8a24494f8c4d 100644
--- a/drivers/message/fusion/mptlan.h
+++ b/drivers/message/fusion/mptlan.h
@@ -65,7 +65,6 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/miscdevice.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
 #include <linux/delay.h>
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 7ee1667acde4..f6308ad35b19 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -1983,6 +1983,7 @@ static struct scsi_host_template mptsas_driver_template = {
 	.target_destroy			= mptsas_target_destroy,
 	.slave_destroy			= mptscsih_slave_destroy,
 	.change_queue_depth 		= mptscsih_change_queue_depth,
+	.eh_timed_out			= mptsas_eh_timed_out,
 	.eh_abort_handler		= mptscsih_abort,
 	.eh_device_reset_handler	= mptscsih_dev_reset,
 	.eh_host_reset_handler		= mptscsih_host_reset,
@@ -2320,10 +2321,10 @@ static int mptsas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 		SmpPassthroughReply_t *smprep;
 
 		smprep = (SmpPassthroughReply_t *)ioc->sas_mgmt.reply;
-		memcpy(req->sense, smprep, sizeof(*smprep));
-		req->sense_len = sizeof(*smprep);
-		req->resid_len = 0;
-		rsp->resid_len -= smprep->ResponseDataLength;
+		memcpy(scsi_req(req)->sense, smprep, sizeof(*smprep));
+		scsi_req(req)->sense_len = sizeof(*smprep);
+		scsi_req(req)->resid_len = 0;
+		scsi_req(rsp)->resid_len -= smprep->ResponseDataLength;
 	} else {
 		printk(MYIOC_s_ERR_FMT
 		    "%s: smp passthru reply failed to be returned\n",
@@ -5398,7 +5399,6 @@ mptsas_init(void)
 	    sas_attach_transport(&mptsas_transport_functions);
 	if (!mptsas_transport_template)
 		return -ENODEV;
-	mptsas_transport_template->eh_timed_out = mptsas_eh_timed_out;
 
 	mptsasDoneCtx = mpt_register(mptscsih_io_done, MPTSAS_DRIVER,
 	    "mptscsih_io_done");
diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
index 1ef7575547e6..be42957a78e1 100644
--- a/drivers/mfd/lpc_ich.c
+++ b/drivers/mfd/lpc_ich.c
@@ -56,6 +56,7 @@
  *	document number TBD : Wildcat Point-LP
  *	document number TBD : 9 Series
  *	document number TBD : Lewisburg
+ *	document number TBD : Apollo Lake SoC
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -83,6 +84,17 @@
 #define ACPIBASE_GCS_OFF	0x3410
 #define ACPIBASE_GCS_END	0x3414
 
+#define SPIBASE_BYT		0x54
+#define SPIBASE_BYT_SZ		512
+#define SPIBASE_BYT_EN		BIT(1)
+
+#define SPIBASE_LPT		0x3800
+#define SPIBASE_LPT_SZ		512
+#define BCR			0xdc
+#define BCR_WPD			BIT(0)
+
+#define SPIBASE_APL_SZ		4096
+
 #define GPIOBASE_ICH0		0x58
 #define GPIOCTRL_ICH0		0x5C
 #define GPIOBASE_ICH6		0x48
@@ -133,6 +145,12 @@ static struct resource gpio_ich_res[] = {
 	},
 };
 
+static struct resource intel_spi_res[] = {
+	{
+		.flags = IORESOURCE_MEM,
+	}
+};
+
 static struct mfd_cell lpc_ich_wdt_cell = {
 	.name = "iTCO_wdt",
 	.num_resources = ARRAY_SIZE(wdt_ich_res),
@@ -147,6 +165,14 @@ static struct mfd_cell lpc_ich_gpio_cell = {
 	.ignore_resource_conflicts = true,
 };
 
+
+static struct mfd_cell lpc_ich_spi_cell = {
+	.name = "intel-spi",
+	.num_resources = ARRAY_SIZE(intel_spi_res),
+	.resources = intel_spi_res,
+	.ignore_resource_conflicts = true,
+};
+
 /* chipset related info */
 enum lpc_chipsets {
 	LPC_ICH = 0,	/* ICH */
@@ -216,6 +242,7 @@ enum lpc_chipsets {
 	LPC_BRASWELL,	/* Braswell SoC */
 	LPC_LEWISBURG,	/* Lewisburg */
 	LPC_9S,		/* 9 Series */
+	LPC_APL,	/* Apollo Lake SoC */
 };
 
 static struct lpc_ich_info lpc_chipset_info[] = {
@@ -494,10 +521,12 @@ static struct lpc_ich_info lpc_chipset_info[] = {
 		.name = "Lynx Point",
 		.iTCO_version = 2,
 		.gpio_version = ICH_V5_GPIO,
+		.spi_type = INTEL_SPI_LPT,
 	},
 	[LPC_LPT_LP] = {
 		.name = "Lynx Point_LP",
 		.iTCO_version = 2,
+		.spi_type = INTEL_SPI_LPT,
 	},
 	[LPC_WBG] = {
 		.name = "Wellsburg",
@@ -511,6 +540,7 @@ static struct lpc_ich_info lpc_chipset_info[] = {
 	[LPC_BAYTRAIL] = {
 		.name = "Bay Trail SoC",
 		.iTCO_version = 3,
+		.spi_type = INTEL_SPI_BYT,
 	},
 	[LPC_COLETO] = {
 		.name = "Coleto Creek",
@@ -519,10 +549,12 @@ static struct lpc_ich_info lpc_chipset_info[] = {
 	[LPC_WPT_LP] = {
 		.name = "Wildcat Point_LP",
 		.iTCO_version = 2,
+		.spi_type = INTEL_SPI_LPT,
 	},
 	[LPC_BRASWELL] = {
 		.name = "Braswell SoC",
 		.iTCO_version = 3,
+		.spi_type = INTEL_SPI_BYT,
 	},
 	[LPC_LEWISBURG] = {
 		.name = "Lewisburg",
@@ -533,6 +565,10 @@ static struct lpc_ich_info lpc_chipset_info[] = {
 		.iTCO_version = 2,
 		.gpio_version = ICH_V5_GPIO,
 	},
+	[LPC_APL] = {
+		.name = "Apollo Lake SoC",
+		.spi_type = INTEL_SPI_BXT,
+	},
 };
 
 /*
@@ -681,6 +717,7 @@ static const struct pci_device_id lpc_ich_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x3b14), LPC_3420},
 	{ PCI_VDEVICE(INTEL, 0x3b16), LPC_3450},
 	{ PCI_VDEVICE(INTEL, 0x5031), LPC_EP80579},
+	{ PCI_VDEVICE(INTEL, 0x5ae8), LPC_APL},
 	{ PCI_VDEVICE(INTEL, 0x8c40), LPC_LPT},
 	{ PCI_VDEVICE(INTEL, 0x8c41), LPC_LPT},
 	{ PCI_VDEVICE(INTEL, 0x8c42), LPC_LPT},
@@ -1056,6 +1093,94 @@ wdt_done:
 	return ret;
 }
 
+static int lpc_ich_init_spi(struct pci_dev *dev)
+{
+	struct lpc_ich_priv *priv = pci_get_drvdata(dev);
+	struct resource *res = &intel_spi_res[0];
+	struct intel_spi_boardinfo *info;
+	u32 spi_base, rcba, bcr;
+
+	info = devm_kzalloc(&dev->dev, sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->type = lpc_chipset_info[priv->chipset].spi_type;
+
+	switch (info->type) {
+	case INTEL_SPI_BYT:
+		pci_read_config_dword(dev, SPIBASE_BYT, &spi_base);
+		if (spi_base & SPIBASE_BYT_EN) {
+			res->start = spi_base & ~(SPIBASE_BYT_SZ - 1);
+			res->end = res->start + SPIBASE_BYT_SZ - 1;
+		}
+		break;
+
+	case INTEL_SPI_LPT:
+		pci_read_config_dword(dev, RCBABASE, &rcba);
+		if (rcba & 1) {
+			spi_base = round_down(rcba, SPIBASE_LPT_SZ);
+			res->start = spi_base + SPIBASE_LPT;
+			res->end = res->start + SPIBASE_LPT_SZ - 1;
+
+			/*
+			 * Try to make the flash chip writeable now by
+			 * setting BCR_WPD. It it fails we tell the driver
+			 * that it can only read the chip.
+			 */
+			pci_read_config_dword(dev, BCR, &bcr);
+			if (!(bcr & BCR_WPD)) {
+				bcr |= BCR_WPD;
+				pci_write_config_dword(dev, BCR, bcr);
+				pci_read_config_dword(dev, BCR, &bcr);
+			}
+			info->writeable = !!(bcr & BCR_WPD);
+		}
+		break;
+
+	case INTEL_SPI_BXT: {
+		unsigned int p2sb = PCI_DEVFN(13, 0);
+		unsigned int spi = PCI_DEVFN(13, 2);
+		struct pci_bus *bus = dev->bus;
+
+		/*
+		 * The P2SB is hidden by BIOS and we need to unhide it in
+		 * order to read BAR of the SPI flash device. Once that is
+		 * done we hide it again.
+		 */
+		pci_bus_write_config_byte(bus, p2sb, 0xe1, 0x0);
+		pci_bus_read_config_dword(bus, spi, PCI_BASE_ADDRESS_0,
+					  &spi_base);
+		if (spi_base != ~0) {
+			res->start = spi_base & 0xfffffff0;
+			res->end = res->start + SPIBASE_APL_SZ - 1;
+
+			pci_bus_read_config_dword(bus, spi, BCR, &bcr);
+			if (!(bcr & BCR_WPD)) {
+				bcr |= BCR_WPD;
+				pci_bus_write_config_dword(bus, spi, BCR, bcr);
+				pci_bus_read_config_dword(bus, spi, BCR, &bcr);
+			}
+			info->writeable = !!(bcr & BCR_WPD);
+		}
+
+		pci_bus_write_config_byte(bus, p2sb, 0xe1, 0x1);
+		break;
+	}
+
+	default:
+		return -EINVAL;
+	}
+
+	if (!res->start)
+		return -ENODEV;
+
+	lpc_ich_spi_cell.platform_data = info;
+	lpc_ich_spi_cell.pdata_size = sizeof(*info);
+
+	return mfd_add_devices(&dev->dev, PLATFORM_DEVID_NONE,
+			       &lpc_ich_spi_cell, 1, NULL, 0, NULL);
+}
+
 static int lpc_ich_probe(struct pci_dev *dev,
 				const struct pci_device_id *id)
 {
@@ -1099,6 +1224,12 @@ static int lpc_ich_probe(struct pci_dev *dev,
 			cell_added = true;
 	}
 
+	if (lpc_chipset_info[priv->chipset].spi_type) {
+		ret = lpc_ich_init_spi(dev);
+		if (!ret)
+			cell_added = true;
+	}
+
 	/*
 	 * We only care if at least one or none of the cells registered
 	 * successfully.
diff --git a/drivers/misc/genwqe/card_dev.c b/drivers/misc/genwqe/card_dev.c
index 7f1b282d7d96..cb290b8ca0c8 100644
--- a/drivers/misc/genwqe/card_dev.c
+++ b/drivers/misc/genwqe/card_dev.c
@@ -1396,7 +1396,7 @@ int genwqe_device_remove(struct genwqe_dev *cd)
 	 * application which will decrease this reference from
 	 * 1/unused to 0/illegal and not from 2/used 1/empty.
 	 */
-	rc = atomic_read(&cd->cdev_genwqe.kobj.kref.refcount);
+	rc = kref_read(&cd->cdev_genwqe.kobj.kref);
 	if (rc != 1) {
 		dev_err(&pci_dev->dev,
 			"[%s] err: cdev_genwqe...refcount=%d\n", __func__, rc);
diff --git a/drivers/misc/lkdtm.h b/drivers/misc/lkdtm.h
index cfa1039c62e7..67d27be60405 100644
--- a/drivers/misc/lkdtm.h
+++ b/drivers/misc/lkdtm.h
@@ -19,8 +19,12 @@ void lkdtm_SOFTLOCKUP(void);
 void lkdtm_HARDLOCKUP(void);
 void lkdtm_SPINLOCKUP(void);
 void lkdtm_HUNG_TASK(void);
-void lkdtm_ATOMIC_UNDERFLOW(void);
-void lkdtm_ATOMIC_OVERFLOW(void);
+void lkdtm_REFCOUNT_SATURATE_INC(void);
+void lkdtm_REFCOUNT_SATURATE_ADD(void);
+void lkdtm_REFCOUNT_ZERO_DEC(void);
+void lkdtm_REFCOUNT_ZERO_INC(void);
+void lkdtm_REFCOUNT_ZERO_SUB(void);
+void lkdtm_REFCOUNT_ZERO_ADD(void);
 void lkdtm_CORRUPT_LIST_ADD(void);
 void lkdtm_CORRUPT_LIST_DEL(void);
 
diff --git a/drivers/misc/lkdtm_bugs.c b/drivers/misc/lkdtm_bugs.c
index 91edd0b55e5c..cba0837aee2e 100644
--- a/drivers/misc/lkdtm_bugs.c
+++ b/drivers/misc/lkdtm_bugs.c
@@ -6,6 +6,7 @@
  */
 #include "lkdtm.h"
 #include <linux/list.h>
+#include <linux/refcount.h>
 #include <linux/sched.h>
 
 struct lkdtm_list {
@@ -129,28 +130,86 @@ void lkdtm_HUNG_TASK(void)
 	schedule();
 }
 
-void lkdtm_ATOMIC_UNDERFLOW(void)
+void lkdtm_REFCOUNT_SATURATE_INC(void)
 {
-	atomic_t under = ATOMIC_INIT(INT_MIN);
+	refcount_t over = REFCOUNT_INIT(UINT_MAX - 1);
 
-	pr_info("attempting good atomic increment\n");
-	atomic_inc(&under);
-	atomic_dec(&under);
+	pr_info("attempting good refcount decrement\n");
+	refcount_dec(&over);
+	refcount_inc(&over);
 
-	pr_info("attempting bad atomic underflow\n");
-	atomic_dec(&under);
+	pr_info("attempting bad refcount inc overflow\n");
+	refcount_inc(&over);
+	refcount_inc(&over);
+	if (refcount_read(&over) == UINT_MAX)
+		pr_err("Correctly stayed saturated, but no BUG?!\n");
+	else
+		pr_err("Fail: refcount wrapped\n");
+}
+
+void lkdtm_REFCOUNT_SATURATE_ADD(void)
+{
+	refcount_t over = REFCOUNT_INIT(UINT_MAX - 1);
+
+	pr_info("attempting good refcount decrement\n");
+	refcount_dec(&over);
+	refcount_inc(&over);
+
+	pr_info("attempting bad refcount add overflow\n");
+	refcount_add(2, &over);
+	if (refcount_read(&over) == UINT_MAX)
+		pr_err("Correctly stayed saturated, but no BUG?!\n");
+	else
+		pr_err("Fail: refcount wrapped\n");
+}
+
+void lkdtm_REFCOUNT_ZERO_DEC(void)
+{
+	refcount_t zero = REFCOUNT_INIT(1);
+
+	pr_info("attempting bad refcount decrement to zero\n");
+	refcount_dec(&zero);
+	if (refcount_read(&zero) == 0)
+		pr_err("Stayed at zero, but no BUG?!\n");
+	else
+		pr_err("Fail: refcount went crazy\n");
 }
 
-void lkdtm_ATOMIC_OVERFLOW(void)
+void lkdtm_REFCOUNT_ZERO_SUB(void)
 {
-	atomic_t over = ATOMIC_INIT(INT_MAX);
+	refcount_t zero = REFCOUNT_INIT(1);
+
+	pr_info("attempting bad refcount subtract past zero\n");
+	if (!refcount_sub_and_test(2, &zero))
+		pr_info("wrap attempt was noticed\n");
+	if (refcount_read(&zero) == 1)
+		pr_err("Correctly stayed above 0, but no BUG?!\n");
+	else
+		pr_err("Fail: refcount wrapped\n");
+}
 
-	pr_info("attempting good atomic decrement\n");
-	atomic_dec(&over);
-	atomic_inc(&over);
+void lkdtm_REFCOUNT_ZERO_INC(void)
+{
+	refcount_t zero = REFCOUNT_INIT(0);
 
-	pr_info("attempting bad atomic overflow\n");
-	atomic_inc(&over);
+	pr_info("attempting bad refcount increment from zero\n");
+	refcount_inc(&zero);
+	if (refcount_read(&zero) == 0)
+		pr_err("Stayed at zero, but no BUG?!\n");
+	else
+		pr_err("Fail: refcount went past zero\n");
+}
+
+void lkdtm_REFCOUNT_ZERO_ADD(void)
+{
+	refcount_t zero = REFCOUNT_INIT(0);
+
+	pr_info("attempting bad refcount addition from zero\n");
+	refcount_add(2, &zero);
+	if (refcount_read(&zero) == 0)
+		pr_err("Stayed at zero, but no BUG?!\n");
+	else
+		pr_err("Fail: refcount went past zero\n");
 }
 
 void lkdtm_CORRUPT_LIST_ADD(void)
diff --git a/drivers/misc/lkdtm_core.c b/drivers/misc/lkdtm_core.c
index 7eeb71a75549..16e4cf110930 100644
--- a/drivers/misc/lkdtm_core.c
+++ b/drivers/misc/lkdtm_core.c
@@ -220,8 +220,12 @@ struct crashtype crashtypes[] = {
 	CRASHTYPE(WRITE_RO),
 	CRASHTYPE(WRITE_RO_AFTER_INIT),
 	CRASHTYPE(WRITE_KERN),
-	CRASHTYPE(ATOMIC_UNDERFLOW),
-	CRASHTYPE(ATOMIC_OVERFLOW),
+	CRASHTYPE(REFCOUNT_SATURATE_INC),
+	CRASHTYPE(REFCOUNT_SATURATE_ADD),
+	CRASHTYPE(REFCOUNT_ZERO_DEC),
+	CRASHTYPE(REFCOUNT_ZERO_INC),
+	CRASHTYPE(REFCOUNT_ZERO_SUB),
+	CRASHTYPE(REFCOUNT_ZERO_ADD),
 	CRASHTYPE(USERCOPY_HEAP_SIZE_TO),
 	CRASHTYPE(USERCOPY_HEAP_SIZE_FROM),
 	CRASHTYPE(USERCOPY_HEAP_FLAG_TO),
diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c
index c6217a4993ad..a617aa5a3ad8 100644
--- a/drivers/misc/mei/debugfs.c
+++ b/drivers/misc/mei/debugfs.c
@@ -67,7 +67,7 @@ static ssize_t mei_dbgfs_read_meclients(struct file *fp, char __user *ubuf,
 				me_cl->props.max_number_of_connections,
 				me_cl->props.max_msg_length,
 				me_cl->props.single_recv_buf,
-				atomic_read(&me_cl->refcnt.refcount));
+				kref_read(&me_cl->refcnt));
 
 			mei_me_cl_put(me_cl);
 		}
diff --git a/drivers/mmc/core/Kconfig b/drivers/mmc/core/Kconfig
index cdfa8520a4b1..fc1ecdaaa9ca 100644
--- a/drivers/mmc/core/Kconfig
+++ b/drivers/mmc/core/Kconfig
@@ -12,6 +12,16 @@ config PWRSEQ_EMMC
 	  This driver can also be built as a module. If so, the module
 	  will be called pwrseq_emmc.
 
+config PWRSEQ_SD8787
+	tristate "HW reset support for SD8787 BT + Wifi module"
+	depends on OF && (MWIFIEX || BT_MRVL_SDIO)
+	help
+	  This selects hardware reset support for the SD8787 BT + Wifi
+	  module. By default this option is set to n.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called pwrseq_sd8787.
+
 config PWRSEQ_SIMPLE
 	tristate "Simple HW reset support for MMC"
 	default y
diff --git a/drivers/mmc/core/Makefile b/drivers/mmc/core/Makefile
index b2a257dc644f..7e3ed1aeada2 100644
--- a/drivers/mmc/core/Makefile
+++ b/drivers/mmc/core/Makefile
@@ -7,9 +7,10 @@ mmc_core-y			:= core.o bus.o host.o \
 				   mmc.o mmc_ops.o sd.o sd_ops.o \
 				   sdio.o sdio_ops.o sdio_bus.o \
 				   sdio_cis.o sdio_io.o sdio_irq.o \
-				   quirks.o slot-gpio.o
+				   slot-gpio.o
 mmc_core-$(CONFIG_OF)		+= pwrseq.o
 obj-$(CONFIG_PWRSEQ_SIMPLE)	+= pwrseq_simple.o
+obj-$(CONFIG_PWRSEQ_SD8787)	+= pwrseq_sd8787.o
 obj-$(CONFIG_PWRSEQ_EMMC)	+= pwrseq_emmc.o
 mmc_core-$(CONFIG_DEBUG_FS)	+= debugfs.o
 obj-$(CONFIG_MMC_BLOCK)		+= mmc_block.o
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index cb1698f268f1..1621fa08e206 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -47,6 +47,13 @@
 
 #include "queue.h"
 #include "block.h"
+#include "core.h"
+#include "card.h"
+#include "host.h"
+#include "bus.h"
+#include "mmc_ops.h"
+#include "quirks.h"
+#include "sd_ops.h"
 
 MODULE_ALIAS("mmc:block");
 #ifdef MODULE_PARAM_PREFIX
@@ -54,12 +61,6 @@ MODULE_ALIAS("mmc:block");
 #endif
 #define MODULE_PARAM_PREFIX "mmcblk."
 
-#define INAND_CMD38_ARG_EXT_CSD  113
-#define INAND_CMD38_ARG_ERASE    0x00
-#define INAND_CMD38_ARG_TRIM     0x01
-#define INAND_CMD38_ARG_SECERASE 0x80
-#define INAND_CMD38_ARG_SECTRIM1 0x81
-#define INAND_CMD38_ARG_SECTRIM2 0x88
 #define MMC_BLK_TIMEOUT_MS  (10 * 60 * 1000)        /* 10 minute timeout */
 #define MMC_SANITIZE_REQ_TIMEOUT 240000
 #define MMC_EXTRACT_INDEX_FROM_ARG(x) ((x & 0x00FF0000) >> 16)
@@ -84,7 +85,6 @@ static int max_devices;
 #define MAX_DEVICES 256
 
 static DEFINE_IDA(mmc_blk_ida);
-static DEFINE_SPINLOCK(mmc_blk_lock);
 
 /*
  * There is one mmc_blk_data per slot.
@@ -157,11 +157,7 @@ static void mmc_blk_put(struct mmc_blk_data *md)
 	if (md->usage == 0) {
 		int devidx = mmc_get_devidx(md->disk);
 		blk_cleanup_queue(md->queue.queue);
-
-		spin_lock(&mmc_blk_lock);
-		ida_remove(&mmc_blk_ida, devidx);
-		spin_unlock(&mmc_blk_lock);
-
+		ida_simple_remove(&mmc_blk_ida, devidx);
 		put_disk(md->disk);
 		kfree(md);
 	}
@@ -442,9 +438,9 @@ out:
 static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
 			       struct mmc_blk_ioc_data *idata)
 {
-	struct mmc_command cmd = {0};
-	struct mmc_data data = {0};
-	struct mmc_request mrq = {NULL};
+	struct mmc_command cmd = {};
+	struct mmc_data data = {};
+	struct mmc_request mrq = {};
 	struct scatterlist sg;
 	int err;
 	int is_rpmb = false;
@@ -762,15 +758,15 @@ static inline int mmc_blk_part_switch(struct mmc_card *card,
 	return 0;
 }
 
-static u32 mmc_sd_num_wr_blocks(struct mmc_card *card)
+static int mmc_sd_num_wr_blocks(struct mmc_card *card, u32 *written_blocks)
 {
 	int err;
 	u32 result;
 	__be32 *blocks;
 
-	struct mmc_request mrq = {NULL};
-	struct mmc_command cmd = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_data data = {};
 
 	struct scatterlist sg;
 
@@ -780,9 +776,9 @@ static u32 mmc_sd_num_wr_blocks(struct mmc_card *card)
 
 	err = mmc_wait_for_cmd(card->host, &cmd, 0);
 	if (err)
-		return (u32)-1;
+		return err;
 	if (!mmc_host_is_spi(card->host) && !(cmd.resp[0] & R1_APP_CMD))
-		return (u32)-1;
+		return -EIO;
 
 	memset(&cmd, 0, sizeof(struct mmc_command));
 
@@ -802,7 +798,7 @@ static u32 mmc_sd_num_wr_blocks(struct mmc_card *card)
 
 	blocks = kmalloc(4, GFP_KERNEL);
 	if (!blocks)
-		return (u32)-1;
+		return -ENOMEM;
 
 	sg_init_one(&sg, blocks, 4);
 
@@ -812,14 +808,16 @@ static u32 mmc_sd_num_wr_blocks(struct mmc_card *card)
 	kfree(blocks);
 
 	if (cmd.error || data.error)
-		result = (u32)-1;
+		return -EIO;
+
+	*written_blocks = result;
 
-	return result;
+	return 0;
 }
 
 static int get_card_status(struct mmc_card *card, u32 *status, int retries)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	int err;
 
 	cmd.opcode = MMC_SEND_STATUS;
@@ -884,7 +882,7 @@ static int send_stop(struct mmc_card *card, unsigned int timeout_ms,
 		struct request *req, bool *gen_err, u32 *stop_status)
 {
 	struct mmc_host *host = card->host;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	int err;
 	bool use_r1b_resp = rq_data_dir(req) == WRITE;
 
@@ -1143,7 +1141,7 @@ int mmc_access_rpmb(struct mmc_queue *mq)
 	return false;
 }
 
-static int mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
+static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
 {
 	struct mmc_blk_data *md = mq->blkdata;
 	struct mmc_card *card = md->queue.card;
@@ -1152,7 +1150,7 @@ static int mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
 
 	if (!mmc_can_erase(card)) {
 		err = -EOPNOTSUPP;
-		goto out;
+		goto fail;
 	}
 
 	from = blk_rq_pos(req);
@@ -1164,29 +1162,26 @@ static int mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req)
 		arg = MMC_TRIM_ARG;
 	else
 		arg = MMC_ERASE_ARG;
-retry:
-	if (card->quirks & MMC_QUIRK_INAND_CMD38) {
-		err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
-				 INAND_CMD38_ARG_EXT_CSD,
-				 arg == MMC_TRIM_ARG ?
-				 INAND_CMD38_ARG_TRIM :
-				 INAND_CMD38_ARG_ERASE,
-				 0);
-		if (err)
-			goto out;
-	}
-	err = mmc_erase(card, from, nr, arg);
-out:
-	if (err == -EIO && !mmc_blk_reset(md, card->host, type))
-		goto retry;
+	do {
+		err = 0;
+		if (card->quirks & MMC_QUIRK_INAND_CMD38) {
+			err = mmc_switch(card, EXT_CSD_CMD_SET_NORMAL,
+					 INAND_CMD38_ARG_EXT_CSD,
+					 arg == MMC_TRIM_ARG ?
+					 INAND_CMD38_ARG_TRIM :
+					 INAND_CMD38_ARG_ERASE,
+					 0);
+		}
+		if (!err)
+			err = mmc_erase(card, from, nr, arg);
+	} while (err == -EIO && !mmc_blk_reset(md, card->host, type));
 	if (!err)
 		mmc_blk_reset_success(md, type);
+fail:
 	blk_end_request(req, err, blk_rq_bytes(req));
-
-	return err ? 0 : 1;
 }
 
-static int mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq,
+static void mmc_blk_issue_secdiscard_rq(struct mmc_queue *mq,
 				       struct request *req)
 {
 	struct mmc_blk_data *md = mq->blkdata;
@@ -1249,11 +1244,9 @@ out_retry:
 		mmc_blk_reset_success(md, type);
 out:
 	blk_end_request(req, err, blk_rq_bytes(req));
-
-	return err ? 0 : 1;
 }
 
-static int mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req)
+static void mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req)
 {
 	struct mmc_blk_data *md = mq->blkdata;
 	struct mmc_card *card = md->queue.card;
@@ -1264,8 +1257,6 @@ static int mmc_blk_issue_flush(struct mmc_queue *mq, struct request *req)
 		ret = -EIO;
 
 	blk_end_request_all(req, ret);
-
-	return ret ? 0 : 1;
 }
 
 /*
@@ -1303,7 +1294,7 @@ static enum mmc_blk_status mmc_blk_err_check(struct mmc_card *card,
 					     struct mmc_async_req *areq)
 {
 	struct mmc_queue_req *mq_mrq = container_of(areq, struct mmc_queue_req,
-						    mmc_active);
+						    areq);
 	struct mmc_blk_request *brq = &mq_mrq->brq;
 	struct request *req = mq_mrq->req;
 	int need_retune = card->host->need_retune;
@@ -1559,17 +1550,19 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
 		brq->data.sg_len = i;
 	}
 
-	mqrq->mmc_active.mrq = &brq->mrq;
-	mqrq->mmc_active.err_check = mmc_blk_err_check;
+	mqrq->areq.mrq = &brq->mrq;
+	mqrq->areq.err_check = mmc_blk_err_check;
 
 	mmc_queue_bounce_pre(mqrq);
 }
 
-static int mmc_blk_cmd_err(struct mmc_blk_data *md, struct mmc_card *card,
-			   struct mmc_blk_request *brq, struct request *req,
-			   int ret)
+static bool mmc_blk_rw_cmd_err(struct mmc_blk_data *md, struct mmc_card *card,
+			       struct mmc_blk_request *brq, struct request *req,
+			       bool old_req_pending)
 {
 	struct mmc_queue_req *mq_rq;
+	bool req_pending;
+
 	mq_rq = container_of(brq, struct mmc_queue_req, brq);
 
 	/*
@@ -1582,62 +1575,104 @@ static int mmc_blk_cmd_err(struct mmc_blk_data *md, struct mmc_card *card,
 	 */
 	if (mmc_card_sd(card)) {
 		u32 blocks;
+		int err;
 
-		blocks = mmc_sd_num_wr_blocks(card);
-		if (blocks != (u32)-1) {
-			ret = blk_end_request(req, 0, blocks << 9);
-		}
+		err = mmc_sd_num_wr_blocks(card, &blocks);
+		if (err)
+			req_pending = old_req_pending;
+		else
+			req_pending = blk_end_request(req, 0, blocks << 9);
 	} else {
-		ret = blk_end_request(req, 0, brq->data.bytes_xfered);
+		req_pending = blk_end_request(req, 0, brq->data.bytes_xfered);
 	}
-	return ret;
+	return req_pending;
+}
+
+static void mmc_blk_rw_cmd_abort(struct mmc_card *card, struct request *req)
+{
+	if (mmc_card_removed(card))
+		req->rq_flags |= RQF_QUIET;
+	while (blk_end_request(req, -EIO, blk_rq_cur_bytes(req)));
+}
+
+/**
+ * mmc_blk_rw_try_restart() - tries to restart the current async request
+ * @mq: the queue with the card and host to restart
+ * @req: a new request that want to be started after the current one
+ */
+static void mmc_blk_rw_try_restart(struct mmc_queue *mq, struct request *req)
+{
+	if (!req)
+		return;
+
+	/*
+	 * If the card was removed, just cancel everything and return.
+	 */
+	if (mmc_card_removed(mq->card)) {
+		req->rq_flags |= RQF_QUIET;
+		blk_end_request_all(req, -EIO);
+		return;
+	}
+	/* Else proceed and try to restart the current async request */
+	mmc_blk_rw_rq_prep(mq->mqrq_cur, mq->card, 0, mq);
+	mmc_start_areq(mq->card->host, &mq->mqrq_cur->areq, NULL);
 }
 
-static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
+static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
 {
 	struct mmc_blk_data *md = mq->blkdata;
 	struct mmc_card *card = md->queue.card;
 	struct mmc_blk_request *brq;
-	int ret = 1, disable_multi = 0, retry = 0, type, retune_retry_done = 0;
+	int disable_multi = 0, retry = 0, type, retune_retry_done = 0;
 	enum mmc_blk_status status;
 	struct mmc_queue_req *mq_rq;
-	struct request *req;
-	struct mmc_async_req *areq;
+	struct request *old_req;
+	struct mmc_async_req *new_areq;
+	struct mmc_async_req *old_areq;
+	bool req_pending = true;
 
-	if (!rqc && !mq->mqrq_prev->req)
-		return 0;
+	if (!new_req && !mq->mqrq_prev->req)
+		return;
 
 	do {
-		if (rqc) {
+		if (new_req) {
 			/*
 			 * When 4KB native sector is enabled, only 8 blocks
 			 * multiple read or write is allowed
 			 */
 			if (mmc_large_sector(card) &&
-				!IS_ALIGNED(blk_rq_sectors(rqc), 8)) {
+				!IS_ALIGNED(blk_rq_sectors(new_req), 8)) {
 				pr_err("%s: Transfer size is not 4KB sector size aligned\n",
-					rqc->rq_disk->disk_name);
-				mq_rq = mq->mqrq_cur;
-				req = rqc;
-				rqc = NULL;
-				goto cmd_abort;
+					new_req->rq_disk->disk_name);
+				mmc_blk_rw_cmd_abort(card, new_req);
+				return;
 			}
 
 			mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq);
-			areq = &mq->mqrq_cur->mmc_active;
+			new_areq = &mq->mqrq_cur->areq;
 		} else
-			areq = NULL;
-		areq = mmc_start_req(card->host, areq, &status);
-		if (!areq) {
+			new_areq = NULL;
+
+		old_areq = mmc_start_areq(card->host, new_areq, &status);
+		if (!old_areq) {
+			/*
+			 * We have just put the first request into the pipeline
+			 * and there is nothing more to do until it is
+			 * complete.
+			 */
 			if (status == MMC_BLK_NEW_REQUEST)
-				mq->flags |= MMC_QUEUE_NEW_REQUEST;
-			return 0;
+				mq->new_request = true;
+			return;
 		}
 
-		mq_rq = container_of(areq, struct mmc_queue_req, mmc_active);
+		/*
+		 * An asynchronous request has been completed and we proceed
+		 * to handle the result of it.
+		 */
+		mq_rq =	container_of(old_areq, struct mmc_queue_req, areq);
 		brq = &mq_rq->brq;
-		req = mq_rq->req;
-		type = rq_data_dir(req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE;
+		old_req = mq_rq->req;
+		type = rq_data_dir(old_req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE;
 		mmc_queue_bounce_post(mq_rq);
 
 		switch (status) {
@@ -1648,28 +1683,32 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 			 */
 			mmc_blk_reset_success(md, type);
 
-			ret = blk_end_request(req, 0,
-					brq->data.bytes_xfered);
-
+			req_pending = blk_end_request(old_req, 0,
+						      brq->data.bytes_xfered);
 			/*
 			 * If the blk_end_request function returns non-zero even
 			 * though all data has been transferred and no errors
 			 * were returned by the host controller, it's a bug.
 			 */
-			if (status == MMC_BLK_SUCCESS && ret) {
+			if (status == MMC_BLK_SUCCESS && req_pending) {
 				pr_err("%s BUG rq_tot %d d_xfer %d\n",
-				       __func__, blk_rq_bytes(req),
+				       __func__, blk_rq_bytes(old_req),
 				       brq->data.bytes_xfered);
-				rqc = NULL;
-				goto cmd_abort;
+				mmc_blk_rw_cmd_abort(card, old_req);
+				return;
 			}
 			break;
 		case MMC_BLK_CMD_ERR:
-			ret = mmc_blk_cmd_err(md, card, brq, req, ret);
-			if (mmc_blk_reset(md, card->host, type))
-				goto cmd_abort;
-			if (!ret)
-				goto start_new_req;
+			req_pending = mmc_blk_rw_cmd_err(md, card, brq, old_req, req_pending);
+			if (mmc_blk_reset(md, card->host, type)) {
+				mmc_blk_rw_cmd_abort(card, old_req);
+				mmc_blk_rw_try_restart(mq, new_req);
+				return;
+			}
+			if (!req_pending) {
+				mmc_blk_rw_try_restart(mq, new_req);
+				return;
+			}
 			break;
 		case MMC_BLK_RETRY:
 			retune_retry_done = brq->retune_retry_done;
@@ -1679,22 +1718,27 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 		case MMC_BLK_ABORT:
 			if (!mmc_blk_reset(md, card->host, type))
 				break;
-			goto cmd_abort;
+			mmc_blk_rw_cmd_abort(card, old_req);
+			mmc_blk_rw_try_restart(mq, new_req);
+			return;
 		case MMC_BLK_DATA_ERR: {
 			int err;
 
 			err = mmc_blk_reset(md, card->host, type);
 			if (!err)
 				break;
-			if (err == -ENODEV)
-				goto cmd_abort;
+			if (err == -ENODEV) {
+				mmc_blk_rw_cmd_abort(card, old_req);
+				mmc_blk_rw_try_restart(mq, new_req);
+				return;
+			}
 			/* Fall through */
 		}
 		case MMC_BLK_ECC_ERR:
 			if (brq->data.blocks > 1) {
 				/* Redo read one sector at a time */
 				pr_warn("%s: retrying using single block read\n",
-					req->rq_disk->disk_name);
+					old_req->rq_disk->disk_name);
 				disable_multi = 1;
 				break;
 			}
@@ -1703,57 +1747,40 @@ static int mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *rqc)
 			 * time, so we only reach here after trying to
 			 * read a single sector.
 			 */
-			ret = blk_end_request(req, -EIO,
-						brq->data.blksz);
-			if (!ret)
-				goto start_new_req;
+			req_pending = blk_end_request(old_req, -EIO,
+						      brq->data.blksz);
+			if (!req_pending) {
+				mmc_blk_rw_try_restart(mq, new_req);
+				return;
+			}
 			break;
 		case MMC_BLK_NOMEDIUM:
-			goto cmd_abort;
+			mmc_blk_rw_cmd_abort(card, old_req);
+			mmc_blk_rw_try_restart(mq, new_req);
+			return;
 		default:
 			pr_err("%s: Unhandled return value (%d)",
-					req->rq_disk->disk_name, status);
-			goto cmd_abort;
+					old_req->rq_disk->disk_name, status);
+			mmc_blk_rw_cmd_abort(card, old_req);
+			mmc_blk_rw_try_restart(mq, new_req);
+			return;
 		}
 
-		if (ret) {
+		if (req_pending) {
 			/*
 			 * In case of a incomplete request
 			 * prepare it again and resend.
 			 */
 			mmc_blk_rw_rq_prep(mq_rq, card,
 					disable_multi, mq);
-			mmc_start_req(card->host,
-					&mq_rq->mmc_active, NULL);
+			mmc_start_areq(card->host,
+					&mq_rq->areq, NULL);
 			mq_rq->brq.retune_retry_done = retune_retry_done;
 		}
-	} while (ret);
-
-	return 1;
-
- cmd_abort:
-	if (mmc_card_removed(card))
-		req->rq_flags |= RQF_QUIET;
-	while (ret)
-		ret = blk_end_request(req, -EIO,
-				blk_rq_cur_bytes(req));
-
- start_new_req:
-	if (rqc) {
-		if (mmc_card_removed(card)) {
-			rqc->rq_flags |= RQF_QUIET;
-			blk_end_request_all(rqc, -EIO);
-		} else {
-			mmc_blk_rw_rq_prep(mq->mqrq_cur, card, 0, mq);
-			mmc_start_req(card->host,
-				      &mq->mqrq_cur->mmc_active, NULL);
-		}
-	}
-
-	return 0;
+	} while (req_pending);
 }
 
-int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
+void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 {
 	int ret;
 	struct mmc_blk_data *md = mq->blkdata;
@@ -1769,32 +1796,31 @@ int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req)
 		if (req) {
 			blk_end_request_all(req, -EIO);
 		}
-		ret = 0;
 		goto out;
 	}
 
-	mq->flags &= ~MMC_QUEUE_NEW_REQUEST;
+	mq->new_request = false;
 	if (req && req_op(req) == REQ_OP_DISCARD) {
 		/* complete ongoing async transfer before issuing discard */
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
-		ret = mmc_blk_issue_discard_rq(mq, req);
+		mmc_blk_issue_discard_rq(mq, req);
 	} else if (req && req_op(req) == REQ_OP_SECURE_ERASE) {
 		/* complete ongoing async transfer before issuing secure erase*/
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
-		ret = mmc_blk_issue_secdiscard_rq(mq, req);
+		mmc_blk_issue_secdiscard_rq(mq, req);
 	} else if (req && req_op(req) == REQ_OP_FLUSH) {
 		/* complete ongoing async transfer before issuing flush */
 		if (card->host->areq)
 			mmc_blk_issue_rw_rq(mq, NULL);
-		ret = mmc_blk_issue_flush(mq, req);
+		mmc_blk_issue_flush(mq, req);
 	} else {
-		ret = mmc_blk_issue_rw_rq(mq, req);
+		mmc_blk_issue_rw_rq(mq, req);
 	}
 
 out:
-	if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || req_is_special)
+	if ((!req && !mq->new_request) || req_is_special)
 		/*
 		 * Release host when there are no more requests
 		 * and after special request(discard, flush) is done.
@@ -1802,7 +1828,6 @@ out:
 		 * the 'mmc_blk_issue_rq' with 'mqrq_prev->req'.
 		 */
 		mmc_put_card(card);
-	return ret;
 }
 
 static inline int mmc_blk_readonly(struct mmc_card *card)
@@ -1821,23 +1846,9 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
 	struct mmc_blk_data *md;
 	int devidx, ret;
 
-again:
-	if (!ida_pre_get(&mmc_blk_ida, GFP_KERNEL))
-		return ERR_PTR(-ENOMEM);
-
-	spin_lock(&mmc_blk_lock);
-	ret = ida_get_new(&mmc_blk_ida, &devidx);
-	spin_unlock(&mmc_blk_lock);
-
-	if (ret == -EAGAIN)
-		goto again;
-	else if (ret)
-		return ERR_PTR(ret);
-
-	if (devidx >= max_devices) {
-		ret = -ENOSPC;
-		goto out;
-	}
+	devidx = ida_simple_get(&mmc_blk_ida, 0, max_devices, GFP_KERNEL);
+	if (devidx < 0)
+		return ERR_PTR(devidx);
 
 	md = kzalloc(sizeof(struct mmc_blk_data), GFP_KERNEL);
 	if (!md) {
@@ -1926,9 +1937,7 @@ again:
  err_kfree:
 	kfree(md);
  out:
-	spin_lock(&mmc_blk_lock);
-	ida_remove(&mmc_blk_ida, devidx);
-	spin_unlock(&mmc_blk_lock);
+	ida_simple_remove(&mmc_blk_ida, devidx);
 	return ERR_PTR(ret);
 }
 
@@ -2093,80 +2102,6 @@ force_ro_fail:
 	return ret;
 }
 
-static const struct mmc_fixup blk_fixups[] =
-{
-	MMC_FIXUP("SEM02G", CID_MANFID_SANDISK, 0x100, add_quirk,
-		  MMC_QUIRK_INAND_CMD38),
-	MMC_FIXUP("SEM04G", CID_MANFID_SANDISK, 0x100, add_quirk,
-		  MMC_QUIRK_INAND_CMD38),
-	MMC_FIXUP("SEM08G", CID_MANFID_SANDISK, 0x100, add_quirk,
-		  MMC_QUIRK_INAND_CMD38),
-	MMC_FIXUP("SEM16G", CID_MANFID_SANDISK, 0x100, add_quirk,
-		  MMC_QUIRK_INAND_CMD38),
-	MMC_FIXUP("SEM32G", CID_MANFID_SANDISK, 0x100, add_quirk,
-		  MMC_QUIRK_INAND_CMD38),
-
-	/*
-	 * Some MMC cards experience performance degradation with CMD23
-	 * instead of CMD12-bounded multiblock transfers. For now we'll
-	 * black list what's bad...
-	 * - Certain Toshiba cards.
-	 *
-	 * N.B. This doesn't affect SD cards.
-	 */
-	MMC_FIXUP("SDMB-32", CID_MANFID_SANDISK, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_BLK_NO_CMD23),
-	MMC_FIXUP("SDM032", CID_MANFID_SANDISK, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_BLK_NO_CMD23),
-	MMC_FIXUP("MMC08G", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_BLK_NO_CMD23),
-	MMC_FIXUP("MMC16G", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_BLK_NO_CMD23),
-	MMC_FIXUP("MMC32G", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_BLK_NO_CMD23),
-
-	/*
-	 * Some MMC cards need longer data read timeout than indicated in CSD.
-	 */
-	MMC_FIXUP(CID_NAME_ANY, CID_MANFID_MICRON, 0x200, add_quirk_mmc,
-		  MMC_QUIRK_LONG_READ_TIME),
-	MMC_FIXUP("008GE0", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_LONG_READ_TIME),
-
-	/*
-	 * On these Samsung MoviNAND parts, performing secure erase or
-	 * secure trim can result in unrecoverable corruption due to a
-	 * firmware bug.
-	 */
-	MMC_FIXUP("M8G2FA", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
-	MMC_FIXUP("MAG4FA", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
-	MMC_FIXUP("MBG8FA", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
-	MMC_FIXUP("MCGAFA", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
-	MMC_FIXUP("VAL00M", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
-	MMC_FIXUP("VYL00M", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
-	MMC_FIXUP("KYL00M", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
-	MMC_FIXUP("VZL00M", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
-
-	/*
-	 *  On Some Kingston eMMCs, performing trim can result in
-	 *  unrecoverable data conrruption occasionally due to a firmware bug.
-	 */
-	MMC_FIXUP("V10008", CID_MANFID_KINGSTON, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_TRIM_BROKEN),
-	MMC_FIXUP("V10016", CID_MANFID_KINGSTON, CID_OEMID_ANY, add_quirk_mmc,
-		  MMC_QUIRK_TRIM_BROKEN),
-
-	END_FIXUP
-};
-
 static int mmc_blk_probe(struct mmc_card *card)
 {
 	struct mmc_blk_data *md, *part_md;
@@ -2178,7 +2113,7 @@ static int mmc_blk_probe(struct mmc_card *card)
 	if (!(card->csd.cmdclass & CCC_BLOCK_READ))
 		return -ENODEV;
 
-	mmc_fixup_device(card, blk_fixups);
+	mmc_fixup_device(card, mmc_blk_fixups);
 
 	md = mmc_blk_alloc(card);
 	if (IS_ERR(md))
diff --git a/drivers/mmc/core/block.h b/drivers/mmc/core/block.h
index cdabb2ee74be..860ca7c8df86 100644
--- a/drivers/mmc/core/block.h
+++ b/drivers/mmc/core/block.h
@@ -1 +1,9 @@
-int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req);
+#ifndef _MMC_CORE_BLOCK_H
+#define _MMC_CORE_BLOCK_H
+
+struct mmc_queue;
+struct request;
+
+void mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req);
+
+#endif
diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index c64266f5a399..301246513a37 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -23,6 +23,8 @@
 #include <linux/mmc/host.h>
 
 #include "core.h"
+#include "card.h"
+#include "host.h"
 #include "sdio_cis.h"
 #include "bus.h"
 
diff --git a/drivers/mmc/core/bus.h b/drivers/mmc/core/bus.h
index 00a19710b6b4..72b0ef03f10a 100644
--- a/drivers/mmc/core/bus.h
+++ b/drivers/mmc/core/bus.h
@@ -11,6 +11,11 @@
 #ifndef _MMC_CORE_BUS_H
 #define _MMC_CORE_BUS_H
 
+#include <linux/device.h>
+
+struct mmc_host;
+struct mmc_card;
+
 #define MMC_DEV_ATTR(name, fmt, args...)					\
 static ssize_t mmc_##name##_show (struct device *dev, struct device_attribute *attr, char *buf)	\
 {										\
@@ -27,5 +32,14 @@ void mmc_remove_card(struct mmc_card *card);
 int mmc_register_bus(void);
 void mmc_unregister_bus(void);
 
-#endif
+struct mmc_driver {
+	struct device_driver drv;
+	int (*probe)(struct mmc_card *card);
+	void (*remove)(struct mmc_card *card);
+	void (*shutdown)(struct mmc_card *card);
+};
 
+int mmc_register_driver(struct mmc_driver *drv);
+void mmc_unregister_driver(struct mmc_driver *drv);
+
+#endif
diff --git a/drivers/mmc/core/card.h b/drivers/mmc/core/card.h
new file mode 100644
index 000000000000..f06cd91964ce
--- /dev/null
+++ b/drivers/mmc/core/card.h
@@ -0,0 +1,221 @@
+/*
+ * Private header for the mmc subsystem
+ *
+ * Copyright (C) 2016 Linaro Ltd
+ *
+ * Author: Ulf Hansson <ulf.hansson@linaro.org>
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+#ifndef _MMC_CORE_CARD_H
+#define _MMC_CORE_CARD_H
+
+#include <linux/mmc/card.h>
+
+#define mmc_card_name(c)	((c)->cid.prod_name)
+#define mmc_card_id(c)		(dev_name(&(c)->dev))
+#define mmc_dev_to_card(d)	container_of(d, struct mmc_card, dev)
+
+/* Card states */
+#define MMC_STATE_PRESENT	(1<<0)		/* present in sysfs */
+#define MMC_STATE_READONLY	(1<<1)		/* card is read-only */
+#define MMC_STATE_BLOCKADDR	(1<<2)		/* card uses block-addressing */
+#define MMC_CARD_SDXC		(1<<3)		/* card is SDXC */
+#define MMC_CARD_REMOVED	(1<<4)		/* card has been removed */
+#define MMC_STATE_DOING_BKOPS	(1<<5)		/* card is doing BKOPS */
+#define MMC_STATE_SUSPENDED	(1<<6)		/* card is suspended */
+
+#define mmc_card_present(c)	((c)->state & MMC_STATE_PRESENT)
+#define mmc_card_readonly(c)	((c)->state & MMC_STATE_READONLY)
+#define mmc_card_blockaddr(c)	((c)->state & MMC_STATE_BLOCKADDR)
+#define mmc_card_ext_capacity(c) ((c)->state & MMC_CARD_SDXC)
+#define mmc_card_removed(c)	((c) && ((c)->state & MMC_CARD_REMOVED))
+#define mmc_card_doing_bkops(c)	((c)->state & MMC_STATE_DOING_BKOPS)
+#define mmc_card_suspended(c)	((c)->state & MMC_STATE_SUSPENDED)
+
+#define mmc_card_set_present(c)	((c)->state |= MMC_STATE_PRESENT)
+#define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY)
+#define mmc_card_set_blockaddr(c) ((c)->state |= MMC_STATE_BLOCKADDR)
+#define mmc_card_set_ext_capacity(c) ((c)->state |= MMC_CARD_SDXC)
+#define mmc_card_set_removed(c) ((c)->state |= MMC_CARD_REMOVED)
+#define mmc_card_set_doing_bkops(c)	((c)->state |= MMC_STATE_DOING_BKOPS)
+#define mmc_card_clr_doing_bkops(c)	((c)->state &= ~MMC_STATE_DOING_BKOPS)
+#define mmc_card_set_suspended(c) ((c)->state |= MMC_STATE_SUSPENDED)
+#define mmc_card_clr_suspended(c) ((c)->state &= ~MMC_STATE_SUSPENDED)
+
+/*
+ * The world is not perfect and supplies us with broken mmc/sdio devices.
+ * For at least some of these bugs we need a work-around.
+ */
+struct mmc_fixup {
+	/* CID-specific fields. */
+	const char *name;
+
+	/* Valid revision range */
+	u64 rev_start, rev_end;
+
+	unsigned int manfid;
+	unsigned short oemid;
+
+	/* SDIO-specific fields. You can use SDIO_ANY_ID here of course */
+	u16 cis_vendor, cis_device;
+
+	/* for MMC cards */
+	unsigned int ext_csd_rev;
+
+	void (*vendor_fixup)(struct mmc_card *card, int data);
+	int data;
+};
+
+#define CID_MANFID_ANY (-1u)
+#define CID_OEMID_ANY ((unsigned short) -1)
+#define CID_NAME_ANY (NULL)
+
+#define EXT_CSD_REV_ANY (-1u)
+
+#define CID_MANFID_SANDISK      0x2
+#define CID_MANFID_TOSHIBA      0x11
+#define CID_MANFID_MICRON       0x13
+#define CID_MANFID_SAMSUNG      0x15
+#define CID_MANFID_KINGSTON     0x70
+#define CID_MANFID_HYNIX	0x90
+
+#define END_FIXUP { NULL }
+
+#define _FIXUP_EXT(_name, _manfid, _oemid, _rev_start, _rev_end,	\
+		   _cis_vendor, _cis_device,				\
+		   _fixup, _data, _ext_csd_rev)				\
+	{						\
+		.name = (_name),			\
+		.manfid = (_manfid),			\
+		.oemid = (_oemid),			\
+		.rev_start = (_rev_start),		\
+		.rev_end = (_rev_end),			\
+		.cis_vendor = (_cis_vendor),		\
+		.cis_device = (_cis_device),		\
+		.vendor_fixup = (_fixup),		\
+		.data = (_data),			\
+		.ext_csd_rev = (_ext_csd_rev),		\
+	}
+
+#define MMC_FIXUP_REV(_name, _manfid, _oemid, _rev_start, _rev_end,	\
+		      _fixup, _data, _ext_csd_rev)			\
+	_FIXUP_EXT(_name, _manfid,					\
+		   _oemid, _rev_start, _rev_end,			\
+		   SDIO_ANY_ID, SDIO_ANY_ID,				\
+		   _fixup, _data, _ext_csd_rev)				\
+
+#define MMC_FIXUP(_name, _manfid, _oemid, _fixup, _data) \
+	MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data,	\
+		      EXT_CSD_REV_ANY)
+
+#define MMC_FIXUP_EXT_CSD_REV(_name, _manfid, _oemid, _fixup, _data,	\
+			      _ext_csd_rev)				\
+	MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data,	\
+		      _ext_csd_rev)
+
+#define SDIO_FIXUP(_vendor, _device, _fixup, _data)			\
+	_FIXUP_EXT(CID_NAME_ANY, CID_MANFID_ANY,			\
+		    CID_OEMID_ANY, 0, -1ull,				\
+		   _vendor, _device,					\
+		   _fixup, _data, EXT_CSD_REV_ANY)			\
+
+#define cid_rev(hwrev, fwrev, year, month)	\
+	(((u64) hwrev) << 40 |			\
+	 ((u64) fwrev) << 32 |			\
+	 ((u64) year) << 16 |			\
+	 ((u64) month))
+
+#define cid_rev_card(card)			\
+	cid_rev(card->cid.hwrev,		\
+		    card->cid.fwrev,		\
+		    card->cid.year,		\
+		    card->cid.month)
+
+/*
+ * Unconditionally quirk add/remove.
+ */
+static inline void __maybe_unused add_quirk(struct mmc_card *card, int data)
+{
+	card->quirks |= data;
+}
+
+static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data)
+{
+	card->quirks &= ~data;
+}
+
+/*
+ * Quirk add/remove for MMC products.
+ */
+static inline void __maybe_unused add_quirk_mmc(struct mmc_card *card, int data)
+{
+	if (mmc_card_mmc(card))
+		card->quirks |= data;
+}
+
+static inline void __maybe_unused remove_quirk_mmc(struct mmc_card *card,
+						   int data)
+{
+	if (mmc_card_mmc(card))
+		card->quirks &= ~data;
+}
+
+/*
+ * Quirk add/remove for SD products.
+ */
+static inline void __maybe_unused add_quirk_sd(struct mmc_card *card, int data)
+{
+	if (mmc_card_sd(card))
+		card->quirks |= data;
+}
+
+static inline void __maybe_unused remove_quirk_sd(struct mmc_card *card,
+						   int data)
+{
+	if (mmc_card_sd(card))
+		card->quirks &= ~data;
+}
+
+static inline int mmc_card_lenient_fn0(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_LENIENT_FN0;
+}
+
+static inline int mmc_blksz_for_byte_mode(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_BLKSZ_FOR_BYTE_MODE;
+}
+
+static inline int mmc_card_disable_cd(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_DISABLE_CD;
+}
+
+static inline int mmc_card_nonstd_func_interface(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_NONSTD_FUNC_IF;
+}
+
+static inline int mmc_card_broken_byte_mode_512(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_BROKEN_BYTE_MODE_512;
+}
+
+static inline int mmc_card_long_read_time(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_LONG_READ_TIME;
+}
+
+static inline int mmc_card_broken_irq_polling(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_BROKEN_IRQ_POLLING;
+}
+
+static inline int mmc_card_broken_hpi(const struct mmc_card *c)
+{
+	return c->quirks & MMC_QUIRK_BROKEN_HPI;
+}
+
+#endif
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 1076b9d89df3..926e0fde07d7 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -40,6 +40,7 @@
 #include <trace/events/mmc.h>
 
 #include "core.h"
+#include "card.h"
 #include "bus.h"
 #include "host.h"
 #include "sdio_bus.h"
@@ -630,10 +631,41 @@ static void mmc_post_req(struct mmc_host *host, struct mmc_request *mrq,
 }
 
 /**
- *	mmc_start_req - start a non-blocking request
+ * mmc_finalize_areq() - finalize an asynchronous request
+ * @host: MMC host to finalize any ongoing request on
+ *
+ * Returns the status of the ongoing asynchronous request, but
+ * MMC_BLK_SUCCESS if no request was going on.
+ */
+static enum mmc_blk_status mmc_finalize_areq(struct mmc_host *host)
+{
+	enum mmc_blk_status status;
+
+	if (!host->areq)
+		return MMC_BLK_SUCCESS;
+
+	status = mmc_wait_for_data_req_done(host, host->areq->mrq);
+	if (status == MMC_BLK_NEW_REQUEST)
+		return status;
+
+	/*
+	 * Check BKOPS urgency for each R1 response
+	 */
+	if (host->card && mmc_card_mmc(host->card) &&
+	    ((mmc_resp_type(host->areq->mrq->cmd) == MMC_RSP_R1) ||
+	     (mmc_resp_type(host->areq->mrq->cmd) == MMC_RSP_R1B)) &&
+	    (host->areq->mrq->cmd->resp[0] & R1_EXCEPTION_EVENT)) {
+		mmc_start_bkops(host->card, true);
+	}
+
+	return status;
+}
+
+/**
+ *	mmc_start_areq - start an asynchronous request
  *	@host: MMC host to start command
- *	@areq: async request to start
- *	@error: out parameter returns 0 for success, otherwise non zero
+ *	@areq: asynchronous request to start
+ *	@ret_stat: out parameter for status
  *
  *	Start a new MMC custom command request for a host.
  *	If there is on ongoing async request wait for completion
@@ -645,11 +677,11 @@ static void mmc_post_req(struct mmc_host *host, struct mmc_request *mrq,
  *	return the completed request. If there is no ongoing request, NULL
  *	is returned without waiting. NULL is not an error condition.
  */
-struct mmc_async_req *mmc_start_req(struct mmc_host *host,
-				    struct mmc_async_req *areq,
-				    enum mmc_blk_status *ret_stat)
+struct mmc_async_req *mmc_start_areq(struct mmc_host *host,
+				     struct mmc_async_req *areq,
+				     enum mmc_blk_status *ret_stat)
 {
-	enum mmc_blk_status status = MMC_BLK_SUCCESS;
+	enum mmc_blk_status status;
 	int start_err = 0;
 	struct mmc_async_req *data = host->areq;
 
@@ -657,44 +689,25 @@ struct mmc_async_req *mmc_start_req(struct mmc_host *host,
 	if (areq)
 		mmc_pre_req(host, areq->mrq);
 
-	if (host->areq) {
-		status = mmc_wait_for_data_req_done(host, host->areq->mrq);
-		if (status == MMC_BLK_NEW_REQUEST) {
-			if (ret_stat)
-				*ret_stat = status;
-			/*
-			 * The previous request was not completed,
-			 * nothing to return
-			 */
-			return NULL;
-		}
-		/*
-		 * Check BKOPS urgency for each R1 response
-		 */
-		if (host->card && mmc_card_mmc(host->card) &&
-		    ((mmc_resp_type(host->areq->mrq->cmd) == MMC_RSP_R1) ||
-		     (mmc_resp_type(host->areq->mrq->cmd) == MMC_RSP_R1B)) &&
-		    (host->areq->mrq->cmd->resp[0] & R1_EXCEPTION_EVENT)) {
-
-			/* Cancel the prepared request */
-			if (areq)
-				mmc_post_req(host, areq->mrq, -EINVAL);
-
-			mmc_start_bkops(host->card, true);
+	/* Finalize previous request */
+	status = mmc_finalize_areq(host);
 
-			/* prepare the request again */
-			if (areq)
-				mmc_pre_req(host, areq->mrq);
-		}
+	/* The previous request is still going on... */
+	if (status == MMC_BLK_NEW_REQUEST) {
+		if (ret_stat)
+			*ret_stat = status;
+		return NULL;
 	}
 
+	/* Fine so far, start the new request! */
 	if (status == MMC_BLK_SUCCESS && areq)
 		start_err = __mmc_start_data_req(host, areq->mrq);
 
+	/* Postprocess the old request at this point */
 	if (host->areq)
 		mmc_post_req(host, host->areq->mrq, 0);
 
-	 /* Cancel a prepared request if it was not started. */
+	/* Cancel a prepared request if it was not started. */
 	if ((status != MMC_BLK_SUCCESS || start_err) && areq)
 		mmc_post_req(host, areq->mrq, -EINVAL);
 
@@ -707,7 +720,7 @@ struct mmc_async_req *mmc_start_req(struct mmc_host *host,
 		*ret_stat = status;
 	return data;
 }
-EXPORT_SYMBOL(mmc_start_req);
+EXPORT_SYMBOL(mmc_start_areq);
 
 /**
  *	mmc_wait_for_req - start a request and wait for completion
@@ -807,7 +820,7 @@ EXPORT_SYMBOL(mmc_interrupt_hpi);
  */
 int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd, int retries)
 {
-	struct mmc_request mrq = {NULL};
+	struct mmc_request mrq = {};
 
 	WARN_ON(!host->claimed);
 
@@ -1630,7 +1643,7 @@ u32 mmc_select_voltage(struct mmc_host *host, u32 ocr)
 	return ocr;
 }
 
-int __mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage)
+int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage)
 {
 	int err = 0;
 	int old_signal_voltage = host->ios.signal_voltage;
@@ -1646,20 +1659,13 @@ int __mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage)
 
 }
 
-int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage, u32 ocr)
+int mmc_set_uhs_voltage(struct mmc_host *host, u32 ocr)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	int err = 0;
 	u32 clock;
 
 	/*
-	 * Send CMD11 only if the request is to switch the card to
-	 * 1.8V signalling.
-	 */
-	if (signal_voltage == MMC_SIGNAL_VOLTAGE_330)
-		return __mmc_set_signal_voltage(host, signal_voltage);
-
-	/*
 	 * If we cannot switch voltages, return failure so the caller
 	 * can continue without UHS mode
 	 */
@@ -1697,7 +1703,7 @@ int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage, u32 ocr)
 	host->ios.clock = 0;
 	mmc_set_ios(host);
 
-	if (__mmc_set_signal_voltage(host, signal_voltage)) {
+	if (mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180)) {
 		/*
 		 * Voltages may not have been switched, but we've already
 		 * sent CMD11, so a power cycle is required anyway
@@ -1806,11 +1812,11 @@ void mmc_power_up(struct mmc_host *host, u32 ocr)
 	mmc_set_initial_state(host);
 
 	/* Try to set signal voltage to 3.3V but fall back to 1.8v or 1.2v */
-	if (__mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330) == 0)
+	if (!mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330))
 		dev_dbg(mmc_dev(host), "Initial signal voltage of 3.3v\n");
-	else if (__mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180) == 0)
+	else if (!mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180))
 		dev_dbg(mmc_dev(host), "Initial signal voltage of 1.8v\n");
-	else if (__mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120) == 0)
+	else if (!mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120))
 		dev_dbg(mmc_dev(host), "Initial signal voltage of 1.2v\n");
 
 	/*
@@ -2129,7 +2135,7 @@ static unsigned int mmc_erase_timeout(struct mmc_card *card,
 static int mmc_do_erase(struct mmc_card *card, unsigned int from,
 			unsigned int to, unsigned int arg)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	unsigned int qty = 0, busy_timeout = 0;
 	bool use_r1b_resp = false;
 	unsigned long timeout;
@@ -2551,7 +2557,7 @@ EXPORT_SYMBOL(mmc_calc_max_discard);
 
 int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	if (mmc_card_blockaddr(card) || mmc_card_ddr52(card) ||
 	    mmc_card_hs400(card) || mmc_card_hs400es(card))
@@ -2567,7 +2573,7 @@ EXPORT_SYMBOL(mmc_set_blocklen);
 int mmc_set_blockcount(struct mmc_card *card, unsigned int blockcount,
 			bool is_rel_write)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	cmd.opcode = MMC_SET_BLOCK_COUNT;
 	cmd.arg = blockcount & 0x0000FFFF;
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index 0fa86a2afc26..55f543fd37c4 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -12,6 +12,11 @@
 #define _MMC_CORE_CORE_H
 
 #include <linux/delay.h>
+#include <linux/sched.h>
+
+struct mmc_host;
+struct mmc_card;
+struct mmc_request;
 
 #define MMC_CMD_RETRIES        3
 
@@ -43,8 +48,8 @@ void mmc_set_clock(struct mmc_host *host, unsigned int hz);
 void mmc_set_bus_mode(struct mmc_host *host, unsigned int mode);
 void mmc_set_bus_width(struct mmc_host *host, unsigned int width);
 u32 mmc_select_voltage(struct mmc_host *host, u32 ocr);
-int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage, u32 ocr);
-int __mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage);
+int mmc_set_uhs_voltage(struct mmc_host *host, u32 ocr);
+int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage);
 void mmc_set_timing(struct mmc_host *host, unsigned int timing);
 void mmc_set_driver_type(struct mmc_host *host, unsigned int drv_type);
 int mmc_select_drive_strength(struct mmc_card *card, unsigned int max_dtr,
@@ -69,6 +74,7 @@ void mmc_start_host(struct mmc_host *host);
 void mmc_stop_host(struct mmc_host *host);
 
 int _mmc_detect_card_removed(struct mmc_host *host);
+int mmc_detect_card_removed(struct mmc_host *host);
 
 int mmc_attach_mmc(struct mmc_host *host);
 int mmc_attach_sd(struct mmc_host *host);
@@ -98,5 +104,38 @@ static inline void mmc_register_pm_notifier(struct mmc_host *host) { }
 static inline void mmc_unregister_pm_notifier(struct mmc_host *host) { }
 #endif
 
-#endif
+void mmc_wait_for_req_done(struct mmc_host *host, struct mmc_request *mrq);
+bool mmc_is_req_done(struct mmc_host *host, struct mmc_request *mrq);
+
+int mmc_erase(struct mmc_card *card, unsigned int from, unsigned int nr,
+		unsigned int arg);
+int mmc_can_erase(struct mmc_card *card);
+int mmc_can_trim(struct mmc_card *card);
+int mmc_can_discard(struct mmc_card *card);
+int mmc_can_sanitize(struct mmc_card *card);
+int mmc_can_secure_erase_trim(struct mmc_card *card);
+int mmc_erase_group_aligned(struct mmc_card *card, unsigned int from,
+			unsigned int nr);
+unsigned int mmc_calc_max_discard(struct mmc_card *card);
+
+int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen);
+int mmc_set_blockcount(struct mmc_card *card, unsigned int blockcount,
+			bool is_rel_write);
+
+int __mmc_claim_host(struct mmc_host *host, atomic_t *abort);
+void mmc_release_host(struct mmc_host *host);
+void mmc_get_card(struct mmc_card *card);
+void mmc_put_card(struct mmc_card *card);
+
+/**
+ *	mmc_claim_host - exclusively claim a host
+ *	@host: mmc host to claim
+ *
+ *	Claim a host for a set of operations.
+ */
+static inline void mmc_claim_host(struct mmc_host *host)
+{
+	__mmc_claim_host(host, NULL);
+}
 
+#endif
diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c
index 30623b8b86a4..a1fba5732d66 100644
--- a/drivers/mmc/core/debugfs.c
+++ b/drivers/mmc/core/debugfs.c
@@ -20,6 +20,8 @@
 #include <linux/mmc/host.h>
 
 #include "core.h"
+#include "card.h"
+#include "host.h"
 #include "mmc_ops.h"
 
 #ifdef CONFIG_FAIL_MMC_REQUEST
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 98f25ffb4258..3f8c85d5aa09 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -34,14 +34,11 @@
 #define cls_dev_to_mmc_host(d)	container_of(d, struct mmc_host, class_dev)
 
 static DEFINE_IDA(mmc_host_ida);
-static DEFINE_SPINLOCK(mmc_host_lock);
 
 static void mmc_host_classdev_release(struct device *dev)
 {
 	struct mmc_host *host = cls_dev_to_mmc_host(dev);
-	spin_lock(&mmc_host_lock);
-	ida_remove(&mmc_host_ida, host->index);
-	spin_unlock(&mmc_host_lock);
+	ida_simple_remove(&mmc_host_ida, host->index);
 	kfree(host);
 }
 
@@ -301,6 +298,8 @@ int mmc_of_parse(struct mmc_host *host)
 	if (of_property_read_bool(np, "wakeup-source") ||
 	    of_property_read_bool(np, "enable-sdio-wakeup")) /* legacy */
 		host->pm_caps |= MMC_PM_WAKE_SDIO_IRQ;
+	if (of_property_read_bool(np, "mmc-ddr-3_3v"))
+		host->caps |= MMC_CAP_3_3V_DDR;
 	if (of_property_read_bool(np, "mmc-ddr-1_8v"))
 		host->caps |= MMC_CAP_1_8V_DDR;
 	if (of_property_read_bool(np, "mmc-ddr-1_2v"))
@@ -354,22 +353,13 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 	/* scanning will be enabled when we're ready */
 	host->rescan_disable = 1;
 
-again:
-	if (!ida_pre_get(&mmc_host_ida, GFP_KERNEL)) {
+	err = ida_simple_get(&mmc_host_ida, 0, 0, GFP_KERNEL);
+	if (err < 0) {
 		kfree(host);
 		return NULL;
 	}
 
-	spin_lock(&mmc_host_lock);
-	err = ida_get_new(&mmc_host_ida, &host->index);
-	spin_unlock(&mmc_host_lock);
-
-	if (err == -EAGAIN) {
-		goto again;
-	} else if (err) {
-		kfree(host);
-		return NULL;
-	}
+	host->index = err;
 
 	dev_set_name(&host->class_dev, "mmc%d", host->index);
 
@@ -381,6 +371,8 @@ again:
 
 	if (mmc_gpio_alloc(host)) {
 		put_device(&host->class_dev);
+		ida_simple_remove(&mmc_host_ida, host->index);
+		kfree(host);
 		return NULL;
 	}
 
diff --git a/drivers/mmc/core/host.h b/drivers/mmc/core/host.h
index 992bf5397633..fb6a76a03833 100644
--- a/drivers/mmc/core/host.h
+++ b/drivers/mmc/core/host.h
@@ -10,6 +10,7 @@
  */
 #ifndef _MMC_CORE_HOST_H
 #define _MMC_CORE_HOST_H
+
 #include <linux/mmc/host.h>
 
 int mmc_register_host_class(void);
@@ -20,6 +21,53 @@ void mmc_retune_disable(struct mmc_host *host);
 void mmc_retune_hold(struct mmc_host *host);
 void mmc_retune_release(struct mmc_host *host);
 int mmc_retune(struct mmc_host *host);
+void mmc_retune_pause(struct mmc_host *host);
+void mmc_retune_unpause(struct mmc_host *host);
+
+static inline void mmc_retune_recheck(struct mmc_host *host)
+{
+	if (host->hold_retune <= 1)
+		host->retune_now = 1;
+}
+
+static inline int mmc_host_cmd23(struct mmc_host *host)
+{
+	return host->caps & MMC_CAP_CMD23;
+}
+
+static inline int mmc_boot_partition_access(struct mmc_host *host)
+{
+	return !(host->caps2 & MMC_CAP2_BOOTPART_NOACC);
+}
+
+static inline int mmc_host_uhs(struct mmc_host *host)
+{
+	return host->caps &
+		(MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 |
+		 MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 |
+		 MMC_CAP_UHS_DDR50);
+}
+
+static inline bool mmc_card_hs200(struct mmc_card *card)
+{
+	return card->host->ios.timing == MMC_TIMING_MMC_HS200;
+}
+
+static inline bool mmc_card_ddr52(struct mmc_card *card)
+{
+	return card->host->ios.timing == MMC_TIMING_MMC_DDR52;
+}
+
+static inline bool mmc_card_hs400(struct mmc_card *card)
+{
+	return card->host->ios.timing == MMC_TIMING_MMC_HS400;
+}
+
+static inline bool mmc_card_hs400es(struct mmc_card *card)
+{
+	return card->host->ios.enhanced_strobe;
+}
+
 
 #endif
 
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index b61b52f9da3d..7fd722868875 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -21,9 +21,11 @@
 #include <linux/mmc/mmc.h>
 
 #include "core.h"
+#include "card.h"
 #include "host.h"
 #include "bus.h"
 #include "mmc_ops.h"
+#include "quirks.h"
 #include "sd_ops.h"
 
 #define DEFAULT_CMD6_TIMEOUT_MS	500
@@ -47,17 +49,6 @@ static const unsigned int tacc_mant[] = {
 	35,	40,	45,	50,	55,	60,	70,	80,
 };
 
-static const struct mmc_fixup mmc_ext_csd_fixups[] = {
-	/*
-	 * Certain Hynix eMMC 4.41 cards might get broken when HPI feature
-	 * is used so disable the HPI feature for such buggy cards.
-	 */
-	MMC_FIXUP_EXT_CSD_REV(CID_NAME_ANY, CID_MANFID_HYNIX,
-			      0x014a, add_quirk, MMC_QUIRK_BROKEN_HPI, 5),
-
-	END_FIXUP
-};
-
 #define UNSTUFF_BITS(resp,start,size)					\
 	({								\
 		const int __size = size;				\
@@ -212,7 +203,7 @@ static void mmc_select_card_type(struct mmc_card *card)
 		avail_type |= EXT_CSD_CARD_TYPE_HS_52;
 	}
 
-	if (caps & MMC_CAP_1_8V_DDR &&
+	if (caps & (MMC_CAP_1_8V_DDR | MMC_CAP_3_3V_DDR) &&
 	    card_type & EXT_CSD_CARD_TYPE_DDR_1_8V) {
 		hs_max_dtr = MMC_HIGH_DDR_MAX_DTR;
 		avail_type |= EXT_CSD_CARD_TYPE_DDR_1_8V;
@@ -307,6 +298,18 @@ static void mmc_manage_enhanced_area(struct mmc_card *card, u8 *ext_csd)
 	}
 }
 
+static void mmc_part_add(struct mmc_card *card, unsigned int size,
+			 unsigned int part_cfg, char *name, int idx, bool ro,
+			 int area_type)
+{
+	card->part[card->nr_parts].size = size;
+	card->part[card->nr_parts].part_cfg = part_cfg;
+	sprintf(card->part[card->nr_parts].name, name, idx);
+	card->part[card->nr_parts].force_ro = ro;
+	card->part[card->nr_parts].area_type = area_type;
+	card->nr_parts++;
+}
+
 static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd)
 {
 	int idx;
@@ -530,8 +533,14 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 						EXT_CSD_MANUAL_BKOPS_MASK);
 			card->ext_csd.raw_bkops_status =
 				ext_csd[EXT_CSD_BKOPS_STATUS];
-			if (!card->ext_csd.man_bkops_en)
-				pr_debug("%s: MAN_BKOPS_EN bit is not set\n",
+			if (card->ext_csd.man_bkops_en)
+				pr_debug("%s: MAN_BKOPS_EN bit is set\n",
+					mmc_hostname(card->host));
+			card->ext_csd.auto_bkops_en =
+					(ext_csd[EXT_CSD_BKOPS_EN] &
+						EXT_CSD_AUTO_BKOPS_MASK);
+			if (card->ext_csd.auto_bkops_en)
+				pr_debug("%s: AUTO_BKOPS_EN bit is set\n",
 					mmc_hostname(card->host));
 		}
 
@@ -617,6 +626,12 @@ static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd)
 		card->ext_csd.ffu_capable =
 			(ext_csd[EXT_CSD_SUPPORTED_MODE] & 0x1) &&
 			!(ext_csd[EXT_CSD_FW_CONFIG] & 0x1);
+
+		card->ext_csd.pre_eol_info = ext_csd[EXT_CSD_PRE_EOL_INFO];
+		card->ext_csd.device_life_time_est_typ_a =
+			ext_csd[EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_A];
+		card->ext_csd.device_life_time_est_typ_b =
+			ext_csd[EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_B];
 	}
 
 	/* eMMC v5.1 or later */
@@ -764,6 +779,10 @@ MMC_DEV_ATTR(manfid, "0x%06x\n", card->cid.manfid);
 MMC_DEV_ATTR(name, "%s\n", card->cid.prod_name);
 MMC_DEV_ATTR(oemid, "0x%04x\n", card->cid.oemid);
 MMC_DEV_ATTR(prv, "0x%x\n", card->cid.prv);
+MMC_DEV_ATTR(pre_eol_info, "%02x\n", card->ext_csd.pre_eol_info);
+MMC_DEV_ATTR(life_time, "0x%02x 0x%02x\n",
+	card->ext_csd.device_life_time_est_typ_a,
+	card->ext_csd.device_life_time_est_typ_b);
 MMC_DEV_ATTR(serial, "0x%08x\n", card->cid.serial);
 MMC_DEV_ATTR(enhanced_area_offset, "%llu\n",
 		card->ext_csd.enhanced_area_offset);
@@ -817,6 +836,8 @@ static struct attribute *mmc_std_attrs[] = {
 	&dev_attr_name.attr,
 	&dev_attr_oemid.attr,
 	&dev_attr_prv.attr,
+	&dev_attr_pre_eol_info.attr,
+	&dev_attr_life_time.attr,
 	&dev_attr_serial.attr,
 	&dev_attr_enhanced_area_offset.attr,
 	&dev_attr_enhanced_area_size.attr,
@@ -1095,16 +1116,19 @@ static int mmc_select_hs_ddr(struct mmc_card *card)
 	 *
 	 * WARNING: eMMC rules are NOT the same as SD DDR
 	 */
-	err = -EINVAL;
-	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_DDR_1_2V)
-		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
+	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_DDR_1_2V) {
+		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
+		if (!err)
+			return 0;
+	}
 
-	if (err && (card->mmc_avail_type & EXT_CSD_CARD_TYPE_DDR_1_8V))
-		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
+	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_DDR_1_8V &&
+	    host->caps & MMC_CAP_1_8V_DDR)
+		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
 
 	/* make sure vccq is 3.3v after switching disaster */
 	if (err)
-		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330);
+		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_330);
 
 	return err;
 }
@@ -1271,10 +1295,10 @@ static int mmc_select_hs400es(struct mmc_card *card)
 	}
 
 	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400_1_2V)
-		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
+		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
 
 	if (err && card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS400_1_8V)
-		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
+		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
 
 	/* If fails try again during next card power cycle */
 	if (err)
@@ -1380,10 +1404,10 @@ static int mmc_select_hs200(struct mmc_card *card)
 
 	old_signal_voltage = host->ios.signal_voltage;
 	if (card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS200_1_2V)
-		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
+		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_120);
 
 	if (err && card->mmc_avail_type & EXT_CSD_CARD_TYPE_HS200_1_8V)
-		err = __mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
+		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180);
 
 	/* If fails try again during next card power cycle */
 	if (err)
@@ -1425,7 +1449,7 @@ static int mmc_select_hs200(struct mmc_card *card)
 err:
 	if (err) {
 		/* fall back to the old signal voltage, if fails report error */
-		if (__mmc_set_signal_voltage(host, old_signal_voltage))
+		if (mmc_set_signal_voltage(host, old_signal_voltage))
 			err = -EIO;
 
 		pr_err("%s: %s failed, error %d\n", mmc_hostname(card->host),
@@ -1706,10 +1730,10 @@ static int mmc_init_card(struct mmc_host *host, u32 ocr,
 		err = mmc_select_hs400(card);
 		if (err)
 			goto free_card;
-	} else if (mmc_card_hs(card)) {
+	} else {
 		/* Select the desired bus width optionally */
 		err = mmc_select_bus_width(card);
-		if (err > 0) {
+		if (err > 0 && mmc_card_hs(card)) {
 			err = mmc_select_hs_ddr(card);
 			if (err)
 				goto free_card;
@@ -1805,7 +1829,7 @@ static int mmc_can_sleep(struct mmc_card *card)
 
 static int mmc_sleep(struct mmc_host *host)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	struct mmc_card *card = host->card;
 	unsigned int timeout_ms = DIV_ROUND_UP(card->ext_csd.sa_timeout, 10000);
 	int err;
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index e6ea8503f40c..fe80f26d6971 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -57,7 +57,7 @@ static const u8 tuning_blk_pattern_8bit[] = {
 int mmc_send_status(struct mmc_card *card, u32 *status)
 {
 	int err;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	cmd.opcode = MMC_SEND_STATUS;
 	if (!mmc_host_is_spi(card->host))
@@ -79,7 +79,7 @@ int mmc_send_status(struct mmc_card *card, u32 *status)
 
 static int _mmc_select_card(struct mmc_host *host, struct mmc_card *card)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	cmd.opcode = MMC_SELECT_CARD;
 
@@ -115,7 +115,7 @@ int mmc_deselect_cards(struct mmc_host *host)
  */
 int mmc_set_dsr(struct mmc_host *host)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	cmd.opcode = MMC_SET_DSR;
 
@@ -128,7 +128,7 @@ int mmc_set_dsr(struct mmc_host *host)
 int mmc_go_idle(struct mmc_host *host)
 {
 	int err;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	/*
 	 * Non-SPI hosts need to prevent chipselect going active during
@@ -164,7 +164,7 @@ int mmc_go_idle(struct mmc_host *host)
 
 int mmc_send_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	int i, err = 0;
 
 	cmd.opcode = MMC_SEND_OP_COND;
@@ -203,7 +203,7 @@ int mmc_send_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr)
 int mmc_all_send_cid(struct mmc_host *host, u32 *cid)
 {
 	int err;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	cmd.opcode = MMC_ALL_SEND_CID;
 	cmd.arg = 0;
@@ -220,7 +220,7 @@ int mmc_all_send_cid(struct mmc_host *host, u32 *cid)
 
 int mmc_set_relative_addr(struct mmc_card *card)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	cmd.opcode = MMC_SET_RELATIVE_ADDR;
 	cmd.arg = card->rca << 16;
@@ -233,7 +233,7 @@ static int
 mmc_send_cxd_native(struct mmc_host *host, u32 arg, u32 *cxd, int opcode)
 {
 	int err;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	cmd.opcode = opcode;
 	cmd.arg = arg;
@@ -256,9 +256,9 @@ static int
 mmc_send_cxd_data(struct mmc_card *card, struct mmc_host *host,
 		u32 opcode, void *buf, unsigned len)
 {
-	struct mmc_request mrq = {NULL};
-	struct mmc_command cmd = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_data data = {};
 	struct scatterlist sg;
 
 	mrq.cmd = &cmd;
@@ -387,7 +387,7 @@ EXPORT_SYMBOL_GPL(mmc_get_ext_csd);
 
 int mmc_spi_read_ocr(struct mmc_host *host, int highcap, u32 *ocrp)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	int err;
 
 	cmd.opcode = MMC_SPI_READ_OCR;
@@ -402,7 +402,7 @@ int mmc_spi_read_ocr(struct mmc_host *host, int highcap, u32 *ocrp)
 
 int mmc_spi_set_crc(struct mmc_host *host, int use_crc)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	int err;
 
 	cmd.opcode = MMC_SPI_CRC_ON_OFF;
@@ -530,7 +530,7 @@ int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 {
 	struct mmc_host *host = card->host;
 	int err;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	bool use_r1b_resp = use_busy_signal;
 	unsigned char old_timing = host->ios.timing;
 
@@ -610,9 +610,9 @@ EXPORT_SYMBOL_GPL(mmc_switch);
 
 int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error)
 {
-	struct mmc_request mrq = {NULL};
-	struct mmc_command cmd = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_data data = {};
 	struct scatterlist sg;
 	struct mmc_ios *ios = &host->ios;
 	const u8 *tuning_block_pattern;
@@ -679,7 +679,7 @@ EXPORT_SYMBOL_GPL(mmc_send_tuning);
 
 int mmc_abort_tuning(struct mmc_host *host, u32 opcode)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	/*
 	 * eMMC specification specifies that CMD12 can be used to stop a tuning
@@ -706,9 +706,9 @@ static int
 mmc_send_bus_test(struct mmc_card *card, struct mmc_host *host, u8 opcode,
 		  u8 len)
 {
-	struct mmc_request mrq = {NULL};
-	struct mmc_command cmd = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_data data = {};
 	struct scatterlist sg;
 	u8 *data_buf;
 	u8 *test_buf;
@@ -802,7 +802,7 @@ int mmc_bus_test(struct mmc_card *card, u8 bus_width)
 
 int mmc_send_hpi_cmd(struct mmc_card *card, u32 *status)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	unsigned int opcode;
 	int err;
 
diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h
index abd525ed74be..74beea8a9c7e 100644
--- a/drivers/mmc/core/mmc_ops.h
+++ b/drivers/mmc/core/mmc_ops.h
@@ -12,6 +12,11 @@
 #ifndef _MMC_MMC_OPS_H
 #define _MMC_MMC_OPS_H
 
+#include <linux/types.h>
+
+struct mmc_host;
+struct mmc_card;
+
 int mmc_select_card(struct mmc_card *card);
 int mmc_deselect_cards(struct mmc_host *host);
 int mmc_set_dsr(struct mmc_host *host);
@@ -26,12 +31,21 @@ int mmc_spi_read_ocr(struct mmc_host *host, int highcap, u32 *ocrp);
 int mmc_spi_set_crc(struct mmc_host *host, int use_crc);
 int mmc_bus_test(struct mmc_card *card, u8 bus_width);
 int mmc_send_hpi_cmd(struct mmc_card *card, u32 *status);
+int mmc_interrupt_hpi(struct mmc_card *card);
 int mmc_can_ext_csd(struct mmc_card *card);
+int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd);
 int mmc_switch_status(struct mmc_card *card);
 int __mmc_switch_status(struct mmc_card *card, bool crc_err_fatal);
 int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		unsigned int timeout_ms, unsigned char timing,
 		bool use_busy_signal, bool send_status,	bool retry_crc_err);
+int mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
+		unsigned int timeout_ms);
+int mmc_stop_bkops(struct mmc_card *card);
+int mmc_read_bkops_status(struct mmc_card *card);
+void mmc_start_bkops(struct mmc_card *card, bool from_exception);
+int mmc_can_reset(struct mmc_card *card);
+int mmc_flush_cache(struct mmc_card *card);
 
 #endif
 
diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c
index 3ab6e52d106c..f99ac3123fd2 100644
--- a/drivers/mmc/core/mmc_test.c
+++ b/drivers/mmc/core/mmc_test.c
@@ -22,6 +22,11 @@
 #include <linux/seq_file.h>
 #include <linux/module.h>
 
+#include "core.h"
+#include "card.h"
+#include "host.h"
+#include "bus.h"
+
 #define RESULT_OK		0
 #define RESULT_FAIL		1
 #define RESULT_UNSUP_HOST	2
@@ -260,7 +265,7 @@ static int mmc_test_busy(struct mmc_command *cmd)
 static int mmc_test_wait_busy(struct mmc_test_card *test)
 {
 	int ret, busy;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	busy = 0;
 	do {
@@ -277,8 +282,7 @@ static int mmc_test_wait_busy(struct mmc_test_card *test)
 		if (!busy && mmc_test_busy(&cmd)) {
 			busy = 1;
 			if (test->card->host->caps & MMC_CAP_WAIT_WHILE_BUSY)
-				pr_info("%s: Warning: Host did not "
-					"wait for busy state to end.\n",
+				pr_info("%s: Warning: Host did not wait for busy state to end.\n",
 					mmc_hostname(test->card->host));
 		}
 	} while (mmc_test_busy(&cmd));
@@ -292,10 +296,10 @@ static int mmc_test_wait_busy(struct mmc_test_card *test)
 static int mmc_test_buffer_transfer(struct mmc_test_card *test,
 	u8 *buffer, unsigned addr, unsigned blksz, int write)
 {
-	struct mmc_request mrq = {0};
-	struct mmc_command cmd = {0};
-	struct mmc_command stop = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_command stop = {};
+	struct mmc_data data = {};
 
 	struct scatterlist sg;
 
@@ -357,12 +361,11 @@ static struct mmc_test_mem *mmc_test_alloc_mem(unsigned long min_sz,
 	if (max_segs > max_page_cnt)
 		max_segs = max_page_cnt;
 
-	mem = kzalloc(sizeof(struct mmc_test_mem), GFP_KERNEL);
+	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
 	if (!mem)
 		return NULL;
 
-	mem->arr = kzalloc(sizeof(struct mmc_test_pages) * max_segs,
-			   GFP_KERNEL);
+	mem->arr = kcalloc(max_segs, sizeof(*mem->arr), GFP_KERNEL);
 	if (!mem->arr)
 		goto out_free;
 
@@ -546,7 +549,7 @@ static void mmc_test_save_transfer_result(struct mmc_test_card *test,
 	if (!test->gr)
 		return;
 
-	tr = kmalloc(sizeof(struct mmc_test_transfer_result), GFP_KERNEL);
+	tr = kmalloc(sizeof(*tr), GFP_KERNEL);
 	if (!tr)
 		return;
 
@@ -641,11 +644,11 @@ static int __mmc_test_prepare(struct mmc_test_card *test, int write)
 	if (write)
 		memset(test->buffer, 0xDF, 512);
 	else {
-		for (i = 0;i < 512;i++)
+		for (i = 0; i < 512; i++)
 			test->buffer[i] = i;
 	}
 
-	for (i = 0;i < BUFFER_SIZE / 512;i++) {
+	for (i = 0; i < BUFFER_SIZE / 512; i++) {
 		ret = mmc_test_buffer_transfer(test, test->buffer, i, 512, 1);
 		if (ret)
 			return ret;
@@ -674,7 +677,7 @@ static int mmc_test_cleanup(struct mmc_test_card *test)
 
 	memset(test->buffer, 0, 512);
 
-	for (i = 0;i < BUFFER_SIZE / 512;i++) {
+	for (i = 0; i < BUFFER_SIZE / 512; i++) {
 		ret = mmc_test_buffer_transfer(test, test->buffer, i, 512, 1);
 		if (ret)
 			return ret;
@@ -850,7 +853,7 @@ static int mmc_test_nonblock_transfer(struct mmc_test_card *test,
 	for (i = 0; i < count; i++) {
 		mmc_test_prepare_mrq(test, cur_areq->mrq, sg, sg_len, dev_addr,
 				     blocks, blksz, write);
-		done_areq = mmc_start_req(test->card->host, cur_areq, &status);
+		done_areq = mmc_start_areq(test->card->host, cur_areq, &status);
 
 		if (status != MMC_BLK_SUCCESS || (!done_areq && i > 0)) {
 			ret = RESULT_FAIL;
@@ -869,7 +872,7 @@ static int mmc_test_nonblock_transfer(struct mmc_test_card *test,
 		dev_addr += blocks;
 	}
 
-	done_areq = mmc_start_req(test->card->host, NULL, &status);
+	done_areq = mmc_start_areq(test->card->host, NULL, &status);
 	if (status != MMC_BLK_SUCCESS)
 		ret = RESULT_FAIL;
 
@@ -885,10 +888,10 @@ static int mmc_test_simple_transfer(struct mmc_test_card *test,
 	struct scatterlist *sg, unsigned sg_len, unsigned dev_addr,
 	unsigned blocks, unsigned blksz, int write)
 {
-	struct mmc_request mrq = {0};
-	struct mmc_command cmd = {0};
-	struct mmc_command stop = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_command stop = {};
+	struct mmc_data data = {};
 
 	mrq.cmd = &cmd;
 	mrq.data = &data;
@@ -910,10 +913,10 @@ static int mmc_test_simple_transfer(struct mmc_test_card *test,
 static int mmc_test_broken_transfer(struct mmc_test_card *test,
 	unsigned blocks, unsigned blksz, int write)
 {
-	struct mmc_request mrq = {0};
-	struct mmc_command cmd = {0};
-	struct mmc_command stop = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_command stop = {};
+	struct mmc_data data = {};
 
 	struct scatterlist sg;
 
@@ -946,7 +949,7 @@ static int mmc_test_transfer(struct mmc_test_card *test,
 	unsigned long flags;
 
 	if (write) {
-		for (i = 0;i < blocks * blksz;i++)
+		for (i = 0; i < blocks * blksz; i++)
 			test->scratch[i] = i;
 	} else {
 		memset(test->scratch, 0, BUFFER_SIZE);
@@ -980,7 +983,7 @@ static int mmc_test_transfer(struct mmc_test_card *test,
 
 		memset(test->buffer, 0, sectors * 512);
 
-		for (i = 0;i < sectors;i++) {
+		for (i = 0; i < sectors; i++) {
 			ret = mmc_test_buffer_transfer(test,
 				test->buffer + i * 512,
 				dev_addr + i, 512, 0);
@@ -988,12 +991,12 @@ static int mmc_test_transfer(struct mmc_test_card *test,
 				return ret;
 		}
 
-		for (i = 0;i < blocks * blksz;i++) {
+		for (i = 0; i < blocks * blksz; i++) {
 			if (test->buffer[i] != (u8)i)
 				return RESULT_FAIL;
 		}
 
-		for (;i < sectors * 512;i++) {
+		for (; i < sectors * 512; i++) {
 			if (test->buffer[i] != 0xDF)
 				return RESULT_FAIL;
 		}
@@ -1001,7 +1004,7 @@ static int mmc_test_transfer(struct mmc_test_card *test,
 		local_irq_save(flags);
 		sg_copy_to_buffer(sg, sg_len, test->scratch, BUFFER_SIZE);
 		local_irq_restore(flags);
-		for (i = 0;i < blocks * blksz;i++) {
+		for (i = 0; i < blocks * blksz; i++) {
 			if (test->scratch[i] != (u8)i)
 				return RESULT_FAIL;
 		}
@@ -1086,7 +1089,7 @@ static int mmc_test_multi_write(struct mmc_test_card *test)
 
 	sg_init_one(&sg, test->buffer, size);
 
-	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
+	return mmc_test_transfer(test, &sg, 1, 0, size / 512, 512, 1);
 }
 
 static int mmc_test_multi_read(struct mmc_test_card *test)
@@ -1107,7 +1110,7 @@ static int mmc_test_multi_read(struct mmc_test_card *test)
 
 	sg_init_one(&sg, test->buffer, size);
 
-	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
+	return mmc_test_transfer(test, &sg, 1, 0, size / 512, 512, 0);
 }
 
 static int mmc_test_pow2_write(struct mmc_test_card *test)
@@ -1118,7 +1121,7 @@ static int mmc_test_pow2_write(struct mmc_test_card *test)
 	if (!test->card->csd.write_partial)
 		return RESULT_UNSUP_CARD;
 
-	for (i = 1; i < 512;i <<= 1) {
+	for (i = 1; i < 512; i <<= 1) {
 		sg_init_one(&sg, test->buffer, i);
 		ret = mmc_test_transfer(test, &sg, 1, 0, 1, i, 1);
 		if (ret)
@@ -1136,7 +1139,7 @@ static int mmc_test_pow2_read(struct mmc_test_card *test)
 	if (!test->card->csd.read_partial)
 		return RESULT_UNSUP_CARD;
 
-	for (i = 1; i < 512;i <<= 1) {
+	for (i = 1; i < 512; i <<= 1) {
 		sg_init_one(&sg, test->buffer, i);
 		ret = mmc_test_transfer(test, &sg, 1, 0, 1, i, 0);
 		if (ret)
@@ -1154,7 +1157,7 @@ static int mmc_test_weird_write(struct mmc_test_card *test)
 	if (!test->card->csd.write_partial)
 		return RESULT_UNSUP_CARD;
 
-	for (i = 3; i < 512;i += 7) {
+	for (i = 3; i < 512; i += 7) {
 		sg_init_one(&sg, test->buffer, i);
 		ret = mmc_test_transfer(test, &sg, 1, 0, 1, i, 1);
 		if (ret)
@@ -1172,7 +1175,7 @@ static int mmc_test_weird_read(struct mmc_test_card *test)
 	if (!test->card->csd.read_partial)
 		return RESULT_UNSUP_CARD;
 
-	for (i = 3; i < 512;i += 7) {
+	for (i = 3; i < 512; i += 7) {
 		sg_init_one(&sg, test->buffer, i);
 		ret = mmc_test_transfer(test, &sg, 1, 0, 1, i, 0);
 		if (ret)
@@ -1231,7 +1234,7 @@ static int mmc_test_align_multi_write(struct mmc_test_card *test)
 
 	for (i = 1; i < TEST_ALIGN_END; i++) {
 		sg_init_one(&sg, test->buffer + i, size);
-		ret = mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
+		ret = mmc_test_transfer(test, &sg, 1, 0, size / 512, 512, 1);
 		if (ret)
 			return ret;
 	}
@@ -1258,7 +1261,7 @@ static int mmc_test_align_multi_read(struct mmc_test_card *test)
 
 	for (i = 1; i < TEST_ALIGN_END; i++) {
 		sg_init_one(&sg, test->buffer + i, size);
-		ret = mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
+		ret = mmc_test_transfer(test, &sg, 1, 0, size / 512, 512, 0);
 		if (ret)
 			return ret;
 	}
@@ -1357,7 +1360,7 @@ static int mmc_test_multi_write_high(struct mmc_test_card *test)
 	sg_init_table(&sg, 1);
 	sg_set_page(&sg, test->highmem, size, 0);
 
-	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 1);
+	return mmc_test_transfer(test, &sg, 1, 0, size / 512, 512, 1);
 }
 
 static int mmc_test_multi_read_high(struct mmc_test_card *test)
@@ -1379,7 +1382,7 @@ static int mmc_test_multi_read_high(struct mmc_test_card *test)
 	sg_init_table(&sg, 1);
 	sg_set_page(&sg, test->highmem, size, 0);
 
-	return mmc_test_transfer(test, &sg, 1, 0, size/512, 512, 0);
+	return mmc_test_transfer(test, &sg, 1, 0, size / 512, 512, 0);
 }
 
 #else
@@ -1533,7 +1536,7 @@ static int mmc_test_area_cleanup(struct mmc_test_card *test)
 
 /*
  * Initialize an area for testing large transfers.  The test area is set to the
- * middle of the card because cards may have different charateristics at the
+ * middle of the card because cards may have different characteristics at the
  * front (for FAT file system optimization).  Optionally, the area is erased
  * (if the card supports it) which may improve write performance.  Optionally,
  * the area is filled with data for subsequent read tests.
@@ -1579,7 +1582,7 @@ static int mmc_test_area_init(struct mmc_test_card *test, int erase, int fill)
 	if (!t->mem)
 		return -ENOMEM;
 
-	t->sg = kmalloc(sizeof(struct scatterlist) * t->max_segs, GFP_KERNEL);
+	t->sg = kmalloc_array(t->max_segs, sizeof(*t->sg), GFP_KERNEL);
 	if (!t->sg) {
 		ret = -ENOMEM;
 		goto out_free;
@@ -2147,7 +2150,7 @@ static int mmc_test_rw_multiple_sg_len(struct mmc_test_card *test,
 	int i;
 
 	for (i = 0 ; i < rw->len && ret == 0; i++) {
-		ret = mmc_test_rw_multiple(test, rw, 512*1024, rw->size,
+		ret = mmc_test_rw_multiple(test, rw, 512 * 1024, rw->size,
 					   rw->sg_len[i]);
 		if (ret)
 			break;
@@ -2399,7 +2402,7 @@ static int mmc_test_ongoing_transfer(struct mmc_test_card *test,
 
 	/* Start ongoing data request */
 	if (use_areq) {
-		mmc_start_req(host, &test_areq.areq, &blkstat);
+		mmc_start_areq(host, &test_areq.areq, &blkstat);
 		if (blkstat != MMC_BLK_SUCCESS) {
 			ret = RESULT_FAIL;
 			goto out_free;
@@ -2437,7 +2440,7 @@ static int mmc_test_ongoing_transfer(struct mmc_test_card *test,
 
 	/* Wait for data request to complete */
 	if (use_areq) {
-		mmc_start_req(host, NULL, &blkstat);
+		mmc_start_areq(host, NULL, &blkstat);
 		if (blkstat != MMC_BLK_SUCCESS)
 			ret = RESULT_FAIL;
 	} else {
@@ -2954,7 +2957,7 @@ static void mmc_test_run(struct mmc_test_card *test, int testcase)
 
 	mmc_claim_host(test->card->host);
 
-	for (i = 0;i < ARRAY_SIZE(mmc_test_cases);i++) {
+	for (i = 0; i < ARRAY_SIZE(mmc_test_cases); i++) {
 		struct mmc_test_general_result *gr;
 
 		if (testcase && ((i + 1) != testcase))
@@ -2967,16 +2970,14 @@ static void mmc_test_run(struct mmc_test_card *test, int testcase)
 		if (mmc_test_cases[i].prepare) {
 			ret = mmc_test_cases[i].prepare(test);
 			if (ret) {
-				pr_info("%s: Result: Prepare "
-					"stage failed! (%d)\n",
+				pr_info("%s: Result: Prepare stage failed! (%d)\n",
 					mmc_hostname(test->card->host),
 					ret);
 				continue;
 			}
 		}
 
-		gr = kzalloc(sizeof(struct mmc_test_general_result),
-			GFP_KERNEL);
+		gr = kzalloc(sizeof(*gr), GFP_KERNEL);
 		if (gr) {
 			INIT_LIST_HEAD(&gr->tr_lst);
 
@@ -3005,13 +3006,11 @@ static void mmc_test_run(struct mmc_test_card *test, int testcase)
 				mmc_hostname(test->card->host));
 			break;
 		case RESULT_UNSUP_HOST:
-			pr_info("%s: Result: UNSUPPORTED "
-				"(by host)\n",
+			pr_info("%s: Result: UNSUPPORTED (by host)\n",
 				mmc_hostname(test->card->host));
 			break;
 		case RESULT_UNSUP_CARD:
-			pr_info("%s: Result: UNSUPPORTED "
-				"(by card)\n",
+			pr_info("%s: Result: UNSUPPORTED (by card)\n",
 				mmc_hostname(test->card->host));
 			break;
 		default:
@@ -3026,8 +3025,7 @@ static void mmc_test_run(struct mmc_test_card *test, int testcase)
 		if (mmc_test_cases[i].cleanup) {
 			ret = mmc_test_cases[i].cleanup(test);
 			if (ret) {
-				pr_info("%s: Warning: Cleanup "
-					"stage failed! (%d)\n",
+				pr_info("%s: Warning: Cleanup stage failed! (%d)\n",
 					mmc_hostname(test->card->host),
 					ret);
 			}
@@ -3113,7 +3111,7 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf,
 	if (ret)
 		return ret;
 
-	test = kzalloc(sizeof(struct mmc_test_card), GFP_KERNEL);
+	test = kzalloc(sizeof(*test), GFP_KERNEL);
 	if (!test)
 		return -ENOMEM;
 
@@ -3163,9 +3161,9 @@ static int mtf_testlist_show(struct seq_file *sf, void *data)
 
 	mutex_lock(&mmc_test_lock);
 
-	seq_printf(sf, "0:\tRun all tests\n");
+	seq_puts(sf, "0:\tRun all tests\n");
 	for (i = 0; i < ARRAY_SIZE(mmc_test_cases); i++)
-		seq_printf(sf, "%d:\t%s\n", i+1, mmc_test_cases[i].name);
+		seq_printf(sf, "%d:\t%s\n", i + 1, mmc_test_cases[i].name);
 
 	mutex_unlock(&mmc_test_lock);
 
@@ -3218,7 +3216,7 @@ static int __mmc_test_register_dbgfs_file(struct mmc_card *card,
 		return -ENODEV;
 	}
 
-	df = kmalloc(sizeof(struct mmc_test_dbgfs_file), GFP_KERNEL);
+	df = kmalloc(sizeof(*df), GFP_KERNEL);
 	if (!df) {
 		debugfs_remove(file);
 		dev_err(&card->dev,
diff --git a/drivers/mmc/core/pwrseq.h b/drivers/mmc/core/pwrseq.h
index d69e751f148b..39c911aa6ebb 100644
--- a/drivers/mmc/core/pwrseq.h
+++ b/drivers/mmc/core/pwrseq.h
@@ -8,7 +8,11 @@
 #ifndef _MMC_CORE_PWRSEQ_H
 #define _MMC_CORE_PWRSEQ_H
 
-#include <linux/mmc/host.h>
+#include <linux/types.h>
+
+struct mmc_host;
+struct device;
+struct module;
 
 struct mmc_pwrseq_ops {
 	void (*pre_power_on)(struct mmc_host *host);
diff --git a/drivers/mmc/core/pwrseq_sd8787.c b/drivers/mmc/core/pwrseq_sd8787.c
new file mode 100644
index 000000000000..1a21e14458d3
--- /dev/null
+++ b/drivers/mmc/core/pwrseq_sd8787.c
@@ -0,0 +1,117 @@
+/*
+ * pwrseq_sd8787.c - power sequence support for Marvell SD8787 BT + Wifi chip
+ *
+ * Copyright (C) 2016 Matt Ranostay <matt@ranostay.consulting>
+ *
+ * Based on the original work pwrseq_simple.c
+ *  Copyright (C) 2014 Linaro Ltd
+ *  Author: Ulf Hansson <ulf.hansson@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+
+#include <linux/mmc/host.h>
+
+#include "pwrseq.h"
+
+struct mmc_pwrseq_sd8787 {
+	struct mmc_pwrseq pwrseq;
+	struct gpio_desc *reset_gpio;
+	struct gpio_desc *pwrdn_gpio;
+};
+
+#define to_pwrseq_sd8787(p) container_of(p, struct mmc_pwrseq_sd8787, pwrseq)
+
+static void mmc_pwrseq_sd8787_pre_power_on(struct mmc_host *host)
+{
+	struct mmc_pwrseq_sd8787 *pwrseq = to_pwrseq_sd8787(host->pwrseq);
+
+	gpiod_set_value_cansleep(pwrseq->reset_gpio, 1);
+
+	msleep(300);
+	gpiod_set_value_cansleep(pwrseq->pwrdn_gpio, 1);
+}
+
+static void mmc_pwrseq_sd8787_power_off(struct mmc_host *host)
+{
+	struct mmc_pwrseq_sd8787 *pwrseq = to_pwrseq_sd8787(host->pwrseq);
+
+	gpiod_set_value_cansleep(pwrseq->pwrdn_gpio, 0);
+	gpiod_set_value_cansleep(pwrseq->reset_gpio, 0);
+}
+
+static const struct mmc_pwrseq_ops mmc_pwrseq_sd8787_ops = {
+	.pre_power_on = mmc_pwrseq_sd8787_pre_power_on,
+	.power_off = mmc_pwrseq_sd8787_power_off,
+};
+
+static const struct of_device_id mmc_pwrseq_sd8787_of_match[] = {
+	{ .compatible = "mmc-pwrseq-sd8787",},
+	{/* sentinel */},
+};
+MODULE_DEVICE_TABLE(of, mmc_pwrseq_sd8787_of_match);
+
+static int mmc_pwrseq_sd8787_probe(struct platform_device *pdev)
+{
+	struct mmc_pwrseq_sd8787 *pwrseq;
+	struct device *dev = &pdev->dev;
+
+	pwrseq = devm_kzalloc(dev, sizeof(*pwrseq), GFP_KERNEL);
+	if (!pwrseq)
+		return -ENOMEM;
+
+	pwrseq->pwrdn_gpio = devm_gpiod_get(dev, "powerdown", GPIOD_OUT_LOW);
+	if (IS_ERR(pwrseq->pwrdn_gpio))
+		return PTR_ERR(pwrseq->pwrdn_gpio);
+
+	pwrseq->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(pwrseq->reset_gpio))
+		return PTR_ERR(pwrseq->reset_gpio);
+
+	pwrseq->pwrseq.dev = dev;
+	pwrseq->pwrseq.ops = &mmc_pwrseq_sd8787_ops;
+	pwrseq->pwrseq.owner = THIS_MODULE;
+	platform_set_drvdata(pdev, pwrseq);
+
+	return mmc_pwrseq_register(&pwrseq->pwrseq);
+}
+
+static int mmc_pwrseq_sd8787_remove(struct platform_device *pdev)
+{
+	struct mmc_pwrseq_sd8787 *pwrseq = platform_get_drvdata(pdev);
+
+	mmc_pwrseq_unregister(&pwrseq->pwrseq);
+
+	return 0;
+}
+
+static struct platform_driver mmc_pwrseq_sd8787_driver = {
+	.probe = mmc_pwrseq_sd8787_probe,
+	.remove = mmc_pwrseq_sd8787_remove,
+	.driver = {
+		.name = "pwrseq_sd8787",
+		.of_match_table = mmc_pwrseq_sd8787_of_match,
+	},
+};
+
+module_platform_driver(mmc_pwrseq_sd8787_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index a6496d8027bc..493eb10ce580 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -20,6 +20,8 @@
 
 #include "queue.h"
 #include "block.h"
+#include "core.h"
+#include "card.h"
 
 #define MMC_QUEUE_BOUNCESZ	65536
 
@@ -30,15 +32,6 @@ static int mmc_prep_request(struct request_queue *q, struct request *req)
 {
 	struct mmc_queue *mq = q->queuedata;
 
-	/*
-	 * We only like normal block requests and discards.
-	 */
-	if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD &&
-	    req_op(req) != REQ_OP_SECURE_ERASE) {
-		blk_dump_rq_flags(req, "MMC bad request");
-		return BLKPREP_KILL;
-	}
-
 	if (mq && (mmc_card_removed(mq->card) || mmc_access_rpmb(mq)))
 		return BLKPREP_KILL;
 
@@ -84,8 +77,8 @@ static int mmc_queue_thread(void *d)
 			set_current_state(TASK_RUNNING);
 			mmc_blk_issue_rq(mq, req);
 			cond_resched();
-			if (mq->flags & MMC_QUEUE_NEW_REQUEST) {
-				mq->flags &= ~MMC_QUEUE_NEW_REQUEST;
+			if (mq->new_request) {
+				mq->new_request = false;
 				continue; /* fetch again */
 			}
 
@@ -152,7 +145,7 @@ static struct scatterlist *mmc_alloc_sg(int sg_len, int *err)
 {
 	struct scatterlist *sg;
 
-	sg = kmalloc(sizeof(struct scatterlist)*sg_len, GFP_KERNEL);
+	sg = kmalloc_array(sg_len, sizeof(*sg), GFP_KERNEL);
 	if (!sg)
 		*err = -ENOMEM;
 	else {
@@ -399,8 +392,8 @@ void mmc_queue_suspend(struct mmc_queue *mq)
 	struct request_queue *q = mq->queue;
 	unsigned long flags;
 
-	if (!(mq->flags & MMC_QUEUE_SUSPENDED)) {
-		mq->flags |= MMC_QUEUE_SUSPENDED;
+	if (!mq->suspended) {
+		mq->suspended |= true;
 
 		spin_lock_irqsave(q->queue_lock, flags);
 		blk_stop_queue(q);
@@ -419,8 +412,8 @@ void mmc_queue_resume(struct mmc_queue *mq)
 	struct request_queue *q = mq->queue;
 	unsigned long flags;
 
-	if (mq->flags & MMC_QUEUE_SUSPENDED) {
-		mq->flags &= ~MMC_QUEUE_SUSPENDED;
+	if (mq->suspended) {
+		mq->suspended = false;
 
 		up(&mq->thread_sem);
 
diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h
index dac8c3d010dd..e298f100101b 100644
--- a/drivers/mmc/core/queue.h
+++ b/drivers/mmc/core/queue.h
@@ -1,6 +1,11 @@
 #ifndef MMC_QUEUE_H
 #define MMC_QUEUE_H
 
+#include <linux/types.h>
+#include <linux/blkdev.h>
+#include <linux/mmc/core.h>
+#include <linux/mmc/host.h>
+
 static inline bool mmc_req_is_special(struct request *req)
 {
 	return req &&
@@ -9,7 +14,6 @@ static inline bool mmc_req_is_special(struct request *req)
 		 req_op(req) == REQ_OP_SECURE_ERASE);
 }
 
-struct request;
 struct task_struct;
 struct mmc_blk_data;
 
@@ -29,16 +33,15 @@ struct mmc_queue_req {
 	char			*bounce_buf;
 	struct scatterlist	*bounce_sg;
 	unsigned int		bounce_sg_len;
-	struct mmc_async_req	mmc_active;
+	struct mmc_async_req	areq;
 };
 
 struct mmc_queue {
 	struct mmc_card		*card;
 	struct task_struct	*thread;
 	struct semaphore	thread_sem;
-	unsigned int		flags;
-#define MMC_QUEUE_SUSPENDED	(1 << 0)
-#define MMC_QUEUE_NEW_REQUEST	(1 << 1)
+	bool			new_request;
+	bool			suspended;
 	bool			asleep;
 	struct mmc_blk_data	*blkdata;
 	struct request_queue	*queue;
diff --git a/drivers/mmc/core/quirks.c b/drivers/mmc/core/quirks.c
deleted file mode 100644
index ca9cade317c7..000000000000
--- a/drivers/mmc/core/quirks.c
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- *  This file contains work-arounds for many known SD/MMC
- *  and SDIO hardware bugs.
- *
- *  Copyright (c) 2011 Andrei Warkentin <andreiw@motorola.com>
- *  Copyright (c) 2011 Pierre Tardy <tardyp@gmail.com>
- *  Inspired from pci fixup code:
- *  Copyright (c) 1999 Martin Mares <mj@ucw.cz>
- *
- */
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/export.h>
-#include <linux/mmc/card.h>
-#include <linux/mmc/sdio_ids.h>
-
-#ifndef SDIO_VENDOR_ID_TI
-#define SDIO_VENDOR_ID_TI		0x0097
-#endif
-
-#ifndef SDIO_DEVICE_ID_TI_WL1271
-#define SDIO_DEVICE_ID_TI_WL1271	0x4076
-#endif
-
-#ifndef SDIO_VENDOR_ID_STE
-#define SDIO_VENDOR_ID_STE		0x0020
-#endif
-
-#ifndef SDIO_DEVICE_ID_STE_CW1200
-#define SDIO_DEVICE_ID_STE_CW1200	0x2280
-#endif
-
-#ifndef SDIO_DEVICE_ID_MARVELL_8797_F0
-#define SDIO_DEVICE_ID_MARVELL_8797_F0	0x9128
-#endif
-
-static const struct mmc_fixup mmc_fixup_methods[] = {
-	SDIO_FIXUP(SDIO_VENDOR_ID_TI, SDIO_DEVICE_ID_TI_WL1271,
-		   add_quirk, MMC_QUIRK_NONSTD_FUNC_IF),
-
-	SDIO_FIXUP(SDIO_VENDOR_ID_TI, SDIO_DEVICE_ID_TI_WL1271,
-		   add_quirk, MMC_QUIRK_DISABLE_CD),
-
-	SDIO_FIXUP(SDIO_VENDOR_ID_STE, SDIO_DEVICE_ID_STE_CW1200,
-		   add_quirk, MMC_QUIRK_BROKEN_BYTE_MODE_512),
-
-	SDIO_FIXUP(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8797_F0,
-		   add_quirk, MMC_QUIRK_BROKEN_IRQ_POLLING),
-
-	END_FIXUP
-};
-
-void mmc_fixup_device(struct mmc_card *card, const struct mmc_fixup *table)
-{
-	const struct mmc_fixup *f;
-	u64 rev = cid_rev_card(card);
-
-	/* Non-core specific workarounds. */
-	if (!table)
-		table = mmc_fixup_methods;
-
-	for (f = table; f->vendor_fixup; f++) {
-		if ((f->manfid == CID_MANFID_ANY ||
-		     f->manfid == card->cid.manfid) &&
-		    (f->oemid == CID_OEMID_ANY ||
-		     f->oemid == card->cid.oemid) &&
-		    (f->name == CID_NAME_ANY ||
-		     !strncmp(f->name, card->cid.prod_name,
-			      sizeof(card->cid.prod_name))) &&
-		    (f->cis_vendor == card->cis.vendor ||
-		     f->cis_vendor == (u16) SDIO_ANY_ID) &&
-		    (f->cis_device == card->cis.device ||
-		     f->cis_device == (u16) SDIO_ANY_ID) &&
-		    (f->ext_csd_rev == EXT_CSD_REV_ANY ||
-		     f->ext_csd_rev == card->ext_csd.rev) &&
-		    rev >= f->rev_start && rev <= f->rev_end) {
-			dev_dbg(&card->dev, "calling %pf\n", f->vendor_fixup);
-			f->vendor_fixup(card, f->data);
-		}
-	}
-}
-EXPORT_SYMBOL(mmc_fixup_device);
diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h
new file mode 100644
index 000000000000..fb725934fa21
--- /dev/null
+++ b/drivers/mmc/core/quirks.h
@@ -0,0 +1,148 @@
+/*
+ *  This file contains work-arounds for many known SD/MMC
+ *  and SDIO hardware bugs.
+ *
+ *  Copyright (c) 2011 Andrei Warkentin <andreiw@motorola.com>
+ *  Copyright (c) 2011 Pierre Tardy <tardyp@gmail.com>
+ *  Inspired from pci fixup code:
+ *  Copyright (c) 1999 Martin Mares <mj@ucw.cz>
+ *
+ */
+
+#include <linux/mmc/sdio_ids.h>
+
+#include "card.h"
+
+static const struct mmc_fixup mmc_blk_fixups[] = {
+#define INAND_CMD38_ARG_EXT_CSD  113
+#define INAND_CMD38_ARG_ERASE    0x00
+#define INAND_CMD38_ARG_TRIM     0x01
+#define INAND_CMD38_ARG_SECERASE 0x80
+#define INAND_CMD38_ARG_SECTRIM1 0x81
+#define INAND_CMD38_ARG_SECTRIM2 0x88
+	/* CMD38 argument is passed through EXT_CSD[113] */
+	MMC_FIXUP("SEM02G", CID_MANFID_SANDISK, 0x100, add_quirk,
+		  MMC_QUIRK_INAND_CMD38),
+	MMC_FIXUP("SEM04G", CID_MANFID_SANDISK, 0x100, add_quirk,
+		  MMC_QUIRK_INAND_CMD38),
+	MMC_FIXUP("SEM08G", CID_MANFID_SANDISK, 0x100, add_quirk,
+		  MMC_QUIRK_INAND_CMD38),
+	MMC_FIXUP("SEM16G", CID_MANFID_SANDISK, 0x100, add_quirk,
+		  MMC_QUIRK_INAND_CMD38),
+	MMC_FIXUP("SEM32G", CID_MANFID_SANDISK, 0x100, add_quirk,
+		  MMC_QUIRK_INAND_CMD38),
+
+	/*
+	 * Some MMC cards experience performance degradation with CMD23
+	 * instead of CMD12-bounded multiblock transfers. For now we'll
+	 * black list what's bad...
+	 * - Certain Toshiba cards.
+	 *
+	 * N.B. This doesn't affect SD cards.
+	 */
+	MMC_FIXUP("SDMB-32", CID_MANFID_SANDISK, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_BLK_NO_CMD23),
+	MMC_FIXUP("SDM032", CID_MANFID_SANDISK, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_BLK_NO_CMD23),
+	MMC_FIXUP("MMC08G", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_BLK_NO_CMD23),
+	MMC_FIXUP("MMC16G", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_BLK_NO_CMD23),
+	MMC_FIXUP("MMC32G", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_BLK_NO_CMD23),
+
+	/*
+	 * Some MMC cards need longer data read timeout than indicated in CSD.
+	 */
+	MMC_FIXUP(CID_NAME_ANY, CID_MANFID_MICRON, 0x200, add_quirk_mmc,
+		  MMC_QUIRK_LONG_READ_TIME),
+	MMC_FIXUP("008GE0", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_LONG_READ_TIME),
+
+	/*
+	 * On these Samsung MoviNAND parts, performing secure erase or
+	 * secure trim can result in unrecoverable corruption due to a
+	 * firmware bug.
+	 */
+	MMC_FIXUP("M8G2FA", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
+	MMC_FIXUP("MAG4FA", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
+	MMC_FIXUP("MBG8FA", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
+	MMC_FIXUP("MCGAFA", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
+	MMC_FIXUP("VAL00M", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
+	MMC_FIXUP("VYL00M", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
+	MMC_FIXUP("KYL00M", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
+	MMC_FIXUP("VZL00M", CID_MANFID_SAMSUNG, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_SEC_ERASE_TRIM_BROKEN),
+
+	/*
+	 *  On Some Kingston eMMCs, performing trim can result in
+	 *  unrecoverable data conrruption occasionally due to a firmware bug.
+	 */
+	MMC_FIXUP("V10008", CID_MANFID_KINGSTON, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_TRIM_BROKEN),
+	MMC_FIXUP("V10016", CID_MANFID_KINGSTON, CID_OEMID_ANY, add_quirk_mmc,
+		  MMC_QUIRK_TRIM_BROKEN),
+
+	END_FIXUP
+};
+
+static const struct mmc_fixup mmc_ext_csd_fixups[] = {
+	/*
+	 * Certain Hynix eMMC 4.41 cards might get broken when HPI feature
+	 * is used so disable the HPI feature for such buggy cards.
+	 */
+	MMC_FIXUP_EXT_CSD_REV(CID_NAME_ANY, CID_MANFID_HYNIX,
+			      0x014a, add_quirk, MMC_QUIRK_BROKEN_HPI, 5),
+
+	END_FIXUP
+};
+
+static const struct mmc_fixup sdio_fixup_methods[] = {
+	SDIO_FIXUP(SDIO_VENDOR_ID_TI, SDIO_DEVICE_ID_TI_WL1271,
+		   add_quirk, MMC_QUIRK_NONSTD_FUNC_IF),
+
+	SDIO_FIXUP(SDIO_VENDOR_ID_TI, SDIO_DEVICE_ID_TI_WL1271,
+		   add_quirk, MMC_QUIRK_DISABLE_CD),
+
+	SDIO_FIXUP(SDIO_VENDOR_ID_STE, SDIO_DEVICE_ID_STE_CW1200,
+		   add_quirk, MMC_QUIRK_BROKEN_BYTE_MODE_512),
+
+	SDIO_FIXUP(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8797_F0,
+		   add_quirk, MMC_QUIRK_BROKEN_IRQ_POLLING),
+
+	END_FIXUP
+};
+
+static inline void mmc_fixup_device(struct mmc_card *card,
+				    const struct mmc_fixup *table)
+{
+	const struct mmc_fixup *f;
+	u64 rev = cid_rev_card(card);
+
+	for (f = table; f->vendor_fixup; f++) {
+		if ((f->manfid == CID_MANFID_ANY ||
+		     f->manfid == card->cid.manfid) &&
+		    (f->oemid == CID_OEMID_ANY ||
+		     f->oemid == card->cid.oemid) &&
+		    (f->name == CID_NAME_ANY ||
+		     !strncmp(f->name, card->cid.prod_name,
+			      sizeof(card->cid.prod_name))) &&
+		    (f->cis_vendor == card->cis.vendor ||
+		     f->cis_vendor == (u16) SDIO_ANY_ID) &&
+		    (f->cis_device == card->cis.device ||
+		     f->cis_device == (u16) SDIO_ANY_ID) &&
+		    (f->ext_csd_rev == EXT_CSD_REV_ANY ||
+		     f->ext_csd_rev == card->ext_csd.rev) &&
+		    rev >= f->rev_start && rev <= f->rev_end) {
+			dev_dbg(&card->dev, "calling %pf\n", f->vendor_fixup);
+			f->vendor_fixup(card, f->data);
+		}
+	}
+}
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index a614f37faf27..89531b48ae84 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -22,6 +22,8 @@
 #include <linux/mmc/sd.h>
 
 #include "core.h"
+#include "card.h"
+#include "host.h"
 #include "bus.h"
 #include "mmc_ops.h"
 #include "sd.h"
@@ -786,8 +788,7 @@ try_again:
 	 */
 	if (!mmc_host_is_spi(host) && rocr &&
 	   ((*rocr & 0x41000000) == 0x41000000)) {
-		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180,
-					pocr);
+		err = mmc_set_uhs_voltage(host, pocr);
 		if (err == -EAGAIN) {
 			retries--;
 			goto try_again;
diff --git a/drivers/mmc/core/sd.h b/drivers/mmc/core/sd.h
index aab824a9a7f3..1ada9808c329 100644
--- a/drivers/mmc/core/sd.h
+++ b/drivers/mmc/core/sd.h
@@ -1,10 +1,13 @@
 #ifndef _MMC_CORE_SD_H
 #define _MMC_CORE_SD_H
 
-#include <linux/mmc/card.h>
+#include <linux/types.h>
 
 extern struct device_type sd_type;
 
+struct mmc_host;
+struct mmc_card;
+
 int mmc_sd_get_cid(struct mmc_host *host, u32 ocr, u32 *cid, u32 *rocr);
 int mmc_sd_get_csd(struct mmc_host *host, struct mmc_card *card);
 void mmc_decode_cid(struct mmc_card *card);
diff --git a/drivers/mmc/core/sd_ops.c b/drivers/mmc/core/sd_ops.c
index de125a41aa7a..9d5824a37586 100644
--- a/drivers/mmc/core/sd_ops.c
+++ b/drivers/mmc/core/sd_ops.c
@@ -25,7 +25,7 @@
 int mmc_app_cmd(struct mmc_host *host, struct mmc_card *card)
 {
 	int err;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	if (WARN_ON(card && card->host != host))
 		return -EINVAL;
@@ -68,7 +68,7 @@ EXPORT_SYMBOL_GPL(mmc_app_cmd);
 int mmc_wait_for_app_cmd(struct mmc_host *host, struct mmc_card *card,
 	struct mmc_command *cmd, int retries)
 {
-	struct mmc_request mrq = {NULL};
+	struct mmc_request mrq = {};
 
 	int i, err;
 
@@ -120,7 +120,7 @@ EXPORT_SYMBOL(mmc_wait_for_app_cmd);
 
 int mmc_app_set_bus_width(struct mmc_card *card, int width)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	cmd.opcode = SD_APP_SET_BUS_WIDTH;
 	cmd.flags = MMC_RSP_R1 | MMC_CMD_AC;
@@ -141,7 +141,7 @@ int mmc_app_set_bus_width(struct mmc_card *card, int width)
 
 int mmc_send_app_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	int i, err = 0;
 
 	cmd.opcode = SD_APP_OP_COND;
@@ -185,7 +185,7 @@ int mmc_send_app_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr)
 
 int mmc_send_if_cond(struct mmc_host *host, u32 ocr)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	int err;
 	static const u8 test_pattern = 0xAA;
 	u8 result_pattern;
@@ -217,7 +217,7 @@ int mmc_send_if_cond(struct mmc_host *host, u32 ocr)
 int mmc_send_relative_addr(struct mmc_host *host, unsigned int *rca)
 {
 	int err;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	cmd.opcode = SD_SEND_RELATIVE_ADDR;
 	cmd.arg = 0;
@@ -235,9 +235,9 @@ int mmc_send_relative_addr(struct mmc_host *host, unsigned int *rca)
 int mmc_app_send_scr(struct mmc_card *card, u32 *scr)
 {
 	int err;
-	struct mmc_request mrq = {NULL};
-	struct mmc_command cmd = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_data data = {};
 	struct scatterlist sg;
 	void *data_buf;
 
@@ -290,9 +290,9 @@ int mmc_app_send_scr(struct mmc_card *card, u32 *scr)
 int mmc_sd_switch(struct mmc_card *card, int mode, int group,
 	u8 value, u8 *resp)
 {
-	struct mmc_request mrq = {NULL};
-	struct mmc_command cmd = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_data data = {};
 	struct scatterlist sg;
 
 	/* NOTE: caller guarantees resp is heap-allocated */
@@ -332,9 +332,9 @@ int mmc_sd_switch(struct mmc_card *card, int mode, int group,
 int mmc_app_sd_status(struct mmc_card *card, void *ssr)
 {
 	int err;
-	struct mmc_request mrq = {NULL};
-	struct mmc_command cmd = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_data data = {};
 	struct scatterlist sg;
 
 	/* NOTE: caller guarantees ssr is heap-allocated */
diff --git a/drivers/mmc/core/sd_ops.h b/drivers/mmc/core/sd_ops.h
index ffc2305d905f..784f8e6b6baa 100644
--- a/drivers/mmc/core/sd_ops.h
+++ b/drivers/mmc/core/sd_ops.h
@@ -12,6 +12,12 @@
 #ifndef _MMC_SD_OPS_H
 #define _MMC_SD_OPS_H
 
+#include <linux/types.h>
+
+struct mmc_card;
+struct mmc_host;
+struct mmc_command;
+
 int mmc_app_set_bus_width(struct mmc_card *card, int width);
 int mmc_send_app_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr);
 int mmc_send_if_cond(struct mmc_host *host, u32 ocr);
@@ -20,6 +26,9 @@ int mmc_app_send_scr(struct mmc_card *card, u32 *scr);
 int mmc_sd_switch(struct mmc_card *card, int mode, int group,
 	u8 value, u8 *resp);
 int mmc_app_sd_status(struct mmc_card *card, void *ssr);
+int mmc_app_cmd(struct mmc_host *host, struct mmc_card *card);
+int mmc_wait_for_app_cmd(struct mmc_host *host, struct mmc_card *card,
+	struct mmc_command *cmd, int retries);
 
 #endif
 
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index ecbc52981ba5..fae732c870a9 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -20,7 +20,10 @@
 #include <linux/mmc/sdio_ids.h>
 
 #include "core.h"
+#include "card.h"
+#include "host.h"
 #include "bus.h"
+#include "quirks.h"
 #include "sd.h"
 #include "sdio_bus.h"
 #include "mmc_ops.h"
@@ -541,6 +544,15 @@ out:
 	return err;
 }
 
+static void mmc_sdio_resend_if_cond(struct mmc_host *host,
+				    struct mmc_card *card)
+{
+	sdio_reset(host);
+	mmc_go_idle(host);
+	mmc_send_if_cond(host, host->ocr_avail);
+	mmc_remove_card(card);
+}
+
 /*
  * Handle the detection and initialisation of a card.
  *
@@ -624,24 +636,21 @@ try_again:
 	 * to switch to 1.8V signaling level.  No 1.8v signalling if
 	 * UHS mode is not enabled to maintain compatibility and some
 	 * systems that claim 1.8v signalling in fact do not support
-	 * it.
+	 * it. Per SDIO spec v3, section 3.1.2, if the voltage is already
+	 * 1.8v, the card sets S18A to 0 in the R4 response. So it will
+	 * fails to check rocr & R4_18V_PRESENT,  but we still need to
+	 * try to init uhs card. sdio_read_cccr will take over this task
+	 * to make sure which speed mode should work.
 	 */
 	if (!powered_resume && (rocr & ocr & R4_18V_PRESENT)) {
-		err = mmc_set_signal_voltage(host, MMC_SIGNAL_VOLTAGE_180,
-					ocr_card);
+		err = mmc_set_uhs_voltage(host, ocr_card);
 		if (err == -EAGAIN) {
-			sdio_reset(host);
-			mmc_go_idle(host);
-			mmc_send_if_cond(host, host->ocr_avail);
-			mmc_remove_card(card);
+			mmc_sdio_resend_if_cond(host, card);
 			retries--;
 			goto try_again;
 		} else if (err) {
 			ocr &= ~R4_18V_PRESENT;
 		}
-		err = 0;
-	} else {
-		ocr &= ~R4_18V_PRESENT;
 	}
 
 	/*
@@ -698,11 +707,20 @@ try_again:
 	}
 
 	/*
-	 * Read the common registers.
+	 * Read the common registers. Note that we should try to
+	 * validate whether UHS would work or not.
 	 */
 	err = sdio_read_cccr(card, ocr);
-	if (err)
-		goto remove;
+	if (err) {
+		mmc_sdio_resend_if_cond(host, card);
+		if (ocr & R4_18V_PRESENT) {
+			/* Retry init sequence, but without R4_18V_PRESENT. */
+			retries = 0;
+			goto try_again;
+		} else {
+			goto remove;
+		}
+	}
 
 	/*
 	 * Read the common CIS tuples.
@@ -721,7 +739,7 @@ try_again:
 		card = oldcard;
 	}
 	card->ocr = ocr_card;
-	mmc_fixup_device(card, NULL);
+	mmc_fixup_device(card, sdio_fixup_methods);
 
 	if (card->type == MMC_TYPE_SD_COMBO) {
 		err = mmc_sd_setup_card(host, card, oldcard != NULL);
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index 86f5b3223aae..e992a7f8a16f 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -25,6 +25,7 @@
 #include <linux/of.h>
 
 #include "core.h"
+#include "card.h"
 #include "sdio_cis.h"
 #include "sdio_bus.h"
 
diff --git a/drivers/mmc/core/sdio_bus.h b/drivers/mmc/core/sdio_bus.h
index 567a76821ba7..b69a2540a076 100644
--- a/drivers/mmc/core/sdio_bus.h
+++ b/drivers/mmc/core/sdio_bus.h
@@ -11,6 +11,9 @@
 #ifndef _MMC_CORE_SDIO_BUS_H
 #define _MMC_CORE_SDIO_BUS_H
 
+struct mmc_card;
+struct sdio_func;
+
 struct sdio_func *sdio_alloc_func(struct mmc_card *card);
 int sdio_add_func(struct sdio_func *func);
 void sdio_remove_func(struct sdio_func *func);
diff --git a/drivers/mmc/core/sdio_cis.h b/drivers/mmc/core/sdio_cis.h
index 4d903c2e425e..16aa563faa00 100644
--- a/drivers/mmc/core/sdio_cis.h
+++ b/drivers/mmc/core/sdio_cis.h
@@ -14,6 +14,9 @@
 #ifndef _MMC_SDIO_CIS_H
 #define _MMC_SDIO_CIS_H
 
+struct mmc_card;
+struct sdio_func;
+
 int sdio_read_common_cis(struct mmc_card *card);
 void sdio_free_common_cis(struct mmc_card *card);
 
diff --git a/drivers/mmc/core/sdio_io.c b/drivers/mmc/core/sdio_io.c
index 406e5f037e32..74195d772f5a 100644
--- a/drivers/mmc/core/sdio_io.c
+++ b/drivers/mmc/core/sdio_io.c
@@ -16,6 +16,8 @@
 #include <linux/mmc/sdio_func.h>
 
 #include "sdio_ops.h"
+#include "core.h"
+#include "card.h"
 
 /**
  *	sdio_claim_host - exclusively claim a bus for a certain SDIO function
diff --git a/drivers/mmc/core/sdio_irq.c b/drivers/mmc/core/sdio_irq.c
index f1faf9acc007..d29faf2addfe 100644
--- a/drivers/mmc/core/sdio_irq.c
+++ b/drivers/mmc/core/sdio_irq.c
@@ -27,6 +27,8 @@
 #include <linux/mmc/sdio_func.h>
 
 #include "sdio_ops.h"
+#include "core.h"
+#include "card.h"
 
 static int process_sdio_pending_irqs(struct mmc_host *host)
 {
diff --git a/drivers/mmc/core/sdio_ops.c b/drivers/mmc/core/sdio_ops.c
index 90fe5545c677..3c0d3ab4324c 100644
--- a/drivers/mmc/core/sdio_ops.c
+++ b/drivers/mmc/core/sdio_ops.c
@@ -21,7 +21,7 @@
 
 int mmc_send_io_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	int i, err = 0;
 
 	cmd.opcode = SD_IO_SEND_OP_COND;
@@ -66,7 +66,7 @@ int mmc_send_io_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr)
 static int mmc_io_rw_direct_host(struct mmc_host *host, int write, unsigned fn,
 	unsigned addr, u8 in, u8 *out)
 {
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 	int err;
 
 	if (fn > 7)
@@ -118,9 +118,9 @@ int mmc_io_rw_direct(struct mmc_card *card, int write, unsigned fn,
 int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 	unsigned addr, int incr_addr, u8 *buf, unsigned blocks, unsigned blksz)
 {
-	struct mmc_request mrq = {NULL};
-	struct mmc_command cmd = {0};
-	struct mmc_data data = {0};
+	struct mmc_request mrq = {};
+	struct mmc_command cmd = {};
+	struct mmc_data data = {};
 	struct scatterlist sg, *sg_ptr;
 	struct sg_table sgtable;
 	unsigned int nents, left_size, i;
diff --git a/drivers/mmc/core/sdio_ops.h b/drivers/mmc/core/sdio_ops.h
index 5660c7f459e9..bed8a8377fec 100644
--- a/drivers/mmc/core/sdio_ops.h
+++ b/drivers/mmc/core/sdio_ops.h
@@ -12,14 +12,19 @@
 #ifndef _MMC_SDIO_OPS_H
 #define _MMC_SDIO_OPS_H
 
+#include <linux/types.h>
 #include <linux/mmc/sdio.h>
 
+struct mmc_host;
+struct mmc_card;
+
 int mmc_send_io_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr);
 int mmc_io_rw_direct(struct mmc_card *card, int write, unsigned fn,
 	unsigned addr, u8 in, u8* out);
 int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 	unsigned addr, int incr_addr, u8 *buf, unsigned blocks, unsigned blksz);
 int sdio_reset(struct mmc_host *host);
+unsigned int mmc_align_data_size(struct mmc_card *card, unsigned int sz);
 
 static inline bool mmc_is_io_op(u32 opcode)
 {
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index babe591aea96..a8450a8701e4 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -235,9 +235,6 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 	struct gpio_desc *desc;
 	int ret;
 
-	if (!con_id)
-		con_id = ctx->cd_label;
-
 	desc = devm_gpiod_get_index(host->parent, con_id, idx, GPIOD_IN);
 	if (IS_ERR(desc))
 		return PTR_ERR(desc);
@@ -289,9 +286,6 @@ int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 	struct gpio_desc *desc;
 	int ret;
 
-	if (!con_id)
-		con_id = ctx->ro_label;
-
 	desc = devm_gpiod_get_index(host->parent, con_id, idx, GPIOD_IN);
 	if (IS_ERR(desc))
 		return PTR_ERR(desc);
diff --git a/drivers/mmc/core/slot-gpio.h b/drivers/mmc/core/slot-gpio.h
index 8c1854dc5d58..a06fd843f025 100644
--- a/drivers/mmc/core/slot-gpio.h
+++ b/drivers/mmc/core/slot-gpio.h
@@ -8,6 +8,8 @@
 #ifndef _MMC_CORE_SLOTGPIO_H
 #define _MMC_CORE_SLOTGPIO_H
 
+struct mmc_host;
+
 int mmc_gpio_alloc(struct mmc_host *host);
 
 #endif
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 2eb97014dc3f..f08691a58d7e 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -683,6 +683,15 @@ config MMC_DW_ROCKCHIP
 	  Synopsys DesignWare Memory Card Interface driver. Select this option
 	  for platforms based on RK3066, RK3188 and RK3288 SoC's.
 
+config MMC_DW_ZX
+	tristate "ZTE specific extensions for Synopsys DW Memory Card Interface"
+	depends on MMC_DW && ARCH_ZX
+	select MMC_DW_PLTFM
+	help
+	  This selects support for ZTE SoC specific extensions to the
+	  Synopsys DesignWare Memory Card Interface driver. Select this option
+	  for platforms based on ZX296718 SoC's.
+
 config MMC_SH_MMCIF
 	tristate "SuperH Internal MMCIF support"
 	depends on HAS_DMA
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index ccc9c4cba154..6d548c4ee2fa 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_MMC_DW_EXYNOS)	+= dw_mmc-exynos.o
 obj-$(CONFIG_MMC_DW_K3)		+= dw_mmc-k3.o
 obj-$(CONFIG_MMC_DW_PCI)	+= dw_mmc-pci.o
 obj-$(CONFIG_MMC_DW_ROCKCHIP)	+= dw_mmc-rockchip.o
+obj-$(CONFIG_MMC_DW_ZX)		+= dw_mmc-zx.o
 obj-$(CONFIG_MMC_SH_MMCIF)	+= sh_mmcif.o
 obj-$(CONFIG_MMC_JZ4740)	+= jz4740_mmc.o
 obj-$(CONFIG_MMC_VUB300)	+= vub300.o
diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c
index 36b5af8eadb8..1e2600da105f 100644
--- a/drivers/mmc/host/davinci_mmc.c
+++ b/drivers/mmc/host/davinci_mmc.c
@@ -36,6 +36,7 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/mmc/slot-gpio.h>
+#include <linux/interrupt.h>
 
 #include <linux/platform_data/mmc-davinci.h>
 
diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index e1335289316c..25691cca1881 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -13,7 +13,6 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/mmc/host.h>
-#include <linux/mmc/dw_mmc.h>
 #include <linux/mmc/mmc.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
diff --git a/drivers/mmc/host/dw_mmc-k3.c b/drivers/mmc/host/dw_mmc-k3.c
index 9821e6bd5d5e..e38fb0020bb1 100644
--- a/drivers/mmc/host/dw_mmc-k3.c
+++ b/drivers/mmc/host/dw_mmc-k3.c
@@ -11,7 +11,6 @@
 #include <linux/clk.h>
 #include <linux/mfd/syscon.h>
 #include <linux/mmc/host.h>
-#include <linux/mmc/dw_mmc.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/platform_device.h>
diff --git a/drivers/mmc/host/dw_mmc-pci.c b/drivers/mmc/host/dw_mmc-pci.c
index ab82796b01e2..ab8713297edb 100644
--- a/drivers/mmc/host/dw_mmc-pci.c
+++ b/drivers/mmc/host/dw_mmc-pci.c
@@ -18,7 +18,6 @@
 #include <linux/slab.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
-#include <linux/mmc/dw_mmc.h>
 #include "dw_mmc.h"
 
 #define PCI_BAR_NO 2
diff --git a/drivers/mmc/host/dw_mmc-pltfm.c b/drivers/mmc/host/dw_mmc-pltfm.c
index 1236d49ba36e..58c13e21bd5a 100644
--- a/drivers/mmc/host/dw_mmc-pltfm.c
+++ b/drivers/mmc/host/dw_mmc-pltfm.c
@@ -20,7 +20,6 @@
 #include <linux/slab.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/mmc.h>
-#include <linux/mmc/dw_mmc.h>
 #include <linux/of.h>
 #include <linux/clk.h>
 
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index 9a46e4694227..372fb6e948c1 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -11,7 +11,6 @@
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/mmc/host.h>
-#include <linux/mmc/dw_mmc.h>
 #include <linux/of_address.h>
 #include <linux/mmc/slot-gpio.h>
 #include <linux/pm_runtime.h>
diff --git a/drivers/mmc/host/dw_mmc-zx.c b/drivers/mmc/host/dw_mmc-zx.c
new file mode 100644
index 000000000000..d38e94ae2b85
--- /dev/null
+++ b/drivers/mmc/host/dw_mmc-zx.c
@@ -0,0 +1,241 @@
+/*
+ * ZX Specific Extensions for Synopsys DW Multimedia Card Interface driver
+ *
+ * Copyright (C) 2016, Linaro Ltd.
+ * Copyright (C) 2016, ZTE Corp.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/mfd/syscon.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include "dw_mmc.h"
+#include "dw_mmc-pltfm.h"
+#include "dw_mmc-zx.h"
+
+struct dw_mci_zx_priv_data {
+	struct regmap	*sysc_base;
+};
+
+enum delay_type {
+	DELAY_TYPE_READ,	/* read dqs delay */
+	DELAY_TYPE_CLK,		/* clk sample delay */
+};
+
+static int dw_mci_zx_emmc_set_delay(struct dw_mci *host, unsigned int delay,
+				    enum delay_type dflag)
+{
+	struct dw_mci_zx_priv_data *priv = host->priv;
+	struct regmap *sysc_base = priv->sysc_base;
+	unsigned int clksel;
+	unsigned int loop = 1000;
+	int ret;
+
+	if (!sysc_base)
+		return -EINVAL;
+
+	ret = regmap_update_bits(sysc_base, LB_AON_EMMC_CFG_REG0,
+				 PARA_HALF_CLK_MODE | PARA_DLL_BYPASS_MODE |
+				 PARA_PHASE_DET_SEL_MASK |
+				 PARA_DLL_LOCK_NUM_MASK |
+				 DLL_REG_SET | PARA_DLL_START_MASK,
+				 PARA_DLL_START(4) | PARA_DLL_LOCK_NUM(4));
+	if (ret)
+		return ret;
+
+	ret = regmap_read(sysc_base, LB_AON_EMMC_CFG_REG1, &clksel);
+	if (ret)
+		return ret;
+
+	if (dflag == DELAY_TYPE_CLK) {
+		clksel &= ~CLK_SAMP_DELAY_MASK;
+		clksel |= CLK_SAMP_DELAY(delay);
+	} else {
+		clksel &= ~READ_DQS_DELAY_MASK;
+		clksel |= READ_DQS_DELAY(delay);
+	}
+
+	regmap_write(sysc_base, LB_AON_EMMC_CFG_REG1, clksel);
+	regmap_update_bits(sysc_base, LB_AON_EMMC_CFG_REG0,
+			   PARA_DLL_START_MASK | PARA_DLL_LOCK_NUM_MASK |
+			   DLL_REG_SET,
+			   PARA_DLL_START(4) | PARA_DLL_LOCK_NUM(4) |
+			   DLL_REG_SET);
+
+	do {
+		ret = regmap_read(sysc_base, LB_AON_EMMC_CFG_REG2, &clksel);
+		if (ret)
+			return ret;
+
+	} while (--loop && !(clksel & ZX_DLL_LOCKED));
+
+	if (!loop) {
+		dev_err(host->dev, "Error: %s dll lock fail\n", __func__);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int dw_mci_zx_emmc_execute_tuning(struct dw_mci_slot *slot, u32 opcode)
+{
+	struct dw_mci *host = slot->host;
+	struct mmc_host *mmc = slot->mmc;
+	int ret, len = 0, start = 0, end = 0, delay, best = 0;
+
+	for (delay = 1; delay < 128; delay++) {
+		ret = dw_mci_zx_emmc_set_delay(host, delay, DELAY_TYPE_CLK);
+		if (!ret && mmc_send_tuning(mmc, opcode, NULL)) {
+			if (start >= 0) {
+				end = delay - 1;
+				/* check and update longest good range */
+				if ((end - start) > len) {
+					best = (start + end) >> 1;
+					len = end - start;
+				}
+			}
+			start = -1;
+			end = 0;
+			continue;
+		}
+		if (start < 0)
+			start = delay;
+	}
+
+	if (start >= 0) {
+		end = delay - 1;
+		if ((end - start) > len) {
+			best = (start + end) >> 1;
+			len = end - start;
+		}
+	}
+	if (best < 0)
+		return -EIO;
+
+	dev_info(host->dev, "%s best range: start %d end %d\n", __func__,
+		 start, end);
+	return dw_mci_zx_emmc_set_delay(host, best, DELAY_TYPE_CLK);
+}
+
+static int dw_mci_zx_prepare_hs400_tuning(struct dw_mci *host,
+					  struct mmc_ios *ios)
+{
+	int ret;
+
+	/* config phase shift as 90 degree */
+	ret = dw_mci_zx_emmc_set_delay(host, 32, DELAY_TYPE_READ);
+	if (ret < 0)
+		return -EIO;
+
+	return 0;
+}
+
+static int dw_mci_zx_execute_tuning(struct dw_mci_slot *slot, u32 opcode)
+{
+	struct dw_mci *host = slot->host;
+
+	if (host->verid == 0x290a) /* only for emmc */
+		return dw_mci_zx_emmc_execute_tuning(slot, opcode);
+	/* TODO: Add 0x210a dedicated tuning for sd/sdio */
+
+	return 0;
+}
+
+static int dw_mci_zx_parse_dt(struct dw_mci *host)
+{
+	struct device_node *np = host->dev->of_node;
+	struct device_node *node;
+	struct dw_mci_zx_priv_data *priv;
+	struct regmap *sysc_base;
+	int ret;
+
+	/* syscon is needed only by emmc */
+	node = of_parse_phandle(np, "zte,aon-syscon", 0);
+	if (node) {
+		sysc_base = syscon_node_to_regmap(node);
+		of_node_put(node);
+
+		if (IS_ERR(sysc_base)) {
+			ret = PTR_ERR(sysc_base);
+			if (ret != -EPROBE_DEFER)
+				dev_err(host->dev, "Can't get syscon: %d\n",
+					ret);
+			return ret;
+		}
+	} else {
+		return 0;
+	}
+
+	priv = devm_kzalloc(host->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	priv->sysc_base = sysc_base;
+	host->priv = priv;
+
+	return 0;
+}
+
+static unsigned long zx_dwmmc_caps[3] = {
+	MMC_CAP_CMD23,
+	MMC_CAP_CMD23,
+	MMC_CAP_CMD23,
+};
+
+static const struct dw_mci_drv_data zx_drv_data = {
+	.caps			= zx_dwmmc_caps,
+	.execute_tuning		= dw_mci_zx_execute_tuning,
+	.prepare_hs400_tuning	= dw_mci_zx_prepare_hs400_tuning,
+	.parse_dt               = dw_mci_zx_parse_dt,
+};
+
+static const struct of_device_id dw_mci_zx_match[] = {
+	{ .compatible = "zte,zx296718-dw-mshc", .data = &zx_drv_data},
+	{},
+};
+MODULE_DEVICE_TABLE(of, dw_mci_zx_match);
+
+static int dw_mci_zx_probe(struct platform_device *pdev)
+{
+	const struct dw_mci_drv_data *drv_data;
+	const struct of_device_id *match;
+
+	match = of_match_node(dw_mci_zx_match, pdev->dev.of_node);
+	drv_data = match->data;
+
+	return dw_mci_pltfm_register(pdev, drv_data);
+}
+
+static const struct dev_pm_ops dw_mci_zx_dev_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(dw_mci_runtime_suspend,
+			   dw_mci_runtime_resume,
+			   NULL)
+};
+
+static struct platform_driver dw_mci_zx_pltfm_driver = {
+	.probe		= dw_mci_zx_probe,
+	.remove		= dw_mci_pltfm_remove,
+	.driver		= {
+		.name		= "dwmmc_zx",
+		.of_match_table	= dw_mci_zx_match,
+		.pm		= &dw_mci_zx_dev_pm_ops,
+	},
+};
+
+module_platform_driver(dw_mci_zx_pltfm_driver);
+
+MODULE_DESCRIPTION("ZTE emmc/sd driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/dw_mmc-zx.h b/drivers/mmc/host/dw_mmc-zx.h
new file mode 100644
index 000000000000..f369997a39ec
--- /dev/null
+++ b/drivers/mmc/host/dw_mmc-zx.h
@@ -0,0 +1,31 @@
+#ifndef _DW_MMC_ZX_H_
+#define _DW_MMC_ZX_H_
+
+/* ZX296718 SoC specific DLL register offset. */
+#define LB_AON_EMMC_CFG_REG0  0x1B0
+#define LB_AON_EMMC_CFG_REG1  0x1B4
+#define LB_AON_EMMC_CFG_REG2  0x1B8
+
+/* LB_AON_EMMC_CFG_REG0 register defines */
+#define PARA_DLL_START(x)	((x) & 0xFF)
+#define PARA_DLL_START_MASK	0xFF
+#define DLL_REG_SET		BIT(8)
+#define PARA_DLL_LOCK_NUM(x)	(((x) & 7) << 16)
+#define PARA_DLL_LOCK_NUM_MASK  (7 << 16)
+#define PARA_PHASE_DET_SEL(x)	(((x) & 7) << 20)
+#define PARA_PHASE_DET_SEL_MASK	(7 << 20)
+#define PARA_DLL_BYPASS_MODE	BIT(23)
+#define PARA_HALF_CLK_MODE	BIT(24)
+
+/* LB_AON_EMMC_CFG_REG1 register defines */
+#define READ_DQS_DELAY(x)	((x) & 0x7F)
+#define READ_DQS_DELAY_MASK	(0x7F)
+#define READ_DQS_BYPASS_MODE	BIT(7)
+#define CLK_SAMP_DELAY(x)	(((x) & 0x7F) << 8)
+#define CLK_SAMP_DELAY_MASK	(0x7F << 8)
+#define CLK_SAMP_BYPASS_MODE	BIT(15)
+
+/* LB_AON_EMMC_CFG_REG2 register defines */
+#define ZX_DLL_LOCKED		BIT(2)
+
+#endif /* _DW_MMC_ZX_H_ */
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index b44306b886cb..a9ac0b457313 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -32,7 +32,6 @@
 #include <linux/mmc/mmc.h>
 #include <linux/mmc/sd.h>
 #include <linux/mmc/sdio.h>
-#include <linux/mmc/dw_mmc.h>
 #include <linux/bitops.h>
 #include <linux/regulator/consumer.h>
 #include <linux/of.h>
@@ -1113,11 +1112,15 @@ static void dw_mci_submit_data(struct dw_mci *host, struct mmc_data *data)
 		mci_writel(host, CTRL, temp);
 
 		/*
-		 * Use the initial fifoth_val for PIO mode.
+		 * Use the initial fifoth_val for PIO mode. If wm_algined
+		 * is set, we set watermark same as data size.
 		 * If next issued data may be transfered by DMA mode,
 		 * prev_blksz should be invalidated.
 		 */
-		mci_writel(host, FIFOTH, host->fifoth_val);
+		if (host->wm_aligned)
+			dw_mci_adjust_fifoth(host, data);
+		else
+			mci_writel(host, FIFOTH, host->fifoth_val);
 		host->prev_blksz = 0;
 	} else {
 		/*
@@ -1179,11 +1182,13 @@ static void dw_mci_setup_bus(struct dw_mci_slot *slot, bool force_clkinit)
 		if ((clock != slot->__clk_old &&
 			!test_bit(DW_MMC_CARD_NEEDS_POLL, &slot->flags)) ||
 			force_clkinit) {
-			dev_info(&slot->mmc->class_dev,
-				 "Bus speed (slot %d) = %dHz (slot req %dHz, actual %dHZ div = %d)\n",
-				 slot->id, host->bus_hz, clock,
-				 div ? ((host->bus_hz / div) >> 1) :
-				 host->bus_hz, div);
+			/* Silent the verbose log if calling from PM context */
+			if (!force_clkinit)
+				dev_info(&slot->mmc->class_dev,
+					 "Bus speed (slot %d) = %dHz (slot req %dHz, actual %dHZ div = %d)\n",
+					 slot->id, host->bus_hz, clock,
+					 div ? ((host->bus_hz / div) >> 1) :
+					 host->bus_hz, div);
 
 			/*
 			 * If card is polling, display the message only
@@ -2977,6 +2982,11 @@ static struct dw_mci_board *dw_mci_parse_dt(struct dw_mci *host)
 
 	of_property_read_u32(np, "card-detect-delay", &pdata->detect_delay_ms);
 
+	of_property_read_u32(np, "data-addr", &host->data_addr_override);
+
+	if (of_get_property(np, "fifo-watermark-aligned", NULL))
+		host->wm_aligned = true;
+
 	if (!of_property_read_u32(np, "clock-frequency", &clock_frequency))
 		pdata->bus_hz = clock_frequency;
 
@@ -3180,7 +3190,9 @@ int dw_mci_probe(struct dw_mci *host)
 	host->verid = SDMMC_GET_VERID(mci_readl(host, VERID));
 	dev_info(host->dev, "Version ID is %04x\n", host->verid);
 
-	if (host->verid < DW_MMC_240A)
+	if (host->data_addr_override)
+		host->fifo_reg = host->regs + host->data_addr_override;
+	else if (host->verid < DW_MMC_240A)
 		host->fifo_reg = host->regs + DATA_OFFSET;
 	else
 		host->fifo_reg = host->regs + DATA_240A_OFFSET;
@@ -3354,10 +3366,11 @@ int dw_mci_runtime_resume(struct device *dev)
 
 		if (!slot)
 			continue;
-		if (slot->mmc->pm_flags & MMC_PM_KEEP_POWER) {
+		if (slot->mmc->pm_flags & MMC_PM_KEEP_POWER)
 			dw_mci_set_ios(slot->mmc, &slot->mmc->ios);
-			dw_mci_setup_bus(slot, true);
-		}
+
+		/* Force setup bus to guarantee available clock output */
+		dw_mci_setup_bus(slot, true);
 	}
 
 	/* Now that slots are all setup, we can enable card detect */
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index c59465829387..ce347361f3dc 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -14,6 +14,269 @@
 #ifndef _DW_MMC_H_
 #define _DW_MMC_H_
 
+#include <linux/scatterlist.h>
+#include <linux/mmc/core.h>
+#include <linux/dmaengine.h>
+#include <linux/reset.h>
+#include <linux/interrupt.h>
+
+#define MAX_MCI_SLOTS	2
+
+enum dw_mci_state {
+	STATE_IDLE = 0,
+	STATE_SENDING_CMD,
+	STATE_SENDING_DATA,
+	STATE_DATA_BUSY,
+	STATE_SENDING_STOP,
+	STATE_DATA_ERROR,
+	STATE_SENDING_CMD11,
+	STATE_WAITING_CMD11_DONE,
+};
+
+enum {
+	EVENT_CMD_COMPLETE = 0,
+	EVENT_XFER_COMPLETE,
+	EVENT_DATA_COMPLETE,
+	EVENT_DATA_ERROR,
+};
+
+enum dw_mci_cookie {
+	COOKIE_UNMAPPED,
+	COOKIE_PRE_MAPPED,	/* mapped by pre_req() of dwmmc */
+	COOKIE_MAPPED,		/* mapped by prepare_data() of dwmmc */
+};
+
+struct mmc_data;
+
+enum {
+	TRANS_MODE_PIO = 0,
+	TRANS_MODE_IDMAC,
+	TRANS_MODE_EDMAC
+};
+
+struct dw_mci_dma_slave {
+	struct dma_chan *ch;
+	enum dma_transfer_direction direction;
+};
+
+/**
+ * struct dw_mci - MMC controller state shared between all slots
+ * @lock: Spinlock protecting the queue and associated data.
+ * @irq_lock: Spinlock protecting the INTMASK setting.
+ * @regs: Pointer to MMIO registers.
+ * @fifo_reg: Pointer to MMIO registers for data FIFO
+ * @sg: Scatterlist entry currently being processed by PIO code, if any.
+ * @sg_miter: PIO mapping scatterlist iterator.
+ * @cur_slot: The slot which is currently using the controller.
+ * @mrq: The request currently being processed on @cur_slot,
+ *	or NULL if the controller is idle.
+ * @cmd: The command currently being sent to the card, or NULL.
+ * @data: The data currently being transferred, or NULL if no data
+ *	transfer is in progress.
+ * @stop_abort: The command currently prepared for stoping transfer.
+ * @prev_blksz: The former transfer blksz record.
+ * @timing: Record of current ios timing.
+ * @use_dma: Whether DMA channel is initialized or not.
+ * @using_dma: Whether DMA is in use for the current transfer.
+ * @dma_64bit_address: Whether DMA supports 64-bit address mode or not.
+ * @sg_dma: Bus address of DMA buffer.
+ * @sg_cpu: Virtual address of DMA buffer.
+ * @dma_ops: Pointer to platform-specific DMA callbacks.
+ * @cmd_status: Snapshot of SR taken upon completion of the current
+ * @ring_size: Buffer size for idma descriptors.
+ *	command. Only valid when EVENT_CMD_COMPLETE is pending.
+ * @dms: structure of slave-dma private data.
+ * @phy_regs: physical address of controller's register map
+ * @data_status: Snapshot of SR taken upon completion of the current
+ *	data transfer. Only valid when EVENT_DATA_COMPLETE or
+ *	EVENT_DATA_ERROR is pending.
+ * @stop_cmdr: Value to be loaded into CMDR when the stop command is
+ *	to be sent.
+ * @dir_status: Direction of current transfer.
+ * @tasklet: Tasklet running the request state machine.
+ * @pending_events: Bitmask of events flagged by the interrupt handler
+ *	to be processed by the tasklet.
+ * @completed_events: Bitmask of events which the state machine has
+ *	processed.
+ * @state: Tasklet state.
+ * @queue: List of slots waiting for access to the controller.
+ * @bus_hz: The rate of @mck in Hz. This forms the basis for MMC bus
+ *	rate and timeout calculations.
+ * @current_speed: Configured rate of the controller.
+ * @num_slots: Number of slots available.
+ * @fifoth_val: The value of FIFOTH register.
+ * @verid: Denote Version ID.
+ * @dev: Device associated with the MMC controller.
+ * @pdata: Platform data associated with the MMC controller.
+ * @drv_data: Driver specific data for identified variant of the controller
+ * @priv: Implementation defined private data.
+ * @biu_clk: Pointer to bus interface unit clock instance.
+ * @ciu_clk: Pointer to card interface unit clock instance.
+ * @slot: Slots sharing this MMC controller.
+ * @fifo_depth: depth of FIFO.
+ * @data_addr_override: override fifo reg offset with this value.
+ * @wm_aligned: force fifo watermark equal with data length in PIO mode.
+ *	Set as true if alignment is needed.
+ * @data_shift: log2 of FIFO item size.
+ * @part_buf_start: Start index in part_buf.
+ * @part_buf_count: Bytes of partial data in part_buf.
+ * @part_buf: Simple buffer for partial fifo reads/writes.
+ * @push_data: Pointer to FIFO push function.
+ * @pull_data: Pointer to FIFO pull function.
+ * @vqmmc_enabled: Status of vqmmc, should be true or false.
+ * @irq_flags: The flags to be passed to request_irq.
+ * @irq: The irq value to be passed to request_irq.
+ * @sdio_id0: Number of slot0 in the SDIO interrupt registers.
+ * @cmd11_timer: Timer for SD3.0 voltage switch over scheme.
+ * @dto_timer: Timer for broken data transfer over scheme.
+ *
+ * Locking
+ * =======
+ *
+ * @lock is a softirq-safe spinlock protecting @queue as well as
+ * @cur_slot, @mrq and @state. These must always be updated
+ * at the same time while holding @lock.
+ *
+ * @irq_lock is an irq-safe spinlock protecting the INTMASK register
+ * to allow the interrupt handler to modify it directly.  Held for only long
+ * enough to read-modify-write INTMASK and no other locks are grabbed when
+ * holding this one.
+ *
+ * The @mrq field of struct dw_mci_slot is also protected by @lock,
+ * and must always be written at the same time as the slot is added to
+ * @queue.
+ *
+ * @pending_events and @completed_events are accessed using atomic bit
+ * operations, so they don't need any locking.
+ *
+ * None of the fields touched by the interrupt handler need any
+ * locking. However, ordering is important: Before EVENT_DATA_ERROR or
+ * EVENT_DATA_COMPLETE is set in @pending_events, all data-related
+ * interrupts must be disabled and @data_status updated with a
+ * snapshot of SR. Similarly, before EVENT_CMD_COMPLETE is set, the
+ * CMDRDY interrupt must be disabled and @cmd_status updated with a
+ * snapshot of SR, and before EVENT_XFER_COMPLETE can be set, the
+ * bytes_xfered field of @data must be written. This is ensured by
+ * using barriers.
+ */
+struct dw_mci {
+	spinlock_t		lock;
+	spinlock_t		irq_lock;
+	void __iomem		*regs;
+	void __iomem		*fifo_reg;
+	u32			data_addr_override;
+	bool			wm_aligned;
+
+	struct scatterlist	*sg;
+	struct sg_mapping_iter	sg_miter;
+
+	struct dw_mci_slot	*cur_slot;
+	struct mmc_request	*mrq;
+	struct mmc_command	*cmd;
+	struct mmc_data		*data;
+	struct mmc_command	stop_abort;
+	unsigned int		prev_blksz;
+	unsigned char		timing;
+
+	/* DMA interface members*/
+	int			use_dma;
+	int			using_dma;
+	int			dma_64bit_address;
+
+	dma_addr_t		sg_dma;
+	void			*sg_cpu;
+	const struct dw_mci_dma_ops	*dma_ops;
+	/* For idmac */
+	unsigned int		ring_size;
+
+	/* For edmac */
+	struct dw_mci_dma_slave *dms;
+	/* Registers's physical base address */
+	resource_size_t		phy_regs;
+
+	u32			cmd_status;
+	u32			data_status;
+	u32			stop_cmdr;
+	u32			dir_status;
+	struct tasklet_struct	tasklet;
+	unsigned long		pending_events;
+	unsigned long		completed_events;
+	enum dw_mci_state	state;
+	struct list_head	queue;
+
+	u32			bus_hz;
+	u32			current_speed;
+	u32			num_slots;
+	u32			fifoth_val;
+	u16			verid;
+	struct device		*dev;
+	struct dw_mci_board	*pdata;
+	const struct dw_mci_drv_data	*drv_data;
+	void			*priv;
+	struct clk		*biu_clk;
+	struct clk		*ciu_clk;
+	struct dw_mci_slot	*slot[MAX_MCI_SLOTS];
+
+	/* FIFO push and pull */
+	int			fifo_depth;
+	int			data_shift;
+	u8			part_buf_start;
+	u8			part_buf_count;
+	union {
+		u16		part_buf16;
+		u32		part_buf32;
+		u64		part_buf;
+	};
+	void (*push_data)(struct dw_mci *host, void *buf, int cnt);
+	void (*pull_data)(struct dw_mci *host, void *buf, int cnt);
+
+	bool			vqmmc_enabled;
+	unsigned long		irq_flags; /* IRQ flags */
+	int			irq;
+
+	int			sdio_id0;
+
+	struct timer_list       cmd11_timer;
+	struct timer_list       dto_timer;
+};
+
+/* DMA ops for Internal/External DMAC interface */
+struct dw_mci_dma_ops {
+	/* DMA Ops */
+	int (*init)(struct dw_mci *host);
+	int (*start)(struct dw_mci *host, unsigned int sg_len);
+	void (*complete)(void *host);
+	void (*stop)(struct dw_mci *host);
+	void (*cleanup)(struct dw_mci *host);
+	void (*exit)(struct dw_mci *host);
+};
+
+struct dma_pdata;
+
+/* Board platform data */
+struct dw_mci_board {
+	u32 num_slots;
+
+	unsigned int bus_hz; /* Clock speed at the cclk_in pad */
+
+	u32 caps;	/* Capabilities */
+	u32 caps2;	/* More capabilities */
+	u32 pm_caps;	/* PM capabilities */
+	/*
+	 * Override fifo depth. If 0, autodetect it from the FIFOTH register,
+	 * but note that this may not be reliable after a bootloader has used
+	 * it.
+	 */
+	unsigned int fifo_depth;
+
+	/* delay in mS before detecting cards after interrupt */
+	u32 detect_delay_ms;
+
+	struct reset_control *rstc;
+	struct dw_mci_dma_ops *dma_ops;
+	struct dma_pdata *data;
+};
+
 #define DW_MMC_240A		0x240a
 #define DW_MMC_280A		0x280a
 
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index 09739352834c..5a959783304b 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -35,6 +35,7 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/regulator/consumer.h>
+#include <linux/interrupt.h>
 
 #define DRIVER_NAME "meson-gx-mmc"
 
@@ -82,6 +83,7 @@
 #define   CFG_RC_CC_MASK 0xf
 #define   CFG_STOP_CLOCK BIT(22)
 #define   CFG_CLK_ALWAYS_ON BIT(18)
+#define   CFG_CHK_DS BIT(20)
 #define   CFG_AUTO_CLK BIT(23)
 
 #define SD_EMMC_STATUS 0x48
@@ -131,7 +133,7 @@ struct meson_host {
 	struct clk_mux mux;
 	struct clk *mux_clk;
 	struct clk *mux_parent[MUX_CLK_NUM_PARENTS];
-	unsigned long mux_parent_rate[MUX_CLK_NUM_PARENTS];
+	unsigned long current_clock;
 
 	struct clk_divider cfg_div;
 	struct clk *cfg_div_clk;
@@ -178,7 +180,7 @@ struct sd_emmc_desc {
 static int meson_mmc_clk_set(struct meson_host *host, unsigned long clk_rate)
 {
 	struct mmc_host *mmc = host->mmc;
-	int ret = 0;
+	int ret;
 	u32 cfg;
 
 	if (clk_rate) {
@@ -188,7 +190,7 @@ static int meson_mmc_clk_set(struct meson_host *host, unsigned long clk_rate)
 			clk_rate = mmc->f_min;
 	}
 
-	if (clk_rate == mmc->actual_clock)
+	if (clk_rate == host->current_clock)
 		return 0;
 
 	/* stop clock */
@@ -201,29 +203,34 @@ static int meson_mmc_clk_set(struct meson_host *host, unsigned long clk_rate)
 	dev_dbg(host->dev, "change clock rate %u -> %lu\n",
 		mmc->actual_clock, clk_rate);
 
-	if (clk_rate == 0) {
+	if (!clk_rate) {
 		mmc->actual_clock = 0;
+		host->current_clock = 0;
+		/* return with clock being stopped */
 		return 0;
 	}
 
 	ret = clk_set_rate(host->cfg_div_clk, clk_rate);
-	if (ret)
-		dev_warn(host->dev, "Unable to set cfg_div_clk to %lu. ret=%d\n",
-			 clk_rate, ret);
-	else if (clk_rate && clk_rate != clk_get_rate(host->cfg_div_clk))
-		dev_warn(host->dev, "divider requested rate %lu != actual rate %lu: ret=%d\n",
-			 clk_rate, clk_get_rate(host->cfg_div_clk), ret);
-	else
-		mmc->actual_clock = clk_rate;
-
-	/* (re)start clock, if non-zero */
-	if (!ret && clk_rate) {
-		cfg = readl(host->regs + SD_EMMC_CFG);
-		cfg &= ~CFG_STOP_CLOCK;
-		writel(cfg, host->regs + SD_EMMC_CFG);
+	if (ret) {
+		dev_err(host->dev, "Unable to set cfg_div_clk to %lu. ret=%d\n",
+			clk_rate, ret);
+		return ret;
 	}
 
-	return ret;
+	mmc->actual_clock = clk_get_rate(host->cfg_div_clk);
+	host->current_clock = clk_rate;
+
+	if (clk_rate != mmc->actual_clock)
+		dev_dbg(host->dev,
+			"divider requested rate %lu != actual rate %u\n",
+			clk_rate, mmc->actual_clock);
+
+	/* (re)start clock */
+	cfg = readl(host->regs + SD_EMMC_CFG);
+	cfg &= ~CFG_STOP_CLOCK;
+	writel(cfg, host->regs + SD_EMMC_CFG);
+
+	return 0;
 }
 
 /*
@@ -239,7 +246,6 @@ static int meson_mmc_clk_init(struct meson_host *host)
 	const char *mux_parent_names[MUX_CLK_NUM_PARENTS];
 	unsigned int mux_parent_count = 0;
 	const char *clk_div_parents[1];
-	unsigned int f_min = UINT_MAX;
 	u32 clk_reg, cfg;
 
 	/* get the mux parents */
@@ -256,20 +262,10 @@ static int meson_mmc_clk_init(struct meson_host *host)
 			return ret;
 		}
 
-		host->mux_parent_rate[i] = clk_get_rate(host->mux_parent[i]);
 		mux_parent_names[i] = __clk_get_name(host->mux_parent[i]);
 		mux_parent_count++;
-		if (host->mux_parent_rate[i] < f_min)
-			f_min = host->mux_parent_rate[i];
 	}
 
-	/* cacluate f_min based on input clocks, and max divider value */
-	if (f_min != UINT_MAX)
-		f_min = DIV_ROUND_UP(CLK_SRC_XTAL_RATE, CLK_DIV_MAX);
-	else
-		f_min = 4000000;  /* default min: 400 MHz */
-	host->mmc->f_min = f_min;
-
 	/* create the mux */
 	snprintf(clk_name, sizeof(clk_name), "%s#mux", dev_name(host->dev));
 	init.name = clk_name;
@@ -324,9 +320,13 @@ static int meson_mmc_clk_init(struct meson_host *host)
 	writel(cfg, host->regs + SD_EMMC_CFG);
 
 	ret = clk_prepare_enable(host->cfg_div_clk);
-	if (!ret)
-		ret = meson_mmc_clk_set(host, f_min);
+	if (ret)
+		return ret;
 
+	/* Get the nearest minimum clock to 400KHz */
+	host->mmc->f_min = clk_round_rate(host->cfg_div_clk, 400000);
+
+	ret = meson_mmc_clk_set(host, host->mmc->f_min);
 	if (!ret)
 		clk_disable_unprepare(host->cfg_div_clk);
 
@@ -378,7 +378,6 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	meson_mmc_clk_set(host, ios->clock);
 
 	/* Bus width */
-	val = readl(host->regs + SD_EMMC_CFG);
 	switch (ios->bus_width) {
 	case MMC_BUS_WIDTH_1:
 		bus_width = CFG_BUS_WIDTH_1;
@@ -393,7 +392,6 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		dev_err(host->dev, "Invalid ios->bus_width: %u.  Setting to 4.\n",
 			ios->bus_width);
 		bus_width = CFG_BUS_WIDTH_4;
-		return;
 	}
 
 	val = readl(host->regs + SD_EMMC_CFG);
@@ -411,6 +409,16 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	val &= ~(CFG_RC_CC_MASK << CFG_RC_CC_SHIFT);
 	val |= ilog2(SD_EMMC_CFG_CMD_GAP) << CFG_RC_CC_SHIFT;
 
+	val &= ~CFG_DDR;
+	if (ios->timing == MMC_TIMING_UHS_DDR50 ||
+	    ios->timing == MMC_TIMING_MMC_DDR52 ||
+	    ios->timing == MMC_TIMING_MMC_HS400)
+		val |= CFG_DDR;
+
+	val &= ~CFG_CHK_DS;
+	if (ios->timing == MMC_TIMING_MMC_HS400)
+		val |= CFG_CHK_DS;
+
 	writel(val, host->regs + SD_EMMC_CFG);
 
 	if (val != orig)
@@ -480,9 +488,9 @@ static void meson_mmc_start_cmd(struct mmc_host *mmc, struct mmc_command *cmd)
 			blk_len = cfg & (CFG_BLK_LEN_MASK << CFG_BLK_LEN_SHIFT);
 			blk_len >>= CFG_BLK_LEN_SHIFT;
 			if (blk_len != ilog2(cmd->data->blksz)) {
-				dev_warn(host->dev, "%s: update blk_len %d -> %d\n",
+				dev_dbg(host->dev, "%s: update blk_len %d -> %d\n",
 					__func__, blk_len,
-					 ilog2(cmd->data->blksz));
+					ilog2(cmd->data->blksz));
 				blk_len = ilog2(cmd->data->blksz);
 				cfg &= ~(CFG_BLK_LEN_MASK << CFG_BLK_LEN_SHIFT);
 				cfg |= blk_len << CFG_BLK_LEN_SHIFT;
@@ -545,11 +553,6 @@ static void meson_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	/* Stop execution */
 	writel(0, host->regs + SD_EMMC_START);
 
-	/* clear, ack, enable all interrupts */
-	writel(0, host->regs + SD_EMMC_IRQ_EN);
-	writel(IRQ_EN_MASK, host->regs + SD_EMMC_STATUS);
-	writel(IRQ_EN_MASK, host->regs + SD_EMMC_IRQ_EN);
-
 	host->mrq = mrq;
 
 	if (mrq->sbc)
@@ -669,7 +672,6 @@ static irqreturn_t meson_mmc_irq_thread(int irq, void *dev_id)
 	struct mmc_command *cmd = host->cmd;
 	struct mmc_data *data;
 	unsigned int xfer_bytes;
-	int ret = IRQ_HANDLED;
 
 	if (WARN_ON(!mrq))
 		return IRQ_NONE;
@@ -678,14 +680,12 @@ static irqreturn_t meson_mmc_irq_thread(int irq, void *dev_id)
 		return IRQ_NONE;
 
 	data = cmd->data;
-	if (data) {
+	if (data && data->flags & MMC_DATA_READ) {
 		xfer_bytes = data->blksz * data->blocks;
-		if (data->flags & MMC_DATA_READ) {
-			WARN_ON(xfer_bytes > host->bounce_buf_size);
-			sg_copy_from_buffer(data->sg, data->sg_len,
-					    host->bounce_buf, xfer_bytes);
-			data->bytes_xfered = xfer_bytes;
-		}
+		WARN_ON(xfer_bytes > host->bounce_buf_size);
+		sg_copy_from_buffer(data->sg, data->sg_len,
+				    host->bounce_buf, xfer_bytes);
+		data->bytes_xfered = xfer_bytes;
 	}
 
 	meson_mmc_read_resp(host->mmc, cmd);
@@ -694,7 +694,7 @@ static irqreturn_t meson_mmc_irq_thread(int irq, void *dev_id)
 	else
 		meson_mmc_start_cmd(host->mmc, data->stop);
 
-	return ret;
+	return IRQ_HANDLED;
 }
 
 /*
@@ -742,7 +742,8 @@ static int meson_mmc_probe(struct platform_device *pdev)
 
 	ret = mmc_of_parse(mmc);
 	if (ret) {
-		dev_warn(&pdev->dev, "error parsing DT: %d\n", ret);
+		if (ret != -EPROBE_DEFER)
+			dev_warn(&pdev->dev, "error parsing DT: %d\n", ret);
 		goto free_host;
 	}
 
@@ -780,6 +781,7 @@ static int meson_mmc_probe(struct platform_device *pdev)
 	/* clear, ack, enable all interrupts */
 	writel(0, host->regs + SD_EMMC_IRQ_EN);
 	writel(IRQ_EN_MASK, host->regs + SD_EMMC_STATUS);
+	writel(IRQ_EN_MASK, host->regs + SD_EMMC_IRQ_EN);
 
 	ret = devm_request_threaded_irq(&pdev->dev, host->irq,
 					meson_mmc_irq, meson_mmc_irq_thread,
@@ -787,8 +789,11 @@ static int meson_mmc_probe(struct platform_device *pdev)
 	if (ret)
 		goto free_host;
 
+	mmc->max_blk_count = CMD_CFG_LENGTH_MASK;
+	mmc->max_req_size = mmc->max_blk_count * mmc->max_blk_size;
+
 	/* data bounce buffer */
-	host->bounce_buf_size = SZ_512K;
+	host->bounce_buf_size = mmc->max_req_size;
 	host->bounce_buf =
 		dma_alloc_coherent(host->dev, host->bounce_buf_size,
 				   &host->bounce_dma_addr, GFP_KERNEL);
@@ -814,12 +819,11 @@ static int meson_mmc_remove(struct platform_device *pdev)
 {
 	struct meson_host *host = dev_get_drvdata(&pdev->dev);
 
-	if (WARN_ON(!host))
-		return 0;
+	/* disable interrupts */
+	writel(0, host->regs + SD_EMMC_IRQ_EN);
 
-	if (host->bounce_buf)
-		dma_free_coherent(host->dev, host->bounce_buf_size,
-				  host->bounce_buf, host->bounce_dma_addr);
+	dma_free_coherent(host->dev, host->bounce_buf_size,
+			  host->bounce_buf, host->bounce_dma_addr);
 
 	clk_disable_unprepare(host->cfg_div_clk);
 	clk_disable_unprepare(host->core_clk);
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 01a804792f30..0c6420bb2f00 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -507,6 +507,7 @@ static void mmci_dma_data_error(struct mmci_host *host)
 {
 	dev_err(mmc_dev(host->mmc), "error during DMA transfer!\n");
 	dmaengine_terminate_all(host->dma_current);
+	host->dma_in_progress = false;
 	host->dma_current = NULL;
 	host->dma_desc_current = NULL;
 	host->data->host_cookie = 0;
@@ -565,6 +566,7 @@ static void mmci_dma_finalize(struct mmci_host *host, struct mmc_data *data)
 		mmci_dma_release(host);
 	}
 
+	host->dma_in_progress = false;
 	host->dma_current = NULL;
 	host->dma_desc_current = NULL;
 }
@@ -665,6 +667,7 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
 	dev_vdbg(mmc_dev(host->mmc),
 		 "Submit MMCI DMA job, sglen %d blksz %04x blks %04x flags %08x\n",
 		 data->sg_len, data->blksz, data->blocks, data->flags);
+	host->dma_in_progress = true;
 	dmaengine_submit(host->dma_desc_current);
 	dma_async_issue_pending(host->dma_current);
 
@@ -740,8 +743,10 @@ static void mmci_post_request(struct mmc_host *mmc, struct mmc_request *mrq,
 		if (host->dma_desc_current == next->dma_desc)
 			host->dma_desc_current = NULL;
 
-		if (host->dma_current == next->dma_chan)
+		if (host->dma_current == next->dma_chan) {
+			host->dma_in_progress = false;
 			host->dma_current = NULL;
+		}
 
 		next->dma_desc = NULL;
 		next->dma_chan = NULL;
@@ -1023,7 +1028,12 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 		if (!host->busy_status && busy_resp &&
 		    !(status & (MCI_CMDCRCFAIL|MCI_CMDTIMEOUT)) &&
 		    (readl(base + MMCISTATUS) & host->variant->busy_detect_flag)) {
-			/* Unmask the busy IRQ */
+
+			/* Clear the busy start IRQ */
+			writel(host->variant->busy_detect_mask,
+			       host->base + MMCICLEAR);
+
+			/* Unmask the busy end IRQ */
 			writel(readl(base + MMCIMASK0) |
 			       host->variant->busy_detect_mask,
 			       base + MMCIMASK0);
@@ -1038,10 +1048,14 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 
 		/*
 		 * At this point we are not busy with a command, we have
-		 * not received a new busy request, mask the busy IRQ and
-		 * fall through to process the IRQ.
+		 * not received a new busy request, clear and mask the busy
+		 * end IRQ and fall through to process the IRQ.
 		 */
 		if (host->busy_status) {
+
+			writel(host->variant->busy_detect_mask,
+			       host->base + MMCICLEAR);
+
 			writel(readl(base + MMCIMASK0) &
 			       ~host->variant->busy_detect_mask,
 			       base + MMCIMASK0);
@@ -1283,12 +1297,21 @@ static irqreturn_t mmci_irq(int irq, void *dev_id)
 		}
 
 		/*
-		 * We intentionally clear the MCI_ST_CARDBUSY IRQ here (if it's
-		 * enabled) since the HW seems to be triggering the IRQ on both
-		 * edges while monitoring DAT0 for busy completion.
+		 * We intentionally clear the MCI_ST_CARDBUSY IRQ (if it's
+		 * enabled) in mmci_cmd_irq() function where ST Micro busy
+		 * detection variant is handled. Considering the HW seems to be
+		 * triggering the IRQ on both edges while monitoring DAT0 for
+		 * busy completion and that same status bit is used to monitor
+		 * start and end of busy detection, special care must be taken
+		 * to make sure that both start and end interrupts are always
+		 * cleared one after the other.
 		 */
 		status &= readl(host->base + MMCIMASK0);
-		writel(status, host->base + MMCICLEAR);
+		if (host->variant->busy_detect)
+			writel(status & ~host->variant->busy_detect_mask,
+			       host->base + MMCICLEAR);
+		else
+			writel(status, host->base + MMCICLEAR);
 
 		dev_dbg(mmc_dev(host->mmc), "irq0 (data+cmd) %08x\n", status);
 
diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h
index 56322c6afba4..4a8bef1aac8f 100644
--- a/drivers/mmc/host/mmci.h
+++ b/drivers/mmc/host/mmci.h
@@ -245,8 +245,9 @@ struct mmci_host {
 	struct dma_chan		*dma_tx_channel;
 	struct dma_async_tx_descriptor	*dma_desc_current;
 	struct mmci_host_next	next_data;
+	bool			dma_in_progress;
 
-#define dma_inprogress(host)	((host)->dma_current)
+#define dma_inprogress(host)	((host)->dma_in_progress)
 #else
 #define dma_inprogress(host)	(0)
 #endif
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 10ef2ae1d2f6..8e32580c12b5 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -28,6 +28,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/interrupt.h>
 
 #include <linux/mmc/card.h>
 #include <linux/mmc/core.h>
@@ -1074,11 +1075,8 @@ static int msdc_card_busy(struct mmc_host *mmc)
 	struct msdc_host *host = mmc_priv(mmc);
 	u32 status = readl(host->base + MSDC_PS);
 
-	/* check if any pin between dat[0:3] is low */
-	if (((status >> 16) & 0xf) != 0xf)
-		return 1;
-
-	return 0;
+	/* only check if data0 is low */
+	return !(status & BIT(16));
 }
 
 static void msdc_request_timeout(struct work_struct *work)
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index c8b8ac66ff7e..add1e70195ea 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -153,7 +153,11 @@ static void mxs_mmc_request_done(struct mxs_mmc_host *host)
 		}
 	}
 
-	if (data) {
+	if (cmd == mrq->sbc) {
+		/* Finished CMD23, now send actual command. */
+		mxs_mmc_start_cmd(host, mrq->cmd);
+		return;
+	} else if (data) {
 		dma_unmap_sg(mmc_dev(host->mmc), data->sg,
 			     data->sg_len, ssp->dma_dir);
 		/*
@@ -166,7 +170,7 @@ static void mxs_mmc_request_done(struct mxs_mmc_host *host)
 			data->bytes_xfered = 0;
 
 		host->data = NULL;
-		if (mrq->stop) {
+		if (data->stop && (data->error || !mrq->sbc)) {
 			mxs_mmc_start_cmd(host, mrq->stop);
 			return;
 		}
@@ -495,7 +499,11 @@ static void mxs_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 	WARN_ON(host->mrq != NULL);
 	host->mrq = mrq;
-	mxs_mmc_start_cmd(host, mrq->cmd);
+
+	if (mrq->sbc)
+		mxs_mmc_start_cmd(host, mrq->sbc);
+	else
+		mxs_mmc_start_cmd(host, mrq->cmd);
 }
 
 static void mxs_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
@@ -642,7 +650,7 @@ static int mxs_mmc_probe(struct platform_device *pdev)
 	/* set mmc core parameters */
 	mmc->ops = &mxs_mmc_ops;
 	mmc->caps = MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED |
-		    MMC_CAP_SDIO_IRQ | MMC_CAP_NEEDS_POLL;
+		    MMC_CAP_SDIO_IRQ | MMC_CAP_NEEDS_POLL | MMC_CAP_CMD23;
 
 	host->broken_cd = of_property_read_bool(np, "broken-cd");
 
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index be3c49fa7382..bd49f34d7654 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -893,7 +893,7 @@ static void mmc_omap_cover_handler(unsigned long param)
 	 * If no card is inserted, we postpone polling until
 	 * the cover has been closed.
 	 */
-	if (slot->mmc->card == NULL || !mmc_card_present(slot->mmc->card))
+	if (slot->mmc->card == NULL)
 		return;
 
 	mod_timer(&slot->cover_timer,
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index ad11c4cc12ed..a58bd653ed8b 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -1162,7 +1162,7 @@ static void omap_hsmmc_do_irq(struct omap_hsmmc_host *host, int status)
 	if (status & ERR_EN) {
 		omap_hsmmc_dbg_report_irq(host, status);
 
-		if (status & (CTO_EN | CCRC_EN))
+		if (status & (CTO_EN | CCRC_EN | CEB_EN))
 			end_cmd = 1;
 		if (host->data || host->response_busy) {
 			end_trans = !end_cmd;
@@ -1469,10 +1469,11 @@ static int omap_hsmmc_setup_dma_transfer(struct omap_hsmmc_host *host,
 }
 
 static void set_data_timeout(struct omap_hsmmc_host *host,
-			     unsigned int timeout_ns,
+			     unsigned long long timeout_ns,
 			     unsigned int timeout_clks)
 {
-	unsigned int timeout, cycle_ns;
+	unsigned long long timeout = timeout_ns;
+	unsigned int cycle_ns;
 	uint32_t reg, clkd, dto = 0;
 
 	reg = OMAP_HSMMC_READ(host->base, SYSCTL);
@@ -1481,7 +1482,7 @@ static void set_data_timeout(struct omap_hsmmc_host *host,
 		clkd = 1;
 
 	cycle_ns = 1000000000 / (host->clk_rate / clkd);
-	timeout = timeout_ns / cycle_ns;
+	do_div(timeout, cycle_ns);
 	timeout += timeout_clks;
 	if (timeout) {
 		while ((timeout & 0x80000000) == 0) {
@@ -1527,16 +1528,24 @@ static int
 omap_hsmmc_prepare_data(struct omap_hsmmc_host *host, struct mmc_request *req)
 {
 	int ret;
+	unsigned long long timeout;
+
 	host->data = req->data;
 
 	if (req->data == NULL) {
 		OMAP_HSMMC_WRITE(host->base, BLK, 0);
-		/*
-		 * Set an arbitrary 100ms data timeout for commands with
-		 * busy signal.
-		 */
-		if (req->cmd->flags & MMC_RSP_BUSY)
-			set_data_timeout(host, 100000000U, 0);
+		if (req->cmd->flags & MMC_RSP_BUSY) {
+			timeout = req->cmd->busy_timeout * NSEC_PER_MSEC;
+
+			/*
+			 * Set an arbitrary 100ms data timeout for commands with
+			 * busy signal and no indication of busy_timeout.
+			 */
+			if (!timeout)
+				timeout = 100000000U;
+
+			set_data_timeout(host, timeout, 0);
+		}
 		return 0;
 	}
 
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index ecb99a8d2fa2..41b57713b620 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -707,7 +707,7 @@ static int sd_tuning_rx_cmd(struct realtek_pci_sdmmc *host,
 		u8 opcode, u8 sample_point)
 {
 	int err;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	err = sd_change_phase(host, sample_point, true);
 	if (err < 0)
diff --git a/drivers/mmc/host/rtsx_usb_sdmmc.c b/drivers/mmc/host/rtsx_usb_sdmmc.c
index dc1abd14acbc..12d2fbe9c520 100644
--- a/drivers/mmc/host/rtsx_usb_sdmmc.c
+++ b/drivers/mmc/host/rtsx_usb_sdmmc.c
@@ -682,7 +682,7 @@ static int sd_tuning_rx_cmd(struct rtsx_usb_sdmmc *host,
 		u8 opcode, u8 sample_point)
 {
 	int err;
-	struct mmc_command cmd = {0};
+	struct mmc_command cmd = {};
 
 	err = sd_change_phase(host, sample_point, 0);
 	if (err)
diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c
index 932a4b1fed33..7a173f8c455b 100644
--- a/drivers/mmc/host/s3cmci.c
+++ b/drivers/mmc/host/s3cmci.c
@@ -21,6 +21,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/gpio.h>
+#include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/io.h>
 
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 278a5a435ab7..9dcb7048e3b1 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -467,7 +467,10 @@ static int sdhci_acpi_probe(struct platform_device *pdev)
 	if (sdhci_acpi_flag(c, SDHCI_ACPI_SD_CD)) {
 		bool v = sdhci_acpi_flag(c, SDHCI_ACPI_SD_CD_OVERRIDE_LEVEL);
 
-		if (mmc_gpiod_request_cd(host->mmc, NULL, 0, v, 0, NULL)) {
+		err = mmc_gpiod_request_cd(host->mmc, NULL, 0, v, 0, NULL);
+		if (err) {
+			if (err == -EPROBE_DEFER)
+				goto err_free;
 			dev_warn(dev, "failed to setup card detect gpio\n");
 			c->use_runtime_pm = false;
 		}
diff --git a/drivers/mmc/host/sdhci-cadence.c b/drivers/mmc/host/sdhci-cadence.c
index 4b0ecb981842..316cfec3f005 100644
--- a/drivers/mmc/host/sdhci-cadence.c
+++ b/drivers/mmc/host/sdhci-cadence.c
@@ -17,6 +17,7 @@
 #include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/mmc/host.h>
+#include <linux/mmc/mmc.h>
 
 #include "sdhci-pltfm.h"
 
@@ -25,7 +26,7 @@
 #define   SDHCI_CDNS_HRS04_ACK			BIT(26)
 #define   SDHCI_CDNS_HRS04_RD			BIT(25)
 #define   SDHCI_CDNS_HRS04_WR			BIT(24)
-#define   SDHCI_CDNS_HRS04_RDATA_SHIFT		12
+#define   SDHCI_CDNS_HRS04_RDATA_SHIFT		16
 #define   SDHCI_CDNS_HRS04_WDATA_SHIFT		8
 #define   SDHCI_CDNS_HRS04_ADDR_SHIFT		0
 
diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h
index de132e281753..ece8b37e51dd 100644
--- a/drivers/mmc/host/sdhci-esdhc.h
+++ b/drivers/mmc/host/sdhci-esdhc.h
@@ -24,30 +24,36 @@
 				SDHCI_QUIRK_PIO_NEEDS_DELAY | \
 				SDHCI_QUIRK_NO_HISPD_BIT)
 
-#define ESDHC_PROCTL		0x28
-
-#define ESDHC_SYSTEM_CONTROL	0x2c
-#define ESDHC_CLOCK_MASK	0x0000fff0
-#define ESDHC_PREDIV_SHIFT	8
-#define ESDHC_DIVIDER_SHIFT	4
-#define ESDHC_CLOCK_PEREN	0x00000004
-#define ESDHC_CLOCK_HCKEN	0x00000002
-#define ESDHC_CLOCK_IPGEN	0x00000001
-
 /* pltfm-specific */
 #define ESDHC_HOST_CONTROL_LE	0x20
 
 /*
- * P2020 interpretation of the SDHCI_HOST_CONTROL register
+ * eSDHC register definition
  */
-#define ESDHC_CTRL_4BITBUS          (0x1 << 1)
-#define ESDHC_CTRL_8BITBUS          (0x2 << 1)
-#define ESDHC_CTRL_BUSWIDTH_MASK    (0x3 << 1)
-
-/* OF-specific */
-#define ESDHC_DMA_SYSCTL	0x40c
-#define ESDHC_DMA_SNOOP		0x00000040
 
-#define ESDHC_HOST_CONTROL_RES	0x01
+/* Present State Register */
+#define ESDHC_PRSSTAT			0x24
+#define ESDHC_CLOCK_STABLE		0x00000008
+
+/* Protocol Control Register */
+#define ESDHC_PROCTL			0x28
+#define ESDHC_CTRL_4BITBUS		(0x1 << 1)
+#define ESDHC_CTRL_8BITBUS		(0x2 << 1)
+#define ESDHC_CTRL_BUSWIDTH_MASK	(0x3 << 1)
+#define ESDHC_HOST_CONTROL_RES		0x01
+
+/* System Control Register */
+#define ESDHC_SYSTEM_CONTROL		0x2c
+#define ESDHC_CLOCK_MASK		0x0000fff0
+#define ESDHC_PREDIV_SHIFT		8
+#define ESDHC_DIVIDER_SHIFT		4
+#define ESDHC_CLOCK_SDCLKEN		0x00000008
+#define ESDHC_CLOCK_PEREN		0x00000004
+#define ESDHC_CLOCK_HCKEN		0x00000002
+#define ESDHC_CLOCK_IPGEN		0x00000001
+
+/* Control Register for DMA transfer */
+#define ESDHC_DMA_SYSCTL		0x40c
+#define ESDHC_DMA_SNOOP			0x00000040
 
 #endif /* _DRIVERS_MMC_SDHCI_ESDHC_H */
diff --git a/drivers/mmc/host/sdhci-iproc.c b/drivers/mmc/host/sdhci-iproc.c
index d7046d67415a..3275d4995812 100644
--- a/drivers/mmc/host/sdhci-iproc.c
+++ b/drivers/mmc/host/sdhci-iproc.c
@@ -211,14 +211,19 @@ static const struct sdhci_iproc_data iproc_data = {
 static const struct sdhci_pltfm_data sdhci_bcm2835_pltfm_data = {
 	.quirks = SDHCI_QUIRK_BROKEN_CARD_DETECTION |
 		  SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK |
-		  SDHCI_QUIRK_MISSING_CAPS,
+		  SDHCI_QUIRK_MISSING_CAPS |
+		  SDHCI_QUIRK_NO_HISPD_BIT,
 	.ops = &sdhci_iproc_32only_ops,
 };
 
 static const struct sdhci_iproc_data bcm2835_data = {
 	.pdata = &sdhci_bcm2835_pltfm_data,
-	.caps = SDHCI_CAN_VDD_330,
-	.caps1 = 0x00000000,
+	.caps = ((0x1 << SDHCI_MAX_BLOCK_SHIFT)
+			& SDHCI_MAX_BLOCK_MASK) |
+		SDHCI_CAN_VDD_330 |
+		SDHCI_CAN_DO_HISPD,
+	.caps1 = SDHCI_DRIVER_TYPE_A |
+		 SDHCI_DRIVER_TYPE_C,
 	.mmc_caps = 0x00000000,
 };
 
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 32879b845b75..10cdc84d5113 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -69,6 +69,7 @@
 #define CORE_DLL_CLOCK_DISABLE	BIT(21)
 
 #define CORE_VENDOR_SPEC	0x10c
+#define CORE_VENDOR_SPEC_POR_VAL	0xa1c
 #define CORE_CLK_PWRSAVE	BIT(1)
 #define CORE_HC_MCLK_SEL_DFLT	(2 << 8)
 #define CORE_HC_MCLK_SEL_HS400	(3 << 8)
@@ -102,6 +103,7 @@
 
 #define CORE_DDR_200_CFG		0x184
 #define CORE_CDC_T4_DLY_SEL		BIT(0)
+#define CORE_CMDIN_RCLK_EN		BIT(1)
 #define CORE_START_CDC_TRAFFIC		BIT(6)
 #define CORE_VENDOR_SPEC3	0x1b0
 #define CORE_PWRSAVE_DLL	BIT(3)
@@ -138,6 +140,46 @@ struct sdhci_msm_host {
 	bool use_cdclp533;
 };
 
+static unsigned int msm_get_clock_rate_for_bus_mode(struct sdhci_host *host,
+						    unsigned int clock)
+{
+	struct mmc_ios ios = host->mmc->ios;
+	/*
+	 * The SDHC requires internal clock frequency to be double the
+	 * actual clock that will be set for DDR mode. The controller
+	 * uses the faster clock(100/400MHz) for some of its parts and
+	 * send the actual required clock (50/200MHz) to the card.
+	 */
+	if (ios.timing == MMC_TIMING_UHS_DDR50 ||
+	    ios.timing == MMC_TIMING_MMC_DDR52 ||
+	    ios.timing == MMC_TIMING_MMC_HS400 ||
+	    host->flags & SDHCI_HS400_TUNING)
+		clock *= 2;
+	return clock;
+}
+
+static void msm_set_clock_rate_for_bus_mode(struct sdhci_host *host,
+					    unsigned int clock)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
+	struct mmc_ios curr_ios = host->mmc->ios;
+	int rc;
+
+	clock = msm_get_clock_rate_for_bus_mode(host, clock);
+	rc = clk_set_rate(msm_host->clk, clock);
+	if (rc) {
+		pr_err("%s: Failed to set clock at rate %u at timing %d\n",
+		       mmc_hostname(host->mmc), clock,
+		       curr_ios.timing);
+		return;
+	}
+	msm_host->clk_rate = clock;
+	pr_debug("%s: Setting clock at rate %lu at timing %d\n",
+		 mmc_hostname(host->mmc), clk_get_rate(msm_host->clk),
+		 curr_ios.timing);
+}
+
 /* Platform specific tuning */
 static inline int msm_dll_poll_ck_out_en(struct sdhci_host *host, u8 poll)
 {
@@ -464,6 +506,122 @@ static int msm_init_cm_dll(struct sdhci_host *host)
 	return 0;
 }
 
+static void msm_hc_select_default(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
+	u32 config;
+
+	if (!msm_host->use_cdclp533) {
+		config = readl_relaxed(host->ioaddr +
+				CORE_VENDOR_SPEC3);
+		config &= ~CORE_PWRSAVE_DLL;
+		writel_relaxed(config, host->ioaddr +
+				CORE_VENDOR_SPEC3);
+	}
+
+	config = readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC);
+	config &= ~CORE_HC_MCLK_SEL_MASK;
+	config |= CORE_HC_MCLK_SEL_DFLT;
+	writel_relaxed(config, host->ioaddr + CORE_VENDOR_SPEC);
+
+	/*
+	 * Disable HC_SELECT_IN to be able to use the UHS mode select
+	 * configuration from Host Control2 register for all other
+	 * modes.
+	 * Write 0 to HC_SELECT_IN and HC_SELECT_IN_EN field
+	 * in VENDOR_SPEC_FUNC
+	 */
+	config = readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC);
+	config &= ~CORE_HC_SELECT_IN_EN;
+	config &= ~CORE_HC_SELECT_IN_MASK;
+	writel_relaxed(config, host->ioaddr + CORE_VENDOR_SPEC);
+
+	/*
+	 * Make sure above writes impacting free running MCLK are completed
+	 * before changing the clk_rate at GCC.
+	 */
+	wmb();
+}
+
+static void msm_hc_select_hs400(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
+	struct mmc_ios ios = host->mmc->ios;
+	u32 config, dll_lock;
+	int rc;
+
+	/* Select the divided clock (free running MCLK/2) */
+	config = readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC);
+	config &= ~CORE_HC_MCLK_SEL_MASK;
+	config |= CORE_HC_MCLK_SEL_HS400;
+
+	writel_relaxed(config, host->ioaddr + CORE_VENDOR_SPEC);
+	/*
+	 * Select HS400 mode using the HC_SELECT_IN from VENDOR SPEC
+	 * register
+	 */
+	if ((msm_host->tuning_done || ios.enhanced_strobe) &&
+	    !msm_host->calibration_done) {
+		config = readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC);
+		config |= CORE_HC_SELECT_IN_HS400;
+		config |= CORE_HC_SELECT_IN_EN;
+		writel_relaxed(config, host->ioaddr + CORE_VENDOR_SPEC);
+	}
+	if (!msm_host->clk_rate && !msm_host->use_cdclp533) {
+		/*
+		 * Poll on DLL_LOCK or DDR_DLL_LOCK bits in
+		 * CORE_DLL_STATUS to be set.  This should get set
+		 * within 15 us at 200 MHz.
+		 */
+		rc = readl_relaxed_poll_timeout(host->ioaddr +
+						CORE_DLL_STATUS,
+						dll_lock,
+						(dll_lock &
+						(CORE_DLL_LOCK |
+						CORE_DDR_DLL_LOCK)), 10,
+						1000);
+		if (rc == -ETIMEDOUT)
+			pr_err("%s: Unable to get DLL_LOCK/DDR_DLL_LOCK, dll_status: 0x%08x\n",
+			       mmc_hostname(host->mmc), dll_lock);
+	}
+	/*
+	 * Make sure above writes impacting free running MCLK are completed
+	 * before changing the clk_rate at GCC.
+	 */
+	wmb();
+}
+
+/*
+ * sdhci_msm_hc_select_mode :- In general all timing modes are
+ * controlled via UHS mode select in Host Control2 register.
+ * eMMC specific HS200/HS400 doesn't have their respective modes
+ * defined here, hence we use these values.
+ *
+ * HS200 - SDR104 (Since they both are equivalent in functionality)
+ * HS400 - This involves multiple configurations
+ *		Initially SDR104 - when tuning is required as HS200
+ *		Then when switching to DDR @ 400MHz (HS400) we use
+ *		the vendor specific HC_SELECT_IN to control the mode.
+ *
+ * In addition to controlling the modes we also need to select the
+ * correct input clock for DLL depending on the mode.
+ *
+ * HS400 - divided clock (free running MCLK/2)
+ * All other modes - default (free running MCLK)
+ */
+void sdhci_msm_hc_select_mode(struct sdhci_host *host)
+{
+	struct mmc_ios ios = host->mmc->ios;
+
+	if (ios.timing == MMC_TIMING_MMC_HS400 ||
+	    host->flags & SDHCI_HS400_TUNING)
+		msm_hc_select_hs400(host);
+	else
+		msm_hc_select_default(host);
+}
+
 static int sdhci_msm_cdclp533_calibration(struct sdhci_host *host)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -506,19 +664,7 @@ static int sdhci_msm_cdclp533_calibration(struct sdhci_host *host)
 	config &= ~CORE_START_CDC_TRAFFIC;
 	writel_relaxed(config, host->ioaddr + CORE_DDR_200_CFG);
 
-	/*
-	 * Perform CDC Register Initialization Sequence
-	 *
-	 * CORE_CSR_CDC_CTLR_CFG0	0x11800EC
-	 * CORE_CSR_CDC_CTLR_CFG1	0x3011111
-	 * CORE_CSR_CDC_CAL_TIMER_CFG0	0x1201000
-	 * CORE_CSR_CDC_CAL_TIMER_CFG1	0x4
-	 * CORE_CSR_CDC_REFCOUNT_CFG	0xCB732020
-	 * CORE_CSR_CDC_COARSE_CAL_CFG	0xB19
-	 * CORE_CSR_CDC_DELAY_CFG	0x3AC
-	 * CORE_CDC_OFFSET_CFG		0x0
-	 * CORE_CDC_SLAVE_DDA_CFG	0x16334
-	 */
+	/* Perform CDC Register Initialization Sequence */
 
 	writel_relaxed(0x11800EC, host->ioaddr + CORE_CSR_CDC_CTLR_CFG0);
 	writel_relaxed(0x3011111, host->ioaddr + CORE_CSR_CDC_CTLR_CFG1);
@@ -526,7 +672,7 @@ static int sdhci_msm_cdclp533_calibration(struct sdhci_host *host)
 	writel_relaxed(0x4, host->ioaddr + CORE_CSR_CDC_CAL_TIMER_CFG1);
 	writel_relaxed(0xCB732020, host->ioaddr + CORE_CSR_CDC_REFCOUNT_CFG);
 	writel_relaxed(0xB19, host->ioaddr + CORE_CSR_CDC_COARSE_CAL_CFG);
-	writel_relaxed(0x3AC, host->ioaddr + CORE_CSR_CDC_DELAY_CFG);
+	writel_relaxed(0x4E2, host->ioaddr + CORE_CSR_CDC_DELAY_CFG);
 	writel_relaxed(0x0, host->ioaddr + CORE_CDC_OFFSET_CFG);
 	writel_relaxed(0x16334, host->ioaddr + CORE_CDC_SLAVE_DDA_CFG);
 
@@ -579,6 +725,7 @@ out:
 
 static int sdhci_msm_cm_dll_sdc4_calibration(struct sdhci_host *host)
 {
+	struct mmc_host *mmc = host->mmc;
 	u32 dll_status, config;
 	int ret;
 
@@ -593,6 +740,12 @@ static int sdhci_msm_cm_dll_sdc4_calibration(struct sdhci_host *host)
 	 */
 	writel_relaxed(DDR_CONFIG_POR_VAL, host->ioaddr + CORE_DDR_CONFIG);
 
+	if (mmc->ios.enhanced_strobe) {
+		config = readl_relaxed(host->ioaddr + CORE_DDR_200_CFG);
+		config |= CORE_CMDIN_RCLK_EN;
+		writel_relaxed(config, host->ioaddr + CORE_DDR_200_CFG);
+	}
+
 	config = readl_relaxed(host->ioaddr + CORE_DLL_CONFIG_2);
 	config |= CORE_DDR_CAL_EN;
 	writel_relaxed(config, host->ioaddr + CORE_DLL_CONFIG_2);
@@ -627,6 +780,7 @@ static int sdhci_msm_hs400_dll_calibration(struct sdhci_host *host)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
+	struct mmc_host *mmc = host->mmc;
 	int ret;
 	u32 config;
 
@@ -640,14 +794,17 @@ static int sdhci_msm_hs400_dll_calibration(struct sdhci_host *host)
 	if (ret)
 		goto out;
 
-	/* Set the selected phase in delay line hw block */
-	ret = msm_config_cm_dll_phase(host, msm_host->saved_tuning_phase);
-	if (ret)
-		goto out;
+	if (!mmc->ios.enhanced_strobe) {
+		/* Set the selected phase in delay line hw block */
+		ret = msm_config_cm_dll_phase(host,
+					      msm_host->saved_tuning_phase);
+		if (ret)
+			goto out;
+		config = readl_relaxed(host->ioaddr + CORE_DLL_CONFIG);
+		config |= CORE_CMD_DAT_TRACK_SEL;
+		writel_relaxed(config, host->ioaddr + CORE_DLL_CONFIG);
+	}
 
-	config = readl_relaxed(host->ioaddr + CORE_DLL_CONFIG);
-	config |= CORE_CMD_DAT_TRACK_SEL;
-	writel_relaxed(config, host->ioaddr + CORE_DLL_CONFIG);
 	if (msm_host->use_cdclp533)
 		ret = sdhci_msm_cdclp533_calibration(host);
 	else
@@ -658,12 +815,12 @@ out:
 	return ret;
 }
 
-static int sdhci_msm_execute_tuning(struct sdhci_host *host, u32 opcode)
+static int sdhci_msm_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
+	struct sdhci_host *host = mmc_priv(mmc);
 	int tuning_seq_cnt = 3;
 	u8 phase, tuned_phases[16], tuned_phase_cnt = 0;
 	int rc;
-	struct mmc_host *mmc = host->mmc;
 	struct mmc_ios ios = host->mmc->ios;
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
@@ -678,6 +835,17 @@ static int sdhci_msm_execute_tuning(struct sdhci_host *host, u32 opcode)
 	    ios.timing == MMC_TIMING_UHS_SDR104))
 		return 0;
 
+	/*
+	 * For HS400 tuning in HS200 timing requires:
+	 * - select MCLK/2 in VENDOR_SPEC
+	 * - program MCLK to 400MHz (or nearest supported) in GCC
+	 */
+	if (host->flags & SDHCI_HS400_TUNING) {
+		sdhci_msm_hc_select_mode(host);
+		msm_set_clock_rate_for_bus_mode(host, ios.clock);
+		host->flags &= ~SDHCI_HS400_TUNING;
+	}
+
 retry:
 	/* First of all reset the tuning block */
 	rc = msm_init_cm_dll(host);
@@ -732,6 +900,30 @@ retry:
 	return rc;
 }
 
+/*
+ * sdhci_msm_hs400 - Calibrate the DLL for HS400 bus speed mode operation.
+ * This needs to be done for both tuning and enhanced_strobe mode.
+ * DLL operation is only needed for clock > 100MHz. For clock <= 100MHz
+ * fixed feedback clock is used.
+ */
+static void sdhci_msm_hs400(struct sdhci_host *host, struct mmc_ios *ios)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
+	int ret;
+
+	if (host->clock > CORE_FREQ_100MHZ &&
+	    (msm_host->tuning_done || ios->enhanced_strobe) &&
+	    !msm_host->calibration_done) {
+		ret = sdhci_msm_hs400_dll_calibration(host);
+		if (!ret)
+			msm_host->calibration_done = true;
+		else
+			pr_err("%s: Failed to calibrate DLL for hs400 mode (%d)\n",
+			       mmc_hostname(host->mmc), ret);
+	}
+}
+
 static void sdhci_msm_set_uhs_signaling(struct sdhci_host *host,
 					unsigned int uhs)
 {
@@ -800,12 +992,10 @@ static void sdhci_msm_set_uhs_signaling(struct sdhci_host *host,
 	sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2);
 
 	spin_unlock_irq(&host->lock);
-	/* CDCLP533 HW calibration is only required for HS400 mode*/
-	if (host->clock > CORE_FREQ_100MHZ &&
-	    msm_host->tuning_done && !msm_host->calibration_done &&
-	    mmc->ios.timing == MMC_TIMING_MMC_HS400)
-		if (!sdhci_msm_hs400_dll_calibration(host))
-			msm_host->calibration_done = true;
+
+	if (mmc->ios.timing == MMC_TIMING_MMC_HS400)
+		sdhci_msm_hs400(host, &mmc->ios);
+
 	spin_lock_irq(&host->lock);
 }
 
@@ -893,9 +1083,6 @@ static void sdhci_msm_set_clock(struct sdhci_host *host, unsigned int clock)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_msm_host *msm_host = sdhci_pltfm_priv(pltfm_host);
-	struct mmc_ios curr_ios = host->mmc->ios;
-	u32 config, dll_lock;
-	int rc;
 
 	if (!clock) {
 		msm_host->clk_rate = clock;
@@ -903,117 +1090,11 @@ static void sdhci_msm_set_clock(struct sdhci_host *host, unsigned int clock)
 	}
 
 	spin_unlock_irq(&host->lock);
-	/*
-	 * The SDHC requires internal clock frequency to be double the
-	 * actual clock that will be set for DDR mode. The controller
-	 * uses the faster clock(100/400MHz) for some of its parts and
-	 * send the actual required clock (50/200MHz) to the card.
-	 */
-	if (curr_ios.timing == MMC_TIMING_UHS_DDR50 ||
-	    curr_ios.timing == MMC_TIMING_MMC_DDR52 ||
-	    curr_ios.timing == MMC_TIMING_MMC_HS400)
-		clock *= 2;
-	/*
-	 * In general all timing modes are controlled via UHS mode select in
-	 * Host Control2 register. eMMC specific HS200/HS400 doesn't have
-	 * their respective modes defined here, hence we use these values.
-	 *
-	 * HS200 - SDR104 (Since they both are equivalent in functionality)
-	 * HS400 - This involves multiple configurations
-	 *		Initially SDR104 - when tuning is required as HS200
-	 *		Then when switching to DDR @ 400MHz (HS400) we use
-	 *		the vendor specific HC_SELECT_IN to control the mode.
-	 *
-	 * In addition to controlling the modes we also need to select the
-	 * correct input clock for DLL depending on the mode.
-	 *
-	 * HS400 - divided clock (free running MCLK/2)
-	 * All other modes - default (free running MCLK)
-	 */
-	if (curr_ios.timing == MMC_TIMING_MMC_HS400) {
-		/* Select the divided clock (free running MCLK/2) */
-		config = readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC);
-		config &= ~CORE_HC_MCLK_SEL_MASK;
-		config |= CORE_HC_MCLK_SEL_HS400;
 
-		writel_relaxed(config, host->ioaddr + CORE_VENDOR_SPEC);
-		/*
-		 * Select HS400 mode using the HC_SELECT_IN from VENDOR SPEC
-		 * register
-		 */
-		if (msm_host->tuning_done && !msm_host->calibration_done) {
-			/*
-			 * Write 0x6 to HC_SELECT_IN and 1 to HC_SELECT_IN_EN
-			 * field in VENDOR_SPEC_FUNC
-			 */
-			config = readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC);
-			config |= CORE_HC_SELECT_IN_HS400;
-			config |= CORE_HC_SELECT_IN_EN;
-			writel_relaxed(config, host->ioaddr + CORE_VENDOR_SPEC);
-		}
-		if (!msm_host->clk_rate && !msm_host->use_cdclp533) {
-			/*
-			 * Poll on DLL_LOCK or DDR_DLL_LOCK bits in
-			 * CORE_DLL_STATUS to be set.  This should get set
-			 * within 15 us at 200 MHz.
-			 */
-			rc = readl_relaxed_poll_timeout(host->ioaddr +
-							CORE_DLL_STATUS,
-							dll_lock,
-							(dll_lock &
-							(CORE_DLL_LOCK |
-							CORE_DDR_DLL_LOCK)), 10,
-							1000);
-			if (rc == -ETIMEDOUT)
-				pr_err("%s: Unable to get DLL_LOCK/DDR_DLL_LOCK, dll_status: 0x%08x\n",
-				       mmc_hostname(host->mmc), dll_lock);
-		}
-	} else {
-		if (!msm_host->use_cdclp533) {
-			config = readl_relaxed(host->ioaddr +
-					CORE_VENDOR_SPEC3);
-			config &= ~CORE_PWRSAVE_DLL;
-			writel_relaxed(config, host->ioaddr +
-					CORE_VENDOR_SPEC3);
-		}
+	sdhci_msm_hc_select_mode(host);
 
-		config = readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC);
-		config &= ~CORE_HC_MCLK_SEL_MASK;
-		config |= CORE_HC_MCLK_SEL_DFLT;
-		writel_relaxed(config, host->ioaddr + CORE_VENDOR_SPEC);
+	msm_set_clock_rate_for_bus_mode(host, clock);
 
-		/*
-		 * Disable HC_SELECT_IN to be able to use the UHS mode select
-		 * configuration from Host Control2 register for all other
-		 * modes.
-		 * Write 0 to HC_SELECT_IN and HC_SELECT_IN_EN field
-		 * in VENDOR_SPEC_FUNC
-		 */
-		config = readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC);
-		config &= ~CORE_HC_SELECT_IN_EN;
-		config &= ~CORE_HC_SELECT_IN_MASK;
-		writel_relaxed(config, host->ioaddr + CORE_VENDOR_SPEC);
-	}
-
-	/*
-	 * Make sure above writes impacting free running MCLK are completed
-	 * before changing the clk_rate at GCC.
-	 */
-	wmb();
-
-	rc = clk_set_rate(msm_host->clk, clock);
-	if (rc) {
-		pr_err("%s: Failed to set clock at rate %u at timing %d\n",
-		       mmc_hostname(host->mmc), clock,
-		       curr_ios.timing);
-		goto out_lock;
-	}
-	msm_host->clk_rate = clock;
-	pr_debug("%s: Setting clock at rate %lu at timing %d\n",
-		 mmc_hostname(host->mmc), clk_get_rate(msm_host->clk),
-		 curr_ios.timing);
-
-out_lock:
 	spin_lock_irq(&host->lock);
 out:
 	__sdhci_msm_set_clock(host, clock);
@@ -1027,7 +1108,6 @@ static const struct of_device_id sdhci_msm_dt_match[] = {
 MODULE_DEVICE_TABLE(of, sdhci_msm_dt_match);
 
 static const struct sdhci_ops sdhci_msm_ops = {
-	.platform_execute_tuning = sdhci_msm_execute_tuning,
 	.reset = sdhci_reset,
 	.set_clock = sdhci_msm_set_clock,
 	.get_min_clock = sdhci_msm_get_min_clock,
@@ -1134,17 +1214,9 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 		goto clk_disable;
 	}
 
-	config = readl_relaxed(msm_host->core_mem + CORE_POWER);
-	config |= CORE_SW_RST;
-	writel_relaxed(config, msm_host->core_mem + CORE_POWER);
-
-	/* SW reset can take upto 10HCLK + 15MCLK cycles. (min 40us) */
-	usleep_range(1000, 5000);
-	if (readl(msm_host->core_mem + CORE_POWER) & CORE_SW_RST) {
-		dev_err(&pdev->dev, "Stuck in reset\n");
-		ret = -ETIMEDOUT;
-		goto clk_disable;
-	}
+	/* Reset the vendor spec register to power on reset state */
+	writel_relaxed(CORE_VENDOR_SPEC_POR_VAL,
+		       host->ioaddr + CORE_VENDOR_SPEC);
 
 	/* Set HC_MODE_EN bit in HC_MODE register */
 	writel_relaxed(HC_MODE_EN, (msm_host->core_mem + CORE_HC_MODE));
@@ -1210,6 +1282,7 @@ static int sdhci_msm_probe(struct platform_device *pdev)
 					 MSM_MMC_AUTOSUSPEND_DELAY_MS);
 	pm_runtime_use_autosuspend(&pdev->dev);
 
+	host->mmc_host_ops.execute_tuning = sdhci_msm_execute_tuning;
 	ret = sdhci_add_host(host);
 	if (ret)
 		goto pm_runtime_disable;
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 9a6eb4492172..d3aa67142839 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -431,6 +431,7 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 	struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host);
 	int pre_div = 1;
 	int div = 1;
+	u32 timeout;
 	u32 temp;
 
 	host->mmc->actual_clock = 0;
@@ -451,8 +452,8 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 	}
 
 	temp = sdhci_readl(host, ESDHC_SYSTEM_CONTROL);
-	temp &= ~(ESDHC_CLOCK_IPGEN | ESDHC_CLOCK_HCKEN | ESDHC_CLOCK_PEREN
-		| ESDHC_CLOCK_MASK);
+	temp &= ~(ESDHC_CLOCK_SDCLKEN | ESDHC_CLOCK_IPGEN | ESDHC_CLOCK_HCKEN |
+		  ESDHC_CLOCK_PEREN | ESDHC_CLOCK_MASK);
 	sdhci_writel(host, temp, ESDHC_SYSTEM_CONTROL);
 
 	while (host->max_clk / pre_div / 16 > clock && pre_div < 256)
@@ -472,7 +473,21 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 		| (div << ESDHC_DIVIDER_SHIFT)
 		| (pre_div << ESDHC_PREDIV_SHIFT));
 	sdhci_writel(host, temp, ESDHC_SYSTEM_CONTROL);
-	mdelay(1);
+
+	/* Wait max 20 ms */
+	timeout = 20;
+	while (!(sdhci_readl(host, ESDHC_PRSSTAT) & ESDHC_CLOCK_STABLE)) {
+		if (timeout == 0) {
+			pr_err("%s: Internal clock never stabilised.\n",
+				mmc_hostname(host->mmc));
+			return;
+		}
+		timeout--;
+		mdelay(1);
+	}
+
+	temp |= ESDHC_CLOCK_SDCLKEN;
+	sdhci_writel(host, temp, ESDHC_SYSTEM_CONTROL);
 }
 
 static void esdhc_pltfm_set_bus_width(struct sdhci_host *host, int width)
@@ -569,16 +584,19 @@ static const struct sdhci_ops sdhci_esdhc_le_ops = {
 };
 
 static const struct sdhci_pltfm_data sdhci_esdhc_be_pdata = {
-	.quirks = ESDHC_DEFAULT_QUIRKS | SDHCI_QUIRK_BROKEN_CARD_DETECTION
-		| SDHCI_QUIRK_NO_CARD_NO_RESET
-		| SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
+	.quirks = ESDHC_DEFAULT_QUIRKS |
+#ifdef CONFIG_PPC
+		  SDHCI_QUIRK_BROKEN_CARD_DETECTION |
+#endif
+		  SDHCI_QUIRK_NO_CARD_NO_RESET |
+		  SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.ops = &sdhci_esdhc_be_ops,
 };
 
 static const struct sdhci_pltfm_data sdhci_esdhc_le_pdata = {
-	.quirks = ESDHC_DEFAULT_QUIRKS | SDHCI_QUIRK_BROKEN_CARD_DETECTION
-		| SDHCI_QUIRK_NO_CARD_NO_RESET
-		| SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
+	.quirks = ESDHC_DEFAULT_QUIRKS |
+		  SDHCI_QUIRK_NO_CARD_NO_RESET |
+		  SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
 	.ops = &sdhci_esdhc_le_ops,
 };
 
@@ -643,8 +661,7 @@ static int sdhci_esdhc_probe(struct platform_device *pdev)
 	    of_device_is_compatible(np, "fsl,p5020-esdhc") ||
 	    of_device_is_compatible(np, "fsl,p4080-esdhc") ||
 	    of_device_is_compatible(np, "fsl,p1020-esdhc") ||
-	    of_device_is_compatible(np, "fsl,t1040-esdhc") ||
-	    of_device_is_compatible(np, "fsl,ls1021a-esdhc"))
+	    of_device_is_compatible(np, "fsl,t1040-esdhc"))
 		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
 
 	if (of_device_is_compatible(np, "fsl,ls1021a-esdhc"))
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 1a72d32af07f..982b3e349426 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -424,7 +424,6 @@ static int byt_sdio_probe_slot(struct sdhci_pci_slot *slot)
 static int byt_sd_probe_slot(struct sdhci_pci_slot *slot)
 {
 	slot->host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
-	slot->cd_con_id = NULL;
 	slot->cd_idx = 0;
 	slot->cd_override_level = true;
 	if (slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_BXT_SD ||
@@ -866,6 +865,86 @@ enum amd_chipset_gen {
 	AMD_CHIPSET_UNKNOWN,
 };
 
+/* AMD registers */
+#define AMD_SD_AUTO_PATTERN		0xB8
+#define AMD_MSLEEP_DURATION		4
+#define AMD_SD_MISC_CONTROL		0xD0
+#define AMD_MAX_TUNE_VALUE		0x0B
+#define AMD_AUTO_TUNE_SEL		0x10800
+#define AMD_FIFO_PTR			0x30
+#define AMD_BIT_MASK			0x1F
+
+static void amd_tuning_reset(struct sdhci_host *host)
+{
+	unsigned int val;
+
+	val = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+	val |= SDHCI_CTRL_PRESET_VAL_ENABLE | SDHCI_CTRL_EXEC_TUNING;
+	sdhci_writew(host, val, SDHCI_HOST_CONTROL2);
+
+	val = sdhci_readw(host, SDHCI_HOST_CONTROL2);
+	val &= ~SDHCI_CTRL_EXEC_TUNING;
+	sdhci_writew(host, val, SDHCI_HOST_CONTROL2);
+}
+
+static void amd_config_tuning_phase(struct pci_dev *pdev, u8 phase)
+{
+	unsigned int val;
+
+	pci_read_config_dword(pdev, AMD_SD_AUTO_PATTERN, &val);
+	val &= ~AMD_BIT_MASK;
+	val |= (AMD_AUTO_TUNE_SEL | (phase << 1));
+	pci_write_config_dword(pdev, AMD_SD_AUTO_PATTERN, val);
+}
+
+static void amd_enable_manual_tuning(struct pci_dev *pdev)
+{
+	unsigned int val;
+
+	pci_read_config_dword(pdev, AMD_SD_MISC_CONTROL, &val);
+	val |= AMD_FIFO_PTR;
+	pci_write_config_dword(pdev, AMD_SD_MISC_CONTROL, val);
+}
+
+static int amd_execute_tuning(struct sdhci_host *host, u32 opcode)
+{
+	struct sdhci_pci_slot *slot = sdhci_priv(host);
+	struct pci_dev *pdev = slot->chip->pdev;
+	u8 valid_win = 0;
+	u8 valid_win_max = 0;
+	u8 valid_win_end = 0;
+	u8 ctrl, tune_around;
+
+	amd_tuning_reset(host);
+
+	for (tune_around = 0; tune_around < 12; tune_around++) {
+		amd_config_tuning_phase(pdev, tune_around);
+
+		if (mmc_send_tuning(host->mmc, opcode, NULL)) {
+			valid_win = 0;
+			msleep(AMD_MSLEEP_DURATION);
+			ctrl = SDHCI_RESET_CMD | SDHCI_RESET_DATA;
+			sdhci_writeb(host, ctrl, SDHCI_SOFTWARE_RESET);
+		} else if (++valid_win > valid_win_max) {
+			valid_win_max = valid_win;
+			valid_win_end = tune_around;
+		}
+	}
+
+	if (!valid_win_max) {
+		dev_err(&pdev->dev, "no tuning point found\n");
+		return -EIO;
+	}
+
+	amd_config_tuning_phase(pdev, valid_win_end - valid_win_max / 2);
+
+	amd_enable_manual_tuning(pdev);
+
+	host->mmc->retune_period = 0;
+
+	return 0;
+}
+
 static int amd_probe(struct sdhci_pci_chip *chip)
 {
 	struct pci_dev	*smbus_dev;
@@ -888,16 +967,24 @@ static int amd_probe(struct sdhci_pci_chip *chip)
 		}
 	}
 
-	if ((gen == AMD_CHIPSET_BEFORE_ML) || (gen == AMD_CHIPSET_CZ)) {
+	if (gen == AMD_CHIPSET_BEFORE_ML || gen == AMD_CHIPSET_CZ)
 		chip->quirks2 |= SDHCI_QUIRK2_CLEAR_TRANSFERMODE_REG_BEFORE_CMD;
-		chip->quirks2 |= SDHCI_QUIRK2_BROKEN_HS200;
-	}
 
 	return 0;
 }
 
+static const struct sdhci_ops amd_sdhci_pci_ops = {
+	.set_clock			= sdhci_set_clock,
+	.enable_dma			= sdhci_pci_enable_dma,
+	.set_bus_width			= sdhci_pci_set_bus_width,
+	.reset				= sdhci_reset,
+	.set_uhs_signaling		= sdhci_set_uhs_signaling,
+	.platform_execute_tuning	= amd_execute_tuning,
+};
+
 static const struct sdhci_pci_fixes sdhci_amd = {
 	.probe		= amd_probe,
+	.ops		= &amd_sdhci_pci_ops,
 };
 
 static const struct pci_device_id pci_ids[] = {
@@ -1817,7 +1904,7 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot(
 	host->mmc->caps2 |= MMC_CAP2_NO_PRESCAN_POWERUP;
 
 	if (slot->cd_idx >= 0) {
-		ret = mmc_gpiod_request_cd(host->mmc, slot->cd_con_id, slot->cd_idx,
+		ret = mmc_gpiod_request_cd(host->mmc, NULL, slot->cd_idx,
 					   slot->cd_override_level, 0, NULL);
 		if (ret == -EPROBE_DEFER)
 			goto remove;
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 4abdaed72bd4..36f743464fcc 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -81,7 +81,6 @@ struct sdhci_pci_slot {
 	int			cd_gpio;
 	int			cd_irq;
 
-	char			*cd_con_id;
 	int			cd_idx;
 	bool			cd_override_level;
 
diff --git a/drivers/mmc/host/sdhci-s3c-regs.h b/drivers/mmc/host/sdhci-s3c-regs.h
deleted file mode 100644
index e34049ad44cc..000000000000
--- a/drivers/mmc/host/sdhci-s3c-regs.h
+++ /dev/null
@@ -1,87 +0,0 @@
-/* linux/arch/arm/plat-s3c/include/plat/regs-sdhci.h
- *
- * Copyright 2008 Openmoko, Inc.
- * Copyright 2008 Simtec Electronics
- *	http://armlinux.simtec.co.uk/
- *	Ben Dooks <ben@simtec.co.uk>
- *
- * S3C Platform - SDHCI (HSMMC) register definitions
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
-
-#ifndef __PLAT_S3C_SDHCI_REGS_H
-#define __PLAT_S3C_SDHCI_REGS_H __FILE__
-
-#define S3C_SDHCI_CONTROL2			(0x80)
-#define S3C_SDHCI_CONTROL3			(0x84)
-#define S3C64XX_SDHCI_CONTROL4			(0x8C)
-
-#define S3C64XX_SDHCI_CTRL2_ENSTAASYNCCLR	(1 << 31)
-#define S3C64XX_SDHCI_CTRL2_ENCMDCNFMSK		(1 << 30)
-#define S3C_SDHCI_CTRL2_CDINVRXD3		(1 << 29)
-#define S3C_SDHCI_CTRL2_SLCARDOUT		(1 << 28)
-
-#define S3C_SDHCI_CTRL2_FLTCLKSEL_MASK		(0xf << 24)
-#define S3C_SDHCI_CTRL2_FLTCLKSEL_SHIFT		(24)
-#define S3C_SDHCI_CTRL2_FLTCLKSEL(_x)		((_x) << 24)
-
-#define S3C_SDHCI_CTRL2_LVLDAT_MASK		(0xff << 16)
-#define S3C_SDHCI_CTRL2_LVLDAT_SHIFT		(16)
-#define S3C_SDHCI_CTRL2_LVLDAT(_x)		((_x) << 16)
-
-#define S3C_SDHCI_CTRL2_ENFBCLKTX		(1 << 15)
-#define S3C_SDHCI_CTRL2_ENFBCLKRX		(1 << 14)
-#define S3C_SDHCI_CTRL2_SDCDSEL			(1 << 13)
-#define S3C_SDHCI_CTRL2_SDSIGPC			(1 << 12)
-#define S3C_SDHCI_CTRL2_ENBUSYCHKTXSTART	(1 << 11)
-
-#define S3C_SDHCI_CTRL2_DFCNT_MASK		(0x3 << 9)
-#define S3C_SDHCI_CTRL2_DFCNT_SHIFT		(9)
-#define S3C_SDHCI_CTRL2_DFCNT_NONE		(0x0 << 9)
-#define S3C_SDHCI_CTRL2_DFCNT_4SDCLK		(0x1 << 9)
-#define S3C_SDHCI_CTRL2_DFCNT_16SDCLK		(0x2 << 9)
-#define S3C_SDHCI_CTRL2_DFCNT_64SDCLK		(0x3 << 9)
-
-#define S3C_SDHCI_CTRL2_ENCLKOUTHOLD		(1 << 8)
-#define S3C_SDHCI_CTRL2_RWAITMODE		(1 << 7)
-#define S3C_SDHCI_CTRL2_DISBUFRD		(1 << 6)
-#define S3C_SDHCI_CTRL2_SELBASECLK_MASK		(0x3 << 4)
-#define S3C_SDHCI_CTRL2_SELBASECLK_SHIFT	(4)
-#define S3C_SDHCI_CTRL2_PWRSYNC			(1 << 3)
-#define S3C_SDHCI_CTRL2_ENCLKOUTMSKCON		(1 << 1)
-#define S3C_SDHCI_CTRL2_HWINITFIN		(1 << 0)
-
-#define S3C_SDHCI_CTRL3_FCSEL3			(1 << 31)
-#define S3C_SDHCI_CTRL3_FCSEL2			(1 << 23)
-#define S3C_SDHCI_CTRL3_FCSEL1			(1 << 15)
-#define S3C_SDHCI_CTRL3_FCSEL0			(1 << 7)
-
-#define S3C_SDHCI_CTRL3_FIA3_MASK		(0x7f << 24)
-#define S3C_SDHCI_CTRL3_FIA3_SHIFT		(24)
-#define S3C_SDHCI_CTRL3_FIA3(_x)		((_x) << 24)
-
-#define S3C_SDHCI_CTRL3_FIA2_MASK		(0x7f << 16)
-#define S3C_SDHCI_CTRL3_FIA2_SHIFT		(16)
-#define S3C_SDHCI_CTRL3_FIA2(_x)		((_x) << 16)
-
-#define S3C_SDHCI_CTRL3_FIA1_MASK		(0x7f << 8)
-#define S3C_SDHCI_CTRL3_FIA1_SHIFT		(8)
-#define S3C_SDHCI_CTRL3_FIA1(_x)		((_x) << 8)
-
-#define S3C_SDHCI_CTRL3_FIA0_MASK		(0x7f << 0)
-#define S3C_SDHCI_CTRL3_FIA0_SHIFT		(0)
-#define S3C_SDHCI_CTRL3_FIA0(_x)		((_x) << 0)
-
-#define S3C64XX_SDHCI_CONTROL4_DRIVE_MASK	(0x3 << 16)
-#define S3C64XX_SDHCI_CONTROL4_DRIVE_SHIFT	(16)
-#define S3C64XX_SDHCI_CONTROL4_DRIVE_2mA	(0x0 << 16)
-#define S3C64XX_SDHCI_CONTROL4_DRIVE_4mA	(0x1 << 16)
-#define S3C64XX_SDHCI_CONTROL4_DRIVE_7mA	(0x2 << 16)
-#define S3C64XX_SDHCI_CONTROL4_DRIVE_9mA	(0x3 << 16)
-
-#define S3C64XX_SDHCI_CONTROL4_BUSY		(1)
-
-#endif /* __PLAT_S3C_SDHCI_REGS_H */
diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c
index de219ca7ea7c..3e5c83d435ae 100644
--- a/drivers/mmc/host/sdhci-s3c.c
+++ b/drivers/mmc/host/sdhci-s3c.c
@@ -29,11 +29,80 @@
 
 #include <linux/mmc/host.h>
 
-#include "sdhci-s3c-regs.h"
 #include "sdhci.h"
 
 #define MAX_BUS_CLK	(4)
 
+#define S3C_SDHCI_CONTROL2			(0x80)
+#define S3C_SDHCI_CONTROL3			(0x84)
+#define S3C64XX_SDHCI_CONTROL4			(0x8C)
+
+#define S3C64XX_SDHCI_CTRL2_ENSTAASYNCCLR	BIT(31)
+#define S3C64XX_SDHCI_CTRL2_ENCMDCNFMSK		BIT(30)
+#define S3C_SDHCI_CTRL2_CDINVRXD3		BIT(29)
+#define S3C_SDHCI_CTRL2_SLCARDOUT		BIT(28)
+
+#define S3C_SDHCI_CTRL2_FLTCLKSEL_MASK		(0xf << 24)
+#define S3C_SDHCI_CTRL2_FLTCLKSEL_SHIFT		(24)
+#define S3C_SDHCI_CTRL2_FLTCLKSEL(_x)		((_x) << 24)
+
+#define S3C_SDHCI_CTRL2_LVLDAT_MASK		(0xff << 16)
+#define S3C_SDHCI_CTRL2_LVLDAT_SHIFT		(16)
+#define S3C_SDHCI_CTRL2_LVLDAT(_x)		((_x) << 16)
+
+#define S3C_SDHCI_CTRL2_ENFBCLKTX		BIT(15)
+#define S3C_SDHCI_CTRL2_ENFBCLKRX		BIT(14)
+#define S3C_SDHCI_CTRL2_SDCDSEL			BIT(13)
+#define S3C_SDHCI_CTRL2_SDSIGPC			BIT(12)
+#define S3C_SDHCI_CTRL2_ENBUSYCHKTXSTART	BIT(11)
+
+#define S3C_SDHCI_CTRL2_DFCNT_MASK		(0x3 << 9)
+#define S3C_SDHCI_CTRL2_DFCNT_SHIFT		(9)
+#define S3C_SDHCI_CTRL2_DFCNT_NONE		(0x0 << 9)
+#define S3C_SDHCI_CTRL2_DFCNT_4SDCLK		(0x1 << 9)
+#define S3C_SDHCI_CTRL2_DFCNT_16SDCLK		(0x2 << 9)
+#define S3C_SDHCI_CTRL2_DFCNT_64SDCLK		(0x3 << 9)
+
+#define S3C_SDHCI_CTRL2_ENCLKOUTHOLD		BIT(8)
+#define S3C_SDHCI_CTRL2_RWAITMODE		BIT(7)
+#define S3C_SDHCI_CTRL2_DISBUFRD		BIT(6)
+
+#define S3C_SDHCI_CTRL2_SELBASECLK_MASK		(0x3 << 4)
+#define S3C_SDHCI_CTRL2_SELBASECLK_SHIFT	(4)
+#define S3C_SDHCI_CTRL2_PWRSYNC			BIT(3)
+#define S3C_SDHCI_CTRL2_ENCLKOUTMSKCON		BIT(1)
+#define S3C_SDHCI_CTRL2_HWINITFIN		BIT(0)
+
+#define S3C_SDHCI_CTRL3_FCSEL3			BIT(31)
+#define S3C_SDHCI_CTRL3_FCSEL2			BIT(23)
+#define S3C_SDHCI_CTRL3_FCSEL1			BIT(15)
+#define S3C_SDHCI_CTRL3_FCSEL0			BIT(7)
+
+#define S3C_SDHCI_CTRL3_FIA3_MASK		(0x7f << 24)
+#define S3C_SDHCI_CTRL3_FIA3_SHIFT		(24)
+#define S3C_SDHCI_CTRL3_FIA3(_x)		((_x) << 24)
+
+#define S3C_SDHCI_CTRL3_FIA2_MASK		(0x7f << 16)
+#define S3C_SDHCI_CTRL3_FIA2_SHIFT		(16)
+#define S3C_SDHCI_CTRL3_FIA2(_x)		((_x) << 16)
+
+#define S3C_SDHCI_CTRL3_FIA1_MASK		(0x7f << 8)
+#define S3C_SDHCI_CTRL3_FIA1_SHIFT		(8)
+#define S3C_SDHCI_CTRL3_FIA1(_x)		((_x) << 8)
+
+#define S3C_SDHCI_CTRL3_FIA0_MASK		(0x7f << 0)
+#define S3C_SDHCI_CTRL3_FIA0_SHIFT		(0)
+#define S3C_SDHCI_CTRL3_FIA0(_x)		((_x) << 0)
+
+#define S3C64XX_SDHCI_CONTROL4_DRIVE_MASK	(0x3 << 16)
+#define S3C64XX_SDHCI_CONTROL4_DRIVE_SHIFT	(16)
+#define S3C64XX_SDHCI_CONTROL4_DRIVE_2mA	(0x0 << 16)
+#define S3C64XX_SDHCI_CONTROL4_DRIVE_4mA	(0x1 << 16)
+#define S3C64XX_SDHCI_CONTROL4_DRIVE_7mA	(0x2 << 16)
+#define S3C64XX_SDHCI_CONTROL4_DRIVE_9mA	(0x3 << 16)
+
+#define S3C64XX_SDHCI_CONTROL4_BUSY		(1)
+
 /**
  * struct sdhci_s3c - S3C SDHCI instance
  * @host: The SDHCI host created
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 23909804ffb8..6fdd7a70f229 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2021,8 +2021,8 @@ static void sdhci_send_tuning(struct sdhci_host *host, u32 opcode,
 			      unsigned long flags)
 {
 	struct mmc_host *mmc = host->mmc;
-	struct mmc_command cmd = {0};
-	struct mmc_request mrq = {NULL};
+	struct mmc_command cmd = {};
+	struct mmc_request mrq = {};
 
 	cmd.opcode = opcode;
 	cmd.flags = MMC_RSP_R1 | MMC_CMD_ADTC;
@@ -2114,7 +2114,6 @@ int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	spin_lock_irqsave(&host->lock, flags);
 
 	hs400_tuning = host->flags & SDHCI_HS400_TUNING;
-	host->flags &= ~SDHCI_HS400_TUNING;
 
 	if (host->tuning_mode == SDHCI_TUNING_MODE_1)
 		tuning_count = host->tuning_count;
@@ -2156,7 +2155,9 @@ int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 
 	if (host->ops->platform_execute_tuning) {
 		spin_unlock_irqrestore(&host->lock, flags);
-		return host->ops->platform_execute_tuning(host, opcode);
+		err = host->ops->platform_execute_tuning(host, opcode);
+		spin_lock_irqsave(&host->lock, flags);
+		goto out_unlock;
 	}
 
 	host->mmc->retune_period = tuning_count;
@@ -2167,6 +2168,7 @@ int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 
 	sdhci_end_tuning(host);
 out_unlock:
+	host->flags &= ~SDHCI_HS400_TUNING;
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	return err;
@@ -2733,7 +2735,8 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 		if (intmask & SDHCI_INT_RETUNE)
 			mmc_retune_needed(host->mmc);
 
-		if (intmask & SDHCI_INT_CARD_INT) {
+		if ((intmask & SDHCI_INT_CARD_INT) &&
+		    (host->ier & SDHCI_INT_CARD_INT)) {
 			sdhci_enable_sdio_irq_nolock(host, false);
 			host->thread_isr |= SDHCI_INT_CARD_INT;
 			result = IRQ_WAKE_THREAD;
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 0b66f210ae82..edf3adfbc213 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -17,6 +17,8 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <linux/io.h>
+#include <linux/leds.h>
+#include <linux/interrupt.h>
 
 #include <linux/mmc/host.h>
 
diff --git a/drivers/mmc/host/sh_mmcif.c b/drivers/mmc/host/sh_mmcif.c
index 900778421be6..4062d6bef3c8 100644
--- a/drivers/mmc/host/sh_mmcif.c
+++ b/drivers/mmc/host/sh_mmcif.c
@@ -1079,26 +1079,10 @@ static void sh_mmcif_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	host->state = STATE_IDLE;
 }
 
-static int sh_mmcif_get_cd(struct mmc_host *mmc)
-{
-	struct sh_mmcif_host *host = mmc_priv(mmc);
-	struct device *dev = sh_mmcif_host_to_dev(host);
-	struct sh_mmcif_plat_data *p = dev->platform_data;
-	int ret = mmc_gpio_get_cd(mmc);
-
-	if (ret >= 0)
-		return ret;
-
-	if (!p || !p->get_cd)
-		return -ENOSYS;
-	else
-		return p->get_cd(host->pd);
-}
-
 static struct mmc_host_ops sh_mmcif_ops = {
 	.request	= sh_mmcif_request,
 	.set_ios	= sh_mmcif_set_ios,
-	.get_cd		= sh_mmcif_get_cd,
+	.get_cd		= mmc_gpio_get_cd,
 };
 
 static bool sh_mmcif_end_cmd(struct sh_mmcif_host *host)
@@ -1443,8 +1427,8 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 	host->mmc	= mmc;
 	host->addr	= reg;
 	host->timeout	= msecs_to_jiffies(10000);
-	host->ccs_enable = !pd || !pd->ccs_unsupported;
-	host->clk_ctrl2_enable = pd && pd->clk_ctrl2_present;
+	host->ccs_enable = true;
+	host->clk_ctrl2_enable = false;
 
 	host->pd = pdev;
 
@@ -1509,12 +1493,6 @@ static int sh_mmcif_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (pd && pd->use_cd_gpio) {
-		ret = mmc_gpio_request_cd(mmc, pd->cd_gpio, 0);
-		if (ret < 0)
-			goto err_clk;
-	}
-
 	mutex_init(&host->thread_lock);
 
 	ret = mmc_add_host(mmc);
diff --git a/drivers/mmc/host/sh_mobile_sdhi.c b/drivers/mmc/host/sh_mobile_sdhi.c
index d46c2d00c182..bc6be0dbea39 100644
--- a/drivers/mmc/host/sh_mobile_sdhi.c
+++ b/drivers/mmc/host/sh_mobile_sdhi.c
@@ -143,6 +143,7 @@ MODULE_DEVICE_TABLE(of, sh_mobile_sdhi_of_match);
 
 struct sh_mobile_sdhi {
 	struct clk *clk;
+	struct clk *clk_cd;
 	struct tmio_mmc_data mmc_data;
 	struct tmio_mmc_dma dma_priv;
 	struct pinctrl *pinctrl;
@@ -190,6 +191,12 @@ static int sh_mobile_sdhi_clk_enable(struct tmio_mmc_host *host)
 	if (ret < 0)
 		return ret;
 
+	ret = clk_prepare_enable(priv->clk_cd);
+	if (ret < 0) {
+		clk_disable_unprepare(priv->clk);
+		return ret;
+	}
+
 	/*
 	 * The clock driver may not know what maximum frequency
 	 * actually works, so it should be set with the max-frequency
@@ -255,6 +262,7 @@ static void sh_mobile_sdhi_clk_disable(struct tmio_mmc_host *host)
 	struct sh_mobile_sdhi *priv = host_to_priv(host);
 
 	clk_disable_unprepare(priv->clk);
+	clk_disable_unprepare(priv->clk_cd);
 }
 
 static int sh_mobile_sdhi_card_busy(struct mmc_host *mmc)
@@ -335,9 +343,6 @@ static unsigned int sh_mobile_sdhi_init_tuning(struct tmio_mmc_host *host)
 {
 	struct sh_mobile_sdhi *priv;
 
-	if (!(host->mmc->caps & MMC_CAP_UHS_SDR104))
-		return 0;
-
 	priv = host_to_priv(host);
 
 	/* set sampling clock selection range */
@@ -444,12 +449,7 @@ static int sh_mobile_sdhi_select_tuning(struct tmio_mmc_host *host)
 
 static bool sh_mobile_sdhi_check_scc_error(struct tmio_mmc_host *host)
 {
-	struct sh_mobile_sdhi *priv;
-
-	if (!(host->mmc->caps & MMC_CAP_UHS_SDR104))
-		return 0;
-
-	priv = host_to_priv(host);
+	struct sh_mobile_sdhi *priv = host_to_priv(host);
 
 	/* Check SCC error */
 	if (sd_scc_read32(host, priv, SH_MOBILE_SDHI_SCC_RVSCNTL) &
@@ -468,9 +468,6 @@ static void sh_mobile_sdhi_hw_reset(struct tmio_mmc_host *host)
 {
 	struct sh_mobile_sdhi *priv;
 
-	if (!(host->mmc->caps & MMC_CAP_UHS_SDR104))
-		return;
-
 	priv = host_to_priv(host);
 
 	/* Reset SCC */
@@ -556,8 +553,7 @@ static void sh_mobile_sdhi_enable_dma(struct tmio_mmc_host *host, bool enable)
 
 static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 {
-	const struct of_device_id *of_id =
-		of_match_device(sh_mobile_sdhi_of_match, &pdev->dev);
+	const struct sh_mobile_sdhi_of_data *of_data = of_device_get_match_data(&pdev->dev);
 	struct sh_mobile_sdhi *priv;
 	struct tmio_mmc_data *mmc_data;
 	struct tmio_mmc_data *mmd = pdev->dev.platform_data;
@@ -584,6 +580,21 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 		goto eprobe;
 	}
 
+	/*
+	 * Some controllers provide a 2nd clock just to run the internal card
+	 * detection logic. Unfortunately, the existing driver architecture does
+	 * not support a separation of clocks for runtime PM usage. When
+	 * native hotplug is used, the tmio driver assumes that the core
+	 * must continue to run for card detect to stay active, so we cannot
+	 * disable it.
+	 * Additionally, it is prohibited to supply a clock to the core but not
+	 * to the card detect circuit. That leaves us with if separate clocks
+	 * are presented, we must treat them both as virtually 1 clock.
+	 */
+	priv->clk_cd = devm_clk_get(&pdev->dev, "cd");
+	if (IS_ERR(priv->clk_cd))
+		priv->clk_cd = NULL;
+
 	priv->pinctrl = devm_pinctrl_get(&pdev->dev);
 	if (!IS_ERR(priv->pinctrl)) {
 		priv->pins_default = pinctrl_lookup_state(priv->pinctrl,
@@ -598,9 +609,8 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 		goto eprobe;
 	}
 
-	if (of_id && of_id->data) {
-		const struct sh_mobile_sdhi_of_data *of_data = of_id->data;
 
+	if (of_data) {
 		mmc_data->flags |= of_data->tmio_flags;
 		mmc_data->ocr_mask = of_data->tmio_ocr_mask;
 		mmc_data->capabilities |= of_data->capabilities;
@@ -623,11 +633,6 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 		host->card_busy	= sh_mobile_sdhi_card_busy;
 		host->start_signal_voltage_switch =
 			sh_mobile_sdhi_start_signal_voltage_switch;
-		host->init_tuning	= sh_mobile_sdhi_init_tuning;
-		host->prepare_tuning	= sh_mobile_sdhi_prepare_tuning;
-		host->select_tuning	= sh_mobile_sdhi_select_tuning;
-		host->check_scc_error	= sh_mobile_sdhi_check_scc_error;
-		host->hw_reset		= sh_mobile_sdhi_hw_reset;
 	}
 
 	/* Orginally registers were 16 bit apart, could be 32 or 64 nowadays */
@@ -659,40 +664,40 @@ static int sh_mobile_sdhi_probe(struct platform_device *pdev)
 	 */
 	mmc_data->flags |= TMIO_MMC_HAVE_CMD12_CTRL;
 
-	/*
-	 * All SDHI need SDIO_INFO1 reserved bit
-	 */
-	mmc_data->flags |= TMIO_MMC_SDIO_STATUS_QUIRK;
+	/* All SDHI have SDIO status bits which must be 1 */
+	mmc_data->flags |= TMIO_MMC_SDIO_STATUS_SETBITS;
 
 	ret = tmio_mmc_host_probe(host, mmc_data);
 	if (ret < 0)
 		goto efree;
 
-	if (host->mmc->caps & MMC_CAP_UHS_SDR104) {
+	/* Enable tuning iff we have an SCC and a supported mode */
+	if (of_data && of_data->scc_offset &&
+	    (host->mmc->caps & MMC_CAP_UHS_SDR104 ||
+	     host->mmc->caps2 & MMC_CAP2_HS200_1_8V_SDR)) {
+		const struct sh_mobile_sdhi_scc *taps = of_data->taps;
+		bool hit = false;
+
 		host->mmc->caps |= MMC_CAP_HW_RESET;
 
-		if (of_id && of_id->data) {
-			const struct sh_mobile_sdhi_of_data *of_data;
-			const struct sh_mobile_sdhi_scc *taps;
-			bool hit = false;
-
-			of_data = of_id->data;
-			taps = of_data->taps;
-
-			for (i = 0; i < of_data->taps_num; i++) {
-				if (taps[i].clk_rate == 0 ||
-				    taps[i].clk_rate == host->mmc->f_max) {
-					host->scc_tappos = taps->tap;
-					hit = true;
-					break;
-				}
+		for (i = 0; i < of_data->taps_num; i++) {
+			if (taps[i].clk_rate == 0 ||
+			    taps[i].clk_rate == host->mmc->f_max) {
+				host->scc_tappos = taps->tap;
+				hit = true;
+				break;
 			}
+		}
 
-			if (!hit)
-				dev_warn(&host->pdev->dev, "Unknown clock rate for SDR104\n");
+		if (!hit)
+			dev_warn(&host->pdev->dev, "Unknown clock rate for SDR104\n");
 
-			priv->scc_ctl = host->ctl + of_data->scc_offset;
-		}
+		priv->scc_ctl = host->ctl + of_data->scc_offset;
+		host->init_tuning = sh_mobile_sdhi_init_tuning;
+		host->prepare_tuning = sh_mobile_sdhi_prepare_tuning;
+		host->select_tuning = sh_mobile_sdhi_select_tuning;
+		host->check_scc_error = sh_mobile_sdhi_check_scc_error;
+		host->hw_reset = sh_mobile_sdhi_hw_reset;
 	}
 
 	i = 0;
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index b1d1303389a7..6ffcd2838272 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -5,6 +5,7 @@
  * (C) Copyright 2013-2014 O2S GmbH <www.o2s.ch>
  * (C) Copyright 2013-2014 David Lanzend�rfer <david.lanzendoerfer@o2s.ch>
  * (C) Copyright 2013-2014 Hans de Goede <hdegoede@redhat.com>
+ * (C) Copyright 2017 Sootech SA
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
@@ -101,6 +102,7 @@
 	(SDXC_SOFT_RESET | SDXC_FIFO_RESET | SDXC_DMA_RESET)
 
 /* clock control bits */
+#define SDXC_MASK_DATA0			BIT(31)
 #define SDXC_CARD_CLOCK_ON		BIT(16)
 #define SDXC_LOW_POWER_ON		BIT(17)
 
@@ -253,6 +255,11 @@ struct sunxi_mmc_cfg {
 
 	/* does the IP block support autocalibration? */
 	bool can_calibrate;
+
+	/* Does DATA0 needs to be masked while the clock is updated */
+	bool mask_data0;
+
+	bool needs_new_timings;
 };
 
 struct sunxi_mmc_host {
@@ -654,11 +661,16 @@ static int sunxi_mmc_oclk_onoff(struct sunxi_mmc_host *host, u32 oclk_en)
 	unsigned long expire = jiffies + msecs_to_jiffies(750);
 	u32 rval;
 
+	dev_dbg(mmc_dev(host->mmc), "%sabling the clock\n",
+		oclk_en ? "en" : "dis");
+
 	rval = mmc_readl(host, REG_CLKCR);
-	rval &= ~(SDXC_CARD_CLOCK_ON | SDXC_LOW_POWER_ON);
+	rval &= ~(SDXC_CARD_CLOCK_ON | SDXC_LOW_POWER_ON | SDXC_MASK_DATA0);
 
 	if (oclk_en)
 		rval |= SDXC_CARD_CLOCK_ON;
+	if (host->cfg->mask_data0)
+		rval |= SDXC_MASK_DATA0;
 
 	mmc_writel(host, REG_CLKCR, rval);
 
@@ -678,46 +690,29 @@ static int sunxi_mmc_oclk_onoff(struct sunxi_mmc_host *host, u32 oclk_en)
 		return -EIO;
 	}
 
+	if (host->cfg->mask_data0) {
+		rval = mmc_readl(host, REG_CLKCR);
+		mmc_writel(host, REG_CLKCR, rval & ~SDXC_MASK_DATA0);
+	}
+
 	return 0;
 }
 
 static int sunxi_mmc_calibrate(struct sunxi_mmc_host *host, int reg_off)
 {
-	u32 reg = readl(host->reg_base + reg_off);
-	u32 delay;
-	unsigned long timeout;
-
 	if (!host->cfg->can_calibrate)
 		return 0;
 
-	reg &= ~(SDXC_CAL_DL_MASK << SDXC_CAL_DL_SW_SHIFT);
-	reg &= ~SDXC_CAL_DL_SW_EN;
-
-	writel(reg | SDXC_CAL_START, host->reg_base + reg_off);
-
-	dev_dbg(mmc_dev(host->mmc), "calibration started\n");
-
-	timeout = jiffies + HZ * SDXC_CAL_TIMEOUT;
-
-	while (!((reg = readl(host->reg_base + reg_off)) & SDXC_CAL_DONE)) {
-		if (time_before(jiffies, timeout))
-			cpu_relax();
-		else {
-			reg &= ~SDXC_CAL_START;
-			writel(reg, host->reg_base + reg_off);
-
-			return -ETIMEDOUT;
-		}
-	}
-
-	delay = (reg >> SDXC_CAL_DL_SHIFT) & SDXC_CAL_DL_MASK;
-
-	reg &= ~SDXC_CAL_START;
-	reg |= (delay << SDXC_CAL_DL_SW_SHIFT) | SDXC_CAL_DL_SW_EN;
-
-	writel(reg, host->reg_base + reg_off);
-
-	dev_dbg(mmc_dev(host->mmc), "calibration ended, reg is 0x%x\n", reg);
+	/*
+	 * FIXME:
+	 * This is not clear how the calibration is supposed to work
+	 * yet. The best rate have been obtained by simply setting the
+	 * delay to 0, as Allwinner does in its BSP.
+	 *
+	 * The only mode that doesn't have such a delay is HS400, that
+	 * is in itself a TODO.
+	 */
+	writel(SDXC_CAL_DL_SW_EN, host->reg_base + reg_off);
 
 	return 0;
 }
@@ -745,6 +740,7 @@ static int sunxi_mmc_clk_set_phase(struct sunxi_mmc_host *host,
 			index = SDXC_CLK_50M_DDR;
 		}
 	} else {
+		dev_dbg(mmc_dev(host->mmc), "Invalid clock... returning\n");
 		return -EINVAL;
 	}
 
@@ -757,10 +753,21 @@ static int sunxi_mmc_clk_set_phase(struct sunxi_mmc_host *host,
 static int sunxi_mmc_clk_set_rate(struct sunxi_mmc_host *host,
 				  struct mmc_ios *ios)
 {
+	struct mmc_host *mmc = host->mmc;
 	long rate;
 	u32 rval, clock = ios->clock;
 	int ret;
 
+	ret = sunxi_mmc_oclk_onoff(host, 0);
+	if (ret)
+		return ret;
+
+	/* Our clock is gated now */
+	mmc->actual_clock = 0;
+
+	if (!ios->clock)
+		return 0;
+
 	/* 8 bit DDR requires a higher module clock */
 	if (ios->timing == MMC_TIMING_MMC_DDR52 &&
 	    ios->bus_width == MMC_BUS_WIDTH_8)
@@ -768,25 +775,21 @@ static int sunxi_mmc_clk_set_rate(struct sunxi_mmc_host *host,
 
 	rate = clk_round_rate(host->clk_mmc, clock);
 	if (rate < 0) {
-		dev_err(mmc_dev(host->mmc), "error rounding clk to %d: %ld\n",
+		dev_err(mmc_dev(mmc), "error rounding clk to %d: %ld\n",
 			clock, rate);
 		return rate;
 	}
-	dev_dbg(mmc_dev(host->mmc), "setting clk to %d, rounded %ld\n",
+	dev_dbg(mmc_dev(mmc), "setting clk to %d, rounded %ld\n",
 		clock, rate);
 
 	/* setting clock rate */
 	ret = clk_set_rate(host->clk_mmc, rate);
 	if (ret) {
-		dev_err(mmc_dev(host->mmc), "error setting clk to %ld: %d\n",
+		dev_err(mmc_dev(mmc), "error setting clk to %ld: %d\n",
 			rate, ret);
 		return ret;
 	}
 
-	ret = sunxi_mmc_oclk_onoff(host, 0);
-	if (ret)
-		return ret;
-
 	/* clear internal divider */
 	rval = mmc_readl(host, REG_CLKCR);
 	rval &= ~0xff;
@@ -798,6 +801,9 @@ static int sunxi_mmc_clk_set_rate(struct sunxi_mmc_host *host,
 	}
 	mmc_writel(host, REG_CLKCR, rval);
 
+	if (host->cfg->needs_new_timings)
+		mmc_writel(host, REG_SD_NTSR, SDXC_2X_TIMING_MODE);
+
 	ret = sunxi_mmc_clk_set_phase(host, ios, rate);
 	if (ret)
 		return ret;
@@ -806,9 +812,22 @@ static int sunxi_mmc_clk_set_rate(struct sunxi_mmc_host *host,
 	if (ret)
 		return ret;
 
-	/* TODO: enable calibrate on sdc2 SDXC_REG_DS_DL_REG of A64 */
+	/*
+	 * FIXME:
+	 *
+	 * In HS400 we'll also need to calibrate the data strobe
+	 * signal. This should only happen on the MMC2 controller (at
+	 * least on the A64).
+	 */
+
+	ret = sunxi_mmc_oclk_onoff(host, 1);
+	if (ret)
+		return ret;
+
+	/* And we just enabled our clock back */
+	mmc->actual_clock = rate;
 
-	return sunxi_mmc_oclk_onoff(host, 1);
+	return 0;
 }
 
 static void sunxi_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
@@ -882,7 +901,7 @@ static void sunxi_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	mmc_writel(host, REG_GCTRL, rval);
 
 	/* set up clock */
-	if (ios->clock && ios->power_mode) {
+	if (ios->power_mode) {
 		host->ferror = sunxi_mmc_clk_set_rate(host, ios);
 		/* Android code had a usleep_range(50000, 55000); here */
 	}
@@ -1089,6 +1108,14 @@ static const struct sunxi_mmc_cfg sun50i_a64_cfg = {
 	.idma_des_size_bits = 16,
 	.clk_delays = NULL,
 	.can_calibrate = true,
+	.mask_data0 = true,
+	.needs_new_timings = true,
+};
+
+static const struct sunxi_mmc_cfg sun50i_a64_emmc_cfg = {
+	.idma_des_size_bits = 13,
+	.clk_delays = NULL,
+	.can_calibrate = true,
 };
 
 static const struct of_device_id sunxi_mmc_of_match[] = {
@@ -1097,6 +1124,7 @@ static const struct of_device_id sunxi_mmc_of_match[] = {
 	{ .compatible = "allwinner,sun7i-a20-mmc", .data = &sun7i_a20_cfg },
 	{ .compatible = "allwinner,sun9i-a80-mmc", .data = &sun9i_a80_cfg },
 	{ .compatible = "allwinner,sun50i-a64-mmc", .data = &sun50i_a64_cfg },
+	{ .compatible = "allwinner,sun50i-a64-emmc", .data = &sun50i_a64_emmc_cfg },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sunxi_mmc_of_match);
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index 9e20bcf3aa8d..2b349d48fb9a 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -24,6 +24,7 @@
 #include <linux/pagemap.h>
 #include <linux/scatterlist.h>
 #include <linux/spinlock.h>
+#include <linux/interrupt.h>
 
 #define CTL_SD_CMD 0x00
 #define CTL_ARG_REG 0x04
@@ -90,6 +91,8 @@
 #define TMIO_SDIO_STAT_EXWT	0x8000
 #define TMIO_SDIO_MASK_ALL	0xc007
 
+#define TMIO_SDIO_SETBITS_MASK	0x0006
+
 /* Define some IRQ masks */
 /* This is the mask used at reset by the chip */
 #define TMIO_MASK_ALL           0x837f031d
diff --git a/drivers/mmc/host/tmio_mmc_pio.c b/drivers/mmc/host/tmio_mmc_pio.c
index 2064fa1a5bf1..6b789a739d4d 100644
--- a/drivers/mmc/host/tmio_mmc_pio.c
+++ b/drivers/mmc/host/tmio_mmc_pio.c
@@ -134,18 +134,25 @@ static void tmio_mmc_enable_sdio_irq(struct mmc_host *mmc, int enable)
 	struct tmio_mmc_host *host = mmc_priv(mmc);
 
 	if (enable && !host->sdio_irq_enabled) {
+		u16 sdio_status;
+
 		/* Keep device active while SDIO irq is enabled */
 		pm_runtime_get_sync(mmc_dev(mmc));
-		host->sdio_irq_enabled = true;
 
+		host->sdio_irq_enabled = true;
 		host->sdio_irq_mask = TMIO_SDIO_MASK_ALL &
 					~TMIO_SDIO_STAT_IOIRQ;
-		sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0001);
+
+		/* Clear obsolete interrupts before enabling */
+		sdio_status = sd_ctrl_read16(host, CTL_SDIO_STATUS) & ~TMIO_SDIO_MASK_ALL;
+		if (host->pdata->flags & TMIO_MMC_SDIO_STATUS_SETBITS)
+			sdio_status |= TMIO_SDIO_SETBITS_MASK;
+		sd_ctrl_write16(host, CTL_SDIO_STATUS, sdio_status);
+
 		sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask);
 	} else if (!enable && host->sdio_irq_enabled) {
 		host->sdio_irq_mask = TMIO_SDIO_MASK_ALL;
 		sd_ctrl_write16(host, CTL_SDIO_IRQ_MASK, host->sdio_irq_mask);
-		sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0000);
 
 		host->sdio_irq_enabled = false;
 		pm_runtime_mark_last_busy(mmc_dev(mmc));
@@ -711,9 +718,8 @@ static bool __tmio_mmc_sdcard_irq(struct tmio_mmc_host *host,
 	return false;
 }
 
-static void tmio_mmc_sdio_irq(int irq, void *devid)
+static void __tmio_mmc_sdio_irq(struct tmio_mmc_host *host)
 {
-	struct tmio_mmc_host *host = devid;
 	struct mmc_host *mmc = host->mmc;
 	struct tmio_mmc_data *pdata = host->pdata;
 	unsigned int ireg, status;
@@ -726,8 +732,8 @@ static void tmio_mmc_sdio_irq(int irq, void *devid)
 	ireg = status & TMIO_SDIO_MASK_ALL & ~host->sdio_irq_mask;
 
 	sdio_status = status & ~TMIO_SDIO_MASK_ALL;
-	if (pdata->flags & TMIO_MMC_SDIO_STATUS_QUIRK)
-		sdio_status |= 6;
+	if (pdata->flags & TMIO_MMC_SDIO_STATUS_SETBITS)
+		sdio_status |= TMIO_SDIO_SETBITS_MASK;
 
 	sd_ctrl_write16(host, CTL_SDIO_STATUS, sdio_status);
 
@@ -754,7 +760,7 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid)
 	if (__tmio_mmc_sdcard_irq(host, ireg, status))
 		return IRQ_HANDLED;
 
-	tmio_mmc_sdio_irq(irq, devid);
+	__tmio_mmc_sdio_irq(host);
 
 	return IRQ_HANDLED;
 }
@@ -902,6 +908,12 @@ static int tmio_mmc_clk_enable(struct tmio_mmc_host *host)
 	return host->clk_enable(host);
 }
 
+static void tmio_mmc_clk_disable(struct tmio_mmc_host *host)
+{
+	if (host->clk_disable)
+		host->clk_disable(host);
+}
+
 static void tmio_mmc_power_on(struct tmio_mmc_host *host, unsigned short vdd)
 {
 	struct mmc_host *mmc = host->mmc;
@@ -1145,7 +1157,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 
 	ret = mmc_of_parse(mmc);
 	if (ret < 0)
-		goto host_free;
+		return ret;
 
 	_host->pdata = pdata;
 	platform_set_drvdata(pdev, mmc);
@@ -1155,14 +1167,12 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 
 	ret = tmio_mmc_init_ocr(_host);
 	if (ret < 0)
-		goto host_free;
+		return ret;
 
 	_host->ctl = devm_ioremap(&pdev->dev,
 				  res_ctl->start, resource_size(res_ctl));
-	if (!_host->ctl) {
-		ret = -ENOMEM;
-		goto host_free;
-	}
+	if (!_host->ctl)
+		return -ENOMEM;
 
 	tmio_mmc_ops.card_busy = _host->card_busy;
 	tmio_mmc_ops.start_signal_voltage_switch = _host->start_signal_voltage_switch;
@@ -1179,8 +1189,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 
 	_host->native_hotplug = !(pdata->flags & TMIO_MMC_USE_GPIO_CD ||
 				  mmc->caps & MMC_CAP_NEEDS_POLL ||
-				  !mmc_card_is_removable(mmc) ||
-				  mmc->slot.cd_irq >= 0);
+				  !mmc_card_is_removable(mmc));
 
 	/*
 	 * On Gen2+, eMMC with NONREMOVABLE currently fails because native
@@ -1200,10 +1209,8 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	 * Check the sanity of mmc->f_min to prevent tmio_mmc_set_clock() from
 	 * looping forever...
 	 */
-	if (mmc->f_min == 0) {
-		ret = -EINVAL;
-		goto host_free;
-	}
+	if (mmc->f_min == 0)
+		return -EINVAL;
 
 	/*
 	 * While using internal tmio hardware logic for card detection, we need
@@ -1232,7 +1239,7 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	if (pdata->flags & TMIO_MMC_SDIO_IRQ) {
 		_host->sdio_irq_mask = TMIO_SDIO_MASK_ALL;
 		sd_ctrl_write16(_host, CTL_SDIO_IRQ_MASK, _host->sdio_irq_mask);
-		sd_ctrl_write16(_host, CTL_TRANSACTION_CTL, 0x0000);
+		sd_ctrl_write16(_host, CTL_TRANSACTION_CTL, 0x0001);
 	}
 
 	spin_lock_init(&_host->lock);
@@ -1268,10 +1275,6 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host,
 	}
 
 	return 0;
-
-host_free:
-
-	return ret;
 }
 EXPORT_SYMBOL(tmio_mmc_host_probe);
 
@@ -1280,6 +1283,9 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 	struct platform_device *pdev = host->pdev;
 	struct mmc_host *mmc = host->mmc;
 
+	if (host->pdata->flags & TMIO_MMC_SDIO_IRQ)
+		sd_ctrl_write16(host, CTL_TRANSACTION_CTL, 0x0000);
+
 	if (!host->native_hotplug)
 		pm_runtime_get_sync(&pdev->dev);
 
@@ -1292,6 +1298,8 @@ void tmio_mmc_host_remove(struct tmio_mmc_host *host)
 
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+
+	tmio_mmc_clk_disable(host);
 }
 EXPORT_SYMBOL(tmio_mmc_host_remove);
 
@@ -1306,8 +1314,7 @@ int tmio_mmc_host_runtime_suspend(struct device *dev)
 	if (host->clk_cache)
 		tmio_mmc_clk_stop(host);
 
-	if (host->clk_disable)
-		host->clk_disable(host);
+	tmio_mmc_clk_disable(host);
 
 	return 0;
 }
diff --git a/drivers/mmc/host/via-sdmmc.c b/drivers/mmc/host/via-sdmmc.c
index 63fac78b3d46..6380044c0628 100644
--- a/drivers/mmc/host/via-sdmmc.c
+++ b/drivers/mmc/host/via-sdmmc.c
@@ -13,6 +13,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/highmem.h>
 #include <linux/delay.h>
+#include <linux/interrupt.h>
 
 #include <linux/mmc/host.h>
 
diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c
index bb3e0d1dd355..c061e7c704be 100644
--- a/drivers/mmc/host/vub300.c
+++ b/drivers/mmc/host/vub300.c
@@ -640,8 +640,6 @@ static void __vub300_irqpoll_response(struct vub300_mmc_host *vub300)
 		mutex_lock(&vub300->irq_mutex);
 		if (vub300->irq_enabled)
 			mmc_signal_sdio_irq(vub300->mmc);
-		else if (vub300->irqs_queued)
-			vub300->irqs_queued += 1;
 		else
 			vub300->irqs_queued += 1;
 		vub300->irq_disabled = 0;
@@ -728,8 +726,7 @@ static void vub300_deadwork_thread(struct work_struct *work)
 		 */
 	} else if (vub300->card_present) {
 		check_vub300_port_status(vub300);
-	} else if (vub300->mmc && vub300->mmc->card &&
-		   mmc_card_present(vub300->mmc->card)) {
+	} else if (vub300->mmc && vub300->mmc->card) {
 		/*
 		 * the MMC core must not have responded
 		 * to the previous indication - lets
@@ -1756,8 +1753,7 @@ static void vub300_cmndwork_thread(struct work_struct *work)
 		int data_length;
 		mutex_lock(&vub300->cmd_mutex);
 		init_completion(&vub300->command_complete);
-		if (likely(vub300->vub_name[0]) || !vub300->mmc->card ||
-		    !mmc_card_present(vub300->mmc->card)) {
+		if (likely(vub300->vub_name[0]) || !vub300->mmc->card) {
 			/*
 			 * the name of the EMPTY Pseudo firmware file
 			 * is used as a flag to indicate that the file
diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c
index 80a3b11f3217..bd04e8bae010 100644
--- a/drivers/mmc/host/wbsd.c
+++ b/drivers/mmc/host/wbsd.c
@@ -1437,11 +1437,14 @@ err:
 
 static void wbsd_release_dma(struct wbsd_host *host)
 {
-	if (!dma_mapping_error(mmc_dev(host->mmc), host->dma_addr)) {
+	/*
+	 * host->dma_addr is valid here iff host->dma_buffer is not NULL.
+	 */
+	if (host->dma_buffer) {
 		dma_unmap_single(mmc_dev(host->mmc), host->dma_addr,
 			WBSD_DMA_SIZE, DMA_BIDIRECTIONAL);
+		kfree(host->dma_buffer);
 	}
-	kfree(host->dma_buffer);
 	if (host->dma >= 0)
 		free_dma(host->dma);
 
diff --git a/drivers/mmc/host/wmt-sdmmc.c b/drivers/mmc/host/wmt-sdmmc.c
index 5af00559e9d6..21ebba88679c 100644
--- a/drivers/mmc/host/wmt-sdmmc.c
+++ b/drivers/mmc/host/wmt-sdmmc.c
@@ -20,6 +20,7 @@
 #include <linux/irq.h>
 #include <linux/clk.h>
 #include <linux/gpio.h>
+#include <linux/interrupt.h>
 
 #include <linux/of.h>
 #include <linux/of_address.h>
diff --git a/drivers/mtd/bcm47xxpart.c b/drivers/mtd/bcm47xxpart.c
index 283ff7e17a0f..d10fa6c8f074 100644
--- a/drivers/mtd/bcm47xxpart.c
+++ b/drivers/mtd/bcm47xxpart.c
@@ -9,6 +9,7 @@
  *
  */
 
+#include <linux/bcm47xx_nvram.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -83,6 +84,91 @@ out_default:
 	return "rootfs";
 }
 
+static int bcm47xxpart_parse_trx(struct mtd_info *master,
+				 struct mtd_partition *trx,
+				 struct mtd_partition *parts,
+				 size_t parts_len)
+{
+	struct trx_header header;
+	size_t bytes_read;
+	int curr_part = 0;
+	int i, err;
+
+	if (parts_len < 3) {
+		pr_warn("No enough space to add TRX partitions!\n");
+		return -ENOMEM;
+	}
+
+	err = mtd_read(master, trx->offset, sizeof(header), &bytes_read,
+		       (uint8_t *)&header);
+	if (err && !mtd_is_bitflip(err)) {
+		pr_err("mtd_read error while reading TRX header: %d\n", err);
+		return err;
+	}
+
+	i = 0;
+
+	/* We have LZMA loader if offset[2] points to sth */
+	if (header.offset[2]) {
+		bcm47xxpart_add_part(&parts[curr_part++], "loader",
+				     trx->offset + header.offset[i], 0);
+		i++;
+	}
+
+	if (header.offset[i]) {
+		bcm47xxpart_add_part(&parts[curr_part++], "linux",
+				     trx->offset + header.offset[i], 0);
+		i++;
+	}
+
+	if (header.offset[i]) {
+		size_t offset = trx->offset + header.offset[i];
+		const char *name = bcm47xxpart_trx_data_part_name(master,
+								  offset);
+
+		bcm47xxpart_add_part(&parts[curr_part++], name, offset, 0);
+		i++;
+	}
+
+	/*
+	 * Assume that every partition ends at the beginning of the one it is
+	 * followed by.
+	 */
+	for (i = 0; i < curr_part; i++) {
+		u64 next_part_offset = (i < curr_part - 1) ?
+					parts[i + 1].offset :
+					trx->offset + trx->size;
+
+		parts[i].size = next_part_offset - parts[i].offset;
+	}
+
+	return curr_part;
+}
+
+/**
+ * bcm47xxpart_bootpartition - gets index of TRX partition used by bootloader
+ *
+ * Some devices may have more than one TRX partition. In such case one of them
+ * is the main one and another a failsafe one. Bootloader may fallback to the
+ * failsafe firmware if it detects corruption of the main image.
+ *
+ * This function provides info about currently used TRX partition. It's the one
+ * containing kernel started by the bootloader.
+ */
+static int bcm47xxpart_bootpartition(void)
+{
+	char buf[4];
+	int bootpartition;
+
+	/* Check CFE environment variable */
+	if (bcm47xx_nvram_getenv("bootpartition", buf, sizeof(buf)) > 0) {
+		if (!kstrtoint(buf, 0, &bootpartition))
+			return bootpartition;
+	}
+
+	return 0;
+}
+
 static int bcm47xxpart_parse(struct mtd_info *master,
 			     const struct mtd_partition **pparts,
 			     struct mtd_part_parser_data *data)
@@ -93,9 +179,8 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 	size_t bytes_read;
 	uint32_t offset;
 	uint32_t blocksize = master->erasesize;
-	struct trx_header *trx;
-	int trx_part = -1;
-	int last_trx_part = -1;
+	int trx_parts[2]; /* Array with indexes of TRX partitions */
+	int trx_num = 0; /* Number of found TRX partitions */
 	int possible_nvram_sizes[] = { 0x8000, 0xF000, 0x10000, };
 	int err;
 
@@ -182,54 +267,18 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 
 		/* TRX */
 		if (buf[0x000 / 4] == TRX_MAGIC) {
-			if (BCM47XXPART_MAX_PARTS - curr_part < 4) {
-				pr_warn("Not enough partitions left to register trx, scanning stopped!\n");
-				break;
-			}
-
-			trx = (struct trx_header *)buf;
+			struct trx_header *trx;
 
-			trx_part = curr_part;
+			if (trx_num >= ARRAY_SIZE(trx_parts))
+				pr_warn("No enough space to store another TRX found at 0x%X\n",
+					offset);
+			else
+				trx_parts[trx_num++] = curr_part;
 			bcm47xxpart_add_part(&parts[curr_part++], "firmware",
 					     offset, 0);
 
-			i = 0;
-			/* We have LZMA loader if offset[2] points to sth */
-			if (trx->offset[2]) {
-				bcm47xxpart_add_part(&parts[curr_part++],
-						     "loader",
-						     offset + trx->offset[i],
-						     0);
-				i++;
-			}
-
-			if (trx->offset[i]) {
-				bcm47xxpart_add_part(&parts[curr_part++],
-						     "linux",
-						     offset + trx->offset[i],
-						     0);
-				i++;
-			}
-
-			/*
-			 * Pure rootfs size is known and can be calculated as:
-			 * trx->length - trx->offset[i]. We don't fill it as
-			 * we want to have jffs2 (overlay) in the same mtd.
-			 */
-			if (trx->offset[i]) {
-				const char *name;
-
-				name = bcm47xxpart_trx_data_part_name(master, offset + trx->offset[i]);
-				bcm47xxpart_add_part(&parts[curr_part++],
-						     name,
-						     offset + trx->offset[i],
-						     0);
-				i++;
-			}
-
-			last_trx_part = curr_part - 1;
-
 			/* Jump to the end of TRX */
+			trx = (struct trx_header *)buf;
 			offset = roundup(offset + trx->length, blocksize);
 			/* Next loop iteration will increase the offset */
 			offset -= blocksize;
@@ -307,9 +356,23 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 				       parts[i + 1].offset : master->size;
 
 		parts[i].size = next_part_offset - parts[i].offset;
-		if (i == last_trx_part && trx_part >= 0)
-			parts[trx_part].size = next_part_offset -
-					       parts[trx_part].offset;
+	}
+
+	/* If there was TRX parse it now */
+	for (i = 0; i < trx_num; i++) {
+		struct mtd_partition *trx = &parts[trx_parts[i]];
+
+		if (i == bcm47xxpart_bootpartition()) {
+			int num_parts;
+
+			num_parts = bcm47xxpart_parse_trx(master, trx,
+							  parts + curr_part,
+							  BCM47XXPART_MAX_PARTS - curr_part);
+			if (num_parts > 0)
+				curr_part += num_parts;
+		} else {
+			trx->name = "failsafe";
+		}
 	}
 
 	*pparts = parts;
diff --git a/drivers/mtd/devices/bcm47xxsflash.c b/drivers/mtd/devices/bcm47xxsflash.c
index 514be04c0b6c..e2bd81817df4 100644
--- a/drivers/mtd/devices/bcm47xxsflash.c
+++ b/drivers/mtd/devices/bcm47xxsflash.c
@@ -105,15 +105,33 @@ static int bcm47xxsflash_read(struct mtd_info *mtd, loff_t from, size_t len,
 			      size_t *retlen, u_char *buf)
 {
 	struct bcm47xxsflash *b47s = mtd->priv;
+	size_t orig_len = len;
 
 	/* Check address range */
 	if ((from + len) > mtd->size)
 		return -EINVAL;
 
-	memcpy_fromio(buf, b47s->window + from, len);
-	*retlen = len;
+	/* Read as much as possible using fast MMIO window */
+	if (from < BCM47XXSFLASH_WINDOW_SZ) {
+		size_t memcpy_len;
 
-	return len;
+		memcpy_len = min(len, (size_t)(BCM47XXSFLASH_WINDOW_SZ - from));
+		memcpy_fromio(buf, b47s->window + from, memcpy_len);
+		from += memcpy_len;
+		len -= memcpy_len;
+		buf += memcpy_len;
+	}
+
+	/* Use indirect access for content out of the window */
+	for (; len; len--) {
+		b47s->cc_write(b47s, BCMA_CC_FLASHADDR, from++);
+		bcm47xxsflash_cmd(b47s, OPCODE_ST_READ4B);
+		*buf++ = b47s->cc_read(b47s, BCMA_CC_FLASHDATA);
+	}
+
+	*retlen = orig_len;
+
+	return orig_len;
 }
 
 static int bcm47xxsflash_write_st(struct mtd_info *mtd, u32 offset, size_t len,
@@ -284,7 +302,6 @@ static int bcm47xxsflash_bcma_probe(struct platform_device *pdev)
 	b47s = devm_kzalloc(dev, sizeof(*b47s), GFP_KERNEL);
 	if (!b47s)
 		return -ENOMEM;
-	sflash->priv = b47s;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
@@ -334,6 +351,8 @@ static int bcm47xxsflash_bcma_probe(struct platform_device *pdev)
 	b47s->size = sflash->size;
 	bcm47xxsflash_fill_mtd(b47s, &pdev->dev);
 
+	platform_set_drvdata(pdev, b47s);
+
 	err = mtd_device_parse_register(&b47s->mtd, probes, NULL, NULL, 0);
 	if (err) {
 		pr_err("Failed to register MTD device: %d\n", err);
@@ -349,8 +368,7 @@ static int bcm47xxsflash_bcma_probe(struct platform_device *pdev)
 
 static int bcm47xxsflash_bcma_remove(struct platform_device *pdev)
 {
-	struct bcma_sflash *sflash = dev_get_platdata(&pdev->dev);
-	struct bcm47xxsflash *b47s = sflash->priv;
+	struct bcm47xxsflash *b47s = platform_get_drvdata(pdev);
 
 	mtd_device_unregister(&b47s->mtd);
 	iounmap(b47s->window);
diff --git a/drivers/mtd/devices/bcm47xxsflash.h b/drivers/mtd/devices/bcm47xxsflash.h
index 1564b62b412e..b2d7b38f75fd 100644
--- a/drivers/mtd/devices/bcm47xxsflash.h
+++ b/drivers/mtd/devices/bcm47xxsflash.h
@@ -3,6 +3,8 @@
 
 #include <linux/mtd/mtd.h>
 
+#define BCM47XXSFLASH_WINDOW_SZ			SZ_16M
+
 /* Used for ST flashes only. */
 #define OPCODE_ST_WREN		0x0006		/* Write Enable */
 #define OPCODE_ST_WRDIS		0x0004		/* Write Disable */
@@ -16,6 +18,7 @@
 #define OPCODE_ST_RES		0x03ab		/* Read Electronic Signature */
 #define OPCODE_ST_CSA		0x1000		/* Keep chip select asserted */
 #define OPCODE_ST_SSE		0x0220		/* Sub-sector Erase */
+#define OPCODE_ST_READ4B	0x6313		/* Read Data Bytes in 4Byte addressing mode */
 
 /* Used for Atmel flashes only. */
 #define OPCODE_AT_READ				0x07e8
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 9cf7fcd28034..c4df3b1bded0 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -172,7 +172,8 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
 
 	t[1].rx_buf = buf;
 	t[1].rx_nbits = m25p80_rx_nbits(nor);
-	t[1].len = min(len, spi_max_transfer_size(spi));
+	t[1].len = min3(len, spi_max_transfer_size(spi),
+			spi_max_message_size(spi) - t[0].len);
 	spi_message_add_tail(&t[1], &m);
 
 	ret = spi_sync(spi, &m);
@@ -288,7 +289,6 @@ static const struct spi_device_id m25p_ids[] = {
 	 * should be kept for backward compatibility.
 	 */
 	{"at25df321a"},	{"at25df641"},	{"at26df081a"},
-	{"mr25h256"},
 	{"mx25l4005a"},	{"mx25l1606e"},	{"mx25l6405d"},	{"mx25l12805d"},
 	{"mx25l25635e"},{"mx66l51235l"},
 	{"n25q064"},	{"n25q128a11"},	{"n25q128a13"},	{"n25q512a"},
@@ -305,6 +305,11 @@ static const struct spi_device_id m25p_ids[] = {
 	{"m25p40-nonjedec"},	{"m25p80-nonjedec"},	{"m25p16-nonjedec"},
 	{"m25p32-nonjedec"},	{"m25p64-nonjedec"},	{"m25p128-nonjedec"},
 
+	/* Everspin MRAMs (non-JEDEC) */
+	{ "mr25h256" }, /* 256 Kib, 40 MHz */
+	{ "mr25h10" },  /*   1 Mib, 40 MHz */
+	{ "mr25h40" },  /*   4 Mib, 40 MHz */
+
 	{ },
 };
 MODULE_DEVICE_TABLE(spi, m25p_ids);
diff --git a/drivers/mtd/devices/serial_flash_cmds.h b/drivers/mtd/devices/serial_flash_cmds.h
index f59a125295d0..8b81e15105dd 100644
--- a/drivers/mtd/devices/serial_flash_cmds.h
+++ b/drivers/mtd/devices/serial_flash_cmds.h
@@ -18,19 +18,12 @@
 #define SPINOR_OP_RDVCR		0x85
 
 /* JEDEC Standard - Serial Flash Discoverable Parmeters (SFDP) Commands */
-#define SPINOR_OP_READ_1_2_2	0xbb	/* DUAL I/O READ */
-#define SPINOR_OP_READ_1_4_4	0xeb	/* QUAD I/O READ */
-
 #define SPINOR_OP_WRITE		0x02	/* PAGE PROGRAM */
 #define SPINOR_OP_WRITE_1_1_2	0xa2	/* DUAL INPUT PROGRAM */
 #define SPINOR_OP_WRITE_1_2_2	0xd2	/* DUAL INPUT EXT PROGRAM */
 #define SPINOR_OP_WRITE_1_1_4	0x32	/* QUAD INPUT PROGRAM */
 #define SPINOR_OP_WRITE_1_4_4	0x12	/* QUAD INPUT EXT PROGRAM */
 
-/* READ commands with 32-bit addressing */
-#define SPINOR_OP_READ4_1_2_2	0xbc
-#define SPINOR_OP_READ4_1_4_4	0xec
-
 /* Configuration flags */
 #define FLASH_FLAG_SINGLE	0x000000ff
 #define FLASH_FLAG_READ_WRITE	0x00000001
diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c
index 5454b4113589..804313a33f2b 100644
--- a/drivers/mtd/devices/st_spi_fsm.c
+++ b/drivers/mtd/devices/st_spi_fsm.c
@@ -507,13 +507,13 @@ static struct seq_rw_config n25q_read3_configs[] = {
  *	- 'FAST' variants configured for 8 dummy cycles (see note above.)
  */
 static struct seq_rw_config n25q_read4_configs[] = {
-	{FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ4_1_4_4,	0, 4, 4, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ4_1_1_4,	0, 1, 4, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ4_1_2_2,	0, 2, 2, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ4_1_1_2,	0, 1, 2, 0x00, 0, 8},
-	{FLASH_FLAG_READ_FAST,	SPINOR_OP_READ4_FAST,	0, 1, 1, 0x00, 0, 8},
-	{FLASH_FLAG_READ_WRITE, SPINOR_OP_READ4,	0, 1, 1, 0x00, 0, 0},
-	{0x00,			0,			0, 0, 0, 0x00, 0, 0},
+	{FLASH_FLAG_READ_1_4_4, SPINOR_OP_READ_1_4_4_4B, 0, 4, 4, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_1_4, SPINOR_OP_READ_1_1_4_4B, 0, 1, 4, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_2_2, SPINOR_OP_READ_1_2_2_4B, 0, 2, 2, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_1_2, SPINOR_OP_READ_1_1_2_4B, 0, 1, 2, 0x00, 0, 8},
+	{FLASH_FLAG_READ_FAST,	SPINOR_OP_READ_FAST_4B,  0, 1, 1, 0x00, 0, 8},
+	{FLASH_FLAG_READ_WRITE, SPINOR_OP_READ_4B,       0, 1, 1, 0x00, 0, 0},
+	{0x00,			0,                       0, 0, 0, 0x00, 0, 0},
 };
 
 /*
@@ -553,13 +553,13 @@ static int stfsm_mx25_en_32bit_addr_seq(struct stfsm_seq *seq)
  * entering a state that is incompatible with the SPIBoot Controller.
  */
 static struct seq_rw_config stfsm_s25fl_read4_configs[] = {
-	{FLASH_FLAG_READ_1_4_4,  SPINOR_OP_READ4_1_4_4,  0, 4, 4, 0x00, 2, 4},
-	{FLASH_FLAG_READ_1_1_4,  SPINOR_OP_READ4_1_1_4,  0, 1, 4, 0x00, 0, 8},
-	{FLASH_FLAG_READ_1_2_2,  SPINOR_OP_READ4_1_2_2,  0, 2, 2, 0x00, 4, 0},
-	{FLASH_FLAG_READ_1_1_2,  SPINOR_OP_READ4_1_1_2,  0, 1, 2, 0x00, 0, 8},
-	{FLASH_FLAG_READ_FAST,   SPINOR_OP_READ4_FAST,   0, 1, 1, 0x00, 0, 8},
-	{FLASH_FLAG_READ_WRITE,  SPINOR_OP_READ4,        0, 1, 1, 0x00, 0, 0},
-	{0x00,                   0,                      0, 0, 0, 0x00, 0, 0},
+	{FLASH_FLAG_READ_1_4_4,  SPINOR_OP_READ_1_4_4_4B,  0, 4, 4, 0x00, 2, 4},
+	{FLASH_FLAG_READ_1_1_4,  SPINOR_OP_READ_1_1_4_4B,  0, 1, 4, 0x00, 0, 8},
+	{FLASH_FLAG_READ_1_2_2,  SPINOR_OP_READ_1_2_2_4B,  0, 2, 2, 0x00, 4, 0},
+	{FLASH_FLAG_READ_1_1_2,  SPINOR_OP_READ_1_1_2_4B,  0, 1, 2, 0x00, 0, 8},
+	{FLASH_FLAG_READ_FAST,   SPINOR_OP_READ_FAST_4B,   0, 1, 1, 0x00, 0, 8},
+	{FLASH_FLAG_READ_WRITE,  SPINOR_OP_READ_4B,        0, 1, 1, 0x00, 0, 0},
+	{0x00,                   0,                        0, 0, 0, 0x00, 0, 0},
 };
 
 static struct seq_rw_config stfsm_s25fl_write4_configs[] = {
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index 5bcc896a48c3..542fdf8e81fa 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -75,7 +75,7 @@ config MTD_PHYSMAP_OF
 	  taken from OF device tree.
 
 config MTD_PHYSMAP_OF_VERSATILE
-	bool "Support ARM Versatile physmap OF"
+	bool "ARM Versatile OF-based physical memory map handling"
 	depends on MTD_PHYSMAP_OF
 	depends on MFD_SYSCON
 	default y if (ARCH_INTEGRATOR || ARCH_VERSATILE || ARCH_REALVIEW)
@@ -84,6 +84,16 @@ config MTD_PHYSMAP_OF_VERSATILE
 	  platforms, basically to add a VPP (write protection) callback so
 	  the flash can be taken out of write protection.
 
+config MTD_PHYSMAP_OF_GEMINI
+	bool "Cortina Gemini OF-based physical memory map handling"
+	depends on MTD_PHYSMAP_OF
+	depends on MFD_SYSCON
+	default ARCH_GEMINI
+	help
+	  This provides some extra DT physmap parsing for the Gemini
+	  platforms, some detection and setting up parallel mode on the
+	  external interface.
+
 config MTD_PMC_MSP_EVM
 	tristate "CFI Flash device mapped on PMC-Sierra MSP"
 	depends on PMC_MSP && MTD_CFI
diff --git a/drivers/mtd/maps/Makefile b/drivers/mtd/maps/Makefile
index 644f7d36d35d..aef1846b4de2 100644
--- a/drivers/mtd/maps/Makefile
+++ b/drivers/mtd/maps/Makefile
@@ -17,10 +17,13 @@ obj-$(CONFIG_MTD_CK804XROM)	+= ck804xrom.o
 obj-$(CONFIG_MTD_TSUNAMI)	+= tsunami_flash.o
 obj-$(CONFIG_MTD_PXA2XX)	+= pxa2xx-flash.o
 obj-$(CONFIG_MTD_PHYSMAP)	+= physmap.o
-obj-$(CONFIG_MTD_PHYSMAP_OF)	+= physmap_of.o
 ifdef CONFIG_MTD_PHYSMAP_OF_VERSATILE
-obj-$(CONFIG_MTD_PHYSMAP_OF)	+= physmap_of_versatile.o
+physmap_of-objs += physmap_of_versatile.o
+endif
+ifdef CONFIG_MTD_PHYSMAP_OF_GEMINI
+physmap_of-objs += physmap_of_gemini.o
 endif
+obj-$(CONFIG_MTD_PHYSMAP_OF)	+= physmap_of.o
 obj-$(CONFIG_MTD_PISMO)		+= pismo.o
 obj-$(CONFIG_MTD_PMC_MSP_EVM)   += pmcmsp-flash.o
 obj-$(CONFIG_MTD_PCMCIA)	+= pcmciamtd.o
diff --git a/drivers/mtd/maps/ichxrom.c b/drivers/mtd/maps/ichxrom.c
index e17d02ae03f0..976d42f63aef 100644
--- a/drivers/mtd/maps/ichxrom.c
+++ b/drivers/mtd/maps/ichxrom.c
@@ -57,10 +57,12 @@ static void ichxrom_cleanup(struct ichxrom_window *window)
 {
 	struct ichxrom_map_info *map, *scratch;
 	u16 word;
+	int ret;
 
 	/* Disable writes through the rom window */
-	pci_read_config_word(window->pdev, BIOS_CNTL, &word);
-	pci_write_config_word(window->pdev, BIOS_CNTL, word & ~1);
+	ret = pci_read_config_word(window->pdev, BIOS_CNTL, &word);
+	if (!ret)
+		pci_write_config_word(window->pdev, BIOS_CNTL, word & ~1);
 	pci_dev_put(window->pdev);
 
 	/* Free all of the mtd devices */
diff --git a/drivers/mtd/maps/lantiq-flash.c b/drivers/mtd/maps/lantiq-flash.c
index c8febb326fa6..3e33ab66eb24 100644
--- a/drivers/mtd/maps/lantiq-flash.c
+++ b/drivers/mtd/maps/lantiq-flash.c
@@ -4,7 +4,7 @@
  *  by the Free Software Foundation.
  *
  *  Copyright (C) 2004 Liu Peng Infineon IFAP DC COM CPE
- *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
+ *  Copyright (C) 2010 John Crispin <john@phrozen.org>
  */
 
 #include <linux/err.h>
@@ -209,5 +209,5 @@ static struct platform_driver ltq_mtd_driver = {
 module_platform_driver(ltq_mtd_driver);
 
 MODULE_LICENSE("GPL");
-MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
+MODULE_AUTHOR("John Crispin <john@phrozen.org>");
 MODULE_DESCRIPTION("Lantiq SoC NOR");
diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c
index 3fad35942895..14e8909c9955 100644
--- a/drivers/mtd/maps/physmap_of.c
+++ b/drivers/mtd/maps/physmap_of.c
@@ -24,6 +24,7 @@
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/slab.h>
+#include "physmap_of_gemini.h"
 #include "physmap_of_versatile.h"
 
 struct of_flash_list {
@@ -241,11 +242,13 @@ static int of_flash_probe(struct platform_device *dev)
 		info->list[i].map.size = res_size;
 		info->list[i].map.bankwidth = be32_to_cpup(width);
 		info->list[i].map.device_node = dp;
+
+		err = of_flash_probe_gemini(dev, dp, &info->list[i].map);
+		if (err)
+			return err;
 		err = of_flash_probe_versatile(dev, dp, &info->list[i].map);
-		if (err) {
-			dev_err(&dev->dev, "Can't probe Versatile VPP\n");
+		if (err)
 			return err;
-		}
 
 		err = -ENOMEM;
 		info->list[i].map.virt = ioremap(info->list[i].map.phys,
diff --git a/drivers/mtd/maps/physmap_of_gemini.c b/drivers/mtd/maps/physmap_of_gemini.c
new file mode 100644
index 000000000000..9d371cd728ea
--- /dev/null
+++ b/drivers/mtd/maps/physmap_of_gemini.c
@@ -0,0 +1,117 @@
+/*
+ * Cortina Systems Gemini OF physmap add-on
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * This SoC has an elaborate flash control register, so we need to
+ * detect and set it up when booting on this platform.
+ */
+#include <linux/export.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/mtd/map.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/bitops.h>
+#include "physmap_of_gemini.h"
+
+/*
+ * The Flash-relevant parts of the global status register
+ * These would also be relevant for a NAND driver.
+ */
+#define GLOBAL_STATUS			0x04
+#define FLASH_TYPE_MASK			(0x3 << 24)
+#define FLASH_TYPE_NAND_2K		(0x3 << 24)
+#define FLASH_TYPE_NAND_512		(0x2 << 24)
+#define FLASH_TYPE_PARALLEL		(0x1 << 24)
+#define FLASH_TYPE_SERIAL		(0x0 << 24)
+/* if parallel */
+#define FLASH_WIDTH_16BIT		(1 << 23)	/* else 8 bit */
+/* if serial */
+#define FLASH_ATMEL			(1 << 23)	/* else STM */
+
+#define FLASH_SIZE_MASK			(0x3 << 21)
+#define NAND_256M			(0x3 << 21)	/* and more */
+#define NAND_128M			(0x2 << 21)
+#define NAND_64M			(0x1 << 21)
+#define NAND_32M			(0x0 << 21)
+#define ATMEL_16M			(0x3 << 21)	/* and more */
+#define ATMEL_8M			(0x2 << 21)
+#define ATMEL_4M_2M			(0x1 << 21)
+#define ATMEL_1M			(0x0 << 21)	/* and less */
+#define STM_32M				(1 << 22)	/* and more */
+#define STM_16M				(0 << 22)	/* and less */
+
+#define FLASH_PARALLEL_HIGH_PIN_CNT	(1 << 20)	/* else low pin cnt */
+
+/* Miscellaneous Control Register */
+#define GLOBAL_MISC_CTRL		0x30
+#define FLASH_PADS_MASK			0x07
+#define NAND_PADS_DISABLE		BIT(2)
+#define PFLASH_PADS_DISABLE		BIT(1)
+#define SFLASH_PADS_DISABLE		BIT(0)
+
+static const struct of_device_id syscon_match[] = {
+	{ .compatible = "cortina,gemini-syscon" },
+	{ },
+};
+
+int of_flash_probe_gemini(struct platform_device *pdev,
+			  struct device_node *np,
+			  struct map_info *map)
+{
+	static struct regmap *rmap;
+	struct device *dev = &pdev->dev;
+	u32 val;
+	int ret;
+
+	/* Multiplatform guard */
+	if (!of_device_is_compatible(np, "cortina,gemini-flash"))
+		return 0;
+
+	rmap = syscon_regmap_lookup_by_phandle(np, "syscon");
+	if (IS_ERR(rmap)) {
+		dev_err(dev, "no syscon\n");
+		return PTR_ERR(rmap);
+	}
+
+	ret = regmap_read(rmap, GLOBAL_STATUS, &val);
+	if (ret) {
+		dev_err(dev, "failed to read global status register\n");
+		return -ENODEV;
+	}
+	dev_dbg(dev, "global status reg: %08x\n", val);
+
+	/*
+	 * It would be contradictory if a physmap flash was NOT parallel.
+	 */
+	if ((val & FLASH_TYPE_MASK) != FLASH_TYPE_PARALLEL) {
+		dev_err(dev, "flash is not parallel\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * Complain if DT data and hardware definition is different.
+	 */
+	if (val & FLASH_WIDTH_16BIT) {
+		if (map->bankwidth != 2)
+			dev_warn(dev, "flash hardware say flash is 16 bit wide but DT says it is %d bits wide\n",
+				 map->bankwidth * 8);
+	} else {
+		if (map->bankwidth != 1)
+			dev_warn(dev, "flash hardware say flash is 8 bit wide but DT says it is %d bits wide\n",
+				 map->bankwidth * 8);
+	}
+
+	/* Activate parallel (NOR flash) mode */
+	ret = regmap_update_bits(rmap, GLOBAL_MISC_CTRL,
+				 FLASH_PADS_MASK,
+				 SFLASH_PADS_DISABLE | NAND_PADS_DISABLE);
+	if (ret) {
+		dev_err(dev, "unable to set up physmap pads\n");
+		return -ENODEV;
+	}
+
+	dev_info(&pdev->dev, "initialized Gemini-specific physmap control\n");
+
+	return 0;
+}
diff --git a/drivers/mtd/maps/physmap_of_gemini.h b/drivers/mtd/maps/physmap_of_gemini.h
new file mode 100644
index 000000000000..c675025288dd
--- /dev/null
+++ b/drivers/mtd/maps/physmap_of_gemini.h
@@ -0,0 +1,16 @@
+#include <linux/of.h>
+#include <linux/mtd/map.h>
+
+#ifdef CONFIG_MTD_PHYSMAP_OF_GEMINI
+int of_flash_probe_gemini(struct platform_device *pdev,
+			  struct device_node *np,
+			  struct map_info *map);
+#else
+static inline
+int of_flash_probe_gemini(struct platform_device *pdev,
+			  struct device_node *np,
+			  struct map_info *map)
+{
+	return 0;
+}
+#endif
diff --git a/drivers/mtd/maps/physmap_of_versatile.c b/drivers/mtd/maps/physmap_of_versatile.c
index 0f39b2a015f4..8c6ccded9be8 100644
--- a/drivers/mtd/maps/physmap_of_versatile.c
+++ b/drivers/mtd/maps/physmap_of_versatile.c
@@ -252,4 +252,3 @@ int of_flash_probe_versatile(struct platform_device *pdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(of_flash_probe_versatile);
diff --git a/drivers/mtd/maps/pmcmsp-flash.c b/drivers/mtd/maps/pmcmsp-flash.c
index f9fa3fad728e..2051f28ddac6 100644
--- a/drivers/mtd/maps/pmcmsp-flash.c
+++ b/drivers/mtd/maps/pmcmsp-flash.c
@@ -139,15 +139,13 @@ static int __init init_msp_flash(void)
 		}
 
 		msp_maps[i].bankwidth = 1;
-		msp_maps[i].name = kmalloc(7, GFP_KERNEL);
+		msp_maps[i].name = kstrndup(flash_name, 7, GFP_KERNEL);
 		if (!msp_maps[i].name) {
 			iounmap(msp_maps[i].virt);
 			kfree(msp_parts[i]);
 			goto cleanup_loop;
 		}
 
-		msp_maps[i].name = strncpy(msp_maps[i].name, flash_name, 7);
-
 		for (j = 0; j < pcnt; j++) {
 			part_name[5] = '0' + i;
 			part_name[7] = '0' + j;
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index df8a5ef334c0..6b8d5cd7dbf6 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -84,9 +84,6 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 	nsect = blk_rq_cur_bytes(req) >> tr->blkshift;
 	buf = bio_data(req->bio);
 
-	if (req->cmd_type != REQ_TYPE_FS)
-		return -EIO;
-
 	if (req_op(req) == REQ_OP_FLUSH)
 		return tr->flush(dev);
 
@@ -94,16 +91,16 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 	    get_capacity(req->rq_disk))
 		return -EIO;
 
-	if (req_op(req) == REQ_OP_DISCARD)
+	switch (req_op(req)) {
+	case REQ_OP_DISCARD:
 		return tr->discard(dev, block, nsect);
-
-	if (rq_data_dir(req) == READ) {
+	case REQ_OP_READ:
 		for (; nsect > 0; nsect--, block++, buf += tr->blksize)
 			if (tr->readsect(dev, block, buf))
 				return -EIO;
 		rq_flush_dcache_pages(req);
 		return 0;
-	} else {
+	case REQ_OP_WRITE:
 		if (!tr->writesect)
 			return -EIO;
 
@@ -112,6 +109,8 @@ static int do_blktrans_request(struct mtd_blktrans_ops *tr,
 			if (tr->writesect(dev, block, buf))
 				return -EIO;
 		return 0;
+	default:
+		return -EIO;
 	}
 }
 
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index ce5ccc573a9c..3568294d4854 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -451,7 +451,7 @@ static int mtdchar_readoob(struct file *file, struct mtd_info *mtd,
 	 * data. For our userspace tools it is important to dump areas
 	 * with ECC errors!
 	 * For kernel internal usage it also might return -EUCLEAN
-	 * to signal the caller that a bitflip has occured and has
+	 * to signal the caller that a bitflip has occurred and has
 	 * been corrected by the ECC algorithm.
 	 *
 	 * Note: currently the standard NAND function, nand_read_oob_std,
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 052772f7caef..66a9dedd1062 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1128,7 +1128,7 @@ EXPORT_SYMBOL_GPL(mtd_write_oob);
  * @oobecc: OOB region struct filled with the appropriate ECC position
  *	    information
  *
- * This functions return ECC section information in the OOB area. I you want
+ * This function returns ECC section information in the OOB area. If you want
  * to get all the ECC bytes information, then you should call
  * mtd_ooblayout_ecc(mtd, section++, oobecc) until it returns -ERANGE.
  *
@@ -1160,7 +1160,7 @@ EXPORT_SYMBOL_GPL(mtd_ooblayout_ecc);
  * @oobfree: OOB region struct filled with the appropriate free position
  *	     information
  *
- * This functions return free bytes position in the OOB area. I you want
+ * This function returns free bytes position in the OOB area. If you want
  * to get all the free bytes information, then you should call
  * mtd_ooblayout_free(mtd, section++, oobfree) until it returns -ERANGE.
  *
@@ -1190,7 +1190,7 @@ EXPORT_SYMBOL_GPL(mtd_ooblayout_free);
  * @iter: iterator function. Should be either mtd_ooblayout_free or
  *	  mtd_ooblayout_ecc depending on the region type you're searching for
  *
- * This functions returns the section id and oobregion information of a
+ * This function returns the section id and oobregion information of a
  * specific byte. For example, say you want to know where the 4th ECC byte is
  * stored, you'll use:
  *
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index fccdd49bb964..ea5e5307f667 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -349,6 +349,14 @@ static const struct mtd_ooblayout_ops part_ooblayout_ops = {
 	.free = part_ooblayout_free,
 };
 
+static int part_max_bad_blocks(struct mtd_info *mtd, loff_t ofs, size_t len)
+{
+	struct mtd_part *part = mtd_to_part(mtd);
+
+	return part->master->_max_bad_blocks(part->master,
+					     ofs + part->offset, len);
+}
+
 static inline void free_partition(struct mtd_part *p)
 {
 	kfree(p->mtd.name);
@@ -424,6 +432,7 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 	slave->mtd.dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) ?
 				&master->dev :
 				master->dev.parent;
+	slave->mtd.dev.of_node = part->of_node;
 
 	slave->mtd._read = part_read;
 	slave->mtd._write = part_write;
@@ -475,6 +484,8 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 		slave->mtd._block_isbad = part_block_isbad;
 	if (master->_block_markbad)
 		slave->mtd._block_markbad = part_block_markbad;
+	if (master->_max_bad_blocks)
+		slave->mtd._max_bad_blocks = part_max_bad_blocks;
 
 	if (master->_get_device)
 		slave->mtd._get_device = part_get_device;
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 9ce5dcb4abd0..6d4d5672d1d8 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -426,6 +426,7 @@ config MTD_NAND_ORION
 
 config MTD_NAND_OXNAS
 	tristate "NAND Flash support for Oxford Semiconductor SoC"
+	depends on ARCH_OXNAS || COMPILE_TEST
 	depends on HAS_IOMEM
 	help
 	  This enables the NAND flash controller on Oxford Semiconductor SoCs.
@@ -535,6 +536,7 @@ config MTD_NAND_JZ4780
 
 config MTD_NAND_FSMC
 	tristate "Support for NAND on ST Micros FSMC"
+	depends on OF
 	depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300
 	help
 	  Enables support for NAND Flash chips on the ST Microelectronics
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index 0a177b1bfe3e..d1570f512f0b 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -258,9 +258,15 @@ static void fsl_ifc_run_command(struct mtd_info *mtd)
 		int bufnum = nctrl->page & priv->bufnum_mask;
 		int sector = bufnum * chip->ecc.steps;
 		int sector_end = sector + chip->ecc.steps - 1;
+		__be32 *eccstat_regs;
+
+		if (ctrl->version >= FSL_IFC_VERSION_2_0_0)
+			eccstat_regs = ifc->ifc_nand.v2_nand_eccstat;
+		else
+			eccstat_regs = ifc->ifc_nand.v1_nand_eccstat;
 
 		for (i = sector / 4; i <= sector_end / 4; i++)
-			eccstat[i] = ifc_in32(&ifc->ifc_nand.nand_eccstat[i]);
+			eccstat[i] = ifc_in32(&eccstat_regs[i]);
 
 		for (i = sector; i <= sector_end; i++) {
 			errors = check_read_ecc(mtd, ctrl, eccstat, i);
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index 4924b43977ef..bda1e4667138 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -35,10 +35,133 @@
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
 #include <linux/slab.h>
-#include <linux/mtd/fsmc.h>
 #include <linux/amba/bus.h>
 #include <mtd/mtd-abi.h>
 
+#define FSMC_NAND_BW8		1
+#define FSMC_NAND_BW16		2
+
+#define FSMC_MAX_NOR_BANKS	4
+#define FSMC_MAX_NAND_BANKS	4
+
+#define FSMC_FLASH_WIDTH8	1
+#define FSMC_FLASH_WIDTH16	2
+
+/* fsmc controller registers for NOR flash */
+#define CTRL			0x0
+	/* ctrl register definitions */
+	#define BANK_ENABLE		(1 << 0)
+	#define MUXED			(1 << 1)
+	#define NOR_DEV			(2 << 2)
+	#define WIDTH_8			(0 << 4)
+	#define WIDTH_16		(1 << 4)
+	#define RSTPWRDWN		(1 << 6)
+	#define WPROT			(1 << 7)
+	#define WRT_ENABLE		(1 << 12)
+	#define WAIT_ENB		(1 << 13)
+
+#define CTRL_TIM		0x4
+	/* ctrl_tim register definitions */
+
+#define FSMC_NOR_BANK_SZ	0x8
+#define FSMC_NOR_REG_SIZE	0x40
+
+#define FSMC_NOR_REG(base, bank, reg)		(base + \
+						FSMC_NOR_BANK_SZ * (bank) + \
+						reg)
+
+/* fsmc controller registers for NAND flash */
+#define PC			0x00
+	/* pc register definitions */
+	#define FSMC_RESET		(1 << 0)
+	#define FSMC_WAITON		(1 << 1)
+	#define FSMC_ENABLE		(1 << 2)
+	#define FSMC_DEVTYPE_NAND	(1 << 3)
+	#define FSMC_DEVWID_8		(0 << 4)
+	#define FSMC_DEVWID_16		(1 << 4)
+	#define FSMC_ECCEN		(1 << 6)
+	#define FSMC_ECCPLEN_512	(0 << 7)
+	#define FSMC_ECCPLEN_256	(1 << 7)
+	#define FSMC_TCLR_1		(1)
+	#define FSMC_TCLR_SHIFT		(9)
+	#define FSMC_TCLR_MASK		(0xF)
+	#define FSMC_TAR_1		(1)
+	#define FSMC_TAR_SHIFT		(13)
+	#define FSMC_TAR_MASK		(0xF)
+#define STS			0x04
+	/* sts register definitions */
+	#define FSMC_CODE_RDY		(1 << 15)
+#define COMM			0x08
+	/* comm register definitions */
+	#define FSMC_TSET_0		0
+	#define FSMC_TSET_SHIFT		0
+	#define FSMC_TSET_MASK		0xFF
+	#define FSMC_TWAIT_6		6
+	#define FSMC_TWAIT_SHIFT	8
+	#define FSMC_TWAIT_MASK		0xFF
+	#define FSMC_THOLD_4		4
+	#define FSMC_THOLD_SHIFT	16
+	#define FSMC_THOLD_MASK		0xFF
+	#define FSMC_THIZ_1		1
+	#define FSMC_THIZ_SHIFT		24
+	#define FSMC_THIZ_MASK		0xFF
+#define ATTRIB			0x0C
+#define IOATA			0x10
+#define ECC1			0x14
+#define ECC2			0x18
+#define ECC3			0x1C
+#define FSMC_NAND_BANK_SZ	0x20
+
+#define FSMC_NAND_REG(base, bank, reg)		(base + FSMC_NOR_REG_SIZE + \
+						(FSMC_NAND_BANK_SZ * (bank)) + \
+						reg)
+
+#define FSMC_BUSY_WAIT_TIMEOUT	(1 * HZ)
+
+struct fsmc_nand_timings {
+	uint8_t tclr;
+	uint8_t tar;
+	uint8_t thiz;
+	uint8_t thold;
+	uint8_t twait;
+	uint8_t tset;
+};
+
+enum access_mode {
+	USE_DMA_ACCESS = 1,
+	USE_WORD_ACCESS,
+};
+
+/**
+ * fsmc_nand_platform_data - platform specific NAND controller config
+ * @nand_timings: timing setup for the physical NAND interface
+ * @partitions: partition table for the platform, use a default fallback
+ * if this is NULL
+ * @nr_partitions: the number of partitions in the previous entry
+ * @options: different options for the driver
+ * @width: bus width
+ * @bank: default bank
+ * @select_bank: callback to select a certain bank, this is
+ * platform-specific. If the controller only supports one bank
+ * this may be set to NULL
+ */
+struct fsmc_nand_platform_data {
+	struct fsmc_nand_timings *nand_timings;
+	struct mtd_partition	*partitions;
+	unsigned int		nr_partitions;
+	unsigned int		options;
+	unsigned int		width;
+	unsigned int		bank;
+
+	enum access_mode	mode;
+
+	void			(*select_bank)(uint32_t bank, uint32_t busw);
+
+	/* priv structures for dma accesses */
+	void			*read_dma_priv;
+	void			*write_dma_priv;
+};
+
 static int fsmc_ecc1_ooblayout_ecc(struct mtd_info *mtd, int section,
 				   struct mtd_oob_region *oobregion)
 {
@@ -714,7 +837,6 @@ static bool filter(struct dma_chan *chan, void *slave)
 	return true;
 }
 
-#ifdef CONFIG_OF
 static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
 				     struct device_node *np)
 {
@@ -757,13 +879,6 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
 	}
 	return 0;
 }
-#else
-static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
-				     struct device_node *np)
-{
-	return -ENOSYS;
-}
-#endif
 
 /*
  * fsmc_nand_probe - Probe function
@@ -782,19 +897,15 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	u32 pid;
 	int i;
 
-	if (np) {
-		pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-		pdev->dev.platform_data = pdata;
-		ret = fsmc_nand_probe_config_dt(pdev, np);
-		if (ret) {
-			dev_err(&pdev->dev, "no platform data\n");
-			return -ENODEV;
-		}
-	}
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return -ENOMEM;
 
-	if (!pdata) {
-		dev_err(&pdev->dev, "platform data is NULL\n");
-		return -EINVAL;
+	pdev->dev.platform_data = pdata;
+	ret = fsmc_nand_probe_config_dt(pdev, np);
+	if (ret) {
+		dev_err(&pdev->dev, "no platform data\n");
+		return -ENODEV;
 	}
 
 	/* Allocate memory for the device structure (and zero it) */
diff --git a/drivers/mtd/nand/lpc32xx_slc.c b/drivers/mtd/nand/lpc32xx_slc.c
index 53bafe23ab39..a0669a33f8fe 100644
--- a/drivers/mtd/nand/lpc32xx_slc.c
+++ b/drivers/mtd/nand/lpc32xx_slc.c
@@ -797,22 +797,17 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	struct resource *rc;
 	int res;
 
-	rc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (rc == NULL) {
-		dev_err(&pdev->dev, "No memory resource found for device\n");
-		return -EBUSY;
-	}
-
 	/* Allocate memory for the device structure (and zero it) */
 	host = devm_kzalloc(&pdev->dev, sizeof(*host), GFP_KERNEL);
 	if (!host)
 		return -ENOMEM;
-	host->io_base_dma = rc->start;
 
+	rc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->io_base = devm_ioremap_resource(&pdev->dev, rc);
 	if (IS_ERR(host->io_base))
 		return PTR_ERR(host->io_base);
 
+	host->io_base_dma = rc->start;
 	if (pdev->dev.of_node)
 		host->ncfg = lpc32xx_parse_dt(&pdev->dev);
 	if (!host->ncfg) {
diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c
index 6c3eed3c2094..6c517c682939 100644
--- a/drivers/mtd/nand/mtk_nand.c
+++ b/drivers/mtd/nand/mtk_nand.c
@@ -1383,7 +1383,6 @@ static int mtk_nfc_probe(struct platform_device *pdev)
 	nfc->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(nfc->regs)) {
 		ret = PTR_ERR(nfc->regs);
-		dev_err(dev, "no nfi base\n");
 		goto release_ecc;
 	}
 
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index ec1c28aaaf23..1492c12906f6 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -3263,6 +3263,42 @@ static int nand_block_markbad(struct mtd_info *mtd, loff_t ofs)
 }
 
 /**
+ * nand_max_bad_blocks - [MTD Interface] Max number of bad blocks for an mtd
+ * @mtd: MTD device structure
+ * @ofs: offset relative to mtd start
+ * @len: length of mtd
+ */
+static int nand_max_bad_blocks(struct mtd_info *mtd, loff_t ofs, size_t len)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	u32 part_start_block;
+	u32 part_end_block;
+	u32 part_start_die;
+	u32 part_end_die;
+
+	/*
+	 * max_bb_per_die and blocks_per_die used to determine
+	 * the maximum bad block count.
+	 */
+	if (!chip->max_bb_per_die || !chip->blocks_per_die)
+		return -ENOTSUPP;
+
+	/* Get the start and end of the partition in erase blocks. */
+	part_start_block = mtd_div_by_eb(ofs, mtd);
+	part_end_block = mtd_div_by_eb(len, mtd) + part_start_block - 1;
+
+	/* Get the start and end LUNs of the partition. */
+	part_start_die = part_start_block / chip->blocks_per_die;
+	part_end_die = part_end_block / chip->blocks_per_die;
+
+	/*
+	 * Look up the bad blocks per unit and multiply by the number of units
+	 * that the partition spans.
+	 */
+	return chip->max_bb_per_die * (part_end_die - part_start_die + 1);
+}
+
+/**
  * nand_onfi_set_features- [REPLACEABLE] set features for ONFI nand
  * @mtd: MTD device structure
  * @chip: nand chip info structure
@@ -3592,6 +3628,9 @@ static int nand_flash_detect_onfi(struct mtd_info *mtd, struct nand_chip *chip,
 	chip->chipsize *= (uint64_t)mtd->erasesize * p->lun_count;
 	chip->bits_per_cell = p->bits_per_cell;
 
+	chip->max_bb_per_die = le16_to_cpu(p->bb_per_lun);
+	chip->blocks_per_die = le32_to_cpu(p->blocks_per_lun);
+
 	if (onfi_feature(chip) & ONFI_FEATURE_16_BIT_BUS)
 		*busw = NAND_BUSWIDTH_16;
 	else
@@ -4815,6 +4854,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 	mtd->_block_isreserved = nand_block_isreserved;
 	mtd->_block_isbad = nand_block_isbad;
 	mtd->_block_markbad = nand_block_markbad;
+	mtd->_max_bad_blocks = nand_max_bad_blocks;
 	mtd->writebufsize = mtd->writesize;
 
 	/*
diff --git a/drivers/mtd/nand/nand_ids.c b/drivers/mtd/nand/nand_ids.c
index b3a332f37e14..4a2f75b0c200 100644
--- a/drivers/mtd/nand/nand_ids.c
+++ b/drivers/mtd/nand/nand_ids.c
@@ -185,6 +185,7 @@ struct nand_manufacturers nand_manuf_ids[] = {
 	{NAND_MFR_SANDISK, "SanDisk"},
 	{NAND_MFR_INTEL, "Intel"},
 	{NAND_MFR_ATO, "ATO"},
+	{NAND_MFR_WINBOND, "Winbond"},
 	{0x0, "Unknown"}
 };
 
diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c
index e40482a65de6..0eeeb8b889ea 100644
--- a/drivers/mtd/nand/sunxi_nand.c
+++ b/drivers/mtd/nand/sunxi_nand.c
@@ -321,6 +321,10 @@ static int sunxi_nfc_wait_events(struct sunxi_nfc *nfc, u32 events,
 
 		ret = wait_for_completion_timeout(&nfc->complete,
 						msecs_to_jiffies(timeout_ms));
+		if (!ret)
+			ret = -ETIMEDOUT;
+		else
+			ret = 0;
 
 		writel(0, nfc->regs + NFC_REG_INT);
 	} else {
@@ -518,6 +522,8 @@ static void sunxi_nfc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	u32 tmp;
 
 	while (len > offs) {
+		bool poll = false;
+
 		cnt = min(len - offs, NFC_SRAM_SIZE);
 
 		ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
@@ -528,7 +534,11 @@ static void sunxi_nfc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 		tmp = NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD;
 		writel(tmp, nfc->regs + NFC_REG_CMD);
 
-		ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+		/* Arbitrary limit for polling mode */
+		if (cnt < 64)
+			poll = true;
+
+		ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, poll, 0);
 		if (ret)
 			break;
 
@@ -551,6 +561,8 @@ static void sunxi_nfc_write_buf(struct mtd_info *mtd, const uint8_t *buf,
 	u32 tmp;
 
 	while (len > offs) {
+		bool poll = false;
+
 		cnt = min(len - offs, NFC_SRAM_SIZE);
 
 		ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
@@ -563,7 +575,11 @@ static void sunxi_nfc_write_buf(struct mtd_info *mtd, const uint8_t *buf,
 		      NFC_ACCESS_DIR;
 		writel(tmp, nfc->regs + NFC_REG_CMD);
 
-		ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+		/* Arbitrary limit for polling mode */
+		if (cnt < 64)
+			poll = true;
+
+		ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, poll, 0);
 		if (ret)
 			break;
 
@@ -588,10 +604,6 @@ static void sunxi_nfc_cmd_ctrl(struct mtd_info *mtd, int dat,
 	struct sunxi_nfc *nfc = to_sunxi_nfc(sunxi_nand->nand.controller);
 	int ret;
 
-	ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
-	if (ret)
-		return;
-
 	if (dat == NAND_CMD_NONE && (ctrl & NAND_NCE) &&
 	    !(ctrl & (NAND_CLE | NAND_ALE))) {
 		u32 cmd = 0;
@@ -621,6 +633,10 @@ static void sunxi_nfc_cmd_ctrl(struct mtd_info *mtd, int dat,
 			writel(sunxi_nand->addr[1],
 			       nfc->regs + NFC_REG_ADDR_HIGH);
 
+		ret = sunxi_nfc_wait_cmd_fifo_empty(nfc);
+		if (ret)
+			return;
+
 		writel(cmd, nfc->regs + NFC_REG_CMD);
 		sunxi_nand->addr[0] = 0;
 		sunxi_nand->addr[1] = 0;
@@ -957,7 +973,7 @@ static int sunxi_nfc_hw_ecc_read_chunk(struct mtd_info *mtd,
 	writel(NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD | NFC_ECC_OP,
 	       nfc->regs + NFC_REG_CMD);
 
-	ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+	ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0);
 	sunxi_nfc_randomizer_disable(mtd);
 	if (ret)
 		return ret;
@@ -1069,7 +1085,7 @@ static int sunxi_nfc_hw_ecc_read_chunks_dma(struct mtd_info *mtd, uint8_t *buf,
 	writel(NFC_PAGE_OP | NFC_DATA_SWAP_METHOD | NFC_DATA_TRANS,
 	       nfc->regs + NFC_REG_CMD);
 
-	ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+	ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0);
 	if (ret)
 		dmaengine_terminate_all(nfc->dmac);
 
@@ -1189,7 +1205,7 @@ static int sunxi_nfc_hw_ecc_write_chunk(struct mtd_info *mtd,
 	       NFC_ACCESS_DIR | NFC_ECC_OP,
 	       nfc->regs + NFC_REG_CMD);
 
-	ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+	ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0);
 	sunxi_nfc_randomizer_disable(mtd);
 	if (ret)
 		return ret;
@@ -1428,7 +1444,7 @@ static int sunxi_nfc_hw_ecc_write_page_dma(struct mtd_info *mtd,
 	       NFC_DATA_TRANS | NFC_ACCESS_DIR,
 	       nfc->regs + NFC_REG_CMD);
 
-	ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, true, 0);
+	ret = sunxi_nfc_wait_events(nfc, NFC_CMD_INT_FLAG, false, 0);
 	if (ret)
 		dmaengine_terminate_all(nfc->dmac);
 
diff --git a/drivers/mtd/nand/xway_nand.c b/drivers/mtd/nand/xway_nand.c
index 895101a5e686..ddee4005248c 100644
--- a/drivers/mtd/nand/xway_nand.c
+++ b/drivers/mtd/nand/xway_nand.c
@@ -3,7 +3,7 @@
  *  under the terms of the GNU General Public License version 2 as published
  *  by the Free Software Foundation.
  *
- *  Copyright © 2012 John Crispin <blogic@openwrt.org>
+ *  Copyright © 2012 John Crispin <john@phrozen.org>
  *  Copyright © 2016 Hauke Mehrtens <hauke@hauke-m.de>
  */
 
diff --git a/drivers/mtd/ofpart.c b/drivers/mtd/ofpart.c
index ede407d6e106..464470122493 100644
--- a/drivers/mtd/ofpart.c
+++ b/drivers/mtd/ofpart.c
@@ -108,6 +108,7 @@ static int parse_ofpart_partitions(struct mtd_info *master,
 
 		parts[i].offset = of_read_number(reg, a_cells);
 		parts[i].size = of_read_number(reg + a_cells, s_cells);
+		parts[i].of_node = pp;
 
 		partname = of_get_property(pp, "label", &len);
 		if (!partname)
diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig
index 4a682ee0f632..7252087ef407 100644
--- a/drivers/mtd/spi-nor/Kconfig
+++ b/drivers/mtd/spi-nor/Kconfig
@@ -29,6 +29,16 @@ config MTD_SPI_NOR_USE_4K_SECTORS
 	  Please note that some tools/drivers/filesystems may not work with
 	  4096 B erase size (e.g. UBIFS requires 15 KiB as a minimum).
 
+config SPI_ASPEED_SMC
+	tristate "Aspeed flash controllers in SPI mode"
+	depends on ARCH_ASPEED || COMPILE_TEST
+	depends on HAS_IOMEM && OF
+	help
+	  This enables support for the Firmware Memory controller (FMC)
+	  in the Aspeed AST2500/AST2400 SoCs when attached to SPI NOR chips,
+	  and support for the SPI flash memory controller (SPI) for
+	  the host firmware. The implementation only supports SPI NOR.
+
 config SPI_ATMEL_QUADSPI
 	tristate "Atmel Quad SPI Controller"
 	depends on ARCH_AT91 || (ARM && COMPILE_TEST)
@@ -40,7 +50,7 @@ config SPI_ATMEL_QUADSPI
 
 config SPI_CADENCE_QUADSPI
 	tristate "Cadence Quad SPI controller"
-	depends on OF && ARM
+	depends on OF && (ARM || COMPILE_TEST)
 	help
 	  Enable support for the Cadence Quad SPI Flash controller.
 
@@ -76,4 +86,24 @@ config SPI_NXP_SPIFI
 	  Flash. Enable this option if you have a device with a SPIFI
 	  controller and want to access the Flash as a mtd device.
 
+config SPI_INTEL_SPI
+	tristate
+
+config SPI_INTEL_SPI_PLATFORM
+	tristate "Intel PCH/PCU SPI flash platform driver" if EXPERT
+	depends on X86
+	select SPI_INTEL_SPI
+	help
+	  This enables platform support for the Intel PCH/PCU SPI
+	  controller in master mode. This controller is present in modern
+	  Intel hardware and is used to hold BIOS and other persistent
+	  settings. Using this driver it is possible to upgrade BIOS
+	  directly from Linux.
+
+	  Say N here unless you know what you are doing. Overwriting the
+	  SPI flash may render the system unbootable.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called intel-spi-platform.
+
 endif # MTD_SPI_NOR
diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile
index 121695e83542..72238a793198 100644
--- a/drivers/mtd/spi-nor/Makefile
+++ b/drivers/mtd/spi-nor/Makefile
@@ -1,7 +1,10 @@
 obj-$(CONFIG_MTD_SPI_NOR)	+= spi-nor.o
+obj-$(CONFIG_SPI_ASPEED_SMC)	+= aspeed-smc.o
 obj-$(CONFIG_SPI_ATMEL_QUADSPI)	+= atmel-quadspi.o
 obj-$(CONFIG_SPI_CADENCE_QUADSPI)	+= cadence-quadspi.o
 obj-$(CONFIG_SPI_FSL_QUADSPI)	+= fsl-quadspi.o
 obj-$(CONFIG_SPI_HISI_SFC)	+= hisi-sfc.o
 obj-$(CONFIG_MTD_MT81xx_NOR)    += mtk-quadspi.o
 obj-$(CONFIG_SPI_NXP_SPIFI)	+= nxp-spifi.o
+obj-$(CONFIG_SPI_INTEL_SPI)	+= intel-spi.o
+obj-$(CONFIG_SPI_INTEL_SPI_PLATFORM)	+= intel-spi-platform.o
diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c
new file mode 100644
index 000000000000..56051d30f000
--- /dev/null
+++ b/drivers/mtd/spi-nor/aspeed-smc.c
@@ -0,0 +1,754 @@
+/*
+ * ASPEED Static Memory Controller driver
+ *
+ * Copyright (c) 2015-2016, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/bug.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/sysfs.h>
+
+#define DEVICE_NAME	"aspeed-smc"
+
+/*
+ * The driver only support SPI flash
+ */
+enum aspeed_smc_flash_type {
+	smc_type_nor  = 0,
+	smc_type_nand = 1,
+	smc_type_spi  = 2,
+};
+
+struct aspeed_smc_chip;
+
+struct aspeed_smc_info {
+	u32 maxsize;		/* maximum size of chip window */
+	u8 nce;			/* number of chip enables */
+	bool hastype;		/* flash type field exists in config reg */
+	u8 we0;			/* shift for write enable bit for CE0 */
+	u8 ctl0;		/* offset in regs of ctl for CE0 */
+
+	void (*set_4b)(struct aspeed_smc_chip *chip);
+};
+
+static void aspeed_smc_chip_set_4b_spi_2400(struct aspeed_smc_chip *chip);
+static void aspeed_smc_chip_set_4b(struct aspeed_smc_chip *chip);
+
+static const struct aspeed_smc_info fmc_2400_info = {
+	.maxsize = 64 * 1024 * 1024,
+	.nce = 5,
+	.hastype = true,
+	.we0 = 16,
+	.ctl0 = 0x10,
+	.set_4b = aspeed_smc_chip_set_4b,
+};
+
+static const struct aspeed_smc_info spi_2400_info = {
+	.maxsize = 64 * 1024 * 1024,
+	.nce = 1,
+	.hastype = false,
+	.we0 = 0,
+	.ctl0 = 0x04,
+	.set_4b = aspeed_smc_chip_set_4b_spi_2400,
+};
+
+static const struct aspeed_smc_info fmc_2500_info = {
+	.maxsize = 256 * 1024 * 1024,
+	.nce = 3,
+	.hastype = true,
+	.we0 = 16,
+	.ctl0 = 0x10,
+	.set_4b = aspeed_smc_chip_set_4b,
+};
+
+static const struct aspeed_smc_info spi_2500_info = {
+	.maxsize = 128 * 1024 * 1024,
+	.nce = 2,
+	.hastype = false,
+	.we0 = 16,
+	.ctl0 = 0x10,
+	.set_4b = aspeed_smc_chip_set_4b,
+};
+
+enum aspeed_smc_ctl_reg_value {
+	smc_base,		/* base value without mode for other commands */
+	smc_read,		/* command reg for (maybe fast) reads */
+	smc_write,		/* command reg for writes */
+	smc_max,
+};
+
+struct aspeed_smc_controller;
+
+struct aspeed_smc_chip {
+	int cs;
+	struct aspeed_smc_controller *controller;
+	void __iomem *ctl;			/* control register */
+	void __iomem *ahb_base;			/* base of chip window */
+	u32 ctl_val[smc_max];			/* control settings */
+	enum aspeed_smc_flash_type type;	/* what type of flash */
+	struct spi_nor nor;
+};
+
+struct aspeed_smc_controller {
+	struct device *dev;
+
+	struct mutex mutex;			/* controller access mutex */
+	const struct aspeed_smc_info *info;	/* type info of controller */
+	void __iomem *regs;			/* controller registers */
+	void __iomem *ahb_base;			/* per-chip windows resource */
+
+	struct aspeed_smc_chip *chips[0];	/* pointers to attached chips */
+};
+
+/*
+ * SPI Flash Configuration Register (AST2500 SPI)
+ *     or
+ * Type setting Register (AST2500 FMC).
+ * CE0 and CE1 can only be of type SPI. CE2 can be of type NOR but the
+ * driver does not support it.
+ */
+#define CONFIG_REG			0x0
+#define CONFIG_DISABLE_LEGACY		BIT(31) /* 1 */
+
+#define CONFIG_CE2_WRITE		BIT(18)
+#define CONFIG_CE1_WRITE		BIT(17)
+#define CONFIG_CE0_WRITE		BIT(16)
+
+#define CONFIG_CE2_TYPE			BIT(4) /* AST2500 FMC only */
+#define CONFIG_CE1_TYPE			BIT(2) /* AST2500 FMC only */
+#define CONFIG_CE0_TYPE			BIT(0) /* AST2500 FMC only */
+
+/*
+ * CE Control Register
+ */
+#define CE_CONTROL_REG			0x4
+
+/*
+ * CEx Control Register
+ */
+#define CONTROL_AAF_MODE		BIT(31)
+#define CONTROL_IO_MODE_MASK		GENMASK(30, 28)
+#define CONTROL_IO_DUAL_DATA		BIT(29)
+#define CONTROL_IO_DUAL_ADDR_DATA	(BIT(29) | BIT(28))
+#define CONTROL_IO_QUAD_DATA		BIT(30)
+#define CONTROL_IO_QUAD_ADDR_DATA	(BIT(30) | BIT(28))
+#define CONTROL_CE_INACTIVE_SHIFT	24
+#define CONTROL_CE_INACTIVE_MASK	GENMASK(27, \
+					CONTROL_CE_INACTIVE_SHIFT)
+/* 0 = 16T ... 15 = 1T   T=HCLK */
+#define CONTROL_COMMAND_SHIFT		16
+#define CONTROL_DUMMY_COMMAND_OUT	BIT(15)
+#define CONTROL_IO_DUMMY_HI		BIT(14)
+#define CONTROL_IO_DUMMY_HI_SHIFT	14
+#define CONTROL_CLK_DIV4		BIT(13) /* others */
+#define CONTROL_IO_ADDRESS_4B		BIT(13) /* AST2400 SPI */
+#define CONTROL_RW_MERGE		BIT(12)
+#define CONTROL_IO_DUMMY_LO_SHIFT	6
+#define CONTROL_IO_DUMMY_LO		GENMASK(7, \
+						CONTROL_IO_DUMMY_LO_SHIFT)
+#define CONTROL_IO_DUMMY_MASK		(CONTROL_IO_DUMMY_HI | \
+					 CONTROL_IO_DUMMY_LO)
+#define CONTROL_IO_DUMMY_SET(dummy)				 \
+	(((((dummy) >> 2) & 0x1) << CONTROL_IO_DUMMY_HI_SHIFT) | \
+	 (((dummy) & 0x3) << CONTROL_IO_DUMMY_LO_SHIFT))
+
+#define CONTROL_CLOCK_FREQ_SEL_SHIFT	8
+#define CONTROL_CLOCK_FREQ_SEL_MASK	GENMASK(11, \
+						CONTROL_CLOCK_FREQ_SEL_SHIFT)
+#define CONTROL_LSB_FIRST		BIT(5)
+#define CONTROL_CLOCK_MODE_3		BIT(4)
+#define CONTROL_IN_DUAL_DATA		BIT(3)
+#define CONTROL_CE_STOP_ACTIVE_CONTROL	BIT(2)
+#define CONTROL_COMMAND_MODE_MASK	GENMASK(1, 0)
+#define CONTROL_COMMAND_MODE_NORMAL	0
+#define CONTROL_COMMAND_MODE_FREAD	1
+#define CONTROL_COMMAND_MODE_WRITE	2
+#define CONTROL_COMMAND_MODE_USER	3
+
+#define CONTROL_KEEP_MASK						\
+	(CONTROL_AAF_MODE | CONTROL_CE_INACTIVE_MASK | CONTROL_CLK_DIV4 | \
+	 CONTROL_IO_DUMMY_MASK | CONTROL_CLOCK_FREQ_SEL_MASK |		\
+	 CONTROL_LSB_FIRST | CONTROL_CLOCK_MODE_3)
+
+/*
+ * The Segment Register uses a 8MB unit to encode the start address
+ * and the end address of the mapping window of a flash SPI slave :
+ *
+ *        | byte 1 | byte 2 | byte 3 | byte 4 |
+ *        +--------+--------+--------+--------+
+ *        |  end   |  start |   0    |   0    |
+ */
+#define SEGMENT_ADDR_REG0		0x30
+#define SEGMENT_ADDR_START(_r)		((((_r) >> 16) & 0xFF) << 23)
+#define SEGMENT_ADDR_END(_r)		((((_r) >> 24) & 0xFF) << 23)
+
+/*
+ * In user mode all data bytes read or written to the chip decode address
+ * range are transferred to or from the SPI bus. The range is treated as a
+ * fifo of arbitratry 1, 2, or 4 byte width but each write has to be aligned
+ * to its size. The address within the multiple 8kB range is ignored when
+ * sending bytes to the SPI bus.
+ *
+ * On the arm architecture, as of Linux version 4.3, memcpy_fromio and
+ * memcpy_toio on little endian targets use the optimized memcpy routines
+ * that were designed for well behavied memory storage. These routines
+ * have a stutter if the source and destination are not both word aligned,
+ * once with a duplicate access to the source after aligning to the
+ * destination to a word boundary, and again with a duplicate access to
+ * the source when the final byte count is not word aligned.
+ *
+ * When writing or reading the fifo this stutter discards data or sends
+ * too much data to the fifo and can not be used by this driver.
+ *
+ * While the low level io string routines that implement the insl family do
+ * the desired accesses and memory increments, the cross architecture io
+ * macros make them essentially impossible to use on a memory mapped address
+ * instead of a a token from the call to iomap of an io port.
+ *
+ * These fifo routines use readl and friends to a constant io port and update
+ * the memory buffer pointer and count via explicit code. The final updates
+ * to len are optimistically suppressed.
+ */
+static int aspeed_smc_read_from_ahb(void *buf, void __iomem *src, size_t len)
+{
+	size_t offset = 0;
+
+	if (IS_ALIGNED((uintptr_t)src, sizeof(uintptr_t)) &&
+	    IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) {
+		ioread32_rep(src, buf, len >> 2);
+		offset = len & ~0x3;
+		len -= offset;
+	}
+	ioread8_rep(src, (u8 *)buf + offset, len);
+	return 0;
+}
+
+static int aspeed_smc_write_to_ahb(void __iomem *dst, const void *buf,
+				   size_t len)
+{
+	size_t offset = 0;
+
+	if (IS_ALIGNED((uintptr_t)dst, sizeof(uintptr_t)) &&
+	    IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) {
+		iowrite32_rep(dst, buf, len >> 2);
+		offset = len & ~0x3;
+		len -= offset;
+	}
+	iowrite8_rep(dst, (const u8 *)buf + offset, len);
+	return 0;
+}
+
+static inline u32 aspeed_smc_chip_write_bit(struct aspeed_smc_chip *chip)
+{
+	return BIT(chip->controller->info->we0 + chip->cs);
+}
+
+static void aspeed_smc_chip_check_config(struct aspeed_smc_chip *chip)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 reg;
+
+	reg = readl(controller->regs + CONFIG_REG);
+
+	if (reg & aspeed_smc_chip_write_bit(chip))
+		return;
+
+	dev_dbg(controller->dev, "config write is not set ! @%p: 0x%08x\n",
+		controller->regs + CONFIG_REG, reg);
+	reg |= aspeed_smc_chip_write_bit(chip);
+	writel(reg, controller->regs + CONFIG_REG);
+}
+
+static void aspeed_smc_start_user(struct spi_nor *nor)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+	u32 ctl = chip->ctl_val[smc_base];
+
+	/*
+	 * When the chip is controlled in user mode, we need write
+	 * access to send the opcodes to it. So check the config.
+	 */
+	aspeed_smc_chip_check_config(chip);
+
+	ctl |= CONTROL_COMMAND_MODE_USER |
+		CONTROL_CE_STOP_ACTIVE_CONTROL;
+	writel(ctl, chip->ctl);
+
+	ctl &= ~CONTROL_CE_STOP_ACTIVE_CONTROL;
+	writel(ctl, chip->ctl);
+}
+
+static void aspeed_smc_stop_user(struct spi_nor *nor)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	u32 ctl = chip->ctl_val[smc_read];
+	u32 ctl2 = ctl | CONTROL_COMMAND_MODE_USER |
+		CONTROL_CE_STOP_ACTIVE_CONTROL;
+
+	writel(ctl2, chip->ctl);	/* stop user CE control */
+	writel(ctl, chip->ctl);		/* default to fread or read mode */
+}
+
+static int aspeed_smc_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	mutex_lock(&chip->controller->mutex);
+	return 0;
+}
+
+static void aspeed_smc_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	mutex_unlock(&chip->controller->mutex);
+}
+
+static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	aspeed_smc_start_user(nor);
+	aspeed_smc_write_to_ahb(chip->ahb_base, &opcode, 1);
+	aspeed_smc_read_from_ahb(buf, chip->ahb_base, len);
+	aspeed_smc_stop_user(nor);
+	return 0;
+}
+
+static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
+				int len)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	aspeed_smc_start_user(nor);
+	aspeed_smc_write_to_ahb(chip->ahb_base, &opcode, 1);
+	aspeed_smc_write_to_ahb(chip->ahb_base, buf, len);
+	aspeed_smc_stop_user(nor);
+	return 0;
+}
+
+static void aspeed_smc_send_cmd_addr(struct spi_nor *nor, u8 cmd, u32 addr)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+	__be32 temp;
+	u32 cmdaddr;
+
+	switch (nor->addr_width) {
+	default:
+		WARN_ONCE(1, "Unexpected address width %u, defaulting to 3\n",
+			  nor->addr_width);
+		/* FALLTHROUGH */
+	case 3:
+		cmdaddr = addr & 0xFFFFFF;
+		cmdaddr |= cmd << 24;
+
+		temp = cpu_to_be32(cmdaddr);
+		aspeed_smc_write_to_ahb(chip->ahb_base, &temp, 4);
+		break;
+	case 4:
+		temp = cpu_to_be32(addr);
+		aspeed_smc_write_to_ahb(chip->ahb_base, &cmd, 1);
+		aspeed_smc_write_to_ahb(chip->ahb_base, &temp, 4);
+		break;
+	}
+}
+
+static ssize_t aspeed_smc_read_user(struct spi_nor *nor, loff_t from,
+				    size_t len, u_char *read_buf)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+	int i;
+	u8 dummy = 0xFF;
+
+	aspeed_smc_start_user(nor);
+	aspeed_smc_send_cmd_addr(nor, nor->read_opcode, from);
+	for (i = 0; i < chip->nor.read_dummy / 8; i++)
+		aspeed_smc_write_to_ahb(chip->ahb_base, &dummy, sizeof(dummy));
+
+	aspeed_smc_read_from_ahb(read_buf, chip->ahb_base, len);
+	aspeed_smc_stop_user(nor);
+	return len;
+}
+
+static ssize_t aspeed_smc_write_user(struct spi_nor *nor, loff_t to,
+				     size_t len, const u_char *write_buf)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	aspeed_smc_start_user(nor);
+	aspeed_smc_send_cmd_addr(nor, nor->program_opcode, to);
+	aspeed_smc_write_to_ahb(chip->ahb_base, write_buf, len);
+	aspeed_smc_stop_user(nor);
+	return len;
+}
+
+static int aspeed_smc_unregister(struct aspeed_smc_controller *controller)
+{
+	struct aspeed_smc_chip *chip;
+	int n;
+
+	for (n = 0; n < controller->info->nce; n++) {
+		chip = controller->chips[n];
+		if (chip)
+			mtd_device_unregister(&chip->nor.mtd);
+	}
+
+	return 0;
+}
+
+static int aspeed_smc_remove(struct platform_device *dev)
+{
+	return aspeed_smc_unregister(platform_get_drvdata(dev));
+}
+
+static const struct of_device_id aspeed_smc_matches[] = {
+	{ .compatible = "aspeed,ast2400-fmc", .data = &fmc_2400_info },
+	{ .compatible = "aspeed,ast2400-spi", .data = &spi_2400_info },
+	{ .compatible = "aspeed,ast2500-fmc", .data = &fmc_2500_info },
+	{ .compatible = "aspeed,ast2500-spi", .data = &spi_2500_info },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, aspeed_smc_matches);
+
+/*
+ * Each chip has a mapping window defined by a segment address
+ * register defining a start and an end address on the AHB bus. These
+ * addresses can be configured to fit the chip size and offer a
+ * contiguous memory region across chips. For the moment, we only
+ * check that each chip segment is valid.
+ */
+static void __iomem *aspeed_smc_chip_base(struct aspeed_smc_chip *chip,
+					  struct resource *res)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 offset = 0;
+	u32 reg;
+
+	if (controller->info->nce > 1) {
+		reg = readl(controller->regs + SEGMENT_ADDR_REG0 +
+			    chip->cs * 4);
+
+		if (SEGMENT_ADDR_START(reg) >= SEGMENT_ADDR_END(reg))
+			return NULL;
+
+		offset = SEGMENT_ADDR_START(reg) - res->start;
+	}
+
+	return controller->ahb_base + offset;
+}
+
+static void aspeed_smc_chip_enable_write(struct aspeed_smc_chip *chip)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 reg;
+
+	reg = readl(controller->regs + CONFIG_REG);
+
+	reg |= aspeed_smc_chip_write_bit(chip);
+	writel(reg, controller->regs + CONFIG_REG);
+}
+
+static void aspeed_smc_chip_set_type(struct aspeed_smc_chip *chip, int type)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 reg;
+
+	chip->type = type;
+
+	reg = readl(controller->regs + CONFIG_REG);
+	reg &= ~(3 << (chip->cs * 2));
+	reg |= chip->type << (chip->cs * 2);
+	writel(reg, controller->regs + CONFIG_REG);
+}
+
+/*
+ * The AST2500 FMC flash controller should be strapped by hardware, or
+ * autodetected, but the AST2500 SPI flash needs to be set.
+ */
+static void aspeed_smc_chip_set_4b(struct aspeed_smc_chip *chip)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 reg;
+
+	if (chip->controller->info == &spi_2500_info) {
+		reg = readl(controller->regs + CE_CONTROL_REG);
+		reg |= 1 << chip->cs;
+		writel(reg, controller->regs + CE_CONTROL_REG);
+	}
+}
+
+/*
+ * The AST2400 SPI flash controller does not have a CE Control
+ * register. It uses the CE0 control register to set 4Byte mode at the
+ * controller level.
+ */
+static void aspeed_smc_chip_set_4b_spi_2400(struct aspeed_smc_chip *chip)
+{
+	chip->ctl_val[smc_base] |= CONTROL_IO_ADDRESS_4B;
+	chip->ctl_val[smc_read] |= CONTROL_IO_ADDRESS_4B;
+}
+
+static int aspeed_smc_chip_setup_init(struct aspeed_smc_chip *chip,
+				      struct resource *res)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	const struct aspeed_smc_info *info = controller->info;
+	u32 reg, base_reg;
+
+	/*
+	 * Always turn on the write enable bit to allow opcodes to be
+	 * sent in user mode.
+	 */
+	aspeed_smc_chip_enable_write(chip);
+
+	/* The driver only supports SPI type flash */
+	if (info->hastype)
+		aspeed_smc_chip_set_type(chip, smc_type_spi);
+
+	/*
+	 * Configure chip base address in memory
+	 */
+	chip->ahb_base = aspeed_smc_chip_base(chip, res);
+	if (!chip->ahb_base) {
+		dev_warn(chip->nor.dev, "CE segment window closed.\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Get value of the inherited control register. U-Boot usually
+	 * does some timing calibration on the FMC chip, so it's good
+	 * to keep them. In the future, we should handle calibration
+	 * from Linux.
+	 */
+	reg = readl(chip->ctl);
+	dev_dbg(controller->dev, "control register: %08x\n", reg);
+
+	base_reg = reg & CONTROL_KEEP_MASK;
+	if (base_reg != reg) {
+		dev_dbg(controller->dev,
+			"control register changed to: %08x\n",
+			base_reg);
+	}
+	chip->ctl_val[smc_base] = base_reg;
+
+	/*
+	 * Retain the prior value of the control register as the
+	 * default if it was normal access mode. Otherwise start with
+	 * the sanitized base value set to read mode.
+	 */
+	if ((reg & CONTROL_COMMAND_MODE_MASK) ==
+	    CONTROL_COMMAND_MODE_NORMAL)
+		chip->ctl_val[smc_read] = reg;
+	else
+		chip->ctl_val[smc_read] = chip->ctl_val[smc_base] |
+			CONTROL_COMMAND_MODE_NORMAL;
+
+	dev_dbg(controller->dev, "default control register: %08x\n",
+		chip->ctl_val[smc_read]);
+	return 0;
+}
+
+static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	const struct aspeed_smc_info *info = controller->info;
+	u32 cmd;
+
+	if (chip->nor.addr_width == 4 && info->set_4b)
+		info->set_4b(chip);
+
+	/*
+	 * base mode has not been optimized yet. use it for writes.
+	 */
+	chip->ctl_val[smc_write] = chip->ctl_val[smc_base] |
+		chip->nor.program_opcode << CONTROL_COMMAND_SHIFT |
+		CONTROL_COMMAND_MODE_WRITE;
+
+	dev_dbg(controller->dev, "write control register: %08x\n",
+		chip->ctl_val[smc_write]);
+
+	/*
+	 * TODO: Adjust clocks if fast read is supported and interpret
+	 * SPI-NOR flags to adjust controller settings.
+	 */
+	switch (chip->nor.flash_read) {
+	case SPI_NOR_NORMAL:
+		cmd = CONTROL_COMMAND_MODE_NORMAL;
+		break;
+	case SPI_NOR_FAST:
+		cmd = CONTROL_COMMAND_MODE_FREAD;
+		break;
+	default:
+		dev_err(chip->nor.dev, "unsupported SPI read mode\n");
+		return -EINVAL;
+	}
+
+	chip->ctl_val[smc_read] |= cmd |
+		CONTROL_IO_DUMMY_SET(chip->nor.read_dummy / 8);
+
+	dev_dbg(controller->dev, "base control register: %08x\n",
+		chip->ctl_val[smc_read]);
+	return 0;
+}
+
+static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
+				  struct device_node *np, struct resource *r)
+{
+	const struct aspeed_smc_info *info = controller->info;
+	struct device *dev = controller->dev;
+	struct device_node *child;
+	unsigned int cs;
+	int ret = -ENODEV;
+
+	for_each_available_child_of_node(np, child) {
+		struct aspeed_smc_chip *chip;
+		struct spi_nor *nor;
+		struct mtd_info *mtd;
+
+		/* This driver does not support NAND or NOR flash devices. */
+		if (!of_device_is_compatible(child, "jedec,spi-nor"))
+			continue;
+
+		ret = of_property_read_u32(child, "reg", &cs);
+		if (ret) {
+			dev_err(dev, "Couldn't not read chip select.\n");
+			break;
+		}
+
+		if (cs >= info->nce) {
+			dev_err(dev, "Chip select %d out of range.\n",
+				cs);
+			ret = -ERANGE;
+			break;
+		}
+
+		if (controller->chips[cs]) {
+			dev_err(dev, "Chip select %d already in use by %s\n",
+				cs, dev_name(controller->chips[cs]->nor.dev));
+			ret = -EBUSY;
+			break;
+		}
+
+		chip = devm_kzalloc(controller->dev, sizeof(*chip), GFP_KERNEL);
+		if (!chip) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		chip->controller = controller;
+		chip->ctl = controller->regs + info->ctl0 + cs * 4;
+		chip->cs = cs;
+
+		nor = &chip->nor;
+		mtd = &nor->mtd;
+
+		nor->dev = dev;
+		nor->priv = chip;
+		spi_nor_set_flash_node(nor, child);
+		nor->read = aspeed_smc_read_user;
+		nor->write = aspeed_smc_write_user;
+		nor->read_reg = aspeed_smc_read_reg;
+		nor->write_reg = aspeed_smc_write_reg;
+		nor->prepare = aspeed_smc_prep;
+		nor->unprepare = aspeed_smc_unprep;
+
+		ret = aspeed_smc_chip_setup_init(chip, r);
+		if (ret)
+			break;
+
+		/*
+		 * TODO: Add support for SPI_NOR_QUAD and SPI_NOR_DUAL
+		 * attach when board support is present as determined
+		 * by of property.
+		 */
+		ret = spi_nor_scan(nor, NULL, SPI_NOR_NORMAL);
+		if (ret)
+			break;
+
+		ret = aspeed_smc_chip_setup_finish(chip);
+		if (ret)
+			break;
+
+		ret = mtd_device_register(mtd, NULL, 0);
+		if (ret)
+			break;
+
+		controller->chips[cs] = chip;
+	}
+
+	if (ret)
+		aspeed_smc_unregister(controller);
+
+	return ret;
+}
+
+static int aspeed_smc_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct device *dev = &pdev->dev;
+	struct aspeed_smc_controller *controller;
+	const struct of_device_id *match;
+	const struct aspeed_smc_info *info;
+	struct resource *res;
+	int ret;
+
+	match = of_match_device(aspeed_smc_matches, &pdev->dev);
+	if (!match || !match->data)
+		return -ENODEV;
+	info = match->data;
+
+	controller = devm_kzalloc(&pdev->dev, sizeof(*controller) +
+		info->nce * sizeof(controller->chips[0]), GFP_KERNEL);
+	if (!controller)
+		return -ENOMEM;
+	controller->info = info;
+	controller->dev = dev;
+
+	mutex_init(&controller->mutex);
+	platform_set_drvdata(pdev, controller);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	controller->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(controller->regs))
+		return PTR_ERR(controller->regs);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	controller->ahb_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(controller->ahb_base))
+		return PTR_ERR(controller->ahb_base);
+
+	ret = aspeed_smc_setup_flash(controller, np, res);
+	if (ret)
+		dev_err(dev, "Aspeed SMC probe failed %d\n", ret);
+
+	return ret;
+}
+
+static struct platform_driver aspeed_smc_driver = {
+	.probe = aspeed_smc_probe,
+	.remove = aspeed_smc_remove,
+	.driver = {
+		.name = DEVICE_NAME,
+		.of_match_table = aspeed_smc_matches,
+	}
+};
+
+module_platform_driver(aspeed_smc_driver);
+
+MODULE_DESCRIPTION("ASPEED Static Memory Controller Driver");
+MODULE_AUTHOR("Cedric Le Goater <clg@kaod.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index d489fbd07c12..9f8102de1b16 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -526,7 +526,8 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor,
 			bytes_to_read *= cqspi->fifo_width;
 			bytes_to_read = bytes_to_read > remaining ?
 					remaining : bytes_to_read;
-			readsl(ahb_base, rxbuf, DIV_ROUND_UP(bytes_to_read, 4));
+			ioread32_rep(ahb_base, rxbuf,
+				     DIV_ROUND_UP(bytes_to_read, 4));
 			rxbuf += bytes_to_read;
 			remaining -= bytes_to_read;
 			bytes_to_read = cqspi_get_rd_sram_level(cqspi);
@@ -610,7 +611,8 @@ static int cqspi_indirect_write_execute(struct spi_nor *nor,
 
 	while (remaining > 0) {
 		write_bytes = remaining > page_size ? page_size : remaining;
-		writesl(cqspi->ahb_base, txbuf, DIV_ROUND_UP(write_bytes, 4));
+		iowrite32_rep(cqspi->ahb_base, txbuf,
+			      DIV_ROUND_UP(write_bytes, 4));
 
 		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
 						  msecs_to_jiffies
@@ -891,7 +893,7 @@ static ssize_t cqspi_write(struct spi_nor *nor, loff_t to,
 	if (ret)
 		return ret;
 
-	return (ret < 0) ? ret : len;
+	return len;
 }
 
 static ssize_t cqspi_read(struct spi_nor *nor, loff_t from,
@@ -911,7 +913,7 @@ static ssize_t cqspi_read(struct spi_nor *nor, loff_t from,
 	if (ret)
 		return ret;
 
-	return (ret < 0) ? ret : len;
+	return len;
 }
 
 static int cqspi_erase(struct spi_nor *nor, loff_t offs)
diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c
index b4d8953fb30a..1476135e0d50 100644
--- a/drivers/mtd/spi-nor/fsl-quadspi.c
+++ b/drivers/mtd/spi-nor/fsl-quadspi.c
@@ -193,7 +193,7 @@
 #define QUADSPI_LUT_NUM		64
 
 /* SEQID -- we can have 16 seqids at most. */
-#define SEQID_QUAD_READ		0
+#define SEQID_READ		0
 #define SEQID_WREN		1
 #define SEQID_WRDI		2
 #define SEQID_RDSR		3
@@ -373,32 +373,26 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q)
 	void __iomem *base = q->iobase;
 	int rxfifo = q->devtype_data->rxfifo;
 	u32 lut_base;
-	u8 cmd, addrlen, dummy;
 	int i;
 
+	struct spi_nor *nor = &q->nor[0];
+	u8 addrlen = (nor->addr_width == 3) ? ADDR24BIT : ADDR32BIT;
+	u8 read_op = nor->read_opcode;
+	u8 read_dm = nor->read_dummy;
+
 	fsl_qspi_unlock_lut(q);
 
 	/* Clear all the LUT table */
 	for (i = 0; i < QUADSPI_LUT_NUM; i++)
 		qspi_writel(q, 0, base + QUADSPI_LUT_BASE + i * 4);
 
-	/* Quad Read */
-	lut_base = SEQID_QUAD_READ * 4;
-
-	if (q->nor_size <= SZ_16M) {
-		cmd = SPINOR_OP_READ_1_1_4;
-		addrlen = ADDR24BIT;
-		dummy = 8;
-	} else {
-		/* use the 4-byte address */
-		cmd = SPINOR_OP_READ_1_1_4;
-		addrlen = ADDR32BIT;
-		dummy = 8;
-	}
+	/* Read */
+	lut_base = SEQID_READ * 4;
 
-	qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+	qspi_writel(q, LUT0(CMD, PAD1, read_op) | LUT1(ADDR, PAD1, addrlen),
 			base + QUADSPI_LUT(lut_base));
-	qspi_writel(q, LUT0(DUMMY, PAD1, dummy) | LUT1(FSL_READ, PAD4, rxfifo),
+	qspi_writel(q, LUT0(DUMMY, PAD1, read_dm) |
+		    LUT1(FSL_READ, PAD4, rxfifo),
 			base + QUADSPI_LUT(lut_base + 1));
 
 	/* Write enable */
@@ -409,16 +403,8 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q)
 	/* Page Program */
 	lut_base = SEQID_PP * 4;
 
-	if (q->nor_size <= SZ_16M) {
-		cmd = SPINOR_OP_PP;
-		addrlen = ADDR24BIT;
-	} else {
-		/* use the 4-byte address */
-		cmd = SPINOR_OP_PP;
-		addrlen = ADDR32BIT;
-	}
-
-	qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+	qspi_writel(q, LUT0(CMD, PAD1, nor->program_opcode) |
+		    LUT1(ADDR, PAD1, addrlen),
 			base + QUADSPI_LUT(lut_base));
 	qspi_writel(q, LUT0(FSL_WRITE, PAD1, 0),
 			base + QUADSPI_LUT(lut_base + 1));
@@ -432,10 +418,8 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q)
 	/* Erase a sector */
 	lut_base = SEQID_SE * 4;
 
-	cmd = q->nor[0].erase_opcode;
-	addrlen = q->nor_size <= SZ_16M ? ADDR24BIT : ADDR32BIT;
-
-	qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+	qspi_writel(q, LUT0(CMD, PAD1, nor->erase_opcode) |
+		    LUT1(ADDR, PAD1, addrlen),
 			base + QUADSPI_LUT(lut_base));
 
 	/* Erase the whole chip */
@@ -484,7 +468,7 @@ static int fsl_qspi_get_seqid(struct fsl_qspi *q, u8 cmd)
 {
 	switch (cmd) {
 	case SPINOR_OP_READ_1_1_4:
-		return SEQID_QUAD_READ;
+		return SEQID_READ;
 	case SPINOR_OP_WREN:
 		return SEQID_WREN;
 	case SPINOR_OP_WRDI:
diff --git a/drivers/mtd/spi-nor/intel-spi-platform.c b/drivers/mtd/spi-nor/intel-spi-platform.c
new file mode 100644
index 000000000000..5c943df9398f
--- /dev/null
+++ b/drivers/mtd/spi-nor/intel-spi-platform.c
@@ -0,0 +1,57 @@
+/*
+ * Intel PCH/PCU SPI flash platform driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "intel-spi.h"
+
+static int intel_spi_platform_probe(struct platform_device *pdev)
+{
+	struct intel_spi_boardinfo *info;
+	struct intel_spi *ispi;
+	struct resource *mem;
+
+	info = dev_get_platdata(&pdev->dev);
+	if (!info)
+		return -EINVAL;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ispi = intel_spi_probe(&pdev->dev, mem, info);
+	if (IS_ERR(ispi))
+		return PTR_ERR(ispi);
+
+	platform_set_drvdata(pdev, ispi);
+	return 0;
+}
+
+static int intel_spi_platform_remove(struct platform_device *pdev)
+{
+	struct intel_spi *ispi = platform_get_drvdata(pdev);
+
+	return intel_spi_remove(ispi);
+}
+
+static struct platform_driver intel_spi_platform_driver = {
+	.probe = intel_spi_platform_probe,
+	.remove = intel_spi_platform_remove,
+	.driver = {
+		.name = "intel-spi",
+	},
+};
+
+module_platform_driver(intel_spi_platform_driver);
+
+MODULE_DESCRIPTION("Intel PCH/PCU SPI flash platform driver");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:intel-spi");
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
new file mode 100644
index 000000000000..a10f6027b386
--- /dev/null
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -0,0 +1,777 @@
+/*
+ * Intel PCH/PCU SPI flash driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/sizes.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
+#include <linux/platform_data/intel-spi.h>
+
+#include "intel-spi.h"
+
+/* Offsets are from @ispi->base */
+#define BFPREG				0x00
+
+#define HSFSTS_CTL			0x04
+#define HSFSTS_CTL_FSMIE		BIT(31)
+#define HSFSTS_CTL_FDBC_SHIFT		24
+#define HSFSTS_CTL_FDBC_MASK		(0x3f << HSFSTS_CTL_FDBC_SHIFT)
+
+#define HSFSTS_CTL_FCYCLE_SHIFT		17
+#define HSFSTS_CTL_FCYCLE_MASK		(0x0f << HSFSTS_CTL_FCYCLE_SHIFT)
+/* HW sequencer opcodes */
+#define HSFSTS_CTL_FCYCLE_READ		(0x00 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_WRITE		(0x02 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_ERASE		(0x03 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_ERASE_64K	(0x04 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_RDID		(0x06 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_WRSR		(0x07 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_RDSR		(0x08 << HSFSTS_CTL_FCYCLE_SHIFT)
+
+#define HSFSTS_CTL_FGO			BIT(16)
+#define HSFSTS_CTL_FLOCKDN		BIT(15)
+#define HSFSTS_CTL_FDV			BIT(14)
+#define HSFSTS_CTL_SCIP			BIT(5)
+#define HSFSTS_CTL_AEL			BIT(2)
+#define HSFSTS_CTL_FCERR		BIT(1)
+#define HSFSTS_CTL_FDONE		BIT(0)
+
+#define FADDR				0x08
+#define DLOCK				0x0c
+#define FDATA(n)			(0x10 + ((n) * 4))
+
+#define FRACC				0x50
+
+#define FREG(n)				(0x54 + ((n) * 4))
+#define FREG_BASE_MASK			0x3fff
+#define FREG_LIMIT_SHIFT		16
+#define FREG_LIMIT_MASK			(0x03fff << FREG_LIMIT_SHIFT)
+
+/* Offset is from @ispi->pregs */
+#define PR(n)				((n) * 4)
+#define PR_WPE				BIT(31)
+#define PR_LIMIT_SHIFT			16
+#define PR_LIMIT_MASK			(0x3fff << PR_LIMIT_SHIFT)
+#define PR_RPE				BIT(15)
+#define PR_BASE_MASK			0x3fff
+/* Last PR is GPR0 */
+#define PR_NUM				(5 + 1)
+
+/* Offsets are from @ispi->sregs */
+#define SSFSTS_CTL			0x00
+#define SSFSTS_CTL_FSMIE		BIT(23)
+#define SSFSTS_CTL_DS			BIT(22)
+#define SSFSTS_CTL_DBC_SHIFT		16
+#define SSFSTS_CTL_SPOP			BIT(11)
+#define SSFSTS_CTL_ACS			BIT(10)
+#define SSFSTS_CTL_SCGO			BIT(9)
+#define SSFSTS_CTL_COP_SHIFT		12
+#define SSFSTS_CTL_FRS			BIT(7)
+#define SSFSTS_CTL_DOFRS		BIT(6)
+#define SSFSTS_CTL_AEL			BIT(4)
+#define SSFSTS_CTL_FCERR		BIT(3)
+#define SSFSTS_CTL_FDONE		BIT(2)
+#define SSFSTS_CTL_SCIP			BIT(0)
+
+#define PREOP_OPTYPE			0x04
+#define OPMENU0				0x08
+#define OPMENU1				0x0c
+
+/* CPU specifics */
+#define BYT_PR				0x74
+#define BYT_SSFSTS_CTL			0x90
+#define BYT_BCR				0xfc
+#define BYT_BCR_WPD			BIT(0)
+#define BYT_FREG_NUM			5
+
+#define LPT_PR				0x74
+#define LPT_SSFSTS_CTL			0x90
+#define LPT_FREG_NUM			5
+
+#define BXT_PR				0x84
+#define BXT_SSFSTS_CTL			0xa0
+#define BXT_FREG_NUM			12
+
+#define INTEL_SPI_TIMEOUT		5000 /* ms */
+#define INTEL_SPI_FIFO_SZ		64
+
+/**
+ * struct intel_spi - Driver private data
+ * @dev: Device pointer
+ * @info: Pointer to board specific info
+ * @nor: SPI NOR layer structure
+ * @base: Beginning of MMIO space
+ * @pregs: Start of protection registers
+ * @sregs: Start of software sequencer registers
+ * @nregions: Maximum number of regions
+ * @writeable: Is the chip writeable
+ * @swseq: Use SW sequencer in register reads/writes
+ * @erase_64k: 64k erase supported
+ * @opcodes: Opcodes which are supported. This are programmed by BIOS
+ *           before it locks down the controller.
+ * @preopcodes: Preopcodes which are supported.
+ */
+struct intel_spi {
+	struct device *dev;
+	const struct intel_spi_boardinfo *info;
+	struct spi_nor nor;
+	void __iomem *base;
+	void __iomem *pregs;
+	void __iomem *sregs;
+	size_t nregions;
+	bool writeable;
+	bool swseq;
+	bool erase_64k;
+	u8 opcodes[8];
+	u8 preopcodes[2];
+};
+
+static bool writeable;
+module_param(writeable, bool, 0);
+MODULE_PARM_DESC(writeable, "Enable write access to SPI flash chip (default=0)");
+
+static void intel_spi_dump_regs(struct intel_spi *ispi)
+{
+	u32 value;
+	int i;
+
+	dev_dbg(ispi->dev, "BFPREG=0x%08x\n", readl(ispi->base + BFPREG));
+
+	value = readl(ispi->base + HSFSTS_CTL);
+	dev_dbg(ispi->dev, "HSFSTS_CTL=0x%08x\n", value);
+	if (value & HSFSTS_CTL_FLOCKDN)
+		dev_dbg(ispi->dev, "-> Locked\n");
+
+	dev_dbg(ispi->dev, "FADDR=0x%08x\n", readl(ispi->base + FADDR));
+	dev_dbg(ispi->dev, "DLOCK=0x%08x\n", readl(ispi->base + DLOCK));
+
+	for (i = 0; i < 16; i++)
+		dev_dbg(ispi->dev, "FDATA(%d)=0x%08x\n",
+			i, readl(ispi->base + FDATA(i)));
+
+	dev_dbg(ispi->dev, "FRACC=0x%08x\n", readl(ispi->base + FRACC));
+
+	for (i = 0; i < ispi->nregions; i++)
+		dev_dbg(ispi->dev, "FREG(%d)=0x%08x\n", i,
+			readl(ispi->base + FREG(i)));
+	for (i = 0; i < PR_NUM; i++)
+		dev_dbg(ispi->dev, "PR(%d)=0x%08x\n", i,
+			readl(ispi->pregs + PR(i)));
+
+	value = readl(ispi->sregs + SSFSTS_CTL);
+	dev_dbg(ispi->dev, "SSFSTS_CTL=0x%08x\n", value);
+	dev_dbg(ispi->dev, "PREOP_OPTYPE=0x%08x\n",
+		readl(ispi->sregs + PREOP_OPTYPE));
+	dev_dbg(ispi->dev, "OPMENU0=0x%08x\n", readl(ispi->sregs + OPMENU0));
+	dev_dbg(ispi->dev, "OPMENU1=0x%08x\n", readl(ispi->sregs + OPMENU1));
+
+	if (ispi->info->type == INTEL_SPI_BYT)
+		dev_dbg(ispi->dev, "BCR=0x%08x\n", readl(ispi->base + BYT_BCR));
+
+	dev_dbg(ispi->dev, "Protected regions:\n");
+	for (i = 0; i < PR_NUM; i++) {
+		u32 base, limit;
+
+		value = readl(ispi->pregs + PR(i));
+		if (!(value & (PR_WPE | PR_RPE)))
+			continue;
+
+		limit = (value & PR_LIMIT_MASK) >> PR_LIMIT_SHIFT;
+		base = value & PR_BASE_MASK;
+
+		dev_dbg(ispi->dev, " %02d base: 0x%08x limit: 0x%08x [%c%c]\n",
+			 i, base << 12, (limit << 12) | 0xfff,
+			 value & PR_WPE ? 'W' : '.',
+			 value & PR_RPE ? 'R' : '.');
+	}
+
+	dev_dbg(ispi->dev, "Flash regions:\n");
+	for (i = 0; i < ispi->nregions; i++) {
+		u32 region, base, limit;
+
+		region = readl(ispi->base + FREG(i));
+		base = region & FREG_BASE_MASK;
+		limit = (region & FREG_LIMIT_MASK) >> FREG_LIMIT_SHIFT;
+
+		if (base >= limit || (i > 0 && limit == 0))
+			dev_dbg(ispi->dev, " %02d disabled\n", i);
+		else
+			dev_dbg(ispi->dev, " %02d base: 0x%08x limit: 0x%08x\n",
+				 i, base << 12, (limit << 12) | 0xfff);
+	}
+
+	dev_dbg(ispi->dev, "Using %cW sequencer for register access\n",
+		ispi->swseq ? 'S' : 'H');
+}
+
+/* Reads max INTEL_SPI_FIFO_SZ bytes from the device fifo */
+static int intel_spi_read_block(struct intel_spi *ispi, void *buf, size_t size)
+{
+	size_t bytes;
+	int i = 0;
+
+	if (size > INTEL_SPI_FIFO_SZ)
+		return -EINVAL;
+
+	while (size > 0) {
+		bytes = min_t(size_t, size, 4);
+		memcpy_fromio(buf, ispi->base + FDATA(i), bytes);
+		size -= bytes;
+		buf += bytes;
+		i++;
+	}
+
+	return 0;
+}
+
+/* Writes max INTEL_SPI_FIFO_SZ bytes to the device fifo */
+static int intel_spi_write_block(struct intel_spi *ispi, const void *buf,
+				 size_t size)
+{
+	size_t bytes;
+	int i = 0;
+
+	if (size > INTEL_SPI_FIFO_SZ)
+		return -EINVAL;
+
+	while (size > 0) {
+		bytes = min_t(size_t, size, 4);
+		memcpy_toio(ispi->base + FDATA(i), buf, bytes);
+		size -= bytes;
+		buf += bytes;
+		i++;
+	}
+
+	return 0;
+}
+
+static int intel_spi_wait_hw_busy(struct intel_spi *ispi)
+{
+	u32 val;
+
+	return readl_poll_timeout(ispi->base + HSFSTS_CTL, val,
+				  !(val & HSFSTS_CTL_SCIP), 0,
+				  INTEL_SPI_TIMEOUT * 1000);
+}
+
+static int intel_spi_wait_sw_busy(struct intel_spi *ispi)
+{
+	u32 val;
+
+	return readl_poll_timeout(ispi->sregs + SSFSTS_CTL, val,
+				  !(val & SSFSTS_CTL_SCIP), 0,
+				  INTEL_SPI_TIMEOUT * 1000);
+}
+
+static int intel_spi_init(struct intel_spi *ispi)
+{
+	u32 opmenu0, opmenu1, val;
+	int i;
+
+	switch (ispi->info->type) {
+	case INTEL_SPI_BYT:
+		ispi->sregs = ispi->base + BYT_SSFSTS_CTL;
+		ispi->pregs = ispi->base + BYT_PR;
+		ispi->nregions = BYT_FREG_NUM;
+
+		if (writeable) {
+			/* Disable write protection */
+			val = readl(ispi->base + BYT_BCR);
+			if (!(val & BYT_BCR_WPD)) {
+				val |= BYT_BCR_WPD;
+				writel(val, ispi->base + BYT_BCR);
+				val = readl(ispi->base + BYT_BCR);
+			}
+
+			ispi->writeable = !!(val & BYT_BCR_WPD);
+		}
+
+		break;
+
+	case INTEL_SPI_LPT:
+		ispi->sregs = ispi->base + LPT_SSFSTS_CTL;
+		ispi->pregs = ispi->base + LPT_PR;
+		ispi->nregions = LPT_FREG_NUM;
+		break;
+
+	case INTEL_SPI_BXT:
+		ispi->sregs = ispi->base + BXT_SSFSTS_CTL;
+		ispi->pregs = ispi->base + BXT_PR;
+		ispi->nregions = BXT_FREG_NUM;
+		ispi->erase_64k = true;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	/* Disable #SMI generation */
+	val = readl(ispi->base + HSFSTS_CTL);
+	val &= ~HSFSTS_CTL_FSMIE;
+	writel(val, ispi->base + HSFSTS_CTL);
+
+	/*
+	 * BIOS programs allowed opcodes and then locks down the register.
+	 * So read back what opcodes it decided to support. That's the set
+	 * we are going to support as well.
+	 */
+	opmenu0 = readl(ispi->sregs + OPMENU0);
+	opmenu1 = readl(ispi->sregs + OPMENU1);
+
+	/*
+	 * Some controllers can only do basic operations using hardware
+	 * sequencer. All other operations are supposed to be carried out
+	 * using software sequencer. If we find that BIOS has programmed
+	 * opcodes for the software sequencer we use that over the hardware
+	 * sequencer.
+	 */
+	if (opmenu0 && opmenu1) {
+		for (i = 0; i < ARRAY_SIZE(ispi->opcodes) / 2; i++) {
+			ispi->opcodes[i] = opmenu0 >> i * 8;
+			ispi->opcodes[i + 4] = opmenu1 >> i * 8;
+		}
+
+		val = readl(ispi->sregs + PREOP_OPTYPE);
+		ispi->preopcodes[0] = val;
+		ispi->preopcodes[1] = val >> 8;
+
+		/* Disable #SMI generation from SW sequencer */
+		val = readl(ispi->sregs + SSFSTS_CTL);
+		val &= ~SSFSTS_CTL_FSMIE;
+		writel(val, ispi->sregs + SSFSTS_CTL);
+
+		ispi->swseq = true;
+	}
+
+	intel_spi_dump_regs(ispi);
+
+	return 0;
+}
+
+static int intel_spi_opcode_index(struct intel_spi *ispi, u8 opcode)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ispi->opcodes); i++)
+		if (ispi->opcodes[i] == opcode)
+			return i;
+	return -EINVAL;
+}
+
+static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf,
+			      int len)
+{
+	u32 val, status;
+	int ret;
+
+	val = readl(ispi->base + HSFSTS_CTL);
+	val &= ~(HSFSTS_CTL_FCYCLE_MASK | HSFSTS_CTL_FDBC_MASK);
+
+	switch (opcode) {
+	case SPINOR_OP_RDID:
+		val |= HSFSTS_CTL_FCYCLE_RDID;
+		break;
+	case SPINOR_OP_WRSR:
+		val |= HSFSTS_CTL_FCYCLE_WRSR;
+		break;
+	case SPINOR_OP_RDSR:
+		val |= HSFSTS_CTL_FCYCLE_RDSR;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	val |= (len - 1) << HSFSTS_CTL_FDBC_SHIFT;
+	val |= HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+	val |= HSFSTS_CTL_FGO;
+	writel(val, ispi->base + HSFSTS_CTL);
+
+	ret = intel_spi_wait_hw_busy(ispi);
+	if (ret)
+		return ret;
+
+	status = readl(ispi->base + HSFSTS_CTL);
+	if (status & HSFSTS_CTL_FCERR)
+		return -EIO;
+	else if (status & HSFSTS_CTL_AEL)
+		return -EACCES;
+
+	return 0;
+}
+
+static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf,
+			      int len)
+{
+	u32 val, status;
+	int ret;
+
+	ret = intel_spi_opcode_index(ispi, opcode);
+	if (ret < 0)
+		return ret;
+
+	val = (len << SSFSTS_CTL_DBC_SHIFT) | SSFSTS_CTL_DS;
+	val |= ret << SSFSTS_CTL_COP_SHIFT;
+	val |= SSFSTS_CTL_FCERR | SSFSTS_CTL_FDONE;
+	val |= SSFSTS_CTL_SCGO;
+	writel(val, ispi->sregs + SSFSTS_CTL);
+
+	ret = intel_spi_wait_sw_busy(ispi);
+	if (ret)
+		return ret;
+
+	status = readl(ispi->base + SSFSTS_CTL);
+	if (status & SSFSTS_CTL_FCERR)
+		return -EIO;
+	else if (status & SSFSTS_CTL_AEL)
+		return -EACCES;
+
+	return 0;
+}
+
+static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+	struct intel_spi *ispi = nor->priv;
+	int ret;
+
+	/* Address of the first chip */
+	writel(0, ispi->base + FADDR);
+
+	if (ispi->swseq)
+		ret = intel_spi_sw_cycle(ispi, opcode, buf, len);
+	else
+		ret = intel_spi_hw_cycle(ispi, opcode, buf, len);
+
+	if (ret)
+		return ret;
+
+	return intel_spi_read_block(ispi, buf, len);
+}
+
+static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+	struct intel_spi *ispi = nor->priv;
+	int ret;
+
+	/*
+	 * This is handled with atomic operation and preop code in Intel
+	 * controller so skip it here now.
+	 */
+	if (opcode == SPINOR_OP_WREN)
+		return 0;
+
+	writel(0, ispi->base + FADDR);
+
+	/* Write the value beforehand */
+	ret = intel_spi_write_block(ispi, buf, len);
+	if (ret)
+		return ret;
+
+	if (ispi->swseq)
+		return intel_spi_sw_cycle(ispi, opcode, buf, len);
+	return intel_spi_hw_cycle(ispi, opcode, buf, len);
+}
+
+static ssize_t intel_spi_read(struct spi_nor *nor, loff_t from, size_t len,
+			      u_char *read_buf)
+{
+	struct intel_spi *ispi = nor->priv;
+	size_t block_size, retlen = 0;
+	u32 val, status;
+	ssize_t ret;
+
+	switch (nor->read_opcode) {
+	case SPINOR_OP_READ:
+	case SPINOR_OP_READ_FAST:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	while (len > 0) {
+		block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ);
+
+		writel(from, ispi->base + FADDR);
+
+		val = readl(ispi->base + HSFSTS_CTL);
+		val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK);
+		val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+		val |= (block_size - 1) << HSFSTS_CTL_FDBC_SHIFT;
+		val |= HSFSTS_CTL_FCYCLE_READ;
+		val |= HSFSTS_CTL_FGO;
+		writel(val, ispi->base + HSFSTS_CTL);
+
+		ret = intel_spi_wait_hw_busy(ispi);
+		if (ret)
+			return ret;
+
+		status = readl(ispi->base + HSFSTS_CTL);
+		if (status & HSFSTS_CTL_FCERR)
+			ret = -EIO;
+		else if (status & HSFSTS_CTL_AEL)
+			ret = -EACCES;
+
+		if (ret < 0) {
+			dev_err(ispi->dev, "read error: %llx: %#x\n", from,
+				status);
+			return ret;
+		}
+
+		ret = intel_spi_read_block(ispi, read_buf, block_size);
+		if (ret)
+			return ret;
+
+		len -= block_size;
+		from += block_size;
+		retlen += block_size;
+		read_buf += block_size;
+	}
+
+	return retlen;
+}
+
+static ssize_t intel_spi_write(struct spi_nor *nor, loff_t to, size_t len,
+			       const u_char *write_buf)
+{
+	struct intel_spi *ispi = nor->priv;
+	size_t block_size, retlen = 0;
+	u32 val, status;
+	ssize_t ret;
+
+	while (len > 0) {
+		block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ);
+
+		writel(to, ispi->base + FADDR);
+
+		val = readl(ispi->base + HSFSTS_CTL);
+		val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK);
+		val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+		val |= (block_size - 1) << HSFSTS_CTL_FDBC_SHIFT;
+		val |= HSFSTS_CTL_FCYCLE_WRITE;
+
+		/* Write enable */
+		if (ispi->preopcodes[1] == SPINOR_OP_WREN)
+			val |= SSFSTS_CTL_SPOP;
+		val |= SSFSTS_CTL_ACS;
+		writel(val, ispi->base + HSFSTS_CTL);
+
+		ret = intel_spi_write_block(ispi, write_buf, block_size);
+		if (ret) {
+			dev_err(ispi->dev, "failed to write block\n");
+			return ret;
+		}
+
+		/* Start the write now */
+		val = readl(ispi->base + HSFSTS_CTL);
+		writel(val | HSFSTS_CTL_FGO, ispi->base + HSFSTS_CTL);
+
+		ret = intel_spi_wait_hw_busy(ispi);
+		if (ret) {
+			dev_err(ispi->dev, "timeout\n");
+			return ret;
+		}
+
+		status = readl(ispi->base + HSFSTS_CTL);
+		if (status & HSFSTS_CTL_FCERR)
+			ret = -EIO;
+		else if (status & HSFSTS_CTL_AEL)
+			ret = -EACCES;
+
+		if (ret < 0) {
+			dev_err(ispi->dev, "write error: %llx: %#x\n", to,
+				status);
+			return ret;
+		}
+
+		len -= block_size;
+		to += block_size;
+		retlen += block_size;
+		write_buf += block_size;
+	}
+
+	return retlen;
+}
+
+static int intel_spi_erase(struct spi_nor *nor, loff_t offs)
+{
+	size_t erase_size, len = nor->mtd.erasesize;
+	struct intel_spi *ispi = nor->priv;
+	u32 val, status, cmd;
+	int ret;
+
+	/* If the hardware can do 64k erase use that when possible */
+	if (len >= SZ_64K && ispi->erase_64k) {
+		cmd = HSFSTS_CTL_FCYCLE_ERASE_64K;
+		erase_size = SZ_64K;
+	} else {
+		cmd = HSFSTS_CTL_FCYCLE_ERASE;
+		erase_size = SZ_4K;
+	}
+
+	while (len > 0) {
+		writel(offs, ispi->base + FADDR);
+
+		val = readl(ispi->base + HSFSTS_CTL);
+		val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK);
+		val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+		val |= cmd;
+		val |= HSFSTS_CTL_FGO;
+		writel(val, ispi->base + HSFSTS_CTL);
+
+		ret = intel_spi_wait_hw_busy(ispi);
+		if (ret)
+			return ret;
+
+		status = readl(ispi->base + HSFSTS_CTL);
+		if (status & HSFSTS_CTL_FCERR)
+			return -EIO;
+		else if (status & HSFSTS_CTL_AEL)
+			return -EACCES;
+
+		offs += erase_size;
+		len -= erase_size;
+	}
+
+	return 0;
+}
+
+static bool intel_spi_is_protected(const struct intel_spi *ispi,
+				   unsigned int base, unsigned int limit)
+{
+	int i;
+
+	for (i = 0; i < PR_NUM; i++) {
+		u32 pr_base, pr_limit, pr_value;
+
+		pr_value = readl(ispi->pregs + PR(i));
+		if (!(pr_value & (PR_WPE | PR_RPE)))
+			continue;
+
+		pr_limit = (pr_value & PR_LIMIT_MASK) >> PR_LIMIT_SHIFT;
+		pr_base = pr_value & PR_BASE_MASK;
+
+		if (pr_base >= base && pr_limit <= limit)
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * There will be a single partition holding all enabled flash regions. We
+ * call this "BIOS".
+ */
+static void intel_spi_fill_partition(struct intel_spi *ispi,
+				     struct mtd_partition *part)
+{
+	u64 end;
+	int i;
+
+	memset(part, 0, sizeof(*part));
+
+	/* Start from the mandatory descriptor region */
+	part->size = 4096;
+	part->name = "BIOS";
+
+	/*
+	 * Now try to find where this partition ends based on the flash
+	 * region registers.
+	 */
+	for (i = 1; i < ispi->nregions; i++) {
+		u32 region, base, limit;
+
+		region = readl(ispi->base + FREG(i));
+		base = region & FREG_BASE_MASK;
+		limit = (region & FREG_LIMIT_MASK) >> FREG_LIMIT_SHIFT;
+
+		if (base >= limit || limit == 0)
+			continue;
+
+		/*
+		 * If any of the regions have protection bits set, make the
+		 * whole partition read-only to be on the safe side.
+		 */
+		if (intel_spi_is_protected(ispi, base, limit))
+			ispi->writeable = 0;
+
+		end = (limit << 12) + 4096;
+		if (end > part->size)
+			part->size = end;
+	}
+}
+
+struct intel_spi *intel_spi_probe(struct device *dev,
+	struct resource *mem, const struct intel_spi_boardinfo *info)
+{
+	struct mtd_partition part;
+	struct intel_spi *ispi;
+	int ret;
+
+	if (!info || !mem)
+		return ERR_PTR(-EINVAL);
+
+	ispi = devm_kzalloc(dev, sizeof(*ispi), GFP_KERNEL);
+	if (!ispi)
+		return ERR_PTR(-ENOMEM);
+
+	ispi->base = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(ispi->base))
+		return ispi->base;
+
+	ispi->dev = dev;
+	ispi->info = info;
+	ispi->writeable = info->writeable;
+
+	ret = intel_spi_init(ispi);
+	if (ret)
+		return ERR_PTR(ret);
+
+	ispi->nor.dev = ispi->dev;
+	ispi->nor.priv = ispi;
+	ispi->nor.read_reg = intel_spi_read_reg;
+	ispi->nor.write_reg = intel_spi_write_reg;
+	ispi->nor.read = intel_spi_read;
+	ispi->nor.write = intel_spi_write;
+	ispi->nor.erase = intel_spi_erase;
+
+	ret = spi_nor_scan(&ispi->nor, NULL, SPI_NOR_NORMAL);
+	if (ret) {
+		dev_info(dev, "failed to locate the chip\n");
+		return ERR_PTR(ret);
+	}
+
+	intel_spi_fill_partition(ispi, &part);
+
+	/* Prevent writes if not explicitly enabled */
+	if (!ispi->writeable || !writeable)
+		ispi->nor.mtd.flags &= ~MTD_WRITEABLE;
+
+	ret = mtd_device_parse_register(&ispi->nor.mtd, NULL, NULL, &part, 1);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return ispi;
+}
+EXPORT_SYMBOL_GPL(intel_spi_probe);
+
+int intel_spi_remove(struct intel_spi *ispi)
+{
+	return mtd_device_unregister(&ispi->nor.mtd);
+}
+EXPORT_SYMBOL_GPL(intel_spi_remove);
+
+MODULE_DESCRIPTION("Intel PCH/PCU SPI flash core driver");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/spi-nor/intel-spi.h b/drivers/mtd/spi-nor/intel-spi.h
new file mode 100644
index 000000000000..5ab7dc250050
--- /dev/null
+++ b/drivers/mtd/spi-nor/intel-spi.h
@@ -0,0 +1,24 @@
+/*
+ * Intel PCH/PCU SPI flash driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef INTEL_SPI_H
+#define INTEL_SPI_H
+
+#include <linux/platform_data/intel-spi.h>
+
+struct intel_spi;
+struct resource;
+
+struct intel_spi *intel_spi_probe(struct device *dev,
+	struct resource *mem, const struct intel_spi_boardinfo *info);
+int intel_spi_remove(struct intel_spi *ispi);
+
+#endif /* INTEL_SPI_H */
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index da7cd69d4857..1ae872bfc3ba 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -75,6 +75,16 @@ struct flash_info {
 					 * bit. Must be used with
 					 * SPI_NOR_HAS_LOCK.
 					 */
+#define	SPI_S3AN		BIT(10)	/*
+					 * Xilinx Spartan 3AN In-System Flash
+					 * (MFR cannot be used for probing
+					 * because it has the same value as
+					 * ATMEL flashes)
+					 */
+#define SPI_NOR_4B_OPCODES	BIT(11)	/*
+					 * Use dedicated 4byte address op codes
+					 * to support memory size above 128Mib.
+					 */
 };
 
 #define JEDEC_MFR(info)	((info)->id[0])
@@ -122,7 +132,7 @@ static int read_fsr(struct spi_nor *nor)
 /*
  * Read configuration register, returning its value in the
  * location. Return the configuration register value.
- * Returns negative if error occured.
+ * Returns negative if error occurred.
  */
 static int read_cr(struct spi_nor *nor)
 {
@@ -188,6 +198,78 @@ static inline struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd)
 	return mtd->priv;
 }
 
+
+static u8 spi_nor_convert_opcode(u8 opcode, const u8 table[][2], size_t size)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		if (table[i][0] == opcode)
+			return table[i][1];
+
+	/* No conversion found, keep input op code. */
+	return opcode;
+}
+
+static inline u8 spi_nor_convert_3to4_read(u8 opcode)
+{
+	static const u8 spi_nor_3to4_read[][2] = {
+		{ SPINOR_OP_READ,	SPINOR_OP_READ_4B },
+		{ SPINOR_OP_READ_FAST,	SPINOR_OP_READ_FAST_4B },
+		{ SPINOR_OP_READ_1_1_2,	SPINOR_OP_READ_1_1_2_4B },
+		{ SPINOR_OP_READ_1_2_2,	SPINOR_OP_READ_1_2_2_4B },
+		{ SPINOR_OP_READ_1_1_4,	SPINOR_OP_READ_1_1_4_4B },
+		{ SPINOR_OP_READ_1_4_4,	SPINOR_OP_READ_1_4_4_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_read,
+				      ARRAY_SIZE(spi_nor_3to4_read));
+}
+
+static inline u8 spi_nor_convert_3to4_program(u8 opcode)
+{
+	static const u8 spi_nor_3to4_program[][2] = {
+		{ SPINOR_OP_PP,		SPINOR_OP_PP_4B },
+		{ SPINOR_OP_PP_1_1_4,	SPINOR_OP_PP_1_1_4_4B },
+		{ SPINOR_OP_PP_1_4_4,	SPINOR_OP_PP_1_4_4_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_program,
+				      ARRAY_SIZE(spi_nor_3to4_program));
+}
+
+static inline u8 spi_nor_convert_3to4_erase(u8 opcode)
+{
+	static const u8 spi_nor_3to4_erase[][2] = {
+		{ SPINOR_OP_BE_4K,	SPINOR_OP_BE_4K_4B },
+		{ SPINOR_OP_BE_32K,	SPINOR_OP_BE_32K_4B },
+		{ SPINOR_OP_SE,		SPINOR_OP_SE_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_erase,
+				      ARRAY_SIZE(spi_nor_3to4_erase));
+}
+
+static void spi_nor_set_4byte_opcodes(struct spi_nor *nor,
+				      const struct flash_info *info)
+{
+	/* Do some manufacturer fixups first */
+	switch (JEDEC_MFR(info)) {
+	case SNOR_MFR_SPANSION:
+		/* No small sector erase for 4-byte command set */
+		nor->erase_opcode = SPINOR_OP_SE;
+		nor->mtd.erasesize = info->sector_size;
+		break;
+
+	default:
+		break;
+	}
+
+	nor->read_opcode = spi_nor_convert_3to4_read(nor->read_opcode);
+	nor->program_opcode = spi_nor_convert_3to4_program(nor->program_opcode);
+	nor->erase_opcode = spi_nor_convert_3to4_erase(nor->erase_opcode);
+}
+
 /* Enable/disable 4-byte addressing mode. */
 static inline int set_4byte(struct spi_nor *nor, const struct flash_info *info,
 			    int enable)
@@ -217,6 +299,21 @@ static inline int set_4byte(struct spi_nor *nor, const struct flash_info *info,
 		return nor->write_reg(nor, SPINOR_OP_BRWR, nor->cmd_buf, 1);
 	}
 }
+
+static int s3an_sr_ready(struct spi_nor *nor)
+{
+	int ret;
+	u8 val;
+
+	ret = nor->read_reg(nor, SPINOR_OP_XRDSR, &val, 1);
+	if (ret < 0) {
+		dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret);
+		return ret;
+	}
+
+	return !!(val & XSR_RDY);
+}
+
 static inline int spi_nor_sr_ready(struct spi_nor *nor)
 {
 	int sr = read_sr(nor);
@@ -238,7 +335,11 @@ static inline int spi_nor_fsr_ready(struct spi_nor *nor)
 static int spi_nor_ready(struct spi_nor *nor)
 {
 	int sr, fsr;
-	sr = spi_nor_sr_ready(nor);
+
+	if (nor->flags & SNOR_F_READY_XSR_RDY)
+		sr = s3an_sr_ready(nor);
+	else
+		sr = spi_nor_sr_ready(nor);
 	if (sr < 0)
 		return sr;
 	fsr = nor->flags & SNOR_F_USE_FSR ? spi_nor_fsr_ready(nor) : 1;
@@ -320,6 +421,27 @@ static void spi_nor_unlock_and_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 }
 
 /*
+ * This code converts an address to the Default Address Mode, that has non
+ * power of two page sizes. We must support this mode because it is the default
+ * mode supported by Xilinx tools, it can access the whole flash area and
+ * changing over to the Power-of-two mode is irreversible and corrupts the
+ * original data.
+ * Addr can safely be unsigned int, the biggest S3AN device is smaller than
+ * 4 MiB.
+ */
+static loff_t spi_nor_s3an_addr_convert(struct spi_nor *nor, unsigned int addr)
+{
+	unsigned int offset;
+	unsigned int page;
+
+	offset = addr % nor->page_size;
+	page = addr / nor->page_size;
+	page <<= (nor->page_size > 512) ? 10 : 9;
+
+	return page | offset;
+}
+
+/*
  * Initiate the erasure of a single sector
  */
 static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
@@ -327,6 +449,9 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
 	u8 buf[SPI_NOR_MAX_ADDR_WIDTH];
 	int i;
 
+	if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT)
+		addr = spi_nor_s3an_addr_convert(nor, addr);
+
 	if (nor->erase)
 		return nor->erase(nor, addr);
 
@@ -368,7 +493,7 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 		return ret;
 
 	/* whole-chip erase? */
-	if (len == mtd->size) {
+	if (len == mtd->size && !(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) {
 		unsigned long timeout;
 
 		write_enable(nor);
@@ -782,6 +907,19 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 		.addr_width = (_addr_width),				\
 		.flags = (_flags),
 
+#define S3AN_INFO(_jedec_id, _n_sectors, _page_size)			\
+		.id = {							\
+			((_jedec_id) >> 16) & 0xff,			\
+			((_jedec_id) >> 8) & 0xff,			\
+			(_jedec_id) & 0xff				\
+			},						\
+		.id_len = 3,						\
+		.sector_size = (8*_page_size),				\
+		.n_sectors = (_n_sectors),				\
+		.page_size = _page_size,				\
+		.addr_width = 3,					\
+		.flags = SPI_NOR_NO_FR | SPI_S3AN,
+
 /* NOTE: double check command sets and memory organization when you add
  * more nor chips.  This current list focusses on newer chips, which
  * have been converging on command sets which including JEDEC ID.
@@ -821,7 +959,7 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "en25s64",	INFO(0x1c3817, 0, 64 * 1024,  128, SECT_4K) },
 
 	/* ESMT */
-	{ "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K) },
+	{ "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K | SPI_NOR_HAS_LOCK) },
 
 	/* Everspin */
 	{ "mr25h256", CAT25_INFO( 32 * 1024, 1, 256, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
@@ -833,6 +971,11 @@ static const struct flash_info spi_nor_ids[] = {
 
 	/* GigaDevice */
 	{
+		"gd25q16", INFO(0xc84015, 0, 64 * 1024,  32,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
+	{
 		"gd25q32", INFO(0xc84016, 0, 64 * 1024,  64,
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
 			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
@@ -1014,6 +1157,13 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "cat25c09", CAT25_INFO( 128, 8, 32, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
 	{ "cat25c17", CAT25_INFO( 256, 8, 32, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
 	{ "cat25128", CAT25_INFO(2048, 8, 64, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
+
+	/* Xilinx S3AN Internal Flash */
+	{ "3S50AN", S3AN_INFO(0x1f2200, 64, 264) },
+	{ "3S200AN", S3AN_INFO(0x1f2400, 256, 264) },
+	{ "3S400AN", S3AN_INFO(0x1f2400, 256, 264) },
+	{ "3S700AN", S3AN_INFO(0x1f2500, 512, 264) },
+	{ "3S1400AN", S3AN_INFO(0x1f2600, 512, 528) },
 	{ },
 };
 
@@ -1054,7 +1204,12 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len,
 		return ret;
 
 	while (len) {
-		ret = nor->read(nor, from, len, buf);
+		loff_t addr = from;
+
+		if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT)
+			addr = spi_nor_s3an_addr_convert(nor, addr);
+
+		ret = nor->read(nor, addr, len, buf);
 		if (ret == 0) {
 			/* We shouldn't see 0-length reads */
 			ret = -EIO;
@@ -1175,17 +1330,32 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 	for (i = 0; i < len; ) {
 		ssize_t written;
+		loff_t addr = to + i;
+
+		/*
+		 * If page_size is a power of two, the offset can be quickly
+		 * calculated with an AND operation. On the other cases we
+		 * need to do a modulus operation (more expensive).
+		 * Power of two numbers have only one bit set and we can use
+		 * the instruction hweight32 to detect if we need to do a
+		 * modulus (do_div()) or not.
+		 */
+		if (hweight32(nor->page_size) == 1) {
+			page_offset = addr & (nor->page_size - 1);
+		} else {
+			uint64_t aux = addr;
 
-		page_offset = (to + i) & (nor->page_size - 1);
-		WARN_ONCE(page_offset,
-			  "Writing at offset %zu into a NOR page. Writing partial pages may decrease reliability and increase wear of NOR flash.",
-			  page_offset);
+			page_offset = do_div(aux, nor->page_size);
+		}
 		/* the size of data remaining on the first page */
 		page_remain = min_t(size_t,
 				    nor->page_size - page_offset, len - i);
 
+		if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT)
+			addr = spi_nor_s3an_addr_convert(nor, addr);
+
 		write_enable(nor);
-		ret = nor->write(nor, to + i, page_remain, buf + i);
+		ret = nor->write(nor, addr, page_remain, buf + i);
 		if (ret < 0)
 			goto write_err;
 		written = ret;
@@ -1216,6 +1386,9 @@ static int macronix_quad_enable(struct spi_nor *nor)
 	val = read_sr(nor);
 	if (val < 0)
 		return val;
+	if (val & SR_QUAD_EN_MX)
+		return 0;
+
 	write_enable(nor);
 
 	write_sr(nor, val | SR_QUAD_EN_MX);
@@ -1236,7 +1409,7 @@ static int macronix_quad_enable(struct spi_nor *nor)
  * Write status Register and configuration register with 2 bytes
  * The first byte will be written to the status register, while the
  * second byte will be written to the configuration register.
- * Return negative if error occured.
+ * Return negative if error occurred.
  */
 static int write_sr_cr(struct spi_nor *nor, u16 val)
 {
@@ -1312,6 +1485,47 @@ static int spi_nor_check(struct spi_nor *nor)
 	return 0;
 }
 
+static int s3an_nor_scan(const struct flash_info *info, struct spi_nor *nor)
+{
+	int ret;
+	u8 val;
+
+	ret = nor->read_reg(nor, SPINOR_OP_XRDSR, &val, 1);
+	if (ret < 0) {
+		dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret);
+		return ret;
+	}
+
+	nor->erase_opcode = SPINOR_OP_XSE;
+	nor->program_opcode = SPINOR_OP_XPP;
+	nor->read_opcode = SPINOR_OP_READ;
+	nor->flags |= SNOR_F_NO_OP_CHIP_ERASE;
+
+	/*
+	 * This flashes have a page size of 264 or 528 bytes (known as
+	 * Default addressing mode). It can be changed to a more standard
+	 * Power of two mode where the page size is 256/512. This comes
+	 * with a price: there is 3% less of space, the data is corrupted
+	 * and the page size cannot be changed back to default addressing
+	 * mode.
+	 *
+	 * The current addressing mode can be read from the XRDSR register
+	 * and should not be changed, because is a destructive operation.
+	 */
+	if (val & XSR_PAGESIZE) {
+		/* Flash in Power of 2 mode */
+		nor->page_size = (nor->page_size == 264) ? 256 : 512;
+		nor->mtd.writebufsize = nor->page_size;
+		nor->mtd.size = 8 * nor->page_size * info->n_sectors;
+		nor->mtd.erasesize = 8 * nor->page_size;
+	} else {
+		/* Flash in Default addressing mode */
+		nor->flags |= SNOR_F_S3AN_ADDR_DEFAULT;
+	}
+
+	return 0;
+}
+
 int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 {
 	const struct flash_info *info = NULL;
@@ -1360,6 +1574,14 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	mutex_init(&nor->lock);
 
 	/*
+	 * Make sure the XSR_RDY flag is set before calling
+	 * spi_nor_wait_till_ready(). Xilinx S3AN share MFR
+	 * with Atmel spi-nor
+	 */
+	if (info->flags & SPI_S3AN)
+		nor->flags |=  SNOR_F_READY_XSR_RDY;
+
+	/*
 	 * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up
 	 * with the software protection bits set
 	 */
@@ -1483,27 +1705,10 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	else if (mtd->size > 0x1000000) {
 		/* enable 4-byte addressing if the device exceeds 16MiB */
 		nor->addr_width = 4;
-		if (JEDEC_MFR(info) == SNOR_MFR_SPANSION) {
-			/* Dedicated 4-byte command set */
-			switch (nor->flash_read) {
-			case SPI_NOR_QUAD:
-				nor->read_opcode = SPINOR_OP_READ4_1_1_4;
-				break;
-			case SPI_NOR_DUAL:
-				nor->read_opcode = SPINOR_OP_READ4_1_1_2;
-				break;
-			case SPI_NOR_FAST:
-				nor->read_opcode = SPINOR_OP_READ4_FAST;
-				break;
-			case SPI_NOR_NORMAL:
-				nor->read_opcode = SPINOR_OP_READ4;
-				break;
-			}
-			nor->program_opcode = SPINOR_OP_PP_4B;
-			/* No small sector erase for 4-byte command set */
-			nor->erase_opcode = SPINOR_OP_SE_4B;
-			mtd->erasesize = info->sector_size;
-		} else
+		if (JEDEC_MFR(info) == SNOR_MFR_SPANSION ||
+		    info->flags & SPI_NOR_4B_OPCODES)
+			spi_nor_set_4byte_opcodes(nor, info);
+		else
 			set_4byte(nor, info, 1);
 	} else {
 		nor->addr_width = 3;
@@ -1517,6 +1722,12 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 
 	nor->read_dummy = spi_nor_read_dummy_cycles(nor);
 
+	if (info->flags & SPI_S3AN) {
+		ret = s3an_nor_scan(info, nor);
+		if (ret)
+			return ret;
+	}
+
 	dev_info(dev, "%s (%lld Kbytes)\n", info->name,
 			(long long)mtd->size >> 10);
 
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index d1e6931c132f..c80869e60909 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -323,16 +323,15 @@ static int ubiblock_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct ubiblock *dev = hctx->queue->queuedata;
 	struct ubiblock_pdu *pdu = blk_mq_rq_to_pdu(req);
 
-	if (req->cmd_type != REQ_TYPE_FS)
+	switch (req_op(req)) {
+	case REQ_OP_READ:
+		ubi_sgl_init(&pdu->usgl);
+		queue_work(dev->wq, &pdu->work);
+		return BLK_MQ_RQ_QUEUE_OK;
+	default:
 		return BLK_MQ_RQ_QUEUE_ERROR;
+	}
 
-	if (rq_data_dir(req) != READ)
-		return BLK_MQ_RQ_QUEUE_ERROR; /* Write not implemented */
-
-	ubi_sgl_init(&pdu->usgl);
-	queue_work(dev->wq, &pdu->work);
-
-	return BLK_MQ_RQ_QUEUE_OK;
 }
 
 static int ubiblock_init_request(void *data, struct request *req,
diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c
index 7be393c96b1a..cf7c18947189 100644
--- a/drivers/net/can/c_can/c_can_pci.c
+++ b/drivers/net/can/c_can/c_can_pci.c
@@ -161,6 +161,7 @@ static int c_can_pci_probe(struct pci_dev *pdev,
 
 	dev->irq = pdev->irq;
 	priv->base = addr;
+	priv->device = &pdev->dev;
 
 	if (!c_can_pci_data->freq) {
 		dev_err(&pdev->dev, "no clock frequency defined\n");
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 680d1ff07a55..6749b1829469 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -948,7 +948,12 @@ static int ti_hecc_probe(struct platform_device *pdev)
 	netif_napi_add(ndev, &priv->napi, ti_hecc_rx_poll,
 		HECC_DEF_NAPI_WEIGHT);
 
-	clk_enable(priv->clk);
+	err = clk_prepare_enable(priv->clk);
+	if (err) {
+		dev_err(&pdev->dev, "clk_prepare_enable() failed\n");
+		goto probe_exit_clk;
+	}
+
 	err = register_candev(ndev);
 	if (err) {
 		dev_err(&pdev->dev, "register_candev() failed\n");
@@ -981,7 +986,7 @@ static int ti_hecc_remove(struct platform_device *pdev)
 	struct ti_hecc_priv *priv = netdev_priv(ndev);
 
 	unregister_candev(ndev);
-	clk_disable(priv->clk);
+	clk_disable_unprepare(priv->clk);
 	clk_put(priv->clk);
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	iounmap(priv->base);
@@ -1006,7 +1011,7 @@ static int ti_hecc_suspend(struct platform_device *pdev, pm_message_t state)
 	hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_PDR);
 	priv->can.state = CAN_STATE_SLEEPING;
 
-	clk_disable(priv->clk);
+	clk_disable_unprepare(priv->clk);
 
 	return 0;
 }
@@ -1015,8 +1020,11 @@ static int ti_hecc_resume(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
 	struct ti_hecc_priv *priv = netdev_priv(dev);
+	int err;
 
-	clk_enable(priv->clk);
+	err = clk_prepare_enable(priv->clk);
+	if (err)
+		return err;
 
 	hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_PDR);
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index c12d2618eebf..3872ab96b80a 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -1152,6 +1152,12 @@ static void init_ring(struct net_device *dev)
 		if (skb == NULL)
 			break;
 		np->rx_info[i].mapping = pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE);
+		if (pci_dma_mapping_error(np->pci_dev,
+					  np->rx_info[i].mapping)) {
+			dev_kfree_skb(skb);
+			np->rx_info[i].skb = NULL;
+			break;
+		}
 		/* Grrr, we cannot offset to correctly align the IP header. */
 		np->rx_ring[i].rxaddr = cpu_to_dma(np->rx_info[i].mapping | RxDescValid);
 	}
@@ -1182,8 +1188,9 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
 {
 	struct netdev_private *np = netdev_priv(dev);
 	unsigned int entry;
+	unsigned int prev_tx;
 	u32 status;
-	int i;
+	int i, j;
 
 	/*
 	 * be cautious here, wrapping the queue has weird semantics
@@ -1201,6 +1208,7 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
 	}
 #endif /* ZEROCOPY && HAS_BROKEN_FIRMWARE */
 
+	prev_tx = np->cur_tx;
 	entry = np->cur_tx % TX_RING_SIZE;
 	for (i = 0; i < skb_num_frags(skb); i++) {
 		int wrap_ring = 0;
@@ -1234,6 +1242,11 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
 					       skb_frag_size(this_frag),
 					       PCI_DMA_TODEVICE);
 		}
+		if (pci_dma_mapping_error(np->pci_dev,
+					  np->tx_info[entry].mapping)) {
+			dev->stats.tx_dropped++;
+			goto err_out;
+		}
 
 		np->tx_ring[entry].addr = cpu_to_dma(np->tx_info[entry].mapping);
 		np->tx_ring[entry].status = cpu_to_le32(status);
@@ -1268,8 +1281,30 @@ static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev)
 		netif_stop_queue(dev);
 
 	return NETDEV_TX_OK;
-}
 
+err_out:
+	entry = prev_tx % TX_RING_SIZE;
+	np->tx_info[entry].skb = NULL;
+	if (i > 0) {
+		pci_unmap_single(np->pci_dev,
+				 np->tx_info[entry].mapping,
+				 skb_first_frag_len(skb),
+				 PCI_DMA_TODEVICE);
+		np->tx_info[entry].mapping = 0;
+		entry = (entry + np->tx_info[entry].used_slots) % TX_RING_SIZE;
+		for (j = 1; j < i; j++) {
+			pci_unmap_single(np->pci_dev,
+					 np->tx_info[entry].mapping,
+					 skb_frag_size(
+						&skb_shinfo(skb)->frags[j-1]),
+					 PCI_DMA_TODEVICE);
+			entry++;
+		}
+	}
+	dev_kfree_skb_any(skb);
+	np->cur_tx = prev_tx;
+	return NETDEV_TX_OK;
+}
 
 /* The interrupt handler does all of the Rx thread work and cleans up
    after the Tx thread. */
@@ -1569,6 +1604,12 @@ static void refill_rx_ring(struct net_device *dev)
 				break;	/* Better luck next round. */
 			np->rx_info[entry].mapping =
 				pci_map_single(np->pci_dev, skb->data, np->rx_buf_sz, PCI_DMA_FROMDEVICE);
+			if (pci_dma_mapping_error(np->pci_dev,
+						np->rx_info[entry].mapping)) {
+				dev_kfree_skb(skb);
+				np->rx_info[entry].skb = NULL;
+				break;
+			}
 			np->rx_ring[entry].rxaddr =
 				cpu_to_dma(np->rx_info[entry].mapping | RxDescValid);
 		}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index 5b7ba25e0065..8a280e7d66bd 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -891,6 +891,8 @@
 #define PCS_V1_WINDOW_SELECT		0x03fc
 #define PCS_V2_WINDOW_DEF		0x9060
 #define PCS_V2_WINDOW_SELECT		0x9064
+#define PCS_V2_RV_WINDOW_DEF		0x1060
+#define PCS_V2_RV_WINDOW_SELECT		0x1064
 
 /* PCS register entry bit positions and sizes */
 #define PCS_V2_WINDOW_DEF_OFFSET_INDEX	6
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index aaf0350076a9..a7d16db5c4b2 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1151,7 +1151,7 @@ static int xgbe_read_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
 	offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
 
 	spin_lock_irqsave(&pdata->xpcs_lock, flags);
-	XPCS32_IOWRITE(pdata, PCS_V2_WINDOW_SELECT, index);
+	XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index);
 	mmd_data = XPCS16_IOREAD(pdata, offset);
 	spin_unlock_irqrestore(&pdata->xpcs_lock, flags);
 
@@ -1183,7 +1183,7 @@ static void xgbe_write_mmd_regs_v2(struct xgbe_prv_data *pdata, int prtad,
 	offset = pdata->xpcs_window + (mmd_address & pdata->xpcs_window_mask);
 
 	spin_lock_irqsave(&pdata->xpcs_lock, flags);
-	XPCS32_IOWRITE(pdata, PCS_V2_WINDOW_SELECT, index);
+	XPCS32_IOWRITE(pdata, pdata->xpcs_window_sel_reg, index);
 	XPCS16_IOWRITE(pdata, offset, mmd_data);
 	spin_unlock_irqrestore(&pdata->xpcs_lock, flags);
 }
@@ -3407,8 +3407,10 @@ static int xgbe_init(struct xgbe_prv_data *pdata)
 
 	/* Flush Tx queues */
 	ret = xgbe_flush_tx_queues(pdata);
-	if (ret)
+	if (ret) {
+		netdev_err(pdata->netdev, "error flushing TX queues\n");
 		return ret;
+	}
 
 	/*
 	 * Initialize DMA related features
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 9943629fcbf9..1c87cc204075 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1070,7 +1070,9 @@ static int xgbe_start(struct xgbe_prv_data *pdata)
 
 	DBGPR("-->xgbe_start\n");
 
-	hw_if->init(pdata);
+	ret = hw_if->init(pdata);
+	if (ret)
+		return ret;
 
 	xgbe_napi_enable(pdata, 1);
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index e76b7f65b805..c2730f15bd8b 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -265,6 +265,7 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct xgbe_prv_data *pdata;
 	struct device *dev = &pdev->dev;
 	void __iomem * const *iomap_table;
+	struct pci_dev *rdev;
 	unsigned int ma_lo, ma_hi;
 	unsigned int reg;
 	int bar_mask;
@@ -326,8 +327,20 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (netif_msg_probe(pdata))
 		dev_dbg(dev, "xpcs_regs  = %p\n", pdata->xpcs_regs);
 
+	/* Set the PCS indirect addressing definition registers */
+	rdev = pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(0, 0));
+	if (rdev &&
+	    (rdev->vendor == PCI_VENDOR_ID_AMD) && (rdev->device == 0x15d0)) {
+		pdata->xpcs_window_def_reg = PCS_V2_RV_WINDOW_DEF;
+		pdata->xpcs_window_sel_reg = PCS_V2_RV_WINDOW_SELECT;
+	} else {
+		pdata->xpcs_window_def_reg = PCS_V2_WINDOW_DEF;
+		pdata->xpcs_window_sel_reg = PCS_V2_WINDOW_SELECT;
+	}
+	pci_dev_put(rdev);
+
 	/* Configure the PCS indirect addressing support */
-	reg = XPCS32_IOREAD(pdata, PCS_V2_WINDOW_DEF);
+	reg = XPCS32_IOREAD(pdata, pdata->xpcs_window_def_reg);
 	pdata->xpcs_window = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, OFFSET);
 	pdata->xpcs_window <<= 6;
 	pdata->xpcs_window_size = XPCS_GET_BITS(reg, PCS_V2_WINDOW_DEF, SIZE);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index f52a9bd05bac..00108815b55e 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -955,6 +955,8 @@ struct xgbe_prv_data {
 
 	/* XPCS indirect addressing lock */
 	spinlock_t xpcs_lock;
+	unsigned int xpcs_window_def_reg;
+	unsigned int xpcs_window_sel_reg;
 	unsigned int xpcs_window;
 	unsigned int xpcs_window_size;
 	unsigned int xpcs_window_mask;
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index c8f525574d68..7dcc907a449d 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -685,8 +685,6 @@ static int alx_alloc_rings(struct alx_priv *alx)
 		return -ENOMEM;
 	}
 
-	alx_reinit_rings(alx);
-
 	return 0;
 }
 
@@ -703,7 +701,7 @@ static void alx_free_rings(struct alx_priv *alx)
 	if (alx->qnapi[0] && alx->qnapi[0]->rxq)
 		kfree(alx->qnapi[0]->rxq->bufs);
 
-	if (!alx->descmem.virt)
+	if (alx->descmem.virt)
 		dma_free_coherent(&alx->hw.pdev->dev,
 				  alx->descmem.size,
 				  alx->descmem.virt,
@@ -984,6 +982,7 @@ static int alx_realloc_resources(struct alx_priv *alx)
 	alx_free_rings(alx);
 	alx_free_napis(alx);
 	alx_disable_advanced_intr(alx);
+	alx_init_intr(alx, false);
 
 	err = alx_alloc_napis(alx);
 	if (err)
@@ -1241,6 +1240,12 @@ static int __alx_open(struct alx_priv *alx, bool resume)
 	if (err)
 		goto out_free_rings;
 
+	/* must be called after alx_request_irq because the chip stops working
+	 * if we copy the dma addresses in alx_init_ring_ptrs twice when
+	 * requesting msi-x interrupts failed
+	 */
+	alx_reinit_rings(alx);
+
 	netif_set_real_num_tx_queues(alx->dev, alx->num_txq);
 	netif_set_real_num_rx_queues(alx->dev, alx->num_rxq);
 
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 3b14d5144228..c483618b57bd 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -913,6 +913,8 @@ static int bcm_enet_open(struct net_device *dev)
 		priv->old_link = 0;
 		priv->old_duplex = -1;
 		priv->old_pause = -1;
+	} else {
+		phydev = NULL;
 	}
 
 	/* mask all interrupts and request them */
@@ -1083,7 +1085,7 @@ static int bcm_enet_open(struct net_device *dev)
 	enet_dmac_writel(priv, priv->dma_chan_int_mask,
 			 ENETDMAC_IRMASK, priv->tx_chan);
 
-	if (priv->has_phy)
+	if (phydev)
 		phy_start(phydev);
 	else
 		bcm_enet_adjust_link(dev);
@@ -1126,7 +1128,7 @@ out_freeirq:
 	free_irq(dev->irq, dev);
 
 out_phy_disconnect:
-	if (priv->has_phy)
+	if (phydev)
 		phy_disconnect(phydev);
 
 	return ret;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9608cb49a11c..4fcc6a84a087 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1099,7 +1099,7 @@ static struct sk_buff *bnxt_gro_func_5730x(struct bnxt_tpa_info *tpa_info,
 {
 #ifdef CONFIG_INET
 	struct tcphdr *th;
-	int len, nw_off, tcp_opt_len;
+	int len, nw_off, tcp_opt_len = 0;
 
 	if (tcp_ts)
 		tcp_opt_len = 12;
@@ -5314,17 +5314,12 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state)
 	if ((link_info->support_auto_speeds | diff) !=
 	    link_info->support_auto_speeds) {
 		/* An advertised speed is no longer supported, so we need to
-		 * update the advertisement settings.  See bnxt_reset() for
-		 * comments about the rtnl_lock() sequence below.
+		 * update the advertisement settings.  Caller holds RTNL
+		 * so we can modify link settings.
 		 */
-		clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-		rtnl_lock();
 		link_info->advertising = link_info->support_auto_speeds;
-		if (test_bit(BNXT_STATE_OPEN, &bp->state) &&
-		    (link_info->autoneg & BNXT_AUTONEG_SPEED))
+		if (link_info->autoneg & BNXT_AUTONEG_SPEED)
 			bnxt_hwrm_set_link_setting(bp, true, false);
-		set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-		rtnl_unlock();
 	}
 	return 0;
 }
@@ -6200,29 +6195,37 @@ bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
 
-/* Only called from bnxt_sp_task() */
-static void bnxt_reset(struct bnxt *bp, bool silent)
+static void bnxt_rtnl_lock_sp(struct bnxt *bp)
 {
-	/* bnxt_reset_task() calls bnxt_close_nic() which waits
-	 * for BNXT_STATE_IN_SP_TASK to clear.
-	 * If there is a parallel dev_close(), bnxt_close() may be holding
+	/* We are called from bnxt_sp_task which has BNXT_STATE_IN_SP_TASK
+	 * set.  If the device is being closed, bnxt_close() may be holding
 	 * rtnl() and waiting for BNXT_STATE_IN_SP_TASK to clear.  So we
 	 * must clear BNXT_STATE_IN_SP_TASK before holding rtnl().
 	 */
 	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
 	rtnl_lock();
-	if (test_bit(BNXT_STATE_OPEN, &bp->state))
-		bnxt_reset_task(bp, silent);
+}
+
+static void bnxt_rtnl_unlock_sp(struct bnxt *bp)
+{
 	set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
 	rtnl_unlock();
 }
 
+/* Only called from bnxt_sp_task() */
+static void bnxt_reset(struct bnxt *bp, bool silent)
+{
+	bnxt_rtnl_lock_sp(bp);
+	if (test_bit(BNXT_STATE_OPEN, &bp->state))
+		bnxt_reset_task(bp, silent);
+	bnxt_rtnl_unlock_sp(bp);
+}
+
 static void bnxt_cfg_ntp_filters(struct bnxt *);
 
 static void bnxt_sp_task(struct work_struct *work)
 {
 	struct bnxt *bp = container_of(work, struct bnxt, sp_task);
-	int rc;
 
 	set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
 	smp_mb__after_atomic();
@@ -6236,16 +6239,6 @@ static void bnxt_sp_task(struct work_struct *work)
 
 	if (test_and_clear_bit(BNXT_RX_NTP_FLTR_SP_EVENT, &bp->sp_event))
 		bnxt_cfg_ntp_filters(bp);
-	if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
-		if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT,
-				       &bp->sp_event))
-			bnxt_hwrm_phy_qcaps(bp);
-
-		rc = bnxt_update_link(bp, true);
-		if (rc)
-			netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
-				   rc);
-	}
 	if (test_and_clear_bit(BNXT_HWRM_EXEC_FWD_REQ_SP_EVENT, &bp->sp_event))
 		bnxt_hwrm_exec_fwd_req(bp);
 	if (test_and_clear_bit(BNXT_VXLAN_ADD_PORT_SP_EVENT, &bp->sp_event)) {
@@ -6266,18 +6259,39 @@ static void bnxt_sp_task(struct work_struct *work)
 		bnxt_hwrm_tunnel_dst_port_free(
 			bp, TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE);
 	}
+	if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event))
+		bnxt_hwrm_port_qstats(bp);
+
+	/* These functions below will clear BNXT_STATE_IN_SP_TASK.  They
+	 * must be the last functions to be called before exiting.
+	 */
+	if (test_and_clear_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event)) {
+		int rc = 0;
+
+		if (test_and_clear_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT,
+				       &bp->sp_event))
+			bnxt_hwrm_phy_qcaps(bp);
+
+		bnxt_rtnl_lock_sp(bp);
+		if (test_bit(BNXT_STATE_OPEN, &bp->state))
+			rc = bnxt_update_link(bp, true);
+		bnxt_rtnl_unlock_sp(bp);
+		if (rc)
+			netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
+				   rc);
+	}
+	if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) {
+		bnxt_rtnl_lock_sp(bp);
+		if (test_bit(BNXT_STATE_OPEN, &bp->state))
+			bnxt_get_port_module_status(bp);
+		bnxt_rtnl_unlock_sp(bp);
+	}
 	if (test_and_clear_bit(BNXT_RESET_TASK_SP_EVENT, &bp->sp_event))
 		bnxt_reset(bp, false);
 
 	if (test_and_clear_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event))
 		bnxt_reset(bp, true);
 
-	if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event))
-		bnxt_get_port_module_status(bp);
-
-	if (test_and_clear_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event))
-		bnxt_hwrm_port_qstats(bp);
-
 	smp_mb__before_atomic();
 	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
 }
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index c0fb80acc2da..baba2db9d9c2 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -43,13 +43,13 @@
 #define DEFAULT_RX_RING_SIZE	512 /* must be power of 2 */
 #define MIN_RX_RING_SIZE	64
 #define MAX_RX_RING_SIZE	8192
-#define RX_RING_BYTES(bp)	(sizeof(struct macb_dma_desc)	\
+#define RX_RING_BYTES(bp)	(macb_dma_desc_get_size(bp)	\
 				 * (bp)->rx_ring_size)
 
 #define DEFAULT_TX_RING_SIZE	512 /* must be power of 2 */
 #define MIN_TX_RING_SIZE	64
 #define MAX_TX_RING_SIZE	4096
-#define TX_RING_BYTES(bp)	(sizeof(struct macb_dma_desc)	\
+#define TX_RING_BYTES(bp)	(macb_dma_desc_get_size(bp)	\
 				 * (bp)->tx_ring_size)
 
 /* level of occupied TX descriptors under which we wake up TX process */
@@ -78,6 +78,37 @@
  */
 #define MACB_HALT_TIMEOUT	1230
 
+/* DMA buffer descriptor might be different size
+ * depends on hardware configuration.
+ */
+static unsigned int macb_dma_desc_get_size(struct macb *bp)
+{
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+		return sizeof(struct macb_dma_desc) + sizeof(struct macb_dma_desc_64);
+#endif
+	return sizeof(struct macb_dma_desc);
+}
+
+static unsigned int macb_adj_dma_desc_idx(struct macb *bp, unsigned int idx)
+{
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	/* Dma buffer descriptor is 4 words length (instead of 2 words)
+	 * for 64b GEM.
+	 */
+	if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+		idx <<= 1;
+#endif
+	return idx;
+}
+
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+static struct macb_dma_desc_64 *macb_64b_desc(struct macb *bp, struct macb_dma_desc *desc)
+{
+	return (struct macb_dma_desc_64 *)((void *)desc + sizeof(struct macb_dma_desc));
+}
+#endif
+
 /* Ring buffer accessors */
 static unsigned int macb_tx_ring_wrap(struct macb *bp, unsigned int index)
 {
@@ -87,7 +118,9 @@ static unsigned int macb_tx_ring_wrap(struct macb *bp, unsigned int index)
 static struct macb_dma_desc *macb_tx_desc(struct macb_queue *queue,
 					  unsigned int index)
 {
-	return &queue->tx_ring[macb_tx_ring_wrap(queue->bp, index)];
+	index = macb_tx_ring_wrap(queue->bp, index);
+	index = macb_adj_dma_desc_idx(queue->bp, index);
+	return &queue->tx_ring[index];
 }
 
 static struct macb_tx_skb *macb_tx_skb(struct macb_queue *queue,
@@ -101,7 +134,7 @@ static dma_addr_t macb_tx_dma(struct macb_queue *queue, unsigned int index)
 	dma_addr_t offset;
 
 	offset = macb_tx_ring_wrap(queue->bp, index) *
-		 sizeof(struct macb_dma_desc);
+			macb_dma_desc_get_size(queue->bp);
 
 	return queue->tx_ring_dma + offset;
 }
@@ -113,7 +146,9 @@ static unsigned int macb_rx_ring_wrap(struct macb *bp, unsigned int index)
 
 static struct macb_dma_desc *macb_rx_desc(struct macb *bp, unsigned int index)
 {
-	return &bp->rx_ring[macb_rx_ring_wrap(bp, index)];
+	index = macb_rx_ring_wrap(bp, index);
+	index = macb_adj_dma_desc_idx(bp, index);
+	return &bp->rx_ring[index];
 }
 
 static void *macb_rx_buffer(struct macb *bp, unsigned int index)
@@ -560,12 +595,32 @@ static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb)
 	}
 }
 
-static inline void macb_set_addr(struct macb_dma_desc *desc, dma_addr_t addr)
+static void macb_set_addr(struct macb *bp, struct macb_dma_desc *desc, dma_addr_t addr)
 {
-	desc->addr = (u32)addr;
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	desc->addrh = (u32)(addr >> 32);
+	struct macb_dma_desc_64 *desc_64;
+
+	if (bp->hw_dma_cap == HW_DMA_CAP_64B) {
+		desc_64 = macb_64b_desc(bp, desc);
+		desc_64->addrh = upper_32_bits(addr);
+	}
 #endif
+	desc->addr = lower_32_bits(addr);
+}
+
+static dma_addr_t macb_get_addr(struct macb *bp, struct macb_dma_desc *desc)
+{
+	dma_addr_t addr = 0;
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	struct macb_dma_desc_64 *desc_64;
+
+	if (bp->hw_dma_cap == HW_DMA_CAP_64B) {
+		desc_64 = macb_64b_desc(bp, desc);
+		addr = ((u64)(desc_64->addrh) << 32);
+	}
+#endif
+	addr |= MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr));
+	return addr;
 }
 
 static void macb_tx_error_task(struct work_struct *work)
@@ -649,16 +704,17 @@ static void macb_tx_error_task(struct work_struct *work)
 
 	/* Set end of TX queue */
 	desc = macb_tx_desc(queue, 0);
-	macb_set_addr(desc, 0);
+	macb_set_addr(bp, desc, 0);
 	desc->ctrl = MACB_BIT(TX_USED);
 
 	/* Make descriptor updates visible to hardware */
 	wmb();
 
 	/* Reinitialize the TX desc queue */
-	queue_writel(queue, TBQP, (u32)(queue->tx_ring_dma));
+	queue_writel(queue, TBQP, lower_32_bits(queue->tx_ring_dma));
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	queue_writel(queue, TBQPH, (u32)(queue->tx_ring_dma >> 32));
+	if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+		queue_writel(queue, TBQPH, upper_32_bits(queue->tx_ring_dma));
 #endif
 	/* Make TX ring reflect state of hardware */
 	queue->tx_head = 0;
@@ -750,6 +806,7 @@ static void gem_rx_refill(struct macb *bp)
 	unsigned int		entry;
 	struct sk_buff		*skb;
 	dma_addr_t		paddr;
+	struct macb_dma_desc *desc;
 
 	while (CIRC_SPACE(bp->rx_prepared_head, bp->rx_tail,
 			  bp->rx_ring_size) > 0) {
@@ -759,6 +816,7 @@ static void gem_rx_refill(struct macb *bp)
 		rmb();
 
 		bp->rx_prepared_head++;
+		desc = macb_rx_desc(bp, entry);
 
 		if (!bp->rx_skbuff[entry]) {
 			/* allocate sk_buff for this free entry in ring */
@@ -782,14 +840,14 @@ static void gem_rx_refill(struct macb *bp)
 
 			if (entry == bp->rx_ring_size - 1)
 				paddr |= MACB_BIT(RX_WRAP);
-			macb_set_addr(&(bp->rx_ring[entry]), paddr);
-			bp->rx_ring[entry].ctrl = 0;
+			macb_set_addr(bp, desc, paddr);
+			desc->ctrl = 0;
 
 			/* properly align Ethernet header */
 			skb_reserve(skb, NET_IP_ALIGN);
 		} else {
-			bp->rx_ring[entry].addr &= ~MACB_BIT(RX_USED);
-			bp->rx_ring[entry].ctrl = 0;
+			desc->addr &= ~MACB_BIT(RX_USED);
+			desc->ctrl = 0;
 		}
 	}
 
@@ -835,16 +893,13 @@ static int gem_rx(struct macb *bp, int budget)
 		bool rxused;
 
 		entry = macb_rx_ring_wrap(bp, bp->rx_tail);
-		desc = &bp->rx_ring[entry];
+		desc = macb_rx_desc(bp, entry);
 
 		/* Make hw descriptor updates visible to CPU */
 		rmb();
 
 		rxused = (desc->addr & MACB_BIT(RX_USED)) ? true : false;
-		addr = MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-		addr |= ((u64)(desc->addrh) << 32);
-#endif
+		addr = macb_get_addr(bp, desc);
 		ctrl = desc->ctrl;
 
 		if (!rxused)
@@ -987,15 +1042,17 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
 static inline void macb_init_rx_ring(struct macb *bp)
 {
 	dma_addr_t addr;
+	struct macb_dma_desc *desc = NULL;
 	int i;
 
 	addr = bp->rx_buffers_dma;
 	for (i = 0; i < bp->rx_ring_size; i++) {
-		bp->rx_ring[i].addr = addr;
-		bp->rx_ring[i].ctrl = 0;
+		desc = macb_rx_desc(bp, i);
+		macb_set_addr(bp, desc, addr);
+		desc->ctrl = 0;
 		addr += bp->rx_buffer_size;
 	}
-	bp->rx_ring[bp->rx_ring_size - 1].addr |= MACB_BIT(RX_WRAP);
+	desc->addr |= MACB_BIT(RX_WRAP);
 	bp->rx_tail = 0;
 }
 
@@ -1008,15 +1065,14 @@ static int macb_rx(struct macb *bp, int budget)
 
 	for (tail = bp->rx_tail; budget > 0; tail++) {
 		struct macb_dma_desc *desc = macb_rx_desc(bp, tail);
-		u32 addr, ctrl;
+		u32 ctrl;
 
 		/* Make hw descriptor updates visible to CPU */
 		rmb();
 
-		addr = desc->addr;
 		ctrl = desc->ctrl;
 
-		if (!(addr & MACB_BIT(RX_USED)))
+		if (!(desc->addr & MACB_BIT(RX_USED)))
 			break;
 
 		if (ctrl & MACB_BIT(RX_SOF)) {
@@ -1336,7 +1392,7 @@ static unsigned int macb_tx_map(struct macb *bp,
 	i = tx_head;
 	entry = macb_tx_ring_wrap(bp, i);
 	ctrl = MACB_BIT(TX_USED);
-	desc = &queue->tx_ring[entry];
+	desc = macb_tx_desc(queue, entry);
 	desc->ctrl = ctrl;
 
 	if (lso_ctrl) {
@@ -1358,7 +1414,7 @@ static unsigned int macb_tx_map(struct macb *bp,
 		i--;
 		entry = macb_tx_ring_wrap(bp, i);
 		tx_skb = &queue->tx_skb[entry];
-		desc = &queue->tx_ring[entry];
+		desc = macb_tx_desc(queue, entry);
 
 		ctrl = (u32)tx_skb->size;
 		if (eof) {
@@ -1379,7 +1435,7 @@ static unsigned int macb_tx_map(struct macb *bp,
 			ctrl |= MACB_BF(MSS_MFS, mss_mfs);
 
 		/* Set TX buffer descriptor */
-		macb_set_addr(desc, tx_skb->mapping);
+		macb_set_addr(bp, desc, tx_skb->mapping);
 		/* desc->addr must be visible to hardware before clearing
 		 * 'TX_USED' bit in desc->ctrl.
 		 */
@@ -1586,11 +1642,9 @@ static void gem_free_rx_buffers(struct macb *bp)
 		if (!skb)
 			continue;
 
-		desc = &bp->rx_ring[i];
-		addr = MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-		addr |= ((u64)(desc->addrh) << 32);
-#endif
+		desc = macb_rx_desc(bp, i);
+		addr = macb_get_addr(bp, desc);
+
 		dma_unmap_single(&bp->pdev->dev, addr, bp->rx_buffer_size,
 				 DMA_FROM_DEVICE);
 		dev_kfree_skb_any(skb);
@@ -1711,15 +1765,17 @@ out_err:
 static void gem_init_rings(struct macb *bp)
 {
 	struct macb_queue *queue;
+	struct macb_dma_desc *desc = NULL;
 	unsigned int q;
 	int i;
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
 		for (i = 0; i < bp->tx_ring_size; i++) {
-			queue->tx_ring[i].addr = 0;
-			queue->tx_ring[i].ctrl = MACB_BIT(TX_USED);
+			desc = macb_tx_desc(queue, i);
+			macb_set_addr(bp, desc, 0);
+			desc->ctrl = MACB_BIT(TX_USED);
 		}
-		queue->tx_ring[bp->tx_ring_size - 1].ctrl |= MACB_BIT(TX_WRAP);
+		desc->ctrl |= MACB_BIT(TX_WRAP);
 		queue->tx_head = 0;
 		queue->tx_tail = 0;
 	}
@@ -1733,16 +1789,18 @@ static void gem_init_rings(struct macb *bp)
 static void macb_init_rings(struct macb *bp)
 {
 	int i;
+	struct macb_dma_desc *desc = NULL;
 
 	macb_init_rx_ring(bp);
 
 	for (i = 0; i < bp->tx_ring_size; i++) {
-		bp->queues[0].tx_ring[i].addr = 0;
-		bp->queues[0].tx_ring[i].ctrl = MACB_BIT(TX_USED);
+		desc = macb_tx_desc(&bp->queues[0], i);
+		macb_set_addr(bp, desc, 0);
+		desc->ctrl = MACB_BIT(TX_USED);
 	}
 	bp->queues[0].tx_head = 0;
 	bp->queues[0].tx_tail = 0;
-	bp->queues[0].tx_ring[bp->tx_ring_size - 1].ctrl |= MACB_BIT(TX_WRAP);
+	desc->ctrl |= MACB_BIT(TX_WRAP);
 }
 
 static void macb_reset_hw(struct macb *bp)
@@ -1863,7 +1921,8 @@ static void macb_configure_dma(struct macb *bp)
 			dmacfg &= ~GEM_BIT(TXCOEN);
 
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-		dmacfg |= GEM_BIT(ADDR64);
+		if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+			dmacfg |= GEM_BIT(ADDR64);
 #endif
 		netdev_dbg(bp->dev, "Cadence configure DMA with 0x%08x\n",
 			   dmacfg);
@@ -1910,14 +1969,16 @@ static void macb_init_hw(struct macb *bp)
 	macb_configure_dma(bp);
 
 	/* Initialize TX and RX buffers */
-	macb_writel(bp, RBQP, (u32)(bp->rx_ring_dma));
+	macb_writel(bp, RBQP, lower_32_bits(bp->rx_ring_dma));
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	macb_writel(bp, RBQPH, (u32)(bp->rx_ring_dma >> 32));
+	if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+		macb_writel(bp, RBQPH, upper_32_bits(bp->rx_ring_dma));
 #endif
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-		queue_writel(queue, TBQP, (u32)(queue->tx_ring_dma));
+		queue_writel(queue, TBQP, lower_32_bits(queue->tx_ring_dma));
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-		queue_writel(queue, TBQPH, (u32)(queue->tx_ring_dma >> 32));
+		if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+			queue_writel(queue, TBQPH, upper_32_bits(queue->tx_ring_dma));
 #endif
 
 		/* Enable interrupts */
@@ -2627,7 +2688,8 @@ static int macb_init(struct platform_device *pdev)
 			queue->IMR  = GEM_IMR(hw_q - 1);
 			queue->TBQP = GEM_TBQP(hw_q - 1);
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-			queue->TBQPH = GEM_TBQPH(hw_q -1);
+			if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+				queue->TBQPH = GEM_TBQPH(hw_q - 1);
 #endif
 		} else {
 			/* queue0 uses legacy registers */
@@ -2637,7 +2699,8 @@ static int macb_init(struct platform_device *pdev)
 			queue->IMR  = MACB_IMR;
 			queue->TBQP = MACB_TBQP;
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-			queue->TBQPH = MACB_TBQPH;
+			if (bp->hw_dma_cap == HW_DMA_CAP_64B)
+				queue->TBQPH = MACB_TBQPH;
 #endif
 		}
 
@@ -2730,13 +2793,14 @@ static int macb_init(struct platform_device *pdev)
 static int at91ether_start(struct net_device *dev)
 {
 	struct macb *lp = netdev_priv(dev);
+	struct macb_dma_desc *desc;
 	dma_addr_t addr;
 	u32 ctl;
 	int i;
 
 	lp->rx_ring = dma_alloc_coherent(&lp->pdev->dev,
 					 (AT91ETHER_MAX_RX_DESCR *
-					  sizeof(struct macb_dma_desc)),
+					  macb_dma_desc_get_size(lp)),
 					 &lp->rx_ring_dma, GFP_KERNEL);
 	if (!lp->rx_ring)
 		return -ENOMEM;
@@ -2748,7 +2812,7 @@ static int at91ether_start(struct net_device *dev)
 	if (!lp->rx_buffers) {
 		dma_free_coherent(&lp->pdev->dev,
 				  AT91ETHER_MAX_RX_DESCR *
-				  sizeof(struct macb_dma_desc),
+				  macb_dma_desc_get_size(lp),
 				  lp->rx_ring, lp->rx_ring_dma);
 		lp->rx_ring = NULL;
 		return -ENOMEM;
@@ -2756,13 +2820,14 @@ static int at91ether_start(struct net_device *dev)
 
 	addr = lp->rx_buffers_dma;
 	for (i = 0; i < AT91ETHER_MAX_RX_DESCR; i++) {
-		lp->rx_ring[i].addr = addr;
-		lp->rx_ring[i].ctrl = 0;
+		desc = macb_rx_desc(lp, i);
+		macb_set_addr(lp, desc, addr);
+		desc->ctrl = 0;
 		addr += AT91ETHER_MAX_RBUFF_SZ;
 	}
 
 	/* Set the Wrap bit on the last descriptor */
-	lp->rx_ring[AT91ETHER_MAX_RX_DESCR - 1].addr |= MACB_BIT(RX_WRAP);
+	desc->addr |= MACB_BIT(RX_WRAP);
 
 	/* Reset buffer index */
 	lp->rx_tail = 0;
@@ -2834,7 +2899,7 @@ static int at91ether_close(struct net_device *dev)
 
 	dma_free_coherent(&lp->pdev->dev,
 			  AT91ETHER_MAX_RX_DESCR *
-			  sizeof(struct macb_dma_desc),
+			  macb_dma_desc_get_size(lp),
 			  lp->rx_ring, lp->rx_ring_dma);
 	lp->rx_ring = NULL;
 
@@ -2885,13 +2950,15 @@ static int at91ether_start_xmit(struct sk_buff *skb, struct net_device *dev)
 static void at91ether_rx(struct net_device *dev)
 {
 	struct macb *lp = netdev_priv(dev);
+	struct macb_dma_desc *desc;
 	unsigned char *p_recv;
 	struct sk_buff *skb;
 	unsigned int pktlen;
 
-	while (lp->rx_ring[lp->rx_tail].addr & MACB_BIT(RX_USED)) {
+	desc = macb_rx_desc(lp, lp->rx_tail);
+	while (desc->addr & MACB_BIT(RX_USED)) {
 		p_recv = lp->rx_buffers + lp->rx_tail * AT91ETHER_MAX_RBUFF_SZ;
-		pktlen = MACB_BF(RX_FRMLEN, lp->rx_ring[lp->rx_tail].ctrl);
+		pktlen = MACB_BF(RX_FRMLEN, desc->ctrl);
 		skb = netdev_alloc_skb(dev, pktlen + 2);
 		if (skb) {
 			skb_reserve(skb, 2);
@@ -2905,17 +2972,19 @@ static void at91ether_rx(struct net_device *dev)
 			lp->stats.rx_dropped++;
 		}
 
-		if (lp->rx_ring[lp->rx_tail].ctrl & MACB_BIT(RX_MHASH_MATCH))
+		if (desc->ctrl & MACB_BIT(RX_MHASH_MATCH))
 			lp->stats.multicast++;
 
 		/* reset ownership bit */
-		lp->rx_ring[lp->rx_tail].addr &= ~MACB_BIT(RX_USED);
+		desc->addr &= ~MACB_BIT(RX_USED);
 
 		/* wrap after last buffer */
 		if (lp->rx_tail == AT91ETHER_MAX_RX_DESCR - 1)
 			lp->rx_tail = 0;
 		else
 			lp->rx_tail++;
+
+		desc = macb_rx_desc(lp, lp->rx_tail);
 	}
 }
 
@@ -3211,8 +3280,11 @@ static int macb_probe(struct platform_device *pdev)
 	device_init_wakeup(&pdev->dev, bp->wol & MACB_WOL_HAS_MAGIC_PACKET);
 
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	if (GEM_BFEXT(DBWDEF, gem_readl(bp, DCFG1)) > GEM_DBW32)
+	if (GEM_BFEXT(DAW64, gem_readl(bp, DCFG6))) {
 		dma_set_mask(&pdev->dev, DMA_BIT_MASK(44));
+		bp->hw_dma_cap = HW_DMA_CAP_64B;
+	} else
+		bp->hw_dma_cap = HW_DMA_CAP_32B;
 #endif
 
 	spin_lock_init(&bp->lock);
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index d67adad67be1..fc8550a5d47f 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -385,6 +385,8 @@
 /* Bitfields in DCFG6. */
 #define GEM_PBUF_LSO_OFFSET			27
 #define GEM_PBUF_LSO_SIZE			1
+#define GEM_DAW64_OFFSET			23
+#define GEM_DAW64_SIZE				1
 
 /* Constants for CLK */
 #define MACB_CLK_DIV8				0
@@ -487,12 +489,20 @@
 struct macb_dma_desc {
 	u32	addr;
 	u32	ctrl;
+};
+
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	u32     addrh;
-	u32     resvd;
-#endif
+enum macb_hw_dma_cap {
+	HW_DMA_CAP_32B,
+	HW_DMA_CAP_64B,
 };
 
+struct macb_dma_desc_64 {
+	u32 addrh;
+	u32 resvd;
+};
+#endif
+
 /* DMA descriptor bitfields */
 #define MACB_RX_USED_OFFSET			0
 #define MACB_RX_USED_SIZE			1
@@ -874,6 +884,10 @@ struct macb {
 	unsigned int		jumbo_max_len;
 
 	u32			wol;
+
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	enum macb_hw_dma_cap hw_dma_cap;
+#endif
 };
 
 static inline bool macb_is_gem(struct macb *bp)
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 2f85b64f01fa..1e4695270da6 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -31,6 +31,7 @@ struct lmac {
 	u8                      lmac_type;
 	u8                      lane_to_sds;
 	bool                    use_training;
+	bool                    autoneg;
 	bool			link_up;
 	int			lmacid; /* ID within BGX */
 	int			lmacid_bd; /* ID on board */
@@ -461,7 +462,17 @@ static int bgx_lmac_sgmii_init(struct bgx *bgx, struct lmac *lmac)
 	/* power down, reset autoneg, autoneg enable */
 	cfg = bgx_reg_read(bgx, lmacid, BGX_GMP_PCS_MRX_CTL);
 	cfg &= ~PCS_MRX_CTL_PWR_DN;
-	cfg |= (PCS_MRX_CTL_RST_AN | PCS_MRX_CTL_AN_EN);
+	cfg |= PCS_MRX_CTL_RST_AN;
+	if (lmac->phydev) {
+		cfg |= PCS_MRX_CTL_AN_EN;
+	} else {
+		/* In scenarios where PHY driver is not present or it's a
+		 * non-standard PHY, FW sets AN_EN to inform Linux driver
+		 * to do auto-neg and link polling or not.
+		 */
+		if (cfg & PCS_MRX_CTL_AN_EN)
+			lmac->autoneg = true;
+	}
 	bgx_reg_write(bgx, lmacid, BGX_GMP_PCS_MRX_CTL, cfg);
 
 	if (lmac->lmac_type == BGX_MODE_QSGMII) {
@@ -472,7 +483,7 @@ static int bgx_lmac_sgmii_init(struct bgx *bgx, struct lmac *lmac)
 		return 0;
 	}
 
-	if (lmac->lmac_type == BGX_MODE_SGMII) {
+	if ((lmac->lmac_type == BGX_MODE_SGMII) && lmac->phydev) {
 		if (bgx_poll_reg(bgx, lmacid, BGX_GMP_PCS_MRX_STATUS,
 				 PCS_MRX_STATUS_AN_CPT, false)) {
 			dev_err(&bgx->pdev->dev, "BGX AN_CPT not completed\n");
@@ -678,12 +689,71 @@ static int bgx_xaui_check_link(struct lmac *lmac)
 	return -1;
 }
 
+static void bgx_poll_for_sgmii_link(struct lmac *lmac)
+{
+	u64 pcs_link, an_result;
+	u8 speed;
+
+	pcs_link = bgx_reg_read(lmac->bgx, lmac->lmacid,
+				BGX_GMP_PCS_MRX_STATUS);
+
+	/*Link state bit is sticky, read it again*/
+	if (!(pcs_link & PCS_MRX_STATUS_LINK))
+		pcs_link = bgx_reg_read(lmac->bgx, lmac->lmacid,
+					BGX_GMP_PCS_MRX_STATUS);
+
+	if (bgx_poll_reg(lmac->bgx, lmac->lmacid, BGX_GMP_PCS_MRX_STATUS,
+			 PCS_MRX_STATUS_AN_CPT, false)) {
+		lmac->link_up = false;
+		lmac->last_speed = SPEED_UNKNOWN;
+		lmac->last_duplex = DUPLEX_UNKNOWN;
+		goto next_poll;
+	}
+
+	lmac->link_up = ((pcs_link & PCS_MRX_STATUS_LINK) != 0) ? true : false;
+	an_result = bgx_reg_read(lmac->bgx, lmac->lmacid,
+				 BGX_GMP_PCS_ANX_AN_RESULTS);
+
+	speed = (an_result >> 3) & 0x3;
+	lmac->last_duplex = (an_result >> 1) & 0x1;
+	switch (speed) {
+	case 0:
+		lmac->last_speed = 10;
+		break;
+	case 1:
+		lmac->last_speed = 100;
+		break;
+	case 2:
+		lmac->last_speed = 1000;
+		break;
+	default:
+		lmac->link_up = false;
+		lmac->last_speed = SPEED_UNKNOWN;
+		lmac->last_duplex = DUPLEX_UNKNOWN;
+		break;
+	}
+
+next_poll:
+
+	if (lmac->last_link != lmac->link_up) {
+		if (lmac->link_up)
+			bgx_sgmii_change_link_state(lmac);
+		lmac->last_link = lmac->link_up;
+	}
+
+	queue_delayed_work(lmac->check_link, &lmac->dwork, HZ * 3);
+}
+
 static void bgx_poll_for_link(struct work_struct *work)
 {
 	struct lmac *lmac;
 	u64 spu_link, smu_link;
 
 	lmac = container_of(work, struct lmac, dwork.work);
+	if (lmac->is_sgmii) {
+		bgx_poll_for_sgmii_link(lmac);
+		return;
+	}
 
 	/* Receive link is latching low. Force it high and verify it */
 	bgx_reg_modify(lmac->bgx, lmac->lmacid,
@@ -775,9 +845,21 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 	    (lmac->lmac_type != BGX_MODE_XLAUI) &&
 	    (lmac->lmac_type != BGX_MODE_40G_KR) &&
 	    (lmac->lmac_type != BGX_MODE_10G_KR)) {
-		if (!lmac->phydev)
-			return -ENODEV;
-
+		if (!lmac->phydev) {
+			if (lmac->autoneg) {
+				bgx_reg_write(bgx, lmacid,
+					      BGX_GMP_PCS_LINKX_TIMER,
+					      PCS_LINKX_TIMER_COUNT);
+				goto poll;
+			} else {
+				/* Default to below link speed and duplex */
+				lmac->link_up = true;
+				lmac->last_speed = 1000;
+				lmac->last_duplex = 1;
+				bgx_sgmii_change_link_state(lmac);
+				return 0;
+			}
+		}
 		lmac->phydev->dev_flags = 0;
 
 		if (phy_connect_direct(&lmac->netdev, lmac->phydev,
@@ -786,15 +868,17 @@ static int bgx_lmac_enable(struct bgx *bgx, u8 lmacid)
 			return -ENODEV;
 
 		phy_start_aneg(lmac->phydev);
-	} else {
-		lmac->check_link = alloc_workqueue("check_link", WQ_UNBOUND |
-						   WQ_MEM_RECLAIM, 1);
-		if (!lmac->check_link)
-			return -ENOMEM;
-		INIT_DELAYED_WORK(&lmac->dwork, bgx_poll_for_link);
-		queue_delayed_work(lmac->check_link, &lmac->dwork, 0);
+		return 0;
 	}
 
+poll:
+	lmac->check_link = alloc_workqueue("check_link", WQ_UNBOUND |
+					   WQ_MEM_RECLAIM, 1);
+	if (!lmac->check_link)
+		return -ENOMEM;
+	INIT_DELAYED_WORK(&lmac->dwork, bgx_poll_for_link);
+	queue_delayed_work(lmac->check_link, &lmac->dwork, 0);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index c18ebfeb2039..a60f189429bb 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -153,10 +153,15 @@
 #define	 PCS_MRX_CTL_LOOPBACK1			BIT_ULL(14)
 #define	 PCS_MRX_CTL_RESET			BIT_ULL(15)
 #define BGX_GMP_PCS_MRX_STATUS		0x30008
+#define	 PCS_MRX_STATUS_LINK			BIT_ULL(2)
 #define	 PCS_MRX_STATUS_AN_CPT			BIT_ULL(5)
+#define BGX_GMP_PCS_ANX_ADV		0x30010
 #define BGX_GMP_PCS_ANX_AN_RESULTS	0x30020
+#define BGX_GMP_PCS_LINKX_TIMER		0x30040
+#define PCS_LINKX_TIMER_COUNT			0x1E84
 #define BGX_GMP_PCS_SGM_AN_ADV		0x30068
 #define BGX_GMP_PCS_MISCX_CTL		0x30078
+#define  PCS_MISC_CTL_MODE			BIT_ULL(8)
 #define  PCS_MISC_CTL_DISP_EN			BIT_ULL(13)
 #define  PCS_MISC_CTL_GMX_ENO			BIT_ULL(11)
 #define  PCS_MISC_CTL_SAMP_PT_MASK	0x7Full
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_xcv.c b/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
index 67befedef709..578c7f8f11bf 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_xcv.c
@@ -116,8 +116,7 @@ void xcv_setup_link(bool link_up, int link_speed)
 	int speed = 2;
 
 	if (!xcv) {
-		dev_err(&xcv->pdev->dev,
-			"XCV init not done, probe may have failed\n");
+		pr_err("XCV init not done, probe may have failed\n");
 		return;
 	}
 
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 1a7f8ad7b9c6..cd49a54c538d 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -362,8 +362,10 @@ static int be_mac_addr_set(struct net_device *netdev, void *p)
 		status = -EPERM;
 		goto err;
 	}
-done:
+
+	/* Remember currently programmed MAC */
 	ether_addr_copy(adapter->dev_mac, addr->sa_data);
+done:
 	ether_addr_copy(netdev->dev_addr, addr->sa_data);
 	dev_info(dev, "MAC address changed to %pM\n", addr->sa_data);
 	return 0;
@@ -3618,8 +3620,10 @@ static void be_disable_if_filters(struct be_adapter *adapter)
 {
 	/* Don't delete MAC on BE3 VFs without FILTMGMT privilege  */
 	if (!BEx_chip(adapter) || !be_virtfn(adapter) ||
-	    check_privilege(adapter, BE_PRIV_FILTMGMT))
+	    check_privilege(adapter, BE_PRIV_FILTMGMT)) {
 		be_dev_mac_del(adapter, adapter->pmac_id[0]);
+		eth_zero_addr(adapter->dev_mac);
+	}
 
 	be_clear_uc_list(adapter);
 	be_clear_mc_list(adapter);
@@ -3773,12 +3777,27 @@ static int be_enable_if_filters(struct be_adapter *adapter)
 	if (status)
 		return status;
 
-	/* Don't add MAC on BE3 VFs without FILTMGMT privilege */
-	if (!BEx_chip(adapter) || !be_virtfn(adapter) ||
-	    check_privilege(adapter, BE_PRIV_FILTMGMT)) {
+	/* Normally this condition usually true as the ->dev_mac is zeroed.
+	 * But on BE3 VFs the initial MAC is pre-programmed by PF and
+	 * subsequent be_dev_mac_add() can fail (after fresh boot)
+	 */
+	if (!ether_addr_equal(adapter->dev_mac, adapter->netdev->dev_addr)) {
+		int old_pmac_id = -1;
+
+		/* Remember old programmed MAC if any - can happen on BE3 VF */
+		if (!is_zero_ether_addr(adapter->dev_mac))
+			old_pmac_id = adapter->pmac_id[0];
+
 		status = be_dev_mac_add(adapter, adapter->netdev->dev_addr);
 		if (status)
 			return status;
+
+		/* Delete the old programmed MAC as we successfully programmed
+		 * a new MAC
+		 */
+		if (old_pmac_id >= 0 && old_pmac_id != adapter->pmac_id[0])
+			be_dev_mac_del(adapter, old_pmac_id);
+
 		ether_addr_copy(adapter->dev_mac, adapter->netdev->dev_addr);
 	}
 
@@ -4552,6 +4571,10 @@ static int be_mac_setup(struct be_adapter *adapter)
 
 		memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
 		memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
+
+		/* Initial MAC for BE3 VFs is already programmed by PF */
+		if (BEx_chip(adapter) && be_virtfn(adapter))
+			memcpy(adapter->dev_mac, mac, ETH_ALEN);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index c9b7ad65e563..726b5693ae8a 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -1668,7 +1668,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv,
 
 free_buffers:
 	/* compensate sw bpool counter changes */
-	for (i--; i > 0; i--) {
+	for (i--; i >= 0; i--) {
 		dpaa_bp = dpaa_bpid2pool(sgt[i].bpid);
 		if (dpaa_bp) {
 			count_ptr = this_cpu_ptr(dpaa_bp->percpu_count);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 38160c2bebcb..8be7034b2e7b 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2910,6 +2910,7 @@ static void set_multicast_list(struct net_device *ndev)
 	struct netdev_hw_addr *ha;
 	unsigned int i, bit, data, crc, tmp;
 	unsigned char hash;
+	unsigned int hash_high = 0, hash_low = 0;
 
 	if (ndev->flags & IFF_PROMISC) {
 		tmp = readl(fep->hwp + FEC_R_CNTRL);
@@ -2932,11 +2933,7 @@ static void set_multicast_list(struct net_device *ndev)
 		return;
 	}
 
-	/* Clear filter and add the addresses in hash register
-	 */
-	writel(0, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
-	writel(0, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
-
+	/* Add the addresses in hash register */
 	netdev_for_each_mc_addr(ha, ndev) {
 		/* calculate crc32 value of mac address */
 		crc = 0xffffffff;
@@ -2954,16 +2951,14 @@ static void set_multicast_list(struct net_device *ndev)
 		 */
 		hash = (crc >> (32 - FEC_HASH_BITS)) & 0x3f;
 
-		if (hash > 31) {
-			tmp = readl(fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
-			tmp |= 1 << (hash - 32);
-			writel(tmp, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
-		} else {
-			tmp = readl(fep->hwp + FEC_GRP_HASH_TABLE_LOW);
-			tmp |= 1 << hash;
-			writel(tmp, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
-		}
+		if (hash > 31)
+			hash_high |= 1 << (hash - 32);
+		else
+			hash_low |= 1 << hash;
 	}
+
+	writel(hash_high, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
+	writel(hash_low, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
 }
 
 /* Set a MAC change in hardware. */
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index a6e7afa878be..957bfc220978 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -2010,8 +2010,8 @@ static void free_skb_rx_queue(struct gfar_priv_rx_q *rx_queue)
 		if (!rxb->page)
 			continue;
 
-		dma_unmap_single(rx_queue->dev, rxb->dma,
-				 PAGE_SIZE, DMA_FROM_DEVICE);
+		dma_unmap_page(rx_queue->dev, rxb->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
 		__free_page(rxb->page);
 
 		rxb->page = NULL;
@@ -2948,7 +2948,7 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus,
 	}
 
 	/* try reuse page */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely(page_count(page) != 1 || page_is_pfmemalloc(page)))
 		return false;
 
 	/* change offset to the other half */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index 87226685f742..8fa18fc17cd2 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -1014,9 +1014,7 @@
 
 static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
 {
-	u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
-	writel(value, reg_addr + reg);
+	writel(value, base + reg);
 }
 
 #define dsaf_write_dev(a, reg, value) \
@@ -1024,9 +1022,7 @@ static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
 
 static inline u32 dsaf_read_reg(u8 __iomem *base, u32 reg)
 {
-	u8 __iomem *reg_addr = ACCESS_ONCE(base);
-
-	return readl(reg_addr + reg);
+	return readl(base + reg);
 }
 
 static inline void dsaf_write_syscon(struct regmap *base, u32 reg, u32 value)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 672b64606321..8aed72860e7c 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -305,8 +305,8 @@ int hns_nic_net_xmit_hw(struct net_device *ndev,
 			struct hns_nic_ring_data *ring_data)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
-	struct device *dev = priv->dev;
 	struct hnae_ring *ring = ring_data->ring;
+	struct device *dev = ring_to_dev(ring);
 	struct netdev_queue *dev_queue;
 	struct skb_frag_struct *frag;
 	int buf_num;
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index a831f947ca8c..309f5c66083c 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1601,8 +1601,11 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	netdev->netdev_ops = &ibmveth_netdev_ops;
 	netdev->ethtool_ops = &netdev_ethtool_ops;
 	SET_NETDEV_DEV(netdev, &dev->dev);
-	netdev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM |
-		NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	netdev->hw_features = NETIF_F_SG;
+	if (vio_get_attribute(dev, "ibm,illan-options", NULL) != NULL) {
+		netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+				       NETIF_F_RXCSUM;
+	}
 
 	netdev->features |= netdev->hw_features;
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index c12596676bbb..a07b8d79174c 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -189,9 +189,10 @@ static int alloc_long_term_buff(struct ibmvnic_adapter *adapter,
 	}
 	ltb->map_id = adapter->map_id;
 	adapter->map_id++;
+
+	init_completion(&adapter->fw_done);
 	send_request_map(adapter, ltb->addr,
 			 ltb->size, ltb->map_id);
-	init_completion(&adapter->fw_done);
 	wait_for_completion(&adapter->fw_done);
 	return 0;
 }
@@ -505,7 +506,7 @@ rx_pool_alloc_failed:
 	adapter->rx_pool = NULL;
 rx_pool_arr_alloc_failed:
 	for (i = 0; i < adapter->req_rx_queues; i++)
-		napi_enable(&adapter->napi[i]);
+		napi_disable(&adapter->napi[i]);
 alloc_napi_failed:
 	return -ENOMEM;
 }
@@ -1121,10 +1122,10 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev,
 	crq.request_statistics.ioba = cpu_to_be32(adapter->stats_token);
 	crq.request_statistics.len =
 	    cpu_to_be32(sizeof(struct ibmvnic_statistics));
-	ibmvnic_send_crq(adapter, &crq);
 
 	/* Wait for data to be written */
 	init_completion(&adapter->stats_done);
+	ibmvnic_send_crq(adapter, &crq);
 	wait_for_completion(&adapter->stats_done);
 
 	for (i = 0; i < ARRAY_SIZE(ibmvnic_stats); i++)
@@ -1496,7 +1497,7 @@ static void init_sub_crqs(struct ibmvnic_adapter *adapter, int retry)
 		adapter->req_rx_queues = adapter->opt_rx_comp_queues;
 		adapter->req_rx_add_queues = adapter->max_rx_add_queues;
 
-		adapter->req_mtu = adapter->max_mtu;
+		adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN;
 	}
 
 	total_queues = adapter->req_tx_queues + adapter->req_rx_queues;
@@ -2185,12 +2186,12 @@ static void handle_error_info_rsp(union ibmvnic_crq *crq,
 
 	if (!found) {
 		dev_err(dev, "Couldn't find error id %x\n",
-			crq->request_error_rsp.error_id);
+			be32_to_cpu(crq->request_error_rsp.error_id));
 		return;
 	}
 
 	dev_err(dev, "Detailed info for error id %x:",
-		crq->request_error_rsp.error_id);
+		be32_to_cpu(crq->request_error_rsp.error_id));
 
 	for (i = 0; i < error_buff->len; i++) {
 		pr_cont("%02x", (int)error_buff->buff[i]);
@@ -2269,8 +2270,8 @@ static void handle_error_indication(union ibmvnic_crq *crq,
 	dev_err(dev, "Firmware reports %serror id %x, cause %d\n",
 		crq->error_indication.
 		    flags & IBMVNIC_FATAL_ERROR ? "FATAL " : "",
-		crq->error_indication.error_id,
-		crq->error_indication.error_cause);
+		be32_to_cpu(crq->error_indication.error_id),
+		be16_to_cpu(crq->error_indication.error_cause));
 
 	error_buff = kmalloc(sizeof(*error_buff), GFP_ATOMIC);
 	if (!error_buff)
@@ -2388,10 +2389,10 @@ static void handle_request_cap_rsp(union ibmvnic_crq *crq,
 	case PARTIALSUCCESS:
 		dev_info(dev, "req=%lld, rsp=%ld in %s queue, retrying.\n",
 			 *req_value,
-			 (long int)be32_to_cpu(crq->request_capability_rsp.
+			 (long int)be64_to_cpu(crq->request_capability_rsp.
 					       number), name);
 		release_sub_crqs_no_irqs(adapter);
-		*req_value = be32_to_cpu(crq->request_capability_rsp.number);
+		*req_value = be64_to_cpu(crq->request_capability_rsp.number);
 		init_sub_crqs(adapter, 1);
 		return;
 	default:
@@ -2626,12 +2627,12 @@ static void handle_query_cap_rsp(union ibmvnic_crq *crq,
 		break;
 	case MIN_MTU:
 		adapter->min_mtu = be64_to_cpu(crq->query_capability.number);
-		netdev->min_mtu = adapter->min_mtu;
+		netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
 		netdev_dbg(netdev, "min_mtu = %lld\n", adapter->min_mtu);
 		break;
 	case MAX_MTU:
 		adapter->max_mtu = be64_to_cpu(crq->query_capability.number);
-		netdev->max_mtu = adapter->max_mtu;
+		netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
 		netdev_dbg(netdev, "max_mtu = %lld\n", adapter->max_mtu);
 		break;
 	case MAX_MULTICAST_FILTERS:
@@ -2799,9 +2800,9 @@ static ssize_t trace_read(struct file *file, char __user *user_buf, size_t len,
 	crq.collect_fw_trace.correlator = adapter->ras_comps[num].correlator;
 	crq.collect_fw_trace.ioba = cpu_to_be32(trace_tok);
 	crq.collect_fw_trace.len = adapter->ras_comps[num].trace_buff_size;
-	ibmvnic_send_crq(adapter, &crq);
 
 	init_completion(&adapter->fw_done);
+	ibmvnic_send_crq(adapter, &crq);
 	wait_for_completion(&adapter->fw_done);
 
 	if (*ppos + len > be32_to_cpu(adapter->ras_comps[num].trace_buff_size))
@@ -3581,9 +3582,9 @@ static int ibmvnic_dump_show(struct seq_file *seq, void *v)
 	memset(&crq, 0, sizeof(crq));
 	crq.request_dump_size.first = IBMVNIC_CRQ_CMD;
 	crq.request_dump_size.cmd = REQUEST_DUMP_SIZE;
-	ibmvnic_send_crq(adapter, &crq);
 
 	init_completion(&adapter->fw_done);
+	ibmvnic_send_crq(adapter, &crq);
 	wait_for_completion(&adapter->fw_done);
 
 	seq_write(seq, adapter->dump_data, adapter->dump_data_size);
@@ -3629,8 +3630,8 @@ static void handle_crq_init_rsp(struct work_struct *work)
 		}
 	}
 
-	send_version_xchg(adapter);
 	reinit_completion(&adapter->init_done);
+	send_version_xchg(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
 		dev_err(dev, "Passive init timeout\n");
 		goto task_failed;
@@ -3640,9 +3641,9 @@ static void handle_crq_init_rsp(struct work_struct *work)
 		if (adapter->renegotiate) {
 			adapter->renegotiate = false;
 			release_sub_crqs_no_irqs(adapter);
-			send_cap_queries(adapter);
 
 			reinit_completion(&adapter->init_done);
+			send_cap_queries(adapter);
 			if (!wait_for_completion_timeout(&adapter->init_done,
 							 timeout)) {
 				dev_err(dev, "Passive init timeout\n");
@@ -3656,9 +3657,7 @@ static void handle_crq_init_rsp(struct work_struct *work)
 		goto task_failed;
 
 	netdev->real_num_tx_queues = adapter->req_tx_queues;
-	netdev->mtu = adapter->req_mtu;
-	netdev->min_mtu = adapter->min_mtu;
-	netdev->max_mtu = adapter->max_mtu;
+	netdev->mtu = adapter->req_mtu - ETH_HLEN;
 
 	if (adapter->failover) {
 		adapter->failover = false;
@@ -3772,9 +3771,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 			adapter->debugfs_dump = ent;
 		}
 	}
-	ibmvnic_send_crq_init(adapter);
 
 	init_completion(&adapter->init_done);
+	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout))
 		return 0;
 
@@ -3782,9 +3781,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 		if (adapter->renegotiate) {
 			adapter->renegotiate = false;
 			release_sub_crqs_no_irqs(adapter);
-			send_cap_queries(adapter);
 
 			reinit_completion(&adapter->init_done);
+			send_cap_queries(adapter);
 			if (!wait_for_completion_timeout(&adapter->init_done,
 							 timeout))
 				return 0;
@@ -3798,7 +3797,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	}
 
 	netdev->real_num_tx_queues = adapter->req_tx_queues;
-	netdev->mtu = adapter->req_mtu;
+	netdev->mtu = adapter->req_mtu - ETH_HLEN;
 
 	rc = register_netdev(netdev);
 	if (rc) {
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 3dd87889e67e..1c29c86f8709 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2517,7 +2517,7 @@ static int mtk_remove(struct platform_device *pdev)
 }
 
 const struct of_device_id of_mtk_match[] = {
-	{ .compatible = "mediatek,mt7623-eth" },
+	{ .compatible = "mediatek,mt2701-eth" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, of_mtk_match);
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index c7e939945259..53daa6ca5d83 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -158,7 +158,7 @@ static int mlx4_reset_slave(struct mlx4_dev *dev)
 	return -ETIMEDOUT;
 }
 
-static int mlx4_comm_internal_err(u32 slave_read)
+int mlx4_comm_internal_err(u32 slave_read)
 {
 	return (u32)COMM_CHAN_EVENT_INTERNAL_ERR ==
 		(slave_read & (u32)COMM_CHAN_EVENT_INTERNAL_ERR) ? 1 : 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index d9c9f86a30df..9aa422691954 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1099,7 +1099,7 @@ static int mlx4_en_set_ringparam(struct net_device *dev,
 	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
 	new_prof.tx_ring_size = tx_size;
 	new_prof.rx_ring_size = rx_size;
-	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true);
 	if (err)
 		goto out;
 
@@ -1732,8 +1732,6 @@ static void mlx4_en_get_channels(struct net_device *dev,
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 
-	memset(channel, 0, sizeof(*channel));
-
 	channel->max_rx = MAX_RX_RINGS;
 	channel->max_tx = MLX4_EN_MAX_TX_RING_P_UP;
 
@@ -1752,10 +1750,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	int xdp_count;
 	int err = 0;
 
-	if (channel->other_count || channel->combined_count ||
-	    channel->tx_count > MLX4_EN_MAX_TX_RING_P_UP ||
-	    channel->rx_count > MAX_RX_RINGS ||
-	    !channel->tx_count || !channel->rx_count)
+	if (!channel->tx_count || !channel->rx_count)
 		return -EINVAL;
 
 	tmp = kzalloc(sizeof(*tmp), GFP_KERNEL);
@@ -1779,7 +1774,7 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	new_prof.tx_ring_num[TX_XDP] = xdp_count;
 	new_prof.rx_ring_num = channel->rx_count;
 
-	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true);
 	if (err)
 		goto out;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 761f8b12399c..3b4961a8e8e4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2042,6 +2042,8 @@ static void mlx4_en_free_resources(struct mlx4_en_priv *priv)
 			if (priv->tx_cq[t] && priv->tx_cq[t][i])
 				mlx4_en_destroy_cq(priv, &priv->tx_cq[t][i]);
 		}
+		kfree(priv->tx_ring[t]);
+		kfree(priv->tx_cq[t]);
 	}
 
 	for (i = 0; i < priv->rx_ring_num; i++) {
@@ -2184,9 +2186,11 @@ static void mlx4_en_update_priv(struct mlx4_en_priv *dst,
 
 int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
 				struct mlx4_en_priv *tmp,
-				struct mlx4_en_port_profile *prof)
+				struct mlx4_en_port_profile *prof,
+				bool carry_xdp_prog)
 {
-	int t;
+	struct bpf_prog *xdp_prog;
+	int i, t;
 
 	mlx4_en_copy_priv(tmp, priv, prof);
 
@@ -2200,6 +2204,23 @@ int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
 		}
 		return -ENOMEM;
 	}
+
+	/* All rx_rings has the same xdp_prog.  Pick the first one. */
+	xdp_prog = rcu_dereference_protected(
+		priv->rx_ring[0]->xdp_prog,
+		lockdep_is_held(&priv->mdev->state_lock));
+
+	if (xdp_prog && carry_xdp_prog) {
+		xdp_prog = bpf_prog_add(xdp_prog, tmp->rx_ring_num);
+		if (IS_ERR(xdp_prog)) {
+			mlx4_en_free_resources(tmp);
+			return PTR_ERR(xdp_prog);
+		}
+		for (i = 0; i < tmp->rx_ring_num; i++)
+			rcu_assign_pointer(tmp->rx_ring[i]->xdp_prog,
+					   xdp_prog);
+	}
+
 	return 0;
 }
 
@@ -2214,7 +2235,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
-	int t;
 
 	en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port);
 
@@ -2248,11 +2268,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev)
 	mlx4_en_free_resources(priv);
 	mutex_unlock(&mdev->state_lock);
 
-	for (t = 0; t < MLX4_EN_NUM_TX_TYPES; t++) {
-		kfree(priv->tx_ring[t]);
-		kfree(priv->tx_cq[t]);
-	}
-
 	free_netdev(dev);
 }
 
@@ -2755,7 +2770,7 @@ static int mlx4_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 		en_warn(priv, "Reducing the number of TX rings, to not exceed the max total rings number.\n");
 	}
 
-	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, false);
 	if (err) {
 		if (prog)
 			bpf_prog_sub(prog, priv->rx_ring_num - 1);
@@ -3499,7 +3514,7 @@ int mlx4_en_reset_config(struct net_device *dev,
 	memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile));
 	memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config));
 
-	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof);
+	err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true);
 	if (err)
 		goto out;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index eac527e25ec9..cc003fdf0ed9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -514,8 +514,11 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
 		return;
 
 	for (ring = 0; ring < priv->rx_ring_num; ring++) {
-		if (mlx4_en_is_ring_empty(priv->rx_ring[ring]))
+		if (mlx4_en_is_ring_empty(priv->rx_ring[ring])) {
+			local_bh_disable();
 			napi_reschedule(&priv->rx_cq[ring]->napi);
+			local_bh_enable();
+		}
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index 0e8b7c44931f..8258d08acd8c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -222,6 +222,18 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 		return;
 
 	mlx4_stop_catas_poll(dev);
+	if (dev->persist->interface_state & MLX4_INTERFACE_STATE_DELETION &&
+	    mlx4_is_slave(dev)) {
+		/* In mlx4_remove_one on a VF */
+		u32 slave_read =
+			swab32(readl(&mlx4_priv(dev)->mfunc.comm->slave_read));
+
+		if (mlx4_comm_internal_err(slave_read)) {
+			mlx4_dbg(dev, "%s: comm channel is down, entering error state.\n",
+				 __func__);
+			mlx4_enter_error_state(dev->persist);
+		}
+	}
 	mutex_lock(&intf_mutex);
 
 	list_for_each_entry(intf, &intf_list, list)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 88ee7d8a5923..086920b615af 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1220,6 +1220,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type);
 void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type);
 
 void mlx4_enter_error_state(struct mlx4_dev_persistent *persist);
+int mlx4_comm_internal_err(u32 slave_read);
 
 int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
 		    enum mlx4_port_type *type);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index ba1c6cd0cc79..cec59bc264c9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -679,7 +679,8 @@ void mlx4_en_set_stats_bitmap(struct mlx4_dev *dev,
 
 int mlx4_en_try_alloc_resources(struct mlx4_en_priv *priv,
 				struct mlx4_en_priv *tmp,
-				struct mlx4_en_port_profile *prof);
+				struct mlx4_en_port_profile *prof,
+				bool carry_xdp_prog);
 void mlx4_en_safe_replace_resources(struct mlx4_en_priv *priv,
 				    struct mlx4_en_priv *tmp);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 3797cc7c1288..caa837e5e2b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1728,7 +1728,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 	if (cmd->cmdif_rev > CMD_IF_REV) {
 		dev_err(&dev->pdev->dev, "driver does not support command interface version. driver %d, firmware %d\n",
 			CMD_IF_REV, cmd->cmdif_rev);
-		err = -ENOTSUPP;
+		err = -EOPNOTSUPP;
 		goto err_free_page;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 951dbd58594d..d5ecb8f53fd4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -791,7 +791,8 @@ void mlx5e_disable_vlan_filter(struct mlx5e_priv *priv);
 int mlx5e_modify_rqs_vsd(struct mlx5e_priv *priv, bool vsd);
 
 int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz, int ix);
-void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv);
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
+				    enum mlx5e_traffic_types tt);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
@@ -863,12 +864,12 @@ static inline void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv) {}
 
 static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 #else
 int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index f0b460f47f29..0523ed47f597 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -89,7 +89,7 @@ static int mlx5e_dcbnl_ieee_getets(struct net_device *netdev,
 	int i;
 
 	if (!MLX5_CAP_GEN(priv->mdev, ets))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	ets->ets_cap = mlx5_max_tc(priv->mdev) + 1;
 	for (i = 0; i < ets->ets_cap; i++) {
@@ -236,7 +236,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev,
 	int err;
 
 	if (!MLX5_CAP_GEN(priv->mdev, ets))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	err = mlx5e_dbcnl_validate_ets(netdev, ets);
 	if (err)
@@ -402,7 +402,7 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct ieee_ets ets;
 	struct ieee_pfc pfc;
-	int err = -ENOTSUPP;
+	int err = -EOPNOTSUPP;
 	int i;
 
 	if (!MLX5_CAP_GEN(mdev, ets))
@@ -511,6 +511,11 @@ static void mlx5e_dcbnl_getpgtccfgtx(struct net_device *netdev,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 
+	if (!MLX5_CAP_GEN(priv->mdev, ets)) {
+		netdev_err(netdev, "%s, ets is not supported\n", __func__);
+		return;
+	}
+
 	if (priority >= CEE_DCBX_MAX_PRIO) {
 		netdev_err(netdev,
 			   "%s, priority is out of range\n", __func__);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 33a399a8b5d5..bb67863aa361 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -543,7 +543,6 @@ static int mlx5e_set_channels(struct net_device *dev,
 			      struct ethtool_channels *ch)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	int ncv = mlx5e_get_max_num_channels(priv->mdev);
 	unsigned int count = ch->combined_count;
 	bool arfs_enabled;
 	bool was_opened;
@@ -554,16 +553,6 @@ static int mlx5e_set_channels(struct net_device *dev,
 			    __func__);
 		return -EINVAL;
 	}
-	if (ch->rx_count || ch->tx_count) {
-		netdev_info(dev, "%s: separate rx/tx count not supported\n",
-			    __func__);
-		return -EINVAL;
-	}
-	if (count > ncv) {
-		netdev_info(dev, "%s: count (%d) > max (%d)\n",
-			    __func__, count, ncv);
-		return -EINVAL;
-	}
 
 	if (priv->params.num_channels == count)
 		return 0;
@@ -606,7 +595,7 @@ static int mlx5e_get_coalesce(struct net_device *netdev,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
 	if (!MLX5_CAP_GEN(priv->mdev, cq_moderation))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	coal->rx_coalesce_usecs       = priv->params.rx_cq_moderation.usec;
 	coal->rx_max_coalesced_frames = priv->params.rx_cq_moderation.pkts;
@@ -631,7 +620,7 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 	int i;
 
 	if (!MLX5_CAP_GEN(mdev, cq_moderation))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&priv->state_lock);
 
@@ -991,15 +980,18 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 
 static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
-	int i;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int ctxlen = MLX5_ST_SZ_BYTES(tirc);
+	int tt;
 
 	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
-	mlx5e_build_tir_ctx_hash(tirc, priv);
 
-	for (i = 0; i < MLX5E_NUM_INDIR_TIRS; i++)
-		mlx5_core_modify_tir(mdev, priv->indir_tir[i].tirn, in, inlen);
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		memset(tirc, 0, ctxlen);
+		mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
+		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
+	}
 }
 
 static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
@@ -1007,6 +999,7 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
+	bool hash_changed = false;
 	void *in;
 
 	if ((hfunc != ETH_RSS_HASH_NO_CHANGE) &&
@@ -1028,14 +1021,21 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 		mlx5e_redirect_rqt(priv, rqtn, MLX5E_INDIR_RQT_SIZE, 0);
 	}
 
-	if (key)
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE &&
+	    hfunc != priv->params.rss_hfunc) {
+		priv->params.rss_hfunc = hfunc;
+		hash_changed = true;
+	}
+
+	if (key) {
 		memcpy(priv->params.toeplitz_hash_key, key,
 		       sizeof(priv->params.toeplitz_hash_key));
+		hash_changed = hash_changed ||
+			       priv->params.rss_hfunc == ETH_RSS_HASH_TOP;
+	}
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE)
-		priv->params.rss_hfunc = hfunc;
-
-	mlx5e_modify_tirs_hash(priv, in, inlen);
+	if (hash_changed)
+		mlx5e_modify_tirs_hash(priv, in, inlen);
 
 	mutex_unlock(&priv->state_lock);
 
@@ -1307,7 +1307,7 @@ static int mlx5e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	u32 mlx5_wol_mode;
 
 	if (!wol_supported)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (wol->wolopts & ~wol_supported)
 		return -EINVAL;
@@ -1437,7 +1437,7 @@ static int set_pflag_rx_cqe_based_moder(struct net_device *netdev, bool enable)
 
 	if (rx_cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE &&
 	    !MLX5_CAP_GEN(mdev, cq_period_start_from_cqe))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (!rx_mode_changed)
 		return 0;
@@ -1463,7 +1463,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev,
 	bool reset;
 
 	if (!MLX5_CAP_GEN(mdev, cqe_compression))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (enable && priv->tstamp.hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE) {
 		netdev_err(netdev, "Can't enable cqe compression while timestamping is enabled.\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index 1fe80de5d68f..a0e5a69402b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -1089,7 +1089,7 @@ int mlx5e_create_flow_steering(struct mlx5e_priv *priv)
 					       MLX5_FLOW_NAMESPACE_KERNEL);
 
 	if (!priv->fs.ns)
-		return -EINVAL;
+		return -EOPNOTSUPP;
 
 	err = mlx5e_arfs_create_tables(priv);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index d088effd7160..f33f72d0237c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -92,7 +92,7 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
 	ns = mlx5_get_flow_namespace(priv->mdev,
 				     MLX5_FLOW_NAMESPACE_ETHTOOL);
 	if (!ns)
-		return ERR_PTR(-ENOTSUPP);
+		return ERR_PTR(-EOPNOTSUPP);
 
 	table_size = min_t(u32, BIT(MLX5_CAP_FLOWTABLE(priv->mdev,
 						       flow_table_properties_nic_receive.log_max_ft_size)),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2b7dd315020c..f14ca3385fdd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2022,8 +2022,23 @@ static void mlx5e_build_tir_ctx_lro(void *tirc, struct mlx5e_priv *priv)
 	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, priv->params.lro_timeout);
 }
 
-void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv)
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_priv *priv, void *tirc,
+				    enum mlx5e_traffic_types tt)
 {
+	void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
+
+#define MLX5_HASH_IP            (MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP)
+
+#define MLX5_HASH_IP_L4PORTS    (MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP   |\
+				 MLX5_HASH_FIELD_SEL_L4_SPORT |\
+				 MLX5_HASH_FIELD_SEL_L4_DPORT)
+
+#define MLX5_HASH_IP_IPSEC_SPI  (MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP   |\
+				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
+
 	MLX5_SET(tirc, tirc, rx_hash_fn,
 		 mlx5e_rx_hash_fn(priv->params.rss_hfunc));
 	if (priv->params.rss_hfunc == ETH_RSS_HASH_TOP) {
@@ -2035,6 +2050,88 @@ void mlx5e_build_tir_ctx_hash(void *tirc, struct mlx5e_priv *priv)
 		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
 		memcpy(rss_key, priv->params.toeplitz_hash_key, len);
 	}
+
+	switch (tt) {
+	case MLX5E_TT_IPV4_TCP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_TCP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_L4PORTS);
+		break;
+
+	case MLX5E_TT_IPV6_TCP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_TCP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_L4PORTS);
+		break;
+
+	case MLX5E_TT_IPV4_UDP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_UDP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_L4PORTS);
+		break;
+
+	case MLX5E_TT_IPV6_UDP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+			 MLX5_L4_PROT_TYPE_UDP);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_L4PORTS);
+		break;
+
+	case MLX5E_TT_IPV4_IPSEC_AH:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_IPSEC_SPI);
+		break;
+
+	case MLX5E_TT_IPV6_IPSEC_AH:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_IPSEC_SPI);
+		break;
+
+	case MLX5E_TT_IPV4_IPSEC_ESP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_IPSEC_SPI);
+		break;
+
+	case MLX5E_TT_IPV6_IPSEC_ESP:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP_IPSEC_SPI);
+		break;
+
+	case MLX5E_TT_IPV4:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV4);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP);
+		break;
+
+	case MLX5E_TT_IPV6:
+		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+			 MLX5_L3_PROT_TYPE_IPV6);
+		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+			 MLX5_HASH_IP);
+		break;
+	default:
+		WARN_ONCE(true, "%s: bad traffic type!\n", __func__);
+	}
 }
 
 static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv)
@@ -2404,110 +2501,13 @@ void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
 				      enum mlx5e_traffic_types tt)
 {
-	void *hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
-
 	MLX5_SET(tirc, tirc, transport_domain, priv->mdev->mlx5e_res.td.tdn);
 
-#define MLX5_HASH_IP            (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP)
-
-#define MLX5_HASH_IP_L4PORTS    (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP   |\
-				 MLX5_HASH_FIELD_SEL_L4_SPORT |\
-				 MLX5_HASH_FIELD_SEL_L4_DPORT)
-
-#define MLX5_HASH_IP_IPSEC_SPI  (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP   |\
-				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
-
 	mlx5e_build_tir_ctx_lro(tirc, priv);
 
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-	mlx5e_build_tir_ctx_hash(tirc, priv);
-
-	switch (tt) {
-	case MLX5E_TT_IPV4_TCP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_TCP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV6_TCP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_TCP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV4_UDP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_UDP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV6_UDP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_UDP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV4_IPSEC_AH:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV6_IPSEC_AH:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV4_IPSEC_ESP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV6_IPSEC_ESP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
-
-	case MLX5E_TT_IPV4:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP);
-		break;
-
-	case MLX5E_TT_IPV6:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP);
-		break;
-	default:
-		WARN_ONCE(true,
-			  "mlx5e_build_indir_tir_ctx: bad traffic type!\n");
-	}
+	mlx5e_build_indir_tir_ctx_hash(priv, tirc, tt);
 }
 
 static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 *tirc,
@@ -3331,7 +3331,7 @@ static const struct net_device_ops mlx5e_netdev_ops_sriov = {
 static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
 {
 	if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	if (!MLX5_CAP_GEN(mdev, eth_net_offloads) ||
 	    !MLX5_CAP_GEN(mdev, nic_flow_table) ||
 	    !MLX5_CAP_ETH(mdev, csum_cap) ||
@@ -3343,7 +3343,7 @@ static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev)
 			       < 3) {
 		mlx5_core_warn(mdev,
 			       "Not creating net device, some required device capabilities are missing\n");
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 	if (!MLX5_CAP_ETH(mdev, self_lb_en_modifiable))
 		mlx5_core_warn(mdev, "Self loop back prevention is not supported\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 0e2fb3ed1790..06d5e6fecb0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -193,6 +193,9 @@ static inline bool mlx5e_rx_cache_put(struct mlx5e_rq *rq,
 		return false;
 	}
 
+	if (unlikely(page_is_pfmemalloc(dma_info->page)))
+		return false;
+
 	cache->page_cache[cache->tail] = *dma_info;
 	cache->tail = tail_next;
 	return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 46bef6a26a8c..2ebbe80d8126 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -663,6 +663,7 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 				   __be32 *saddr,
 				   int *out_ttl)
 {
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct rtable *rt;
 	struct neighbour *n = NULL;
 	int ttl;
@@ -677,12 +678,11 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 #else
 	return -EOPNOTSUPP;
 #endif
-
-	if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev)) {
-		pr_warn("%s: can't offload, devices not on same HW e-switch\n", __func__);
-		ip_rt_put(rt);
-		return -EOPNOTSUPP;
-	}
+	/* if the egress device isn't on the same HW e-switch, we use the uplink */
+	if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev))
+		*out_dev = mlx5_eswitch_get_uplink_netdev(esw);
+	else
+		*out_dev = rt->dst.dev;
 
 	ttl = ip4_dst_hoplimit(&rt->dst);
 	n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
@@ -693,7 +693,6 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	*out_n = n;
 	*saddr = fl4->saddr;
 	*out_ttl = ttl;
-	*out_dev = rt->dst.dev;
 
 	return 0;
 }
@@ -1088,10 +1087,14 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv,
 
 	mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
 
+	preempt_disable();
+
 	tcf_exts_to_list(f->exts, &actions);
 	list_for_each_entry(a, &actions, list)
 		tcf_action_stats_update(a, bytes, packets, lastuse);
 
+	preempt_enable();
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index f14d9c9ba773..d0c8bf014453 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -133,7 +133,7 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport,
 
 	if (!MLX5_CAP_ESW(dev, vport_cvlan_strip) ||
 	    !MLX5_CAP_ESW(dev, vport_cvlan_insert_if_not_exist))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	esw_debug(dev, "Set Vport[%d] VLAN %d qos %d set=%x\n",
 		  vport, vlan, qos, set_flags);
@@ -353,7 +353,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports)
 	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get FDB flow namespace\n");
-		return -ENOMEM;
+		return -EOPNOTSUPP;
 	}
 
 	flow_group_in = mlx5_vzalloc(inlen);
@@ -962,7 +962,7 @@ static int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch egress flow namespace\n");
-		return -EIO;
+		return -EOPNOTSUPP;
 	}
 
 	flow_group_in = mlx5_vzalloc(inlen);
@@ -1079,7 +1079,7 @@ static int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch ingress flow namespace\n");
-		return -EIO;
+		return -EOPNOTSUPP;
 	}
 
 	flow_group_in = mlx5_vzalloc(inlen);
@@ -1630,7 +1630,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) ||
 	    !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
 		esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	}
 
 	if (!MLX5_CAP_ESW_INGRESS_ACL(esw->dev, ft_support))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 03293ed1cc22..595f7c7383b3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -166,7 +166,7 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
 	return 0;
 
 out_notsupp:
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
@@ -424,6 +424,7 @@ static int esw_create_offloads_fdb_table(struct mlx5_eswitch *esw, int nvports)
 	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get FDB flow namespace\n");
+		err = -EOPNOTSUPP;
 		goto ns_err;
 	}
 
@@ -535,7 +536,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw)
 	ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_OFFLOADS);
 	if (!ns) {
 		esw_warn(esw->dev, "Failed to get offloads flow namespace\n");
-		return -ENOMEM;
+		return -EOPNOTSUPP;
 	}
 
 	ft_offloads = mlx5_create_flow_table(ns, 0, dev->priv.sriov.num_vfs + 2, 0, 0);
@@ -655,7 +656,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw)
 		esw_warn(esw->dev, "Failed setting eswitch to offloads, err %d\n", err);
 		err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
 		if (err1)
-			esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err);
+			esw_warn(esw->dev, "Failed setting eswitch back to legacy, err %d\n", err1);
 	}
 	if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) {
 		if (mlx5_eswitch_inline_mode_get(esw,
@@ -674,9 +675,14 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 	int vport;
 	int err;
 
+	/* disable PF RoCE so missed packets don't go through RoCE steering */
+	mlx5_dev_list_lock();
+	mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+	mlx5_dev_list_unlock();
+
 	err = esw_create_offloads_fdb_table(esw, nvports);
 	if (err)
-		return err;
+		goto create_fdb_err;
 
 	err = esw_create_offloads_table(esw);
 	if (err)
@@ -696,11 +702,6 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
 			goto err_reps;
 	}
 
-	/* disable PF RoCE so missed packets don't go through RoCE steering */
-	mlx5_dev_list_lock();
-	mlx5_remove_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-	mlx5_dev_list_unlock();
-
 	return 0;
 
 err_reps:
@@ -717,6 +718,13 @@ create_fg_err:
 
 create_ft_err:
 	esw_destroy_offloads_fdb_table(esw);
+
+create_fdb_err:
+	/* enable back PF RoCE */
+	mlx5_dev_list_lock();
+	mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+	mlx5_dev_list_unlock();
+
 	return err;
 }
 
@@ -724,11 +732,6 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw)
 {
 	int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
 
-	/* enable back PF RoCE */
-	mlx5_dev_list_lock();
-	mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-	mlx5_dev_list_unlock();
-
 	mlx5_eswitch_disable_sriov(esw);
 	err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
 	if (err) {
@@ -738,6 +741,11 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw)
 			esw_warn(esw->dev, "Failed setting eswitch back to offloads, err %d\n", err);
 	}
 
+	/* enable back PF RoCE */
+	mlx5_dev_list_lock();
+	mlx5_add_dev_by_protocol(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+	mlx5_dev_list_unlock();
+
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index c4478ecd8056..b53fc85a2375 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -322,7 +322,7 @@ int mlx5_cmd_update_fte(struct mlx5_core_dev *dev,
 						flow_table_properties_nic_receive.
 						flow_modify_en);
 	if (!atomic_mod_cap)
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 	opmod = 1;
 
 	return	mlx5_cmd_set_fte(dev, opmod, modify_mask, ft, group_id, fte);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 0ac7a2fc916c..6346a8f5883b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1822,7 +1822,7 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering)
 	struct mlx5_flow_table *ft;
 
 	ns = mlx5_get_flow_namespace(steering->dev, MLX5_FLOW_NAMESPACE_ANCHOR);
-	if (!ns)
+	if (WARN_ON(!ns))
 		return -EINVAL;
 	ft = mlx5_create_flow_table(ns, ANCHOR_PRIO, ANCHOR_SIZE, ANCHOR_LEVEL, 0);
 	if (IS_ERR(ft)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index d01e9f21d469..3c315eb8d270 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -807,7 +807,7 @@ static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
 		return 0;
 	}
 
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index d2ec9d232a70..fd12e0a377a5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -620,7 +620,7 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 	u32 out[MLX5_ST_SZ_DW(qtct_reg)];
 
 	if (!MLX5_CAP_GEN(mdev, ets))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	return mlx5_core_access_reg(mdev, in, inlen, out, sizeof(out),
 				    MLX5_REG_QETCR, 0, 1);
@@ -632,7 +632,7 @@ static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out,
 	u32 in[MLX5_ST_SZ_DW(qtct_reg)];
 
 	if (!MLX5_CAP_GEN(mdev, ets))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	memset(in, 0, sizeof(in));
 	return mlx5_core_access_reg(mdev, in, sizeof(in), out, outlen,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 269e4401c342..7129c30a2ab4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -532,7 +532,7 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
 		return -EACCES;
 	if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	in = mlx5_vzalloc(inlen);
 	if (!in)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 01d0efa9c5c7..9e494a446b7e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1172,7 +1172,8 @@ static int mlxsw_sp_nexthop_mac_update(struct mlxsw_sp *mlxsw_sp, u32 adj_index,
 
 static int
 mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp,
-				  struct mlxsw_sp_nexthop_group *nh_grp)
+				  struct mlxsw_sp_nexthop_group *nh_grp,
+				  bool reallocate)
 {
 	u32 adj_index = nh_grp->adj_index; /* base */
 	struct mlxsw_sp_nexthop *nh;
@@ -1187,7 +1188,7 @@ mlxsw_sp_nexthop_group_mac_update(struct mlxsw_sp *mlxsw_sp,
 			continue;
 		}
 
-		if (nh->update) {
+		if (nh->update || reallocate) {
 			err = mlxsw_sp_nexthop_mac_update(mlxsw_sp,
 							  adj_index, nh);
 			if (err)
@@ -1248,7 +1249,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 		/* Nothing was added or removed, so no need to reallocate. Just
 		 * update MAC on existing adjacency indexes.
 		 */
-		err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp);
+		err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp,
+							false);
 		if (err) {
 			dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
 			goto set_trap;
@@ -1276,7 +1278,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 	nh_grp->adj_index_valid = 1;
 	nh_grp->adj_index = adj_index;
 	nh_grp->ecmp_size = ecmp_size;
-	err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp);
+	err = mlxsw_sp_nexthop_group_mac_update(mlxsw_sp, nh_grp, true);
 	if (err) {
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to update neigh MAC in adjacency table.\n");
 		goto set_trap;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 8e5cb7605b0f..873ce2cd76ba 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -297,7 +297,7 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 		list_del(&p_pkt->list_entry);
 		b_last_packet = list_empty(&p_tx->active_descq);
 		list_add_tail(&p_pkt->list_entry, &p_tx->free_descq);
-		if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO) {
+		if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO) {
 			struct qed_ooo_buffer *p_buffer;
 
 			p_buffer = (struct qed_ooo_buffer *)p_pkt->cookie;
@@ -309,7 +309,7 @@ static void qed_ll2_txq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 			b_last_frag =
 				p_tx->cur_completing_bd_idx == p_pkt->bd_used;
 			tx_frag = p_pkt->bds_set[0].tx_frag;
-			if (p_ll2_conn->gsi_enable)
+			if (p_ll2_conn->conn.gsi_enable)
 				qed_ll2b_release_tx_gsi_packet(p_hwfn,
 							       p_ll2_conn->
 							       my_id,
@@ -378,7 +378,7 @@ static int qed_ll2_txq_completion(struct qed_hwfn *p_hwfn, void *p_cookie)
 
 		spin_unlock_irqrestore(&p_tx->lock, flags);
 		tx_frag = p_pkt->bds_set[0].tx_frag;
-		if (p_ll2_conn->gsi_enable)
+		if (p_ll2_conn->conn.gsi_enable)
 			qed_ll2b_complete_tx_gsi_packet(p_hwfn,
 							p_ll2_conn->my_id,
 							p_pkt->cookie,
@@ -550,7 +550,7 @@ static void qed_ll2_rxq_flush(struct qed_hwfn *p_hwfn, u8 connection_handle)
 
 		list_move_tail(&p_pkt->list_entry, &p_rx->free_descq);
 
-		if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO) {
+		if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO) {
 			struct qed_ooo_buffer *p_buffer;
 
 			p_buffer = (struct qed_ooo_buffer *)p_pkt->cookie;
@@ -738,7 +738,7 @@ qed_ooo_submit_tx_buffers(struct qed_hwfn *p_hwfn,
 		rc = qed_ll2_prepare_tx_packet(p_hwfn, p_ll2_conn->my_id, 1,
 					       p_buffer->vlan, bd_flags,
 					       l4_hdr_offset_w,
-					       p_ll2_conn->tx_dest, 0,
+					       p_ll2_conn->conn.tx_dest, 0,
 					       first_frag,
 					       p_buffer->packet_length,
 					       p_buffer, true);
@@ -858,7 +858,7 @@ qed_ll2_acquire_connection_ooo(struct qed_hwfn *p_hwfn,
 	u16 buf_idx;
 	int rc = 0;
 
-	if (p_ll2_info->conn_type != QED_LL2_TYPE_ISCSI_OOO)
+	if (p_ll2_info->conn.conn_type != QED_LL2_TYPE_ISCSI_OOO)
 		return rc;
 
 	if (!rx_num_ooo_buffers)
@@ -901,7 +901,7 @@ static void
 qed_ll2_establish_connection_ooo(struct qed_hwfn *p_hwfn,
 				 struct qed_ll2_info *p_ll2_conn)
 {
-	if (p_ll2_conn->conn_type != QED_LL2_TYPE_ISCSI_OOO)
+	if (p_ll2_conn->conn.conn_type != QED_LL2_TYPE_ISCSI_OOO)
 		return;
 
 	qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info);
@@ -913,7 +913,7 @@ static void qed_ll2_release_connection_ooo(struct qed_hwfn *p_hwfn,
 {
 	struct qed_ooo_buffer *p_buffer;
 
-	if (p_ll2_conn->conn_type != QED_LL2_TYPE_ISCSI_OOO)
+	if (p_ll2_conn->conn.conn_type != QED_LL2_TYPE_ISCSI_OOO)
 		return;
 
 	qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info);
@@ -945,23 +945,19 @@ static int qed_ll2_start_ooo(struct qed_dev *cdev,
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
 	u8 *handle = &hwfn->pf_params.iscsi_pf_params.ll2_ooo_queue_id;
-	struct qed_ll2_info *ll2_info;
+	struct qed_ll2_conn ll2_info;
 	int rc;
 
-	ll2_info = kzalloc(sizeof(*ll2_info), GFP_KERNEL);
-	if (!ll2_info)
-		return -ENOMEM;
-	ll2_info->conn_type = QED_LL2_TYPE_ISCSI_OOO;
-	ll2_info->mtu = params->mtu;
-	ll2_info->rx_drop_ttl0_flg = params->drop_ttl0_packets;
-	ll2_info->rx_vlan_removal_en = params->rx_vlan_stripping;
-	ll2_info->tx_tc = OOO_LB_TC;
-	ll2_info->tx_dest = CORE_TX_DEST_LB;
-
-	rc = qed_ll2_acquire_connection(hwfn, ll2_info,
+	ll2_info.conn_type = QED_LL2_TYPE_ISCSI_OOO;
+	ll2_info.mtu = params->mtu;
+	ll2_info.rx_drop_ttl0_flg = params->drop_ttl0_packets;
+	ll2_info.rx_vlan_removal_en = params->rx_vlan_stripping;
+	ll2_info.tx_tc = OOO_LB_TC;
+	ll2_info.tx_dest = CORE_TX_DEST_LB;
+
+	rc = qed_ll2_acquire_connection(hwfn, &ll2_info,
 					QED_LL2_RX_SIZE, QED_LL2_TX_SIZE,
 					handle);
-	kfree(ll2_info);
 	if (rc) {
 		DP_INFO(cdev, "Failed to acquire LL2 OOO connection\n");
 		goto out;
@@ -1006,7 +1002,7 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn,
 				     struct qed_ll2_info *p_ll2_conn,
 				     u8 action_on_error)
 {
-	enum qed_ll2_conn_type conn_type = p_ll2_conn->conn_type;
+	enum qed_ll2_conn_type conn_type = p_ll2_conn->conn.conn_type;
 	struct qed_ll2_rx_queue *p_rx = &p_ll2_conn->rx_queue;
 	struct core_rx_start_ramrod_data *p_ramrod = NULL;
 	struct qed_spq_entry *p_ent = NULL;
@@ -1032,7 +1028,7 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn,
 	p_ramrod->sb_index = p_rx->rx_sb_index;
 	p_ramrod->complete_event_flg = 1;
 
-	p_ramrod->mtu = cpu_to_le16(p_ll2_conn->mtu);
+	p_ramrod->mtu = cpu_to_le16(p_ll2_conn->conn.mtu);
 	DMA_REGPAIR_LE(p_ramrod->bd_base,
 		       p_rx->rxq_chain.p_phys_addr);
 	cqe_pbl_size = (u16)qed_chain_get_page_cnt(&p_rx->rcq_chain);
@@ -1040,8 +1036,8 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn,
 	DMA_REGPAIR_LE(p_ramrod->cqe_pbl_addr,
 		       qed_chain_get_pbl_phys(&p_rx->rcq_chain));
 
-	p_ramrod->drop_ttl0_flg = p_ll2_conn->rx_drop_ttl0_flg;
-	p_ramrod->inner_vlan_removal_en = p_ll2_conn->rx_vlan_removal_en;
+	p_ramrod->drop_ttl0_flg = p_ll2_conn->conn.rx_drop_ttl0_flg;
+	p_ramrod->inner_vlan_removal_en = p_ll2_conn->conn.rx_vlan_removal_en;
 	p_ramrod->queue_id = p_ll2_conn->queue_id;
 	p_ramrod->main_func_queue = (conn_type == QED_LL2_TYPE_ISCSI_OOO) ? 0
 									  : 1;
@@ -1056,14 +1052,14 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn,
 	}
 
 	p_ramrod->action_on_error.error_type = action_on_error;
-	p_ramrod->gsi_offload_flag = p_ll2_conn->gsi_enable;
+	p_ramrod->gsi_offload_flag = p_ll2_conn->conn.gsi_enable;
 	return qed_spq_post(p_hwfn, p_ent, NULL);
 }
 
 static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 				     struct qed_ll2_info *p_ll2_conn)
 {
-	enum qed_ll2_conn_type conn_type = p_ll2_conn->conn_type;
+	enum qed_ll2_conn_type conn_type = p_ll2_conn->conn.conn_type;
 	struct qed_ll2_tx_queue *p_tx = &p_ll2_conn->tx_queue;
 	struct core_tx_start_ramrod_data *p_ramrod = NULL;
 	struct qed_spq_entry *p_ent = NULL;
@@ -1075,7 +1071,7 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 	if (!QED_LL2_TX_REGISTERED(p_ll2_conn))
 		return 0;
 
-	if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO)
+	if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO)
 		p_ll2_conn->tx_stats_en = 0;
 	else
 		p_ll2_conn->tx_stats_en = 1;
@@ -1096,7 +1092,7 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 
 	p_ramrod->sb_id = cpu_to_le16(qed_int_get_sp_sb_id(p_hwfn));
 	p_ramrod->sb_index = p_tx->tx_sb_index;
-	p_ramrod->mtu = cpu_to_le16(p_ll2_conn->mtu);
+	p_ramrod->mtu = cpu_to_le16(p_ll2_conn->conn.mtu);
 	p_ramrod->stats_en = p_ll2_conn->tx_stats_en;
 	p_ramrod->stats_id = p_ll2_conn->tx_stats_id;
 
@@ -1106,7 +1102,7 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 	p_ramrod->pbl_size = cpu_to_le16(pbl_size);
 
 	memset(&pq_params, 0, sizeof(pq_params));
-	pq_params.core.tc = p_ll2_conn->tx_tc;
+	pq_params.core.tc = p_ll2_conn->conn.tx_tc;
 	pq_id = qed_get_qm_pq(p_hwfn, PROTOCOLID_CORE, &pq_params);
 	p_ramrod->qm_pq_id = cpu_to_le16(pq_id);
 
@@ -1123,7 +1119,7 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 		DP_NOTICE(p_hwfn, "Unknown connection type: %d\n", conn_type);
 	}
 
-	p_ramrod->gsi_offload_flag = p_ll2_conn->gsi_enable;
+	p_ramrod->gsi_offload_flag = p_ll2_conn->conn.gsi_enable;
 	return qed_spq_post(p_hwfn, p_ent, NULL);
 }
 
@@ -1224,7 +1220,7 @@ qed_ll2_acquire_connection_rx(struct qed_hwfn *p_hwfn,
 
 	DP_VERBOSE(p_hwfn, QED_MSG_LL2,
 		   "Allocated LL2 Rxq [Type %08x] with 0x%08x buffers\n",
-		   p_ll2_info->conn_type, rx_num_desc);
+		   p_ll2_info->conn.conn_type, rx_num_desc);
 
 out:
 	return rc;
@@ -1262,7 +1258,7 @@ static int qed_ll2_acquire_connection_tx(struct qed_hwfn *p_hwfn,
 
 	DP_VERBOSE(p_hwfn, QED_MSG_LL2,
 		   "Allocated LL2 Txq [Type %08x] with 0x%08x buffers\n",
-		   p_ll2_info->conn_type, tx_num_desc);
+		   p_ll2_info->conn.conn_type, tx_num_desc);
 
 out:
 	if (rc)
@@ -1273,7 +1269,7 @@ out:
 }
 
 int qed_ll2_acquire_connection(struct qed_hwfn *p_hwfn,
-			       struct qed_ll2_info *p_params,
+			       struct qed_ll2_conn *p_params,
 			       u16 rx_num_desc,
 			       u16 tx_num_desc,
 			       u8 *p_connection_handle)
@@ -1302,15 +1298,7 @@ int qed_ll2_acquire_connection(struct qed_hwfn *p_hwfn,
 	if (!p_ll2_info)
 		return -EBUSY;
 
-	p_ll2_info->conn_type = p_params->conn_type;
-	p_ll2_info->mtu = p_params->mtu;
-	p_ll2_info->rx_drop_ttl0_flg = p_params->rx_drop_ttl0_flg;
-	p_ll2_info->rx_vlan_removal_en = p_params->rx_vlan_removal_en;
-	p_ll2_info->tx_tc = p_params->tx_tc;
-	p_ll2_info->tx_dest = p_params->tx_dest;
-	p_ll2_info->ai_err_packet_too_big = p_params->ai_err_packet_too_big;
-	p_ll2_info->ai_err_no_buf = p_params->ai_err_no_buf;
-	p_ll2_info->gsi_enable = p_params->gsi_enable;
+	p_ll2_info->conn = *p_params;
 
 	rc = qed_ll2_acquire_connection_rx(p_hwfn, p_ll2_info, rx_num_desc);
 	if (rc)
@@ -1371,9 +1359,9 @@ static int qed_ll2_establish_connection_rx(struct qed_hwfn *p_hwfn,
 
 	SET_FIELD(action_on_error,
 		  CORE_RX_ACTION_ON_ERROR_PACKET_TOO_BIG,
-		  p_ll2_conn->ai_err_packet_too_big);
+		  p_ll2_conn->conn.ai_err_packet_too_big);
 	SET_FIELD(action_on_error,
-		  CORE_RX_ACTION_ON_ERROR_NO_BUFF, p_ll2_conn->ai_err_no_buf);
+		  CORE_RX_ACTION_ON_ERROR_NO_BUFF, p_ll2_conn->conn.ai_err_no_buf);
 
 	return qed_sp_ll2_rx_queue_start(p_hwfn, p_ll2_conn, action_on_error);
 }
@@ -1600,7 +1588,7 @@ static void qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn,
 		   "LL2 [q 0x%02x cid 0x%08x type 0x%08x] Tx Producer at [0x%04x] - set with a %04x bytes %02x BDs buffer at %08x:%08x\n",
 		   p_ll2->queue_id,
 		   p_ll2->cid,
-		   p_ll2->conn_type,
+		   p_ll2->conn.conn_type,
 		   prod_idx,
 		   first_frag_len,
 		   num_of_bds,
@@ -1676,7 +1664,7 @@ static void qed_ll2_tx_packet_notify(struct qed_hwfn *p_hwfn,
 		   (NETIF_MSG_TX_QUEUED | QED_MSG_LL2),
 		   "LL2 [q 0x%02x cid 0x%08x type 0x%08x] Doorbelled [producer 0x%04x]\n",
 		   p_ll2_conn->queue_id,
-		   p_ll2_conn->cid, p_ll2_conn->conn_type, db_msg.spq_prod);
+		   p_ll2_conn->cid, p_ll2_conn->conn.conn_type, db_msg.spq_prod);
 }
 
 int qed_ll2_prepare_tx_packet(struct qed_hwfn *p_hwfn,
@@ -1817,7 +1805,7 @@ int qed_ll2_terminate_connection(struct qed_hwfn *p_hwfn, u8 connection_handle)
 		qed_ll2_rxq_flush(p_hwfn, connection_handle);
 	}
 
-	if (p_ll2_conn->conn_type == QED_LL2_TYPE_ISCSI_OOO)
+	if (p_ll2_conn->conn.conn_type == QED_LL2_TYPE_ISCSI_OOO)
 		qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info);
 
 	return rc;
@@ -1993,7 +1981,7 @@ static void qed_ll2_register_cb_ops(struct qed_dev *cdev,
 
 static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
 {
-	struct qed_ll2_info ll2_info;
+	struct qed_ll2_conn ll2_info;
 	struct qed_ll2_buffer *buffer, *tmp_buffer;
 	enum qed_ll2_conn_type conn_type;
 	struct qed_ptt *p_ptt;
@@ -2041,6 +2029,7 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
 
 	/* Prepare the temporary ll2 information */
 	memset(&ll2_info, 0, sizeof(ll2_info));
+
 	ll2_info.conn_type = conn_type;
 	ll2_info.mtu = params->mtu;
 	ll2_info.rx_drop_ttl0_flg = params->drop_ttl0_packets;
@@ -2120,7 +2109,6 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
 	}
 
 	ether_addr_copy(cdev->ll2_mac_address, params->ll2_mac_address);
-
 	return 0;
 
 release_terminate_all:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
index 6625a3ae5a33..31417928b635 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
@@ -112,15 +112,8 @@ struct qed_ll2_tx_queue {
 	bool b_completing_packet;
 };
 
-struct qed_ll2_info {
-	/* Lock protecting the state of LL2 */
-	struct mutex mutex;
+struct qed_ll2_conn {
 	enum qed_ll2_conn_type conn_type;
-	u32 cid;
-	u8 my_id;
-	u8 queue_id;
-	u8 tx_stats_id;
-	bool b_active;
 	u16 mtu;
 	u8 rx_drop_ttl0_flg;
 	u8 rx_vlan_removal_en;
@@ -128,10 +121,21 @@ struct qed_ll2_info {
 	enum core_tx_dest tx_dest;
 	enum core_error_handle ai_err_packet_too_big;
 	enum core_error_handle ai_err_no_buf;
+	u8 gsi_enable;
+};
+
+struct qed_ll2_info {
+	/* Lock protecting the state of LL2 */
+	struct mutex mutex;
+	struct qed_ll2_conn conn;
+	u32 cid;
+	u8 my_id;
+	u8 queue_id;
+	u8 tx_stats_id;
+	bool b_active;
 	u8 tx_stats_en;
 	struct qed_ll2_rx_queue rx_queue;
 	struct qed_ll2_tx_queue tx_queue;
-	u8 gsi_enable;
 };
 
 /**
@@ -149,7 +153,7 @@ struct qed_ll2_info {
  * @return 0 on success, failure otherwise
  */
 int qed_ll2_acquire_connection(struct qed_hwfn *p_hwfn,
-			       struct qed_ll2_info *p_params,
+			       struct qed_ll2_conn *p_params,
 			       u16 rx_num_desc,
 			       u16 tx_num_desc,
 			       u8 *p_connection_handle);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 2a16547c8966..2dbdb3298991 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -2632,7 +2632,7 @@ static int qed_roce_ll2_start(struct qed_dev *cdev,
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
 	struct qed_roce_ll2_info *roce_ll2;
-	struct qed_ll2_info ll2_params;
+	struct qed_ll2_conn ll2_params;
 	int rc;
 
 	if (!params) {
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 89ac1e3f6175..301f48755093 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -179,6 +179,49 @@ static struct mdiobb_ops bb_ops = {
 	.get_mdio_data = ravb_get_mdio_data,
 };
 
+/* Free TX skb function for AVB-IP */
+static int ravb_tx_free(struct net_device *ndev, int q, bool free_txed_only)
+{
+	struct ravb_private *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &priv->stats[q];
+	struct ravb_tx_desc *desc;
+	int free_num = 0;
+	int entry;
+	u32 size;
+
+	for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) {
+		bool txed;
+
+		entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] *
+					     NUM_TX_DESC);
+		desc = &priv->tx_ring[q][entry];
+		txed = desc->die_dt == DT_FEMPTY;
+		if (free_txed_only && !txed)
+			break;
+		/* Descriptor type must be checked before all other reads */
+		dma_rmb();
+		size = le16_to_cpu(desc->ds_tagl) & TX_DS;
+		/* Free the original skb. */
+		if (priv->tx_skb[q][entry / NUM_TX_DESC]) {
+			dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr),
+					 size, DMA_TO_DEVICE);
+			/* Last packet descriptor? */
+			if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) {
+				entry /= NUM_TX_DESC;
+				dev_kfree_skb_any(priv->tx_skb[q][entry]);
+				priv->tx_skb[q][entry] = NULL;
+				if (txed)
+					stats->tx_packets++;
+			}
+			free_num++;
+		}
+		if (txed)
+			stats->tx_bytes += size;
+		desc->die_dt = DT_EEMPTY;
+	}
+	return free_num;
+}
+
 /* Free skb's and DMA buffers for Ethernet AVB */
 static void ravb_ring_free(struct net_device *ndev, int q)
 {
@@ -194,19 +237,21 @@ static void ravb_ring_free(struct net_device *ndev, int q)
 	kfree(priv->rx_skb[q]);
 	priv->rx_skb[q] = NULL;
 
-	/* Free TX skb ringbuffer */
-	if (priv->tx_skb[q]) {
-		for (i = 0; i < priv->num_tx_ring[q]; i++)
-			dev_kfree_skb(priv->tx_skb[q][i]);
-	}
-	kfree(priv->tx_skb[q]);
-	priv->tx_skb[q] = NULL;
-
 	/* Free aligned TX buffers */
 	kfree(priv->tx_align[q]);
 	priv->tx_align[q] = NULL;
 
 	if (priv->rx_ring[q]) {
+		for (i = 0; i < priv->num_rx_ring[q]; i++) {
+			struct ravb_ex_rx_desc *desc = &priv->rx_ring[q][i];
+
+			if (!dma_mapping_error(ndev->dev.parent,
+					       le32_to_cpu(desc->dptr)))
+				dma_unmap_single(ndev->dev.parent,
+						 le32_to_cpu(desc->dptr),
+						 PKT_BUF_SZ,
+						 DMA_FROM_DEVICE);
+		}
 		ring_size = sizeof(struct ravb_ex_rx_desc) *
 			    (priv->num_rx_ring[q] + 1);
 		dma_free_coherent(ndev->dev.parent, ring_size, priv->rx_ring[q],
@@ -215,12 +260,20 @@ static void ravb_ring_free(struct net_device *ndev, int q)
 	}
 
 	if (priv->tx_ring[q]) {
+		ravb_tx_free(ndev, q, false);
+
 		ring_size = sizeof(struct ravb_tx_desc) *
 			    (priv->num_tx_ring[q] * NUM_TX_DESC + 1);
 		dma_free_coherent(ndev->dev.parent, ring_size, priv->tx_ring[q],
 				  priv->tx_desc_dma[q]);
 		priv->tx_ring[q] = NULL;
 	}
+
+	/* Free TX skb ringbuffer.
+	 * SKBs are freed by ravb_tx_free() call above.
+	 */
+	kfree(priv->tx_skb[q]);
+	priv->tx_skb[q] = NULL;
 }
 
 /* Format skb and descriptor buffer for Ethernet AVB */
@@ -431,44 +484,6 @@ static int ravb_dmac_init(struct net_device *ndev)
 	return 0;
 }
 
-/* Free TX skb function for AVB-IP */
-static int ravb_tx_free(struct net_device *ndev, int q)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-	struct net_device_stats *stats = &priv->stats[q];
-	struct ravb_tx_desc *desc;
-	int free_num = 0;
-	int entry;
-	u32 size;
-
-	for (; priv->cur_tx[q] - priv->dirty_tx[q] > 0; priv->dirty_tx[q]++) {
-		entry = priv->dirty_tx[q] % (priv->num_tx_ring[q] *
-					     NUM_TX_DESC);
-		desc = &priv->tx_ring[q][entry];
-		if (desc->die_dt != DT_FEMPTY)
-			break;
-		/* Descriptor type must be checked before all other reads */
-		dma_rmb();
-		size = le16_to_cpu(desc->ds_tagl) & TX_DS;
-		/* Free the original skb. */
-		if (priv->tx_skb[q][entry / NUM_TX_DESC]) {
-			dma_unmap_single(ndev->dev.parent, le32_to_cpu(desc->dptr),
-					 size, DMA_TO_DEVICE);
-			/* Last packet descriptor? */
-			if (entry % NUM_TX_DESC == NUM_TX_DESC - 1) {
-				entry /= NUM_TX_DESC;
-				dev_kfree_skb_any(priv->tx_skb[q][entry]);
-				priv->tx_skb[q][entry] = NULL;
-				stats->tx_packets++;
-			}
-			free_num++;
-		}
-		stats->tx_bytes += size;
-		desc->die_dt = DT_EEMPTY;
-	}
-	return free_num;
-}
-
 static void ravb_get_tx_tstamp(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
@@ -902,7 +917,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 			spin_lock_irqsave(&priv->lock, flags);
 			/* Clear TX interrupt */
 			ravb_write(ndev, ~mask, TIS);
-			ravb_tx_free(ndev, q);
+			ravb_tx_free(ndev, q, true);
 			netif_wake_subqueue(ndev, q);
 			mmiowb();
 			spin_unlock_irqrestore(&priv->lock, flags);
@@ -1567,7 +1582,8 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	priv->cur_tx[q] += NUM_TX_DESC;
 	if (priv->cur_tx[q] - priv->dirty_tx[q] >
-	    (priv->num_tx_ring[q] - 1) * NUM_TX_DESC && !ravb_tx_free(ndev, q))
+	    (priv->num_tx_ring[q] - 1) * NUM_TX_DESC &&
+	    !ravb_tx_free(ndev, q, true))
 		netif_stop_subqueue(ndev, q);
 
 exit:
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index be3c91c7f211..5484fd726d5a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -305,8 +305,12 @@ static int dwmac1000_irq_status(struct mac_device_info *hw,
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 intr_status = readl(ioaddr + GMAC_INT_STATUS);
+	u32 intr_mask = readl(ioaddr + GMAC_INT_MASK);
 	int ret = 0;
 
+	/* Discard masked bits */
+	intr_status &= ~intr_mask;
+
 	/* Not used events (e.g. MMC interrupts) are not handled. */
 	if ((intr_status & GMAC_INT_STATUS_MMCTIS))
 		x->mmc_tx_irq_n++;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 082cd48db6a7..36942f5a6a53 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -351,6 +351,7 @@ void stmmac_remove_config_dt(struct platform_device *pdev,
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(plat->phy_node);
+	of_node_put(plat->mdio_node);
 }
 #else
 struct plat_stmmacenet_data *
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index b203143647e6..65088224c207 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -3160,7 +3160,7 @@ static int cpsw_resume(struct device *dev)
 {
 	struct platform_device	*pdev = to_platform_device(dev);
 	struct net_device	*ndev = platform_get_drvdata(pdev);
-	struct cpsw_common	*cpsw = netdev_priv(ndev);
+	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
 
 	/* Select default pin state */
 	pinctrl_pm_select_default_state(dev);
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 93dc10b10c09..aa02a03a6d8d 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -100,6 +100,14 @@
 /* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */
 #define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT)
 
+#ifdef __BIG_ENDIAN
+#define xemaclite_readl		ioread32be
+#define xemaclite_writel	iowrite32be
+#else
+#define xemaclite_readl		ioread32
+#define xemaclite_writel	iowrite32
+#endif
+
 /**
  * struct net_local - Our private per device data
  * @ndev:		instance of the network device
@@ -156,15 +164,15 @@ static void xemaclite_enable_interrupts(struct net_local *drvdata)
 	u32 reg_data;
 
 	/* Enable the Tx interrupts for the first Buffer */
-	reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET);
-	__raw_writel(reg_data | XEL_TSR_XMIT_IE_MASK,
-		     drvdata->base_addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data | XEL_TSR_XMIT_IE_MASK,
+			 drvdata->base_addr + XEL_TSR_OFFSET);
 
 	/* Enable the Rx interrupts for the first buffer */
-	__raw_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET);
+	xemaclite_writel(XEL_RSR_RECV_IE_MASK, drvdata->base_addr + XEL_RSR_OFFSET);
 
 	/* Enable the Global Interrupt Enable */
-	__raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
+	xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
 }
 
 /**
@@ -179,17 +187,17 @@ static void xemaclite_disable_interrupts(struct net_local *drvdata)
 	u32 reg_data;
 
 	/* Disable the Global Interrupt Enable */
-	__raw_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
+	xemaclite_writel(XEL_GIER_GIE_MASK, drvdata->base_addr + XEL_GIER_OFFSET);
 
 	/* Disable the Tx interrupts for the first buffer */
-	reg_data = __raw_readl(drvdata->base_addr + XEL_TSR_OFFSET);
-	__raw_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK),
-		     drvdata->base_addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(drvdata->base_addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data & (~XEL_TSR_XMIT_IE_MASK),
+			 drvdata->base_addr + XEL_TSR_OFFSET);
 
 	/* Disable the Rx interrupts for the first buffer */
-	reg_data = __raw_readl(drvdata->base_addr + XEL_RSR_OFFSET);
-	__raw_writel(reg_data & (~XEL_RSR_RECV_IE_MASK),
-		     drvdata->base_addr + XEL_RSR_OFFSET);
+	reg_data = xemaclite_readl(drvdata->base_addr + XEL_RSR_OFFSET);
+	xemaclite_writel(reg_data & (~XEL_RSR_RECV_IE_MASK),
+			 drvdata->base_addr + XEL_RSR_OFFSET);
 }
 
 /**
@@ -321,7 +329,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 		byte_count = ETH_FRAME_LEN;
 
 	/* Check if the expected buffer is available */
-	reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 	if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK |
 	     XEL_TSR_XMIT_ACTIVE_MASK)) == 0) {
 
@@ -334,7 +342,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 
 		addr = (void __iomem __force *)((u32 __force)addr ^
 						 XEL_BUFFER_OFFSET);
-		reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+		reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 
 		if ((reg_data & (XEL_TSR_XMIT_BUSY_MASK |
 		     XEL_TSR_XMIT_ACTIVE_MASK)) != 0)
@@ -345,16 +353,16 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 	/* Write the frame to the buffer */
 	xemaclite_aligned_write(data, (u32 __force *) addr, byte_count);
 
-	__raw_writel((byte_count & XEL_TPLR_LENGTH_MASK),
-		     addr + XEL_TPLR_OFFSET);
+	xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK),
+			 addr + XEL_TPLR_OFFSET);
 
 	/* Update the Tx Status Register to indicate that there is a
 	 * frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which
 	 * is used by the interrupt handler to check whether a frame
 	 * has been transmitted */
-	reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 	reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK);
-	__raw_writel(reg_data, addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET);
 
 	return 0;
 }
@@ -369,7 +377,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
  *
  * Return:	Total number of bytes received
  */
-static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
+static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 {
 	void __iomem *addr;
 	u16 length, proto_type;
@@ -379,7 +387,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
 	addr = (drvdata->base_addr + drvdata->next_rx_buf_to_use);
 
 	/* Verify which buffer has valid data */
-	reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
 
 	if ((reg_data & XEL_RSR_RECV_DONE_MASK) == XEL_RSR_RECV_DONE_MASK) {
 		if (drvdata->rx_ping_pong != 0)
@@ -396,27 +404,28 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
 			return 0;	/* No data was available */
 
 		/* Verify that buffer has valid data */
-		reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+		reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
 		if ((reg_data & XEL_RSR_RECV_DONE_MASK) !=
 		     XEL_RSR_RECV_DONE_MASK)
 			return 0;	/* No data was available */
 	}
 
 	/* Get the protocol type of the ethernet frame that arrived */
-	proto_type = ((ntohl(__raw_readl(addr + XEL_HEADER_OFFSET +
+	proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET +
 			XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) &
 			XEL_RPLR_LENGTH_MASK);
 
 	/* Check if received ethernet frame is a raw ethernet frame
 	 * or an IP packet or an ARP packet */
-	if (proto_type > (ETH_FRAME_LEN + ETH_FCS_LEN)) {
+	if (proto_type > ETH_DATA_LEN) {
 
 		if (proto_type == ETH_P_IP) {
-			length = ((ntohl(__raw_readl(addr +
+			length = ((ntohl(xemaclite_readl(addr +
 					XEL_HEADER_IP_LENGTH_OFFSET +
 					XEL_RXBUFF_OFFSET)) >>
 					XEL_HEADER_SHIFT) &
 					XEL_RPLR_LENGTH_MASK);
+			length = min_t(u16, length, ETH_DATA_LEN);
 			length += ETH_HLEN + ETH_FCS_LEN;
 
 		} else if (proto_type == ETH_P_ARP)
@@ -429,14 +438,17 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data)
 		/* Use the length in the frame, plus the header and trailer */
 		length = proto_type + ETH_HLEN + ETH_FCS_LEN;
 
+	if (WARN_ON(length > maxlen))
+		length = maxlen;
+
 	/* Read from the EmacLite device */
 	xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET),
 				data, length);
 
 	/* Acknowledge the frame */
-	reg_data = __raw_readl(addr + XEL_RSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_RSR_OFFSET);
 	reg_data &= ~XEL_RSR_RECV_DONE_MASK;
-	__raw_writel(reg_data, addr + XEL_RSR_OFFSET);
+	xemaclite_writel(reg_data, addr + XEL_RSR_OFFSET);
 
 	return length;
 }
@@ -463,14 +475,14 @@ static void xemaclite_update_address(struct net_local *drvdata,
 
 	xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN);
 
-	__raw_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
+	xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
 
 	/* Update the MAC address in the EmacLite */
-	reg_data = __raw_readl(addr + XEL_TSR_OFFSET);
-	__raw_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET);
+	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
+	xemaclite_writel(reg_data | XEL_TSR_PROG_MAC_ADDR, addr + XEL_TSR_OFFSET);
 
 	/* Wait for EmacLite to finish with the MAC address update */
-	while ((__raw_readl(addr + XEL_TSR_OFFSET) &
+	while ((xemaclite_readl(addr + XEL_TSR_OFFSET) &
 		XEL_TSR_PROG_MAC_ADDR) != 0)
 		;
 }
@@ -603,7 +615,7 @@ static void xemaclite_rx_handler(struct net_device *dev)
 
 	skb_reserve(skb, 2);
 
-	len = xemaclite_recv_data(lp, (u8 *) skb->data);
+	len = xemaclite_recv_data(lp, (u8 *) skb->data, len);
 
 	if (!len) {
 		dev->stats.rx_errors++;
@@ -640,32 +652,32 @@ static irqreturn_t xemaclite_interrupt(int irq, void *dev_id)
 	u32 tx_status;
 
 	/* Check if there is Rx Data available */
-	if ((__raw_readl(base_addr + XEL_RSR_OFFSET) &
+	if ((xemaclite_readl(base_addr + XEL_RSR_OFFSET) &
 			 XEL_RSR_RECV_DONE_MASK) ||
-	    (__raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET)
+	    (xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_RSR_OFFSET)
 			 & XEL_RSR_RECV_DONE_MASK))
 
 		xemaclite_rx_handler(dev);
 
 	/* Check if the Transmission for the first buffer is completed */
-	tx_status = __raw_readl(base_addr + XEL_TSR_OFFSET);
+	tx_status = xemaclite_readl(base_addr + XEL_TSR_OFFSET);
 	if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) &&
 		(tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) {
 
 		tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
-		__raw_writel(tx_status, base_addr + XEL_TSR_OFFSET);
+		xemaclite_writel(tx_status, base_addr + XEL_TSR_OFFSET);
 
 		tx_complete = true;
 	}
 
 	/* Check if the Transmission for the second buffer is completed */
-	tx_status = __raw_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
+	tx_status = xemaclite_readl(base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
 	if (((tx_status & XEL_TSR_XMIT_BUSY_MASK) == 0) &&
 		(tx_status & XEL_TSR_XMIT_ACTIVE_MASK) != 0) {
 
 		tx_status &= ~XEL_TSR_XMIT_ACTIVE_MASK;
-		__raw_writel(tx_status, base_addr + XEL_BUFFER_OFFSET +
-			     XEL_TSR_OFFSET);
+		xemaclite_writel(tx_status, base_addr + XEL_BUFFER_OFFSET +
+				 XEL_TSR_OFFSET);
 
 		tx_complete = true;
 	}
@@ -698,7 +710,7 @@ static int xemaclite_mdio_wait(struct net_local *lp)
 	/* wait for the MDIO interface to not be busy or timeout
 	   after some time.
 	*/
-	while (__raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
+	while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
 			XEL_MDIOCTRL_MDIOSTS_MASK) {
 		if (time_before_eq(end, jiffies)) {
 			WARN_ON(1);
@@ -734,17 +746,17 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 	 * MDIO Address register. Set the Status bit in the MDIO Control
 	 * register to start a MDIO read transaction.
 	 */
-	ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
-	__raw_writel(XEL_MDIOADDR_OP_MASK |
-		     ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
-		     lp->base_addr + XEL_MDIOADDR_OFFSET);
-	__raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
-		     lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	xemaclite_writel(XEL_MDIOADDR_OP_MASK |
+			 ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
+			 lp->base_addr + XEL_MDIOADDR_OFFSET);
+	xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
+			 lp->base_addr + XEL_MDIOCTRL_OFFSET);
 
 	if (xemaclite_mdio_wait(lp))
 		return -ETIMEDOUT;
 
-	rc = __raw_readl(lp->base_addr + XEL_MDIORD_OFFSET);
+	rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET);
 
 	dev_dbg(&lp->ndev->dev,
 		"xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
@@ -781,13 +793,13 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
 	 * Data register. Finally, set the Status bit in the MDIO Control
 	 * register to start a MDIO write transaction.
 	 */
-	ctrl_reg = __raw_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
-	__raw_writel(~XEL_MDIOADDR_OP_MASK &
-		     ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
-		     lp->base_addr + XEL_MDIOADDR_OFFSET);
-	__raw_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET);
-	__raw_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
-		     lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	ctrl_reg = xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	xemaclite_writel(~XEL_MDIOADDR_OP_MASK &
+			 ((phy_id << XEL_MDIOADDR_PHYADR_SHIFT) | reg),
+			 lp->base_addr + XEL_MDIOADDR_OFFSET);
+	xemaclite_writel(val, lp->base_addr + XEL_MDIOWR_OFFSET);
+	xemaclite_writel(ctrl_reg | XEL_MDIOCTRL_MDIOSTS_MASK,
+			 lp->base_addr + XEL_MDIOCTRL_OFFSET);
 
 	return 0;
 }
@@ -834,8 +846,8 @@ static int xemaclite_mdio_setup(struct net_local *lp, struct device *dev)
 	/* Enable the MDIO bus by asserting the enable bit in MDIO Control
 	 * register.
 	 */
-	__raw_writel(XEL_MDIOCTRL_MDIOEN_MASK,
-		     lp->base_addr + XEL_MDIOCTRL_OFFSET);
+	xemaclite_writel(XEL_MDIOCTRL_MDIOEN_MASK,
+			 lp->base_addr + XEL_MDIOCTRL_OFFSET);
 
 	bus = mdiobus_alloc();
 	if (!bus) {
@@ -1140,8 +1152,8 @@ static int xemaclite_of_probe(struct platform_device *ofdev)
 	}
 
 	/* Clear the Tx CSR's in case this is a restart */
-	__raw_writel(0, lp->base_addr + XEL_TSR_OFFSET);
-	__raw_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
+	xemaclite_writel(0, lp->base_addr + XEL_TSR_OFFSET);
+	xemaclite_writel(0, lp->base_addr + XEL_BUFFER_OFFSET + XEL_TSR_OFFSET);
 
 	/* Set the MAC address in the EmacLite device */
 	xemaclite_update_address(lp, ndev->dev_addr);
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 8b6810bad54b..99d3df788ce8 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -69,7 +69,6 @@ struct gtp_dev {
 	struct socket		*sock0;
 	struct socket		*sock1u;
 
-	struct net		*net;
 	struct net_device	*dev;
 
 	unsigned int		hash_size;
@@ -316,7 +315,7 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
 
 	netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk);
 
-	xnet = !net_eq(gtp->net, dev_net(gtp->dev));
+	xnet = !net_eq(sock_net(sk), dev_net(gtp->dev));
 
 	switch (udp_sk(sk)->encap_type) {
 	case UDP_ENCAP_GTP0:
@@ -612,7 +611,7 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 				    pktinfo.fl4.saddr, pktinfo.fl4.daddr,
 				    pktinfo.iph->tos,
 				    ip4_dst_hoplimit(&pktinfo.rt->dst),
-				    htons(IP_DF),
+				    0,
 				    pktinfo.gtph_port, pktinfo.gtph_port,
 				    true, false);
 		break;
@@ -658,7 +657,7 @@ static void gtp_link_setup(struct net_device *dev)
 static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
 static void gtp_hashtable_free(struct gtp_dev *gtp);
 static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
-			    int fd_gtp0, int fd_gtp1, struct net *src_net);
+			    int fd_gtp0, int fd_gtp1);
 
 static int gtp_newlink(struct net *src_net, struct net_device *dev,
 			struct nlattr *tb[], struct nlattr *data[])
@@ -675,7 +674,7 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev,
 	fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
 	fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
 
-	err = gtp_encap_enable(dev, gtp, fd0, fd1, src_net);
+	err = gtp_encap_enable(dev, gtp, fd0, fd1);
 	if (err < 0)
 		goto out_err;
 
@@ -821,7 +820,7 @@ static void gtp_hashtable_free(struct gtp_dev *gtp)
 }
 
 static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
-			    int fd_gtp0, int fd_gtp1, struct net *src_net)
+			    int fd_gtp0, int fd_gtp1)
 {
 	struct udp_tunnel_sock_cfg tuncfg = {NULL};
 	struct socket *sock0, *sock1u;
@@ -858,7 +857,6 @@ static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
 
 	gtp->sock0 = sock0;
 	gtp->sock1u = sock1u;
-	gtp->net = src_net;
 
 	tuncfg.sk_user_data = gtp;
 	tuncfg.encap_rcv = gtp_encap_recv;
@@ -1376,3 +1374,4 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Harald Welte <hwelte@sysmocom.de>");
 MODULE_DESCRIPTION("Interface driver for GTP encapsulated traffic");
 MODULE_ALIAS_RTNL_LINK("gtp");
+MODULE_ALIAS_GENL_FAMILY("gtp");
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index ece59c54a653..4a40a3d825b4 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -648,8 +648,8 @@ static void ax_setup(struct net_device *dev)
 {
 	/* Finish setting up the DEVICE info. */
 	dev->mtu             = AX_MTU;
-	dev->hard_header_len = 0;
-	dev->addr_len        = 0;
+	dev->hard_header_len = AX25_MAX_HEADER_LEN;
+	dev->addr_len        = AX25_ADDR_LEN;
 	dev->type            = ARPHRD_AX25;
 	dev->tx_queue_len    = 10;
 	dev->header_ops      = &ax25_header_ops;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 5a1cc089acb7..86e5749226ef 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -1295,6 +1295,9 @@ void netvsc_channel_cb(void *context)
 	ndev = hv_get_drvdata(device);
 	buffer = get_per_channel_state(channel);
 
+	/* commit_rd_index() -> hv_signal_on_read() needs this. */
+	init_cached_read_index(channel);
+
 	do {
 		desc = get_next_pkt_raw(channel);
 		if (desc != NULL) {
@@ -1347,6 +1350,9 @@ void netvsc_channel_cb(void *context)
 
 			bufferlen = bytes_recvd;
 		}
+
+		init_cached_read_index(channel);
+
 	} while (1);
 
 	if (bufferlen > NETVSC_PACKET_SIZE)
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 1e05b7c2d157..0844f8496413 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -164,6 +164,7 @@ static void loopback_setup(struct net_device *dev)
 {
 	dev->mtu		= 64 * 1024;
 	dev->hard_header_len	= ETH_HLEN;	/* 14	*/
+	dev->min_header_len	= ETH_HLEN;	/* 14	*/
 	dev->addr_len		= ETH_ALEN;	/* 6	*/
 	dev->type		= ARPHRD_LOOPBACK;	/* 0x0001*/
 	dev->flags		= IFF_LOOPBACK;
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 5c26653eceb5..c27011bbe30c 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -681,7 +681,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, struct msghdr *m,
 	size_t linear;
 
 	if (q->flags & IFF_VNET_HDR) {
-		vnet_hdr_len = q->vnet_hdr_sz;
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 
 		err = -EINVAL;
 		if (len < vnet_hdr_len)
@@ -820,12 +820,12 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
 
 	if (q->flags & IFF_VNET_HDR) {
 		struct virtio_net_hdr vnet_hdr;
-		vnet_hdr_len = q->vnet_hdr_sz;
+		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 		if (iov_iter_count(iter) < vnet_hdr_len)
 			return -EINVAL;
 
 		if (virtio_net_hdr_from_skb(skb, &vnet_hdr,
-					    macvtap_is_little_endian(q)))
+					    macvtap_is_little_endian(q), true))
 			BUG();
 
 		if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
index e741bf614c4e..b0492ef2cdaa 100644
--- a/drivers/net/phy/bcm63xx.c
+++ b/drivers/net/phy/bcm63xx.c
@@ -21,6 +21,23 @@ MODULE_DESCRIPTION("Broadcom 63xx internal PHY driver");
 MODULE_AUTHOR("Maxime Bizon <mbizon@freebox.fr>");
 MODULE_LICENSE("GPL");
 
+static int bcm63xx_config_intr(struct phy_device *phydev)
+{
+	int reg, err;
+
+	reg = phy_read(phydev, MII_BCM63XX_IR);
+	if (reg < 0)
+		return reg;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+		reg &= ~MII_BCM63XX_IR_GMASK;
+	else
+		reg |= MII_BCM63XX_IR_GMASK;
+
+	err = phy_write(phydev, MII_BCM63XX_IR, reg);
+	return err;
+}
+
 static int bcm63xx_config_init(struct phy_device *phydev)
 {
 	int reg, err;
@@ -55,7 +72,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= bcm_phy_ack_intr,
-	.config_intr	= bcm_phy_config_intr,
+	.config_intr	= bcm63xx_config_intr,
 }, {
 	/* same phy as above, with just a different OUI */
 	.phy_id		= 0x002bdc00,
@@ -67,7 +84,7 @@ static struct phy_driver bcm63xx_driver[] = {
 	.config_aneg	= genphy_config_aneg,
 	.read_status	= genphy_read_status,
 	.ack_interrupt	= bcm_phy_ack_intr,
-	.config_intr	= bcm_phy_config_intr,
+	.config_intr	= bcm63xx_config_intr,
 } };
 
 module_phy_driver(bcm63xx_driver);
diff --git a/drivers/net/phy/dp83848.c b/drivers/net/phy/dp83848.c
index 800b39f06279..a10d0e7fc5f7 100644
--- a/drivers/net/phy/dp83848.c
+++ b/drivers/net/phy/dp83848.c
@@ -17,6 +17,7 @@
 #include <linux/phy.h>
 
 #define TI_DP83848C_PHY_ID		0x20005ca0
+#define TI_DP83620_PHY_ID		0x20005ce0
 #define NS_DP83848C_PHY_ID		0x20005c90
 #define TLK10X_PHY_ID			0x2000a210
 #define TI_DP83822_PHY_ID		0x2000a240
@@ -77,6 +78,7 @@ static int dp83848_config_intr(struct phy_device *phydev)
 static struct mdio_device_id __maybe_unused dp83848_tbl[] = {
 	{ TI_DP83848C_PHY_ID, 0xfffffff0 },
 	{ NS_DP83848C_PHY_ID, 0xfffffff0 },
+	{ TI_DP83620_PHY_ID, 0xfffffff0 },
 	{ TLK10X_PHY_ID, 0xfffffff0 },
 	{ TI_DP83822_PHY_ID, 0xfffffff0 },
 	{ }
@@ -106,6 +108,7 @@ MODULE_DEVICE_TABLE(mdio, dp83848_tbl);
 static struct phy_driver dp83848_driver[] = {
 	DP83848_PHY_DRIVER(TI_DP83848C_PHY_ID, "TI DP83848C 10/100 Mbps PHY"),
 	DP83848_PHY_DRIVER(NS_DP83848C_PHY_ID, "NS DP83848C 10/100 Mbps PHY"),
+	DP83848_PHY_DRIVER(TI_DP83620_PHY_ID, "TI DP83620 10/100 Mbps PHY"),
 	DP83848_PHY_DRIVER(TLK10X_PHY_ID, "TI TLK10X 10/100 Mbps PHY"),
 	DP83848_PHY_DRIVER(TI_DP83822_PHY_ID, "TI DP83822 10/100 Mbps PHY"),
 };
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 0b78210c0fa7..ed0d235cf850 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1679,6 +1679,8 @@ static struct phy_driver marvell_drivers[] = {
 		.ack_interrupt = &marvell_ack_interrupt,
 		.config_intr = &marvell_config_intr,
 		.did_interrupt = &m88e1121_did_interrupt,
+		.get_wol = &m88e1318_get_wol,
+		.set_wol = &m88e1318_set_wol,
 		.resume = &marvell_resume,
 		.suspend = &marvell_suspend,
 		.get_sset_count = marvell_get_sset_count,
diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c
index c0b4e65267af..46fe1ae919a3 100644
--- a/drivers/net/phy/mdio-bcm-iproc.c
+++ b/drivers/net/phy/mdio-bcm-iproc.c
@@ -81,8 +81,6 @@ static int iproc_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 	if (rc)
 		return rc;
 
-	iproc_mdio_config_clk(priv->base);
-
 	/* Prepare the read operation */
 	cmd = (MII_DATA_TA_VAL << MII_DATA_TA_SHIFT) |
 		(reg << MII_DATA_RA_SHIFT) |
@@ -112,8 +110,6 @@ static int iproc_mdio_write(struct mii_bus *bus, int phy_id,
 	if (rc)
 		return rc;
 
-	iproc_mdio_config_clk(priv->base);
-
 	/* Prepare the write operation */
 	cmd = (MII_DATA_TA_VAL << MII_DATA_TA_SHIFT) |
 		(reg << MII_DATA_RA_SHIFT) |
@@ -163,6 +159,8 @@ static int iproc_mdio_probe(struct platform_device *pdev)
 	bus->read = iproc_mdio_read;
 	bus->write = iproc_mdio_write;
 
+	iproc_mdio_config_clk(priv->base);
+
 	rc = of_mdiobus_register(bus, pdev->dev.of_node);
 	if (rc) {
 		dev_err(&pdev->dev, "MDIO bus registration failed\n");
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 9a77289109b7..6742070ca676 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1008,6 +1008,20 @@ static struct phy_driver ksphy_driver[] = {
 	.get_stats	= kszphy_get_stats,
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
+}, {
+	.phy_id		= PHY_ID_KSZ8795,
+	.phy_id_mask	= MICREL_PHY_ID_MASK,
+	.name		= "Micrel KSZ8795",
+	.features	= PHY_BASIC_FEATURES,
+	.flags		= PHY_HAS_MAGICANEG | PHY_HAS_INTERRUPT,
+	.config_init	= kszphy_config_init,
+	.config_aneg	= ksz8873mll_config_aneg,
+	.read_status	= ksz8873mll_read_status,
+	.get_sset_count = kszphy_get_sset_count,
+	.get_strings	= kszphy_get_strings,
+	.get_stats	= kszphy_get_stats,
+	.suspend	= genphy_suspend,
+	.resume		= genphy_resume,
 } };
 
 module_phy_driver(ksphy_driver);
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 48da6e93c3f7..7cc1b7dcfe05 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -29,6 +29,7 @@
 #include <linux/mii.h>
 #include <linux/ethtool.h>
 #include <linux/phy.h>
+#include <linux/phy_led_triggers.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/mdio.h>
@@ -649,14 +650,18 @@ void phy_start_machine(struct phy_device *phydev)
  * phy_trigger_machine - trigger the state machine to run
  *
  * @phydev: the phy_device struct
+ * @sync: indicate whether we should wait for the workqueue cancelation
  *
  * Description: There has been a change in state which requires that the
  *   state machine runs.
  */
 
-static void phy_trigger_machine(struct phy_device *phydev)
+static void phy_trigger_machine(struct phy_device *phydev, bool sync)
 {
-	cancel_delayed_work_sync(&phydev->state_queue);
+	if (sync)
+		cancel_delayed_work_sync(&phydev->state_queue);
+	else
+		cancel_delayed_work(&phydev->state_queue);
 	queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
 }
 
@@ -693,7 +698,7 @@ static void phy_error(struct phy_device *phydev)
 	phydev->state = PHY_HALTED;
 	mutex_unlock(&phydev->lock);
 
-	phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev, false);
 }
 
 /**
@@ -840,7 +845,7 @@ void phy_change(struct phy_device *phydev)
 	}
 
 	/* reschedule state queue work to run as soon as possible */
-	phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev, true);
 	return;
 
 ignore:
@@ -942,7 +947,7 @@ void phy_start(struct phy_device *phydev)
 	if (do_resume)
 		phy_resume(phydev);
 
-	phy_trigger_machine(phydev);
+	phy_trigger_machine(phydev, true);
 }
 EXPORT_SYMBOL(phy_start);
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 92b08383cafa..8c8e15b8739d 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -908,6 +908,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	struct module *ndev_owner = dev->dev.parent->driver->owner;
 	struct mii_bus *bus = phydev->mdio.bus;
 	struct device *d = &phydev->mdio.dev;
+	bool using_genphy = false;
 	int err;
 
 	/* For Ethernet device drivers that register their own MDIO bus, we
@@ -933,12 +934,22 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 			d->driver =
 				&genphy_driver[GENPHY_DRV_1G].mdiodrv.driver;
 
+		using_genphy = true;
+	}
+
+	if (!try_module_get(d->driver->owner)) {
+		dev_err(&dev->dev, "failed to get the device driver module\n");
+		err = -EIO;
+		goto error_put_device;
+	}
+
+	if (using_genphy) {
 		err = d->driver->probe(d);
 		if (err >= 0)
 			err = device_bind_driver(d);
 
 		if (err)
-			goto error;
+			goto error_module_put;
 	}
 
 	if (phydev->attached_dev) {
@@ -975,7 +986,13 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	return err;
 
 error:
+	/* phy_detach() does all of the cleanup below */
 	phy_detach(phydev);
+	return err;
+
+error_module_put:
+	module_put(d->driver->owner);
+error_put_device:
 	put_device(d);
 	if (ndev_owner != bus->owner)
 		module_put(bus->owner);
@@ -1039,6 +1056,8 @@ void phy_detach(struct phy_device *phydev)
 
 	phy_led_triggers_unregister(phydev);
 
+	module_put(phydev->mdio.dev.driver->owner);
+
 	/* If the device had no specific driver before (i.e. - it
 	 * was using the generic driver), we unbind the device
 	 * from the generic driver so that there's a chance a
diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c
index fa62bdf2f526..94ca42e630bb 100644
--- a/drivers/net/phy/phy_led_triggers.c
+++ b/drivers/net/phy/phy_led_triggers.c
@@ -12,6 +12,7 @@
  */
 #include <linux/leds.h>
 #include <linux/phy.h>
+#include <linux/phy_led_triggers.h>
 #include <linux/netdevice.h>
 
 static struct phy_led_trigger *phy_speed_to_led_trigger(struct phy_device *phy,
@@ -102,8 +103,10 @@ int phy_led_triggers_register(struct phy_device *phy)
 					    sizeof(struct phy_led_trigger) *
 						   phy->phy_num_led_triggers,
 					    GFP_KERNEL);
-	if (!phy->phy_led_triggers)
-		return -ENOMEM;
+	if (!phy->phy_led_triggers) {
+		err = -ENOMEM;
+		goto out_clear;
+	}
 
 	for (i = 0; i < phy->phy_num_led_triggers; i++) {
 		err = phy_led_trigger_register(phy, &phy->phy_led_triggers[i],
@@ -120,6 +123,8 @@ out_unreg:
 	while (i--)
 		phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
 	devm_kfree(&phy->mdio.dev, phy->phy_led_triggers);
+out_clear:
+	phy->phy_num_led_triggers = 0;
 	return err;
 }
 EXPORT_SYMBOL_GPL(phy_led_triggers_register);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index cd8e02c94be0..bfabe180053e 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1170,9 +1170,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	}
 
 	if (tun->flags & IFF_VNET_HDR) {
-		if (len < tun->vnet_hdr_sz)
+		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
+
+		if (len < vnet_hdr_sz)
 			return -EINVAL;
-		len -= tun->vnet_hdr_sz;
+		len -= vnet_hdr_sz;
 
 		if (!copy_from_iter_full(&gso, sizeof(gso), from))
 			return -EFAULT;
@@ -1183,7 +1185,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 		if (tun16_to_cpu(tun, gso.hdr_len) > len)
 			return -EINVAL;
-		iov_iter_advance(from, tun->vnet_hdr_sz - sizeof(gso));
+		iov_iter_advance(from, vnet_hdr_sz - sizeof(gso));
 	}
 
 	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
@@ -1335,7 +1337,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 		vlan_hlen = VLAN_HLEN;
 
 	if (tun->flags & IFF_VNET_HDR)
-		vnet_hdr_sz = tun->vnet_hdr_sz;
+		vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
 
 	total = skb->len + vlan_hlen + vnet_hdr_sz;
 
@@ -1360,7 +1362,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 			return -EINVAL;
 
 		if (virtio_net_hdr_from_skb(skb, &gso,
-					    tun_is_little_endian(tun))) {
+					    tun_is_little_endian(tun), true)) {
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
 			pr_err("unexpected GSO type: "
 			       "0x%x, gso_size %d, hdr_len %d\n",
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index 3daa41bdd4ea..0acc9b640419 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -776,7 +776,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	struct net_device *netdev;
 	struct catc *catc;
 	u8 broadcast[ETH_ALEN];
-	int i, pktsz;
+	int pktsz, ret;
 
 	if (usb_set_interface(usbdev,
 			intf->altsetting->desc.bInterfaceNumber, 1)) {
@@ -811,12 +811,8 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	if ((!catc->ctrl_urb) || (!catc->tx_urb) || 
 	    (!catc->rx_urb) || (!catc->irq_urb)) {
 		dev_err(&intf->dev, "No free urbs available.\n");
-		usb_free_urb(catc->ctrl_urb);
-		usb_free_urb(catc->tx_urb);
-		usb_free_urb(catc->rx_urb);
-		usb_free_urb(catc->irq_urb);
-		free_netdev(netdev);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto fail_free;
 	}
 
 	/* The F5U011 has the same vendor/product as the netmate but a device version of 0x130 */
@@ -844,15 +840,24 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
                 catc->irq_buf, 2, catc_irq_done, catc, 1);
 
 	if (!catc->is_f5u011) {
+		u32 *buf;
+		int i;
+
 		dev_dbg(dev, "Checking memory size\n");
 
-		i = 0x12345678;
-		catc_write_mem(catc, 0x7a80, &i, 4);
-		i = 0x87654321;	
-		catc_write_mem(catc, 0xfa80, &i, 4);
-		catc_read_mem(catc, 0x7a80, &i, 4);
+		buf = kmalloc(4, GFP_KERNEL);
+		if (!buf) {
+			ret = -ENOMEM;
+			goto fail_free;
+		}
+
+		*buf = 0x12345678;
+		catc_write_mem(catc, 0x7a80, buf, 4);
+		*buf = 0x87654321;
+		catc_write_mem(catc, 0xfa80, buf, 4);
+		catc_read_mem(catc, 0x7a80, buf, 4);
 	  
-		switch (i) {
+		switch (*buf) {
 		case 0x12345678:
 			catc_set_reg(catc, TxBufCount, 8);
 			catc_set_reg(catc, RxBufCount, 32);
@@ -867,6 +872,8 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 			dev_dbg(dev, "32k Memory\n");
 			break;
 		}
+
+		kfree(buf);
 	  
 		dev_dbg(dev, "Getting MAC from SEEROM.\n");
 	  
@@ -913,16 +920,21 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 	usb_set_intfdata(intf, catc);
 
 	SET_NETDEV_DEV(netdev, &intf->dev);
-	if (register_netdev(netdev) != 0) {
-		usb_set_intfdata(intf, NULL);
-		usb_free_urb(catc->ctrl_urb);
-		usb_free_urb(catc->tx_urb);
-		usb_free_urb(catc->rx_urb);
-		usb_free_urb(catc->irq_urb);
-		free_netdev(netdev);
-		return -EIO;
-	}
+	ret = register_netdev(netdev);
+	if (ret)
+		goto fail_clear_intfdata;
+
 	return 0;
+
+fail_clear_intfdata:
+	usb_set_intfdata(intf, NULL);
+fail_free:
+	usb_free_urb(catc->ctrl_urb);
+	usb_free_urb(catc->tx_urb);
+	usb_free_urb(catc->rx_urb);
+	usb_free_urb(catc->irq_urb);
+	free_netdev(netdev);
+	return ret;
 }
 
 static void catc_disconnect(struct usb_interface *intf)
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index fe7b2886cb6b..86144f9a80ee 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -531,6 +531,7 @@ static const struct driver_info wwan_info = {
 #define SAMSUNG_VENDOR_ID	0x04e8
 #define LENOVO_VENDOR_ID	0x17ef
 #define NVIDIA_VENDOR_ID	0x0955
+#define HP_VENDOR_ID		0x03f0
 
 static const struct usb_device_id	products[] = {
 /* BLACKLIST !!
@@ -677,6 +678,13 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* HP lt2523 (Novatel E371) - handled by qmi_wwan */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(HP_VENDOR_ID, 0x421d, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* AnyDATA ADU960S - handled by qmi_wwan */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(0x16d5, 0x650a, USB_CLASS_COMM,
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 24e803fe9a53..36674484c6fb 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -126,40 +126,61 @@ static void async_ctrl_callback(struct urb *urb)
 
 static int get_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data)
 {
+	u8 *buf;
 	int ret;
 
+	buf = kmalloc(size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
 	ret = usb_control_msg(pegasus->usb, usb_rcvctrlpipe(pegasus->usb, 0),
 			      PEGASUS_REQ_GET_REGS, PEGASUS_REQT_READ, 0,
-			      indx, data, size, 1000);
+			      indx, buf, size, 1000);
 	if (ret < 0)
 		netif_dbg(pegasus, drv, pegasus->net,
 			  "%s returned %d\n", __func__, ret);
+	else if (ret <= size)
+		memcpy(data, buf, ret);
+	kfree(buf);
 	return ret;
 }
 
-static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size, void *data)
+static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size,
+			 const void *data)
 {
+	u8 *buf;
 	int ret;
 
+	buf = kmemdup(data, size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
 	ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0),
 			      PEGASUS_REQ_SET_REGS, PEGASUS_REQT_WRITE, 0,
-			      indx, data, size, 100);
+			      indx, buf, size, 100);
 	if (ret < 0)
 		netif_dbg(pegasus, drv, pegasus->net,
 			  "%s returned %d\n", __func__, ret);
+	kfree(buf);
 	return ret;
 }
 
 static int set_register(pegasus_t *pegasus, __u16 indx, __u8 data)
 {
+	u8 *buf;
 	int ret;
 
+	buf = kmemdup(&data, 1, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
 	ret = usb_control_msg(pegasus->usb, usb_sndctrlpipe(pegasus->usb, 0),
 			      PEGASUS_REQ_SET_REG, PEGASUS_REQT_WRITE, data,
-			      indx, &data, 1, 1000);
+			      indx, buf, 1, 1000);
 	if (ret < 0)
 		netif_dbg(pegasus, drv, pegasus->net,
 			  "%s returned %d\n", __func__, ret);
+	kfree(buf);
 	return ret;
 }
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 6fe1cdb0174f..24d5272cdce5 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -654,6 +654,13 @@ static const struct usb_device_id products[] = {
 					      USB_CDC_PROTO_NONE),
 		.driver_info        = (unsigned long)&qmi_wwan_info,
 	},
+	{	/* HP lt2523 (Novatel E371) */
+		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d,
+					      USB_CLASS_COMM,
+					      USB_CDC_SUBCLASS_ETHERNET,
+					      USB_CDC_PROTO_NONE),
+		.driver_info        = (unsigned long)&qmi_wwan_info,
+	},
 	{	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 		USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7),
 		.driver_info = (unsigned long)&qmi_wwan_info,
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index f3b48ad90865..ad42295356dd 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -32,7 +32,7 @@
 #define NETNEXT_VERSION		"08"
 
 /* Information for net */
-#define NET_VERSION		"6"
+#define NET_VERSION		"8"
 
 #define DRIVER_VERSION		"v1." NETNEXT_VERSION "." NET_VERSION
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
@@ -1936,6 +1936,9 @@ static int r8152_poll(struct napi_struct *napi, int budget)
 		napi_complete(napi);
 		if (!list_empty(&tp->rx_done))
 			napi_schedule(napi);
+		else if (!skb_queue_empty(&tp->tx_queue) &&
+			 !list_empty(&tp->tx_free))
+			napi_schedule(napi);
 	}
 
 	return work_done;
@@ -3155,10 +3158,13 @@ static void set_carrier(struct r8152 *tp)
 		if (!netif_carrier_ok(netdev)) {
 			tp->rtl_ops.enable(tp);
 			set_bit(RTL8152_SET_RX_MODE, &tp->flags);
+			netif_stop_queue(netdev);
 			napi_disable(&tp->napi);
 			netif_carrier_on(netdev);
 			rtl_start_rx(tp);
 			napi_enable(&tp->napi);
+			netif_wake_queue(netdev);
+			netif_info(tp, link, netdev, "carrier on\n");
 		}
 	} else {
 		if (netif_carrier_ok(netdev)) {
@@ -3166,6 +3172,7 @@ static void set_carrier(struct r8152 *tp)
 			napi_disable(&tp->napi);
 			tp->rtl_ops.disable(tp);
 			napi_enable(&tp->napi);
+			netif_info(tp, link, netdev, "carrier off\n");
 		}
 	}
 }
@@ -3515,12 +3522,12 @@ static int rtl8152_pre_reset(struct usb_interface *intf)
 	if (!netif_running(netdev))
 		return 0;
 
+	netif_stop_queue(netdev);
 	napi_disable(&tp->napi);
 	clear_bit(WORK_ENABLE, &tp->flags);
 	usb_kill_urb(tp->intr_urb);
 	cancel_delayed_work_sync(&tp->schedule);
 	if (netif_carrier_ok(netdev)) {
-		netif_stop_queue(netdev);
 		mutex_lock(&tp->control);
 		tp->rtl_ops.disable(tp);
 		mutex_unlock(&tp->control);
@@ -3545,12 +3552,17 @@ static int rtl8152_post_reset(struct usb_interface *intf)
 	if (netif_carrier_ok(netdev)) {
 		mutex_lock(&tp->control);
 		tp->rtl_ops.enable(tp);
+		rtl_start_rx(tp);
 		rtl8152_set_rx_mode(netdev);
 		mutex_unlock(&tp->control);
-		netif_wake_queue(netdev);
 	}
 
 	napi_enable(&tp->napi);
+	netif_wake_queue(netdev);
+	usb_submit_urb(tp->intr_urb, GFP_KERNEL);
+
+	if (!list_empty(&tp->rx_done))
+		napi_schedule(&tp->napi);
 
 	return 0;
 }
@@ -3572,6 +3584,8 @@ static bool delay_autosuspend(struct r8152 *tp)
 	 */
 	if (!sw_linking && tp->rtl_ops.in_nway(tp))
 		return true;
+	else if (!skb_queue_empty(&tp->tx_queue))
+		return true;
 	else
 		return false;
 }
@@ -3581,10 +3595,15 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp)
 	struct net_device *netdev = tp->netdev;
 	int ret = 0;
 
+	set_bit(SELECTIVE_SUSPEND, &tp->flags);
+	smp_mb__after_atomic();
+
 	if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) {
 		u32 rcr = 0;
 
 		if (delay_autosuspend(tp)) {
+			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+			smp_mb__after_atomic();
 			ret = -EBUSY;
 			goto out1;
 		}
@@ -3601,6 +3620,8 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp)
 			if (!(ocp_data & RXFIFO_EMPTY)) {
 				rxdy_gated_en(tp, false);
 				ocp_write_dword(tp, MCU_TYPE_PLA, PLA_RCR, rcr);
+				clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+				smp_mb__after_atomic();
 				ret = -EBUSY;
 				goto out1;
 			}
@@ -3620,8 +3641,6 @@ static int rtl8152_rumtime_suspend(struct r8152 *tp)
 		}
 	}
 
-	set_bit(SELECTIVE_SUSPEND, &tp->flags);
-
 out1:
 	return ret;
 }
@@ -3677,12 +3696,15 @@ static int rtl8152_resume(struct usb_interface *intf)
 	if (netif_running(tp->netdev) && tp->netdev->flags & IFF_UP) {
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 			tp->rtl_ops.autosuspend_en(tp, false);
-			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
 			napi_disable(&tp->napi);
 			set_bit(WORK_ENABLE, &tp->flags);
 			if (netif_carrier_ok(tp->netdev))
 				rtl_start_rx(tp);
 			napi_enable(&tp->napi);
+			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+			smp_mb__after_atomic();
+			if (!list_empty(&tp->rx_done))
+				napi_schedule(&tp->napi);
 		} else {
 			tp->rtl_ops.up(tp);
 			netif_carrier_off(tp->netdev);
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 95b7bd0d7abc..c81c79110cef 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -155,16 +155,36 @@ static const char driver_name [] = "rtl8150";
 */
 static int get_registers(rtl8150_t * dev, u16 indx, u16 size, void *data)
 {
-	return usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
-			       RTL8150_REQ_GET_REGS, RTL8150_REQT_READ,
-			       indx, 0, data, size, 500);
+	void *buf;
+	int ret;
+
+	buf = kmalloc(size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
+			      RTL8150_REQ_GET_REGS, RTL8150_REQT_READ,
+			      indx, 0, buf, size, 500);
+	if (ret > 0 && ret <= size)
+		memcpy(data, buf, ret);
+	kfree(buf);
+	return ret;
 }
 
-static int set_registers(rtl8150_t * dev, u16 indx, u16 size, void *data)
+static int set_registers(rtl8150_t * dev, u16 indx, u16 size, const void *data)
 {
-	return usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
-			       RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE,
-			       indx, 0, data, size, 500);
+	void *buf;
+	int ret;
+
+	buf = kmemdup(data, size, GFP_NOIO);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
+			      RTL8150_REQ_SET_REGS, RTL8150_REQT_WRITE,
+			      indx, 0, buf, size, 500);
+	kfree(buf);
+	return ret;
 }
 
 static void async_set_reg_cb(struct urb *urb)
diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c
index 12071f1582df..d9440bc022f2 100644
--- a/drivers/net/usb/sierra_net.c
+++ b/drivers/net/usb/sierra_net.c
@@ -73,8 +73,6 @@ static	atomic_t iface_counter = ATOMIC_INIT(0);
 /* Private data structure */
 struct sierra_net_data {
 
-	u8 ethr_hdr_tmpl[ETH_HLEN]; /* ethernet header template for rx'd pkts */
-
 	u16 link_up;		/* air link up or down */
 	u8 tx_hdr_template[4];	/* part of HIP hdr for tx'd packets */
 
@@ -122,6 +120,7 @@ struct param {
 
 /* LSI Protocol types */
 #define SIERRA_NET_PROTOCOL_UMTS      0x01
+#define SIERRA_NET_PROTOCOL_UMTS_DS   0x04
 /* LSI Coverage */
 #define SIERRA_NET_COVERAGE_NONE      0x00
 #define SIERRA_NET_COVERAGE_NOPACKET  0x01
@@ -129,7 +128,8 @@ struct param {
 /* LSI Session */
 #define SIERRA_NET_SESSION_IDLE       0x00
 /* LSI Link types */
-#define SIERRA_NET_AS_LINK_TYPE_IPv4  0x00
+#define SIERRA_NET_AS_LINK_TYPE_IPV4  0x00
+#define SIERRA_NET_AS_LINK_TYPE_IPV6  0x02
 
 struct lsi_umts {
 	u8 protocol;
@@ -137,9 +137,14 @@ struct lsi_umts {
 	__be16 length;
 	/* eventually use a union for the rest - assume umts for now */
 	u8 coverage;
-	u8 unused2[41];
+	u8 network_len; /* network name len */
+	u8 network[40]; /* network name (UCS2, bigendian) */
 	u8 session_state;
 	u8 unused3[33];
+} __packed;
+
+struct lsi_umts_single {
+	struct lsi_umts lsi;
 	u8 link_type;
 	u8 pdp_addr_len; /* NW-supplied PDP address len */
 	u8 pdp_addr[16]; /* NW-supplied PDP address (bigendian)) */
@@ -158,10 +163,31 @@ struct lsi_umts {
 	u8 reserved[8];
 } __packed;
 
+struct lsi_umts_dual {
+	struct lsi_umts lsi;
+	u8 pdp_addr4_len; /* NW-supplied PDP IPv4 address len */
+	u8 pdp_addr4[4];  /* NW-supplied PDP IPv4 address (bigendian)) */
+	u8 pdp_addr6_len; /* NW-supplied PDP IPv6 address len */
+	u8 pdp_addr6[16]; /* NW-supplied PDP IPv6 address (bigendian)) */
+	u8 unused4[23];
+	u8 dns1_addr4_len; /* NW-supplied 1st DNS v4 address len (bigendian) */
+	u8 dns1_addr4[4];  /* NW-supplied 1st DNS v4 address */
+	u8 dns1_addr6_len; /* NW-supplied 1st DNS v6 address len */
+	u8 dns1_addr6[16]; /* NW-supplied 1st DNS v6 address (bigendian)*/
+	u8 dns2_addr4_len; /* NW-supplied 2nd DNS v4 address len (bigendian) */
+	u8 dns2_addr4[4];  /* NW-supplied 2nd DNS v4 address */
+	u8 dns2_addr6_len; /* NW-supplied 2nd DNS v6 address len */
+	u8 dns2_addr6[16]; /* NW-supplied 2nd DNS v6 address (bigendian)*/
+	u8 unused5[68];
+} __packed;
+
 #define SIERRA_NET_LSI_COMMON_LEN      4
-#define SIERRA_NET_LSI_UMTS_LEN        (sizeof(struct lsi_umts))
+#define SIERRA_NET_LSI_UMTS_LEN        (sizeof(struct lsi_umts_single))
 #define SIERRA_NET_LSI_UMTS_STATUS_LEN \
 	(SIERRA_NET_LSI_UMTS_LEN - SIERRA_NET_LSI_COMMON_LEN)
+#define SIERRA_NET_LSI_UMTS_DS_LEN     (sizeof(struct lsi_umts_dual))
+#define SIERRA_NET_LSI_UMTS_DS_STATUS_LEN \
+	(SIERRA_NET_LSI_UMTS_DS_LEN - SIERRA_NET_LSI_COMMON_LEN)
 
 /* Forward definitions */
 static void sierra_sync_timer(unsigned long syncdata);
@@ -190,10 +216,11 @@ static inline void sierra_net_set_private(struct usbnet *dev,
 	dev->data[0] = (unsigned long)priv;
 }
 
-/* is packet IPv4 */
+/* is packet IPv4/IPv6 */
 static inline int is_ip(struct sk_buff *skb)
 {
-	return skb->protocol == cpu_to_be16(ETH_P_IP);
+	return skb->protocol == cpu_to_be16(ETH_P_IP) ||
+	       skb->protocol == cpu_to_be16(ETH_P_IPV6);
 }
 
 /*
@@ -349,49 +376,54 @@ static inline int sierra_net_is_valid_addrlen(u8 len)
 static int sierra_net_parse_lsi(struct usbnet *dev, char *data, int datalen)
 {
 	struct lsi_umts *lsi = (struct lsi_umts *)data;
+	u32 expected_length;
 
-	if (datalen < sizeof(struct lsi_umts)) {
-		netdev_err(dev->net, "%s: Data length %d, exp %Zu\n",
-				__func__, datalen,
-				sizeof(struct lsi_umts));
+	if (datalen < sizeof(struct lsi_umts_single)) {
+		netdev_err(dev->net, "%s: Data length %d, exp >= %Zu\n",
+			   __func__, datalen, sizeof(struct lsi_umts_single));
 		return -1;
 	}
 
-	if (lsi->length != cpu_to_be16(SIERRA_NET_LSI_UMTS_STATUS_LEN)) {
-		netdev_err(dev->net, "%s: LSI_UMTS_STATUS_LEN %d, exp %u\n",
-				__func__, be16_to_cpu(lsi->length),
-				(u32)SIERRA_NET_LSI_UMTS_STATUS_LEN);
-		return -1;
+	/* Validate the session state */
+	if (lsi->session_state == SIERRA_NET_SESSION_IDLE) {
+		netdev_err(dev->net, "Session idle, 0x%02x\n",
+			   lsi->session_state);
+		return 0;
 	}
 
 	/* Validate the protocol  - only support UMTS for now */
-	if (lsi->protocol != SIERRA_NET_PROTOCOL_UMTS) {
+	if (lsi->protocol == SIERRA_NET_PROTOCOL_UMTS) {
+		struct lsi_umts_single *single = (struct lsi_umts_single *)lsi;
+
+		/* Validate the link type */
+		if (single->link_type != SIERRA_NET_AS_LINK_TYPE_IPV4 &&
+		    single->link_type != SIERRA_NET_AS_LINK_TYPE_IPV6) {
+			netdev_err(dev->net, "Link type unsupported: 0x%02x\n",
+				   single->link_type);
+			return -1;
+		}
+		expected_length = SIERRA_NET_LSI_UMTS_STATUS_LEN;
+	} else if (lsi->protocol == SIERRA_NET_PROTOCOL_UMTS_DS) {
+		expected_length = SIERRA_NET_LSI_UMTS_DS_STATUS_LEN;
+	} else {
 		netdev_err(dev->net, "Protocol unsupported, 0x%02x\n",
-			lsi->protocol);
+			   lsi->protocol);
 		return -1;
 	}
 
-	/* Validate the link type */
-	if (lsi->link_type != SIERRA_NET_AS_LINK_TYPE_IPv4) {
-		netdev_err(dev->net, "Link type unsupported: 0x%02x\n",
-			lsi->link_type);
+	if (be16_to_cpu(lsi->length) != expected_length) {
+		netdev_err(dev->net, "%s: LSI_UMTS_STATUS_LEN %d, exp %u\n",
+			   __func__, be16_to_cpu(lsi->length), expected_length);
 		return -1;
 	}
 
 	/* Validate the coverage */
-	if (lsi->coverage == SIERRA_NET_COVERAGE_NONE
-	   || lsi->coverage == SIERRA_NET_COVERAGE_NOPACKET) {
+	if (lsi->coverage == SIERRA_NET_COVERAGE_NONE ||
+	    lsi->coverage == SIERRA_NET_COVERAGE_NOPACKET) {
 		netdev_err(dev->net, "No coverage, 0x%02x\n", lsi->coverage);
 		return 0;
 	}
 
-	/* Validate the session state */
-	if (lsi->session_state == SIERRA_NET_SESSION_IDLE) {
-		netdev_err(dev->net, "Session idle, 0x%02x\n",
-			lsi->session_state);
-		return 0;
-	}
-
 	/* Set link_sense true */
 	return 1;
 }
@@ -652,7 +684,6 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf)
 	u8	numendpoints;
 	u16	fwattr = 0;
 	int	status;
-	struct ethhdr *eth;
 	struct sierra_net_data *priv;
 	static const u8 sync_tmplate[sizeof(priv->sync_msg)] = {
 		0x00, 0x00, SIERRA_NET_HIP_MSYNC_ID, 0x00};
@@ -690,11 +721,6 @@ static int sierra_net_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->dev_addr[ETH_ALEN-2] = atomic_inc_return(&iface_counter);
 	dev->net->dev_addr[ETH_ALEN-1] = ifacenum;
 
-	/* we will have to manufacture ethernet headers, prepare template */
-	eth = (struct ethhdr *)priv->ethr_hdr_tmpl;
-	memcpy(&eth->h_dest, dev->net->dev_addr, ETH_ALEN);
-	eth->h_proto = cpu_to_be16(ETH_P_IP);
-
 	/* prepare shutdown message template */
 	memcpy(priv->shdwn_msg, shdwn_tmplate, sizeof(priv->shdwn_msg));
 	/* set context index initially to 0 - prepares tx hdr template */
@@ -824,9 +850,14 @@ static int sierra_net_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 
 		skb_pull(skb, hh.hdrlen);
 
-		/* We are going to accept this packet, prepare it */
-		memcpy(skb->data, sierra_net_get_private(dev)->ethr_hdr_tmpl,
-			ETH_HLEN);
+		/* We are going to accept this packet, prepare it.
+		 * In case protocol is IPv6, keep it, otherwise force IPv4.
+		 */
+		skb_reset_mac_header(skb);
+		if (eth_hdr(skb)->h_proto != cpu_to_be16(ETH_P_IPV6))
+			eth_hdr(skb)->h_proto = cpu_to_be16(ETH_P_IP);
+		eth_zero_addr(eth_hdr(skb)->h_source);
+		memcpy(eth_hdr(skb)->h_dest, dev->net->dev_addr, ETH_ALEN);
 
 		/* Last packet in batch handled by usbnet */
 		if (hh.payload_len.word == skb->len)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 4a105006ca63..765c2d6358da 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -48,8 +48,16 @@ module_param(gso, bool, 0444);
  */
 DECLARE_EWMA(pkt_len, 1, 64)
 
+/* With mergeable buffers we align buffer address and use the low bits to
+ * encode its true size. Buffer size is up to 1 page so we need to align to
+ * square root of page size to ensure we reserve enough bits to encode the true
+ * size.
+ */
+#define MERGEABLE_BUFFER_MIN_ALIGN_SHIFT ((PAGE_SHIFT + 1) / 2)
+
 /* Minimum alignment for mergeable packet buffers. */
-#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, 256)
+#define MERGEABLE_BUFFER_ALIGN max(L1_CACHE_BYTES, \
+				   1 << MERGEABLE_BUFFER_MIN_ALIGN_SHIFT)
 
 #define VIRTNET_DRIVER_VERSION "1.0.0"
 
@@ -1104,7 +1112,7 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb)
 		hdr = skb_vnet_hdr(skb);
 
 	if (virtio_net_hdr_from_skb(skb, &hdr->hdr,
-				    virtio_is_little_endian(vi->vdev)))
+				    virtio_is_little_endian(vi->vdev), false))
 		BUG();
 
 	if (vi->mergeable_rx_bufs)
@@ -1707,6 +1715,11 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog)
 	u16 xdp_qp = 0, curr_qp;
 	int i, err;
 
+	if (prog && prog->xdp_adjust_head) {
+		netdev_warn(dev, "Does not support bpf_xdp_adjust_head()\n");
+		return -EOPNOTSUPP;
+	}
+
 	if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO4) ||
 	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_TSO6) ||
 	    virtio_has_feature(vi->vdev, VIRTIO_NET_F_GUEST_ECN) ||
@@ -1890,8 +1903,12 @@ static void free_receive_page_frags(struct virtnet_info *vi)
 			put_page(vi->rq[i].alloc_frag.page);
 }
 
-static bool is_xdp_queue(struct virtnet_info *vi, int q)
+static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
 {
+	/* For small receive mode always use kfree_skb variants */
+	if (!vi->mergeable_rx_bufs)
+		return false;
+
 	if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs))
 		return false;
 	else if (q < vi->curr_queue_pairs)
@@ -1908,7 +1925,7 @@ static void free_unused_bufs(struct virtnet_info *vi)
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		struct virtqueue *vq = vi->sq[i].vq;
 		while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) {
-			if (!is_xdp_queue(vi, i))
+			if (!is_xdp_raw_buffer_queue(vi, i))
 				dev_kfree_skb(buf);
 			else
 				put_page(virt_to_head_page(buf));
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index ca7196c40060..30b04cf2bb1e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2268,7 +2268,7 @@ static void vxlan_cleanup(unsigned long arg)
 				= container_of(p, struct vxlan_fdb, hlist);
 			unsigned long timeout;
 
-			if (f->state & NUD_PERMANENT)
+			if (f->state & (NUD_PERMANENT | NUD_NOARP))
 				continue;
 
 			timeout = f->used + vxlan->cfg.age_interval * HZ;
@@ -2354,7 +2354,7 @@ static int vxlan_open(struct net_device *dev)
 }
 
 /* Purge the forwarding table */
-static void vxlan_flush(struct vxlan_dev *vxlan)
+static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
 {
 	unsigned int h;
 
@@ -2364,6 +2364,8 @@ static void vxlan_flush(struct vxlan_dev *vxlan)
 		hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
 			struct vxlan_fdb *f
 				= container_of(p, struct vxlan_fdb, hlist);
+			if (!do_all && (f->state & (NUD_PERMANENT | NUD_NOARP)))
+				continue;
 			/* the all_zeros_mac entry is deleted at vxlan_uninit */
 			if (!is_zero_ether_addr(f->eth_addr))
 				vxlan_fdb_destroy(vxlan, f);
@@ -2385,7 +2387,7 @@ static int vxlan_stop(struct net_device *dev)
 
 	del_timer_sync(&vxlan->age_timer);
 
-	vxlan_flush(vxlan);
+	vxlan_flush(vxlan, false);
 	vxlan_sock_release(vxlan);
 
 	return ret;
@@ -2437,7 +2439,8 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 
 		rt = vxlan_get_route(vxlan, dev, sock4, skb, 0, info->key.tos,
 				     info->key.u.ipv4.dst,
-				     &info->key.u.ipv4.src, dport, sport, NULL, info);
+				     &info->key.u.ipv4.src, dport, sport,
+				     &info->dst_cache, info);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 		ip_rt_put(rt);
@@ -2448,7 +2451,8 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 
 		ndst = vxlan6_get_route(vxlan, dev, sock6, skb, 0, info->key.tos,
 					info->key.label, &info->key.u.ipv6.dst,
-					&info->key.u.ipv6.src, dport, sport, NULL, info);
+					&info->key.u.ipv6.src, dport, sport,
+					&info->dst_cache, info);
 		if (IS_ERR(ndst))
 			return PTR_ERR(ndst);
 		dst_release(ndst);
@@ -2890,7 +2894,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	memcpy(&vxlan->cfg, conf, sizeof(*conf));
 	if (!vxlan->cfg.dst_port) {
 		if (conf->flags & VXLAN_F_GPE)
-			vxlan->cfg.dst_port = 4790; /* IANA assigned VXLAN-GPE port */
+			vxlan->cfg.dst_port = htons(4790); /* IANA VXLAN-GPE port */
 		else
 			vxlan->cfg.dst_port = default_port;
 	}
@@ -3058,6 +3062,8 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id);
 
+	vxlan_flush(vxlan, true);
+
 	spin_lock(&vn->sock_lock);
 	if (!hlist_unhashed(&vxlan->hlist))
 		hlist_del_rcu(&vxlan->hlist);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
index d02ca1491d16..8d3e53fac1da 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c
@@ -91,7 +91,7 @@
 
 #define IWL8000_FW_PRE "iwlwifi-8000C-"
 #define IWL8000_MODULE_FIRMWARE(api) \
-	IWL8000_FW_PRE "-" __stringify(api) ".ucode"
+	IWL8000_FW_PRE __stringify(api) ".ucode"
 
 #define IWL8265_FW_PRE "iwlwifi-8265-"
 #define IWL8265_MODULE_FIRMWARE(api) \
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 636c8b03e318..09e9e2e3ed04 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1164,9 +1164,10 @@ static void iwl_mvm_realloc_queues_after_restart(struct iwl_mvm *mvm,
 		.frame_limit = IWL_FRAME_LIMIT,
 	};
 
-	/* Make sure reserved queue is still marked as such (or allocated) */
-	mvm->queue_info[mvm_sta->reserved_queue].status =
-		IWL_MVM_QUEUE_RESERVED;
+	/* Make sure reserved queue is still marked as such (if allocated) */
+	if (mvm_sta->reserved_queue != IEEE80211_INVAL_HW_QUEUE)
+		mvm->queue_info[mvm_sta->reserved_queue].status =
+			IWL_MVM_QUEUE_RESERVED;
 
 	for (i = 0; i <= IWL_MAX_TID_COUNT; i++) {
 		struct iwl_mvm_tid_data *tid_data = &mvm_sta->tid_data[i];
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index 63a051be832e..bec7d9c46087 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -843,8 +843,10 @@ static void iwl_mvm_thermal_zone_unregister(struct iwl_mvm *mvm)
 		return;
 
 	IWL_DEBUG_TEMP(mvm, "Thermal zone device unregister\n");
-	thermal_zone_device_unregister(mvm->tz_device.tzone);
-	mvm->tz_device.tzone = NULL;
+	if (mvm->tz_device.tzone) {
+		thermal_zone_device_unregister(mvm->tz_device.tzone);
+		mvm->tz_device.tzone = NULL;
+	}
 }
 
 static void iwl_mvm_cooling_device_unregister(struct iwl_mvm *mvm)
@@ -853,8 +855,10 @@ static void iwl_mvm_cooling_device_unregister(struct iwl_mvm *mvm)
 		return;
 
 	IWL_DEBUG_TEMP(mvm, "Cooling device unregister\n");
-	thermal_cooling_device_unregister(mvm->cooling_dev.cdev);
-	mvm->cooling_dev.cdev = NULL;
+	if (mvm->cooling_dev.cdev) {
+		thermal_cooling_device_unregister(mvm->cooling_dev.cdev);
+		mvm->cooling_dev.cdev = NULL;
+	}
 }
 #endif /* CONFIG_THERMAL */
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
index 691ddef1ae28..a33a06d58a9a 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c
@@ -92,7 +92,7 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw));
 	struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw));
-	char *fw_name = "rtlwifi/rtl8192cfwU.bin";
+	char *fw_name;
 
 	rtl8192ce_bt_reg_init(hw);
 
@@ -164,8 +164,13 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw)
 	}
 
 	/* request fw */
-	if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version))
+	if (IS_VENDOR_UMC_A_CUT(rtlhal->version) &&
+	    !IS_92C_SERIAL(rtlhal->version))
+		fw_name = "rtlwifi/rtl8192cfwU.bin";
+	else if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version))
 		fw_name = "rtlwifi/rtl8192cfwU_B.bin";
+	else
+		fw_name = "rtlwifi/rtl8192cfw.bin";
 
 	rtlpriv->max_fw_size = 0x4000;
 	pr_info("Using firmware %s\n", fw_name);
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 3ce1f7da8647..530586be05b4 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -113,10 +113,10 @@ struct xenvif_stats {
 	 * A subset of struct net_device_stats that contains only the
 	 * fields that are updated in netback.c for each queue.
 	 */
-	unsigned int rx_bytes;
-	unsigned int rx_packets;
-	unsigned int tx_bytes;
-	unsigned int tx_packets;
+	u64 rx_bytes;
+	u64 rx_packets;
+	u64 tx_bytes;
+	u64 tx_packets;
 
 	/* Additional stats used by xenvif */
 	unsigned long rx_gso_checksum_fixup;
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index e30ffd29b7e9..50fa1692d985 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -221,18 +221,18 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
 {
 	struct xenvif *vif = netdev_priv(dev);
 	struct xenvif_queue *queue = NULL;
-	unsigned int num_queues = vif->num_queues;
-	unsigned long rx_bytes = 0;
-	unsigned long rx_packets = 0;
-	unsigned long tx_bytes = 0;
-	unsigned long tx_packets = 0;
+	u64 rx_bytes = 0;
+	u64 rx_packets = 0;
+	u64 tx_bytes = 0;
+	u64 tx_packets = 0;
 	unsigned int index;
 
+	spin_lock(&vif->lock);
 	if (vif->queues == NULL)
 		goto out;
 
 	/* Aggregate tx and rx stats from each queue */
-	for (index = 0; index < num_queues; ++index) {
+	for (index = 0; index < vif->num_queues; ++index) {
 		queue = &vif->queues[index];
 		rx_bytes += queue->stats.rx_bytes;
 		rx_packets += queue->stats.rx_packets;
@@ -241,6 +241,8 @@ static struct net_device_stats *xenvif_get_stats(struct net_device *dev)
 	}
 
 out:
+	spin_unlock(&vif->lock);
+
 	vif->dev->stats.rx_bytes = rx_bytes;
 	vif->dev->stats.rx_packets = rx_packets;
 	vif->dev->stats.tx_bytes = tx_bytes;
diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c
index 3124eaec9427..85b742e1c42f 100644
--- a/drivers/net/xen-netback/xenbus.c
+++ b/drivers/net/xen-netback/xenbus.c
@@ -493,11 +493,22 @@ static int backend_create_xenvif(struct backend_info *be)
 static void backend_disconnect(struct backend_info *be)
 {
 	if (be->vif) {
+		unsigned int queue_index;
+
 		xen_unregister_watchers(be->vif);
 #ifdef CONFIG_DEBUG_FS
 		xenvif_debugfs_delif(be->vif);
 #endif /* CONFIG_DEBUG_FS */
 		xenvif_disconnect_data(be->vif);
+		for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index)
+			xenvif_deinit_queue(&be->vif->queues[queue_index]);
+
+		spin_lock(&be->vif->lock);
+		vfree(be->vif->queues);
+		be->vif->num_queues = 0;
+		be->vif->queues = NULL;
+		spin_unlock(&be->vif->lock);
+
 		xenvif_disconnect_ctrl(be->vif);
 	}
 }
@@ -1034,6 +1045,8 @@ static void connect(struct backend_info *be)
 err:
 	if (be->vif->num_queues > 0)
 		xenvif_disconnect_data(be->vif); /* Clean up existing queues */
+	for (queue_index = 0; queue_index < be->vif->num_queues; ++queue_index)
+		xenvif_deinit_queue(&be->vif->queues[queue_index]);
 	vfree(be->vif->queues);
 	be->vif->queues = NULL;
 	be->vif->num_queues = 0;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index a479cd99911d..1e4125a98291 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -281,6 +281,7 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 {
 	RING_IDX req_prod = queue->rx.req_prod_pvt;
 	int notify;
+	int err = 0;
 
 	if (unlikely(!netif_carrier_ok(queue->info->netdev)))
 		return;
@@ -295,8 +296,10 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 		struct xen_netif_rx_request *req;
 
 		skb = xennet_alloc_one_rx_buffer(queue);
-		if (!skb)
+		if (!skb) {
+			err = -ENOMEM;
 			break;
+		}
 
 		id = xennet_rxidx(req_prod);
 
@@ -320,8 +323,13 @@ static void xennet_alloc_rx_buffers(struct netfront_queue *queue)
 
 	queue->rx.req_prod_pvt = req_prod;
 
-	/* Not enough requests? Try again later. */
-	if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN) {
+	/* Try again later if there are not enough requests or skb allocation
+	 * failed.
+	 * Enough requests is quantified as the sum of newly created slots and
+	 * the unconsumed slots at the backend.
+	 */
+	if (req_prod - queue->rx.rsp_cons < NET_RX_SLOTS_MIN ||
+	    unlikely(err)) {
 		mod_timer(&queue->rx_refill_timer, jiffies + (HZ/10));
 		return;
 	}
@@ -1379,6 +1387,8 @@ static void xennet_disconnect_backend(struct netfront_info *info)
 	for (i = 0; i < num_queues && info->queues; ++i) {
 		struct netfront_queue *queue = &info->queues[i];
 
+		del_timer_sync(&queue->rx_refill_timer);
+
 		if (queue->tx_irq && (queue->tx_irq == queue->rx_irq))
 			unbind_from_irqhandler(queue->tx_irq, queue);
 		if (queue->tx_irq && (queue->tx_irq != queue->rx_irq)) {
@@ -1733,7 +1743,6 @@ static void xennet_destroy_queues(struct netfront_info *info)
 
 		if (netif_running(info->netdev))
 			napi_disable(&queue->napi);
-		del_timer_sync(&queue->rx_refill_timer);
 		netif_napi_del(&queue->napi);
 	}
 
@@ -1822,27 +1831,19 @@ static int talk_to_netback(struct xenbus_device *dev,
 		xennet_destroy_queues(info);
 
 	err = xennet_create_queues(info, &num_queues);
-	if (err < 0)
-		goto destroy_ring;
+	if (err < 0) {
+		xenbus_dev_fatal(dev, err, "creating queues");
+		kfree(info->queues);
+		info->queues = NULL;
+		goto out;
+	}
 
 	/* Create shared ring, alloc event channel -- for each queue */
 	for (i = 0; i < num_queues; ++i) {
 		queue = &info->queues[i];
 		err = setup_netfront(dev, queue, feature_split_evtchn);
-		if (err) {
-			/* setup_netfront() will tidy up the current
-			 * queue on error, but we need to clean up
-			 * those already allocated.
-			 */
-			if (i > 0) {
-				rtnl_lock();
-				netif_set_real_num_tx_queues(info->netdev, i);
-				rtnl_unlock();
-				goto destroy_ring;
-			} else {
-				goto out;
-			}
-		}
+		if (err)
+			goto destroy_ring;
 	}
 
 again:
@@ -1932,9 +1933,10 @@ abort_transaction_no_dev_fatal:
 	xenbus_transaction_end(xbt, 1);
  destroy_ring:
 	xennet_disconnect_backend(info);
-	kfree(info->queues);
-	info->queues = NULL;
+	xennet_destroy_queues(info);
  out:
+	unregister_netdev(info->netdev);
+	xennet_free_netdev(info->netdev);
 	return err;
 }
 
diff --git a/drivers/ntb/hw/intel/ntb_hw_intel.c b/drivers/ntb/hw/intel/ntb_hw_intel.c
index eca9688bf9d9..c00238491673 100644
--- a/drivers/ntb/hw/intel/ntb_hw_intel.c
+++ b/drivers/ntb/hw/intel/ntb_hw_intel.c
@@ -1629,6 +1629,28 @@ static void atom_deinit_dev(struct intel_ntb_dev *ndev)
 
 /* Skylake Xeon NTB */
 
+static int skx_poll_link(struct intel_ntb_dev *ndev)
+{
+	u16 reg_val;
+	int rc;
+
+	ndev->reg->db_iowrite(ndev->db_link_mask,
+			      ndev->self_mmio +
+			      ndev->self_reg->db_clear);
+
+	rc = pci_read_config_word(ndev->ntb.pdev,
+				  SKX_LINK_STATUS_OFFSET, &reg_val);
+	if (rc)
+		return 0;
+
+	if (reg_val == ndev->lnk_sta)
+		return 0;
+
+	ndev->lnk_sta = reg_val;
+
+	return 1;
+}
+
 static u64 skx_db_ioread(void __iomem *mmio)
 {
 	return ioread64(mmio);
@@ -2852,7 +2874,7 @@ static struct intel_b2b_addr xeon_b2b_dsd_addr = {
 };
 
 static const struct intel_ntb_reg skx_reg = {
-	.poll_link		= xeon_poll_link,
+	.poll_link		= skx_poll_link,
 	.link_is_up		= xeon_link_is_up,
 	.db_ioread		= skx_db_ioread,
 	.db_iowrite		= skx_db_iowrite,
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index f81aa4b18d9f..02ca45fdd892 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1802,7 +1802,7 @@ ntb_transport_create_queue(void *data, struct device *client_dev,
 
 	node = dev_to_node(&ndev->dev);
 
-	free_queue = ffs(nt->qp_bitmap);
+	free_queue = ffs(nt->qp_bitmap_free);
 	if (!free_queue)
 		goto err;
 
@@ -2273,9 +2273,8 @@ module_init(ntb_transport_init);
 
 static void __exit ntb_transport_exit(void)
 {
-	debugfs_remove_recursive(nt_debugfs_dir);
-
 	ntb_unregister_client(&ntb_transport_client);
 	bus_unregister(&ntb_transport_bus);
+	debugfs_remove_recursive(nt_debugfs_dir);
 }
 module_exit(ntb_transport_exit);
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index e75d4fdc0866..434e1d474f33 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -265,6 +265,8 @@ static ssize_t perf_copy(struct pthr_ctx *pctx, char __iomem *dst,
 	if (dma_submit_error(cookie))
 		goto err_set_unmap;
 
+	dmaengine_unmap_put(unmap);
+
 	atomic_inc(&pctx->dma_sync);
 	dma_async_issue_pending(chan);
 
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index a518cb1b59d4..ce3e8dfa10ad 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -52,17 +52,17 @@ static void namespace_blk_release(struct device *dev)
 	kfree(nsblk);
 }
 
-static struct device_type namespace_io_device_type = {
+static const struct device_type namespace_io_device_type = {
 	.name = "nd_namespace_io",
 	.release = namespace_io_release,
 };
 
-static struct device_type namespace_pmem_device_type = {
+static const struct device_type namespace_pmem_device_type = {
 	.name = "nd_namespace_pmem",
 	.release = namespace_pmem_release,
 };
 
-static struct device_type namespace_blk_device_type = {
+static const struct device_type namespace_blk_device_type = {
 	.name = "nd_namespace_blk",
 	.release = namespace_blk_release,
 };
@@ -962,8 +962,8 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 	struct nvdimm_drvdata *ndd;
 	struct nd_label_id label_id;
 	u32 flags = 0, remainder;
+	int rc, i, id = -1;
 	u8 *uuid = NULL;
-	int rc, i;
 
 	if (dev->driver || ndns->claim)
 		return -EBUSY;
@@ -972,11 +972,13 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
 
 		uuid = nspm->uuid;
+		id = nspm->id;
 	} else if (is_namespace_blk(dev)) {
 		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
 
 		uuid = nsblk->uuid;
 		flags = NSLABEL_FLAG_LOCAL;
+		id = nsblk->id;
 	}
 
 	/*
@@ -1039,10 +1041,11 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 
 	/*
 	 * Try to delete the namespace if we deleted all of its
-	 * allocation, this is not the seed device for the region, and
-	 * it is not actively claimed by a btt instance.
+	 * allocation, this is not the seed or 0th device for the
+	 * region, and it is not actively claimed by a btt, pfn, or dax
+	 * instance.
 	 */
-	if (val == 0 && nd_region->ns_seed != dev && !ndns->claim)
+	if (val == 0 && id != 0 && nd_region->ns_seed != dev && !ndns->claim)
 		nd_device_unregister(dev, ND_ASYNC);
 
 	return rc;
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index a2ac9e641aa9..6c033c9a2f06 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -627,15 +627,12 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	size = resource_size(&nsio->res);
 	npfns = (size - start_pad - end_trunc - SZ_8K) / SZ_4K;
 	if (nd_pfn->mode == PFN_MODE_PMEM) {
-		unsigned long memmap_size;
-
 		/*
 		 * vmemmap_populate_hugepages() allocates the memmap array in
 		 * HPAGE_SIZE chunks.
 		 */
-		memmap_size = ALIGN(64 * npfns, HPAGE_SIZE);
-		offset = ALIGN(start + SZ_8K + memmap_size + dax_label_reserve,
-				nd_pfn->align) - start;
+		offset = ALIGN(start + SZ_8K + 64 * npfns + dax_label_reserve,
+				max(nd_pfn->align, HPAGE_SIZE)) - start;
 	} else if (nd_pfn->mode == PFN_MODE_RAM)
 		offset = ALIGN(start + SZ_8K + dax_label_reserve,
 				nd_pfn->align) - start;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 8a3c3e32a704..44a1a257e0b5 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -208,18 +208,18 @@ EXPORT_SYMBOL_GPL(nvme_requeue_req);
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, unsigned int flags, int qid)
 {
+	unsigned op = nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
 	struct request *req;
 
 	if (qid == NVME_QID_ANY) {
-		req = blk_mq_alloc_request(q, nvme_is_write(cmd), flags);
+		req = blk_mq_alloc_request(q, op, flags);
 	} else {
-		req = blk_mq_alloc_request_hctx(q, nvme_is_write(cmd), flags,
+		req = blk_mq_alloc_request_hctx(q, op, flags,
 				qid ? qid - 1 : 0);
 	}
 	if (IS_ERR(req))
 		return req;
 
-	req->cmd_type = REQ_TYPE_DRV_PRIV;
 	req->cmd_flags |= REQ_FAILFAST_DRIVER;
 	nvme_req(req)->cmd = cmd;
 
@@ -238,26 +238,38 @@ static inline void nvme_setup_flush(struct nvme_ns *ns,
 static inline int nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmnd)
 {
+	unsigned short segments = blk_rq_nr_discard_segments(req), n = 0;
 	struct nvme_dsm_range *range;
-	unsigned int nr_bytes = blk_rq_bytes(req);
+	struct bio *bio;
 
-	range = kmalloc(sizeof(*range), GFP_ATOMIC);
+	range = kmalloc_array(segments, sizeof(*range), GFP_ATOMIC);
 	if (!range)
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
-	range->cattr = cpu_to_le32(0);
-	range->nlb = cpu_to_le32(nr_bytes >> ns->lba_shift);
-	range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
+	__rq_for_each_bio(bio, req) {
+		u64 slba = nvme_block_nr(ns, bio->bi_iter.bi_sector);
+		u32 nlb = bio->bi_iter.bi_size >> ns->lba_shift;
+
+		range[n].cattr = cpu_to_le32(0);
+		range[n].nlb = cpu_to_le32(nlb);
+		range[n].slba = cpu_to_le64(slba);
+		n++;
+	}
+
+	if (WARN_ON_ONCE(n != segments)) {
+		kfree(range);
+		return BLK_MQ_RQ_QUEUE_ERROR;
+	}
 
 	memset(cmnd, 0, sizeof(*cmnd));
 	cmnd->dsm.opcode = nvme_cmd_dsm;
 	cmnd->dsm.nsid = cpu_to_le32(ns->ns_id);
-	cmnd->dsm.nr = 0;
+	cmnd->dsm.nr = segments - 1;
 	cmnd->dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
 
 	req->special_vec.bv_page = virt_to_page(range);
 	req->special_vec.bv_offset = offset_in_page(range);
-	req->special_vec.bv_len = sizeof(*range);
+	req->special_vec.bv_len = sizeof(*range) * segments;
 	req->rq_flags |= RQF_SPECIAL_PAYLOAD;
 
 	return BLK_MQ_RQ_QUEUE_OK;
@@ -309,17 +321,27 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 {
 	int ret = BLK_MQ_RQ_QUEUE_OK;
 
-	if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+	switch (req_op(req)) {
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
 		memcpy(cmd, nvme_req(req)->cmd, sizeof(*cmd));
-	else if (req_op(req) == REQ_OP_FLUSH)
+		break;
+	case REQ_OP_FLUSH:
 		nvme_setup_flush(ns, cmd);
-	else if (req_op(req) == REQ_OP_DISCARD)
+		break;
+	case REQ_OP_DISCARD:
 		ret = nvme_setup_discard(ns, req, cmd);
-	else
+		break;
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
 		nvme_setup_rw(ns, req, cmd);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return BLK_MQ_RQ_QUEUE_ERROR;
+	}
 
 	cmd->common.command_id = req->tag;
-
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_setup_cmd);
@@ -784,6 +806,13 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
 		return nvme_sg_io(ns, (void __user *)arg);
 #endif
 	default:
+#ifdef CONFIG_NVM
+		if (ns->ndev)
+			return nvme_nvm_ioctl(ns, cmd, arg);
+#endif
+		if (is_sed_ioctl(cmd))
+			return sed_ioctl(ns->ctrl->opal_dev, cmd,
+					 (void __user *) arg);
 		return -ENOTTY;
 	}
 }
@@ -861,6 +890,9 @@ static void nvme_config_discard(struct nvme_ns *ns)
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	u32 logical_block_size = queue_logical_block_size(ns->queue);
 
+	BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
+			NVME_DSM_MAX_RANGES);
+
 	if (ctrl->quirks & NVME_QUIRK_DISCARD_ZEROES)
 		ns->queue->limits.discard_zeroes_data = 1;
 	else
@@ -869,6 +901,7 @@ static void nvme_config_discard(struct nvme_ns *ns)
 	ns->queue->limits.discard_alignment = logical_block_size;
 	ns->queue->limits.discard_granularity = logical_block_size;
 	blk_queue_max_discard_sectors(ns->queue, UINT_MAX);
+	blk_queue_max_discard_segments(ns->queue, NVME_DSM_MAX_RANGES);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
 }
 
@@ -1051,6 +1084,28 @@ static const struct pr_ops nvme_pr_ops = {
 	.pr_clear	= nvme_pr_clear,
 };
 
+#ifdef CONFIG_BLK_SED_OPAL
+int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
+		bool send)
+{
+	struct nvme_ctrl *ctrl = data;
+	struct nvme_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	if (send)
+		cmd.common.opcode = nvme_admin_security_send;
+	else
+		cmd.common.opcode = nvme_admin_security_recv;
+	cmd.common.nsid = 0;
+	cmd.common.cdw10[0] = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
+	cmd.common.cdw10[1] = cpu_to_le32(len);
+
+	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
+				      ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0);
+}
+EXPORT_SYMBOL_GPL(nvme_sec_submit);
+#endif /* CONFIG_BLK_SED_OPAL */
+
 static const struct block_device_operations nvme_fops = {
 	.owner		= THIS_MODULE,
 	.ioctl		= nvme_ioctl,
@@ -1230,6 +1285,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		return -EIO;
 	}
 
+	ctrl->oacs = le16_to_cpu(id->oacs);
 	ctrl->vid = le16_to_cpu(id->vid);
 	ctrl->oncs = le16_to_cpup(&id->oncs);
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index fcc9dcfdf675..fb51a8de9b29 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1663,13 +1663,13 @@ nvme_fc_map_data(struct nvme_fc_ctrl *ctrl, struct request *rq,
 		return 0;
 
 	freq->sg_table.sgl = freq->first_sgl;
-	ret = sg_alloc_table_chained(&freq->sg_table, rq->nr_phys_segments,
-			freq->sg_table.sgl);
+	ret = sg_alloc_table_chained(&freq->sg_table,
+			blk_rq_nr_phys_segments(rq), freq->sg_table.sgl);
 	if (ret)
 		return -ENOMEM;
 
 	op->nents = blk_rq_map_sg(rq->q, rq, freq->sg_table.sgl);
-	WARN_ON(op->nents > rq->nr_phys_segments);
+	WARN_ON(op->nents > blk_rq_nr_phys_segments(rq));
 	dir = (rq_data_dir(rq) == WRITE) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
 	freq->sg_cnt = fc_dma_map_sg(ctrl->lport->dev, freq->sg_table.sgl,
 				op->nents, dir);
@@ -1937,7 +1937,7 @@ nvme_fc_complete_rq(struct request *rq)
 			return;
 		}
 
-		if (rq->cmd_type == REQ_TYPE_DRV_PRIV)
+		if (blk_rq_is_passthrough(rq))
 			error = rq->errors;
 		else
 			error = nvme_error_status(rq->errors);
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 588d4a34c083..21cac8523bd8 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -26,6 +26,8 @@
 #include <linux/bitops.h>
 #include <linux/lightnvm.h>
 #include <linux/vmalloc.h>
+#include <linux/sched/sysctl.h>
+#include <uapi/linux/lightnvm.h>
 
 enum nvme_nvm_admin_opcode {
 	nvme_nvm_admin_identity		= 0xe2,
@@ -248,50 +250,48 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
 {
 	struct nvme_nvm_id_group *src;
 	struct nvm_id_group *dst;
-	int i, end;
-
-	end = min_t(u32, 4, nvm_id->cgrps);
-
-	for (i = 0; i < end; i++) {
-		src = &nvme_nvm_id->groups[i];
-		dst = &nvm_id->groups[i];
-
-		dst->mtype = src->mtype;
-		dst->fmtype = src->fmtype;
-		dst->num_ch = src->num_ch;
-		dst->num_lun = src->num_lun;
-		dst->num_pln = src->num_pln;
-
-		dst->num_pg = le16_to_cpu(src->num_pg);
-		dst->num_blk = le16_to_cpu(src->num_blk);
-		dst->fpg_sz = le16_to_cpu(src->fpg_sz);
-		dst->csecs = le16_to_cpu(src->csecs);
-		dst->sos = le16_to_cpu(src->sos);
-
-		dst->trdt = le32_to_cpu(src->trdt);
-		dst->trdm = le32_to_cpu(src->trdm);
-		dst->tprt = le32_to_cpu(src->tprt);
-		dst->tprm = le32_to_cpu(src->tprm);
-		dst->tbet = le32_to_cpu(src->tbet);
-		dst->tbem = le32_to_cpu(src->tbem);
-		dst->mpos = le32_to_cpu(src->mpos);
-		dst->mccap = le32_to_cpu(src->mccap);
-
-		dst->cpar = le16_to_cpu(src->cpar);
-
-		if (dst->fmtype == NVM_ID_FMTYPE_MLC) {
-			memcpy(dst->lptbl.id, src->lptbl.id, 8);
-			dst->lptbl.mlc.num_pairs =
-					le16_to_cpu(src->lptbl.mlc.num_pairs);
-
-			if (dst->lptbl.mlc.num_pairs > NVME_NVM_LP_MLC_PAIRS) {
-				pr_err("nvm: number of MLC pairs not supported\n");
-				return -EINVAL;
-			}
 
-			memcpy(dst->lptbl.mlc.pairs, src->lptbl.mlc.pairs,
-						dst->lptbl.mlc.num_pairs);
+	if (nvme_nvm_id->cgrps != 1)
+		return -EINVAL;
+
+	src = &nvme_nvm_id->groups[0];
+	dst = &nvm_id->grp;
+
+	dst->mtype = src->mtype;
+	dst->fmtype = src->fmtype;
+	dst->num_ch = src->num_ch;
+	dst->num_lun = src->num_lun;
+	dst->num_pln = src->num_pln;
+
+	dst->num_pg = le16_to_cpu(src->num_pg);
+	dst->num_blk = le16_to_cpu(src->num_blk);
+	dst->fpg_sz = le16_to_cpu(src->fpg_sz);
+	dst->csecs = le16_to_cpu(src->csecs);
+	dst->sos = le16_to_cpu(src->sos);
+
+	dst->trdt = le32_to_cpu(src->trdt);
+	dst->trdm = le32_to_cpu(src->trdm);
+	dst->tprt = le32_to_cpu(src->tprt);
+	dst->tprm = le32_to_cpu(src->tprm);
+	dst->tbet = le32_to_cpu(src->tbet);
+	dst->tbem = le32_to_cpu(src->tbem);
+	dst->mpos = le32_to_cpu(src->mpos);
+	dst->mccap = le32_to_cpu(src->mccap);
+
+	dst->cpar = le16_to_cpu(src->cpar);
+
+	if (dst->fmtype == NVM_ID_FMTYPE_MLC) {
+		memcpy(dst->lptbl.id, src->lptbl.id, 8);
+		dst->lptbl.mlc.num_pairs =
+				le16_to_cpu(src->lptbl.mlc.num_pairs);
+
+		if (dst->lptbl.mlc.num_pairs > NVME_NVM_LP_MLC_PAIRS) {
+			pr_err("nvm: number of MLC pairs not supported\n");
+			return -EINVAL;
 		}
+
+		memcpy(dst->lptbl.mlc.pairs, src->lptbl.mlc.pairs,
+					dst->lptbl.mlc.num_pairs);
 	}
 
 	return 0;
@@ -321,7 +321,6 @@ static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id)
 
 	nvm_id->ver_id = nvme_nvm_id->ver_id;
 	nvm_id->vmnt = nvme_nvm_id->vmnt;
-	nvm_id->cgrps = nvme_nvm_id->cgrps;
 	nvm_id->cap = le32_to_cpu(nvme_nvm_id->cap);
 	nvm_id->dom = le32_to_cpu(nvme_nvm_id->dom);
 	memcpy(&nvm_id->ppaf, &nvme_nvm_id->ppaf,
@@ -372,7 +371,7 @@ static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb,
 		}
 
 		/* Transform physical address to target address space */
-		nvmdev->mt->part_to_tgt(nvmdev, entries, cmd_nlb);
+		nvm_part_to_tgt(nvmdev, entries, cmd_nlb);
 
 		if (update_l2p(cmd_slba, cmd_nlb, entries, priv)) {
 			ret = -EINTR;
@@ -485,7 +484,8 @@ static void nvme_nvm_end_io(struct request *rq, int error)
 	struct nvm_rq *rqd = rq->end_io_data;
 
 	rqd->ppa_status = nvme_req(rq)->result.u64;
-	nvm_end_io(rqd, error);
+	rqd->error = error;
+	nvm_end_io(rqd);
 
 	kfree(nvme_req(rq)->cmd);
 	blk_mq_free_request(rq);
@@ -586,6 +586,224 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = {
 	.max_phys_sect		= 64,
 };
 
+static void nvme_nvm_end_user_vio(struct request *rq, int error)
+{
+	struct completion *waiting = rq->end_io_data;
+
+	complete(waiting);
+}
+
+static int nvme_nvm_submit_user_cmd(struct request_queue *q,
+				struct nvme_ns *ns,
+				struct nvme_nvm_command *vcmd,
+				void __user *ubuf, unsigned int bufflen,
+				void __user *meta_buf, unsigned int meta_len,
+				void __user *ppa_buf, unsigned int ppa_len,
+				u32 *result, u64 *status, unsigned int timeout)
+{
+	bool write = nvme_is_write((struct nvme_command *)vcmd);
+	struct nvm_dev *dev = ns->ndev;
+	struct gendisk *disk = ns->disk;
+	struct request *rq;
+	struct bio *bio = NULL;
+	__le64 *ppa_list = NULL;
+	dma_addr_t ppa_dma;
+	__le64 *metadata = NULL;
+	dma_addr_t metadata_dma;
+	DECLARE_COMPLETION_ONSTACK(wait);
+	int ret;
+
+	rq = nvme_alloc_request(q, (struct nvme_command *)vcmd, 0,
+			NVME_QID_ANY);
+	if (IS_ERR(rq)) {
+		ret = -ENOMEM;
+		goto err_cmd;
+	}
+
+	rq->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+
+	rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
+	rq->end_io_data = &wait;
+
+	if (ppa_buf && ppa_len) {
+		ppa_list = dma_pool_alloc(dev->dma_pool, GFP_KERNEL, &ppa_dma);
+		if (!ppa_list) {
+			ret = -ENOMEM;
+			goto err_rq;
+		}
+		if (copy_from_user(ppa_list, (void __user *)ppa_buf,
+						sizeof(u64) * (ppa_len + 1))) {
+			ret = -EFAULT;
+			goto err_ppa;
+		}
+		vcmd->ph_rw.spba = cpu_to_le64(ppa_dma);
+	} else {
+		vcmd->ph_rw.spba = cpu_to_le64((uintptr_t)ppa_buf);
+	}
+
+	if (ubuf && bufflen) {
+		ret = blk_rq_map_user(q, rq, NULL, ubuf, bufflen, GFP_KERNEL);
+		if (ret)
+			goto err_ppa;
+		bio = rq->bio;
+
+		if (meta_buf && meta_len) {
+			metadata = dma_pool_alloc(dev->dma_pool, GFP_KERNEL,
+								&metadata_dma);
+			if (!metadata) {
+				ret = -ENOMEM;
+				goto err_map;
+			}
+
+			if (write) {
+				if (copy_from_user(metadata,
+						(void __user *)meta_buf,
+						meta_len)) {
+					ret = -EFAULT;
+					goto err_meta;
+				}
+			}
+			vcmd->ph_rw.metadata = cpu_to_le64(metadata_dma);
+		}
+
+		if (!disk)
+			goto submit;
+
+		bio->bi_bdev = bdget_disk(disk, 0);
+		if (!bio->bi_bdev) {
+			ret = -ENODEV;
+			goto err_meta;
+		}
+	}
+
+submit:
+	blk_execute_rq_nowait(q, NULL, rq, 0, nvme_nvm_end_user_vio);
+
+	wait_for_completion_io(&wait);
+
+	ret = nvme_error_status(rq->errors);
+	if (result)
+		*result = rq->errors & 0x7ff;
+	if (status)
+		*status = le64_to_cpu(nvme_req(rq)->result.u64);
+
+	if (metadata && !ret && !write) {
+		if (copy_to_user(meta_buf, (void *)metadata, meta_len))
+			ret = -EFAULT;
+	}
+err_meta:
+	if (meta_buf && meta_len)
+		dma_pool_free(dev->dma_pool, metadata, metadata_dma);
+err_map:
+	if (bio) {
+		if (disk && bio->bi_bdev)
+			bdput(bio->bi_bdev);
+		blk_rq_unmap_user(bio);
+	}
+err_ppa:
+	if (ppa_buf && ppa_len)
+		dma_pool_free(dev->dma_pool, ppa_list, ppa_dma);
+err_rq:
+	blk_mq_free_request(rq);
+err_cmd:
+	return ret;
+}
+
+static int nvme_nvm_submit_vio(struct nvme_ns *ns,
+					struct nvm_user_vio __user *uvio)
+{
+	struct nvm_user_vio vio;
+	struct nvme_nvm_command c;
+	unsigned int length;
+	int ret;
+
+	if (copy_from_user(&vio, uvio, sizeof(vio)))
+		return -EFAULT;
+	if (vio.flags)
+		return -EINVAL;
+
+	memset(&c, 0, sizeof(c));
+	c.ph_rw.opcode = vio.opcode;
+	c.ph_rw.nsid = cpu_to_le32(ns->ns_id);
+	c.ph_rw.control = cpu_to_le16(vio.control);
+	c.ph_rw.length = cpu_to_le16(vio.nppas);
+
+	length = (vio.nppas + 1) << ns->lba_shift;
+
+	ret = nvme_nvm_submit_user_cmd(ns->queue, ns, &c,
+			(void __user *)(uintptr_t)vio.addr, length,
+			(void __user *)(uintptr_t)vio.metadata,
+							vio.metadata_len,
+			(void __user *)(uintptr_t)vio.ppa_list, vio.nppas,
+			&vio.result, &vio.status, 0);
+
+	if (ret && copy_to_user(uvio, &vio, sizeof(vio)))
+		return -EFAULT;
+
+	return ret;
+}
+
+static int nvme_nvm_user_vcmd(struct nvme_ns *ns, int admin,
+					struct nvm_passthru_vio __user *uvcmd)
+{
+	struct nvm_passthru_vio vcmd;
+	struct nvme_nvm_command c;
+	struct request_queue *q;
+	unsigned int timeout = 0;
+	int ret;
+
+	if (copy_from_user(&vcmd, uvcmd, sizeof(vcmd)))
+		return -EFAULT;
+	if ((vcmd.opcode != 0xF2) && (!capable(CAP_SYS_ADMIN)))
+		return -EACCES;
+	if (vcmd.flags)
+		return -EINVAL;
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = vcmd.opcode;
+	c.common.nsid = cpu_to_le32(ns->ns_id);
+	c.common.cdw2[0] = cpu_to_le32(vcmd.cdw2);
+	c.common.cdw2[1] = cpu_to_le32(vcmd.cdw3);
+	/* cdw11-12 */
+	c.ph_rw.length = cpu_to_le16(vcmd.nppas);
+	c.ph_rw.control  = cpu_to_le32(vcmd.control);
+	c.common.cdw10[3] = cpu_to_le32(vcmd.cdw13);
+	c.common.cdw10[4] = cpu_to_le32(vcmd.cdw14);
+	c.common.cdw10[5] = cpu_to_le32(vcmd.cdw15);
+
+	if (vcmd.timeout_ms)
+		timeout = msecs_to_jiffies(vcmd.timeout_ms);
+
+	q = admin ? ns->ctrl->admin_q : ns->queue;
+
+	ret = nvme_nvm_submit_user_cmd(q, ns,
+			(struct nvme_nvm_command *)&c,
+			(void __user *)(uintptr_t)vcmd.addr, vcmd.data_len,
+			(void __user *)(uintptr_t)vcmd.metadata,
+							vcmd.metadata_len,
+			(void __user *)(uintptr_t)vcmd.ppa_list, vcmd.nppas,
+			&vcmd.result, &vcmd.status, timeout);
+
+	if (ret && copy_to_user(uvcmd, &vcmd, sizeof(vcmd)))
+		return -EFAULT;
+
+	return ret;
+}
+
+int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case NVME_NVM_IOCTL_ADMIN_VIO:
+		return nvme_nvm_user_vcmd(ns, 1, (void __user *)arg);
+	case NVME_NVM_IOCTL_IO_VIO:
+		return nvme_nvm_user_vcmd(ns, 0, (void __user *)arg);
+	case NVME_NVM_IOCTL_SUBMIT_VIO:
+		return nvme_nvm_submit_vio(ns, (void __user *)arg);
+	default:
+		return -ENOTTY;
+	}
+}
+
 int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node)
 {
 	struct request_queue *q = ns->queue;
@@ -622,7 +840,7 @@ static ssize_t nvm_dev_attr_show(struct device *dev,
 		return 0;
 
 	id = &ndev->identity;
-	grp = &id->groups[0];
+	grp = &id->grp;
 	attr = &dattr->attr;
 
 	if (strcmp(attr->name, "version") == 0) {
@@ -633,10 +851,9 @@ static ssize_t nvm_dev_attr_show(struct device *dev,
 		return scnprintf(page, PAGE_SIZE, "%u\n", id->cap);
 	} else if (strcmp(attr->name, "device_mode") == 0) {
 		return scnprintf(page, PAGE_SIZE, "%u\n", id->dom);
+	/* kept for compatibility */
 	} else if (strcmp(attr->name, "media_manager") == 0) {
-		if (!ndev->mt)
-			return scnprintf(page, PAGE_SIZE, "%s\n", "none");
-		return scnprintf(page, PAGE_SIZE, "%s\n", ndev->mt->name);
+		return scnprintf(page, PAGE_SIZE, "%s\n", "gennvm");
 	} else if (strcmp(attr->name, "ppa_format") == 0) {
 		return scnprintf(page, PAGE_SIZE,
 			"0x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x\n",
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index aead6d08ed2c..14cfc6f7facb 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -19,6 +19,7 @@
 #include <linux/kref.h>
 #include <linux/blk-mq.h>
 #include <linux/lightnvm.h>
+#include <linux/sed-opal.h>
 
 enum {
 	/*
@@ -125,6 +126,8 @@ struct nvme_ctrl {
 	struct list_head node;
 	struct ida ns_ida;
 
+	struct opal_dev *opal_dev;
+
 	char name[12];
 	char serial[20];
 	char model[40];
@@ -137,6 +140,7 @@ struct nvme_ctrl {
 	u32 max_hw_sectors;
 	u16 oncs;
 	u16 vid;
+	u16 oacs;
 	atomic_t abort_limit;
 	u8 event_limit;
 	u8 vwc;
@@ -267,6 +271,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl);
 void nvme_queue_scan(struct nvme_ctrl *ctrl);
 void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
 
+int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
+		bool send);
+
 #define NVME_NR_AERS	1
 void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		union nvme_result *res);
@@ -318,6 +325,7 @@ int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
 void nvme_nvm_unregister(struct nvme_ns *ns);
 int nvme_nvm_register_sysfs(struct nvme_ns *ns);
 void nvme_nvm_unregister_sysfs(struct nvme_ns *ns);
+int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, unsigned long arg);
 #else
 static inline int nvme_nvm_register(struct nvme_ns *ns, char *disk_name,
 				    int node)
@@ -335,6 +343,11 @@ static inline int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *i
 {
 	return 0;
 }
+static inline int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd,
+							unsigned long arg)
+{
+	return -ENOTTY;
+}
 #endif /* CONFIG_NVM */
 
 static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 3faefabf339c..ddc51adb594d 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -43,6 +43,7 @@
 #include <linux/types.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <asm/unaligned.h>
+#include <linux/sed-opal.h>
 
 #include "nvme.h"
 
@@ -588,7 +589,7 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 */
 	if (ns && ns->ms && !blk_integrity_rq(req)) {
 		if (!(ns->pi_type && ns->ms == 8) &&
-					req->cmd_type != REQ_TYPE_DRV_PRIV) {
+		    !blk_rq_is_passthrough(req)) {
 			blk_mq_end_request(req, -EFAULT);
 			return BLK_MQ_RQ_QUEUE_OK;
 		}
@@ -645,7 +646,7 @@ static void nvme_complete_rq(struct request *req)
 			return;
 		}
 
-		if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+		if (blk_rq_is_passthrough(req))
 			error = req->errors;
 		else
 			error = nvme_error_status(req->errors);
@@ -895,12 +896,11 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		return BLK_EH_HANDLED;
 	}
 
-	iod->aborted = 1;
-
 	if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
 		atomic_inc(&dev->ctrl.abort_limit);
 		return BLK_EH_RESET_TIMER;
 	}
+	iod->aborted = 1;
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.abort.opcode = nvme_admin_abort_cmd;
@@ -1178,6 +1178,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
 		dev->admin_tagset.numa_node = dev_to_node(dev->dev);
 		dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
+		dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
 		dev->admin_tagset.driver_data = dev;
 
 		if (blk_mq_alloc_tag_set(&dev->admin_tagset))
@@ -1738,6 +1739,7 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 	if (dev->ctrl.admin_q)
 		blk_put_queue(dev->ctrl.admin_q);
 	kfree(dev->queues);
+	kfree(dev->ctrl.opal_dev);
 	kfree(dev);
 }
 
@@ -1754,6 +1756,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
 static void nvme_reset_work(struct work_struct *work)
 {
 	struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work);
+	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result = -ENODEV;
 
 	if (WARN_ON(dev->ctrl.state == NVME_CTRL_RESETTING))
@@ -1786,6 +1789,14 @@ static void nvme_reset_work(struct work_struct *work)
 	if (result)
 		goto out;
 
+	if ((dev->ctrl.oacs & NVME_CTRL_OACS_SEC_SUPP) && !dev->ctrl.opal_dev) {
+		dev->ctrl.opal_dev =
+			init_opal_dev(&dev->ctrl, &nvme_sec_submit);
+	}
+
+	if (was_suspend)
+		opal_unlock_from_suspend(dev->ctrl.opal_dev);
+
 	result = nvme_setup_io_queues(dev);
 	if (result)
 		goto out;
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 557f29b1f1bb..a75e95d42b3f 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1423,7 +1423,7 @@ static inline bool nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue,
 	if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) {
 		struct nvme_command *cmd = nvme_req(rq)->cmd;
 
-		if (rq->cmd_type != REQ_TYPE_DRV_PRIV ||
+		if (!blk_rq_is_passthrough(rq) ||
 		    cmd->common.opcode != nvme_fabrics_command ||
 		    cmd->fabrics.fctype != nvme_fabrics_type_connect)
 			return false;
@@ -1471,7 +1471,7 @@ static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	ib_dma_sync_single_for_device(dev, sqe->dma,
 			sizeof(struct nvme_command), DMA_TO_DEVICE);
 
-	if (rq->cmd_type == REQ_TYPE_FS && req_op(rq) == REQ_OP_FLUSH)
+	if (req_op(rq) == REQ_OP_FLUSH)
 		flush = true;
 	ret = nvme_rdma_post_send(queue, sqe, req->sge, req->num_sge,
 			req->mr->need_inval ? &req->reg_wr.wr : NULL, flush);
@@ -1522,7 +1522,7 @@ static void nvme_rdma_complete_rq(struct request *rq)
 			return;
 		}
 
-		if (rq->cmd_type == REQ_TYPE_DRV_PRIV)
+		if (blk_rq_is_passthrough(rq))
 			error = rq->errors;
 		else
 			error = nvme_error_status(rq->errors);
diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c
index a5c09e703bd8..f49ae2758bb7 100644
--- a/drivers/nvme/host/scsi.c
+++ b/drivers/nvme/host/scsi.c
@@ -43,6 +43,7 @@
 #include <asm/unaligned.h>
 #include <scsi/sg.h>
 #include <scsi/scsi.h>
+#include <scsi/scsi_request.h>
 
 #include "nvme.h"
 
@@ -2347,12 +2348,14 @@ static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
 
 static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr *hdr)
 {
-	u8 cmd[BLK_MAX_CDB];
+	u8 cmd[16];
 	int retcode;
 	unsigned int opcode;
 
 	if (hdr->cmdp == NULL)
 		return -EMSGSIZE;
+	if (hdr->cmd_len > sizeof(cmd))
+		return -EINVAL;
 	if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len))
 		return -EFAULT;
 
@@ -2451,8 +2454,6 @@ int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr)
 		return -EFAULT;
 	if (hdr.interface_id != 'S')
 		return -EINVAL;
-	if (hdr.cmd_len > BLK_MAX_CDB)
-		return -EINVAL;
 
 	/*
 	 * A positive return code means a NVMe status, which has been
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 6f5074153dcd..be8c800078e2 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -631,6 +631,7 @@ static void nvmet_subsys_release(struct config_item *item)
 {
 	struct nvmet_subsys *subsys = to_subsys(item);
 
+	nvmet_subsys_del_ctrls(subsys);
 	nvmet_subsys_put(subsys);
 }
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index b1d66ed655c9..fc5ba2f9e15f 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -200,7 +200,7 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 	pr_err("ctrl %d keep-alive timer (%d seconds) expired!\n",
 		ctrl->cntlid, ctrl->kato);
 
-	ctrl->ops->delete_ctrl(ctrl);
+	nvmet_ctrl_fatal_error(ctrl);
 }
 
 static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
@@ -816,6 +816,9 @@ static void nvmet_ctrl_free(struct kref *ref)
 	list_del(&ctrl->subsys_entry);
 	mutex_unlock(&subsys->lock);
 
+	flush_work(&ctrl->async_event_work);
+	cancel_work_sync(&ctrl->fatal_err_work);
+
 	ida_simple_remove(&subsys->cntlid_ida, ctrl->cntlid);
 	nvmet_subsys_put(subsys);
 
@@ -935,6 +938,16 @@ static void nvmet_subsys_free(struct kref *ref)
 	kfree(subsys);
 }
 
+void nvmet_subsys_del_ctrls(struct nvmet_subsys *subsys)
+{
+	struct nvmet_ctrl *ctrl;
+
+	mutex_lock(&subsys->lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		ctrl->ops->delete_ctrl(ctrl);
+	mutex_unlock(&subsys->lock);
+}
+
 void nvmet_subsys_put(struct nvmet_subsys *subsys)
 {
 	kref_put(&subsys->ref, nvmet_subsys_free);
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 173e842f19c9..ba57f9852bde 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1314,7 +1314,7 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 			(struct fcnvme_ls_disconnect_rqst *)iod->rqstbuf;
 	struct fcnvme_ls_disconnect_acc *acc =
 			(struct fcnvme_ls_disconnect_acc *)iod->rspbuf;
-	struct nvmet_fc_tgt_queue *queue;
+	struct nvmet_fc_tgt_queue *queue = NULL;
 	struct nvmet_fc_tgt_assoc *assoc;
 	int ret = 0;
 	bool del_assoc = false;
@@ -1348,7 +1348,18 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 		assoc = nvmet_fc_find_target_assoc(tgtport,
 				be64_to_cpu(rqst->associd.association_id));
 		iod->assoc = assoc;
-		if (!assoc)
+		if (assoc) {
+			if (rqst->discon_cmd.scope ==
+					FCNVME_DISCONN_CONNECTION) {
+				queue = nvmet_fc_find_target_queue(tgtport,
+						be64_to_cpu(
+							rqst->discon_cmd.id));
+				if (!queue) {
+					nvmet_fc_tgt_a_put(assoc);
+					ret = VERR_NO_CONN;
+				}
+			}
+		} else
 			ret = VERR_NO_ASSOC;
 	}
 
@@ -1373,21 +1384,18 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
 			FCNVME_LS_DISCONNECT);
 
 
-	if (rqst->discon_cmd.scope == FCNVME_DISCONN_CONNECTION) {
-		queue = nvmet_fc_find_target_queue(tgtport,
-					be64_to_cpu(rqst->discon_cmd.id));
-		if (queue) {
-			int qid = queue->qid;
+	/* are we to delete a Connection ID (queue) */
+	if (queue) {
+		int qid = queue->qid;
 
-			nvmet_fc_delete_target_queue(queue);
+		nvmet_fc_delete_target_queue(queue);
 
-			/* release the get taken by find_target_queue */
-			nvmet_fc_tgt_q_put(queue);
+		/* release the get taken by find_target_queue */
+		nvmet_fc_tgt_q_put(queue);
 
-			/* tear association down if io queue terminated */
-			if (!qid)
-				del_assoc = true;
-		}
+		/* tear association down if io queue terminated */
+		if (!qid)
+			del_assoc = true;
 	}
 
 	/* release get taken in nvmet_fc_find_target_assoc */
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 9aaa70071ae5..f3862e38f574 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -104,7 +104,7 @@ static void nvme_loop_complete_rq(struct request *req)
 			return;
 		}
 
-		if (req->cmd_type == REQ_TYPE_DRV_PRIV)
+		if (blk_rq_is_passthrough(req))
 			error = req->errors;
 		else
 			error = nvme_error_status(req->errors);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 23d5eb1c944f..cc7ad06b43a7 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -282,6 +282,7 @@ void nvmet_ctrl_put(struct nvmet_ctrl *ctrl);
 struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
 		enum nvme_subsys_type type);
 void nvmet_subsys_put(struct nvmet_subsys *subsys);
+void nvmet_subsys_del_ctrls(struct nvmet_subsys *subsys);
 
 struct nvmet_ns *nvmet_find_namespace(struct nvmet_ctrl *ctrl, __le32 nsid);
 void nvmet_put_namespace(struct nvmet_ns *ns);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 8c3760a78ac0..60990220bd83 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -438,6 +438,10 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
 {
 	struct ib_recv_wr *bad_wr;
 
+	ib_dma_sync_single_for_device(ndev->device,
+		cmd->sge[0].addr, cmd->sge[0].length,
+		DMA_FROM_DEVICE);
+
 	if (ndev->srq)
 		return ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
 	return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
@@ -538,6 +542,11 @@ static void nvmet_rdma_queue_response(struct nvmet_req *req)
 		first_wr = &rsp->send_wr;
 
 	nvmet_rdma_post_recv(rsp->queue->dev, rsp->cmd);
+
+	ib_dma_sync_single_for_device(rsp->queue->dev->device,
+		rsp->send_sge.addr, rsp->send_sge.length,
+		DMA_TO_DEVICE);
+
 	if (ib_post_send(cm_id->qp, first_wr, &bad_wr)) {
 		pr_err("sending cmd response failed\n");
 		nvmet_rdma_release_rsp(rsp);
@@ -698,6 +707,14 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
 	cmd->n_rdma = 0;
 	cmd->req.port = queue->port;
 
+
+	ib_dma_sync_single_for_cpu(queue->dev->device,
+		cmd->cmd->sge[0].addr, cmd->cmd->sge[0].length,
+		DMA_FROM_DEVICE);
+	ib_dma_sync_single_for_cpu(queue->dev->device,
+		cmd->send_sge.addr, cmd->send_sge.length,
+		DMA_TO_DEVICE);
+
 	if (!nvmet_req_init(&cmd->req, &queue->nvme_cq,
 			&queue->nvme_sq, &nvmet_rdma_ops))
 		return;
diff --git a/drivers/parport/parport_gsc.c b/drivers/parport/parport_gsc.c
index dd6d4ccb41e4..3858b87fd0bb 100644
--- a/drivers/parport/parport_gsc.c
+++ b/drivers/parport/parport_gsc.c
@@ -293,7 +293,7 @@ struct parport *parport_gsc_probe_port(unsigned long base,
 		p->irq = PARPORT_IRQ_NONE;
 	}
 	if (p->irq != PARPORT_IRQ_NONE) {
-		printk(", irq %d", p->irq);
+		pr_cont(", irq %d", p->irq);
 
 		if (p->dma == PARPORT_DMA_AUTO) {
 			p->dma = PARPORT_DMA_NONE;
@@ -303,8 +303,8 @@ struct parport *parport_gsc_probe_port(unsigned long base,
                                            is mandatory (see above) */
 		p->dma = PARPORT_DMA_NONE;
 
-	printk(" [");
-#define printmode(x) {if(p->modes&PARPORT_MODE_##x){printk("%s%s",f?",":"",#x);f++;}}
+	pr_cont(" [");
+#define printmode(x) {if(p->modes&PARPORT_MODE_##x){pr_cont("%s%s",f?",":"",#x);f++;}}
 	{
 		int f = 0;
 		printmode(PCSPP);
@@ -315,7 +315,7 @@ struct parport *parport_gsc_probe_port(unsigned long base,
 //		printmode(DMA);
 	}
 #undef printmode
-	printk("]\n");
+	pr_cont("]\n");
 
 	if (p->irq != PARPORT_IRQ_NONE) {
 		if (request_irq (p->irq, parport_irq_handler,
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 10c9c0ba8ff2..ec0b4c11ccd9 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -31,7 +31,6 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/slab.h>
-#include <linux/pm_runtime.h>
 #include <linux/pci.h>
 #include "../pci.h"
 #include "pciehp.h"
@@ -99,7 +98,6 @@ static int board_added(struct slot *p_slot)
 	pciehp_green_led_blink(p_slot);
 
 	/* Check link training status */
-	pm_runtime_get_sync(&ctrl->pcie->port->dev);
 	retval = pciehp_check_link_status(ctrl);
 	if (retval) {
 		ctrl_err(ctrl, "Failed to check link status\n");
@@ -120,14 +118,12 @@ static int board_added(struct slot *p_slot)
 		if (retval != -EEXIST)
 			goto err_exit;
 	}
-	pm_runtime_put(&ctrl->pcie->port->dev);
 
 	pciehp_green_led_on(p_slot);
 	pciehp_set_attention_status(p_slot, 0);
 	return 0;
 
 err_exit:
-	pm_runtime_put(&ctrl->pcie->port->dev);
 	set_slot_off(ctrl, p_slot);
 	return retval;
 }
@@ -141,9 +137,7 @@ static int remove_board(struct slot *p_slot)
 	int retval;
 	struct controller *ctrl = p_slot->ctrl;
 
-	pm_runtime_get_sync(&ctrl->pcie->port->dev);
 	retval = pciehp_unconfigure_device(p_slot);
-	pm_runtime_put(&ctrl->pcie->port->dev);
 	if (retval)
 		return retval;
 
diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c
index 56efaf72d08e..d2961ef39a3a 100644
--- a/drivers/pci/hotplug/pnv_php.c
+++ b/drivers/pci/hotplug/pnv_php.c
@@ -155,7 +155,7 @@ static void pnv_php_detach_device_nodes(struct device_node *parent)
 		pnv_php_detach_device_nodes(dn);
 
 		of_node_put(dn);
-		refcount = atomic_read(&dn->kobj.kref.refcount);
+		refcount = kref_read(&dn->kobj.kref);
 		if (refcount != 1)
 			pr_warn("Invalid refcount %d on <%s>\n",
 				refcount, of_node_full_name(dn));
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 50c5003295ca..7f73bacf13ed 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1206,6 +1206,16 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs,
 	if (flags & PCI_IRQ_AFFINITY) {
 		if (!affd)
 			affd = &msi_default_affd;
+
+		if (affd->pre_vectors + affd->post_vectors > min_vecs)
+			return -EINVAL;
+
+		/*
+		 * If there aren't any vectors left after applying the pre/post
+		 * vectors don't bother with assigning affinity.
+		 */
+		if (affd->pre_vectors + affd->post_vectors == min_vecs)
+			affd = NULL;
 	} else {
 		if (WARN_ON(affd))
 			affd = NULL;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a881c0d3d2e8..7904d02ffdb9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2241,10 +2241,13 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge)
 			return false;
 
 		/*
-		 * Hotplug ports handled by firmware in System Management Mode
+		 * Hotplug interrupts cannot be delivered if the link is down,
+		 * so parents of a hotplug port must stay awake. In addition,
+		 * hotplug ports handled by firmware in System Management Mode
 		 * may not be put into D3 by the OS (Thunderbolt on non-Macs).
+		 * For simplicity, disallow in general for now.
 		 */
-		if (bridge->is_hotplug_bridge && !pciehp_is_native(bridge))
+		if (bridge->is_hotplug_bridge)
 			return false;
 
 		if (pci_bridge_d3_force)
@@ -2276,10 +2279,7 @@ static int pci_dev_check_d3cold(struct pci_dev *dev, void *data)
 	     !pci_pme_capable(dev, PCI_D3cold)) ||
 
 	    /* If it is a bridge it must be allowed to go to D3. */
-	    !pci_power_manageable(dev) ||
-
-	    /* Hotplug interrupts cannot be delivered if the link is down. */
-	    dev->is_hotplug_bridge)
+	    !pci_power_manageable(dev))
 
 		*d3cold_ok = false;
 
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 17ac1dce3286..3dd8bcbb3011 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -532,25 +532,32 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev)
 	link = kzalloc(sizeof(*link), GFP_KERNEL);
 	if (!link)
 		return NULL;
+
 	INIT_LIST_HEAD(&link->sibling);
 	INIT_LIST_HEAD(&link->children);
 	INIT_LIST_HEAD(&link->link);
 	link->pdev = pdev;
-	if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT) {
+
+	/*
+	 * Root Ports and PCI/PCI-X to PCIe Bridges are roots of PCIe
+	 * hierarchies.
+	 */
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT ||
+	    pci_pcie_type(pdev) == PCI_EXP_TYPE_PCIE_BRIDGE) {
+		link->root = link;
+	} else {
 		struct pcie_link_state *parent;
+
 		parent = pdev->bus->parent->self->link_state;
 		if (!parent) {
 			kfree(link);
 			return NULL;
 		}
+
 		link->parent = parent;
+		link->root = link->parent->root;
 		list_add(&link->link, &parent->children);
 	}
-	/* Setup a pointer to the root port link */
-	if (!link->parent)
-		link->root = link;
-	else
-		link->root = link->parent->root;
 
 	list_add(&link->sibling, &link_list);
 	pdev->link_state = link;
diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c
index 717529331dac..2dd1c68e6de8 100644
--- a/drivers/pci/pcie/pme.c
+++ b/drivers/pci/pcie/pme.c
@@ -433,6 +433,17 @@ static int pcie_pme_resume(struct pcie_device *srv)
 	return 0;
 }
 
+/**
+ * pcie_pme_remove - Prepare PCIe PME service device for removal.
+ * @srv - PCIe service device to remove.
+ */
+static void pcie_pme_remove(struct pcie_device *srv)
+{
+	pcie_pme_suspend(srv);
+	free_irq(srv->irq, srv);
+	kfree(get_service_data(srv));
+}
+
 static struct pcie_port_service_driver pcie_pme_driver = {
 	.name		= "pcie_pme",
 	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
@@ -441,6 +452,7 @@ static struct pcie_port_service_driver pcie_pme_driver = {
 	.probe		= pcie_pme_probe,
 	.suspend	= pcie_pme_suspend,
 	.resume		= pcie_pme_resume,
+	.remove		= pcie_pme_remove,
 };
 
 /**
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 429d34c348b9..e42909524dee 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -345,7 +345,7 @@ EXPORT_SYMBOL_GPL(pci_create_slot);
 void pci_destroy_slot(struct pci_slot *slot)
 {
 	dev_dbg(&slot->bus->dev, "dev %02x, dec refcount to %d\n",
-		slot->number, atomic_read(&slot->kobj.kref.refcount) - 1);
+		slot->number, kref_read(&slot->kobj.kref) - 1);
 
 	mutex_lock(&pci_slot_mutex);
 	kobject_put(&slot->kobj);
diff --git a/drivers/pinctrl/berlin/berlin-bg4ct.c b/drivers/pinctrl/berlin/berlin-bg4ct.c
index 09172043d589..c617ec49e9ed 100644
--- a/drivers/pinctrl/berlin/berlin-bg4ct.c
+++ b/drivers/pinctrl/berlin/berlin-bg4ct.c
@@ -217,7 +217,7 @@ static const struct berlin_desc_group berlin4ct_soc_pinctrl_groups[] = {
 	BERLIN_PINCTRL_GROUP("SCRD0_CRD_PRES", 0xc, 0x3, 0x15,
 			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO20 */
 			BERLIN_PINCTRL_FUNCTION(0x1, "scrd0"), /* crd pres */
-			BERLIN_PINCTRL_FUNCTION(0x1, "sd1a")), /* DAT3 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "sd1a")), /* DAT3 */
 	BERLIN_PINCTRL_GROUP("SPI1_SS0n", 0xc, 0x3, 0x18,
 			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS0n */
 			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO37 */
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 37300634b7d2..d94aef17348b 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -731,16 +731,23 @@ static void __iomem *byt_gpio_reg(struct byt_gpio *vg, unsigned int offset,
 				  int reg)
 {
 	struct byt_community *comm = byt_get_community(vg, offset);
-	u32 reg_offset = 0;
+	u32 reg_offset;
 
 	if (!comm)
 		return NULL;
 
 	offset -= comm->pin_base;
-	if (reg == BYT_INT_STAT_REG)
+	switch (reg) {
+	case BYT_INT_STAT_REG:
 		reg_offset = (offset / 32) * 4;
-	else
+		break;
+	case BYT_DEBOUNCE_REG:
+		reg_offset = 0;
+		break;
+	default:
 		reg_offset = comm->pad_map[offset] * 16;
+		break;
+	}
 
 	return comm->reg_base + reg_offset + reg;
 }
@@ -1092,6 +1099,7 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset,
 	enum pin_config_param param = pinconf_to_config_param(*config);
 	void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+	void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG);
 	unsigned long flags;
 	u32 conf, pull, val, debounce;
 	u16 arg = 0;
@@ -1128,7 +1136,7 @@ static int byt_pin_config_get(struct pinctrl_dev *pctl_dev, unsigned int offset,
 			return -EINVAL;
 
 		raw_spin_lock_irqsave(&vg->lock, flags);
-		debounce = readl(byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG));
+		debounce = readl(db_reg);
 		raw_spin_unlock_irqrestore(&vg->lock, flags);
 
 		switch (debounce & BYT_DEBOUNCE_PULSE_MASK) {
@@ -1176,6 +1184,7 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 	unsigned int param, arg;
 	void __iomem *conf_reg = byt_gpio_reg(vg, offset, BYT_CONF0_REG);
 	void __iomem *val_reg = byt_gpio_reg(vg, offset, BYT_VAL_REG);
+	void __iomem *db_reg = byt_gpio_reg(vg, offset, BYT_DEBOUNCE_REG);
 	unsigned long flags;
 	u32 conf, val, debounce;
 	int i, ret = 0;
@@ -1238,36 +1247,44 @@ static int byt_pin_config_set(struct pinctrl_dev *pctl_dev,
 
 			break;
 		case PIN_CONFIG_INPUT_DEBOUNCE:
-			debounce = readl(byt_gpio_reg(vg, offset,
-						      BYT_DEBOUNCE_REG));
-			conf &= ~BYT_DEBOUNCE_PULSE_MASK;
+			debounce = readl(db_reg);
+			debounce &= ~BYT_DEBOUNCE_PULSE_MASK;
+
+			if (arg)
+				conf |= BYT_DEBOUNCE_EN;
+			else
+				conf &= ~BYT_DEBOUNCE_EN;
 
 			switch (arg) {
 			case 375:
-				conf |= BYT_DEBOUNCE_PULSE_375US;
+				debounce |= BYT_DEBOUNCE_PULSE_375US;
 				break;
 			case 750:
-				conf |= BYT_DEBOUNCE_PULSE_750US;
+				debounce |= BYT_DEBOUNCE_PULSE_750US;
 				break;
 			case 1500:
-				conf |= BYT_DEBOUNCE_PULSE_1500US;
+				debounce |= BYT_DEBOUNCE_PULSE_1500US;
 				break;
 			case 3000:
-				conf |= BYT_DEBOUNCE_PULSE_3MS;
+				debounce |= BYT_DEBOUNCE_PULSE_3MS;
 				break;
 			case 6000:
-				conf |= BYT_DEBOUNCE_PULSE_6MS;
+				debounce |= BYT_DEBOUNCE_PULSE_6MS;
 				break;
 			case 12000:
-				conf |= BYT_DEBOUNCE_PULSE_12MS;
+				debounce |= BYT_DEBOUNCE_PULSE_12MS;
 				break;
 			case 24000:
-				conf |= BYT_DEBOUNCE_PULSE_24MS;
+				debounce |= BYT_DEBOUNCE_PULSE_24MS;
 				break;
 			default:
-				ret = -EINVAL;
+				if (arg)
+					ret = -EINVAL;
+				break;
 			}
 
+			if (!ret)
+				writel(debounce, db_reg);
 			break;
 		default:
 			ret = -ENOTSUPP;
@@ -1606,7 +1623,9 @@ static void byt_gpio_irq_handler(struct irq_desc *desc)
 			continue;
 		}
 
+		raw_spin_lock(&vg->lock);
 		pending = readl(reg);
+		raw_spin_unlock(&vg->lock);
 		for_each_set_bit(pin, &pending, 32) {
 			virq = irq_find_mapping(vg->chip.irqdomain, base + pin);
 			generic_handle_irq(virq);
@@ -1617,6 +1636,8 @@ static void byt_gpio_irq_handler(struct irq_desc *desc)
 
 static void byt_gpio_irq_init_hw(struct byt_gpio *vg)
 {
+	struct gpio_chip *gc = &vg->chip;
+	struct device *dev = &vg->pdev->dev;
 	void __iomem *reg;
 	u32 base, value;
 	int i;
@@ -1638,10 +1659,12 @@ static void byt_gpio_irq_init_hw(struct byt_gpio *vg)
 		}
 
 		value = readl(reg);
-		if ((value & BYT_PIN_MUX) == byt_get_gpio_mux(vg, i) &&
-		    !(value & BYT_DIRECT_IRQ_EN)) {
+		if (value & BYT_DIRECT_IRQ_EN) {
+			clear_bit(i, gc->irq_valid_mask);
+			dev_dbg(dev, "excluding GPIO %d from IRQ domain\n", i);
+		} else if ((value & BYT_PIN_MUX) == byt_get_gpio_mux(vg, i)) {
 			byt_gpio_clear_triggering(vg, i);
-			dev_dbg(&vg->pdev->dev, "disabling GPIO %d\n", i);
+			dev_dbg(dev, "disabling GPIO %d\n", i);
 		}
 	}
 
@@ -1680,6 +1703,7 @@ static int byt_gpio_probe(struct byt_gpio *vg)
 	gc->can_sleep	= false;
 	gc->parent	= &vg->pdev->dev;
 	gc->ngpio	= vg->soc_data->npins;
+	gc->irq_need_valid_mask	= true;
 
 #ifdef CONFIG_PM_SLEEP
 	vg->saved_context = devm_kcalloc(&vg->pdev->dev, gc->ngpio,
diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c
index 59cb7a6fc5be..901b356b09d7 100644
--- a/drivers/pinctrl/intel/pinctrl-broxton.c
+++ b/drivers/pinctrl/intel/pinctrl-broxton.c
@@ -19,7 +19,7 @@
 
 #define BXT_PAD_OWN	0x020
 #define BXT_HOSTSW_OWN	0x080
-#define BXT_PADCFGLOCK	0x090
+#define BXT_PADCFGLOCK	0x060
 #define BXT_GPI_IE	0x110
 
 #define BXT_COMMUNITY(s, e)				\
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 1e139672f1af..6df35dcb29ae 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -353,6 +353,21 @@ static int intel_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned function,
 	return 0;
 }
 
+static void __intel_gpio_set_direction(void __iomem *padcfg0, bool input)
+{
+	u32 value;
+
+	value = readl(padcfg0);
+	if (input) {
+		value &= ~PADCFG0_GPIORXDIS;
+		value |= PADCFG0_GPIOTXDIS;
+	} else {
+		value &= ~PADCFG0_GPIOTXDIS;
+		value |= PADCFG0_GPIORXDIS;
+	}
+	writel(value, padcfg0);
+}
+
 static int intel_gpio_request_enable(struct pinctrl_dev *pctldev,
 				     struct pinctrl_gpio_range *range,
 				     unsigned pin)
@@ -375,11 +390,11 @@ static int intel_gpio_request_enable(struct pinctrl_dev *pctldev,
 	/* Disable SCI/SMI/NMI generation */
 	value &= ~(PADCFG0_GPIROUTIOXAPIC | PADCFG0_GPIROUTSCI);
 	value &= ~(PADCFG0_GPIROUTSMI | PADCFG0_GPIROUTNMI);
-	/* Disable TX buffer and enable RX (this will be input) */
-	value &= ~PADCFG0_GPIORXDIS;
-	value |= PADCFG0_GPIOTXDIS;
 	writel(value, padcfg0);
 
+	/* Disable TX buffer and enable RX (this will be input) */
+	__intel_gpio_set_direction(padcfg0, true);
+
 	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
 	return 0;
@@ -392,18 +407,11 @@ static int intel_gpio_set_direction(struct pinctrl_dev *pctldev,
 	struct intel_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev);
 	void __iomem *padcfg0;
 	unsigned long flags;
-	u32 value;
 
 	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	padcfg0 = intel_get_padcfg(pctrl, pin, PADCFG0);
-
-	value = readl(padcfg0);
-	if (input)
-		value |= PADCFG0_GPIOTXDIS;
-	else
-		value &= ~PADCFG0_GPIOTXDIS;
-	writel(value, padcfg0);
+	__intel_gpio_set_direction(padcfg0, input);
 
 	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
diff --git a/drivers/pinctrl/intel/pinctrl-merrifield.c b/drivers/pinctrl/intel/pinctrl-merrifield.c
index b21896126f76..4d4ef42a39b5 100644
--- a/drivers/pinctrl/intel/pinctrl-merrifield.c
+++ b/drivers/pinctrl/intel/pinctrl-merrifield.c
@@ -794,6 +794,9 @@ static int mrfld_config_set(struct pinctrl_dev *pctldev, unsigned int pin,
 	unsigned int i;
 	int ret;
 
+	if (!mrfld_buf_available(mp, pin))
+		return -ENOTSUPP;
+
 	for (i = 0; i < nconfigs; i++) {
 		switch (pinconf_to_config_param(configs[i])) {
 		case PIN_CONFIG_BIAS_DISABLE:
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
index c3928aa3fefa..e0bca4df2a2f 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
@@ -253,9 +253,8 @@ static const unsigned int uart_tx_ao_a_pins[]	= { PIN(GPIOAO_0, 0) };
 static const unsigned int uart_rx_ao_a_pins[]	= { PIN(GPIOAO_1, 0) };
 static const unsigned int uart_cts_ao_a_pins[]	= { PIN(GPIOAO_2, 0) };
 static const unsigned int uart_rts_ao_a_pins[]	= { PIN(GPIOAO_3, 0) };
-static const unsigned int uart_tx_ao_b_pins[]	= { PIN(GPIOAO_0, 0) };
-static const unsigned int uart_rx_ao_b_pins[]	= { PIN(GPIOAO_1, 0),
-						    PIN(GPIOAO_5, 0) };
+static const unsigned int uart_tx_ao_b_pins[]	= { PIN(GPIOAO_4, 0) };
+static const unsigned int uart_rx_ao_b_pins[]	= { PIN(GPIOAO_5, 0) };
 static const unsigned int uart_cts_ao_b_pins[]	= { PIN(GPIOAO_2, 0) };
 static const unsigned int uart_rts_ao_b_pins[]	= { PIN(GPIOAO_3, 0) };
 
@@ -498,7 +497,7 @@ static struct meson_pmx_group meson_gxbb_aobus_groups[] = {
 	GPIO_GROUP(GPIOAO_13, 0),
 
 	/* bank AO */
-	GROUP(uart_tx_ao_b,	0,	26),
+	GROUP(uart_tx_ao_b,	0,	24),
 	GROUP(uart_rx_ao_b,	0,	25),
 	GROUP(uart_tx_ao_a,	0,	12),
 	GROUP(uart_rx_ao_a,	0,	11),
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxl.c b/drivers/pinctrl/meson/pinctrl-meson-gxl.c
index 25694f7094c7..b69743b07a1d 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxl.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxl.c
@@ -214,9 +214,8 @@ static const unsigned int uart_tx_ao_a_pins[]	= { PIN(GPIOAO_0, 0) };
 static const unsigned int uart_rx_ao_a_pins[]	= { PIN(GPIOAO_1, 0) };
 static const unsigned int uart_cts_ao_a_pins[]	= { PIN(GPIOAO_2, 0) };
 static const unsigned int uart_rts_ao_a_pins[]	= { PIN(GPIOAO_3, 0) };
-static const unsigned int uart_tx_ao_b_pins[]	= { PIN(GPIOAO_0, 0) };
-static const unsigned int uart_rx_ao_b_pins[]	= { PIN(GPIOAO_1, 0),
-						    PIN(GPIOAO_5, 0) };
+static const unsigned int uart_tx_ao_b_pins[]	= { PIN(GPIOAO_4, 0) };
+static const unsigned int uart_rx_ao_b_pins[]	= { PIN(GPIOAO_5, 0) };
 static const unsigned int uart_cts_ao_b_pins[]	= { PIN(GPIOAO_2, 0) };
 static const unsigned int uart_rts_ao_b_pins[]	= { PIN(GPIOAO_3, 0) };
 
@@ -409,7 +408,7 @@ static struct meson_pmx_group meson_gxl_aobus_groups[] = {
 	GPIO_GROUP(GPIOAO_9, 0),
 
 	/* bank AO */
-	GROUP(uart_tx_ao_b,	0,	26),
+	GROUP(uart_tx_ao_b,	0,	24),
 	GROUP(uart_rx_ao_b,	0,	25),
 	GROUP(uart_tx_ao_a,	0,	12),
 	GROUP(uart_rx_ao_a,	0,	11),
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index c9a146948192..537b52055756 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -202,6 +202,8 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc)
 			i = 128;
 			pin_num = AMD_GPIO_PINS_BANK2 + i;
 			break;
+		default:
+			return;
 		}
 
 		for (; i < pin_num; i++) {
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 0eb51e33cb1b..207a8de4e1ed 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -564,8 +564,7 @@ static int sunxi_pconf_group_set(struct pinctrl_dev *pctldev,
 			val = arg / 10 - 1;
 			break;
 		case PIN_CONFIG_BIAS_DISABLE:
-			val = 0;
-			break;
+			continue;
 		case PIN_CONFIG_BIAS_PULL_UP:
 			if (arg == 0)
 				return -EINVAL;
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
index aa8bd9794683..96686336e3a3 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
@@ -561,7 +561,7 @@ static const int ether_rgmii_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 					  0, 0, 0, 0};
 static const unsigned ether_rmii_pins[] = {30, 31, 32, 33, 34, 35, 36, 37, 39,
 					   41, 42, 45};
-static const int ether_rmii_muxvals[] = {1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1};
+static const int ether_rmii_muxvals[] = {0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1};
 static const unsigned i2c0_pins[] = {63, 64};
 static const int i2c0_muxvals[] = {0, 0};
 static const unsigned i2c1_pins[] = {65, 66};
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index 59aa8e302bc3..49a594855f98 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -816,13 +816,6 @@ config INTEL_SCU_IPC_UTIL
 	  low level access for debug work and updating the firmware. Say
 	  N unless you will be doing this on an Intel MID platform.
 
-config GPIO_INTEL_PMIC
-	bool "Intel PMIC GPIO support"
-	depends on INTEL_SCU_IPC && GPIOLIB
-	---help---
-	  Say Y here to support GPIO via the SCU IPC interface
-	  on Intel MID platforms.
-
 config INTEL_MID_POWER_BUTTON
 	tristate "power button driver for Intel MID platforms"
 	depends on INTEL_SCU_IPC && INPUT
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index d4111f0f8a78..b2f52a7690af 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -50,7 +50,6 @@ obj-$(CONFIG_INTEL_SCU_IPC)	+= intel_scu_ipc.o
 obj-$(CONFIG_INTEL_SCU_IPC_UTIL) += intel_scu_ipcutil.o
 obj-$(CONFIG_INTEL_MFLD_THERMAL) += intel_mid_thermal.o
 obj-$(CONFIG_INTEL_IPS)		+= intel_ips.o
-obj-$(CONFIG_GPIO_INTEL_PMIC)	+= intel_pmic_gpio.o
 obj-$(CONFIG_XO1_RFKILL)	+= xo1-rfkill.o
 obj-$(CONFIG_XO15_EBOOK)	+= xo15-ebook.o
 obj-$(CONFIG_IBM_RTL)		+= ibm_rtl.o
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index 410741acb3c9..f46ece2ce3c4 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -813,6 +813,7 @@ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data)
 			case 8:
 			case 7:
 			case 6:
+			case 1:
 				ideapad_input_report(priv, vpc_bit);
 				break;
 			case 5:
diff --git a/drivers/platform/x86/intel_mid_powerbtn.c b/drivers/platform/x86/intel_mid_powerbtn.c
index 1fc0de870ff8..361770568ad0 100644
--- a/drivers/platform/x86/intel_mid_powerbtn.c
+++ b/drivers/platform/x86/intel_mid_powerbtn.c
@@ -77,7 +77,7 @@ static int mfld_pb_probe(struct platform_device *pdev)
 
 	input_set_capability(input, EV_KEY, KEY_POWER);
 
-	error = request_threaded_irq(irq, NULL, mfld_pb_isr, 0,
+	error = request_threaded_irq(irq, NULL, mfld_pb_isr, IRQF_ONESHOT,
 				     DRIVER_NAME, input);
 	if (error) {
 		dev_err(&pdev->dev, "Unable to request irq %d for mfld power"
diff --git a/drivers/platform/x86/intel_pmic_gpio.c b/drivers/platform/x86/intel_pmic_gpio.c
deleted file mode 100644
index 91ae58510d92..000000000000
--- a/drivers/platform/x86/intel_pmic_gpio.c
+++ /dev/null
@@ -1,326 +0,0 @@
-/* Moorestown PMIC GPIO (access through IPC) driver
- * Copyright (c) 2008 - 2009, Intel Corporation.
- *
- * Author: Alek Du <alek.du@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-/* Supports:
- * Moorestown platform PMIC chip
- */
-
-#define pr_fmt(fmt) "%s: " fmt, __func__
-
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/stddef.h>
-#include <linux/slab.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/gpio/driver.h>
-#include <asm/intel_scu_ipc.h>
-#include <linux/device.h>
-#include <linux/intel_pmic_gpio.h>
-#include <linux/platform_device.h>
-
-#define DRIVER_NAME "pmic_gpio"
-
-/* register offset that IPC driver should use
- * 8 GPIO + 8 GPOSW (6 controllable) + 8GPO
- */
-enum pmic_gpio_register {
-	GPIO0		= 0xE0,
-	GPIO7		= 0xE7,
-	GPIOINT		= 0xE8,
-	GPOSWCTL0	= 0xEC,
-	GPOSWCTL5	= 0xF1,
-	GPO		= 0xF4,
-};
-
-/* bits definition for GPIO & GPOSW */
-#define GPIO_DRV 0x01
-#define GPIO_DIR 0x02
-#define GPIO_DIN 0x04
-#define GPIO_DOU 0x08
-#define GPIO_INTCTL 0x30
-#define GPIO_DBC 0xc0
-
-#define GPOSW_DRV 0x01
-#define GPOSW_DOU 0x08
-#define GPOSW_RDRV 0x30
-
-#define GPIO_UPDATE_TYPE	0x80000000
-
-#define NUM_GPIO 24
-
-struct pmic_gpio {
-	struct mutex		buslock;
-	struct gpio_chip	chip;
-	void			*gpiointr;
-	int			irq;
-	unsigned		irq_base;
-	unsigned int		update_type;
-	u32			trigger_type;
-};
-
-static void pmic_program_irqtype(int gpio, int type)
-{
-	if (type & IRQ_TYPE_EDGE_RISING)
-		intel_scu_ipc_update_register(GPIO0 + gpio, 0x20, 0x20);
-	else
-		intel_scu_ipc_update_register(GPIO0 + gpio, 0x00, 0x20);
-
-	if (type & IRQ_TYPE_EDGE_FALLING)
-		intel_scu_ipc_update_register(GPIO0 + gpio, 0x10, 0x10);
-	else
-		intel_scu_ipc_update_register(GPIO0 + gpio, 0x00, 0x10);
-};
-
-static int pmic_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
-{
-	if (offset >= 8) {
-		pr_err("only pin 0-7 support input\n");
-		return -1;/* we only have 8 GPIO can use as input */
-	}
-	return intel_scu_ipc_update_register(GPIO0 + offset,
-							GPIO_DIR, GPIO_DIR);
-}
-
-static int pmic_gpio_direction_output(struct gpio_chip *chip,
-			unsigned offset, int value)
-{
-	int rc = 0;
-
-	if (offset < 8)/* it is GPIO */
-		rc = intel_scu_ipc_update_register(GPIO0 + offset,
-				GPIO_DRV | (value ? GPIO_DOU : 0),
-				GPIO_DRV | GPIO_DOU | GPIO_DIR);
-	else if (offset < 16)/* it is GPOSW */
-		rc = intel_scu_ipc_update_register(GPOSWCTL0 + offset - 8,
-				GPOSW_DRV | (value ? GPOSW_DOU : 0),
-				GPOSW_DRV | GPOSW_DOU | GPOSW_RDRV);
-	else if (offset > 15 && offset < 24)/* it is GPO */
-		rc = intel_scu_ipc_update_register(GPO,
-				value ? 1 << (offset - 16) : 0,
-				1 << (offset - 16));
-	else {
-		pr_err("invalid PMIC GPIO pin %d!\n", offset);
-		WARN_ON(1);
-	}
-
-	return rc;
-}
-
-static int pmic_gpio_get(struct gpio_chip *chip, unsigned offset)
-{
-	u8 r;
-	int ret;
-
-	/* we only have 8 GPIO pins we can use as input */
-	if (offset >= 8)
-		return -EOPNOTSUPP;
-	ret = intel_scu_ipc_ioread8(GPIO0 + offset, &r);
-	if (ret < 0)
-		return ret;
-	return r & GPIO_DIN;
-}
-
-static void pmic_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
-{
-	if (offset < 8)/* it is GPIO */
-		intel_scu_ipc_update_register(GPIO0 + offset,
-			GPIO_DRV | (value ? GPIO_DOU : 0),
-			GPIO_DRV | GPIO_DOU);
-	else if (offset < 16)/* it is GPOSW */
-		intel_scu_ipc_update_register(GPOSWCTL0 + offset - 8,
-			GPOSW_DRV | (value ? GPOSW_DOU : 0),
-			GPOSW_DRV | GPOSW_DOU | GPOSW_RDRV);
-	else if (offset > 15 && offset < 24) /* it is GPO */
-		intel_scu_ipc_update_register(GPO,
-			value ? 1 << (offset - 16) : 0,
-			1 << (offset - 16));
-}
-
-/*
- * This is called from genirq with pg->buslock locked and
- * irq_desc->lock held. We can not access the scu bus here, so we
- * store the change and update in the bus_sync_unlock() function below
- */
-static int pmic_irq_type(struct irq_data *data, unsigned type)
-{
-	struct pmic_gpio *pg = irq_data_get_irq_chip_data(data);
-	u32 gpio = data->irq - pg->irq_base;
-
-	if (gpio >= pg->chip.ngpio)
-		return -EINVAL;
-
-	pg->trigger_type = type;
-	pg->update_type = gpio | GPIO_UPDATE_TYPE;
-	return 0;
-}
-
-static int pmic_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
-{
-	struct pmic_gpio *pg = gpiochip_get_data(chip);
-
-	return pg->irq_base + offset;
-}
-
-static void pmic_bus_lock(struct irq_data *data)
-{
-	struct pmic_gpio *pg = irq_data_get_irq_chip_data(data);
-
-	mutex_lock(&pg->buslock);
-}
-
-static void pmic_bus_sync_unlock(struct irq_data *data)
-{
-	struct pmic_gpio *pg = irq_data_get_irq_chip_data(data);
-
-	if (pg->update_type) {
-		unsigned int gpio = pg->update_type & ~GPIO_UPDATE_TYPE;
-
-		pmic_program_irqtype(gpio, pg->trigger_type);
-		pg->update_type = 0;
-	}
-	mutex_unlock(&pg->buslock);
-}
-
-/* the gpiointr register is read-clear, so just do nothing. */
-static void pmic_irq_unmask(struct irq_data *data) { }
-
-static void pmic_irq_mask(struct irq_data *data) { }
-
-static struct irq_chip pmic_irqchip = {
-	.name			= "PMIC-GPIO",
-	.irq_mask		= pmic_irq_mask,
-	.irq_unmask		= pmic_irq_unmask,
-	.irq_set_type		= pmic_irq_type,
-	.irq_bus_lock		= pmic_bus_lock,
-	.irq_bus_sync_unlock	= pmic_bus_sync_unlock,
-};
-
-static irqreturn_t pmic_irq_handler(int irq, void *data)
-{
-	struct pmic_gpio *pg = data;
-	u8 intsts = *((u8 *)pg->gpiointr + 4);
-	int gpio;
-	irqreturn_t ret = IRQ_NONE;
-
-	for (gpio = 0; gpio < 8; gpio++) {
-		if (intsts & (1 << gpio)) {
-			pr_debug("pmic pin %d triggered\n", gpio);
-			generic_handle_irq(pg->irq_base + gpio);
-			ret = IRQ_HANDLED;
-		}
-	}
-	return ret;
-}
-
-static int platform_pmic_gpio_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	int irq = platform_get_irq(pdev, 0);
-	struct intel_pmic_gpio_platform_data *pdata = dev->platform_data;
-
-	struct pmic_gpio *pg;
-	int retval;
-	int i;
-
-	if (irq < 0) {
-		dev_dbg(dev, "no IRQ line\n");
-		return -EINVAL;
-	}
-
-	if (!pdata || !pdata->gpio_base || !pdata->irq_base) {
-		dev_dbg(dev, "incorrect or missing platform data\n");
-		return -EINVAL;
-	}
-
-	pg = kzalloc(sizeof(*pg), GFP_KERNEL);
-	if (!pg)
-		return -ENOMEM;
-
-	dev_set_drvdata(dev, pg);
-
-	pg->irq = irq;
-	/* setting up SRAM mapping for GPIOINT register */
-	pg->gpiointr = ioremap_nocache(pdata->gpiointr, 8);
-	if (!pg->gpiointr) {
-		pr_err("Can not map GPIOINT\n");
-		retval = -EINVAL;
-		goto err2;
-	}
-	pg->irq_base = pdata->irq_base;
-	pg->chip.label = "intel_pmic";
-	pg->chip.direction_input = pmic_gpio_direction_input;
-	pg->chip.direction_output = pmic_gpio_direction_output;
-	pg->chip.get = pmic_gpio_get;
-	pg->chip.set = pmic_gpio_set;
-	pg->chip.to_irq = pmic_gpio_to_irq;
-	pg->chip.base = pdata->gpio_base;
-	pg->chip.ngpio = NUM_GPIO;
-	pg->chip.can_sleep = 1;
-	pg->chip.parent = dev;
-
-	mutex_init(&pg->buslock);
-
-	pg->chip.parent = dev;
-	retval = gpiochip_add_data(&pg->chip, pg);
-	if (retval) {
-		pr_err("Can not add pmic gpio chip\n");
-		goto err;
-	}
-
-	retval = request_irq(pg->irq, pmic_irq_handler, 0, "pmic", pg);
-	if (retval) {
-		pr_warn("Interrupt request failed\n");
-		goto fail_request_irq;
-	}
-
-	for (i = 0; i < 8; i++) {
-		irq_set_chip_and_handler_name(i + pg->irq_base,
-					      &pmic_irqchip,
-					      handle_simple_irq,
-					      "demux");
-		irq_set_chip_data(i + pg->irq_base, pg);
-	}
-	return 0;
-
-fail_request_irq:
-	gpiochip_remove(&pg->chip);
-err:
-	iounmap(pg->gpiointr);
-err2:
-	kfree(pg);
-	return retval;
-}
-
-/* at the same time, register a platform driver
- * this supports the sfi 0.81 fw */
-static struct platform_driver platform_pmic_gpio_driver = {
-	.driver = {
-		.name		= DRIVER_NAME,
-	},
-	.probe		= platform_pmic_gpio_probe,
-};
-
-static int __init platform_pmic_gpio_init(void)
-{
-	return platform_driver_register(&platform_pmic_gpio_driver);
-}
-subsys_initcall(platform_pmic_gpio_init);
diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c
index 97b4c3a219c0..25f15df5c2d7 100644
--- a/drivers/platform/x86/mlx-platform.c
+++ b/drivers/platform/x86/mlx-platform.c
@@ -326,7 +326,7 @@ static int __init mlxplat_init(void)
 	return 0;
 
 fail_platform_mux_register:
-	for (i--; i > 0 ; i--)
+	while (--i >= 0)
 		platform_device_unregister(priv->pdev_mux[i]);
 	platform_device_unregister(priv->pdev_i2c);
 fail_alloc:
diff --git a/drivers/platform/x86/surface3-wmi.c b/drivers/platform/x86/surface3-wmi.c
index cbf4d83a7271..25b176996cb7 100644
--- a/drivers/platform/x86/surface3-wmi.c
+++ b/drivers/platform/x86/surface3-wmi.c
@@ -139,7 +139,7 @@ static acpi_status s3_wmi_attach_spi_device(acpi_handle handle,
 
 static int s3_wmi_check_platform_device(struct device *dev, void *data)
 {
-	struct acpi_device *adev, *ts_adev;
+	struct acpi_device *adev, *ts_adev = NULL;
 	acpi_handle handle;
 	acpi_status status;
 
@@ -244,13 +244,11 @@ static int s3_wmi_remove(struct platform_device *device)
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int s3_wmi_resume(struct device *dev)
+static int __maybe_unused s3_wmi_resume(struct device *dev)
 {
 	s3_wmi_send_lid_state();
 	return 0;
 }
-#endif
 static SIMPLE_DEV_PM_OPS(s3_wmi_pm, NULL, s3_wmi_resume);
 
 static struct platform_driver s3_wmi_driver = {
diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig
index abeb77217a21..b8cacccf18c8 100644
--- a/drivers/power/reset/Kconfig
+++ b/drivers/power/reset/Kconfig
@@ -32,7 +32,7 @@ config POWER_RESET_AT91_RESET
 
 config POWER_RESET_AT91_SAMA5D2_SHDWC
 	tristate "Atmel AT91 SAMA5D2-Compatible shutdown controller driver"
-	depends on ARCH_AT91 || COMPILE_TEST
+	depends on ARCH_AT91
 	default SOC_SAMA5
 	help
 	  This driver supports the alternate shutdown controller for some Atmel
diff --git a/drivers/power/reset/at91-poweroff.c b/drivers/power/reset/at91-poweroff.c
index a85dd4d233af..c6c3beea72f9 100644
--- a/drivers/power/reset/at91-poweroff.c
+++ b/drivers/power/reset/at91-poweroff.c
@@ -14,9 +14,12 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/platform_device.h>
 #include <linux/printk.h>
 
+#include <soc/at91/at91sam9_ddrsdr.h>
+
 #define AT91_SHDW_CR	0x00		/* Shut Down Control Register */
 #define AT91_SHDW_SHDW		BIT(0)			/* Shut Down command */
 #define AT91_SHDW_KEY		(0xa5 << 24)		/* KEY Password */
@@ -50,6 +53,7 @@ static const char *shdwc_wakeup_modes[] = {
 
 static void __iomem *at91_shdwc_base;
 static struct clk *sclk;
+static void __iomem *mpddrc_base;
 
 static void __init at91_wakeup_status(void)
 {
@@ -73,6 +77,29 @@ static void at91_poweroff(void)
 	writel(AT91_SHDW_KEY | AT91_SHDW_SHDW, at91_shdwc_base + AT91_SHDW_CR);
 }
 
+static void at91_lpddr_poweroff(void)
+{
+	asm volatile(
+		/* Align to cache lines */
+		".balign 32\n\t"
+
+		/* Ensure AT91_SHDW_CR is in the TLB by reading it */
+		"	ldr	r6, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t"
+
+		/* Power down SDRAM0 */
+		"	str	%1, [%0, #" __stringify(AT91_DDRSDRC_LPR) "]\n\t"
+		/* Shutdown CPU */
+		"	str	%3, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t"
+
+		"	b	.\n\t"
+		:
+		: "r" (mpddrc_base),
+		  "r" cpu_to_le32(AT91_DDRSDRC_LPDDR2_PWOFF),
+		  "r" (at91_shdwc_base),
+		  "r" cpu_to_le32(AT91_SHDW_KEY | AT91_SHDW_SHDW)
+		: "r0");
+}
+
 static int at91_poweroff_get_wakeup_mode(struct device_node *np)
 {
 	const char *pm;
@@ -124,6 +151,8 @@ static void at91_poweroff_dt_set_wakeup_mode(struct platform_device *pdev)
 static int __init at91_poweroff_probe(struct platform_device *pdev)
 {
 	struct resource *res;
+	struct device_node *np;
+	u32 ddr_type;
 	int ret;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -150,12 +179,30 @@ static int __init at91_poweroff_probe(struct platform_device *pdev)
 
 	pm_power_off = at91_poweroff;
 
+	np = of_find_compatible_node(NULL, NULL, "atmel,sama5d3-ddramc");
+	if (!np)
+		return 0;
+
+	mpddrc_base = of_iomap(np, 0);
+	of_node_put(np);
+
+	if (!mpddrc_base)
+		return 0;
+
+	ddr_type = readl(mpddrc_base + AT91_DDRSDRC_MDR) & AT91_DDRSDRC_MD;
+	if ((ddr_type == AT91_DDRSDRC_MD_LPDDR2) ||
+	    (ddr_type == AT91_DDRSDRC_MD_LPDDR3))
+		pm_power_off = at91_lpddr_poweroff;
+	else
+		iounmap(mpddrc_base);
+
 	return 0;
 }
 
 static int __exit at91_poweroff_remove(struct platform_device *pdev)
 {
-	if (pm_power_off == at91_poweroff)
+	if (pm_power_off == at91_poweroff ||
+	    pm_power_off == at91_lpddr_poweroff)
 		pm_power_off = NULL;
 
 	clk_disable_unprepare(sclk);
@@ -163,6 +210,11 @@ static int __exit at91_poweroff_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id at91_ramc_of_match[] = {
+	{ .compatible = "atmel,sama5d3-ddramc", },
+	{ /* sentinel */ }
+};
+
 static const struct of_device_id at91_poweroff_of_match[] = {
 	{ .compatible = "atmel,at91sam9260-shdwc", },
 	{ .compatible = "atmel,at91sam9rl-shdwc", },
diff --git a/drivers/power/reset/at91-reset.c b/drivers/power/reset/at91-reset.c
index 568580cf0655..b99769f8ab15 100644
--- a/drivers/power/reset/at91-reset.c
+++ b/drivers/power/reset/at91-reset.c
@@ -134,6 +134,15 @@ static int sama5d3_restart(struct notifier_block *this, unsigned long mode,
 	return NOTIFY_DONE;
 }
 
+static int samx7_restart(struct notifier_block *this, unsigned long mode,
+			 void *cmd)
+{
+	writel(cpu_to_le32(AT91_RSTC_KEY | AT91_RSTC_PROCRST),
+	       at91_rstc_base);
+
+	return NOTIFY_DONE;
+}
+
 static void __init at91_reset_status(struct platform_device *pdev)
 {
 	u32 reg = readl(at91_rstc_base + AT91_RSTC_SR);
@@ -173,6 +182,7 @@ static const struct of_device_id at91_reset_of_match[] = {
 	{ .compatible = "atmel,at91sam9260-rstc", .data = at91sam9260_restart },
 	{ .compatible = "atmel,at91sam9g45-rstc", .data = at91sam9g45_restart },
 	{ .compatible = "atmel,sama5d3-rstc", .data = sama5d3_restart },
+	{ .compatible = "atmel,samx7-rstc", .data = samx7_restart },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, at91_reset_of_match);
@@ -238,20 +248,12 @@ static int __exit at91_reset_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct platform_device_id at91_reset_plat_match[] = {
-	{ "at91-sam9260-reset", (unsigned long)at91sam9260_restart },
-	{ "at91-sam9g45-reset", (unsigned long)at91sam9g45_restart },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(platform, at91_reset_plat_match);
-
 static struct platform_driver at91_reset_driver = {
 	.remove = __exit_p(at91_reset_remove),
 	.driver = {
 		.name = "at91-reset",
 		.of_match_table = at91_reset_of_match,
 	},
-	.id_table = at91_reset_plat_match,
 };
 module_platform_driver_probe(at91_reset_driver, at91_reset_probe);
 
diff --git a/drivers/power/reset/at91-sama5d2_shdwc.c b/drivers/power/reset/at91-sama5d2_shdwc.c
index 8a5ac9706c9c..90b0b5a70ce5 100644
--- a/drivers/power/reset/at91-sama5d2_shdwc.c
+++ b/drivers/power/reset/at91-sama5d2_shdwc.c
@@ -22,9 +22,12 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/platform_device.h>
 #include <linux/printk.h>
 
+#include <soc/at91/at91sam9_ddrsdr.h>
+
 #define SLOW_CLOCK_FREQ	32768
 
 #define AT91_SHDW_CR	0x00		/* Shut Down Control Register */
@@ -75,6 +78,7 @@ struct shdwc {
  */
 static struct shdwc *at91_shdwc;
 static struct clk *sclk;
+static void __iomem *mpddrc_base;
 
 static const unsigned long long sdwc_dbc_period[] = {
 	0, 3, 32, 512, 4096, 32768,
@@ -108,6 +112,29 @@ static void at91_poweroff(void)
 	       at91_shdwc->at91_shdwc_base + AT91_SHDW_CR);
 }
 
+static void at91_lpddr_poweroff(void)
+{
+	asm volatile(
+		/* Align to cache lines */
+		".balign 32\n\t"
+
+		/* Ensure AT91_SHDW_CR is in the TLB by reading it */
+		"	ldr	r6, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t"
+
+		/* Power down SDRAM0 */
+		"	str	%1, [%0, #" __stringify(AT91_DDRSDRC_LPR) "]\n\t"
+		/* Shutdown CPU */
+		"	str	%3, [%2, #" __stringify(AT91_SHDW_CR) "]\n\t"
+
+		"	b	.\n\t"
+		:
+		: "r" (mpddrc_base),
+		  "r" cpu_to_le32(AT91_DDRSDRC_LPDDR2_PWOFF),
+		  "r" (at91_shdwc->at91_shdwc_base),
+		  "r" cpu_to_le32(AT91_SHDW_KEY | AT91_SHDW_SHDW)
+		: "r0");
+}
+
 static u32 at91_shdwc_debouncer_value(struct platform_device *pdev,
 				      u32 in_period_us)
 {
@@ -212,6 +239,8 @@ static int __init at91_shdwc_probe(struct platform_device *pdev)
 {
 	struct resource *res;
 	const struct of_device_id *match;
+	struct device_node *np;
+	u32 ddr_type;
 	int ret;
 
 	if (!pdev->dev.of_node)
@@ -249,6 +278,23 @@ static int __init at91_shdwc_probe(struct platform_device *pdev)
 
 	pm_power_off = at91_poweroff;
 
+	np = of_find_compatible_node(NULL, NULL, "atmel,sama5d3-ddramc");
+	if (!np)
+		return 0;
+
+	mpddrc_base = of_iomap(np, 0);
+	of_node_put(np);
+
+	if (!mpddrc_base)
+		return 0;
+
+	ddr_type = readl(mpddrc_base + AT91_DDRSDRC_MDR) & AT91_DDRSDRC_MD;
+	if ((ddr_type == AT91_DDRSDRC_MD_LPDDR2) ||
+	    (ddr_type == AT91_DDRSDRC_MD_LPDDR3))
+		pm_power_off = at91_lpddr_poweroff;
+	else
+		iounmap(mpddrc_base);
+
 	return 0;
 }
 
@@ -256,7 +302,8 @@ static int __exit at91_shdwc_remove(struct platform_device *pdev)
 {
 	struct shdwc *shdw = platform_get_drvdata(pdev);
 
-	if (pm_power_off == at91_poweroff)
+	if (pm_power_off == at91_poweroff ||
+	    pm_power_off == at91_lpddr_poweroff)
 		pm_power_off = NULL;
 
 	/* Reset values to disable wake-up features  */
diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig
index 76806a0be820..da54ac88f068 100644
--- a/drivers/power/supply/Kconfig
+++ b/drivers/power/supply/Kconfig
@@ -164,6 +164,12 @@ config BATTERY_SBS
 	  Say Y to include support for SBS battery driver for SBS-compliant
 	  gas gauges.
 
+config CHARGER_SBS
+        tristate "SBS Compliant charger"
+        depends on I2C
+        help
+	  Say Y to include support for SBS compilant battery chargers.
+
 config BATTERY_BQ27XXX
 	tristate "BQ27xxx battery driver"
 	help
@@ -214,6 +220,18 @@ config BATTERY_DA9150
 	  This driver can also be built as a module. If so, the module will be
 	  called da9150-fg.
 
+config CHARGER_AXP20X
+	tristate "X-Powers AXP20X and AXP22X AC power supply driver"
+	depends on MFD_AXP20X
+	depends on AXP20X_ADC
+	depends on IIO
+	help
+	  Say Y here to enable support for X-Powers AXP20X and AXP22X PMICs' AC
+	  power supply.
+
+	  This driver can also be built as a module. If so, the module will be
+	  called axp20x_ac_power.
+
 config AXP288_CHARGER
 	tristate "X-Powers AXP288 Charger"
 	depends on MFD_AXP20X && EXTCON_AXP288
@@ -292,13 +310,6 @@ config BATTERY_JZ4740
 	  This driver can be build as a module. If so, the module will be
 	  called jz4740-battery.
 
-config BATTERY_INTEL_MID
-	tristate "Battery driver for Intel MID platforms"
-	depends on INTEL_SCU_IPC && SPI
-	help
-	  Say Y here to enable the battery driver on Intel MID
-	  platforms.
-
 config BATTERY_RX51
 	tristate "Nokia RX-51 (N900) battery driver"
 	depends on TWL4030_MADC
@@ -370,6 +381,16 @@ config CHARGER_MAX14577
 	  Say Y to enable support for the battery charger control sysfs and
 	  platform data of MAX14577/77836 MUICs.
 
+config CHARGER_DETECTOR_MAX14656
+	tristate "Maxim MAX14656 USB charger detector"
+	depends on I2C
+	depends on OF
+	help
+	  Say Y to enable support for the Maxim MAX14656 USB charger detector.
+	  The device is compliant with the USB Battery Charging Specification
+	  Revision 1.2 and can be found e.g. in Kindle 4/5th generation
+	  readers and certain LG devices.
+
 config CHARGER_MAX77693
 	tristate "Maxim MAX77693 battery charger driver"
 	depends on MFD_MAX77693
@@ -395,6 +416,7 @@ config CHARGER_QCOM_SMBB
 	depends on MFD_SPMI_PMIC || COMPILE_TEST
 	depends on OF
 	depends on EXTCON
+	depends on REGULATOR
 	help
 	  Say Y to include support for the Switch-Mode Battery Charger and
 	  Boost (SMBB) hardware found in Qualcomm PM8941 PMICs.  The charger
diff --git a/drivers/power/supply/Makefile b/drivers/power/supply/Makefile
index 36c599d9a495..3789a2c06fdf 100644
--- a/drivers/power/supply/Makefile
+++ b/drivers/power/supply/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_TEST_POWER)	+= test_power.o
 
 obj-$(CONFIG_BATTERY_88PM860X)	+= 88pm860x_battery.o
 obj-$(CONFIG_BATTERY_ACT8945A)	+= act8945a_charger.o
+obj-$(CONFIG_CHARGER_AXP20X)	+= axp20x_ac_power.o
 obj-$(CONFIG_BATTERY_DS2760)	+= ds2760_battery.o
 obj-$(CONFIG_BATTERY_DS2780)	+= ds2780_battery.o
 obj-$(CONFIG_BATTERY_DS2781)	+= ds2781_battery.o
@@ -31,6 +32,7 @@ obj-$(CONFIG_BATTERY_COLLIE)	+= collie_battery.o
 obj-$(CONFIG_BATTERY_IPAQ_MICRO) += ipaq_micro_battery.o
 obj-$(CONFIG_BATTERY_WM97XX)	+= wm97xx_battery.o
 obj-$(CONFIG_BATTERY_SBS)	+= sbs-battery.o
+obj-$(CONFIG_CHARGER_SBS)	+= sbs-charger.o
 obj-$(CONFIG_BATTERY_BQ27XXX)	+= bq27xxx_battery.o
 obj-$(CONFIG_BATTERY_BQ27XXX_I2C) += bq27xxx_battery_i2c.o
 obj-$(CONFIG_BATTERY_DA9030)	+= da9030_battery.o
@@ -47,7 +49,6 @@ obj-$(CONFIG_BATTERY_TWL4030_MADC)	+= twl4030_madc_battery.o
 obj-$(CONFIG_CHARGER_88PM860X)	+= 88pm860x_charger.o
 obj-$(CONFIG_CHARGER_PCF50633)	+= pcf50633-charger.o
 obj-$(CONFIG_BATTERY_JZ4740)	+= jz4740-battery.o
-obj-$(CONFIG_BATTERY_INTEL_MID)	+= intel_mid_battery.o
 obj-$(CONFIG_BATTERY_RX51)	+= rx51_battery.o
 obj-$(CONFIG_AB8500_BM)		+= ab8500_bmdata.o ab8500_charger.o ab8500_fg.o ab8500_btemp.o abx500_chargalg.o pm2301_charger.o
 obj-$(CONFIG_CHARGER_ISP1704)	+= isp1704_charger.o
@@ -58,6 +59,7 @@ obj-$(CONFIG_CHARGER_LP8788)	+= lp8788-charger.o
 obj-$(CONFIG_CHARGER_GPIO)	+= gpio-charger.o
 obj-$(CONFIG_CHARGER_MANAGER)	+= charger-manager.o
 obj-$(CONFIG_CHARGER_MAX14577)	+= max14577_charger.o
+obj-$(CONFIG_CHARGER_DETECTOR_MAX14656)	+= max14656_charger_detector.o
 obj-$(CONFIG_CHARGER_MAX77693)	+= max77693_charger.o
 obj-$(CONFIG_CHARGER_MAX8997)	+= max8997_charger.o
 obj-$(CONFIG_CHARGER_MAX8998)	+= max8998_charger.o
diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c
index 6ffdc18f2599..f7a35ebfbab2 100644
--- a/drivers/power/supply/ab8500_btemp.c
+++ b/drivers/power/supply/ab8500_btemp.c
@@ -76,8 +76,8 @@ struct ab8500_btemp_ranges {
  * @dev:		Pointer to the structure device
  * @node:		List of AB8500 BTEMPs, hence prepared for reentrance
  * @curr_source:	What current source we use, in uA
- * @bat_temp:		Dispatched battery temperature in degree Celcius
- * @prev_bat_temp	Last measured battery temperature in degree Celcius
+ * @bat_temp:		Dispatched battery temperature in degree Celsius
+ * @prev_bat_temp	Last measured battery temperature in degree Celsius
  * @parent:		Pointer to the struct ab8500
  * @gpadc:		Pointer to the struct gpadc
  * @fg:			Pointer to the struct fg
@@ -123,10 +123,7 @@ static LIST_HEAD(ab8500_btemp_list);
  */
 struct ab8500_btemp *ab8500_btemp_get(void)
 {
-	struct ab8500_btemp *btemp;
-	btemp = list_first_entry(&ab8500_btemp_list, struct ab8500_btemp, node);
-
-	return btemp;
+	return list_first_entry(&ab8500_btemp_list, struct ab8500_btemp, node);
 }
 EXPORT_SYMBOL(ab8500_btemp_get);
 
@@ -464,13 +461,13 @@ static int ab8500_btemp_get_batctrl_res(struct ab8500_btemp *di)
  * @tbl_size:	size of the resistance to temperature table
  * @res:	resistance to calculate the temperature from
  *
- * This function returns the battery temperature in degrees Celcius
+ * This function returns the battery temperature in degrees Celsius
  * based on the NTC resistance.
  */
 static int ab8500_btemp_res_to_temp(struct ab8500_btemp *di,
 	const struct abx500_res_to_temp *tbl, int tbl_size, int res)
 {
-	int i, temp;
+	int i;
 	/*
 	 * Calculate the formula for the straight line
 	 * Simple interpolation if we are within
@@ -488,9 +485,8 @@ static int ab8500_btemp_res_to_temp(struct ab8500_btemp *di,
 			i++;
 	}
 
-	temp = tbl[i].temp + ((tbl[i + 1].temp - tbl[i].temp) *
+	return tbl[i].temp + ((tbl[i + 1].temp - tbl[i].temp) *
 		(res - tbl[i].resist)) / (tbl[i + 1].resist - tbl[i].resist);
-	return temp;
 }
 
 /**
diff --git a/drivers/power/supply/axp20x_ac_power.c b/drivers/power/supply/axp20x_ac_power.c
new file mode 100644
index 000000000000..38f4e87cf24d
--- /dev/null
+++ b/drivers/power/supply/axp20x_ac_power.c
@@ -0,0 +1,253 @@
+/*
+ * AXP20X and AXP22X PMICs' ACIN power supply driver
+ *
+ * Copyright (C) 2016 Free Electrons
+ *	Quentin Schulz <quentin.schulz@free-electrons.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under  the terms of the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/axp20x.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/iio/consumer.h>
+
+#define AXP20X_PWR_STATUS_ACIN_PRESENT	BIT(7)
+#define AXP20X_PWR_STATUS_ACIN_AVAIL	BIT(6)
+
+#define DRVNAME "axp20x-ac-power-supply"
+
+struct axp20x_ac_power {
+	struct regmap *regmap;
+	struct power_supply *supply;
+	struct iio_channel *acin_v;
+	struct iio_channel *acin_i;
+};
+
+static irqreturn_t axp20x_ac_power_irq(int irq, void *devid)
+{
+	struct axp20x_ac_power *power = devid;
+
+	power_supply_changed(power->supply);
+
+	return IRQ_HANDLED;
+}
+
+static int axp20x_ac_power_get_property(struct power_supply *psy,
+					enum power_supply_property psp,
+					union power_supply_propval *val)
+{
+	struct axp20x_ac_power *power = power_supply_get_drvdata(psy);
+	int ret, reg;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_HEALTH:
+		ret = regmap_read(power->regmap, AXP20X_PWR_INPUT_STATUS, &reg);
+		if (ret)
+			return ret;
+
+		if (reg & AXP20X_PWR_STATUS_ACIN_PRESENT) {
+			val->intval = POWER_SUPPLY_HEALTH_GOOD;
+			return 0;
+		}
+
+		val->intval = POWER_SUPPLY_HEALTH_UNKNOWN;
+		return 0;
+
+	case POWER_SUPPLY_PROP_PRESENT:
+		ret = regmap_read(power->regmap, AXP20X_PWR_INPUT_STATUS, &reg);
+		if (ret)
+			return ret;
+
+		val->intval = !!(reg & AXP20X_PWR_STATUS_ACIN_PRESENT);
+		return 0;
+
+	case POWER_SUPPLY_PROP_ONLINE:
+		ret = regmap_read(power->regmap, AXP20X_PWR_INPUT_STATUS, &reg);
+		if (ret)
+			return ret;
+
+		val->intval = !!(reg & AXP20X_PWR_STATUS_ACIN_AVAIL);
+		return 0;
+
+	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		ret = iio_read_channel_processed(power->acin_v, &val->intval);
+		if (ret)
+			return ret;
+
+		/* IIO framework gives mV but Power Supply framework gives uV */
+		val->intval *= 1000;
+
+		return 0;
+
+	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		ret = iio_read_channel_processed(power->acin_i, &val->intval);
+		if (ret)
+			return ret;
+
+		/* IIO framework gives mA but Power Supply framework gives uA */
+		val->intval *= 1000;
+
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}
+
+static enum power_supply_property axp20x_ac_power_properties[] = {
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+};
+
+static enum power_supply_property axp22x_ac_power_properties[] = {
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_ONLINE,
+};
+
+static const struct power_supply_desc axp20x_ac_power_desc = {
+	.name = "axp20x-ac",
+	.type = POWER_SUPPLY_TYPE_MAINS,
+	.properties = axp20x_ac_power_properties,
+	.num_properties = ARRAY_SIZE(axp20x_ac_power_properties),
+	.get_property = axp20x_ac_power_get_property,
+};
+
+static const struct power_supply_desc axp22x_ac_power_desc = {
+	.name = "axp22x-ac",
+	.type = POWER_SUPPLY_TYPE_MAINS,
+	.properties = axp22x_ac_power_properties,
+	.num_properties = ARRAY_SIZE(axp22x_ac_power_properties),
+	.get_property = axp20x_ac_power_get_property,
+};
+
+struct axp_data {
+	const struct power_supply_desc	*power_desc;
+	bool				acin_adc;
+};
+
+static const struct axp_data axp20x_data = {
+	.power_desc = &axp20x_ac_power_desc,
+	.acin_adc = true,
+};
+
+static const struct axp_data axp22x_data = {
+	.power_desc = &axp22x_ac_power_desc,
+	.acin_adc = false,
+};
+
+static int axp20x_ac_power_probe(struct platform_device *pdev)
+{
+	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
+	struct power_supply_config psy_cfg = {};
+	struct axp20x_ac_power *power;
+	struct axp_data *axp_data;
+	static const char * const irq_names[] = { "ACIN_PLUGIN", "ACIN_REMOVAL",
+		NULL };
+	int i, irq, ret;
+
+	if (!of_device_is_available(pdev->dev.of_node))
+		return -ENODEV;
+
+	if (!axp20x) {
+		dev_err(&pdev->dev, "Parent drvdata not set\n");
+		return -EINVAL;
+	}
+
+	power = devm_kzalloc(&pdev->dev, sizeof(*power), GFP_KERNEL);
+	if (!power)
+		return -ENOMEM;
+
+	axp_data = (struct axp_data *)of_device_get_match_data(&pdev->dev);
+
+	if (axp_data->acin_adc) {
+		power->acin_v = devm_iio_channel_get(&pdev->dev, "acin_v");
+		if (IS_ERR(power->acin_v)) {
+			if (PTR_ERR(power->acin_v) == -ENODEV)
+				return -EPROBE_DEFER;
+			return PTR_ERR(power->acin_v);
+		}
+
+		power->acin_i = devm_iio_channel_get(&pdev->dev, "acin_i");
+		if (IS_ERR(power->acin_i)) {
+			if (PTR_ERR(power->acin_i) == -ENODEV)
+				return -EPROBE_DEFER;
+			return PTR_ERR(power->acin_i);
+		}
+	}
+
+	power->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+
+	platform_set_drvdata(pdev, power);
+
+	psy_cfg.of_node = pdev->dev.of_node;
+	psy_cfg.drv_data = power;
+
+	power->supply = devm_power_supply_register(&pdev->dev,
+						   axp_data->power_desc,
+						   &psy_cfg);
+	if (IS_ERR(power->supply))
+		return PTR_ERR(power->supply);
+
+	/* Request irqs after registering, as irqs may trigger immediately */
+	for (i = 0; irq_names[i]; i++) {
+		irq = platform_get_irq_byname(pdev, irq_names[i]);
+		if (irq < 0) {
+			dev_warn(&pdev->dev, "No IRQ for %s: %d\n",
+				 irq_names[i], irq);
+			continue;
+		}
+		irq = regmap_irq_get_virq(axp20x->regmap_irqc, irq);
+		ret = devm_request_any_context_irq(&pdev->dev, irq,
+						   axp20x_ac_power_irq, 0,
+						   DRVNAME, power);
+		if (ret < 0)
+			dev_warn(&pdev->dev, "Error requesting %s IRQ: %d\n",
+				 irq_names[i], ret);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id axp20x_ac_power_match[] = {
+	{
+		.compatible = "x-powers,axp202-ac-power-supply",
+		.data = (void *)&axp20x_data,
+	}, {
+		.compatible = "x-powers,axp221-ac-power-supply",
+		.data = (void *)&axp22x_data,
+	}, { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, axp20x_ac_power_match);
+
+static struct platform_driver axp20x_ac_power_driver = {
+	.probe = axp20x_ac_power_probe,
+	.driver = {
+		.name = DRVNAME,
+		.of_match_table = axp20x_ac_power_match,
+	},
+};
+
+module_platform_driver(axp20x_ac_power_driver);
+
+MODULE_AUTHOR("Quentin Schulz <quentin.schulz@free-electrons.com>");
+MODULE_DESCRIPTION("AXP20X and AXP22X PMICs' AC power supply driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/power/supply/axp20x_usb_power.c b/drivers/power/supply/axp20x_usb_power.c
index 6af6feb7058d..2397c482656e 100644
--- a/drivers/power/supply/axp20x_usb_power.c
+++ b/drivers/power/supply/axp20x_usb_power.c
@@ -17,10 +17,12 @@
 #include <linux/mfd/axp20x.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/power_supply.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
+#include <linux/iio/consumer.h>
 
 #define DRVNAME "axp20x-usb-power-supply"
 
@@ -30,6 +32,8 @@
 #define AXP20X_USB_STATUS_VBUS_VALID	BIT(2)
 
 #define AXP20X_VBUS_VHOLD_uV(b)		(4000000 + (((b) >> 3) & 7) * 100000)
+#define AXP20X_VBUS_VHOLD_MASK		GENMASK(5, 3)
+#define AXP20X_VBUS_VHOLD_OFFSET	3
 #define AXP20X_VBUS_CLIMIT_MASK		3
 #define AXP20X_VBUC_CLIMIT_900mA	0
 #define AXP20X_VBUC_CLIMIT_500mA	1
@@ -45,6 +49,9 @@ struct axp20x_usb_power {
 	struct device_node *np;
 	struct regmap *regmap;
 	struct power_supply *supply;
+	enum axp20x_variants axp20x_id;
+	struct iio_channel *vbus_v;
+	struct iio_channel *vbus_i;
 };
 
 static irqreturn_t axp20x_usb_power_irq(int irq, void *devid)
@@ -72,6 +79,20 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
 		val->intval = AXP20X_VBUS_VHOLD_uV(v);
 		return 0;
 	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+		if (IS_ENABLED(CONFIG_AXP20X_ADC)) {
+			ret = iio_read_channel_processed(power->vbus_v,
+							 &val->intval);
+			if (ret)
+				return ret;
+
+			/*
+			 * IIO framework gives mV but Power Supply framework
+			 * gives uV.
+			 */
+			val->intval *= 1000;
+			return 0;
+		}
+
 		ret = axp20x_read_variable_width(power->regmap,
 						 AXP20X_VBUS_V_ADC_H, 12);
 		if (ret < 0)
@@ -86,12 +107,10 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
 
 		switch (v & AXP20X_VBUS_CLIMIT_MASK) {
 		case AXP20X_VBUC_CLIMIT_100mA:
-			if (of_device_is_compatible(power->np,
-					"x-powers,axp202-usb-power-supply")) {
-				val->intval = 100000;
-			} else {
+			if (power->axp20x_id == AXP221_ID)
 				val->intval = -1; /* No 100mA limit */
-			}
+			else
+				val->intval = 100000;
 			break;
 		case AXP20X_VBUC_CLIMIT_500mA:
 			val->intval = 500000;
@@ -105,6 +124,20 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
 		}
 		return 0;
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
+		if (IS_ENABLED(CONFIG_AXP20X_ADC)) {
+			ret = iio_read_channel_processed(power->vbus_i,
+							 &val->intval);
+			if (ret)
+				return ret;
+
+			/*
+			 * IIO framework gives mA but Power Supply framework
+			 * gives uA.
+			 */
+			val->intval *= 1000;
+			return 0;
+		}
+
 		ret = axp20x_read_variable_width(power->regmap,
 						 AXP20X_VBUS_I_ADC_H, 12);
 		if (ret < 0)
@@ -130,8 +163,7 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
 
 		val->intval = POWER_SUPPLY_HEALTH_GOOD;
 
-		if (of_device_is_compatible(power->np,
-				"x-powers,axp202-usb-power-supply")) {
+		if (power->axp20x_id == AXP202_ID) {
 			ret = regmap_read(power->regmap,
 					  AXP20X_USB_OTG_STATUS, &v);
 			if (ret)
@@ -155,6 +187,81 @@ static int axp20x_usb_power_get_property(struct power_supply *psy,
 	return 0;
 }
 
+static int axp20x_usb_power_set_voltage_min(struct axp20x_usb_power *power,
+					    int intval)
+{
+	int val;
+
+	switch (intval) {
+	case 4000000:
+	case 4100000:
+	case 4200000:
+	case 4300000:
+	case 4400000:
+	case 4500000:
+	case 4600000:
+	case 4700000:
+		val = (intval - 4000000) / 100000;
+		return regmap_update_bits(power->regmap,
+					  AXP20X_VBUS_IPSOUT_MGMT,
+					  AXP20X_VBUS_VHOLD_MASK,
+					  val << AXP20X_VBUS_VHOLD_OFFSET);
+	default:
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}
+
+static int axp20x_usb_power_set_current_max(struct axp20x_usb_power *power,
+					    int intval)
+{
+	int val;
+
+	switch (intval) {
+	case 100000:
+		if (power->axp20x_id == AXP221_ID)
+			return -EINVAL;
+	case 500000:
+	case 900000:
+		val = (900000 - intval) / 400000;
+		return regmap_update_bits(power->regmap,
+					  AXP20X_VBUS_IPSOUT_MGMT,
+					  AXP20X_VBUS_CLIMIT_MASK, val);
+	default:
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}
+
+static int axp20x_usb_power_set_property(struct power_supply *psy,
+					 enum power_supply_property psp,
+					 const union power_supply_propval *val)
+{
+	struct axp20x_usb_power *power = power_supply_get_drvdata(psy);
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_VOLTAGE_MIN:
+		return axp20x_usb_power_set_voltage_min(power, val->intval);
+
+	case POWER_SUPPLY_PROP_CURRENT_MAX:
+		return axp20x_usb_power_set_current_max(power, val->intval);
+
+	default:
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}
+
+static int axp20x_usb_power_prop_writeable(struct power_supply *psy,
+					   enum power_supply_property psp)
+{
+	return psp == POWER_SUPPLY_PROP_VOLTAGE_MIN ||
+	       psp == POWER_SUPPLY_PROP_CURRENT_MAX;
+}
+
 static enum power_supply_property axp20x_usb_power_properties[] = {
 	POWER_SUPPLY_PROP_HEALTH,
 	POWER_SUPPLY_PROP_PRESENT,
@@ -178,7 +285,9 @@ static const struct power_supply_desc axp20x_usb_power_desc = {
 	.type = POWER_SUPPLY_TYPE_USB,
 	.properties = axp20x_usb_power_properties,
 	.num_properties = ARRAY_SIZE(axp20x_usb_power_properties),
+	.property_is_writeable = axp20x_usb_power_prop_writeable,
 	.get_property = axp20x_usb_power_get_property,
+	.set_property = axp20x_usb_power_set_property,
 };
 
 static const struct power_supply_desc axp22x_usb_power_desc = {
@@ -186,9 +295,41 @@ static const struct power_supply_desc axp22x_usb_power_desc = {
 	.type = POWER_SUPPLY_TYPE_USB,
 	.properties = axp22x_usb_power_properties,
 	.num_properties = ARRAY_SIZE(axp22x_usb_power_properties),
+	.property_is_writeable = axp20x_usb_power_prop_writeable,
 	.get_property = axp20x_usb_power_get_property,
+	.set_property = axp20x_usb_power_set_property,
 };
 
+static int configure_iio_channels(struct platform_device *pdev,
+				  struct axp20x_usb_power *power)
+{
+	power->vbus_v = devm_iio_channel_get(&pdev->dev, "vbus_v");
+	if (IS_ERR(power->vbus_v)) {
+		if (PTR_ERR(power->vbus_v) == -ENODEV)
+			return -EPROBE_DEFER;
+		return PTR_ERR(power->vbus_v);
+	}
+
+	power->vbus_i = devm_iio_channel_get(&pdev->dev, "vbus_i");
+	if (IS_ERR(power->vbus_i)) {
+		if (PTR_ERR(power->vbus_i) == -ENODEV)
+			return -EPROBE_DEFER;
+		return PTR_ERR(power->vbus_i);
+	}
+
+	return 0;
+}
+
+static int configure_adc_registers(struct axp20x_usb_power *power)
+{
+	/* Enable vbus voltage and current measurement */
+	return regmap_update_bits(power->regmap, AXP20X_ADC_EN1,
+				  AXP20X_ADC_EN1_VBUS_CURR |
+				  AXP20X_ADC_EN1_VBUS_VOLT,
+				  AXP20X_ADC_EN1_VBUS_CURR |
+				  AXP20X_ADC_EN1_VBUS_VOLT);
+}
+
 static int axp20x_usb_power_probe(struct platform_device *pdev)
 {
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
@@ -214,11 +355,13 @@ static int axp20x_usb_power_probe(struct platform_device *pdev)
 	if (!power)
 		return -ENOMEM;
 
+	power->axp20x_id = (enum axp20x_variants)of_device_get_match_data(
+								&pdev->dev);
+
 	power->np = pdev->dev.of_node;
 	power->regmap = axp20x->regmap;
 
-	if (of_device_is_compatible(power->np,
-			"x-powers,axp202-usb-power-supply")) {
+	if (power->axp20x_id == AXP202_ID) {
 		/* Enable vbus valid checking */
 		ret = regmap_update_bits(power->regmap, AXP20X_VBUS_MON,
 					 AXP20X_VBUS_MON_VBUS_VALID,
@@ -226,17 +369,18 @@ static int axp20x_usb_power_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 
-		/* Enable vbus voltage and current measurement */
-		ret = regmap_update_bits(power->regmap, AXP20X_ADC_EN1,
-			AXP20X_ADC_EN1_VBUS_CURR | AXP20X_ADC_EN1_VBUS_VOLT,
-			AXP20X_ADC_EN1_VBUS_CURR | AXP20X_ADC_EN1_VBUS_VOLT);
+		if (IS_ENABLED(CONFIG_AXP20X_ADC))
+			ret = configure_iio_channels(pdev, power);
+		else
+			ret = configure_adc_registers(power);
+
 		if (ret)
 			return ret;
 
 		usb_power_desc = &axp20x_usb_power_desc;
 		irq_names = axp20x_irq_names;
-	} else if (of_device_is_compatible(power->np,
-			"x-powers,axp221-usb-power-supply")) {
+	} else if (power->axp20x_id == AXP221_ID ||
+		   power->axp20x_id == AXP223_ID) {
 		usb_power_desc = &axp22x_usb_power_desc;
 		irq_names = axp22x_irq_names;
 	} else {
@@ -273,9 +417,16 @@ static int axp20x_usb_power_probe(struct platform_device *pdev)
 }
 
 static const struct of_device_id axp20x_usb_power_match[] = {
-	{ .compatible = "x-powers,axp202-usb-power-supply" },
-	{ .compatible = "x-powers,axp221-usb-power-supply" },
-	{ }
+	{
+		.compatible = "x-powers,axp202-usb-power-supply",
+		.data = (void *)AXP202_ID,
+	}, {
+		.compatible = "x-powers,axp221-usb-power-supply",
+		.data = (void *)AXP221_ID,
+	}, {
+		.compatible = "x-powers,axp223-usb-power-supply",
+		.data = (void *)AXP223_ID,
+	}, { /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, axp20x_usb_power_match);
 
diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c
index 75b8e0c7402b..6be2fe27bb07 100644
--- a/drivers/power/supply/axp288_charger.c
+++ b/drivers/power/supply/axp288_charger.c
@@ -90,20 +90,6 @@
 #define CHRG_VLTFC_0C			0xA5	/* 0 DegC */
 #define CHRG_VHTFC_45C			0x1F	/* 45 DegC */
 
-#define BAT_IRQ_CFG_CHRG_DONE		(1 << 2)
-#define BAT_IRQ_CFG_CHRG_START		(1 << 3)
-#define BAT_IRQ_CFG_BAT_SAFE_EXIT	(1 << 4)
-#define BAT_IRQ_CFG_BAT_SAFE_ENTER	(1 << 5)
-#define BAT_IRQ_CFG_BAT_DISCON		(1 << 6)
-#define BAT_IRQ_CFG_BAT_CONN		(1 << 7)
-#define BAT_IRQ_CFG_BAT_MASK		0xFC
-
-#define TEMP_IRQ_CFG_QCBTU		(1 << 4)
-#define TEMP_IRQ_CFG_CBTU		(1 << 5)
-#define TEMP_IRQ_CFG_QCBTO		(1 << 6)
-#define TEMP_IRQ_CFG_CBTO		(1 << 7)
-#define TEMP_IRQ_CFG_MASK		0xF0
-
 #define FG_CNTL_OCV_ADJ_EN		(1 << 3)
 
 #define CV_4100MV			4100	/* 4100mV */
@@ -127,6 +113,10 @@
 #define ILIM_3000MA			3000	/* 3000mA */
 
 #define AXP288_EXTCON_DEV_NAME		"axp288_extcon"
+#define USB_HOST_EXTCON_DEV_NAME	"INT3496:00"
+
+static const unsigned int cable_ids[] =
+	{ EXTCON_CHG_USB_SDP, EXTCON_CHG_USB_CDP, EXTCON_CHG_USB_DCP };
 
 enum {
 	VBUS_OV_IRQ = 0,
@@ -143,7 +133,6 @@ enum {
 
 struct axp288_chrg_info {
 	struct platform_device *pdev;
-	struct axp20x_chrg_pdata *pdata;
 	struct regmap *regmap;
 	struct regmap_irq_chip_data *regmap_irqc;
 	int irq[CHRG_INTR_END];
@@ -163,20 +152,16 @@ struct axp288_chrg_info {
 		struct extcon_dev *edev;
 		bool connected;
 		enum power_supply_type chg_type;
-		struct notifier_block nb;
+		struct notifier_block nb[ARRAY_SIZE(cable_ids)];
 		struct work_struct work;
 	} cable;
 
-	int health;
 	int inlmt;
 	int cc;
 	int cv;
 	int max_cc;
 	int max_cv;
-	bool online;
-	bool present;
-	bool enable_charger;
-	bool is_charger_enabled;
+	int is_charger_enabled;
 };
 
 static inline int axp288_charger_set_cc(struct axp288_chrg_info *info, int cc)
@@ -305,6 +290,9 @@ static int axp288_charger_enable_charger(struct axp288_chrg_info *info,
 {
 	int ret;
 
+	if ((int)enable == info->is_charger_enabled)
+		return 0;
+
 	if (enable)
 		ret = regmap_update_bits(info->regmap, AXP20X_CHRG_CTRL1,
 				CHRG_CCCV_CHG_EN, CHRG_CCCV_CHG_EN);
@@ -430,8 +418,7 @@ static int axp288_charger_usb_get_property(struct power_supply *psy,
 		ret = axp288_charger_is_present(info);
 		if (ret < 0)
 			goto psy_get_prop_fail;
-		info->present = ret;
-		val->intval = info->present;
+		val->intval = ret;
 		break;
 	case POWER_SUPPLY_PROP_ONLINE:
 		/* Check for OTG case first */
@@ -442,8 +429,7 @@ static int axp288_charger_usb_get_property(struct power_supply *psy,
 		ret = axp288_charger_is_online(info);
 		if (ret < 0)
 			goto psy_get_prop_fail;
-		info->online = ret;
-		val->intval = info->online;
+		val->intval = ret;
 		break;
 	case POWER_SUPPLY_PROP_HEALTH:
 		val->intval = axp288_get_charger_health(info);
@@ -576,20 +562,20 @@ static void axp288_charger_extcon_evt_worker(struct work_struct *work)
 	struct axp288_chrg_info *info =
 	    container_of(work, struct axp288_chrg_info, cable.work);
 	int ret, current_limit;
-	bool changed = false;
 	struct extcon_dev *edev = info->cable.edev;
 	bool old_connected = info->cable.connected;
+	enum power_supply_type old_chg_type = info->cable.chg_type;
 
 	/* Determine cable/charger type */
-	if (extcon_get_cable_state_(edev, EXTCON_CHG_USB_SDP) > 0) {
+	if (extcon_get_state(edev, EXTCON_CHG_USB_SDP) > 0) {
 		dev_dbg(&info->pdev->dev, "USB SDP charger  is connected");
 		info->cable.connected = true;
 		info->cable.chg_type = POWER_SUPPLY_TYPE_USB;
-	} else if (extcon_get_cable_state_(edev, EXTCON_CHG_USB_CDP) > 0) {
+	} else if (extcon_get_state(edev, EXTCON_CHG_USB_CDP) > 0) {
 		dev_dbg(&info->pdev->dev, "USB CDP charger is connected");
 		info->cable.connected = true;
 		info->cable.chg_type = POWER_SUPPLY_TYPE_USB_CDP;
-	} else if (extcon_get_cable_state_(edev, EXTCON_CHG_USB_DCP) > 0) {
+	} else if (extcon_get_state(edev, EXTCON_CHG_USB_DCP) > 0) {
 		dev_dbg(&info->pdev->dev, "USB DCP charger is connected");
 		info->cable.connected = true;
 		info->cable.chg_type = POWER_SUPPLY_TYPE_USB_DCP;
@@ -601,22 +587,15 @@ static void axp288_charger_extcon_evt_worker(struct work_struct *work)
 	}
 
 	/* Cable status changed */
-	if (old_connected != info->cable.connected)
-		changed = true;
-
-	if (!changed)
+	if (old_connected == info->cable.connected &&
+	    old_chg_type == info->cable.chg_type)
 		return;
 
 	mutex_lock(&info->lock);
 
-	if (info->is_charger_enabled && !info->cable.connected) {
-		info->enable_charger = false;
-		ret = axp288_charger_enable_charger(info, info->enable_charger);
-		if (ret < 0)
-			dev_err(&info->pdev->dev,
-				"cannot disable charger (%d)", ret);
+	if (info->cable.connected) {
+		axp288_charger_enable_charger(info, false);
 
-	} else if (!info->is_charger_enabled && info->cable.connected) {
 		switch (info->cable.chg_type) {
 		case POWER_SUPPLY_TYPE_USB:
 			current_limit = ILIM_500MA;
@@ -635,36 +614,49 @@ static void axp288_charger_extcon_evt_worker(struct work_struct *work)
 
 		/* Set vbus current limit first, then enable charger */
 		ret = axp288_charger_set_vbus_inlmt(info, current_limit);
-		if (ret < 0) {
+		if (ret == 0)
+			axp288_charger_enable_charger(info, true);
+		else
 			dev_err(&info->pdev->dev,
 				"error setting current limit (%d)", ret);
-		} else {
-			info->enable_charger = (current_limit > 0);
-			ret = axp288_charger_enable_charger(info,
-							info->enable_charger);
-			if (ret < 0)
-				dev_err(&info->pdev->dev,
-					"cannot enable charger (%d)", ret);
-		}
+	} else {
+		axp288_charger_enable_charger(info, false);
 	}
 
-	if (changed)
-		info->health = axp288_get_charger_health(info);
-
 	mutex_unlock(&info->lock);
 
-	if (changed)
-		power_supply_changed(info->psy_usb);
+	power_supply_changed(info->psy_usb);
 }
 
-static int axp288_charger_handle_cable_evt(struct notifier_block *nb,
-					  unsigned long event, void *param)
+/*
+ * We need 3 copies of this, because there is no way to find out for which
+ * cable id we are being called from the passed in arguments; and we must
+ * have a separate nb for each extcon_register_notifier call.
+ */
+static int axp288_charger_handle_cable0_evt(struct notifier_block *nb,
+					    unsigned long event, void *param)
 {
 	struct axp288_chrg_info *info =
-	    container_of(nb, struct axp288_chrg_info, cable.nb);
+		container_of(nb, struct axp288_chrg_info, cable.nb[0]);
+	schedule_work(&info->cable.work);
+	return NOTIFY_OK;
+}
 
+static int axp288_charger_handle_cable1_evt(struct notifier_block *nb,
+					    unsigned long event, void *param)
+{
+	struct axp288_chrg_info *info =
+		container_of(nb, struct axp288_chrg_info, cable.nb[1]);
 	schedule_work(&info->cable.work);
+	return NOTIFY_OK;
+}
 
+static int axp288_charger_handle_cable2_evt(struct notifier_block *nb,
+					    unsigned long event, void *param)
+{
+	struct axp288_chrg_info *info =
+		container_of(nb, struct axp288_chrg_info, cable.nb[2]);
+	schedule_work(&info->cable.work);
 	return NOTIFY_OK;
 }
 
@@ -672,7 +664,17 @@ static void axp288_charger_otg_evt_worker(struct work_struct *work)
 {
 	struct axp288_chrg_info *info =
 	    container_of(work, struct axp288_chrg_info, otg.work);
-	int ret;
+	struct extcon_dev *edev = info->otg.cable;
+	int ret, usb_host = extcon_get_state(edev, EXTCON_USB_HOST);
+
+	dev_dbg(&info->pdev->dev, "external connector USB-Host is %s\n",
+				usb_host ? "attached" : "detached");
+
+	/*
+	 * Set usb_id_short flag to avoid running charger detection logic
+	 * in case usb host.
+	 */
+	info->otg.id_short = usb_host;
 
 	/* Disable VBUS path before enabling the 5V boost */
 	ret = axp288_charger_vbus_path_select(info, !info->otg.id_short);
@@ -685,135 +687,109 @@ static int axp288_charger_handle_otg_evt(struct notifier_block *nb,
 {
 	struct axp288_chrg_info *info =
 	    container_of(nb, struct axp288_chrg_info, otg.id_nb);
-	struct extcon_dev *edev = info->otg.cable;
-	int usb_host = extcon_get_cable_state_(edev, EXTCON_USB_HOST);
 
-	dev_dbg(&info->pdev->dev, "external connector USB-Host is %s\n",
-				usb_host ? "attached" : "detached");
-
-	/*
-	 * Set usb_id_short flag to avoid running charger detection logic
-	 * in case usb host.
-	 */
-	info->otg.id_short = usb_host;
 	schedule_work(&info->otg.work);
 
 	return NOTIFY_OK;
 }
 
-static void charger_init_hw_regs(struct axp288_chrg_info *info)
+static int charger_init_hw_regs(struct axp288_chrg_info *info)
 {
 	int ret, cc, cv;
 	unsigned int val;
 
 	/* Program temperature thresholds */
 	ret = regmap_write(info->regmap, AXP20X_V_LTF_CHRG, CHRG_VLTFC_0C);
-	if (ret < 0)
-		dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
+	if (ret < 0) {
+		dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
 							AXP20X_V_LTF_CHRG, ret);
+		return ret;
+	}
 
 	ret = regmap_write(info->regmap, AXP20X_V_HTF_CHRG, CHRG_VHTFC_45C);
-	if (ret < 0)
-		dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
+	if (ret < 0) {
+		dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
 							AXP20X_V_HTF_CHRG, ret);
+		return ret;
+	}
 
 	/* Do not turn-off charger o/p after charge cycle ends */
 	ret = regmap_update_bits(info->regmap,
 				AXP20X_CHRG_CTRL2,
-				CNTL2_CHG_OUT_TURNON, 1);
-	if (ret < 0)
-		dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
+				CNTL2_CHG_OUT_TURNON, CNTL2_CHG_OUT_TURNON);
+	if (ret < 0) {
+		dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
 						AXP20X_CHRG_CTRL2, ret);
-
-	/* Enable interrupts */
-	ret = regmap_update_bits(info->regmap,
-				AXP20X_IRQ2_EN,
-				BAT_IRQ_CFG_BAT_MASK, 1);
-	if (ret < 0)
-		dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
-						AXP20X_IRQ2_EN, ret);
-
-	ret = regmap_update_bits(info->regmap, AXP20X_IRQ3_EN,
-				TEMP_IRQ_CFG_MASK, 1);
-	if (ret < 0)
-		dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
-						AXP20X_IRQ3_EN, ret);
+		return ret;
+	}
 
 	/* Setup ending condition for charging to be 10% of I(chrg) */
 	ret = regmap_update_bits(info->regmap,
 				AXP20X_CHRG_CTRL1,
 				CHRG_CCCV_ITERM_20P, 0);
-	if (ret < 0)
-		dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
+	if (ret < 0) {
+		dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
 						AXP20X_CHRG_CTRL1, ret);
+		return ret;
+	}
 
 	/* Disable OCV-SOC curve calibration */
 	ret = regmap_update_bits(info->regmap,
 				AXP20X_CC_CTRL,
 				FG_CNTL_OCV_ADJ_EN, 0);
-	if (ret < 0)
-		dev_warn(&info->pdev->dev, "register(%x) write error(%d)\n",
+	if (ret < 0) {
+		dev_err(&info->pdev->dev, "register(%x) write error(%d)\n",
 						AXP20X_CC_CTRL, ret);
-
-	/* Init charging current and voltage */
-	info->max_cc = info->pdata->max_cc;
-	info->max_cv = info->pdata->max_cv;
+		return ret;
+	}
 
 	/* Read current charge voltage and current limit */
 	ret = regmap_read(info->regmap, AXP20X_CHRG_CTRL1, &val);
 	if (ret < 0) {
-		/* Assume default if cannot read */
-		info->cc = info->pdata->def_cc;
-		info->cv = info->pdata->def_cv;
-	} else {
-		/* Determine charge voltage */
-		cv = (val & CHRG_CCCV_CV_MASK) >> CHRG_CCCV_CV_BIT_POS;
-		switch (cv) {
-		case CHRG_CCCV_CV_4100MV:
-			info->cv = CV_4100MV;
-			break;
-		case CHRG_CCCV_CV_4150MV:
-			info->cv = CV_4150MV;
-			break;
-		case CHRG_CCCV_CV_4200MV:
-			info->cv = CV_4200MV;
-			break;
-		case CHRG_CCCV_CV_4350MV:
-			info->cv = CV_4350MV;
-			break;
-		default:
-			info->cv = INT_MAX;
-			break;
-		}
+		dev_err(&info->pdev->dev, "register(%x) read error(%d)\n",
+			AXP20X_CHRG_CTRL1, ret);
+		return ret;
+	}
 
-		/* Determine charge current limit */
-		cc = (ret & CHRG_CCCV_CC_MASK) >> CHRG_CCCV_CC_BIT_POS;
-		cc = (cc * CHRG_CCCV_CC_LSB_RES) + CHRG_CCCV_CC_OFFSET;
-		info->cc = cc;
+	/* Determine charge voltage */
+	cv = (val & CHRG_CCCV_CV_MASK) >> CHRG_CCCV_CV_BIT_POS;
+	switch (cv) {
+	case CHRG_CCCV_CV_4100MV:
+		info->cv = CV_4100MV;
+		break;
+	case CHRG_CCCV_CV_4150MV:
+		info->cv = CV_4150MV;
+		break;
+	case CHRG_CCCV_CV_4200MV:
+		info->cv = CV_4200MV;
+		break;
+	case CHRG_CCCV_CV_4350MV:
+		info->cv = CV_4350MV;
+		break;
+	}
 
-		/* Program default charging voltage and current */
-		cc = min(info->pdata->def_cc, info->max_cc);
-		cv = min(info->pdata->def_cv, info->max_cv);
+	/* Determine charge current limit */
+	cc = (ret & CHRG_CCCV_CC_MASK) >> CHRG_CCCV_CC_BIT_POS;
+	cc = (cc * CHRG_CCCV_CC_LSB_RES) + CHRG_CCCV_CC_OFFSET;
+	info->cc = cc;
 
-		ret = axp288_charger_set_cc(info, cc);
-		if (ret < 0)
-			dev_warn(&info->pdev->dev,
-					"error(%d) in setting CC\n", ret);
+	/*
+	 * Do not allow the user to configure higher settings then those
+	 * set by the firmware
+	 */
+	info->max_cv = info->cv;
+	info->max_cc = info->cc;
 
-		ret = axp288_charger_set_cv(info, cv);
-		if (ret < 0)
-			dev_warn(&info->pdev->dev,
-					"error(%d) in setting CV\n", ret);
-	}
+	return 0;
 }
 
 static int axp288_charger_probe(struct platform_device *pdev)
 {
 	int ret, i, pirq;
 	struct axp288_chrg_info *info;
+	struct device *dev = &pdev->dev;
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
 	struct power_supply_config charger_cfg = {};
-
 	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
@@ -821,15 +797,8 @@ static int axp288_charger_probe(struct platform_device *pdev)
 	info->pdev = pdev;
 	info->regmap = axp20x->regmap;
 	info->regmap_irqc = axp20x->regmap_irqc;
-	info->pdata = pdev->dev.platform_data;
-
-	if (!info->pdata) {
-		/* Try ACPI provided pdata via device properties */
-		if (!device_property_present(&pdev->dev,
-						"axp288_charger_data\n"))
-			dev_err(&pdev->dev, "failed to get platform data\n");
-		return -ENODEV;
-	}
+	info->cable.chg_type = -1;
+	info->is_charger_enabled = -1;
 
 	info->cable.edev = extcon_get_extcon_dev(AXP288_EXTCON_DEV_NAME);
 	if (info->cable.edev == NULL) {
@@ -838,63 +807,55 @@ static int axp288_charger_probe(struct platform_device *pdev)
 		return -EPROBE_DEFER;
 	}
 
-	/* Register for extcon notification */
-	INIT_WORK(&info->cable.work, axp288_charger_extcon_evt_worker);
-	info->cable.nb.notifier_call = axp288_charger_handle_cable_evt;
-	ret = extcon_register_notifier(info->cable.edev, EXTCON_CHG_USB_SDP,
-					&info->cable.nb);
-	if (ret) {
-		dev_err(&info->pdev->dev,
-			"failed to register extcon notifier for SDP %d\n", ret);
-		return ret;
-	}
-
-	ret = extcon_register_notifier(info->cable.edev, EXTCON_CHG_USB_CDP,
-					&info->cable.nb);
-	if (ret) {
-		dev_err(&info->pdev->dev,
-			"failed to register extcon notifier for CDP %d\n", ret);
-		extcon_unregister_notifier(info->cable.edev,
-				EXTCON_CHG_USB_SDP, &info->cable.nb);
-		return ret;
-	}
-
-	ret = extcon_register_notifier(info->cable.edev, EXTCON_CHG_USB_DCP,
-					&info->cable.nb);
-	if (ret) {
-		dev_err(&info->pdev->dev,
-			"failed to register extcon notifier for DCP %d\n", ret);
-		extcon_unregister_notifier(info->cable.edev,
-				EXTCON_CHG_USB_SDP, &info->cable.nb);
-		extcon_unregister_notifier(info->cable.edev,
-				EXTCON_CHG_USB_CDP, &info->cable.nb);
-		return ret;
+	info->otg.cable = extcon_get_extcon_dev(USB_HOST_EXTCON_DEV_NAME);
+	if (info->otg.cable == NULL) {
+		dev_dbg(dev, "EXTCON_USB_HOST is not ready, probe deferred\n");
+		return -EPROBE_DEFER;
 	}
 
 	platform_set_drvdata(pdev, info);
 	mutex_init(&info->lock);
 
+	ret = charger_init_hw_regs(info);
+	if (ret)
+		return ret;
+
 	/* Register with power supply class */
 	charger_cfg.drv_data = info;
-	info->psy_usb = power_supply_register(&pdev->dev, &axp288_charger_desc,
-						&charger_cfg);
+	info->psy_usb = devm_power_supply_register(dev, &axp288_charger_desc,
+						   &charger_cfg);
 	if (IS_ERR(info->psy_usb)) {
-		dev_err(&pdev->dev, "failed to register power supply charger\n");
 		ret = PTR_ERR(info->psy_usb);
-		goto psy_reg_failed;
+		dev_err(dev, "failed to register power supply: %d\n", ret);
+		return ret;
+	}
+
+	/* Register for extcon notification */
+	INIT_WORK(&info->cable.work, axp288_charger_extcon_evt_worker);
+	info->cable.nb[0].notifier_call = axp288_charger_handle_cable0_evt;
+	info->cable.nb[1].notifier_call = axp288_charger_handle_cable1_evt;
+	info->cable.nb[2].notifier_call = axp288_charger_handle_cable2_evt;
+	for (i = 0; i < ARRAY_SIZE(cable_ids); i++) {
+		ret = devm_extcon_register_notifier(dev, info->cable.edev,
+					  cable_ids[i], &info->cable.nb[i]);
+		if (ret) {
+			dev_err(dev, "failed to register extcon notifier for %u: %d\n",
+				cable_ids[i], ret);
+			return ret;
+		}
 	}
+	schedule_work(&info->cable.work);
 
 	/* Register for OTG notification */
 	INIT_WORK(&info->otg.work, axp288_charger_otg_evt_worker);
 	info->otg.id_nb.notifier_call = axp288_charger_handle_otg_evt;
-	ret = extcon_register_notifier(info->otg.cable, EXTCON_USB_HOST,
-				       &info->otg.id_nb);
-	if (ret)
-		dev_warn(&pdev->dev, "failed to register otg notifier\n");
-
-	if (info->otg.cable)
-		info->otg.id_short = extcon_get_cable_state_(
-					info->otg.cable, EXTCON_USB_HOST);
+	ret = devm_extcon_register_notifier(&pdev->dev, info->otg.cable,
+					EXTCON_USB_HOST, &info->otg.id_nb);
+	if (ret) {
+		dev_err(dev, "failed to register EXTCON_USB_HOST notifier\n");
+		return ret;
+	}
+	schedule_work(&info->otg.work);
 
 	/* Register charger interrupts */
 	for (i = 0; i < CHRG_INTR_END; i++) {
@@ -903,8 +864,7 @@ static int axp288_charger_probe(struct platform_device *pdev)
 		if (info->irq[i] < 0) {
 			dev_warn(&info->pdev->dev,
 				"failed to get virtual interrupt=%d\n", pirq);
-			ret = info->irq[i];
-			goto intr_reg_failed;
+			return info->irq[i];
 		}
 		ret = devm_request_threaded_irq(&info->pdev->dev, info->irq[i],
 					NULL, axp288_charger_irq_thread_handler,
@@ -912,51 +872,22 @@ static int axp288_charger_probe(struct platform_device *pdev)
 		if (ret) {
 			dev_err(&pdev->dev, "failed to request interrupt=%d\n",
 								info->irq[i]);
-			goto intr_reg_failed;
+			return ret;
 		}
 	}
 
-	charger_init_hw_regs(info);
-
 	return 0;
-
-intr_reg_failed:
-	if (info->otg.cable)
-		extcon_unregister_notifier(info->otg.cable, EXTCON_USB_HOST,
-					&info->otg.id_nb);
-	power_supply_unregister(info->psy_usb);
-psy_reg_failed:
-	extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_SDP,
-					&info->cable.nb);
-	extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_CDP,
-					&info->cable.nb);
-	extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_DCP,
-					&info->cable.nb);
-	return ret;
 }
 
-static int axp288_charger_remove(struct platform_device *pdev)
-{
-	struct axp288_chrg_info *info =  dev_get_drvdata(&pdev->dev);
-
-	if (info->otg.cable)
-		extcon_unregister_notifier(info->otg.cable, EXTCON_USB_HOST,
-					&info->otg.id_nb);
-
-	extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_SDP,
-					&info->cable.nb);
-	extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_CDP,
-					&info->cable.nb);
-	extcon_unregister_notifier(info->cable.edev, EXTCON_CHG_USB_DCP,
-					&info->cable.nb);
-	power_supply_unregister(info->psy_usb);
-
-	return 0;
-}
+static const struct platform_device_id axp288_charger_id_table[] = {
+	{ .name = "axp288_charger" },
+	{},
+};
+MODULE_DEVICE_TABLE(platform, axp288_charger_id_table);
 
 static struct platform_driver axp288_charger_driver = {
 	.probe = axp288_charger_probe,
-	.remove = axp288_charger_remove,
+	.id_table = axp288_charger_id_table,
 	.driver = {
 		.name = "axp288_charger",
 	},
diff --git a/drivers/power/supply/axp288_fuel_gauge.c b/drivers/power/supply/axp288_fuel_gauge.c
index 539eb41504bb..a8dcabc32721 100644
--- a/drivers/power/supply/axp288_fuel_gauge.c
+++ b/drivers/power/supply/axp288_fuel_gauge.c
@@ -29,6 +29,7 @@
 #include <linux/iio/consumer.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <asm/unaligned.h>
 
 #define CHRG_STAT_BAT_SAFE_MODE		(1 << 3)
 #define CHRG_STAT_BAT_VALID			(1 << 4)
@@ -49,23 +50,6 @@
 #define CHRG_CCCV_CV_4350MV			0x3     /* 4.35V */
 #define CHRG_CCCV_CHG_EN			(1 << 7)
 
-#define CV_4100						4100    /* 4100mV */
-#define CV_4150						4150    /* 4150mV */
-#define CV_4200						4200    /* 4200mV */
-#define CV_4350						4350    /* 4350mV */
-
-#define TEMP_IRQ_CFG_QWBTU			(1 << 0)
-#define TEMP_IRQ_CFG_WBTU			(1 << 1)
-#define TEMP_IRQ_CFG_QWBTO			(1 << 2)
-#define TEMP_IRQ_CFG_WBTO			(1 << 3)
-#define TEMP_IRQ_CFG_MASK			0xf
-
-#define FG_IRQ_CFG_LOWBATT_WL2		(1 << 0)
-#define FG_IRQ_CFG_LOWBATT_WL1		(1 << 1)
-#define FG_IRQ_CFG_LOWBATT_MASK		0x3
-#define LOWBAT_IRQ_STAT_LOWBATT_WL2	(1 << 0)
-#define LOWBAT_IRQ_STAT_LOWBATT_WL1	(1 << 1)
-
 #define FG_CNTL_OCV_ADJ_STAT		(1 << 2)
 #define FG_CNTL_OCV_ADJ_EN			(1 << 3)
 #define FG_CNTL_CAP_ADJ_STAT		(1 << 4)
@@ -73,17 +57,15 @@
 #define FG_CNTL_CC_EN				(1 << 6)
 #define FG_CNTL_GAUGE_EN			(1 << 7)
 
+#define FG_15BIT_WORD_VALID			(1 << 15)
+#define FG_15BIT_VAL_MASK			0x7fff
+
 #define FG_REP_CAP_VALID			(1 << 7)
 #define FG_REP_CAP_VAL_MASK			0x7F
 
 #define FG_DES_CAP1_VALID			(1 << 7)
-#define FG_DES_CAP1_VAL_MASK		0x7F
-#define FG_DES_CAP0_VAL_MASK		0xFF
 #define FG_DES_CAP_RES_LSB			1456    /* 1.456mAhr */
 
-#define FG_CC_MTR1_VALID			(1 << 7)
-#define FG_CC_MTR1_VAL_MASK			0x7F
-#define FG_CC_MTR0_VAL_MASK			0xFF
 #define FG_DES_CC_RES_LSB			1456    /* 1.456mAhr */
 
 #define FG_OCV_CAP_VALID			(1 << 7)
@@ -104,9 +86,7 @@
 
 /* 1.1mV per LSB expressed in uV */
 #define VOLTAGE_FROM_ADC(a)			((a * 11) / 10)
-/* properties converted to tenths of degrees, uV, uA, uW */
-#define PROP_TEMP(a)		((a) * 10)
-#define UNPROP_TEMP(a)		((a) / 10)
+/* properties converted to uV, uA */
 #define PROP_VOLT(a)		((a) * 1000)
 #define PROP_CURR(a)		((a) * 1000)
 
@@ -122,13 +102,13 @@ enum {
 
 struct axp288_fg_info {
 	struct platform_device *pdev;
-	struct axp20x_fg_pdata *pdata;
 	struct regmap *regmap;
 	struct regmap_irq_chip_data *regmap_irqc;
 	int irq[AXP288_FG_INTR_NUM];
 	struct power_supply *bat;
 	struct mutex lock;
 	int status;
+	int max_volt;
 	struct delayed_work status_monitor;
 	struct dentry *debug_file;
 };
@@ -138,22 +118,14 @@ static enum power_supply_property fuel_gauge_props[] = {
 	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_HEALTH,
 	POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN,
-	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
 	POWER_SUPPLY_PROP_VOLTAGE_NOW,
 	POWER_SUPPLY_PROP_VOLTAGE_OCV,
 	POWER_SUPPLY_PROP_CURRENT_NOW,
 	POWER_SUPPLY_PROP_CAPACITY,
 	POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN,
-	POWER_SUPPLY_PROP_TEMP,
-	POWER_SUPPLY_PROP_TEMP_MAX,
-	POWER_SUPPLY_PROP_TEMP_MIN,
-	POWER_SUPPLY_PROP_TEMP_ALERT_MIN,
-	POWER_SUPPLY_PROP_TEMP_ALERT_MAX,
 	POWER_SUPPLY_PROP_TECHNOLOGY,
 	POWER_SUPPLY_PROP_CHARGE_FULL,
 	POWER_SUPPLY_PROP_CHARGE_NOW,
-	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
-	POWER_SUPPLY_PROP_MODEL_NAME,
 };
 
 static int fuel_gauge_reg_readb(struct axp288_fg_info *info, int reg)
@@ -169,8 +141,10 @@ static int fuel_gauge_reg_readb(struct axp288_fg_info *info, int reg)
 			break;
 	}
 
-	if (ret < 0)
+	if (ret < 0) {
 		dev_err(&info->pdev->dev, "axp288 reg read err:%d\n", ret);
+		return ret;
+	}
 
 	return val;
 }
@@ -187,6 +161,44 @@ static int fuel_gauge_reg_writeb(struct axp288_fg_info *info, int reg, u8 val)
 	return ret;
 }
 
+static int fuel_gauge_read_15bit_word(struct axp288_fg_info *info, int reg)
+{
+	unsigned char buf[2];
+	int ret;
+
+	ret = regmap_bulk_read(info->regmap, reg, buf, 2);
+	if (ret < 0) {
+		dev_err(&info->pdev->dev, "Error reading reg 0x%02x err: %d\n",
+			reg, ret);
+		return ret;
+	}
+
+	ret = get_unaligned_be16(buf);
+	if (!(ret & FG_15BIT_WORD_VALID)) {
+		dev_err(&info->pdev->dev, "Error reg 0x%02x contents not valid\n",
+			reg);
+		return -ENXIO;
+	}
+
+	return ret & FG_15BIT_VAL_MASK;
+}
+
+static int fuel_gauge_read_12bit_word(struct axp288_fg_info *info, int reg)
+{
+	unsigned char buf[2];
+	int ret;
+
+	ret = regmap_bulk_read(info->regmap, reg, buf, 2);
+	if (ret < 0) {
+		dev_err(&info->pdev->dev, "Error reading reg 0x%02x err: %d\n",
+			reg, ret);
+		return ret;
+	}
+
+	/* 12-bit data values have upper 8 bits in buf[0], lower 4 in buf[1] */
+	return (buf[0] << 4) | ((buf[1] >> 4) & 0x0f);
+}
+
 static int pmic_read_adc_val(const char *name, int *raw_val,
 		struct axp288_fg_info *info)
 {
@@ -247,24 +259,15 @@ static int fuel_gauge_debug_show(struct seq_file *s, void *data)
 	seq_printf(s, "    FG_RDC0[%02x] : %02x\n",
 		AXP288_FG_RDC0_REG,
 		fuel_gauge_reg_readb(info, AXP288_FG_RDC0_REG));
-	seq_printf(s, "    FG_OCVH[%02x] : %02x\n",
+	seq_printf(s, "     FG_OCV[%02x] : %04x\n",
 		AXP288_FG_OCVH_REG,
-		fuel_gauge_reg_readb(info, AXP288_FG_OCVH_REG));
-	seq_printf(s, "    FG_OCVL[%02x] : %02x\n",
-		AXP288_FG_OCVL_REG,
-		fuel_gauge_reg_readb(info, AXP288_FG_OCVL_REG));
-	seq_printf(s, "FG_DES_CAP1[%02x] : %02x\n",
+		fuel_gauge_read_12bit_word(info, AXP288_FG_OCVH_REG));
+	seq_printf(s, " FG_DES_CAP[%02x] : %04x\n",
 		AXP288_FG_DES_CAP1_REG,
-		fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG));
-	seq_printf(s, "FG_DES_CAP0[%02x] : %02x\n",
-		AXP288_FG_DES_CAP0_REG,
-		fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP0_REG));
-	seq_printf(s, " FG_CC_MTR1[%02x] : %02x\n",
+		fuel_gauge_read_15bit_word(info, AXP288_FG_DES_CAP1_REG));
+	seq_printf(s, "  FG_CC_MTR[%02x] : %04x\n",
 		AXP288_FG_CC_MTR1_REG,
-		fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR1_REG));
-	seq_printf(s, " FG_CC_MTR0[%02x] : %02x\n",
-		AXP288_FG_CC_MTR0_REG,
-		fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR0_REG));
+		fuel_gauge_read_15bit_word(info, AXP288_FG_CC_MTR1_REG));
 	seq_printf(s, " FG_OCV_CAP[%02x] : %02x\n",
 		AXP288_FG_OCV_CAP_REG,
 		fuel_gauge_reg_readb(info, AXP288_FG_OCV_CAP_REG));
@@ -417,143 +420,27 @@ current_read_fail:
 	return ret;
 }
 
-static int temp_to_adc(struct axp288_fg_info *info, int tval)
-{
-	int rntc = 0, i, ret, adc_val;
-	int rmin, rmax, tmin, tmax;
-	int tcsz = info->pdata->tcsz;
-
-	/* get the Rntc resitance value for this temp */
-	if (tval > info->pdata->thermistor_curve[0][1]) {
-		rntc = info->pdata->thermistor_curve[0][0];
-	} else if (tval <= info->pdata->thermistor_curve[tcsz-1][1]) {
-		rntc = info->pdata->thermistor_curve[tcsz-1][0];
-	} else {
-		for (i = 1; i < tcsz; i++) {
-			if (tval > info->pdata->thermistor_curve[i][1]) {
-				rmin = info->pdata->thermistor_curve[i-1][0];
-				rmax = info->pdata->thermistor_curve[i][0];
-				tmin = info->pdata->thermistor_curve[i-1][1];
-				tmax = info->pdata->thermistor_curve[i][1];
-				rntc = rmin + ((rmax - rmin) *
-					(tval - tmin) / (tmax - tmin));
-				break;
-			}
-		}
-	}
-
-	/* we need the current to calculate the proper adc voltage */
-	ret = fuel_gauge_reg_readb(info, AXP20X_ADC_RATE);
-	if (ret < 0) {
-		dev_err(&info->pdev->dev, "%s:read err:%d\n", __func__, ret);
-		ret = 0x30;
-	}
-
-	/*
-	 * temperature is proportional to NTS thermistor resistance
-	 * ADC_RATE[5-4] determines current, 00=20uA,01=40uA,10=60uA,11=80uA
-	 * [12-bit ADC VAL] = R_NTC(Ω) * current / 800
-	 */
-	adc_val = rntc * (20 + (20 * ((ret >> 4) & 0x3))) / 800;
-
-	return adc_val;
-}
-
-static int adc_to_temp(struct axp288_fg_info *info, int adc_val)
-{
-	int ret, r, i, tval = 0;
-	int rmin, rmax, tmin, tmax;
-	int tcsz = info->pdata->tcsz;
-
-	ret = fuel_gauge_reg_readb(info, AXP20X_ADC_RATE);
-	if (ret < 0) {
-		dev_err(&info->pdev->dev, "%s:read err:%d\n", __func__, ret);
-		ret = 0x30;
-	}
-
-	/*
-	 * temperature is proportional to NTS thermistor resistance
-	 * ADC_RATE[5-4] determines current, 00=20uA,01=40uA,10=60uA,11=80uA
-	 * R_NTC(Ω) = [12-bit ADC VAL] * 800 / current
-	 */
-	r = adc_val * 800 / (20 + (20 * ((ret >> 4) & 0x3)));
-
-	if (r < info->pdata->thermistor_curve[0][0]) {
-		tval = info->pdata->thermistor_curve[0][1];
-	} else if (r >= info->pdata->thermistor_curve[tcsz-1][0]) {
-		tval = info->pdata->thermistor_curve[tcsz-1][1];
-	} else {
-		for (i = 1; i < tcsz; i++) {
-			if (r < info->pdata->thermistor_curve[i][0]) {
-				rmin = info->pdata->thermistor_curve[i-1][0];
-				rmax = info->pdata->thermistor_curve[i][0];
-				tmin = info->pdata->thermistor_curve[i-1][1];
-				tmax = info->pdata->thermistor_curve[i][1];
-				tval = tmin + ((tmax - tmin) *
-					(r - rmin) / (rmax - rmin));
-				break;
-			}
-		}
-	}
-
-	return tval;
-}
-
-static int fuel_gauge_get_btemp(struct axp288_fg_info *info, int *btemp)
-{
-	int ret, raw_val = 0;
-
-	ret = pmic_read_adc_val("axp288-batt-temp", &raw_val, info);
-	if (ret < 0)
-		goto temp_read_fail;
-
-	*btemp = adc_to_temp(info, raw_val);
-
-temp_read_fail:
-	return ret;
-}
-
 static int fuel_gauge_get_vocv(struct axp288_fg_info *info, int *vocv)
 {
-	int ret, value;
-
-	/* 12-bit data value, upper 8 in OCVH, lower 4 in OCVL */
-	ret = fuel_gauge_reg_readb(info, AXP288_FG_OCVH_REG);
-	if (ret < 0)
-		goto vocv_read_fail;
-	value = ret << 4;
+	int ret;
 
-	ret = fuel_gauge_reg_readb(info, AXP288_FG_OCVL_REG);
-	if (ret < 0)
-		goto vocv_read_fail;
-	value |= (ret & 0xf);
+	ret = fuel_gauge_read_12bit_word(info, AXP288_FG_OCVH_REG);
+	if (ret >= 0)
+		*vocv = VOLTAGE_FROM_ADC(ret);
 
-	*vocv = VOLTAGE_FROM_ADC(value);
-vocv_read_fail:
 	return ret;
 }
 
 static int fuel_gauge_battery_health(struct axp288_fg_info *info)
 {
-	int temp, vocv;
-	int ret, health = POWER_SUPPLY_HEALTH_UNKNOWN;
-
-	ret = fuel_gauge_get_btemp(info, &temp);
-	if (ret < 0)
-		goto health_read_fail;
+	int ret, vocv, health = POWER_SUPPLY_HEALTH_UNKNOWN;
 
 	ret = fuel_gauge_get_vocv(info, &vocv);
 	if (ret < 0)
 		goto health_read_fail;
 
-	if (vocv > info->pdata->max_volt)
+	if (vocv > info->max_volt)
 		health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
-	else if (temp > info->pdata->max_temp)
-		health = POWER_SUPPLY_HEALTH_OVERHEAT;
-	else if (temp < info->pdata->min_temp)
-		health = POWER_SUPPLY_HEALTH_COLD;
-	else if (vocv < info->pdata->min_volt)
-		health = POWER_SUPPLY_HEALTH_DEAD;
 	else
 		health = POWER_SUPPLY_HEALTH_GOOD;
 
@@ -561,28 +448,6 @@ health_read_fail:
 	return health;
 }
 
-static int fuel_gauge_set_high_btemp_alert(struct axp288_fg_info *info)
-{
-	int ret, adc_val;
-
-	/* program temperature threshold as 1/16 ADC value */
-	adc_val = temp_to_adc(info, info->pdata->max_temp);
-	ret = fuel_gauge_reg_writeb(info, AXP20X_V_HTF_DISCHRG, adc_val >> 4);
-
-	return ret;
-}
-
-static int fuel_gauge_set_low_btemp_alert(struct axp288_fg_info *info)
-{
-	int ret, adc_val;
-
-	/* program temperature threshold as 1/16 ADC value */
-	adc_val = temp_to_adc(info, info->pdata->min_temp);
-	ret = fuel_gauge_reg_writeb(info, AXP20X_V_LTF_DISCHRG, adc_val >> 4);
-
-	return ret;
-}
-
 static int fuel_gauge_get_property(struct power_supply *ps,
 		enum power_supply_property prop,
 		union power_supply_propval *val)
@@ -643,58 +508,25 @@ static int fuel_gauge_get_property(struct power_supply *ps,
 			goto fuel_gauge_read_err;
 		val->intval = (ret & 0x0f);
 		break;
-	case POWER_SUPPLY_PROP_TEMP:
-		ret = fuel_gauge_get_btemp(info, &value);
-		if (ret < 0)
-			goto fuel_gauge_read_err;
-		val->intval = PROP_TEMP(value);
-		break;
-	case POWER_SUPPLY_PROP_TEMP_MAX:
-	case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
-		val->intval = PROP_TEMP(info->pdata->max_temp);
-		break;
-	case POWER_SUPPLY_PROP_TEMP_MIN:
-	case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
-		val->intval = PROP_TEMP(info->pdata->min_temp);
-		break;
 	case POWER_SUPPLY_PROP_TECHNOLOGY:
 		val->intval = POWER_SUPPLY_TECHNOLOGY_LION;
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_NOW:
-		ret = fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR1_REG);
+		ret = fuel_gauge_read_15bit_word(info, AXP288_FG_CC_MTR1_REG);
 		if (ret < 0)
 			goto fuel_gauge_read_err;
 
-		value = (ret & FG_CC_MTR1_VAL_MASK) << 8;
-		ret = fuel_gauge_reg_readb(info, AXP288_FG_CC_MTR0_REG);
-		if (ret < 0)
-			goto fuel_gauge_read_err;
-		value |= (ret & FG_CC_MTR0_VAL_MASK);
-		val->intval = value * FG_DES_CAP_RES_LSB;
+		val->intval = ret * FG_DES_CAP_RES_LSB;
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_FULL:
-		ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG);
+		ret = fuel_gauge_read_15bit_word(info, AXP288_FG_DES_CAP1_REG);
 		if (ret < 0)
 			goto fuel_gauge_read_err;
 
-		value = (ret & FG_DES_CAP1_VAL_MASK) << 8;
-		ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP0_REG);
-		if (ret < 0)
-			goto fuel_gauge_read_err;
-		value |= (ret & FG_DES_CAP0_VAL_MASK);
-		val->intval = value * FG_DES_CAP_RES_LSB;
-		break;
-	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
-		val->intval = PROP_CURR(info->pdata->design_cap);
+		val->intval = ret * FG_DES_CAP_RES_LSB;
 		break;
 	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
-		val->intval = PROP_VOLT(info->pdata->max_volt);
-		break;
-	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
-		val->intval = PROP_VOLT(info->pdata->min_volt);
-		break;
-	case POWER_SUPPLY_PROP_MODEL_NAME:
-		val->strval = info->pdata->battid;
+		val->intval = PROP_VOLT(info->max_volt);
 		break;
 	default:
 		mutex_unlock(&info->lock);
@@ -718,35 +550,6 @@ static int fuel_gauge_set_property(struct power_supply *ps,
 
 	mutex_lock(&info->lock);
 	switch (prop) {
-	case POWER_SUPPLY_PROP_STATUS:
-		info->status = val->intval;
-		break;
-	case POWER_SUPPLY_PROP_TEMP_MIN:
-	case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
-		if ((val->intval < PD_DEF_MIN_TEMP) ||
-			(val->intval > PD_DEF_MAX_TEMP)) {
-			ret = -EINVAL;
-			break;
-		}
-		info->pdata->min_temp = UNPROP_TEMP(val->intval);
-		ret = fuel_gauge_set_low_btemp_alert(info);
-		if (ret < 0)
-			dev_err(&info->pdev->dev,
-				"temp alert min set fail:%d\n", ret);
-		break;
-	case POWER_SUPPLY_PROP_TEMP_MAX:
-	case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
-		if ((val->intval < PD_DEF_MIN_TEMP) ||
-			(val->intval > PD_DEF_MAX_TEMP)) {
-			ret = -EINVAL;
-			break;
-		}
-		info->pdata->max_temp = UNPROP_TEMP(val->intval);
-		ret = fuel_gauge_set_high_btemp_alert(info);
-		if (ret < 0)
-			dev_err(&info->pdev->dev,
-				"temp alert max set fail:%d\n", ret);
-		break;
 	case POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN:
 		if ((val->intval < 0) || (val->intval > 15)) {
 			ret = -EINVAL;
@@ -774,11 +577,6 @@ static int fuel_gauge_property_is_writeable(struct power_supply *psy,
 	int ret;
 
 	switch (psp) {
-	case POWER_SUPPLY_PROP_STATUS:
-	case POWER_SUPPLY_PROP_TEMP_MIN:
-	case POWER_SUPPLY_PROP_TEMP_ALERT_MIN:
-	case POWER_SUPPLY_PROP_TEMP_MAX:
-	case POWER_SUPPLY_PROP_TEMP_ALERT_MAX:
 	case POWER_SUPPLY_PROP_CAPACITY_ALERT_MIN:
 		ret = 1;
 		break;
@@ -863,158 +661,6 @@ static const struct power_supply_desc fuel_gauge_desc = {
 	.external_power_changed	= fuel_gauge_external_power_changed,
 };
 
-static int fuel_gauge_set_lowbatt_thresholds(struct axp288_fg_info *info)
-{
-	int ret;
-	u8 reg_val;
-
-	ret = fuel_gauge_reg_readb(info, AXP20X_FG_RES);
-	if (ret < 0) {
-		dev_err(&info->pdev->dev, "%s:read err:%d\n", __func__, ret);
-		return ret;
-	}
-	ret = (ret & FG_REP_CAP_VAL_MASK);
-
-	if (ret > FG_LOW_CAP_WARN_THR)
-		reg_val = FG_LOW_CAP_WARN_THR;
-	else if (ret > FG_LOW_CAP_CRIT_THR)
-		reg_val = FG_LOW_CAP_CRIT_THR;
-	else
-		reg_val = FG_LOW_CAP_SHDN_THR;
-
-	reg_val |= FG_LOW_CAP_THR1_VAL;
-	ret = fuel_gauge_reg_writeb(info, AXP288_FG_LOW_CAP_REG, reg_val);
-	if (ret < 0)
-		dev_err(&info->pdev->dev, "%s:write err:%d\n", __func__, ret);
-
-	return ret;
-}
-
-static int fuel_gauge_program_vbatt_full(struct axp288_fg_info *info)
-{
-	int ret;
-	u8 val;
-
-	ret = fuel_gauge_reg_readb(info, AXP20X_CHRG_CTRL1);
-	if (ret < 0)
-		goto fg_prog_ocv_fail;
-	else
-		val = (ret & ~CHRG_CCCV_CV_MASK);
-
-	switch (info->pdata->max_volt) {
-	case CV_4100:
-		val |= (CHRG_CCCV_CV_4100MV << CHRG_CCCV_CV_BIT_POS);
-		break;
-	case CV_4150:
-		val |= (CHRG_CCCV_CV_4150MV << CHRG_CCCV_CV_BIT_POS);
-		break;
-	case CV_4200:
-		val |= (CHRG_CCCV_CV_4200MV << CHRG_CCCV_CV_BIT_POS);
-		break;
-	case CV_4350:
-		val |= (CHRG_CCCV_CV_4350MV << CHRG_CCCV_CV_BIT_POS);
-		break;
-	default:
-		val |= (CHRG_CCCV_CV_4200MV << CHRG_CCCV_CV_BIT_POS);
-		break;
-	}
-
-	ret = fuel_gauge_reg_writeb(info, AXP20X_CHRG_CTRL1, val);
-fg_prog_ocv_fail:
-	return ret;
-}
-
-static int fuel_gauge_program_design_cap(struct axp288_fg_info *info)
-{
-	int ret;
-
-	ret = fuel_gauge_reg_writeb(info,
-		AXP288_FG_DES_CAP1_REG, info->pdata->cap1);
-	if (ret < 0)
-		goto fg_prog_descap_fail;
-
-	ret = fuel_gauge_reg_writeb(info,
-		AXP288_FG_DES_CAP0_REG, info->pdata->cap0);
-
-fg_prog_descap_fail:
-	return ret;
-}
-
-static int fuel_gauge_program_ocv_curve(struct axp288_fg_info *info)
-{
-	int ret = 0, i;
-
-	for (i = 0; i < OCV_CURVE_SIZE; i++) {
-		ret = fuel_gauge_reg_writeb(info,
-			AXP288_FG_OCV_CURVE_REG + i, info->pdata->ocv_curve[i]);
-		if (ret < 0)
-			goto fg_prog_ocv_fail;
-	}
-
-fg_prog_ocv_fail:
-	return ret;
-}
-
-static int fuel_gauge_program_rdc_vals(struct axp288_fg_info *info)
-{
-	int ret;
-
-	ret = fuel_gauge_reg_writeb(info,
-		AXP288_FG_RDC1_REG, info->pdata->rdc1);
-	if (ret < 0)
-		goto fg_prog_ocv_fail;
-
-	ret = fuel_gauge_reg_writeb(info,
-		AXP288_FG_RDC0_REG, info->pdata->rdc0);
-
-fg_prog_ocv_fail:
-	return ret;
-}
-
-static void fuel_gauge_init_config_regs(struct axp288_fg_info *info)
-{
-	int ret;
-
-	/*
-	 * check if the config data is already
-	 * programmed and if so just return.
-	 */
-
-	ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG);
-	if (ret < 0) {
-		dev_warn(&info->pdev->dev, "CAP1 reg read err!!\n");
-	} else if (!(ret & FG_DES_CAP1_VALID)) {
-		dev_info(&info->pdev->dev, "FG data needs to be initialized\n");
-	} else {
-		dev_info(&info->pdev->dev, "FG data is already initialized\n");
-		return;
-	}
-
-	ret = fuel_gauge_program_vbatt_full(info);
-	if (ret < 0)
-		dev_err(&info->pdev->dev, "set vbatt full fail:%d\n", ret);
-
-	ret = fuel_gauge_program_design_cap(info);
-	if (ret < 0)
-		dev_err(&info->pdev->dev, "set design cap fail:%d\n", ret);
-
-	ret = fuel_gauge_program_rdc_vals(info);
-	if (ret < 0)
-		dev_err(&info->pdev->dev, "set rdc fail:%d\n", ret);
-
-	ret = fuel_gauge_program_ocv_curve(info);
-	if (ret < 0)
-		dev_err(&info->pdev->dev, "set ocv curve fail:%d\n", ret);
-
-	ret = fuel_gauge_set_lowbatt_thresholds(info);
-	if (ret < 0)
-		dev_err(&info->pdev->dev, "lowbatt thr set fail:%d\n", ret);
-
-	ret = fuel_gauge_reg_writeb(info, AXP20X_CC_CTRL, 0xef);
-	if (ret < 0)
-		dev_err(&info->pdev->dev, "gauge cntl set fail:%d\n", ret);
-}
-
 static void fuel_gauge_init_irq(struct axp288_fg_info *info)
 {
 	int ret, i, pirq;
@@ -1052,29 +698,6 @@ intr_failed:
 	}
 }
 
-static void fuel_gauge_init_hw_regs(struct axp288_fg_info *info)
-{
-	int ret;
-	unsigned int val;
-
-	ret = fuel_gauge_set_high_btemp_alert(info);
-	if (ret < 0)
-		dev_err(&info->pdev->dev, "high batt temp set fail:%d\n", ret);
-
-	ret = fuel_gauge_set_low_btemp_alert(info);
-	if (ret < 0)
-		dev_err(&info->pdev->dev, "low batt temp set fail:%d\n", ret);
-
-	/* enable interrupts */
-	val = fuel_gauge_reg_readb(info, AXP20X_IRQ3_EN);
-	val |= TEMP_IRQ_CFG_MASK;
-	fuel_gauge_reg_writeb(info, AXP20X_IRQ3_EN, val);
-
-	val = fuel_gauge_reg_readb(info, AXP20X_IRQ4_EN);
-	val |= FG_IRQ_CFG_LOWBATT_MASK;
-	val = fuel_gauge_reg_writeb(info, AXP20X_IRQ4_EN, val);
-}
-
 static int axp288_fuel_gauge_probe(struct platform_device *pdev)
 {
 	int ret = 0;
@@ -1090,15 +713,39 @@ static int axp288_fuel_gauge_probe(struct platform_device *pdev)
 	info->regmap = axp20x->regmap;
 	info->regmap_irqc = axp20x->regmap_irqc;
 	info->status = POWER_SUPPLY_STATUS_UNKNOWN;
-	info->pdata = pdev->dev.platform_data;
-	if (!info->pdata)
-		return -ENODEV;
 
 	platform_set_drvdata(pdev, info);
 
 	mutex_init(&info->lock);
 	INIT_DELAYED_WORK(&info->status_monitor, fuel_gauge_status_monitor);
 
+	ret = fuel_gauge_reg_readb(info, AXP288_FG_DES_CAP1_REG);
+	if (ret < 0)
+		return ret;
+
+	if (!(ret & FG_DES_CAP1_VALID)) {
+		dev_err(&pdev->dev, "axp288 not configured by firmware\n");
+		return -ENODEV;
+	}
+
+	ret = fuel_gauge_reg_readb(info, AXP20X_CHRG_CTRL1);
+	if (ret < 0)
+		return ret;
+	switch ((ret & CHRG_CCCV_CV_MASK) >> CHRG_CCCV_CV_BIT_POS) {
+	case CHRG_CCCV_CV_4100MV:
+		info->max_volt = 4100;
+		break;
+	case CHRG_CCCV_CV_4150MV:
+		info->max_volt = 4150;
+		break;
+	case CHRG_CCCV_CV_4200MV:
+		info->max_volt = 4200;
+		break;
+	case CHRG_CCCV_CV_4350MV:
+		info->max_volt = 4350;
+		break;
+	}
+
 	psy_cfg.drv_data = info;
 	info->bat = power_supply_register(&pdev->dev, &fuel_gauge_desc, &psy_cfg);
 	if (IS_ERR(info->bat)) {
@@ -1108,12 +755,10 @@ static int axp288_fuel_gauge_probe(struct platform_device *pdev)
 	}
 
 	fuel_gauge_create_debugfs(info);
-	fuel_gauge_init_config_regs(info);
 	fuel_gauge_init_irq(info);
-	fuel_gauge_init_hw_regs(info);
 	schedule_delayed_work(&info->status_monitor, STATUS_MON_DELAY_JIFFIES);
 
-	return ret;
+	return 0;
 }
 
 static const struct platform_device_id axp288_fg_id_table[] = {
diff --git a/drivers/power/supply/bq2415x_charger.c b/drivers/power/supply/bq2415x_charger.c
index 73e2f0b79dd4..c4770a94cc8e 100644
--- a/drivers/power/supply/bq2415x_charger.c
+++ b/drivers/power/supply/bq2415x_charger.c
@@ -1569,6 +1569,11 @@ static int bq2415x_probe(struct i2c_client *client,
 		acpi_id =
 			acpi_match_device(client->dev.driver->acpi_match_table,
 					  &client->dev);
+		if (!acpi_id) {
+			dev_err(&client->dev, "failed to match device name\n");
+			ret = -ENODEV;
+			goto error_1;
+		}
 		name = kasprintf(GFP_KERNEL, "%s-%d", acpi_id->id, num);
 	}
 	if (!name) {
diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c
index e9584330aeed..a4f08492abeb 100644
--- a/drivers/power/supply/bq24190_charger.c
+++ b/drivers/power/supply/bq24190_charger.c
@@ -144,10 +144,7 @@
  * so the first read after a fault returns the latched value and subsequent
  * reads return the current value.  In order to return the fault status
  * to the user, have the interrupt handler save the reg's value and retrieve
- * it in the appropriate health/status routine.  Each routine has its own
- * flag indicating whether it should use the value stored by the last run
- * of the interrupt handler or do an actual reg read.  That way each routine
- * can report back whatever fault may have occured.
+ * it in the appropriate health/status routine.
  */
 struct bq24190_dev_info {
 	struct i2c_client		*client;
@@ -159,10 +156,6 @@ struct bq24190_dev_info {
 	unsigned int			gpio_int;
 	unsigned int			irq;
 	struct mutex			f_reg_lock;
-	bool				first_time;
-	bool				charger_health_valid;
-	bool				battery_health_valid;
-	bool				battery_status_valid;
 	u8				f_reg;
 	u8				ss_reg;
 	u8				watchdog;
@@ -199,7 +192,7 @@ static const int bq24190_cvc_vreg_values[] = {
 	4400000
 };
 
-/* REG06[1:0] (TREG) in tenths of degrees Celcius */
+/* REG06[1:0] (TREG) in tenths of degrees Celsius */
 static const int bq24190_ictrc_treg_values[] = {
 	600, 800, 1000, 1200
 };
@@ -636,21 +629,11 @@ static int bq24190_charger_get_health(struct bq24190_dev_info *bdi,
 		union power_supply_propval *val)
 {
 	u8 v;
-	int health, ret;
+	int health;
 
 	mutex_lock(&bdi->f_reg_lock);
-
-	if (bdi->charger_health_valid) {
-		v = bdi->f_reg;
-		bdi->charger_health_valid = false;
-		mutex_unlock(&bdi->f_reg_lock);
-	} else {
-		mutex_unlock(&bdi->f_reg_lock);
-
-		ret = bq24190_read(bdi, BQ24190_REG_F, &v);
-		if (ret < 0)
-			return ret;
-	}
+	v = bdi->f_reg;
+	mutex_unlock(&bdi->f_reg_lock);
 
 	if (v & BQ24190_REG_F_BOOST_FAULT_MASK) {
 		/*
@@ -937,18 +920,8 @@ static int bq24190_battery_get_status(struct bq24190_dev_info *bdi,
 	int status, ret;
 
 	mutex_lock(&bdi->f_reg_lock);
-
-	if (bdi->battery_status_valid) {
-		chrg_fault = bdi->f_reg;
-		bdi->battery_status_valid = false;
-		mutex_unlock(&bdi->f_reg_lock);
-	} else {
-		mutex_unlock(&bdi->f_reg_lock);
-
-		ret = bq24190_read(bdi, BQ24190_REG_F, &chrg_fault);
-		if (ret < 0)
-			return ret;
-	}
+	chrg_fault = bdi->f_reg;
+	mutex_unlock(&bdi->f_reg_lock);
 
 	chrg_fault &= BQ24190_REG_F_CHRG_FAULT_MASK;
 	chrg_fault >>= BQ24190_REG_F_CHRG_FAULT_SHIFT;
@@ -996,21 +969,11 @@ static int bq24190_battery_get_health(struct bq24190_dev_info *bdi,
 		union power_supply_propval *val)
 {
 	u8 v;
-	int health, ret;
+	int health;
 
 	mutex_lock(&bdi->f_reg_lock);
-
-	if (bdi->battery_health_valid) {
-		v = bdi->f_reg;
-		bdi->battery_health_valid = false;
-		mutex_unlock(&bdi->f_reg_lock);
-	} else {
-		mutex_unlock(&bdi->f_reg_lock);
-
-		ret = bq24190_read(bdi, BQ24190_REG_F, &v);
-		if (ret < 0)
-			return ret;
-	}
+	v = bdi->f_reg;
+	mutex_unlock(&bdi->f_reg_lock);
 
 	if (v & BQ24190_REG_F_BAT_FAULT_MASK) {
 		health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
@@ -1197,9 +1160,12 @@ static const struct power_supply_desc bq24190_battery_desc = {
 static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 {
 	struct bq24190_dev_info *bdi = data;
-	bool alert_userspace = false;
+	const u8 battery_mask_ss = BQ24190_REG_SS_CHRG_STAT_MASK;
+	const u8 battery_mask_f = BQ24190_REG_F_BAT_FAULT_MASK
+				| BQ24190_REG_F_NTC_FAULT_MASK;
+	bool alert_charger = false, alert_battery = false;
 	u8 ss_reg = 0, f_reg = 0;
-	int ret;
+	int i, ret;
 
 	pm_runtime_get_sync(bdi->dev);
 
@@ -1209,6 +1175,32 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 		goto out;
 	}
 
+	i = 0;
+	do {
+		ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg);
+		if (ret < 0) {
+			dev_err(bdi->dev, "Can't read F reg: %d\n", ret);
+			goto out;
+		}
+	} while (f_reg && ++i < 2);
+
+	if (f_reg != bdi->f_reg) {
+		dev_info(bdi->dev,
+			"Fault: boost %d, charge %d, battery %d, ntc %d\n",
+			!!(f_reg & BQ24190_REG_F_BOOST_FAULT_MASK),
+			!!(f_reg & BQ24190_REG_F_CHRG_FAULT_MASK),
+			!!(f_reg & BQ24190_REG_F_BAT_FAULT_MASK),
+			!!(f_reg & BQ24190_REG_F_NTC_FAULT_MASK));
+
+		mutex_lock(&bdi->f_reg_lock);
+		if ((bdi->f_reg & battery_mask_f) != (f_reg & battery_mask_f))
+			alert_battery = true;
+		if ((bdi->f_reg & ~battery_mask_f) != (f_reg & ~battery_mask_f))
+			alert_charger = true;
+		bdi->f_reg = f_reg;
+		mutex_unlock(&bdi->f_reg_lock);
+	}
+
 	if (ss_reg != bdi->ss_reg) {
 		/*
 		 * The device is in host mode so when PG_STAT goes from 1->0
@@ -1225,47 +1217,17 @@ static irqreturn_t bq24190_irq_handler_thread(int irq, void *data)
 					ret);
 		}
 
+		if ((bdi->ss_reg & battery_mask_ss) != (ss_reg & battery_mask_ss))
+			alert_battery = true;
+		if ((bdi->ss_reg & ~battery_mask_ss) != (ss_reg & ~battery_mask_ss))
+			alert_charger = true;
 		bdi->ss_reg = ss_reg;
-		alert_userspace = true;
-	}
-
-	mutex_lock(&bdi->f_reg_lock);
-
-	ret = bq24190_read(bdi, BQ24190_REG_F, &f_reg);
-	if (ret < 0) {
-		mutex_unlock(&bdi->f_reg_lock);
-		dev_err(bdi->dev, "Can't read F reg: %d\n", ret);
-		goto out;
-	}
-
-	if (f_reg != bdi->f_reg) {
-		bdi->f_reg = f_reg;
-		bdi->charger_health_valid = true;
-		bdi->battery_health_valid = true;
-		bdi->battery_status_valid = true;
-
-		alert_userspace = true;
 	}
 
-	mutex_unlock(&bdi->f_reg_lock);
-
-	/*
-	 * Sometimes bq24190 gives a steady trickle of interrupts even
-	 * though the watchdog timer is turned off and neither the STATUS
-	 * nor FAULT registers have changed.  Weed out these sprurious
-	 * interrupts so userspace isn't alerted for no reason.
-	 * In addition, the chip always generates an interrupt after
-	 * register reset so we should ignore that one (the very first
-	 * interrupt received).
-	 */
-	if (alert_userspace) {
-		if (!bdi->first_time) {
-			power_supply_changed(bdi->charger);
-			power_supply_changed(bdi->battery);
-		} else {
-			bdi->first_time = false;
-		}
-	}
+	if (alert_charger)
+		power_supply_changed(bdi->charger);
+	if (alert_battery)
+		power_supply_changed(bdi->battery);
 
 out:
 	pm_runtime_put_sync(bdi->dev);
@@ -1300,6 +1262,10 @@ static int bq24190_hw_init(struct bq24190_dev_info *bdi)
 		goto out;
 
 	ret = bq24190_set_mode_host(bdi);
+	if (ret < 0)
+		goto out;
+
+	ret = bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
 out:
 	pm_runtime_put_sync(bdi->dev);
 	return ret;
@@ -1375,10 +1341,8 @@ static int bq24190_probe(struct i2c_client *client,
 	bdi->model = id->driver_data;
 	strncpy(bdi->model_name, id->name, I2C_NAME_SIZE);
 	mutex_init(&bdi->f_reg_lock);
-	bdi->first_time = true;
-	bdi->charger_health_valid = false;
-	bdi->battery_health_valid = false;
-	bdi->battery_status_valid = false;
+	bdi->f_reg = 0;
+	bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */
 
 	i2c_set_clientdata(client, bdi);
 
@@ -1392,22 +1356,13 @@ static int bq24190_probe(struct i2c_client *client,
 		return -EINVAL;
 	}
 
-	ret = devm_request_threaded_irq(dev, bdi->irq, NULL,
-			bq24190_irq_handler_thread,
-			IRQF_TRIGGER_RISING | IRQF_ONESHOT,
-			"bq24190-charger", bdi);
-	if (ret < 0) {
-		dev_err(dev, "Can't set up irq handler\n");
-		goto out1;
-	}
-
 	pm_runtime_enable(dev);
 	pm_runtime_resume(dev);
 
 	ret = bq24190_hw_init(bdi);
 	if (ret < 0) {
 		dev_err(dev, "Hardware init failed\n");
-		goto out2;
+		goto out1;
 	}
 
 	charger_cfg.drv_data = bdi;
@@ -1418,7 +1373,7 @@ static int bq24190_probe(struct i2c_client *client,
 	if (IS_ERR(bdi->charger)) {
 		dev_err(dev, "Can't register charger\n");
 		ret = PTR_ERR(bdi->charger);
-		goto out2;
+		goto out1;
 	}
 
 	battery_cfg.drv_data = bdi;
@@ -1427,27 +1382,39 @@ static int bq24190_probe(struct i2c_client *client,
 	if (IS_ERR(bdi->battery)) {
 		dev_err(dev, "Can't register battery\n");
 		ret = PTR_ERR(bdi->battery);
-		goto out3;
+		goto out2;
 	}
 
 	ret = bq24190_sysfs_create_group(bdi);
 	if (ret) {
 		dev_err(dev, "Can't create sysfs entries\n");
+		goto out3;
+	}
+
+	ret = devm_request_threaded_irq(dev, bdi->irq, NULL,
+			bq24190_irq_handler_thread,
+			IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+			"bq24190-charger", bdi);
+	if (ret < 0) {
+		dev_err(dev, "Can't set up irq handler\n");
 		goto out4;
 	}
 
 	return 0;
 
 out4:
-	power_supply_unregister(bdi->battery);
+	bq24190_sysfs_remove_group(bdi);
+
 out3:
-	power_supply_unregister(bdi->charger);
+	power_supply_unregister(bdi->battery);
+
 out2:
-	pm_runtime_disable(dev);
+	power_supply_unregister(bdi->charger);
+
 out1:
+	pm_runtime_disable(dev);
 	if (bdi->gpio_int)
 		gpio_free(bdi->gpio_int);
-
 	return ret;
 }
 
@@ -1488,12 +1455,13 @@ static int bq24190_pm_resume(struct device *dev)
 	struct i2c_client *client = to_i2c_client(dev);
 	struct bq24190_dev_info *bdi = i2c_get_clientdata(client);
 
-	bdi->charger_health_valid = false;
-	bdi->battery_health_valid = false;
-	bdi->battery_status_valid = false;
+	bdi->f_reg = 0;
+	bdi->ss_reg = BQ24190_REG_SS_VBUS_STAT_MASK; /* impossible state */
 
 	pm_runtime_get_sync(bdi->dev);
 	bq24190_register_reset(bdi);
+	bq24190_set_mode_host(bdi);
+	bq24190_read(bdi, BQ24190_REG_SS, &bdi->ss_reg);
 	pm_runtime_put_sync(bdi->dev);
 
 	/* Things may have changed while suspended so alert upper layer */
diff --git a/drivers/power/supply/bq24735-charger.c b/drivers/power/supply/bq24735-charger.c
index eb7783b42e0a..eb0145380def 100644
--- a/drivers/power/supply/bq24735-charger.c
+++ b/drivers/power/supply/bq24735-charger.c
@@ -50,6 +50,8 @@ struct bq24735 {
 	struct bq24735_platform		*pdata;
 	struct mutex			lock;
 	struct gpio_desc		*status_gpio;
+	struct delayed_work		poll;
+	u32				poll_interval;
 	bool				charging;
 };
 
@@ -105,26 +107,6 @@ static int bq24735_update_word(struct i2c_client *client, u8 reg,
 	return bq24735_write_word(client, reg, tmp);
 }
 
-static inline int bq24735_enable_charging(struct bq24735 *charger)
-{
-	if (charger->pdata->ext_control)
-		return 0;
-
-	return bq24735_update_word(charger->client, BQ24735_CHG_OPT,
-				   BQ24735_CHG_OPT_CHARGE_DISABLE,
-				   ~BQ24735_CHG_OPT_CHARGE_DISABLE);
-}
-
-static inline int bq24735_disable_charging(struct bq24735 *charger)
-{
-	if (charger->pdata->ext_control)
-		return 0;
-
-	return bq24735_update_word(charger->client, BQ24735_CHG_OPT,
-				   BQ24735_CHG_OPT_CHARGE_DISABLE,
-				   BQ24735_CHG_OPT_CHARGE_DISABLE);
-}
-
 static int bq24735_config_charger(struct bq24735 *charger)
 {
 	struct bq24735_platform *pdata = charger->pdata;
@@ -176,6 +158,31 @@ static int bq24735_config_charger(struct bq24735 *charger)
 	return 0;
 }
 
+static inline int bq24735_enable_charging(struct bq24735 *charger)
+{
+	int ret;
+
+	if (charger->pdata->ext_control)
+		return 0;
+
+	ret = bq24735_config_charger(charger);
+	if (ret)
+		return ret;
+
+	return bq24735_update_word(charger->client, BQ24735_CHG_OPT,
+				   BQ24735_CHG_OPT_CHARGE_DISABLE, 0);
+}
+
+static inline int bq24735_disable_charging(struct bq24735 *charger)
+{
+	if (charger->pdata->ext_control)
+		return 0;
+
+	return bq24735_update_word(charger->client, BQ24735_CHG_OPT,
+				   BQ24735_CHG_OPT_CHARGE_DISABLE,
+				   BQ24735_CHG_OPT_CHARGE_DISABLE);
+}
+
 static bool bq24735_charger_is_present(struct bq24735 *charger)
 {
 	if (charger->status_gpio) {
@@ -185,7 +192,7 @@ static bool bq24735_charger_is_present(struct bq24735 *charger)
 
 		ac = bq24735_read_word(charger->client, BQ24735_CHG_OPT);
 		if (ac < 0) {
-			dev_err(&charger->client->dev,
+			dev_dbg(&charger->client->dev,
 				"Failed to read charger options : %d\n",
 				ac);
 			return false;
@@ -210,11 +217,8 @@ static int bq24735_charger_is_charging(struct bq24735 *charger)
 	return !(ret & BQ24735_CHG_OPT_CHARGE_DISABLE);
 }
 
-static irqreturn_t bq24735_charger_isr(int irq, void *devid)
+static void bq24735_update(struct bq24735 *charger)
 {
-	struct power_supply *psy = devid;
-	struct bq24735 *charger = to_bq24735(psy);
-
 	mutex_lock(&charger->lock);
 
 	if (charger->charging && bq24735_charger_is_present(charger))
@@ -224,11 +228,29 @@ static irqreturn_t bq24735_charger_isr(int irq, void *devid)
 
 	mutex_unlock(&charger->lock);
 
-	power_supply_changed(psy);
+	power_supply_changed(charger->charger);
+}
+
+static irqreturn_t bq24735_charger_isr(int irq, void *devid)
+{
+	struct power_supply *psy = devid;
+	struct bq24735 *charger = to_bq24735(psy);
+
+	bq24735_update(charger);
 
 	return IRQ_HANDLED;
 }
 
+static void bq24735_poll(struct work_struct *work)
+{
+	struct bq24735 *charger = container_of(work, struct bq24735, poll.work);
+
+	bq24735_update(charger);
+
+	schedule_delayed_work(&charger->poll,
+			      msecs_to_jiffies(charger->poll_interval));
+}
+
 static int bq24735_charger_get_property(struct power_supply *psy,
 					enum power_supply_property psp,
 					union power_supply_propval *val)
@@ -276,7 +298,6 @@ static int bq24735_charger_set_property(struct power_supply *psy,
 			mutex_unlock(&charger->lock);
 			if (ret)
 				return ret;
-			bq24735_config_charger(charger);
 			break;
 		case POWER_SUPPLY_STATUS_DISCHARGING:
 		case POWER_SUPPLY_STATUS_NOT_CHARGING:
@@ -395,7 +416,7 @@ static int bq24735_charger_probe(struct i2c_client *client,
 		return ret;
 	}
 
-	if (!charger->status_gpio || bq24735_charger_is_present(charger)) {
+	if (bq24735_charger_is_present(charger)) {
 		ret = bq24735_read_word(client, BQ24735_MANUFACTURER_ID);
 		if (ret < 0) {
 			dev_err(&client->dev, "Failed to read manufacturer id : %d\n",
@@ -416,16 +437,7 @@ static int bq24735_charger_probe(struct i2c_client *client,
 				"device id mismatch. 0x000b != 0x%04x\n", ret);
 			return -ENODEV;
 		}
-	}
-
-	ret = bq24735_config_charger(charger);
-	if (ret < 0) {
-		dev_err(&client->dev, "failed in configuring charger");
-		return ret;
-	}
 
-	/* check for AC adapter presence */
-	if (bq24735_charger_is_present(charger)) {
 		ret = bq24735_enable_charging(charger);
 		if (ret < 0) {
 			dev_err(&client->dev, "Failed to enable charging\n");
@@ -456,11 +468,32 @@ static int bq24735_charger_probe(struct i2c_client *client,
 				client->irq, ret);
 			return ret;
 		}
+	} else {
+		ret = device_property_read_u32(&client->dev, "poll-interval",
+					       &charger->poll_interval);
+		if (ret)
+			return 0;
+		if (!charger->poll_interval)
+			return 0;
+
+		INIT_DELAYED_WORK(&charger->poll, bq24735_poll);
+		schedule_delayed_work(&charger->poll,
+				      msecs_to_jiffies(charger->poll_interval));
 	}
 
 	return 0;
 }
 
+static int bq24735_charger_remove(struct i2c_client *client)
+{
+	struct bq24735 *charger = i2c_get_clientdata(client);
+
+	if (charger->poll_interval)
+		cancel_delayed_work_sync(&charger->poll);
+
+	return 0;
+}
+
 static const struct i2c_device_id bq24735_charger_id[] = {
 	{ "bq24735-charger", 0 },
 	{}
@@ -479,6 +512,7 @@ static struct i2c_driver bq24735_charger_driver = {
 		.of_match_table = bq24735_match_ids,
 	},
 	.probe = bq24735_charger_probe,
+	.remove = bq24735_charger_remove,
 	.id_table = bq24735_charger_id,
 };
 
diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c
index 08c36b8e04bd..398801a21b86 100644
--- a/drivers/power/supply/bq27xxx_battery.c
+++ b/drivers/power/supply/bq27xxx_battery.c
@@ -22,8 +22,14 @@
  * http://www.ti.com/product/bq27010
  * http://www.ti.com/product/bq27210
  * http://www.ti.com/product/bq27500
+ * http://www.ti.com/product/bq27510-g1
+ * http://www.ti.com/product/bq27510-g2
  * http://www.ti.com/product/bq27510-g3
  * http://www.ti.com/product/bq27520-g4
+ * http://www.ti.com/product/bq27520-g1
+ * http://www.ti.com/product/bq27520-g2
+ * http://www.ti.com/product/bq27520-g3
+ * http://www.ti.com/product/bq27520-g4
  * http://www.ti.com/product/bq27530-g1
  * http://www.ti.com/product/bq27531-g1
  * http://www.ti.com/product/bq27541-g1
@@ -145,7 +151,7 @@ static u8 bq27xxx_regs[][BQ27XXX_REG_MAX] = {
 		[BQ27XXX_REG_DCAP] = 0x76,
 		[BQ27XXX_REG_AP] = INVALID_REG_ADDR,
 	},
-	[BQ27500] = {
+	[BQ2750X] = {
 		[BQ27XXX_REG_CTRL] = 0x00,
 		[BQ27XXX_REG_TEMP] = 0x06,
 		[BQ27XXX_REG_INT_TEMP] = 0x28,
@@ -164,7 +170,83 @@ static u8 bq27xxx_regs[][BQ27XXX_REG_MAX] = {
 		[BQ27XXX_REG_DCAP] = 0x3c,
 		[BQ27XXX_REG_AP] = INVALID_REG_ADDR,
 	},
-	[BQ27510] = {
+	[BQ2751X] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = 0x28,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTES] = 0x1a,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x1e,
+		[BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SOC] = 0x20,
+		[BQ27XXX_REG_DCAP] = 0x2e,
+		[BQ27XXX_REG_AP] = INVALID_REG_ADDR,
+	},
+	[BQ27500] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = 0x18,
+		[BQ27XXX_REG_TTES] = 0x1c,
+		[BQ27XXX_REG_TTECP] = 0x26,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = 0x22,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x24,
+	},
+	[BQ27510G1] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = 0x18,
+		[BQ27XXX_REG_TTES] = 0x1c,
+		[BQ27XXX_REG_TTECP] = 0x26,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = 0x22,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x24,
+	},
+	[BQ27510G2] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = 0x18,
+		[BQ27XXX_REG_TTES] = 0x1c,
+		[BQ27XXX_REG_TTECP] = 0x26,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = 0x22,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x24,
+	},
+	[BQ27510G3] = {
 		[BQ27XXX_REG_CTRL] = 0x00,
 		[BQ27XXX_REG_TEMP] = 0x06,
 		[BQ27XXX_REG_INT_TEMP] = 0x28,
@@ -183,6 +265,82 @@ static u8 bq27xxx_regs[][BQ27XXX_REG_MAX] = {
 		[BQ27XXX_REG_DCAP] = 0x2e,
 		[BQ27XXX_REG_AP] = INVALID_REG_ADDR,
 	},
+	[BQ27520G1] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = 0x18,
+		[BQ27XXX_REG_TTES] = 0x1c,
+		[BQ27XXX_REG_TTECP] = 0x26,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_AE] = 0x22,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x24,
+	},
+	[BQ27520G2] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = 0x36,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = 0x18,
+		[BQ27XXX_REG_TTES] = 0x1c,
+		[BQ27XXX_REG_TTECP] = 0x26,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = 0x22,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x24,
+	},
+	[BQ27520G3] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = 0x36,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTES] = 0x1c,
+		[BQ27XXX_REG_TTECP] = 0x26,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x2a,
+		[BQ27XXX_REG_AE] = 0x22,
+		[BQ27XXX_REG_SOC] = 0x2c,
+		[BQ27XXX_REG_DCAP] = 0x3c,
+		[BQ27XXX_REG_AP] = 0x24,
+	},
+	[BQ27520G4] = {
+		[BQ27XXX_REG_CTRL] = 0x00,
+		[BQ27XXX_REG_TEMP] = 0x06,
+		[BQ27XXX_REG_INT_TEMP] = 0x28,
+		[BQ27XXX_REG_VOLT] = 0x08,
+		[BQ27XXX_REG_AI] = 0x14,
+		[BQ27XXX_REG_FLAGS] = 0x0a,
+		[BQ27XXX_REG_TTE] = 0x16,
+		[BQ27XXX_REG_TTF] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_TTES] = 0x1c,
+		[BQ27XXX_REG_TTECP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_NAC] = 0x0c,
+		[BQ27XXX_REG_FCC] = 0x12,
+		[BQ27XXX_REG_CYCT] = 0x1e,
+		[BQ27XXX_REG_AE] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_SOC] = 0x20,
+		[BQ27XXX_REG_DCAP] = INVALID_REG_ADDR,
+		[BQ27XXX_REG_AP] = INVALID_REG_ADDR,
+	},
 	[BQ27530] = {
 		[BQ27XXX_REG_CTRL] = 0x00,
 		[BQ27XXX_REG_TEMP] = 0x06,
@@ -303,6 +461,42 @@ static enum power_supply_property bq27010_battery_props[] = {
 	POWER_SUPPLY_PROP_MANUFACTURER,
 };
 
+static enum power_supply_property bq2750x_battery_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq2751x_battery_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
 static enum power_supply_property bq27500_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
@@ -312,6 +506,69 @@ static enum power_supply_property bq27500_battery_props[] = {
 	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
 	POWER_SUPPLY_PROP_TEMP,
 	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27510g1_battery_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27510g2_battery_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27510g3_battery_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
 	POWER_SUPPLY_PROP_TECHNOLOGY,
 	POWER_SUPPLY_PROP_CHARGE_FULL,
 	POWER_SUPPLY_PROP_CHARGE_NOW,
@@ -321,7 +578,27 @@ static enum power_supply_property bq27500_battery_props[] = {
 	POWER_SUPPLY_PROP_MANUFACTURER,
 };
 
-static enum power_supply_property bq27510_battery_props[] = {
+static enum power_supply_property bq27520g1_battery_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27520g2_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
 	POWER_SUPPLY_PROP_VOLTAGE_NOW,
@@ -330,11 +607,51 @@ static enum power_supply_property bq27510_battery_props[] = {
 	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
 	POWER_SUPPLY_PROP_TEMP,
 	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TIME_TO_FULL_NOW,
 	POWER_SUPPLY_PROP_TECHNOLOGY,
 	POWER_SUPPLY_PROP_CHARGE_FULL,
 	POWER_SUPPLY_PROP_CHARGE_NOW,
 	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
 	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27520g3_battery_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_POWER_AVG,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static enum power_supply_property bq27520g4_battery_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_CURRENT_NOW,
+	POWER_SUPPLY_PROP_CAPACITY,
+	POWER_SUPPLY_PROP_CAPACITY_LEVEL,
+	POWER_SUPPLY_PROP_TEMP,
+	POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CHARGE_FULL,
+	POWER_SUPPLY_PROP_CHARGE_NOW,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
 	POWER_SUPPLY_PROP_HEALTH,
 	POWER_SUPPLY_PROP_MANUFACTURER,
 };
@@ -421,8 +738,16 @@ static struct {
 } bq27xxx_battery_props[] = {
 	BQ27XXX_PROP(BQ27000, bq27000_battery_props),
 	BQ27XXX_PROP(BQ27010, bq27010_battery_props),
+	BQ27XXX_PROP(BQ2750X, bq2750x_battery_props),
+	BQ27XXX_PROP(BQ2751X, bq2751x_battery_props),
 	BQ27XXX_PROP(BQ27500, bq27500_battery_props),
-	BQ27XXX_PROP(BQ27510, bq27510_battery_props),
+	BQ27XXX_PROP(BQ27510G1, bq27510g1_battery_props),
+	BQ27XXX_PROP(BQ27510G2, bq27510g2_battery_props),
+	BQ27XXX_PROP(BQ27510G3, bq27510g3_battery_props),
+	BQ27XXX_PROP(BQ27520G1, bq27520g1_battery_props),
+	BQ27XXX_PROP(BQ27520G2, bq27520g2_battery_props),
+	BQ27XXX_PROP(BQ27520G3, bq27520g3_battery_props),
+	BQ27XXX_PROP(BQ27520G4, bq27520g4_battery_props),
 	BQ27XXX_PROP(BQ27530, bq27530_battery_props),
 	BQ27XXX_PROP(BQ27541, bq27541_battery_props),
 	BQ27XXX_PROP(BQ27545, bq27545_battery_props),
@@ -674,13 +999,26 @@ static int bq27xxx_battery_read_pwr_avg(struct bq27xxx_device_info *di)
  */
 static bool bq27xxx_battery_overtemp(struct bq27xxx_device_info *di, u16 flags)
 {
-	if (di->chip == BQ27500 || di->chip == BQ27510 ||
-	    di->chip == BQ27541 || di->chip == BQ27545)
+	switch (di->chip) {
+	case BQ2750X:
+	case BQ2751X:
+	case BQ27500:
+	case BQ27510G1:
+	case BQ27510G2:
+	case BQ27510G3:
+	case BQ27520G1:
+	case BQ27520G2:
+	case BQ27520G3:
+	case BQ27520G4:
+	case BQ27541:
+	case BQ27545:
 		return flags & (BQ27XXX_FLAG_OTC | BQ27XXX_FLAG_OTD);
-	if (di->chip == BQ27530 || di->chip == BQ27421)
+	case BQ27530:
+	case BQ27421:
 		return flags & BQ27XXX_FLAG_OT;
-
-	return false;
+	default:
+		return false;
+	}
 }
 
 /*
diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c
index 5c5c3a6f9923..c68fbc3fe50a 100644
--- a/drivers/power/supply/bq27xxx_battery_i2c.c
+++ b/drivers/power/supply/bq27xxx_battery_i2c.c
@@ -148,9 +148,17 @@ static int bq27xxx_battery_i2c_remove(struct i2c_client *client)
 static const struct i2c_device_id bq27xxx_i2c_id_table[] = {
 	{ "bq27200", BQ27000 },
 	{ "bq27210", BQ27010 },
-	{ "bq27500", BQ27500 },
-	{ "bq27510", BQ27510 },
-	{ "bq27520", BQ27510 },
+	{ "bq27500", BQ2750X },
+	{ "bq27510", BQ2751X },
+	{ "bq27520", BQ2751X },
+	{ "bq27500-1", BQ27500 },
+	{ "bq27510g1", BQ27510G1 },
+	{ "bq27510g2", BQ27510G2 },
+	{ "bq27510g3", BQ27510G3 },
+	{ "bq27520g1", BQ27520G1 },
+	{ "bq27520g2", BQ27520G2 },
+	{ "bq27520g3", BQ27520G3 },
+	{ "bq27520g4", BQ27520G4 },
 	{ "bq27530", BQ27530 },
 	{ "bq27531", BQ27530 },
 	{ "bq27541", BQ27541 },
@@ -173,6 +181,14 @@ static const struct of_device_id bq27xxx_battery_i2c_of_match_table[] = {
 	{ .compatible = "ti,bq27500" },
 	{ .compatible = "ti,bq27510" },
 	{ .compatible = "ti,bq27520" },
+	{ .compatible = "ti,bq27500-1" },
+	{ .compatible = "ti,bq27510g1" },
+	{ .compatible = "ti,bq27510g2" },
+	{ .compatible = "ti,bq27510g3" },
+	{ .compatible = "ti,bq27520g1" },
+	{ .compatible = "ti,bq27520g2" },
+	{ .compatible = "ti,bq27520g3" },
+	{ .compatible = "ti,bq27520g4" },
 	{ .compatible = "ti,bq27530" },
 	{ .compatible = "ti,bq27531" },
 	{ .compatible = "ti,bq27541" },
diff --git a/drivers/power/supply/gpio-charger.c b/drivers/power/supply/gpio-charger.c
index c5869b1941ac..001731e88718 100644
--- a/drivers/power/supply/gpio-charger.c
+++ b/drivers/power/supply/gpio-charger.c
@@ -14,7 +14,7 @@
  */
 
 #include <linux/device.h>
-#include <linux/gpio.h>
+#include <linux/gpio.h> /* For legacy platform data */
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
@@ -23,7 +23,7 @@
 #include <linux/power_supply.h>
 #include <linux/slab.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
+#include <linux/gpio/consumer.h>
 
 #include <linux/power/gpio-charger.h>
 
@@ -34,6 +34,8 @@ struct gpio_charger {
 
 	struct power_supply *charger;
 	struct power_supply_desc charger_desc;
+	struct gpio_desc *gpiod;
+	bool legacy_gpio_requested;
 };
 
 static irqreturn_t gpio_charger_irq(int irq, void *devid)
@@ -58,7 +60,8 @@ static int gpio_charger_get_property(struct power_supply *psy,
 
 	switch (psp) {
 	case POWER_SUPPLY_PROP_ONLINE:
-		val->intval = !!gpio_get_value_cansleep(pdata->gpio);
+		val->intval = gpiod_get_value_cansleep(gpio_charger->gpiod);
+		/* This xor is only ever used with legacy pdata GPIO */
 		val->intval ^= pdata->gpio_active_low;
 		break;
 	default:
@@ -78,7 +81,6 @@ struct gpio_charger_platform_data *gpio_charger_parse_dt(struct device *dev)
 	struct device_node *np = dev->of_node;
 	struct gpio_charger_platform_data *pdata;
 	const char *chargetype;
-	enum of_gpio_flags flags;
 	int ret;
 
 	if (!np)
@@ -89,16 +91,6 @@ struct gpio_charger_platform_data *gpio_charger_parse_dt(struct device *dev)
 		return ERR_PTR(-ENOMEM);
 
 	pdata->name = np->name;
-
-	pdata->gpio = of_get_gpio_flags(np, 0, &flags);
-	if (pdata->gpio < 0) {
-		if (pdata->gpio != -EPROBE_DEFER)
-			dev_err(dev, "could not get charger gpio\n");
-		return ERR_PTR(pdata->gpio);
-	}
-
-	pdata->gpio_active_low = !!(flags & OF_GPIO_ACTIVE_LOW);
-
 	pdata->type = POWER_SUPPLY_TYPE_UNKNOWN;
 	ret = of_property_read_string(np, "charger-type", &chargetype);
 	if (ret >= 0) {
@@ -144,11 +136,6 @@ static int gpio_charger_probe(struct platform_device *pdev)
 		}
 	}
 
-	if (!gpio_is_valid(pdata->gpio)) {
-		dev_err(&pdev->dev, "Invalid gpio pin\n");
-		return -EINVAL;
-	}
-
 	gpio_charger = devm_kzalloc(&pdev->dev, sizeof(*gpio_charger),
 					GFP_KERNEL);
 	if (!gpio_charger) {
@@ -156,6 +143,45 @@ static int gpio_charger_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	/*
+	 * This will fetch a GPIO descriptor from device tree, ACPI or
+	 * boardfile descriptor tables. It's good to try this first.
+	 */
+	gpio_charger->gpiod = devm_gpiod_get(&pdev->dev, NULL, GPIOD_IN);
+
+	/*
+	 * If this fails and we're not using device tree, try the
+	 * legacy platform data method.
+	 */
+	if (IS_ERR(gpio_charger->gpiod) && !pdev->dev.of_node) {
+		/* Non-DT: use legacy GPIO numbers */
+		if (!gpio_is_valid(pdata->gpio)) {
+			dev_err(&pdev->dev, "Invalid gpio pin in pdata\n");
+			return -EINVAL;
+		}
+		ret = gpio_request(pdata->gpio, dev_name(&pdev->dev));
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to request gpio pin: %d\n",
+				ret);
+			return ret;
+		}
+		gpio_charger->legacy_gpio_requested = true;
+		ret = gpio_direction_input(pdata->gpio);
+		if (ret) {
+			dev_err(&pdev->dev, "Failed to set gpio to input: %d\n",
+				ret);
+			goto err_gpio_free;
+		}
+		/* Then convert this to gpiod for now */
+		gpio_charger->gpiod = gpio_to_desc(pdata->gpio);
+	} else if (IS_ERR(gpio_charger->gpiod)) {
+		/* Just try again if this happens */
+		if (PTR_ERR(gpio_charger->gpiod) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+		dev_err(&pdev->dev, "error getting GPIO descriptor\n");
+		return PTR_ERR(gpio_charger->gpiod);
+	}
+
 	charger_desc = &gpio_charger->charger_desc;
 
 	charger_desc->name = pdata->name ? pdata->name : "gpio-charger";
@@ -169,17 +195,6 @@ static int gpio_charger_probe(struct platform_device *pdev)
 	psy_cfg.of_node = pdev->dev.of_node;
 	psy_cfg.drv_data = gpio_charger;
 
-	ret = gpio_request(pdata->gpio, dev_name(&pdev->dev));
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to request gpio pin: %d\n", ret);
-		goto err_free;
-	}
-	ret = gpio_direction_input(pdata->gpio);
-	if (ret) {
-		dev_err(&pdev->dev, "Failed to set gpio to input: %d\n", ret);
-		goto err_gpio_free;
-	}
-
 	gpio_charger->pdata = pdata;
 
 	gpio_charger->charger = power_supply_register(&pdev->dev,
@@ -191,7 +206,7 @@ static int gpio_charger_probe(struct platform_device *pdev)
 		goto err_gpio_free;
 	}
 
-	irq = gpio_to_irq(pdata->gpio);
+	irq = gpiod_to_irq(gpio_charger->gpiod);
 	if (irq > 0) {
 		ret = request_any_context_irq(irq, gpio_charger_irq,
 				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
@@ -209,8 +224,8 @@ static int gpio_charger_probe(struct platform_device *pdev)
 	return 0;
 
 err_gpio_free:
-	gpio_free(pdata->gpio);
-err_free:
+	if (gpio_charger->legacy_gpio_requested)
+		gpio_free(pdata->gpio);
 	return ret;
 }
 
@@ -223,7 +238,8 @@ static int gpio_charger_remove(struct platform_device *pdev)
 
 	power_supply_unregister(gpio_charger->charger);
 
-	gpio_free(gpio_charger->pdata->gpio);
+	if (gpio_charger->legacy_gpio_requested)
+		gpio_free(gpio_charger->pdata->gpio);
 
 	return 0;
 }
diff --git a/drivers/power/supply/intel_mid_battery.c b/drivers/power/supply/intel_mid_battery.c
deleted file mode 100644
index dc7feef1bea4..000000000000
--- a/drivers/power/supply/intel_mid_battery.c
+++ /dev/null
@@ -1,795 +0,0 @@
-/*
- * intel_mid_battery.c - Intel MID PMIC Battery Driver
- *
- * Copyright (C) 2009 Intel Corporation
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.	See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- * Author: Nithish Mahalingam <nithish.mahalingam@intel.com>
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/err.h>
-#include <linux/interrupt.h>
-#include <linux/workqueue.h>
-#include <linux/jiffies.h>
-#include <linux/param.h>
-#include <linux/device.h>
-#include <linux/spi/spi.h>
-#include <linux/platform_device.h>
-#include <linux/power_supply.h>
-
-#include <asm/intel_scu_ipc.h>
-
-#define DRIVER_NAME "pmic_battery"
-
-/*********************************************************************
- *		Generic defines
- *********************************************************************/
-
-static int debug;
-module_param(debug, int, 0444);
-MODULE_PARM_DESC(debug, "Flag to enable PMIC Battery debug messages.");
-
-#define PMIC_BATT_DRV_INFO_UPDATED	1
-#define PMIC_BATT_PRESENT		1
-#define PMIC_BATT_NOT_PRESENT		0
-#define PMIC_USB_PRESENT		PMIC_BATT_PRESENT
-#define PMIC_USB_NOT_PRESENT		PMIC_BATT_NOT_PRESENT
-
-/* pmic battery register related */
-#define PMIC_BATT_CHR_SCHRGINT_ADDR	0xD2
-#define PMIC_BATT_CHR_SBATOVP_MASK	(1 << 1)
-#define PMIC_BATT_CHR_STEMP_MASK	(1 << 2)
-#define PMIC_BATT_CHR_SCOMP_MASK	(1 << 3)
-#define PMIC_BATT_CHR_SUSBDET_MASK	(1 << 4)
-#define PMIC_BATT_CHR_SBATDET_MASK	(1 << 5)
-#define PMIC_BATT_CHR_SDCLMT_MASK	(1 << 6)
-#define PMIC_BATT_CHR_SUSBOVP_MASK	(1 << 7)
-#define PMIC_BATT_CHR_EXCPT_MASK	0x86
-
-#define PMIC_BATT_ADC_ACCCHRG_MASK	(1 << 31)
-#define PMIC_BATT_ADC_ACCCHRGVAL_MASK	0x7FFFFFFF
-
-/* pmic ipc related */
-#define PMIC_BATT_CHR_IPC_FCHRG_SUBID	0x4
-#define PMIC_BATT_CHR_IPC_TCHRG_SUBID	0x6
-
-/* types of battery charging */
-enum batt_charge_type {
-	BATT_USBOTG_500MA_CHARGE,
-	BATT_USBOTG_TRICKLE_CHARGE,
-};
-
-/* valid battery events */
-enum batt_event {
-	BATT_EVENT_BATOVP_EXCPT,
-	BATT_EVENT_USBOVP_EXCPT,
-	BATT_EVENT_TEMP_EXCPT,
-	BATT_EVENT_DCLMT_EXCPT,
-	BATT_EVENT_EXCPT
-};
-
-
-/*********************************************************************
- *		Battery properties
- *********************************************************************/
-
-/*
- * pmic battery info
- */
-struct pmic_power_module_info {
-	bool is_dev_info_updated;
-	struct device *dev;
-	/* pmic battery data */
-	unsigned long update_time;		/* jiffies when data read */
-	unsigned int usb_is_present;
-	unsigned int batt_is_present;
-	unsigned int batt_health;
-	unsigned int usb_health;
-	unsigned int batt_status;
-	unsigned int batt_charge_now;		/* in mAS */
-	unsigned int batt_prev_charge_full;	/* in mAS */
-	unsigned int batt_charge_rate;		/* in units per second */
-
-	struct power_supply *usb;
-	struct power_supply *batt;
-	int irq;				/* GPE_ID or IRQ# */
-	struct workqueue_struct *monitor_wqueue;
-	struct delayed_work monitor_battery;
-	struct work_struct handler;
-};
-
-static unsigned int delay_time = 2000;	/* in ms */
-
-/*
- * pmic ac properties
- */
-static enum power_supply_property pmic_usb_props[] = {
-	POWER_SUPPLY_PROP_PRESENT,
-	POWER_SUPPLY_PROP_HEALTH,
-};
-
-/*
- * pmic battery properties
- */
-static enum power_supply_property pmic_battery_props[] = {
-	POWER_SUPPLY_PROP_STATUS,
-	POWER_SUPPLY_PROP_HEALTH,
-	POWER_SUPPLY_PROP_PRESENT,
-	POWER_SUPPLY_PROP_CHARGE_NOW,
-	POWER_SUPPLY_PROP_CHARGE_FULL,
-};
-
-
-/*
- * Glue functions for talking to the IPC
- */
-
-struct battery_property {
-	u32 capacity;	/* Charger capacity */
-	u8  crnt;	/* Quick charge current value*/
-	u8  volt;	/* Fine adjustment of constant charge voltage */
-	u8  prot;	/* CHRGPROT register value */
-	u8  prot2;	/* CHRGPROT1 register value */
-	u8  timer;	/* Charging timer */
-};
-
-#define IPCMSG_BATTERY		0xEF
-
-/* Battery coulomb counter accumulator commands */
-#define IPC_CMD_CC_WR		  0 /* Update coulomb counter value */
-#define IPC_CMD_CC_RD		  1 /* Read coulomb counter value */
-#define IPC_CMD_BATTERY_PROPERTY  2 /* Read Battery property */
-
-/**
- *	pmic_scu_ipc_battery_cc_read	-	read battery cc
- *	@value: battery coulomb counter read
- *
- *	Reads the battery couloumb counter value, returns 0 on success, or
- *	an error code
- *
- *	This function may sleep. Locking for SCU accesses is handled for
- *	the caller.
- */
-static int pmic_scu_ipc_battery_cc_read(u32 *value)
-{
-	return intel_scu_ipc_command(IPCMSG_BATTERY, IPC_CMD_CC_RD,
-					NULL, 0, value, 1);
-}
-
-/**
- *	pmic_scu_ipc_battery_property_get	-	fetch properties
- *	@prop: battery properties
- *
- *	Retrieve the battery properties from the power management
- *
- *	This function may sleep. Locking for SCU accesses is handled for
- *	the caller.
- */
-static int pmic_scu_ipc_battery_property_get(struct battery_property *prop)
-{
-	u32 data[3];
-	u8 *p = (u8 *)&data[1];
-	int err = intel_scu_ipc_command(IPCMSG_BATTERY,
-				IPC_CMD_BATTERY_PROPERTY, NULL, 0, data, 3);
-
-	prop->capacity = data[0];
-	prop->crnt = *p++;
-	prop->volt = *p++;
-	prop->prot = *p++;
-	prop->prot2 = *p++;
-	prop->timer = *p++;
-
-	return err;
-}
-
-/**
- *	pmic_scu_ipc_set_charger	-	set charger
- *	@charger: charger to select
- *
- *	Switch the charging mode for the SCU
- */
-
-static int pmic_scu_ipc_set_charger(int charger)
-{
-	return intel_scu_ipc_simple_command(IPCMSG_BATTERY, charger);
-}
-
-/**
- * pmic_battery_log_event - log battery events
- * @event: battery event to be logged
- * Context: can sleep
- *
- * There are multiple battery events which may be of interest to users;
- * this battery function logs the different battery events onto the
- * kernel log messages.
- */
-static void pmic_battery_log_event(enum batt_event event)
-{
-	printk(KERN_WARNING "pmic-battery: ");
-	switch (event) {
-	case BATT_EVENT_BATOVP_EXCPT:
-		printk(KERN_CONT "battery overvoltage condition\n");
-		break;
-	case BATT_EVENT_USBOVP_EXCPT:
-		printk(KERN_CONT "usb charger overvoltage condition\n");
-		break;
-	case BATT_EVENT_TEMP_EXCPT:
-		printk(KERN_CONT "high battery temperature condition\n");
-		break;
-	case BATT_EVENT_DCLMT_EXCPT:
-		printk(KERN_CONT "over battery charge current condition\n");
-		break;
-	default:
-		printk(KERN_CONT "charger/battery exception %d\n", event);
-		break;
-	}
-}
-
-/**
- * pmic_battery_read_status - read battery status information
- * @pbi: device info structure to update the read information
- * Context: can sleep
- *
- * PMIC power source information need to be updated based on the data read
- * from the PMIC battery registers.
- *
- */
-static void pmic_battery_read_status(struct pmic_power_module_info *pbi)
-{
-	unsigned int update_time_intrvl;
-	unsigned int chrg_val;
-	u32 ccval;
-	u8 r8;
-	struct battery_property batt_prop;
-	int batt_present = 0;
-	int usb_present = 0;
-	int batt_exception = 0;
-
-	/* make sure the last batt_status read happened delay_time before */
-	if (pbi->update_time && time_before(jiffies, pbi->update_time +
-						msecs_to_jiffies(delay_time)))
-		return;
-
-	update_time_intrvl = jiffies_to_msecs(jiffies -	pbi->update_time);
-	pbi->update_time = jiffies;
-
-	/* read coulomb counter registers and schrgint register */
-	if (pmic_scu_ipc_battery_cc_read(&ccval)) {
-		dev_warn(pbi->dev, "%s(): ipc config cmd failed\n",
-								__func__);
-		return;
-	}
-
-	if (intel_scu_ipc_ioread8(PMIC_BATT_CHR_SCHRGINT_ADDR, &r8)) {
-		dev_warn(pbi->dev, "%s(): ipc pmic read failed\n",
-								__func__);
-		return;
-	}
-
-	/*
-	 * set pmic_power_module_info members based on pmic register values
-	 * read.
-	 */
-
-	/* set batt_is_present */
-	if (r8 & PMIC_BATT_CHR_SBATDET_MASK) {
-		pbi->batt_is_present = PMIC_BATT_PRESENT;
-		batt_present = 1;
-	} else {
-		pbi->batt_is_present = PMIC_BATT_NOT_PRESENT;
-		pbi->batt_health = POWER_SUPPLY_HEALTH_UNKNOWN;
-		pbi->batt_status = POWER_SUPPLY_STATUS_UNKNOWN;
-	}
-
-	/* set batt_health */
-	if (batt_present) {
-		if (r8 & PMIC_BATT_CHR_SBATOVP_MASK) {
-			pbi->batt_health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
-			pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
-			pmic_battery_log_event(BATT_EVENT_BATOVP_EXCPT);
-			batt_exception = 1;
-		} else if (r8 & PMIC_BATT_CHR_STEMP_MASK) {
-			pbi->batt_health = POWER_SUPPLY_HEALTH_OVERHEAT;
-			pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
-			pmic_battery_log_event(BATT_EVENT_TEMP_EXCPT);
-			batt_exception = 1;
-		} else {
-			pbi->batt_health = POWER_SUPPLY_HEALTH_GOOD;
-			if (r8 & PMIC_BATT_CHR_SDCLMT_MASK) {
-				/* PMIC will change charging current automatically */
-				pmic_battery_log_event(BATT_EVENT_DCLMT_EXCPT);
-			}
-		}
-	}
-
-	/* set usb_is_present */
-	if (r8 & PMIC_BATT_CHR_SUSBDET_MASK) {
-		pbi->usb_is_present = PMIC_USB_PRESENT;
-		usb_present = 1;
-	} else {
-		pbi->usb_is_present = PMIC_USB_NOT_PRESENT;
-		pbi->usb_health = POWER_SUPPLY_HEALTH_UNKNOWN;
-	}
-
-	if (usb_present) {
-		if (r8 & PMIC_BATT_CHR_SUSBOVP_MASK) {
-			pbi->usb_health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
-			pmic_battery_log_event(BATT_EVENT_USBOVP_EXCPT);
-		} else {
-			pbi->usb_health = POWER_SUPPLY_HEALTH_GOOD;
-		}
-	}
-
-	chrg_val = ccval & PMIC_BATT_ADC_ACCCHRGVAL_MASK;
-
-	/* set batt_prev_charge_full to battery capacity the first time */
-	if (!pbi->is_dev_info_updated) {
-		if (pmic_scu_ipc_battery_property_get(&batt_prop)) {
-			dev_warn(pbi->dev, "%s(): ipc config cmd failed\n",
-								__func__);
-			return;
-		}
-		pbi->batt_prev_charge_full = batt_prop.capacity;
-	}
-
-	/* set batt_status */
-	if (batt_present && !batt_exception) {
-		if (r8 & PMIC_BATT_CHR_SCOMP_MASK) {
-			pbi->batt_status = POWER_SUPPLY_STATUS_FULL;
-			pbi->batt_prev_charge_full = chrg_val;
-		} else if (ccval & PMIC_BATT_ADC_ACCCHRG_MASK) {
-			pbi->batt_status = POWER_SUPPLY_STATUS_DISCHARGING;
-		} else {
-			pbi->batt_status = POWER_SUPPLY_STATUS_CHARGING;
-		}
-	}
-
-	/* set batt_charge_rate */
-	if (pbi->is_dev_info_updated && batt_present && !batt_exception) {
-		if (pbi->batt_status == POWER_SUPPLY_STATUS_DISCHARGING) {
-			if (pbi->batt_charge_now - chrg_val) {
-				pbi->batt_charge_rate = ((pbi->batt_charge_now -
-					chrg_val) * 1000 * 60) /
-					update_time_intrvl;
-			}
-		} else if (pbi->batt_status == POWER_SUPPLY_STATUS_CHARGING) {
-			if (chrg_val - pbi->batt_charge_now) {
-				pbi->batt_charge_rate = ((chrg_val -
-					pbi->batt_charge_now) * 1000 * 60) /
-					update_time_intrvl;
-			}
-		} else
-			pbi->batt_charge_rate = 0;
-	} else {
-		pbi->batt_charge_rate = -1;
-	}
-
-	/* batt_charge_now */
-	if (batt_present && !batt_exception)
-		pbi->batt_charge_now = chrg_val;
-	else
-		pbi->batt_charge_now = -1;
-
-	pbi->is_dev_info_updated = PMIC_BATT_DRV_INFO_UPDATED;
-}
-
-/**
- * pmic_usb_get_property - usb power source get property
- * @psy: usb power supply context
- * @psp: usb power source property
- * @val: usb power source property value
- * Context: can sleep
- *
- * PMIC usb power source property needs to be provided to power_supply
- * subsytem for it to provide the information to users.
- */
-static int pmic_usb_get_property(struct power_supply *psy,
-				enum power_supply_property psp,
-				union power_supply_propval *val)
-{
-	struct pmic_power_module_info *pbi = power_supply_get_drvdata(psy);
-
-	/* update pmic_power_module_info members */
-	pmic_battery_read_status(pbi);
-
-	switch (psp) {
-	case POWER_SUPPLY_PROP_PRESENT:
-		val->intval = pbi->usb_is_present;
-		break;
-	case POWER_SUPPLY_PROP_HEALTH:
-		val->intval = pbi->usb_health;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static inline unsigned long mAStouAh(unsigned long v)
-{
-	/* seconds to hours, mA to µA */
-	return (v * 1000) / 3600;
-}
-
-/**
- * pmic_battery_get_property - battery power source get property
- * @psy: battery power supply context
- * @psp: battery power source property
- * @val: battery power source property value
- * Context: can sleep
- *
- * PMIC battery power source property needs to be provided to power_supply
- * subsytem for it to provide the information to users.
- */
-static int pmic_battery_get_property(struct power_supply *psy,
-				enum power_supply_property psp,
-				union power_supply_propval *val)
-{
-	struct pmic_power_module_info *pbi = power_supply_get_drvdata(psy);
-
-	/* update pmic_power_module_info members */
-	pmic_battery_read_status(pbi);
-
-	switch (psp) {
-	case POWER_SUPPLY_PROP_STATUS:
-		val->intval = pbi->batt_status;
-		break;
-	case POWER_SUPPLY_PROP_HEALTH:
-		val->intval = pbi->batt_health;
-		break;
-	case POWER_SUPPLY_PROP_PRESENT:
-		val->intval = pbi->batt_is_present;
-		break;
-	case POWER_SUPPLY_PROP_CHARGE_NOW:
-		val->intval = mAStouAh(pbi->batt_charge_now);
-		break;
-	case POWER_SUPPLY_PROP_CHARGE_FULL:
-		val->intval = mAStouAh(pbi->batt_prev_charge_full);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/**
- * pmic_battery_monitor - monitor battery status
- * @work: work structure
- * Context: can sleep
- *
- * PMIC battery status needs to be monitored for any change
- * and information needs to be frequently updated.
- */
-static void pmic_battery_monitor(struct work_struct *work)
-{
-	struct pmic_power_module_info *pbi = container_of(work,
-			struct pmic_power_module_info, monitor_battery.work);
-
-	/* update pmic_power_module_info members */
-	pmic_battery_read_status(pbi);
-	queue_delayed_work(pbi->monitor_wqueue, &pbi->monitor_battery, HZ * 10);
-}
-
-/**
- * pmic_battery_set_charger - set battery charger
- * @pbi: device info structure
- * @chrg: charge mode to set battery charger in
- * Context: can sleep
- *
- * PMIC battery charger needs to be enabled based on the usb charge
- * capabilities connected to the platform.
- */
-static int pmic_battery_set_charger(struct pmic_power_module_info *pbi,
-						enum batt_charge_type chrg)
-{
-	int retval;
-
-	/* set usblmt bits and chrgcntl register bits appropriately */
-	switch (chrg) {
-	case BATT_USBOTG_500MA_CHARGE:
-		retval = pmic_scu_ipc_set_charger(PMIC_BATT_CHR_IPC_FCHRG_SUBID);
-		break;
-	case BATT_USBOTG_TRICKLE_CHARGE:
-		retval = pmic_scu_ipc_set_charger(PMIC_BATT_CHR_IPC_TCHRG_SUBID);
-		break;
-	default:
-		dev_warn(pbi->dev, "%s(): out of range usb charger "
-						"charge detected\n", __func__);
-		return -EINVAL;
-	}
-
-	if (retval) {
-		dev_warn(pbi->dev, "%s(): ipc pmic read failed\n",
-								__func__);
-		return retval;
-	}
-
-	return 0;
-}
-
-/**
- * pmic_battery_interrupt_handler - pmic battery interrupt handler
- * Context: interrupt context
- *
- * PMIC battery interrupt handler which will be called with either
- * battery full condition occurs or usb otg & battery connect
- * condition occurs.
- */
-static irqreturn_t pmic_battery_interrupt_handler(int id, void *dev)
-{
-	struct pmic_power_module_info *pbi = dev;
-
-	schedule_work(&pbi->handler);
-
-	return IRQ_HANDLED;
-}
-
-/**
- * pmic_battery_handle_intrpt - pmic battery service interrupt
- * @work: work structure
- * Context: can sleep
- *
- * PMIC battery needs to either update the battery status as full
- * if it detects battery full condition caused the interrupt or needs
- * to enable battery charger if it detects usb and battery detect
- * caused the source of interrupt.
- */
-static void pmic_battery_handle_intrpt(struct work_struct *work)
-{
-	struct pmic_power_module_info *pbi = container_of(work,
-				struct pmic_power_module_info, handler);
-	enum batt_charge_type chrg;
-	u8 r8;
-
-	if (intel_scu_ipc_ioread8(PMIC_BATT_CHR_SCHRGINT_ADDR, &r8)) {
-		dev_warn(pbi->dev, "%s(): ipc pmic read failed\n",
-								__func__);
-		return;
-	}
-	/* find the cause of the interrupt */
-	if (r8 & PMIC_BATT_CHR_SBATDET_MASK) {
-		pbi->batt_is_present = PMIC_BATT_PRESENT;
-	} else {
-		pbi->batt_is_present = PMIC_BATT_NOT_PRESENT;
-		pbi->batt_health = POWER_SUPPLY_HEALTH_UNKNOWN;
-		pbi->batt_status = POWER_SUPPLY_STATUS_UNKNOWN;
-		return;
-	}
-
-	if (r8 & PMIC_BATT_CHR_EXCPT_MASK) {
-		pbi->batt_health = POWER_SUPPLY_HEALTH_UNKNOWN;
-		pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
-		pbi->usb_health = POWER_SUPPLY_HEALTH_UNKNOWN;
-		pmic_battery_log_event(BATT_EVENT_EXCPT);
-		return;
-	} else {
-		pbi->batt_health = POWER_SUPPLY_HEALTH_GOOD;
-		pbi->usb_health = POWER_SUPPLY_HEALTH_GOOD;
-	}
-
-	if (r8 & PMIC_BATT_CHR_SCOMP_MASK) {
-		u32 ccval;
-		pbi->batt_status = POWER_SUPPLY_STATUS_FULL;
-
-		if (pmic_scu_ipc_battery_cc_read(&ccval)) {
-			dev_warn(pbi->dev, "%s(): ipc config cmd "
-							"failed\n", __func__);
-			return;
-		}
-		pbi->batt_prev_charge_full = ccval &
-						PMIC_BATT_ADC_ACCCHRGVAL_MASK;
-		return;
-	}
-
-	if (r8 & PMIC_BATT_CHR_SUSBDET_MASK) {
-		pbi->usb_is_present = PMIC_USB_PRESENT;
-	} else {
-		pbi->usb_is_present = PMIC_USB_NOT_PRESENT;
-		pbi->usb_health = POWER_SUPPLY_HEALTH_UNKNOWN;
-		return;
-	}
-
-	/* setup battery charging */
-
-#if 0
-	/* check usb otg power capability and set charger accordingly */
-	retval = langwell_udc_maxpower(&power);
-	if (retval) {
-		dev_warn(pbi->dev,
-		    "%s(): usb otg power query failed with error code %d\n",
-			__func__, retval);
-		return;
-	}
-
-	if (power >= 500)
-		chrg = BATT_USBOTG_500MA_CHARGE;
-	else
-#endif
-		chrg = BATT_USBOTG_TRICKLE_CHARGE;
-
-	/* enable battery charging */
-	if (pmic_battery_set_charger(pbi, chrg)) {
-		dev_warn(pbi->dev,
-			"%s(): failed to set up battery charging\n", __func__);
-		return;
-	}
-
-	dev_dbg(pbi->dev,
-		"pmic-battery: %s() - setting up battery charger successful\n",
-			__func__);
-}
-
-/*
- * Description of power supplies
- */
-static const struct power_supply_desc pmic_usb_desc = {
-	.name		= "pmic-usb",
-	.type		= POWER_SUPPLY_TYPE_USB,
-	.properties	= pmic_usb_props,
-	.num_properties	= ARRAY_SIZE(pmic_usb_props),
-	.get_property	= pmic_usb_get_property,
-};
-
-static const struct power_supply_desc pmic_batt_desc = {
-	.name		= "pmic-batt",
-	.type		= POWER_SUPPLY_TYPE_BATTERY,
-	.properties	= pmic_battery_props,
-	.num_properties	= ARRAY_SIZE(pmic_battery_props),
-	.get_property	= pmic_battery_get_property,
-};
-
-/**
- * pmic_battery_probe - pmic battery initialize
- * @irq: pmic battery device irq
- * @dev: pmic battery device structure
- * Context: can sleep
- *
- * PMIC battery initializes its internal data structue and other
- * infrastructure components for it to work as expected.
- */
-static int probe(int irq, struct device *dev)
-{
-	int retval = 0;
-	struct pmic_power_module_info *pbi;
-	struct power_supply_config psy_cfg = {};
-
-	dev_dbg(dev, "pmic-battery: found pmic battery device\n");
-
-	pbi = kzalloc(sizeof(*pbi), GFP_KERNEL);
-	if (!pbi) {
-		dev_err(dev, "%s(): memory allocation failed\n",
-								__func__);
-		return -ENOMEM;
-	}
-
-	pbi->dev = dev;
-	pbi->irq = irq;
-	dev_set_drvdata(dev, pbi);
-	psy_cfg.drv_data = pbi;
-
-	/* initialize all required framework before enabling interrupts */
-	INIT_WORK(&pbi->handler, pmic_battery_handle_intrpt);
-	INIT_DELAYED_WORK(&pbi->monitor_battery, pmic_battery_monitor);
-	pbi->monitor_wqueue = alloc_workqueue(dev_name(dev), WQ_MEM_RECLAIM, 0);
-	if (!pbi->monitor_wqueue) {
-		dev_err(dev, "%s(): wqueue init failed\n", __func__);
-		retval = -ESRCH;
-		goto wqueue_failed;
-	}
-
-	/* register interrupt */
-	retval = request_irq(pbi->irq, pmic_battery_interrupt_handler,
-							0, DRIVER_NAME, pbi);
-	if (retval) {
-		dev_err(dev, "%s(): cannot get IRQ\n", __func__);
-		goto requestirq_failed;
-	}
-
-	/* register pmic-batt with power supply subsystem */
-	pbi->batt = power_supply_register(dev, &pmic_usb_desc, &psy_cfg);
-	if (IS_ERR(pbi->batt)) {
-		dev_err(dev,
-			"%s(): failed to register pmic battery device with power supply subsystem\n",
-				__func__);
-		retval = PTR_ERR(pbi->batt);
-		goto power_reg_failed;
-	}
-
-	dev_dbg(dev, "pmic-battery: %s() - pmic battery device "
-		"registration with power supply subsystem successful\n",
-		__func__);
-
-	queue_delayed_work(pbi->monitor_wqueue, &pbi->monitor_battery, HZ * 1);
-
-	/* register pmic-usb with power supply subsystem */
-	pbi->usb = power_supply_register(dev, &pmic_batt_desc, &psy_cfg);
-	if (IS_ERR(pbi->usb)) {
-		dev_err(dev,
-			"%s(): failed to register pmic usb device with power supply subsystem\n",
-				__func__);
-		retval = PTR_ERR(pbi->usb);
-		goto power_reg_failed_1;
-	}
-
-	if (debug)
-		printk(KERN_INFO "pmic-battery: %s() - pmic usb device "
-			"registration with power supply subsystem successful\n",
-			__func__);
-
-	return retval;
-
-power_reg_failed_1:
-	power_supply_unregister(pbi->batt);
-power_reg_failed:
-	cancel_delayed_work_sync(&pbi->monitor_battery);
-requestirq_failed:
-	destroy_workqueue(pbi->monitor_wqueue);
-wqueue_failed:
-	kfree(pbi);
-
-	return retval;
-}
-
-static int platform_pmic_battery_probe(struct platform_device *pdev)
-{
-	return probe(pdev->id, &pdev->dev);
-}
-
-/**
- * pmic_battery_remove - pmic battery finalize
- * @dev: pmic battery device structure
- * Context: can sleep
- *
- * PMIC battery finalizes its internal data structue and other
- * infrastructure components that it initialized in
- * pmic_battery_probe.
- */
-
-static int platform_pmic_battery_remove(struct platform_device *pdev)
-{
-	struct pmic_power_module_info *pbi = platform_get_drvdata(pdev);
-
-	free_irq(pbi->irq, pbi);
-	cancel_delayed_work_sync(&pbi->monitor_battery);
-	destroy_workqueue(pbi->monitor_wqueue);
-
-	power_supply_unregister(pbi->usb);
-	power_supply_unregister(pbi->batt);
-
-	cancel_work_sync(&pbi->handler);
-	kfree(pbi);
-	return 0;
-}
-
-static struct platform_driver platform_pmic_battery_driver = {
-	.driver = {
-		.name = DRIVER_NAME,
-	},
-	.probe = platform_pmic_battery_probe,
-	.remove = platform_pmic_battery_remove,
-};
-
-module_platform_driver(platform_pmic_battery_driver);
-
-MODULE_AUTHOR("Nithish Mahalingam <nithish.mahalingam@intel.com>");
-MODULE_DESCRIPTION("Intel Moorestown PMIC Battery Driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/power/supply/max14656_charger_detector.c b/drivers/power/supply/max14656_charger_detector.c
new file mode 100644
index 000000000000..b91b1d2999dc
--- /dev/null
+++ b/drivers/power/supply/max14656_charger_detector.c
@@ -0,0 +1,327 @@
+/*
+ * Maxim MAX14656 / AL32 USB Charger Detector driver
+ *
+ * Copyright (C) 2014 LG Electronics, Inc
+ * Copyright (C) 2016 Alexander Kurz <akurz@blala.de>
+ *
+ * Components from Maxim AL32 Charger detection Driver for MX50 Yoshi Board
+ * Copyright (C) Amazon Technologies Inc. All rights reserved.
+ * Manish Lachwani (lachwani@lab126.com)
+ *
+ * This package is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/of_device.h>
+#include <linux/workqueue.h>
+#include <linux/power_supply.h>
+
+#define MAX14656_MANUFACTURER	"Maxim Integrated"
+#define MAX14656_NAME		"max14656"
+
+#define MAX14656_DEVICE_ID	0x00
+#define MAX14656_INTERRUPT_1	0x01
+#define MAX14656_INTERRUPT_2	0x02
+#define MAX14656_STATUS_1	0x03
+#define MAX14656_STATUS_2	0x04
+#define MAX14656_INTMASK_1	0x05
+#define MAX14656_INTMASK_2	0x06
+#define MAX14656_CONTROL_1	0x07
+#define MAX14656_CONTROL_2	0x08
+#define MAX14656_CONTROL_3	0x09
+
+#define DEVICE_VENDOR_MASK	0xf0
+#define DEVICE_REV_MASK		0x0f
+#define INT_EN_REG_MASK		BIT(4)
+#define CHG_TYPE_INT_MASK	BIT(0)
+#define STATUS1_VB_VALID_MASK	BIT(4)
+#define STATUS1_CHG_TYPE_MASK	0xf
+#define INT1_DCD_TIMEOUT_MASK	BIT(7)
+#define CONTROL1_DEFAULT	0x0d
+#define CONTROL1_INT_EN		BIT(4)
+#define CONTROL1_INT_ACTIVE_HIGH	BIT(5)
+#define CONTROL1_EDGE		BIT(7)
+#define CONTROL2_DEFAULT	0x8e
+#define CONTROL2_ADC_EN		BIT(0)
+#define CONTROL3_DEFAULT	0x8d
+
+enum max14656_chg_type {
+	MAX14656_NO_CHARGER	= 0,
+	MAX14656_SDP_CHARGER,
+	MAX14656_CDP_CHARGER,
+	MAX14656_DCP_CHARGER,
+	MAX14656_APPLE_500MA_CHARGER,
+	MAX14656_APPLE_1A_CHARGER,
+	MAX14656_APPLE_2A_CHARGER,
+	MAX14656_SPECIAL_500MA_CHARGER,
+	MAX14656_APPLE_12W,
+	MAX14656_CHARGER_LAST
+};
+
+static const struct max14656_chg_type_props {
+	enum power_supply_type type;
+} chg_type_props[] = {
+	{ POWER_SUPPLY_TYPE_UNKNOWN },
+	{ POWER_SUPPLY_TYPE_USB },
+	{ POWER_SUPPLY_TYPE_USB_CDP },
+	{ POWER_SUPPLY_TYPE_USB_DCP },
+	{ POWER_SUPPLY_TYPE_USB_DCP },
+	{ POWER_SUPPLY_TYPE_USB_DCP },
+	{ POWER_SUPPLY_TYPE_USB_DCP },
+	{ POWER_SUPPLY_TYPE_USB_DCP },
+	{ POWER_SUPPLY_TYPE_USB },
+};
+
+struct max14656_chip {
+	struct i2c_client	*client;
+	struct power_supply	*detect_psy;
+	struct power_supply_desc psy_desc;
+	struct delayed_work	irq_work;
+
+	int irq;
+	int online;
+};
+
+static int max14656_read_reg(struct i2c_client *client, int reg, u8 *val)
+{
+	s32 ret;
+
+	ret = i2c_smbus_read_byte_data(client, reg);
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"i2c read fail: can't read from %02x: %d\n",
+			reg, ret);
+		return ret;
+	}
+	*val = ret;
+	return 0;
+}
+
+static int max14656_write_reg(struct i2c_client *client, int reg, u8 val)
+{
+	s32 ret;
+
+	ret = i2c_smbus_write_byte_data(client, reg, val);
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"i2c write fail: can't write %02x to %02x: %d\n",
+			val, reg, ret);
+		return ret;
+	}
+	return 0;
+}
+
+static int max14656_read_block_reg(struct i2c_client *client, u8 reg,
+				  u8 length, u8 *val)
+{
+	int ret;
+
+	ret = i2c_smbus_read_i2c_block_data(client, reg, length, val);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed to block read reg 0x%x: %d\n",
+				reg, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+#define        REG_TOTAL_NUM   5
+static void max14656_irq_worker(struct work_struct *work)
+{
+	struct max14656_chip *chip =
+		container_of(work, struct max14656_chip, irq_work.work);
+
+	u8 buf[REG_TOTAL_NUM];
+	u8 chg_type;
+	int ret = 0;
+
+	ret = max14656_read_block_reg(chip->client, MAX14656_DEVICE_ID,
+				      REG_TOTAL_NUM, buf);
+
+	if ((buf[MAX14656_STATUS_1] & STATUS1_VB_VALID_MASK) &&
+		(buf[MAX14656_STATUS_1] & STATUS1_CHG_TYPE_MASK)) {
+		chg_type = buf[MAX14656_STATUS_1] & STATUS1_CHG_TYPE_MASK;
+		if (chg_type < MAX14656_CHARGER_LAST)
+			chip->psy_desc.type = chg_type_props[chg_type].type;
+		else
+			chip->psy_desc.type = POWER_SUPPLY_TYPE_UNKNOWN;
+		chip->online = 1;
+	} else {
+		chip->online = 0;
+		chip->psy_desc.type = POWER_SUPPLY_TYPE_UNKNOWN;
+	}
+
+	power_supply_changed(chip->detect_psy);
+}
+
+static irqreturn_t max14656_irq(int irq, void *dev_id)
+{
+	struct max14656_chip *chip = dev_id;
+
+	schedule_delayed_work(&chip->irq_work, msecs_to_jiffies(100));
+
+	return IRQ_HANDLED;
+}
+
+static int max14656_hw_init(struct max14656_chip *chip)
+{
+	uint8_t val = 0;
+	uint8_t rev;
+	struct i2c_client *client = chip->client;
+
+	if (max14656_read_reg(client, MAX14656_DEVICE_ID, &val))
+		return -ENODEV;
+
+	if ((val & DEVICE_VENDOR_MASK) != 0x20) {
+		dev_err(&client->dev, "wrong vendor ID %d\n",
+			((val & DEVICE_VENDOR_MASK) >> 4));
+		return -ENODEV;
+	}
+	rev = val & DEVICE_REV_MASK;
+
+	/* Turn on ADC_EN */
+	if (max14656_write_reg(client, MAX14656_CONTROL_2, CONTROL2_ADC_EN))
+		return -EINVAL;
+
+	/* turn on interrupts and low power mode */
+	if (max14656_write_reg(client, MAX14656_CONTROL_1,
+		CONTROL1_DEFAULT |
+		CONTROL1_INT_EN |
+		CONTROL1_INT_ACTIVE_HIGH |
+		CONTROL1_EDGE))
+		return -EINVAL;
+
+	if (max14656_write_reg(client, MAX14656_INTMASK_1, 0x3))
+		return -EINVAL;
+
+	if (max14656_write_reg(client, MAX14656_INTMASK_2, 0x1))
+		return -EINVAL;
+
+	dev_info(&client->dev, "detected revision %d\n", rev);
+	return 0;
+}
+
+static int max14656_get_property(struct power_supply *psy,
+			    enum power_supply_property psp,
+			    union power_supply_propval *val)
+{
+	struct max14656_chip *chip = power_supply_get_drvdata(psy);
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = chip->online;
+		break;
+	case POWER_SUPPLY_PROP_MODEL_NAME:
+		val->strval = MAX14656_NAME;
+		break;
+	case POWER_SUPPLY_PROP_MANUFACTURER:
+		val->strval = MAX14656_MANUFACTURER;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static enum power_supply_property max14656_battery_props[] = {
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_MODEL_NAME,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static int max14656_probe(struct i2c_client *client,
+			  const struct i2c_device_id *id)
+{
+	struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
+	struct device *dev = &client->dev;
+	struct power_supply_config psy_cfg = {};
+	struct max14656_chip *chip;
+	int irq = client->irq;
+	int ret = 0;
+
+	if (irq <= 0) {
+		dev_err(dev, "invalid irq number: %d\n", irq);
+		return -ENODEV;
+	}
+
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
+		dev_err(dev, "No support for SMBUS_BYTE_DATA\n");
+		return -ENODEV;
+	}
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	psy_cfg.drv_data = chip;
+	chip->client = client;
+	chip->online = 0;
+	chip->psy_desc.name = MAX14656_NAME;
+	chip->psy_desc.type = POWER_SUPPLY_TYPE_UNKNOWN;
+	chip->psy_desc.properties = max14656_battery_props;
+	chip->psy_desc.num_properties = ARRAY_SIZE(max14656_battery_props);
+	chip->psy_desc.get_property = max14656_get_property;
+	chip->irq = irq;
+
+	ret = max14656_hw_init(chip);
+	if (ret)
+		return -ENODEV;
+
+	INIT_DELAYED_WORK(&chip->irq_work, max14656_irq_worker);
+
+	ret = devm_request_irq(dev, chip->irq, max14656_irq,
+			       IRQF_TRIGGER_FALLING,
+			       MAX14656_NAME, chip);
+	if (ret) {
+		dev_err(dev, "request_irq %d failed\n", chip->irq);
+		return -EINVAL;
+	}
+	enable_irq_wake(chip->irq);
+
+	chip->detect_psy = devm_power_supply_register(dev,
+		       &chip->psy_desc, &psy_cfg);
+	if (IS_ERR(chip->detect_psy)) {
+		dev_err(dev, "power_supply_register failed\n");
+		return -EINVAL;
+	}
+
+	schedule_delayed_work(&chip->irq_work, msecs_to_jiffies(2000));
+
+	return 0;
+}
+
+static const struct i2c_device_id max14656_id[] = {
+	{ "max14656", 0 },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, max14656_id);
+
+static const struct of_device_id max14656_match_table[] = {
+	{ .compatible = "maxim,max14656", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, max14656_match_table);
+
+static struct i2c_driver max14656_i2c_driver = {
+	.driver = {
+		.name	= "max14656",
+		.of_match_table = max14656_match_table,
+	},
+	.probe		= max14656_probe,
+	.id_table	= max14656_id,
+};
+module_i2c_driver(max14656_i2c_driver);
+
+MODULE_DESCRIPTION("MAX14656 USB charger detector");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/supply/max8997_charger.c b/drivers/power/supply/max8997_charger.c
index 290ddc12b040..fa861003fece 100644
--- a/drivers/power/supply/max8997_charger.c
+++ b/drivers/power/supply/max8997_charger.c
@@ -148,10 +148,8 @@ static int max8997_battery_probe(struct platform_device *pdev)
 
 	charger = devm_kzalloc(&pdev->dev, sizeof(struct charger_data),
 				GFP_KERNEL);
-	if (charger == NULL) {
-		dev_err(&pdev->dev, "Cannot allocate memory.\n");
+	if (!charger)
 		return -ENOMEM;
-	}
 
 	platform_set_drvdata(pdev, charger);
 
@@ -161,7 +159,7 @@ static int max8997_battery_probe(struct platform_device *pdev)
 
 	psy_cfg.drv_data = charger;
 
-	charger->battery = power_supply_register(&pdev->dev,
+	charger->battery = devm_power_supply_register(&pdev->dev,
 						 &max8997_battery_desc,
 						 &psy_cfg);
 	if (IS_ERR(charger->battery)) {
@@ -172,14 +170,6 @@ static int max8997_battery_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int max8997_battery_remove(struct platform_device *pdev)
-{
-	struct charger_data *charger = platform_get_drvdata(pdev);
-
-	power_supply_unregister(charger->battery);
-	return 0;
-}
-
 static const struct platform_device_id max8997_battery_id[] = {
 	{ "max8997-battery", 0 },
 	{ }
@@ -191,7 +181,6 @@ static struct platform_driver max8997_battery_driver = {
 		.name = "max8997-battery",
 	},
 	.probe = max8997_battery_probe,
-	.remove = max8997_battery_remove,
 	.id_table = max8997_battery_id,
 };
 
diff --git a/drivers/power/supply/pcf50633-charger.c b/drivers/power/supply/pcf50633-charger.c
index d05597b4e40f..b3c1873ad84d 100644
--- a/drivers/power/supply/pcf50633-charger.c
+++ b/drivers/power/supply/pcf50633-charger.c
@@ -393,7 +393,6 @@ static int pcf50633_mbc_probe(struct platform_device *pdev)
 {
 	struct power_supply_config psy_cfg = {};
 	struct pcf50633_mbc *mbc;
-	int ret;
 	int i;
 	u8 mbcs1;
 
@@ -419,8 +418,7 @@ static int pcf50633_mbc_probe(struct platform_device *pdev)
 					     &psy_cfg);
 	if (IS_ERR(mbc->adapter)) {
 		dev_err(mbc->pcf->dev, "failed to register adapter\n");
-		ret = PTR_ERR(mbc->adapter);
-		return ret;
+		return PTR_ERR(mbc->adapter);
 	}
 
 	mbc->usb = power_supply_register(&pdev->dev, &pcf50633_mbc_usb_desc,
@@ -428,8 +426,7 @@ static int pcf50633_mbc_probe(struct platform_device *pdev)
 	if (IS_ERR(mbc->usb)) {
 		dev_err(mbc->pcf->dev, "failed to register usb\n");
 		power_supply_unregister(mbc->adapter);
-		ret = PTR_ERR(mbc->usb);
-		return ret;
+		return PTR_ERR(mbc->usb);
 	}
 
 	mbc->ac = power_supply_register(&pdev->dev, &pcf50633_mbc_ac_desc,
@@ -438,12 +435,10 @@ static int pcf50633_mbc_probe(struct platform_device *pdev)
 		dev_err(mbc->pcf->dev, "failed to register ac\n");
 		power_supply_unregister(mbc->adapter);
 		power_supply_unregister(mbc->usb);
-		ret = PTR_ERR(mbc->ac);
-		return ret;
+		return PTR_ERR(mbc->ac);
 	}
 
-	ret = sysfs_create_group(&pdev->dev.kobj, &mbc_attr_group);
-	if (ret)
+	if (sysfs_create_group(&pdev->dev.kobj, &mbc_attr_group))
 		dev_err(mbc->pcf->dev, "failed to create sysfs entries\n");
 
 	mbcs1 = pcf50633_reg_read(mbc->pcf, PCF50633_REG_MBCS1);
diff --git a/drivers/power/supply/qcom_smbb.c b/drivers/power/supply/qcom_smbb.c
index b5896ba2a602..f6a0d245731d 100644
--- a/drivers/power/supply/qcom_smbb.c
+++ b/drivers/power/supply/qcom_smbb.c
@@ -35,6 +35,7 @@
 #include <linux/regmap.h>
 #include <linux/slab.h>
 #include <linux/extcon.h>
+#include <linux/regulator/driver.h>
 
 #define SMBB_CHG_VMAX		0x040
 #define SMBB_CHG_VSAFE		0x041
@@ -72,6 +73,8 @@
 #define BTC_CTRL_HOT_EXT_N	BIT(0)
 
 #define SMBB_USB_IMAX		0x344
+#define SMBB_USB_OTG_CTL	0x348
+#define OTG_CTL_EN		BIT(0)
 #define SMBB_USB_ENUM_TIMER_STOP 0x34e
 #define ENUM_TIMER_STOP		BIT(0)
 #define SMBB_USB_SEC_ACCESS	0x3d0
@@ -125,6 +128,9 @@ struct smbb_charger {
 	struct power_supply *dc_psy;
 	struct power_supply *bat_psy;
 	struct regmap *regmap;
+
+	struct regulator_desc otg_rdesc;
+	struct regulator_dev *otg_reg;
 };
 
 static const unsigned int smbb_usb_extcon_cable[] = {
@@ -378,7 +384,7 @@ static irqreturn_t smbb_usb_valid_handler(int irq, void *_data)
 	struct smbb_charger *chg = _data;
 
 	smbb_set_line_flag(chg, irq, STATUS_USBIN_VALID);
-	extcon_set_cable_state_(chg->edev, EXTCON_USB,
+	extcon_set_state_sync(chg->edev, EXTCON_USB,
 				chg->status & STATUS_USBIN_VALID);
 	power_supply_changed(chg->usb_psy);
 
@@ -787,12 +793,56 @@ static const struct power_supply_desc dc_psy_desc = {
 	.property_is_writeable = smbb_charger_writable_property,
 };
 
+static int smbb_chg_otg_enable(struct regulator_dev *rdev)
+{
+	struct smbb_charger *chg = rdev_get_drvdata(rdev);
+	int rc;
+
+	rc = regmap_update_bits(chg->regmap, chg->addr + SMBB_USB_OTG_CTL,
+				OTG_CTL_EN, OTG_CTL_EN);
+	if (rc)
+		dev_err(chg->dev, "failed to update OTG_CTL\n");
+	return rc;
+}
+
+static int smbb_chg_otg_disable(struct regulator_dev *rdev)
+{
+	struct smbb_charger *chg = rdev_get_drvdata(rdev);
+	int rc;
+
+	rc = regmap_update_bits(chg->regmap, chg->addr + SMBB_USB_OTG_CTL,
+				OTG_CTL_EN, 0);
+	if (rc)
+		dev_err(chg->dev, "failed to update OTG_CTL\n");
+	return rc;
+}
+
+static int smbb_chg_otg_is_enabled(struct regulator_dev *rdev)
+{
+	struct smbb_charger *chg = rdev_get_drvdata(rdev);
+	unsigned int value = 0;
+	int rc;
+
+	rc = regmap_read(chg->regmap, chg->addr + SMBB_USB_OTG_CTL, &value);
+	if (rc)
+		dev_err(chg->dev, "failed to read OTG_CTL\n");
+
+	return !!(value & OTG_CTL_EN);
+}
+
+static const struct regulator_ops smbb_chg_otg_ops = {
+	.enable = smbb_chg_otg_enable,
+	.disable = smbb_chg_otg_disable,
+	.is_enabled = smbb_chg_otg_is_enabled,
+};
+
 static int smbb_charger_probe(struct platform_device *pdev)
 {
 	struct power_supply_config bat_cfg = {};
 	struct power_supply_config usb_cfg = {};
 	struct power_supply_config dc_cfg = {};
 	struct smbb_charger *chg;
+	struct regulator_config config = { };
 	int rc, i;
 
 	chg = devm_kzalloc(&pdev->dev, sizeof(*chg), GFP_KERNEL);
@@ -905,6 +955,26 @@ static int smbb_charger_probe(struct platform_device *pdev)
 		}
 	}
 
+	/*
+	 * otg regulator is used to control VBUS voltage direction
+	 * when USB switches between host and gadget mode
+	 */
+	chg->otg_rdesc.id = -1;
+	chg->otg_rdesc.name = "otg-vbus";
+	chg->otg_rdesc.ops = &smbb_chg_otg_ops;
+	chg->otg_rdesc.owner = THIS_MODULE;
+	chg->otg_rdesc.type = REGULATOR_VOLTAGE;
+	chg->otg_rdesc.supply_name = "usb-otg-in";
+	chg->otg_rdesc.of_match = "otg-vbus";
+
+	config.dev = &pdev->dev;
+	config.driver_data = chg;
+
+	chg->otg_reg = devm_regulator_register(&pdev->dev, &chg->otg_rdesc,
+					       &config);
+	if (IS_ERR(chg->otg_reg))
+		return PTR_ERR(chg->otg_reg);
+
 	chg->jeita_ext_temp = of_property_read_bool(pdev->dev.of_node,
 			"qcom,jeita-extended-temp-range");
 
diff --git a/drivers/power/supply/sbs-charger.c b/drivers/power/supply/sbs-charger.c
new file mode 100644
index 000000000000..353765a5f44c
--- /dev/null
+++ b/drivers/power/supply/sbs-charger.c
@@ -0,0 +1,274 @@
+/*
+ * Copyright (c) 2016, Prodys S.L.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This adds support for sbs-charger compilant chips as defined here:
+ * http://sbs-forum.org/specs/sbc110.pdf
+ *
+ * Implemetation based on sbs-battery.c
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/power_supply.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/gpio.h>
+#include <linux/regmap.h>
+#include <linux/of_gpio.h>
+#include <linux/bitops.h>
+
+#define SBS_CHARGER_REG_SPEC_INFO		0x11
+#define SBS_CHARGER_REG_STATUS			0x13
+#define SBS_CHARGER_REG_ALARM_WARNING		0x16
+
+#define SBS_CHARGER_STATUS_CHARGE_INHIBITED	BIT(1)
+#define SBS_CHARGER_STATUS_RES_COLD		BIT(9)
+#define SBS_CHARGER_STATUS_RES_HOT		BIT(10)
+#define SBS_CHARGER_STATUS_BATTERY_PRESENT	BIT(14)
+#define SBS_CHARGER_STATUS_AC_PRESENT		BIT(15)
+
+#define SBS_CHARGER_POLL_TIME			500
+
+struct sbs_info {
+	struct i2c_client		*client;
+	struct power_supply		*power_supply;
+	struct regmap			*regmap;
+	struct delayed_work		work;
+	unsigned int			last_state;
+};
+
+static int sbs_get_property(struct power_supply *psy,
+			    enum power_supply_property psp,
+			    union power_supply_propval *val)
+{
+	struct sbs_info *chip = power_supply_get_drvdata(psy);
+	unsigned int reg;
+
+	reg = chip->last_state;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_PRESENT:
+		val->intval = !!(reg & SBS_CHARGER_STATUS_BATTERY_PRESENT);
+		break;
+
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = !!(reg & SBS_CHARGER_STATUS_AC_PRESENT);
+		break;
+
+	case POWER_SUPPLY_PROP_STATUS:
+		val->intval = POWER_SUPPLY_STATUS_UNKNOWN;
+
+		if (!(reg & SBS_CHARGER_STATUS_BATTERY_PRESENT))
+			val->intval = POWER_SUPPLY_STATUS_NOT_CHARGING;
+		else if (reg & SBS_CHARGER_STATUS_AC_PRESENT &&
+			 !(reg & SBS_CHARGER_STATUS_CHARGE_INHIBITED))
+			val->intval = POWER_SUPPLY_STATUS_CHARGING;
+		else
+			val->intval = POWER_SUPPLY_STATUS_DISCHARGING;
+
+		break;
+
+	case POWER_SUPPLY_PROP_HEALTH:
+		if (reg & SBS_CHARGER_STATUS_RES_COLD)
+			val->intval = POWER_SUPPLY_HEALTH_COLD;
+		if (reg & SBS_CHARGER_STATUS_RES_HOT)
+			val->intval = POWER_SUPPLY_HEALTH_OVERHEAT;
+		else
+			val->intval = POWER_SUPPLY_HEALTH_GOOD;
+
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int sbs_check_state(struct sbs_info *chip)
+{
+	unsigned int reg;
+	int ret;
+
+	ret = regmap_read(chip->regmap, SBS_CHARGER_REG_STATUS, &reg);
+	if (!ret && reg != chip->last_state) {
+		chip->last_state = reg;
+		power_supply_changed(chip->power_supply);
+		return 1;
+	}
+
+	return 0;
+}
+
+static void sbs_delayed_work(struct work_struct *work)
+{
+	struct sbs_info *chip = container_of(work, struct sbs_info, work.work);
+
+	sbs_check_state(chip);
+
+	schedule_delayed_work(&chip->work,
+			      msecs_to_jiffies(SBS_CHARGER_POLL_TIME));
+}
+
+static irqreturn_t sbs_irq_thread(int irq, void *data)
+{
+	struct sbs_info *chip = data;
+	int ret;
+
+	ret = sbs_check_state(chip);
+
+	return ret ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static enum power_supply_property sbs_properties[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_HEALTH,
+};
+
+static bool sbs_readable_reg(struct device *dev, unsigned int reg)
+{
+	if (reg < SBS_CHARGER_REG_SPEC_INFO)
+		return false;
+	else
+		return true;
+}
+
+static bool sbs_volatile_reg(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case SBS_CHARGER_REG_STATUS:
+		return true;
+	}
+
+	return false;
+}
+
+static const struct regmap_config sbs_regmap = {
+	.reg_bits	= 8,
+	.val_bits	= 16,
+	.max_register	= SBS_CHARGER_REG_ALARM_WARNING,
+	.readable_reg	= sbs_readable_reg,
+	.volatile_reg	= sbs_volatile_reg,
+	.val_format_endian = REGMAP_ENDIAN_LITTLE, /* since based on SMBus */
+};
+
+static const struct power_supply_desc sbs_desc = {
+	.name = "sbs-charger",
+	.type = POWER_SUPPLY_TYPE_MAINS,
+	.properties = sbs_properties,
+	.num_properties = ARRAY_SIZE(sbs_properties),
+	.get_property = sbs_get_property,
+};
+
+static int sbs_probe(struct i2c_client *client,
+		     const struct i2c_device_id *id)
+{
+	struct power_supply_config psy_cfg = {};
+	struct sbs_info *chip;
+	int ret, val;
+
+	chip = devm_kzalloc(&client->dev, sizeof(struct sbs_info), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	chip->client = client;
+	psy_cfg.of_node = client->dev.of_node;
+	psy_cfg.drv_data = chip;
+
+	i2c_set_clientdata(client, chip);
+
+	chip->regmap = devm_regmap_init_i2c(client, &sbs_regmap);
+	if (IS_ERR(chip->regmap))
+		return PTR_ERR(chip->regmap);
+
+	/*
+	 * Before we register, we need to make sure we can actually talk
+	 * to the battery.
+	 */
+	ret = regmap_read(chip->regmap, SBS_CHARGER_REG_STATUS, &val);
+	if (ret) {
+		dev_err(&client->dev, "Failed to get device status\n");
+		return ret;
+	}
+	chip->last_state = val;
+
+	chip->power_supply = devm_power_supply_register(&client->dev, &sbs_desc,
+							&psy_cfg);
+	if (IS_ERR(chip->power_supply)) {
+		dev_err(&client->dev, "Failed to register power supply\n");
+		return PTR_ERR(chip->power_supply);
+	}
+
+	/*
+	 * The sbs-charger spec doesn't impose the use of an interrupt. So in
+	 * the case it wasn't provided we use polling in order get the charger's
+	 * status.
+	 */
+	if (client->irq) {
+		ret = devm_request_threaded_irq(&client->dev, client->irq,
+					NULL, sbs_irq_thread,
+					IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+					dev_name(&client->dev), chip);
+		if (ret) {
+			dev_err(&client->dev, "Failed to request irq, %d\n", ret);
+			return ret;
+		}
+	} else {
+		INIT_DELAYED_WORK(&chip->work, sbs_delayed_work);
+		schedule_delayed_work(&chip->work,
+				      msecs_to_jiffies(SBS_CHARGER_POLL_TIME));
+	}
+
+	dev_info(&client->dev,
+		 "%s: smart charger device registered\n", client->name);
+
+	return 0;
+}
+
+static int sbs_remove(struct i2c_client *client)
+{
+	struct sbs_info *chip = i2c_get_clientdata(client);
+
+	cancel_delayed_work_sync(&chip->work);
+
+	return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id sbs_dt_ids[] = {
+	{ .compatible = "sbs,sbs-charger" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, sbs_dt_ids);
+#endif
+
+static const struct i2c_device_id sbs_id[] = {
+	{ "sbs-charger", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, sbs_id);
+
+static struct i2c_driver sbs_driver = {
+	.probe		= sbs_probe,
+	.remove		= sbs_remove,
+	.id_table	= sbs_id,
+	.driver = {
+		.name	= "sbs-charger",
+		.of_match_table = of_match_ptr(sbs_dt_ids),
+	},
+};
+module_i2c_driver(sbs_driver);
+
+MODULE_AUTHOR("Nicolas Saenz Julienne <nicolassaenzj@gmail.com>");
+MODULE_DESCRIPTION("SBS smart charger driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/supply/tps65217_charger.c b/drivers/power/supply/tps65217_charger.c
index 9fd019f9b88c..29b61e81b385 100644
--- a/drivers/power/supply/tps65217_charger.c
+++ b/drivers/power/supply/tps65217_charger.c
@@ -35,22 +35,22 @@
 #include <linux/mfd/core.h>
 #include <linux/mfd/tps65217.h>
 
+#define CHARGER_STATUS_PRESENT	(TPS65217_STATUS_ACPWR | TPS65217_STATUS_USBPWR)
+#define NUM_CHARGER_IRQS	2
 #define POLL_INTERVAL		(HZ * 2)
 
 struct tps65217_charger {
 	struct tps65217 *tps;
 	struct device *dev;
-	struct power_supply *ac;
+	struct power_supply *psy;
 
-	int	ac_online;
-	int	prev_ac_online;
+	int	online;
+	int	prev_online;
 
 	struct task_struct	*poll_task;
-
-	int	irq;
 };
 
-static enum power_supply_property tps65217_ac_props[] = {
+static enum power_supply_property tps65217_charger_props[] = {
 	POWER_SUPPLY_PROP_ONLINE,
 };
 
@@ -95,7 +95,7 @@ static int tps65217_enable_charging(struct tps65217_charger *charger)
 	int ret;
 
 	/* charger already enabled */
-	if (charger->ac_online)
+	if (charger->online)
 		return 0;
 
 	dev_dbg(charger->dev, "%s: enable charging\n", __func__);
@@ -110,19 +110,19 @@ static int tps65217_enable_charging(struct tps65217_charger *charger)
 		return ret;
 	}
 
-	charger->ac_online = 1;
+	charger->online = 1;
 
 	return 0;
 }
 
-static int tps65217_ac_get_property(struct power_supply *psy,
-			enum power_supply_property psp,
-			union power_supply_propval *val)
+static int tps65217_charger_get_property(struct power_supply *psy,
+					 enum power_supply_property psp,
+					 union power_supply_propval *val)
 {
 	struct tps65217_charger *charger = power_supply_get_drvdata(psy);
 
 	if (psp == POWER_SUPPLY_PROP_ONLINE) {
-		val->intval = charger->ac_online;
+		val->intval = charger->online;
 		return 0;
 	}
 	return -EINVAL;
@@ -133,7 +133,7 @@ static irqreturn_t tps65217_charger_irq(int irq, void *dev)
 	int ret, val;
 	struct tps65217_charger *charger = dev;
 
-	charger->prev_ac_online = charger->ac_online;
+	charger->prev_online = charger->online;
 
 	ret = tps65217_reg_read(charger->tps, TPS65217_REG_STATUS, &val);
 	if (ret < 0) {
@@ -144,8 +144,8 @@ static irqreturn_t tps65217_charger_irq(int irq, void *dev)
 
 	dev_dbg(charger->dev, "%s: 0x%x\n", __func__, val);
 
-	/* check for AC status bit */
-	if (val & TPS65217_STATUS_ACPWR) {
+	/* check for charger status bit */
+	if (val & CHARGER_STATUS_PRESENT) {
 		ret = tps65217_enable_charging(charger);
 		if (ret) {
 			dev_err(charger->dev,
@@ -153,11 +153,11 @@ static irqreturn_t tps65217_charger_irq(int irq, void *dev)
 			return IRQ_HANDLED;
 		}
 	} else {
-		charger->ac_online = 0;
+		charger->online = 0;
 	}
 
-	if (charger->prev_ac_online != charger->ac_online)
-		power_supply_changed(charger->ac);
+	if (charger->prev_online != charger->online)
+		power_supply_changed(charger->psy);
 
 	ret = tps65217_reg_read(charger->tps, TPS65217_REG_CHGCONFIG0, &val);
 	if (ret < 0) {
@@ -188,11 +188,11 @@ static int tps65217_charger_poll_task(void *data)
 }
 
 static const struct power_supply_desc tps65217_charger_desc = {
-	.name			= "tps65217-ac",
+	.name			= "tps65217-charger",
 	.type			= POWER_SUPPLY_TYPE_MAINS,
-	.get_property		= tps65217_ac_get_property,
-	.properties		= tps65217_ac_props,
-	.num_properties		= ARRAY_SIZE(tps65217_ac_props),
+	.get_property		= tps65217_charger_get_property,
+	.properties		= tps65217_charger_props,
+	.num_properties		= ARRAY_SIZE(tps65217_charger_props),
 };
 
 static int tps65217_charger_probe(struct platform_device *pdev)
@@ -200,8 +200,10 @@ static int tps65217_charger_probe(struct platform_device *pdev)
 	struct tps65217 *tps = dev_get_drvdata(pdev->dev.parent);
 	struct tps65217_charger *charger;
 	struct power_supply_config cfg = {};
-	int irq;
+	struct task_struct *poll_task;
+	int irq[NUM_CHARGER_IRQS];
 	int ret;
+	int i;
 
 	dev_dbg(&pdev->dev, "%s\n", __func__);
 
@@ -216,18 +218,16 @@ static int tps65217_charger_probe(struct platform_device *pdev)
 	cfg.of_node = pdev->dev.of_node;
 	cfg.drv_data = charger;
 
-	charger->ac = devm_power_supply_register(&pdev->dev,
-						 &tps65217_charger_desc,
-						 &cfg);
-	if (IS_ERR(charger->ac)) {
+	charger->psy = devm_power_supply_register(&pdev->dev,
+						  &tps65217_charger_desc,
+						  &cfg);
+	if (IS_ERR(charger->psy)) {
 		dev_err(&pdev->dev, "failed: power supply register\n");
-		return PTR_ERR(charger->ac);
+		return PTR_ERR(charger->psy);
 	}
 
-	irq = platform_get_irq_byname(pdev, "AC");
-	if (irq < 0)
-		irq = -ENXIO;
-	charger->irq = irq;
+	irq[0] = platform_get_irq_byname(pdev, "USB");
+	irq[1] = platform_get_irq_byname(pdev, "AC");
 
 	ret = tps65217_config_charger(charger);
 	if (ret < 0) {
@@ -235,29 +235,36 @@ static int tps65217_charger_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	if (irq != -ENXIO) {
-		ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
+	/* Create a polling thread if an interrupt is invalid */
+	if (irq[0] < 0 || irq[1] < 0) {
+		poll_task = kthread_run(tps65217_charger_poll_task,
+					charger, "ktps65217charger");
+		if (IS_ERR(poll_task)) {
+			ret = PTR_ERR(poll_task);
+			dev_err(charger->dev,
+				"Unable to run kthread err %d\n", ret);
+			return ret;
+		}
+
+		charger->poll_task = poll_task;
+		return 0;
+	}
+
+	/* Create IRQ threads for charger interrupts */
+	for (i = 0; i < NUM_CHARGER_IRQS; i++) {
+		ret = devm_request_threaded_irq(&pdev->dev, irq[i], NULL,
 						tps65217_charger_irq,
 						0, "tps65217-charger",
 						charger);
 		if (ret) {
 			dev_err(charger->dev,
-				"Unable to register irq %d err %d\n", irq,
+				"Unable to register irq %d err %d\n", irq[i],
 				ret);
 			return ret;
 		}
 
 		/* Check current state */
-		tps65217_charger_irq(irq, charger);
-	} else {
-		charger->poll_task = kthread_run(tps65217_charger_poll_task,
-						charger, "ktps65217charger");
-		if (IS_ERR(charger->poll_task)) {
-			ret = PTR_ERR(charger->poll_task);
-			dev_err(charger->dev,
-				"Unable to run kthread err %d\n", ret);
-			return ret;
-		}
+		tps65217_charger_irq(-1, charger);
 	}
 
 	return 0;
@@ -267,7 +274,7 @@ static int tps65217_charger_remove(struct platform_device *pdev)
 {
 	struct tps65217_charger *charger = platform_get_drvdata(pdev);
 
-	if (charger->irq == -ENXIO)
+	if (charger->poll_task)
 		kthread_stop(charger->poll_task);
 
 	return 0;
diff --git a/drivers/power/supply/wm97xx_battery.c b/drivers/power/supply/wm97xx_battery.c
index e3edb31ac880..bd4f66651513 100644
--- a/drivers/power/supply/wm97xx_battery.c
+++ b/drivers/power/supply/wm97xx_battery.c
@@ -175,11 +175,6 @@ static int wm97xx_bat_probe(struct platform_device *dev)
 	if (dev->id != -1)
 		return -EINVAL;
 
-	if (!pdata) {
-		dev_err(&dev->dev, "No platform_data supplied\n");
-		return -EINVAL;
-	}
-
 	if (gpio_is_valid(pdata->charge_gpio)) {
 		ret = gpio_request(pdata->charge_gpio, "BATT CHRG");
 		if (ret)
diff --git a/drivers/regulator/88pm800.c b/drivers/regulator/88pm800.c
index a62a89674fb5..89bbd6e8bad1 100644
--- a/drivers/regulator/88pm800.c
+++ b/drivers/regulator/88pm800.c
@@ -180,7 +180,7 @@ static int pm800_get_current_limit(struct regulator_dev *rdev)
 	return info->max_ua;
 }
 
-static struct regulator_ops pm800_volt_range_ops = {
+static const struct regulator_ops pm800_volt_range_ops = {
 	.list_voltage		= regulator_list_voltage_linear_range,
 	.map_voltage		= regulator_map_voltage_linear_range,
 	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
@@ -191,7 +191,7 @@ static struct regulator_ops pm800_volt_range_ops = {
 	.get_current_limit	= pm800_get_current_limit,
 };
 
-static struct regulator_ops pm800_volt_table_ops = {
+static const struct regulator_ops pm800_volt_table_ops = {
 	.list_voltage		= regulator_list_voltage_table,
 	.map_voltage		= regulator_map_voltage_iterate,
 	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
diff --git a/drivers/regulator/88pm8607.c b/drivers/regulator/88pm8607.c
index b100a63ff3b3..fd86446e499b 100644
--- a/drivers/regulator/88pm8607.c
+++ b/drivers/regulator/88pm8607.c
@@ -220,7 +220,7 @@ static int pm8607_list_voltage(struct regulator_dev *rdev, unsigned index)
 	return ret;
 }
 
-static struct regulator_ops pm8607_regulator_ops = {
+static const struct regulator_ops pm8607_regulator_ops = {
 	.list_voltage	= pm8607_list_voltage,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
@@ -229,7 +229,7 @@ static struct regulator_ops pm8607_regulator_ops = {
 	.is_enabled = regulator_is_enabled_regmap,
 };
 
-static struct regulator_ops pm8606_preg_ops = {
+static const struct regulator_ops pm8606_preg_ops = {
 	.enable		= regulator_enable_regmap,
 	.disable	= regulator_disable_regmap,
 	.is_enabled	= regulator_is_enabled_regmap,
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 936f7ccc9736..be06eb29c681 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -163,6 +163,13 @@ config REGULATOR_BCM590XX
 	  BCM590xx PMUs. This will enable support for the software
 	  controllable LDO/Switching regulators.
 
+config REGULATOR_CPCAP
+	tristate "Motorola CPCAP regulator"
+	depends on MFD_CPCAP
+	help
+	  Say y here for CPCAP regulator found on some Motorola phones
+	  and tablets such as Droid 4.
+
 config REGULATOR_DA903X
 	tristate "Dialog Semiconductor DA9030/DA9034 regulators"
 	depends on PMIC_DA903X
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 14294692beb9..ef7725e2592a 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_REGULATOR_USERSPACE_CONSUMER) += userspace-consumer.o
 
 obj-$(CONFIG_REGULATOR_88PM800) += 88pm800.o
 obj-$(CONFIG_REGULATOR_88PM8607) += 88pm8607.o
+obj-$(CONFIG_REGULATOR_CPCAP) += cpcap-regulator.o
 obj-$(CONFIG_REGULATOR_AAT2870) += aat2870-regulator.o
 obj-$(CONFIG_REGULATOR_AB3100) += ab3100.o
 obj-$(CONFIG_REGULATOR_AB8500)	+= ab8500-ext.o ab8500.o
diff --git a/drivers/regulator/aat2870-regulator.c b/drivers/regulator/aat2870-regulator.c
index 9dfabda8f478..afc5b5900181 100644
--- a/drivers/regulator/aat2870-regulator.c
+++ b/drivers/regulator/aat2870-regulator.c
@@ -97,7 +97,7 @@ static int aat2870_ldo_is_enabled(struct regulator_dev *rdev)
 	return val & ri->enable_mask ? 1 : 0;
 }
 
-static struct regulator_ops aat2870_ldo_ops = {
+static const struct regulator_ops aat2870_ldo_ops = {
 	.list_voltage = regulator_list_voltage_table,
 	.map_voltage = regulator_map_voltage_ascend,
 	.set_voltage_sel = aat2870_ldo_set_voltage_sel,
diff --git a/drivers/regulator/act8945a-regulator.c b/drivers/regulator/act8945a-regulator.c
index 441864b9fece..43fda8b4455a 100644
--- a/drivers/regulator/act8945a-regulator.c
+++ b/drivers/regulator/act8945a-regulator.c
@@ -69,7 +69,7 @@ static const struct regulator_linear_range act8945a_voltage_ranges[] = {
 	REGULATOR_LINEAR_RANGE(2400000, 48, 63, 100000),
 };
 
-static struct regulator_ops act8945a_ops = {
+static const struct regulator_ops act8945a_ops = {
 	.list_voltage		= regulator_list_voltage_linear_range,
 	.map_voltage		= regulator_map_voltage_linear_range,
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
diff --git a/drivers/regulator/ad5398.c b/drivers/regulator/ad5398.c
index 8b0f788a9bbb..11c1f880b7bb 100644
--- a/drivers/regulator/ad5398.c
+++ b/drivers/regulator/ad5398.c
@@ -181,7 +181,7 @@ static int ad5398_disable(struct regulator_dev *rdev)
 	return ret;
 }
 
-static struct regulator_ops ad5398_ops = {
+static const struct regulator_ops ad5398_ops = {
 	.get_current_limit = ad5398_get_current_limit,
 	.set_current_limit = ad5398_set_current_limit,
 	.enable = ad5398_enable,
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 3a6d0290c54c..b041f277a38b 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -301,7 +301,19 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 			return -EINVAL;
 		}
 	} else {
+		u32 enable_bit;
+
 		rdesc->ops = &anatop_rops;
+
+		if (!of_property_read_u32(np, "anatop-enable-bit",
+					  &enable_bit)) {
+			anatop_rops.enable  = regulator_enable_regmap;
+			anatop_rops.disable = regulator_disable_regmap;
+			anatop_rops.is_enabled = regulator_is_enabled_regmap;
+
+			rdesc->enable_reg = sreg->control_reg;
+			rdesc->enable_mask = BIT(enable_bit);
+		}
 	}
 
 	/* register regulator */
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index 302b57cb89c6..e76d094591e7 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -109,7 +109,7 @@ static int arizona_ldo1_hc_get_voltage_sel(struct regulator_dev *rdev)
 	return (val & ARIZONA_LDO1_VSEL_MASK) >> ARIZONA_LDO1_VSEL_SHIFT;
 }
 
-static struct regulator_ops arizona_ldo1_hc_ops = {
+static const struct regulator_ops arizona_ldo1_hc_ops = {
 	.list_voltage = arizona_ldo1_hc_list_voltage,
 	.map_voltage = arizona_ldo1_hc_map_voltage,
 	.get_voltage_sel = arizona_ldo1_hc_get_voltage_sel,
@@ -135,7 +135,7 @@ static const struct regulator_desc arizona_ldo1_hc = {
 	.owner = THIS_MODULE,
 };
 
-static struct regulator_ops arizona_ldo1_ops = {
+static const struct regulator_ops arizona_ldo1_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 	.map_voltage = regulator_map_voltage_linear,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
diff --git a/drivers/regulator/arizona-micsupp.c b/drivers/regulator/arizona-micsupp.c
index fcb98dbda837..22bd71407622 100644
--- a/drivers/regulator/arizona-micsupp.c
+++ b/drivers/regulator/arizona-micsupp.c
@@ -45,6 +45,7 @@ static void arizona_micsupp_check_cp(struct work_struct *work)
 	struct arizona_micsupp *micsupp =
 		container_of(work, struct arizona_micsupp, check_cp_work);
 	struct snd_soc_dapm_context *dapm = micsupp->arizona->dapm;
+	struct snd_soc_component *component = snd_soc_dapm_to_component(dapm);
 	struct arizona *arizona = micsupp->arizona;
 	struct regmap *regmap = arizona->regmap;
 	unsigned int reg;
@@ -59,9 +60,10 @@ static void arizona_micsupp_check_cp(struct work_struct *work)
 	if (dapm) {
 		if ((reg & (ARIZONA_CPMIC_ENA | ARIZONA_CPMIC_BYPASS)) ==
 		    ARIZONA_CPMIC_ENA)
-			snd_soc_dapm_force_enable_pin(dapm, "MICSUPP");
+			snd_soc_component_force_enable_pin(component,
+							   "MICSUPP");
 		else
-			snd_soc_dapm_disable_pin(dapm, "MICSUPP");
+			snd_soc_component_disable_pin(component, "MICSUPP");
 
 		snd_soc_dapm_sync(dapm);
 	}
@@ -104,7 +106,7 @@ static int arizona_micsupp_set_bypass(struct regulator_dev *rdev, bool ena)
 	return ret;
 }
 
-static struct regulator_ops arizona_micsupp_ops = {
+static const struct regulator_ops arizona_micsupp_ops = {
 	.enable = arizona_micsupp_enable,
 	.disable = arizona_micsupp_disable,
 	.is_enabled = regulator_is_enabled_regmap,
diff --git a/drivers/regulator/as3711-regulator.c b/drivers/regulator/as3711-regulator.c
index c0e93b1332f7..874d415d6b4f 100644
--- a/drivers/regulator/as3711-regulator.c
+++ b/drivers/regulator/as3711-regulator.c
@@ -82,7 +82,7 @@ static unsigned int as3711_get_mode_sd(struct regulator_dev *rdev)
 	return -EINVAL;
 }
 
-static struct regulator_ops as3711_sd_ops = {
+static const struct regulator_ops as3711_sd_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -94,7 +94,7 @@ static struct regulator_ops as3711_sd_ops = {
 	.set_mode		= as3711_set_mode_sd,
 };
 
-static struct regulator_ops as3711_aldo_ops = {
+static const struct regulator_ops as3711_aldo_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -104,7 +104,7 @@ static struct regulator_ops as3711_aldo_ops = {
 	.map_voltage		= regulator_map_voltage_linear_range,
 };
 
-static struct regulator_ops as3711_dldo_ops = {
+static const struct regulator_ops as3711_dldo_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index e6a512ebeae2..0b9d4e3e52c7 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -128,11 +128,11 @@
 		.ops		= &axp20x_ops_range,				\
 	}
 
-static struct regulator_ops axp20x_ops_fixed = {
+static const struct regulator_ops axp20x_ops_fixed = {
 	.list_voltage		= regulator_list_voltage_linear,
 };
 
-static struct regulator_ops axp20x_ops_range = {
+static const struct regulator_ops axp20x_ops_range = {
 	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
 	.list_voltage		= regulator_list_voltage_linear_range,
@@ -141,7 +141,7 @@ static struct regulator_ops axp20x_ops_range = {
 	.is_enabled		= regulator_is_enabled_regmap,
 };
 
-static struct regulator_ops axp20x_ops = {
+static const struct regulator_ops axp20x_ops = {
 	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
 	.list_voltage		= regulator_list_voltage_linear,
@@ -150,7 +150,7 @@ static struct regulator_ops axp20x_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 };
 
-static struct regulator_ops axp20x_ops_sw = {
+static const struct regulator_ops axp20x_ops_sw = {
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -272,7 +272,7 @@ static const struct regulator_desc axp806_regulators[] = {
 			64, AXP806_DCDCD_V_CTRL, 0x3f, AXP806_PWR_OUT_CTRL1,
 			BIT(3)),
 	AXP_DESC(AXP806, DCDCE, "dcdce", "vine", 1100, 3400, 100,
-		 AXP806_DCDCB_V_CTRL, 0x1f, AXP806_PWR_OUT_CTRL1, BIT(4)),
+		 AXP806_DCDCE_V_CTRL, 0x1f, AXP806_PWR_OUT_CTRL1, BIT(4)),
 	AXP_DESC(AXP806, ALDO1, "aldo1", "aldoin", 700, 3300, 100,
 		 AXP806_ALDO1_V_CTRL, 0x1f, AXP806_PWR_OUT_CTRL1, BIT(5)),
 	AXP_DESC(AXP806, ALDO2, "aldo2", "aldoin", 700, 3400, 100,
diff --git a/drivers/regulator/bcm590xx-regulator.c b/drivers/regulator/bcm590xx-regulator.c
index 76b01835dcb4..9dd715407b39 100644
--- a/drivers/regulator/bcm590xx-regulator.c
+++ b/drivers/regulator/bcm590xx-regulator.c
@@ -250,7 +250,7 @@ static int bcm590xx_get_enable_register(int id)
 	return reg;
 }
 
-static struct regulator_ops bcm590xx_ops_ldo = {
+static const struct regulator_ops bcm590xx_ops_ldo = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -260,7 +260,7 @@ static struct regulator_ops bcm590xx_ops_ldo = {
 	.map_voltage		= regulator_map_voltage_iterate,
 };
 
-static struct regulator_ops bcm590xx_ops_dcdc = {
+static const struct regulator_ops bcm590xx_ops_dcdc = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -270,7 +270,7 @@ static struct regulator_ops bcm590xx_ops_dcdc = {
 	.map_voltage		= regulator_map_voltage_linear_range,
 };
 
-static struct regulator_ops bcm590xx_ops_vbus = {
+static const struct regulator_ops bcm590xx_ops_vbus = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 04baac9a165b..53d4fc70dbd0 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1455,12 +1455,14 @@ static struct regulator_dev *regulator_lookup_by_name(const char *name)
  * lookup could succeed in the future.
  *
  * If successful, returns a struct regulator_dev that corresponds to the name
- * @supply and with the embedded struct device refcount incremented by one,
- * or NULL on failure. The refcount must be dropped by calling put_device().
+ * @supply and with the embedded struct device refcount incremented by one.
+ * The refcount must be dropped by calling put_device().
+ * On failure one of the following ERR-PTR-encoded values is returned:
+ * -ENODEV if lookup fails permanently, -EPROBE_DEFER if lookup could succeed
+ * in the future.
  */
 static struct regulator_dev *regulator_dev_lookup(struct device *dev,
-						  const char *supply,
-						  int *ret)
+						  const char *supply)
 {
 	struct regulator_dev *r;
 	struct device_node *node;
@@ -1476,16 +1478,12 @@ static struct regulator_dev *regulator_dev_lookup(struct device *dev,
 			r = of_find_regulator_by_node(node);
 			if (r)
 				return r;
-			*ret = -EPROBE_DEFER;
-			return NULL;
-		} else {
+
 			/*
-			 * If we couldn't even get the node then it's
-			 * not just that the device didn't register
-			 * yet, there's no node and we'll never
-			 * succeed.
+			 * We have a node, but there is no device.
+			 * assume it has not registered yet.
 			 */
-			*ret = -ENODEV;
+			return ERR_PTR(-EPROBE_DEFER);
 		}
 	}
 
@@ -1506,13 +1504,16 @@ static struct regulator_dev *regulator_dev_lookup(struct device *dev,
 
 		if (strcmp(map->supply, supply) == 0 &&
 		    get_device(&map->regulator->dev)) {
-			mutex_unlock(&regulator_list_mutex);
-			return map->regulator;
+			r = map->regulator;
+			break;
 		}
 	}
 	mutex_unlock(&regulator_list_mutex);
 
-	return NULL;
+	if (r)
+		return r;
+
+	return ERR_PTR(-ENODEV);
 }
 
 static int regulator_resolve_supply(struct regulator_dev *rdev)
@@ -1529,8 +1530,10 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 	if (rdev->supply)
 		return 0;
 
-	r = regulator_dev_lookup(dev, rdev->supply_name, &ret);
-	if (!r) {
+	r = regulator_dev_lookup(dev, rdev->supply_name);
+	if (IS_ERR(r)) {
+		ret = PTR_ERR(r);
+
 		if (ret == -ENODEV) {
 			/*
 			 * No supply was specified for this regulator and
@@ -1553,6 +1556,19 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 		}
 	}
 
+	/*
+	 * If the supply's parent device is not the same as the
+	 * regulator's parent device, then ensure the parent device
+	 * is bound before we resolve the supply, in case the parent
+	 * device get probe deferred and unregisters the supply.
+	 */
+	if (r->dev.parent && r->dev.parent != rdev->dev.parent) {
+		if (!device_is_bound(r->dev.parent)) {
+			put_device(&r->dev);
+			return -EPROBE_DEFER;
+		}
+	}
+
 	/* Recursively resolve the supply of the supply */
 	ret = regulator_resolve_supply(r);
 	if (ret < 0) {
@@ -1580,69 +1596,72 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 }
 
 /* Internal regulator request function */
-static struct regulator *_regulator_get(struct device *dev, const char *id,
-					bool exclusive, bool allow_dummy)
+struct regulator *_regulator_get(struct device *dev, const char *id,
+				 enum regulator_get_type get_type)
 {
 	struct regulator_dev *rdev;
-	struct regulator *regulator = ERR_PTR(-EPROBE_DEFER);
-	const char *devname = NULL;
+	struct regulator *regulator;
+	const char *devname = dev ? dev_name(dev) : "deviceless";
 	int ret;
 
+	if (get_type >= MAX_GET_TYPE) {
+		dev_err(dev, "invalid type %d in %s\n", get_type, __func__);
+		return ERR_PTR(-EINVAL);
+	}
+
 	if (id == NULL) {
 		pr_err("get() with no identifier\n");
 		return ERR_PTR(-EINVAL);
 	}
 
-	if (dev)
-		devname = dev_name(dev);
+	rdev = regulator_dev_lookup(dev, id);
+	if (IS_ERR(rdev)) {
+		ret = PTR_ERR(rdev);
 
-	if (have_full_constraints())
-		ret = -ENODEV;
-	else
-		ret = -EPROBE_DEFER;
-
-	rdev = regulator_dev_lookup(dev, id, &ret);
-	if (rdev)
-		goto found;
-
-	regulator = ERR_PTR(ret);
+		/*
+		 * If regulator_dev_lookup() fails with error other
+		 * than -ENODEV our job here is done, we simply return it.
+		 */
+		if (ret != -ENODEV)
+			return ERR_PTR(ret);
 
-	/*
-	 * If we have return value from dev_lookup fail, we do not expect to
-	 * succeed, so, quit with appropriate error value
-	 */
-	if (ret && ret != -ENODEV)
-		return regulator;
+		if (!have_full_constraints()) {
+			dev_warn(dev,
+				 "incomplete constraints, dummy supplies not allowed\n");
+			return ERR_PTR(-ENODEV);
+		}
 
-	if (!devname)
-		devname = "deviceless";
+		switch (get_type) {
+		case NORMAL_GET:
+			/*
+			 * Assume that a regulator is physically present and
+			 * enabled, even if it isn't hooked up, and just
+			 * provide a dummy.
+			 */
+			dev_warn(dev,
+				 "%s supply %s not found, using dummy regulator\n",
+				 devname, id);
+			rdev = dummy_regulator_rdev;
+			get_device(&rdev->dev);
+			break;
 
-	/*
-	 * Assume that a regulator is physically present and enabled
-	 * even if it isn't hooked up and just provide a dummy.
-	 */
-	if (have_full_constraints() && allow_dummy) {
-		pr_warn("%s supply %s not found, using dummy regulator\n",
-			devname, id);
+		case EXCLUSIVE_GET:
+			dev_warn(dev,
+				 "dummy supplies not allowed for exclusive requests\n");
+			/* fall through */
 
-		rdev = dummy_regulator_rdev;
-		get_device(&rdev->dev);
-		goto found;
-	/* Don't log an error when called from regulator_get_optional() */
-	} else if (!have_full_constraints() || exclusive) {
-		dev_warn(dev, "dummy supplies not allowed\n");
+		default:
+			return ERR_PTR(-ENODEV);
+		}
 	}
 
-	return regulator;
-
-found:
 	if (rdev->exclusive) {
 		regulator = ERR_PTR(-EPERM);
 		put_device(&rdev->dev);
 		return regulator;
 	}
 
-	if (exclusive && rdev->open_count) {
+	if (get_type == EXCLUSIVE_GET && rdev->open_count) {
 		regulator = ERR_PTR(-EBUSY);
 		put_device(&rdev->dev);
 		return regulator;
@@ -1656,6 +1675,7 @@ found:
 	}
 
 	if (!try_module_get(rdev->owner)) {
+		regulator = ERR_PTR(-EPROBE_DEFER);
 		put_device(&rdev->dev);
 		return regulator;
 	}
@@ -1669,7 +1689,7 @@ found:
 	}
 
 	rdev->open_count++;
-	if (exclusive) {
+	if (get_type == EXCLUSIVE_GET) {
 		rdev->exclusive = 1;
 
 		ret = _regulator_is_enabled(rdev);
@@ -1697,7 +1717,7 @@ found:
  */
 struct regulator *regulator_get(struct device *dev, const char *id)
 {
-	return _regulator_get(dev, id, false, true);
+	return _regulator_get(dev, id, NORMAL_GET);
 }
 EXPORT_SYMBOL_GPL(regulator_get);
 
@@ -1724,7 +1744,7 @@ EXPORT_SYMBOL_GPL(regulator_get);
  */
 struct regulator *regulator_get_exclusive(struct device *dev, const char *id)
 {
-	return _regulator_get(dev, id, true, false);
+	return _regulator_get(dev, id, EXCLUSIVE_GET);
 }
 EXPORT_SYMBOL_GPL(regulator_get_exclusive);
 
@@ -1750,7 +1770,7 @@ EXPORT_SYMBOL_GPL(regulator_get_exclusive);
  */
 struct regulator *regulator_get_optional(struct device *dev, const char *id)
 {
-	return _regulator_get(dev, id, false, false);
+	return _regulator_get(dev, id, OPTIONAL_GET);
 }
 EXPORT_SYMBOL_GPL(regulator_get_optional);
 
@@ -3660,7 +3680,7 @@ err:
 	for (++i; i < num_consumers; ++i) {
 		r = regulator_enable(consumers[i].consumer);
 		if (r != 0)
-			pr_err("Failed to reename %s: %d\n",
+			pr_err("Failed to re-enable %s: %d\n",
 			       consumers[i].supply, r);
 	}
 
@@ -3686,21 +3706,17 @@ int regulator_bulk_force_disable(int num_consumers,
 			   struct regulator_bulk_data *consumers)
 {
 	int i;
-	int ret;
+	int ret = 0;
 
-	for (i = 0; i < num_consumers; i++)
+	for (i = 0; i < num_consumers; i++) {
 		consumers[i].ret =
 			    regulator_force_disable(consumers[i].consumer);
 
-	for (i = 0; i < num_consumers; i++) {
-		if (consumers[i].ret != 0) {
+		/* Store first error for reporting */
+		if (consumers[i].ret && !ret)
 			ret = consumers[i].ret;
-			goto out;
-		}
 	}
 
-	return 0;
-out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(regulator_bulk_force_disable);
@@ -4391,12 +4407,13 @@ static void regulator_summary_show_subtree(struct seq_file *s,
 	seq_puts(s, "\n");
 
 	list_for_each_entry(consumer, &rdev->consumer_list, list) {
-		if (consumer->dev->class == &regulator_class)
+		if (consumer->dev && consumer->dev->class == &regulator_class)
 			continue;
 
 		seq_printf(s, "%*s%-*s ",
 			   (level + 1) * 3 + 1, "",
-			   30 - (level + 1) * 3, dev_name(consumer->dev));
+			   30 - (level + 1) * 3,
+			   consumer->dev ? dev_name(consumer->dev) : "deviceless");
 
 		switch (rdev->desc->type) {
 		case REGULATOR_VOLTAGE:
@@ -4540,6 +4557,16 @@ static int __init regulator_init_complete(void)
 	if (of_have_populated_dt())
 		has_full_constraints = true;
 
+	/*
+	 * Regulators may had failed to resolve their input supplies
+	 * when were registered, either because the input supply was
+	 * not registered yet or because its parent device was not
+	 * bound yet. So attempt to resolve the input supplies for
+	 * pending regulators before trying to disable unused ones.
+	 */
+	class_for_each_device(&regulator_class, NULL, NULL,
+			      regulator_register_resolve_supply);
+
 	/* If we have a full configuration then disable any regulators
 	 * we have permission to change the status for and which are
 	 * not in use or always_on.  This is effectively the default
diff --git a/drivers/regulator/cpcap-regulator.c b/drivers/regulator/cpcap-regulator.c
new file mode 100644
index 000000000000..cc98aceed1c1
--- /dev/null
+++ b/drivers/regulator/cpcap-regulator.c
@@ -0,0 +1,464 @@
+/*
+ * Motorola CPCAP PMIC regulator driver
+ *
+ * Based on cpcap-regulator.c from Motorola Linux kernel tree
+ * Copyright (C) 2009-2011 Motorola, Inc.
+ *
+ * Rewritten for mainline kernel to use device tree and regmap
+ * Copyright (C) 2017 Tony Lindgren <tony@atomide.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/of_regulator.h>
+#include <linux/mfd/motorola-cpcap.h>
+
+/*
+ * Resource assignment register bits. These seem to control the state
+ * idle modes adn are used at least for omap4.
+ */
+
+/* CPCAP_REG_ASSIGN2 bits - Resource Assignment 2 */
+#define CPCAP_BIT_VSDIO_SEL		BIT(15)
+#define CPCAP_BIT_VDIG_SEL		BIT(14)
+#define CPCAP_BIT_VCAM_SEL		BIT(13)
+#define CPCAP_BIT_SW6_SEL		BIT(12)
+#define CPCAP_BIT_SW5_SEL		BIT(11)
+#define CPCAP_BIT_SW4_SEL		BIT(10)
+#define CPCAP_BIT_SW3_SEL		BIT(9)
+#define CPCAP_BIT_SW2_SEL		BIT(8)
+#define CPCAP_BIT_SW1_SEL		BIT(7)
+
+/* CPCAP_REG_ASSIGN3 bits - Resource Assignment 3 */
+#define CPCAP_BIT_VUSBINT2_SEL		BIT(15)
+#define CPCAP_BIT_VUSBINT1_SEL		BIT(14)
+#define CPCAP_BIT_VVIB_SEL		BIT(13)
+#define CPCAP_BIT_VWLAN1_SEL		BIT(12)
+#define CPCAP_BIT_VRF1_SEL		BIT(11)
+#define CPCAP_BIT_VHVIO_SEL		BIT(10)
+#define CPCAP_BIT_VDAC_SEL		BIT(9)
+#define CPCAP_BIT_VUSB_SEL		BIT(8)
+#define CPCAP_BIT_VSIM_SEL		BIT(7)
+#define CPCAP_BIT_VRFREF_SEL		BIT(6)
+#define CPCAP_BIT_VPLL_SEL		BIT(5)
+#define CPCAP_BIT_VFUSE_SEL		BIT(4)
+#define CPCAP_BIT_VCSI_SEL		BIT(3)
+#define CPCAP_BIT_SPARE_14_2		BIT(2)
+#define CPCAP_BIT_VWLAN2_SEL		BIT(1)
+#define CPCAP_BIT_VRF2_SEL		BIT(0)
+
+/* CPCAP_REG_ASSIGN4 bits - Resource Assignment 4 */
+#define CPCAP_BIT_VAUDIO_SEL		BIT(0)
+
+/*
+ * Enable register bits. At least CPCAP_BIT_AUDIO_LOW_PWR is generic,
+ * and not limited to audio regulator. Let's use the Motorola kernel
+ * naming for now until we have a better understanding of the other
+ * enable register bits. No idea why BIT(3) is not defined.
+ */
+#define CPCAP_BIT_AUDIO_LOW_PWR		BIT(6)
+#define CPCAP_BIT_AUD_LOWPWR_SPEED	BIT(5)
+#define CPCAP_BIT_VAUDIOPRISTBY		BIT(4)
+#define CPCAP_BIT_VAUDIO_MODE1		BIT(2)
+#define CPCAP_BIT_VAUDIO_MODE0		BIT(1)
+#define CPCAP_BIT_V_AUDIO_EN		BIT(0)
+
+/*
+ * Off mode configuration bit. Used currently only by SW5 on omap4. There's
+ * the following comment in Motorola Linux kernel tree for it:
+ *
+ * When set in the regulator mode, the regulator assignment will be changed
+ * to secondary when the regulator is disabled. The mode will be set back to
+ * primary when the regulator is turned on.
+ */
+#define CPCAP_REG_OFF_MODE_SEC		BIT(15)
+
+/**
+ * SoC specific configuraion for CPCAP regulator. There are at least three
+ * different SoCs each with their own parameters: omap3, omap4 and tegra2.
+ *
+ * The assign_reg and assign_mask seem to allow toggling between primary
+ * and secondary mode that at least omap4 uses for off mode.
+ */
+struct cpcap_regulator {
+	struct regulator_desc rdesc;
+	const u16 assign_reg;
+	const u16 assign_mask;
+	const u16 vsel_shift;
+};
+
+#define CPCAP_REG(_ID, reg, assignment_reg, assignment_mask, val_tbl,	\
+		mode_mask, volt_mask, volt_shft,			\
+		mode_val, off_val, volt_trans_time) {			\
+	.rdesc = {							\
+		.name = #_ID,						\
+		.of_match = of_match_ptr(#_ID),				\
+		.ops = &cpcap_regulator_ops,				\
+		.regulators_node = of_match_ptr("regulators"),		\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = CPCAP_##_ID,					\
+		.owner = THIS_MODULE,					\
+		.n_voltages = ARRAY_SIZE(val_tbl),			\
+		.volt_table = (val_tbl),				\
+		.vsel_reg = (reg),					\
+		.vsel_mask = (volt_mask),				\
+		.enable_reg = (reg),					\
+		.enable_mask = (mode_mask),				\
+		.enable_val = (mode_val),				\
+		.disable_val = (off_val),				\
+		.ramp_delay = (volt_trans_time),			\
+	},								\
+	.assign_reg = (assignment_reg),					\
+	.assign_mask = (assignment_mask),				\
+	.vsel_shift = (volt_shft),					\
+}
+
+struct cpcap_ddata {
+	struct regmap *reg;
+	struct device *dev;
+	const struct cpcap_regulator *soc;
+};
+
+enum cpcap_regulator_id {
+	CPCAP_SW1,
+	CPCAP_SW2,
+	CPCAP_SW3,
+	CPCAP_SW4,
+	CPCAP_SW5,
+	CPCAP_SW6,
+	CPCAP_VCAM,
+	CPCAP_VCSI,
+	CPCAP_VDAC,
+	CPCAP_VDIG,
+	CPCAP_VFUSE,
+	CPCAP_VHVIO,
+	CPCAP_VSDIO,
+	CPCAP_VPLL,
+	CPCAP_VRF1,
+	CPCAP_VRF2,
+	CPCAP_VRFREF,
+	CPCAP_VWLAN1,
+	CPCAP_VWLAN2,
+	CPCAP_VSIM,
+	CPCAP_VSIMCARD,
+	CPCAP_VVIB,
+	CPCAP_VUSB,
+	CPCAP_VAUDIO,
+	CPCAP_NR_REGULATORS,
+};
+
+/*
+ * We need to also configure regulator idle mode for SoC off mode if
+ * CPCAP_REG_OFF_MODE_SEC is set.
+ */
+static int cpcap_regulator_enable(struct regulator_dev *rdev)
+{
+	struct cpcap_regulator *regulator = rdev_get_drvdata(rdev);
+	int error, ignore;
+
+	error = regulator_enable_regmap(rdev);
+	if (error)
+		return error;
+
+	if (rdev->desc->enable_val & CPCAP_REG_OFF_MODE_SEC) {
+		error = regmap_update_bits(rdev->regmap, regulator->assign_reg,
+					   regulator->assign_mask,
+					   regulator->assign_mask);
+		if (error)
+			ignore = regulator_disable_regmap(rdev);
+	}
+
+	return error;
+}
+
+/*
+ * We need to also configure regulator idle mode for SoC off mode if
+ * CPCAP_REG_OFF_MODE_SEC is set.
+ */
+static int cpcap_regulator_disable(struct regulator_dev *rdev)
+{
+	struct cpcap_regulator *regulator = rdev_get_drvdata(rdev);
+	int error, ignore;
+
+	if (rdev->desc->enable_val & CPCAP_REG_OFF_MODE_SEC) {
+		error = regmap_update_bits(rdev->regmap, regulator->assign_reg,
+					   regulator->assign_mask, 0);
+		if (error)
+			return error;
+	}
+
+	error = regulator_disable_regmap(rdev);
+	if (error && (rdev->desc->enable_val & CPCAP_REG_OFF_MODE_SEC)) {
+		ignore = regmap_update_bits(rdev->regmap, regulator->assign_reg,
+					    regulator->assign_mask,
+					    regulator->assign_mask);
+	}
+
+	return error;
+}
+
+static unsigned int cpcap_regulator_get_mode(struct regulator_dev *rdev)
+{
+	int value;
+
+	regmap_read(rdev->regmap, rdev->desc->enable_reg, &value);
+
+	if (!(value & CPCAP_BIT_AUDIO_LOW_PWR))
+		return REGULATOR_MODE_STANDBY;
+
+	return REGULATOR_MODE_NORMAL;
+}
+
+static int cpcap_regulator_set_mode(struct regulator_dev *rdev,
+				    unsigned int mode)
+{
+	int value;
+
+	switch (mode) {
+	case REGULATOR_MODE_NORMAL:
+		value = CPCAP_BIT_AUDIO_LOW_PWR;
+		break;
+	case REGULATOR_MODE_STANDBY:
+		value = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return regmap_update_bits(rdev->regmap, rdev->desc->enable_reg,
+				  CPCAP_BIT_AUDIO_LOW_PWR, value);
+}
+
+static struct regulator_ops cpcap_regulator_ops = {
+	.enable = cpcap_regulator_enable,
+	.disable = cpcap_regulator_disable,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_table,
+	.map_voltage = regulator_map_voltage_iterate,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_mode = cpcap_regulator_get_mode,
+	.set_mode = cpcap_regulator_set_mode,
+};
+
+static const unsigned int unknown_val_tbl[] = { 0, };
+static const unsigned int sw5_val_tbl[] = { 0, 5050000, };
+static const unsigned int vcam_val_tbl[] = { 2600000, 2700000, 2800000,
+					     2900000, };
+static const unsigned int vcsi_val_tbl[] = { 1200000, 1800000, };
+static const unsigned int vdac_val_tbl[] = { 1200000, 1500000, 1800000,
+					     2500000,};
+static const unsigned int vdig_val_tbl[] = { 1200000, 1350000, 1500000,
+					     1875000, };
+static const unsigned int vfuse_val_tbl[] = { 1500000, 1600000, 1700000,
+					      1800000, 1900000, 2000000,
+					      2100000, 2200000, 2300000,
+					      2400000, 2500000, 2600000,
+					      2700000, 3150000, };
+static const unsigned int vhvio_val_tbl[] = { 2775000, };
+static const unsigned int vsdio_val_tbl[] = { 1500000, 1600000, 1800000,
+					      2600000, 2700000, 2800000,
+					      2900000, 3000000, };
+static const unsigned int vpll_val_tbl[] = { 1200000, 1300000, 1400000,
+					     1800000, };
+/* Quirk: 2775000 is before 2500000 for vrf1 regulator */
+static const unsigned int vrf1_val_tbl[] = { 2775000, 2500000, };
+static const unsigned int vrf2_val_tbl[] = { 0, 2775000, };
+static const unsigned int vrfref_val_tbl[] = { 2500000, 2775000, };
+static const unsigned int vwlan1_val_tbl[] = { 1800000, 1900000, };
+static const unsigned int vwlan2_val_tbl[] = { 2775000, 3000000, 3300000,
+					       3300000, };
+static const unsigned int vsim_val_tbl[] = { 1800000, 2900000, };
+static const unsigned int vsimcard_val_tbl[] = { 1800000, 2900000, };
+static const unsigned int vvib_val_tbl[] = { 1300000, 1800000, 2000000,
+					     3000000, };
+static const unsigned int vusb_val_tbl[] = { 0, 3300000, };
+static const unsigned int vaudio_val_tbl[] = { 0, 2775000, };
+
+/**
+ * SoC specific configuration for omap4. The data below is comes from Motorola
+ * Linux kernel tree. It's basically the values of cpcap_regltr_data,
+ * cpcap_regulator_mode_values and cpcap_regulator_off_mode_values, see
+ * CPCAP_REG macro above.
+ *
+ * SW1 to SW4 and SW6 seems to be unused for mapphone. Note that VSIM and
+ * VSIMCARD have a shared resource assignment bit.
+ */
+static struct cpcap_regulator omap4_regulators[] = {
+	CPCAP_REG(SW1, CPCAP_REG_S1C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW1_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(SW2, CPCAP_REG_S2C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW2_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(SW3, CPCAP_REG_S3C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW3_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(SW4, CPCAP_REG_S4C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW4_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(SW5, CPCAP_REG_S5C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW5_SEL, sw5_val_tbl,
+		  0x28, 0, 0, 0x20 | CPCAP_REG_OFF_MODE_SEC, 0, 0),
+	CPCAP_REG(SW6, CPCAP_REG_S6C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW6_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(VCAM, CPCAP_REG_VCAMC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VCAM_SEL, vcam_val_tbl,
+		  0x87, 0x30, 4, 0x3, 0, 420),
+	CPCAP_REG(VCSI, CPCAP_REG_VCSIC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VCSI_SEL, vcsi_val_tbl,
+		  0x47, 0x10, 4, 0x43, 0x41, 350),
+	CPCAP_REG(VDAC, CPCAP_REG_VDACC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VDAC_SEL, vdac_val_tbl,
+		  0x87, 0x30, 4, 0x3, 0, 420),
+	CPCAP_REG(VDIG, CPCAP_REG_VDIGC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VDIG_SEL, vdig_val_tbl,
+		  0x87, 0x30, 4, 0x82, 0, 420),
+	CPCAP_REG(VFUSE, CPCAP_REG_VFUSEC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VFUSE_SEL, vfuse_val_tbl,
+		  0x80, 0xf, 0, 0x80, 0, 420),
+	CPCAP_REG(VHVIO, CPCAP_REG_VHVIOC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VHVIO_SEL, vhvio_val_tbl,
+		  0x17, 0, 0, 0, 0x12, 0),
+	CPCAP_REG(VSDIO, CPCAP_REG_VSDIOC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VSDIO_SEL, vsdio_val_tbl,
+		  0x87, 0x38, 3, 0x82, 0, 420),
+	CPCAP_REG(VPLL, CPCAP_REG_VPLLC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VPLL_SEL, vpll_val_tbl,
+		  0x43, 0x18, 3, 0x2, 0, 420),
+	CPCAP_REG(VRF1, CPCAP_REG_VRF1C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRF1_SEL, vrf1_val_tbl,
+		  0xac, 0x2, 1, 0x4, 0, 10),
+	CPCAP_REG(VRF2, CPCAP_REG_VRF2C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRF2_SEL, vrf2_val_tbl,
+		  0x23, 0x8, 3, 0, 0, 10),
+	CPCAP_REG(VRFREF, CPCAP_REG_VRFREFC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRFREF_SEL, vrfref_val_tbl,
+		  0x23, 0x8, 3, 0, 0, 420),
+	CPCAP_REG(VWLAN1, CPCAP_REG_VWLAN1C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VWLAN1_SEL, vwlan1_val_tbl,
+		  0x47, 0x10, 4, 0, 0, 420),
+	CPCAP_REG(VWLAN2, CPCAP_REG_VWLAN2C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VWLAN2_SEL, vwlan2_val_tbl,
+		  0x20c, 0xc0, 6, 0x20c, 0, 420),
+	CPCAP_REG(VSIM, CPCAP_REG_VSIMC, CPCAP_REG_ASSIGN3,
+		  0xffff, vsim_val_tbl,
+		  0x23, 0x8, 3, 0x3, 0, 420),
+	CPCAP_REG(VSIMCARD, CPCAP_REG_VSIMC, CPCAP_REG_ASSIGN3,
+		  0xffff, vsimcard_val_tbl,
+		  0x1e80, 0x8, 3, 0x1e00, 0, 420),
+	CPCAP_REG(VVIB, CPCAP_REG_VVIBC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VVIB_SEL, vvib_val_tbl,
+		  0x1, 0xc, 2, 0x1, 0, 500),
+	CPCAP_REG(VUSB, CPCAP_REG_VUSBC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VUSB_SEL, vusb_val_tbl,
+		  0x11c, 0x40, 6, 0xc, 0, 0),
+	CPCAP_REG(VAUDIO, CPCAP_REG_VAUDIOC, CPCAP_REG_ASSIGN4,
+		  CPCAP_BIT_VAUDIO_SEL, vaudio_val_tbl,
+		  0x16, 0x1, 0, 0x4, 0, 0),
+	{ /* sentinel */ },
+};
+
+static const struct of_device_id cpcap_regulator_id_table[] = {
+	{
+		.compatible = "motorola,cpcap-regulator",
+	},
+	{
+		.compatible = "motorola,mapphone-cpcap-regulator",
+		.data = omap4_regulators,
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, cpcap_regulator_id_table);
+
+static int cpcap_regulator_probe(struct platform_device *pdev)
+{
+	struct cpcap_ddata *ddata;
+	const struct of_device_id *match;
+	struct regulator_config config;
+	struct regulator_init_data init_data;
+	int i;
+
+	match = of_match_device(of_match_ptr(cpcap_regulator_id_table),
+				&pdev->dev);
+	if (!match)
+		return -EINVAL;
+
+	if (!match->data) {
+		dev_err(&pdev->dev, "no configuration data found\n");
+
+		return -ENODEV;
+	}
+
+	ddata = devm_kzalloc(&pdev->dev, sizeof(*ddata), GFP_KERNEL);
+	if (!ddata)
+		return -ENOMEM;
+
+	ddata->reg = dev_get_regmap(pdev->dev.parent, NULL);
+	if (!ddata->reg)
+		return -ENODEV;
+
+	ddata->dev = &pdev->dev;
+	ddata->soc = match->data;
+	platform_set_drvdata(pdev, ddata);
+
+	memset(&config, 0, sizeof(config));
+	memset(&init_data, 0, sizeof(init_data));
+	config.dev = &pdev->dev;
+	config.regmap = ddata->reg;
+	config.init_data = &init_data;
+
+	for (i = 0; i < CPCAP_NR_REGULATORS; i++) {
+		const struct cpcap_regulator *regulator = &ddata->soc[i];
+		struct regulator_dev *rdev;
+
+		if (!regulator->rdesc.name)
+			break;
+
+		if (regulator->rdesc.volt_table == unknown_val_tbl)
+			continue;
+
+		config.driver_data = (void *)regulator;
+		rdev = devm_regulator_register(&pdev->dev,
+					       &regulator->rdesc,
+					       &config);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "failed to register regulator %s\n",
+				regulator->rdesc.name);
+
+			return PTR_ERR(rdev);
+		}
+	}
+
+	return 0;
+}
+
+static struct platform_driver cpcap_regulator_driver = {
+	.probe		= cpcap_regulator_probe,
+	.driver		= {
+		.name	= "cpcap-regulator",
+		.of_match_table = of_match_ptr(cpcap_regulator_id_table),
+	},
+};
+
+module_platform_driver(cpcap_regulator_driver);
+
+MODULE_ALIAS("platform:cpcap-regulator");
+MODULE_AUTHOR("Tony Lindgren <tony@atomide.com>");
+MODULE_DESCRIPTION("CPCAP regulator driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/devres.c b/drivers/regulator/devres.c
index 6ec1d400adae..784e3bf32210 100644
--- a/drivers/regulator/devres.c
+++ b/drivers/regulator/devres.c
@@ -19,12 +19,6 @@
 
 #include "internal.h"
 
-enum {
-	NORMAL_GET,
-	EXCLUSIVE_GET,
-	OPTIONAL_GET,
-};
-
 static void devm_regulator_release(struct device *dev, void *res)
 {
 	regulator_put(*(struct regulator **)res);
@@ -39,20 +33,7 @@ static struct regulator *_devm_regulator_get(struct device *dev, const char *id,
 	if (!ptr)
 		return ERR_PTR(-ENOMEM);
 
-	switch (get_type) {
-	case NORMAL_GET:
-		regulator = regulator_get(dev, id);
-		break;
-	case EXCLUSIVE_GET:
-		regulator = regulator_get_exclusive(dev, id);
-		break;
-	case OPTIONAL_GET:
-		regulator = regulator_get_optional(dev, id);
-		break;
-	default:
-		regulator = ERR_PTR(-EINVAL);
-	}
-
+	regulator = _regulator_get(dev, id, get_type);
 	if (!IS_ERR(regulator)) {
 		*ptr = regulator;
 		devres_add(dev, ptr);
@@ -139,6 +120,18 @@ void devm_regulator_put(struct regulator *regulator)
 }
 EXPORT_SYMBOL_GPL(devm_regulator_put);
 
+struct regulator_bulk_devres {
+	struct regulator_bulk_data *consumers;
+	int num_consumers;
+};
+
+static void devm_regulator_bulk_release(struct device *dev, void *res)
+{
+	struct regulator_bulk_devres *devres = res;
+
+	regulator_bulk_free(devres->num_consumers, devres->consumers);
+}
+
 /**
  * devm_regulator_bulk_get - managed get multiple regulator consumers
  *
@@ -157,29 +150,22 @@ EXPORT_SYMBOL_GPL(devm_regulator_put);
 int devm_regulator_bulk_get(struct device *dev, int num_consumers,
 			    struct regulator_bulk_data *consumers)
 {
-	int i;
+	struct regulator_bulk_devres *devres;
 	int ret;
 
-	for (i = 0; i < num_consumers; i++)
-		consumers[i].consumer = NULL;
-
-	for (i = 0; i < num_consumers; i++) {
-		consumers[i].consumer = devm_regulator_get(dev,
-							   consumers[i].supply);
-		if (IS_ERR(consumers[i].consumer)) {
-			ret = PTR_ERR(consumers[i].consumer);
-			dev_err(dev, "Failed to get supply '%s': %d\n",
-				consumers[i].supply, ret);
-			consumers[i].consumer = NULL;
-			goto err;
-		}
-	}
-
-	return 0;
+	devres = devres_alloc(devm_regulator_bulk_release,
+			      sizeof(*devres), GFP_KERNEL);
+	if (!devres)
+		return -ENOMEM;
 
-err:
-	for (i = 0; i < num_consumers && consumers[i].consumer; i++)
-		devm_regulator_put(consumers[i].consumer);
+	ret = regulator_bulk_get(dev, num_consumers, consumers);
+	if (!ret) {
+		devres->consumers = consumers;
+		devres->num_consumers = num_consumers;
+		devres_add(dev, devres);
+	} else {
+		devres_free(devres);
+	}
 
 	return ret;
 }
diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c
index d7da81a875cf..60f431831582 100644
--- a/drivers/regulator/fan53555.c
+++ b/drivers/regulator/fan53555.c
@@ -202,7 +202,7 @@ static int fan53555_set_ramp(struct regulator_dev *rdev, int ramp)
 				  CTL_SLEW_MASK, regval << CTL_SLEW_SHIFT);
 }
 
-static struct regulator_ops fan53555_regulator_ops = {
+static const struct regulator_ops fan53555_regulator_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_time_sel = regulator_set_voltage_time_sel,
diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c
index a43b0e8a438d..988a7472c2ab 100644
--- a/drivers/regulator/fixed.c
+++ b/drivers/regulator/fixed.c
@@ -30,9 +30,6 @@
 #include <linux/of_gpio.h>
 #include <linux/regulator/of_regulator.h>
 #include <linux/regulator/machine.h>
-#include <linux/acpi.h>
-#include <linux/property.h>
-#include <linux/gpio/consumer.h>
 
 struct fixed_voltage_data {
 	struct regulator_desc desc;
@@ -97,44 +94,6 @@ of_get_fixed_voltage_config(struct device *dev,
 	return config;
 }
 
-/**
- * acpi_get_fixed_voltage_config - extract fixed_voltage_config structure info
- * @dev: device requesting for fixed_voltage_config
- * @desc: regulator description
- *
- * Populates fixed_voltage_config structure by extracting data through ACPI
- * interface, returns a pointer to the populated structure of NULL if memory
- * alloc fails.
- */
-static struct fixed_voltage_config *
-acpi_get_fixed_voltage_config(struct device *dev,
-			      const struct regulator_desc *desc)
-{
-	struct fixed_voltage_config *config;
-	const char *supply_name;
-	struct gpio_desc *gpiod;
-	int ret;
-
-	config = devm_kzalloc(dev, sizeof(*config), GFP_KERNEL);
-	if (!config)
-		return ERR_PTR(-ENOMEM);
-
-	ret = device_property_read_string(dev, "supply-name", &supply_name);
-	if (!ret)
-		config->supply_name = supply_name;
-
-	gpiod = gpiod_get(dev, "gpio", GPIOD_ASIS);
-	if (IS_ERR(gpiod))
-		return ERR_PTR(-ENODEV);
-
-	config->gpio = desc_to_gpio(gpiod);
-	config->enable_high = device_property_read_bool(dev,
-							"enable-active-high");
-	gpiod_put(gpiod);
-
-	return config;
-}
-
 static struct regulator_ops fixed_voltage_ops = {
 };
 
@@ -155,11 +114,6 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev)
 						     &drvdata->desc);
 		if (IS_ERR(config))
 			return PTR_ERR(config);
-	} else if (ACPI_HANDLE(&pdev->dev)) {
-		config = acpi_get_fixed_voltage_config(&pdev->dev,
-						       &drvdata->desc);
-		if (IS_ERR(config))
-			return PTR_ERR(config);
 	} else {
 		config = dev_get_platdata(&pdev->dev);
 	}
diff --git a/drivers/regulator/hi655x-regulator.c b/drivers/regulator/hi655x-regulator.c
index aca18466f522..065c100e9a03 100644
--- a/drivers/regulator/hi655x-regulator.c
+++ b/drivers/regulator/hi655x-regulator.c
@@ -96,7 +96,7 @@ static int hi655x_disable(struct regulator_dev *rdev)
 	return ret;
 }
 
-static struct regulator_ops hi655x_regulator_ops = {
+static const struct regulator_ops hi655x_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = hi655x_disable,
 	.is_enabled = hi655x_is_enabled,
@@ -105,7 +105,7 @@ static struct regulator_ops hi655x_regulator_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 };
 
-static struct regulator_ops hi655x_ldo_linear_ops = {
+static const struct regulator_ops hi655x_ldo_linear_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = hi655x_disable,
 	.is_enabled = hi655x_is_enabled,
diff --git a/drivers/regulator/internal.h b/drivers/regulator/internal.h
index c74ac8734023..1dd575b28564 100644
--- a/drivers/regulator/internal.h
+++ b/drivers/regulator/internal.h
@@ -51,4 +51,14 @@ regulator_of_get_init_data(struct device *dev,
 }
 #endif
 
+enum regulator_get_type {
+	NORMAL_GET,
+	EXCLUSIVE_GET,
+	OPTIONAL_GET,
+	MAX_GET_TYPE
+};
+
+struct regulator *_regulator_get(struct device *dev, const char *id,
+				 enum regulator_get_type get_type);
+
 #endif
diff --git a/drivers/regulator/lp8755.c b/drivers/regulator/lp8755.c
index d6773da925ba..db34e1da75ef 100644
--- a/drivers/regulator/lp8755.c
+++ b/drivers/regulator/lp8755.c
@@ -227,7 +227,7 @@ err_i2c:
 	return ret;
 }
 
-static struct regulator_ops lp8755_buck_ops = {
+static const struct regulator_ops lp8755_buck_ops = {
 	.map_voltage = regulator_map_voltage_linear,
 	.list_voltage = regulator_list_voltage_linear,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
diff --git a/drivers/regulator/ltc3589.c b/drivers/regulator/ltc3589.c
index 47bef328fb58..a7a1a0313bbf 100644
--- a/drivers/regulator/ltc3589.c
+++ b/drivers/regulator/ltc3589.c
@@ -161,7 +161,7 @@ static int ltc3589_set_suspend_mode(struct regulator_dev *rdev,
 }
 
 /* SW1, SW2, SW3, LDO2 */
-static struct regulator_ops ltc3589_linear_regulator_ops = {
+static const struct regulator_ops ltc3589_linear_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
@@ -175,18 +175,18 @@ static struct regulator_ops ltc3589_linear_regulator_ops = {
 };
 
 /* BB_OUT, LDO3 */
-static struct regulator_ops ltc3589_fixed_regulator_ops = {
+static const struct regulator_ops ltc3589_fixed_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
 };
 
 /* LDO1 */
-static struct regulator_ops ltc3589_fixed_standby_regulator_ops = {
+static const struct regulator_ops ltc3589_fixed_standby_regulator_ops = {
 };
 
 /* LDO4 */
-static struct regulator_ops ltc3589_table_regulator_ops = {
+static const struct regulator_ops ltc3589_table_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
diff --git a/drivers/regulator/ltc3676.c b/drivers/regulator/ltc3676.c
index e2b476ca2b4d..503cd90eba39 100644
--- a/drivers/regulator/ltc3676.c
+++ b/drivers/regulator/ltc3676.c
@@ -161,7 +161,7 @@ static int ltc3676_of_parse_cb(struct device_node *np,
 }
 
 /* SW1, SW2, SW3, SW4 linear 0.8V-3.3V with scalar via R1/R2 feeback res */
-static struct regulator_ops ltc3676_linear_regulator_ops = {
+static const struct regulator_ops ltc3676_linear_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
@@ -173,11 +173,11 @@ static struct regulator_ops ltc3676_linear_regulator_ops = {
 };
 
 /* LDO1 always on fixed 0.8V-3.3V via scalar via R1/R2 feeback res */
-static struct regulator_ops ltc3676_fixed_standby_regulator_ops = {
+static const struct regulator_ops ltc3676_fixed_standby_regulator_ops = {
 };
 
 /* LDO2, LDO3 fixed (LDO2 has external scalar via R1/R2 feedback res) */
-static struct regulator_ops ltc3676_fixed_regulator_ops = {
+static const struct regulator_ops ltc3676_fixed_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
diff --git a/drivers/regulator/max14577-regulator.c b/drivers/regulator/max14577-regulator.c
index c9ff26199711..0db288ce319c 100644
--- a/drivers/regulator/max14577-regulator.c
+++ b/drivers/regulator/max14577-regulator.c
@@ -85,14 +85,14 @@ static int max14577_reg_set_current_limit(struct regulator_dev *rdev,
 			reg_data);
 }
 
-static struct regulator_ops max14577_safeout_ops = {
+static const struct regulator_ops max14577_safeout_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
 	.list_voltage		= regulator_list_voltage_linear,
 };
 
-static struct regulator_ops max14577_charger_ops = {
+static const struct regulator_ops max14577_charger_ops = {
 	.is_enabled		= max14577_reg_is_enabled,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -130,7 +130,7 @@ static const struct regulator_desc max14577_supported_regulators[] = {
 	[MAX14577_CHARGER] = MAX14577_CHARGER_REG,
 };
 
-static struct regulator_ops max77836_ldo_ops = {
+static const struct regulator_ops max77836_ldo_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
diff --git a/drivers/regulator/max77620-regulator.c b/drivers/regulator/max77620-regulator.c
index d088a7c79e60..b94e3a721721 100644
--- a/drivers/regulator/max77620-regulator.c
+++ b/drivers/regulator/max77620-regulator.c
@@ -644,7 +644,7 @@ static int max77620_of_parse_cb(struct device_node *np,
 	return max77620_init_pmic(pmic, desc->id);
 }
 
-static struct regulator_ops max77620_regulator_ops = {
+static const struct regulator_ops max77620_regulator_ops = {
 	.is_enabled = max77620_regulator_is_enabled,
 	.enable = max77620_regulator_enable,
 	.disable = max77620_regulator_disable,
diff --git a/drivers/regulator/max77686-regulator.c b/drivers/regulator/max77686-regulator.c
index ac4fa581e0a5..c301f3733475 100644
--- a/drivers/regulator/max77686-regulator.c
+++ b/drivers/regulator/max77686-regulator.c
@@ -289,7 +289,7 @@ static int max77686_of_parse_cb(struct device_node *np,
 	return 0;
 }
 
-static struct regulator_ops max77686_ops = {
+static const struct regulator_ops max77686_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -301,7 +301,7 @@ static struct regulator_ops max77686_ops = {
 	.set_suspend_mode	= max77686_set_suspend_mode,
 };
 
-static struct regulator_ops max77686_ldo_ops = {
+static const struct regulator_ops max77686_ldo_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -314,7 +314,7 @@ static struct regulator_ops max77686_ldo_ops = {
 	.set_suspend_disable	= max77686_set_suspend_disable,
 };
 
-static struct regulator_ops max77686_buck1_ops = {
+static const struct regulator_ops max77686_buck1_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -326,7 +326,7 @@ static struct regulator_ops max77686_buck1_ops = {
 	.set_suspend_disable	= max77686_set_suspend_disable,
 };
 
-static struct regulator_ops max77686_buck_dvs_ops = {
+static const struct regulator_ops max77686_buck_dvs_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= regulator_is_enabled_regmap,
diff --git a/drivers/regulator/max77693-regulator.c b/drivers/regulator/max77693-regulator.c
index cfbb9512e486..3fce67982682 100644
--- a/drivers/regulator/max77693-regulator.c
+++ b/drivers/regulator/max77693-regulator.c
@@ -141,7 +141,7 @@ static const unsigned int max77693_safeout_table[] = {
 	3300000,
 };
 
-static struct regulator_ops max77693_safeout_ops = {
+static const struct regulator_ops max77693_safeout_ops = {
 	.list_voltage		= regulator_list_voltage_table,
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
diff --git a/drivers/regulator/max77802-regulator.c b/drivers/regulator/max77802-regulator.c
index 1d3539324d9a..b6261903818c 100644
--- a/drivers/regulator/max77802-regulator.c
+++ b/drivers/regulator/max77802-regulator.c
@@ -288,7 +288,7 @@ static int max77802_set_ramp_delay_4bit(struct regulator_dev *rdev,
 /*
  * LDOs 2, 4-19, 22-35
  */
-static struct regulator_ops max77802_ldo_ops_logic1 = {
+static const struct regulator_ops max77802_ldo_ops_logic1 = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -304,7 +304,7 @@ static struct regulator_ops max77802_ldo_ops_logic1 = {
 /*
  * LDOs 1, 20, 21, 3
  */
-static struct regulator_ops max77802_ldo_ops_logic2 = {
+static const struct regulator_ops max77802_ldo_ops_logic2 = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -319,7 +319,7 @@ static struct regulator_ops max77802_ldo_ops_logic2 = {
 };
 
 /* BUCKS 1, 6 */
-static struct regulator_ops max77802_buck_16_dvs_ops = {
+static const struct regulator_ops max77802_buck_16_dvs_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -333,7 +333,7 @@ static struct regulator_ops max77802_buck_16_dvs_ops = {
 };
 
 /* BUCKs 2-4 */
-static struct regulator_ops max77802_buck_234_ops = {
+static const struct regulator_ops max77802_buck_234_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -348,7 +348,7 @@ static struct regulator_ops max77802_buck_234_ops = {
 };
 
 /* BUCKs 5, 7-10 */
-static struct regulator_ops max77802_buck_dvs_ops = {
+static const struct regulator_ops max77802_buck_dvs_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= regulator_is_enabled_regmap,
diff --git a/drivers/regulator/max8907-regulator.c b/drivers/regulator/max8907-regulator.c
index 5e941db5ccaf..860400d2cd85 100644
--- a/drivers/regulator/max8907-regulator.c
+++ b/drivers/regulator/max8907-regulator.c
@@ -109,7 +109,7 @@ struct max8907_regulator {
 #define LDO_650_25(id, supply, base) REG_LDO(id, supply, (base), \
 			650000, 2225000, 25000)
 
-static struct regulator_ops max8907_mbatt_ops = {
+static const struct regulator_ops max8907_mbatt_ops = {
 };
 
 static struct regulator_ops max8907_ldo_ops = {
@@ -121,13 +121,13 @@ static struct regulator_ops max8907_ldo_ops = {
 	.is_enabled = regulator_is_enabled_regmap,
 };
 
-static struct regulator_ops max8907_ldo_hwctl_ops = {
+static const struct regulator_ops max8907_ldo_hwctl_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 };
 
-static struct regulator_ops max8907_fixed_ops = {
+static const struct regulator_ops max8907_fixed_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 };
 
@@ -138,11 +138,11 @@ static struct regulator_ops max8907_out5v_ops = {
 	.is_enabled = regulator_is_enabled_regmap,
 };
 
-static struct regulator_ops max8907_out5v_hwctl_ops = {
+static const struct regulator_ops max8907_out5v_hwctl_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 };
 
-static struct regulator_ops max8907_bbat_ops = {
+static const struct regulator_ops max8907_bbat_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
diff --git a/drivers/regulator/max8925-regulator.c b/drivers/regulator/max8925-regulator.c
index c802f0239dc7..39b63ddefeb2 100644
--- a/drivers/regulator/max8925-regulator.c
+++ b/drivers/regulator/max8925-regulator.c
@@ -132,7 +132,7 @@ static int max8925_set_dvm_disable(struct regulator_dev *rdev)
 	return max8925_set_bits(info->i2c, info->vol_reg, 1 << SD1_DVM_EN, 0);
 }
 
-static struct regulator_ops max8925_regulator_sdv_ops = {
+static const struct regulator_ops max8925_regulator_sdv_ops = {
 	.map_voltage		= regulator_map_voltage_linear,
 	.list_voltage		= regulator_list_voltage_linear,
 	.set_voltage_sel	= max8925_set_voltage_sel,
@@ -145,7 +145,7 @@ static struct regulator_ops max8925_regulator_sdv_ops = {
 	.set_suspend_disable	= max8925_set_dvm_disable,
 };
 
-static struct regulator_ops max8925_regulator_ldo_ops = {
+static const struct regulator_ops max8925_regulator_ldo_ops = {
 	.map_voltage		= regulator_map_voltage_linear,
 	.list_voltage		= regulator_list_voltage_linear,
 	.set_voltage_sel	= max8925_set_voltage_sel,
diff --git a/drivers/regulator/max8952.c b/drivers/regulator/max8952.c
index 1af8f4a2ab86..1096546c05e9 100644
--- a/drivers/regulator/max8952.c
+++ b/drivers/regulator/max8952.c
@@ -113,7 +113,7 @@ static int max8952_set_voltage_sel(struct regulator_dev *rdev,
 	return 0;
 }
 
-static struct regulator_ops max8952_ops = {
+static const struct regulator_ops max8952_ops = {
 	.list_voltage		= max8952_list_voltage,
 	.get_voltage_sel	= max8952_get_voltage_sel,
 	.set_voltage_sel	= max8952_set_voltage_sel,
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index f11d41dad9c1..31ae5ee3a80d 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -528,7 +528,7 @@ static int palmas_smps_set_ramp_delay(struct regulator_dev *rdev,
 	return ret;
 }
 
-static struct regulator_ops palmas_ops_smps = {
+static const struct regulator_ops palmas_ops_smps = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -542,7 +542,7 @@ static struct regulator_ops palmas_ops_smps = {
 	.set_ramp_delay		= palmas_smps_set_ramp_delay,
 };
 
-static struct regulator_ops palmas_ops_ext_control_smps = {
+static const struct regulator_ops palmas_ops_ext_control_smps = {
 	.set_mode		= palmas_set_mode_smps,
 	.get_mode		= palmas_get_mode_smps,
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
@@ -553,7 +553,7 @@ static struct regulator_ops palmas_ops_ext_control_smps = {
 	.set_ramp_delay		= palmas_smps_set_ramp_delay,
 };
 
-static struct regulator_ops palmas_ops_smps10 = {
+static const struct regulator_ops palmas_ops_smps10 = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -565,7 +565,7 @@ static struct regulator_ops palmas_ops_smps10 = {
 	.get_bypass		= regulator_get_bypass_regmap,
 };
 
-static struct regulator_ops tps65917_ops_smps = {
+static const struct regulator_ops tps65917_ops_smps = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -578,7 +578,7 @@ static struct regulator_ops tps65917_ops_smps = {
 	.set_voltage_time_sel	= regulator_set_voltage_time_sel,
 };
 
-static struct regulator_ops tps65917_ops_ext_control_smps = {
+static const struct regulator_ops tps65917_ops_ext_control_smps = {
 	.set_mode		= palmas_set_mode_smps,
 	.get_mode		= palmas_get_mode_smps,
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
@@ -602,7 +602,7 @@ static int palmas_is_enabled_ldo(struct regulator_dev *dev)
 	return !!(reg);
 }
 
-static struct regulator_ops palmas_ops_ldo = {
+static const struct regulator_ops palmas_ops_ldo = {
 	.is_enabled		= palmas_is_enabled_ldo,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -612,7 +612,7 @@ static struct regulator_ops palmas_ops_ldo = {
 	.map_voltage		= regulator_map_voltage_linear,
 };
 
-static struct regulator_ops palmas_ops_ldo9 = {
+static const struct regulator_ops palmas_ops_ldo9 = {
 	.is_enabled		= palmas_is_enabled_ldo,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -624,23 +624,23 @@ static struct regulator_ops palmas_ops_ldo9 = {
 	.get_bypass		= regulator_get_bypass_regmap,
 };
 
-static struct regulator_ops palmas_ops_ext_control_ldo = {
+static const struct regulator_ops palmas_ops_ext_control_ldo = {
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
 	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 };
 
-static struct regulator_ops palmas_ops_extreg = {
+static const struct regulator_ops palmas_ops_extreg = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
 };
 
-static struct regulator_ops palmas_ops_ext_control_extreg = {
+static const struct regulator_ops palmas_ops_ext_control_extreg = {
 };
 
-static struct regulator_ops tps65917_ops_ldo = {
+static const struct regulator_ops tps65917_ops_ldo = {
 	.is_enabled		= palmas_is_enabled_ldo,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
@@ -651,7 +651,7 @@ static struct regulator_ops tps65917_ops_ldo = {
 	.set_voltage_time_sel	= regulator_set_voltage_time_sel,
 };
 
-static struct regulator_ops tps65917_ops_ldo_1_2 = {
+static const struct regulator_ops tps65917_ops_ldo_1_2 = {
 	.is_enabled		= palmas_is_enabled_ldo,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
diff --git a/drivers/regulator/pbias-regulator.c b/drivers/regulator/pbias-regulator.c
index f9d74d63be7c..0cb76ba29e84 100644
--- a/drivers/regulator/pbias-regulator.c
+++ b/drivers/regulator/pbias-regulator.c
@@ -54,7 +54,7 @@ static const unsigned int pbias_volt_table[] = {
 	3000000
 };
 
-static struct regulator_ops pbias_regulator_voltage_ops = {
+static const struct regulator_ops pbias_regulator_voltage_ops = {
 	.list_voltage = regulator_list_voltage_table,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
diff --git a/drivers/regulator/pcap-regulator.c b/drivers/regulator/pcap-regulator.c
index 9b16e6158f15..79cb971a69bb 100644
--- a/drivers/regulator/pcap-regulator.c
+++ b/drivers/regulator/pcap-regulator.c
@@ -210,7 +210,7 @@ static int pcap_regulator_is_enabled(struct regulator_dev *rdev)
 	return (tmp >> vreg->en) & 1;
 }
 
-static struct regulator_ops pcap_regulator_ops = {
+static const struct regulator_ops pcap_regulator_ops = {
 	.list_voltage	= regulator_list_voltage_table,
 	.set_voltage_sel = pcap_regulator_set_voltage_sel,
 	.get_voltage_sel = pcap_regulator_get_voltage_sel,
diff --git a/drivers/regulator/pcf50633-regulator.c b/drivers/regulator/pcf50633-regulator.c
index 134f90ec9ca1..762e18447cae 100644
--- a/drivers/regulator/pcf50633-regulator.c
+++ b/drivers/regulator/pcf50633-regulator.c
@@ -41,7 +41,7 @@
 		.enable_mask = PCF50633_REGULATOR_ON,		\
 	}
 
-static struct regulator_ops pcf50633_regulator_ops = {
+static const struct regulator_ops pcf50633_regulator_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.list_voltage = regulator_list_voltage_linear,
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index cb18b5c4f2db..e193bbbb8ffc 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -126,7 +126,7 @@ static int pfuze100_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay)
 	return ret;
 }
 
-static struct regulator_ops pfuze100_ldo_regulator_ops = {
+static const struct regulator_ops pfuze100_ldo_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
@@ -135,14 +135,14 @@ static struct regulator_ops pfuze100_ldo_regulator_ops = {
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 };
 
-static struct regulator_ops pfuze100_fixed_regulator_ops = {
+static const struct regulator_ops pfuze100_fixed_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
 	.list_voltage = regulator_list_voltage_linear,
 };
 
-static struct regulator_ops pfuze100_sw_regulator_ops = {
+static const struct regulator_ops pfuze100_sw_regulator_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
@@ -150,7 +150,7 @@ static struct regulator_ops pfuze100_sw_regulator_ops = {
 	.set_ramp_delay = pfuze100_set_ramp_delay,
 };
 
-static struct regulator_ops pfuze100_swb_regulator_ops = {
+static const struct regulator_ops pfuze100_swb_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.list_voltage = regulator_list_voltage_table,
diff --git a/drivers/regulator/pv88060-regulator.c b/drivers/regulator/pv88060-regulator.c
index 6c4afc73ecac..a9446056435f 100644
--- a/drivers/regulator/pv88060-regulator.c
+++ b/drivers/regulator/pv88060-regulator.c
@@ -162,7 +162,7 @@ static int pv88060_get_current_limit(struct regulator_dev *rdev)
 	return info->current_limits[data];
 }
 
-static struct regulator_ops pv88060_buck_ops = {
+static const struct regulator_ops pv88060_buck_ops = {
 	.get_mode = pv88060_buck_get_mode,
 	.set_mode = pv88060_buck_set_mode,
 	.enable = regulator_enable_regmap,
@@ -175,7 +175,7 @@ static struct regulator_ops pv88060_buck_ops = {
 	.get_current_limit = pv88060_get_current_limit,
 };
 
-static struct regulator_ops pv88060_ldo_ops = {
+static const struct regulator_ops pv88060_ldo_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
diff --git a/drivers/regulator/pv88080-regulator.c b/drivers/regulator/pv88080-regulator.c
index 954a20eeb26f..9a08cb2de501 100644
--- a/drivers/regulator/pv88080-regulator.c
+++ b/drivers/regulator/pv88080-regulator.c
@@ -306,7 +306,7 @@ static int pv88080_get_current_limit(struct regulator_dev *rdev)
 	return info->current_limits[data];
 }
 
-static struct regulator_ops pv88080_buck_ops = {
+static const struct regulator_ops pv88080_buck_ops = {
 	.get_mode = pv88080_buck_get_mode,
 	.set_mode = pv88080_buck_set_mode,
 	.enable = regulator_enable_regmap,
@@ -319,7 +319,7 @@ static struct regulator_ops pv88080_buck_ops = {
 	.get_current_limit = pv88080_get_current_limit,
 };
 
-static struct regulator_ops pv88080_hvbuck_ops = {
+static const struct regulator_ops pv88080_hvbuck_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
diff --git a/drivers/regulator/pv88090-regulator.c b/drivers/regulator/pv88090-regulator.c
index 421641175352..ab51e254d13a 100644
--- a/drivers/regulator/pv88090-regulator.c
+++ b/drivers/regulator/pv88090-regulator.c
@@ -184,7 +184,7 @@ static int pv88090_get_current_limit(struct regulator_dev *rdev)
 	return info->current_limits[data];
 }
 
-static struct regulator_ops pv88090_buck_ops = {
+static const struct regulator_ops pv88090_buck_ops = {
 	.get_mode = pv88090_buck_get_mode,
 	.set_mode = pv88090_buck_set_mode,
 	.enable = regulator_enable_regmap,
@@ -197,7 +197,7 @@ static struct regulator_ops pv88090_buck_ops = {
 	.get_current_limit = pv88090_get_current_limit,
 };
 
-static struct regulator_ops pv88090_ldo_ops = {
+static const struct regulator_ops pv88090_ldo_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
 	.is_enabled = regulator_is_enabled_regmap,
diff --git a/drivers/regulator/qcom_smd-regulator.c b/drivers/regulator/qcom_smd-regulator.c
index 8ed46a9a55c8..f35994a2a5be 100644
--- a/drivers/regulator/qcom_smd-regulator.c
+++ b/drivers/regulator/qcom_smd-regulator.c
@@ -305,6 +305,56 @@ static const struct regulator_desc pm8916_buck_hvo_smps = {
 	.ops = &rpm_smps_ldo_ops,
 };
 
+static const struct regulator_desc pm8994_hfsmps = {
+	.linear_ranges = (struct regulator_linear_range[]) {
+		REGULATOR_LINEAR_RANGE( 375000,  0,  95, 12500),
+		REGULATOR_LINEAR_RANGE(1550000, 96, 158, 25000),
+	},
+	.n_linear_ranges = 2,
+	.n_voltages = 159,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm8994_ftsmps = {
+	.linear_ranges = (struct regulator_linear_range[]) {
+		REGULATOR_LINEAR_RANGE(350000,  0, 199, 5000),
+		REGULATOR_LINEAR_RANGE(700000, 200, 349, 10000),
+	},
+	.n_linear_ranges = 2,
+	.n_voltages = 350,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm8994_nldo = {
+	.linear_ranges = (struct regulator_linear_range[]) {
+		REGULATOR_LINEAR_RANGE(750000, 0, 63, 12500),
+	},
+	.n_linear_ranges = 1,
+	.n_voltages = 64,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm8994_pldo = {
+	.linear_ranges = (struct regulator_linear_range[]) {
+		REGULATOR_LINEAR_RANGE( 750000,  0,  63, 12500),
+		REGULATOR_LINEAR_RANGE(1550000, 64, 126, 25000),
+		REGULATOR_LINEAR_RANGE(3100000, 127, 163, 50000),
+	},
+	.n_linear_ranges = 3,
+	.n_voltages = 164,
+	.ops = &rpm_smps_ldo_ops,
+};
+
+static const struct regulator_desc pm8994_switch = {
+	.ops = &rpm_switch_ops,
+};
+
+static const struct regulator_desc pm8994_lnldo = {
+	.fixed_uV = 1740000,
+	.n_voltages = 1,
+	.ops = &rpm_smps_ldo_ops_fixed,
+};
+
 struct rpm_regulator_data {
 	const char *name;
 	u32 type;
@@ -443,10 +493,62 @@ static const struct rpm_regulator_data rpm_pma8084_regulators[] = {
 	{}
 };
 
+static const struct rpm_regulator_data rpm_pm8994_regulators[] = {
+	{ "s1", QCOM_SMD_RPM_SMPA, 1, &pm8994_ftsmps, "vdd_s1" },
+	{ "s2", QCOM_SMD_RPM_SMPA, 2, &pm8994_ftsmps, "vdd_s2" },
+	{ "s3", QCOM_SMD_RPM_SMPA, 3, &pm8994_hfsmps, "vdd_s3" },
+	{ "s4", QCOM_SMD_RPM_SMPA, 4, &pm8994_hfsmps, "vdd_s4" },
+	{ "s5", QCOM_SMD_RPM_SMPA, 5, &pm8994_hfsmps, "vdd_s5" },
+	{ "s6", QCOM_SMD_RPM_SMPA, 6, &pm8994_ftsmps, "vdd_s6" },
+	{ "s7", QCOM_SMD_RPM_SMPA, 7, &pm8994_hfsmps, "vdd_s7" },
+	{ "s8", QCOM_SMD_RPM_SMPA, 8, &pm8994_ftsmps, "vdd_s8" },
+	{ "s9", QCOM_SMD_RPM_SMPA, 9, &pm8994_ftsmps, "vdd_s9" },
+	{ "s10", QCOM_SMD_RPM_SMPA, 10, &pm8994_ftsmps, "vdd_s10" },
+	{ "s11", QCOM_SMD_RPM_SMPA, 11, &pm8994_ftsmps, "vdd_s11" },
+	{ "s12", QCOM_SMD_RPM_SMPA, 12, &pm8994_ftsmps, "vdd_s12" },
+	{ "l1", QCOM_SMD_RPM_LDOA, 1, &pm8994_nldo, "vdd_l1" },
+	{ "l2", QCOM_SMD_RPM_LDOA, 2, &pm8994_nldo, "vdd_l2_l26_l28" },
+	{ "l3", QCOM_SMD_RPM_LDOA, 3, &pm8994_nldo, "vdd_l3_l11" },
+	{ "l4", QCOM_SMD_RPM_LDOA, 4, &pm8994_nldo, "vdd_l4_l27_l31" },
+	{ "l5", QCOM_SMD_RPM_LDOA, 5, &pm8994_lnldo, "vdd_l5_l7" },
+	{ "l6", QCOM_SMD_RPM_LDOA, 6, &pm8994_pldo, "vdd_l6_l12_l32" },
+	{ "l7", QCOM_SMD_RPM_LDOA, 7, &pm8994_lnldo, "vdd_l5_l7" },
+	{ "l8", QCOM_SMD_RPM_LDOA, 8, &pm8994_pldo, "vdd_l8_l16_l30" },
+	{ "l9", QCOM_SMD_RPM_LDOA, 9, &pm8994_pldo, "vdd_l9_l10_l18_l22" },
+	{ "l10", QCOM_SMD_RPM_LDOA, 10, &pm8994_pldo, "vdd_l9_l10_l18_l22" },
+	{ "l11", QCOM_SMD_RPM_LDOA, 11, &pm8994_nldo, "vdd_l3_l11" },
+	{ "l12", QCOM_SMD_RPM_LDOA, 12, &pm8994_pldo, "vdd_l6_l12_l32" },
+	{ "l13", QCOM_SMD_RPM_LDOA, 13, &pm8994_pldo, "vdd_l13_l19_l23_l24" },
+	{ "l14", QCOM_SMD_RPM_LDOA, 14, &pm8994_pldo, "vdd_l14_l15" },
+	{ "l15", QCOM_SMD_RPM_LDOA, 15, &pm8994_pldo, "vdd_l14_l15" },
+	{ "l16", QCOM_SMD_RPM_LDOA, 16, &pm8994_pldo, "vdd_l8_l16_l30" },
+	{ "l17", QCOM_SMD_RPM_LDOA, 17, &pm8994_pldo, "vdd_l17_l29" },
+	{ "l18", QCOM_SMD_RPM_LDOA, 18, &pm8994_pldo, "vdd_l9_l10_l18_l22" },
+	{ "l19", QCOM_SMD_RPM_LDOA, 19, &pm8994_pldo, "vdd_l13_l19_l23_l24" },
+	{ "l20", QCOM_SMD_RPM_LDOA, 20, &pm8994_pldo, "vdd_l20_l21" },
+	{ "l21", QCOM_SMD_RPM_LDOA, 21, &pm8994_pldo, "vdd_l20_l21" },
+	{ "l22", QCOM_SMD_RPM_LDOA, 22, &pm8994_pldo, "vdd_l9_l10_l18_l22" },
+	{ "l23", QCOM_SMD_RPM_LDOA, 23, &pm8994_pldo, "vdd_l13_l19_l23_l24" },
+	{ "l24", QCOM_SMD_RPM_LDOA, 24, &pm8994_pldo, "vdd_l13_l19_l23_l24" },
+	{ "l25", QCOM_SMD_RPM_LDOA, 25, &pm8994_pldo, "vdd_l25" },
+	{ "l26", QCOM_SMD_RPM_LDOA, 26, &pm8994_nldo, "vdd_l2_l26_l28" },
+	{ "l27", QCOM_SMD_RPM_LDOA, 27, &pm8994_nldo, "vdd_l4_l27_l31" },
+	{ "l28", QCOM_SMD_RPM_LDOA, 28, &pm8994_nldo, "vdd_l2_l26_l28" },
+	{ "l29", QCOM_SMD_RPM_LDOA, 29, &pm8994_pldo, "vdd_l17_l29" },
+	{ "l30", QCOM_SMD_RPM_LDOA, 30, &pm8994_pldo, "vdd_l8_l16_l30" },
+	{ "l31", QCOM_SMD_RPM_LDOA, 31, &pm8994_nldo, "vdd_l4_l27_l31" },
+	{ "l32", QCOM_SMD_RPM_LDOA, 32, &pm8994_pldo, "vdd_l6_l12_l32" },
+	{ "lvs1", QCOM_SMD_RPM_VSA, 1, &pm8994_switch, "vdd_lvs1_2" },
+	{ "lvs2", QCOM_SMD_RPM_VSA, 2, &pm8994_switch, "vdd_lvs1_2" },
+
+	{}
+};
+
 static const struct of_device_id rpm_of_match[] = {
 	{ .compatible = "qcom,rpm-pm8841-regulators", .data = &rpm_pm8841_regulators },
 	{ .compatible = "qcom,rpm-pm8916-regulators", .data = &rpm_pm8916_regulators },
 	{ .compatible = "qcom,rpm-pm8941-regulators", .data = &rpm_pm8941_regulators },
+	{ .compatible = "qcom,rpm-pm8994-regulators", .data = &rpm_pm8994_regulators },
 	{ .compatible = "qcom,rpm-pma8084-regulators", .data = &rpm_pma8084_regulators },
 	{}
 };
diff --git a/drivers/regulator/rc5t583-regulator.c b/drivers/regulator/rc5t583-regulator.c
index d2e67c512195..d0f1340168b1 100644
--- a/drivers/regulator/rc5t583-regulator.c
+++ b/drivers/regulator/rc5t583-regulator.c
@@ -61,7 +61,7 @@ static int rc5t583_regulator_enable_time(struct regulator_dev *rdev)
 	return DIV_ROUND_UP(curr_uV, reg->reg_info->enable_uv_per_us);
 }
 
-static struct regulator_ops rc5t583_ops = {
+static const struct regulator_ops rc5t583_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
diff --git a/drivers/regulator/rn5t618-regulator.c b/drivers/regulator/rn5t618-regulator.c
index 9c930eb68cda..8d2819e36654 100644
--- a/drivers/regulator/rn5t618-regulator.c
+++ b/drivers/regulator/rn5t618-regulator.c
@@ -19,7 +19,7 @@
 #include <linux/regulator/driver.h>
 #include <linux/regulator/of_regulator.h>
 
-static struct regulator_ops rn5t618_reg_ops = {
+static const struct regulator_ops rn5t618_reg_ops = {
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
 	.is_enabled		= regulator_is_enabled_regmap,
diff --git a/drivers/regulator/s2mpa01.c b/drivers/regulator/s2mpa01.c
index 92f88753bfed..38ee97a085f9 100644
--- a/drivers/regulator/s2mpa01.c
+++ b/drivers/regulator/s2mpa01.c
@@ -26,6 +26,7 @@
 #define S2MPA01_REGULATOR_CNT ARRAY_SIZE(regulators)
 
 struct s2mpa01_info {
+	struct of_regulator_match rdata[S2MPA01_REGULATOR_MAX];
 	int ramp_delay24;
 	int ramp_delay3;
 	int ramp_delay5;
@@ -341,9 +342,9 @@ static int s2mpa01_pmic_probe(struct platform_device *pdev)
 {
 	struct sec_pmic_dev *iodev = dev_get_drvdata(pdev->dev.parent);
 	struct sec_platform_data *pdata = dev_get_platdata(iodev->dev);
-	struct of_regulator_match rdata[S2MPA01_REGULATOR_MAX] = { };
 	struct device_node *reg_np = NULL;
 	struct regulator_config config = { };
+	struct of_regulator_match *rdata;
 	struct s2mpa01_info *s2mpa01;
 	int i;
 
@@ -351,6 +352,7 @@ static int s2mpa01_pmic_probe(struct platform_device *pdev)
 	if (!s2mpa01)
 		return -ENOMEM;
 
+	rdata = s2mpa01->rdata;
 	for (i = 0; i < S2MPA01_REGULATOR_CNT; i++)
 		rdata[i].name = regulators[i].name;
 
diff --git a/drivers/regulator/tps65086-regulator.c b/drivers/regulator/tps65086-regulator.c
index ecb0371780af..45e96e154690 100644
--- a/drivers/regulator/tps65086-regulator.c
+++ b/drivers/regulator/tps65086-regulator.c
@@ -157,19 +157,19 @@ static struct tps65086_regulator regulators[] = {
 			   VDOA23_VID_MASK, TPS65086_LDOA3CTRL, BIT(0),
 			   tps65086_ldoa23_ranges, 0, 0),
 	TPS65086_SWITCH("SWA1", "swa1", SWA1, TPS65086_SWVTT_EN, BIT(5)),
-	TPS65086_SWITCH("SWB1", "swa2", SWB1, TPS65086_SWVTT_EN, BIT(6)),
-	TPS65086_SWITCH("SWB2", "swa3", SWB2, TPS65086_SWVTT_EN, BIT(7)),
+	TPS65086_SWITCH("SWB1", "swb1", SWB1, TPS65086_SWVTT_EN, BIT(6)),
+	TPS65086_SWITCH("SWB2", "swb2", SWB2, TPS65086_SWVTT_EN, BIT(7)),
 	TPS65086_SWITCH("VTT", "vtt", VTT, TPS65086_SWVTT_EN, BIT(4)),
 };
 
-static int tps65086_of_parse_cb(struct device_node *dev,
+static int tps65086_of_parse_cb(struct device_node *node,
 				const struct regulator_desc *desc,
 				struct regulator_config *config)
 {
 	int ret;
 
 	/* Check for 25mV step mode */
-	if (of_property_read_bool(config->of_node, "ti,regulator-step-size-25mv")) {
+	if (of_property_read_bool(node, "ti,regulator-step-size-25mv")) {
 		switch (desc->id) {
 		case BUCK1:
 		case BUCK2:
@@ -193,7 +193,7 @@ static int tps65086_of_parse_cb(struct device_node *dev,
 	}
 
 	/* Check for decay mode */
-	if (desc->id <= BUCK6 && of_property_read_bool(config->of_node, "ti,regulator-decay")) {
+	if (desc->id <= BUCK6 && of_property_read_bool(node, "ti,regulator-decay")) {
 		ret = regmap_write_bits(config->regmap,
 					regulators[desc->id].decay_reg,
 					regulators[desc->id].decay_mask,
diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c
index 2d12b9af3540..5324dc9e6d6e 100644
--- a/drivers/regulator/tps65217-regulator.c
+++ b/drivers/regulator/tps65217-regulator.c
@@ -179,7 +179,8 @@ static const struct regulator_desc regulators[] = {
 	TPS65217_REGULATOR("DCDC1", TPS65217_DCDC_1, "dcdc1",
 			   tps65217_pmic_ops, 64, TPS65217_REG_DEFDCDC1,
 			   TPS65217_DEFDCDCX_DCDC_MASK, TPS65217_ENABLE_DC1_EN,
-			   NULL, tps65217_uv1_ranges, 2, TPS65217_REG_SEQ1,
+			   NULL, tps65217_uv1_ranges,
+			   ARRAY_SIZE(tps65217_uv1_ranges), TPS65217_REG_SEQ1,
 			   TPS65217_SEQ1_DC1_SEQ_MASK),
 	TPS65217_REGULATOR("DCDC2", TPS65217_DCDC_2, "dcdc2",
 			   tps65217_pmic_ops, 64, TPS65217_REG_DEFDCDC2,
@@ -190,7 +191,8 @@ static const struct regulator_desc regulators[] = {
 	TPS65217_REGULATOR("DCDC3", TPS65217_DCDC_3, "dcdc3",
 			   tps65217_pmic_ops, 64, TPS65217_REG_DEFDCDC3,
 			   TPS65217_DEFDCDCX_DCDC_MASK, TPS65217_ENABLE_DC3_EN,
-			   NULL, tps65217_uv1_ranges, 1, TPS65217_REG_SEQ2,
+			   NULL, tps65217_uv1_ranges,
+			   ARRAY_SIZE(tps65217_uv1_ranges), TPS65217_REG_SEQ2,
 			   TPS65217_SEQ2_DC3_SEQ_MASK),
 	TPS65217_REGULATOR("LDO1", TPS65217_LDO_1, "ldo1",
 			   tps65217_pmic_ldo1_ops, 16, TPS65217_REG_DEFLDO1,
diff --git a/drivers/regulator/twl6030-regulator.c b/drivers/regulator/twl6030-regulator.c
index 4864b9d742c0..716191046a70 100644
--- a/drivers/regulator/twl6030-regulator.c
+++ b/drivers/regulator/twl6030-regulator.c
@@ -452,7 +452,7 @@ static int twl6030smps_map_voltage(struct regulator_dev *rdev, int min_uV,
 			vsel = 62;
 		else if ((min_uV > 1800000) && (min_uV <= 1900000))
 			vsel = 61;
-		else if ((min_uV > 1350000) && (min_uV <= 1800000))
+		else if ((min_uV > 1500000) && (min_uV <= 1800000))
 			vsel = 60;
 		else if ((min_uV > 1350000) && (min_uV <= 1500000))
 			vsel = 59;
diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index 10368ed8fd13..b6f5f1e1826c 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -163,7 +163,7 @@ int reset_control_reset(struct reset_control *rstc)
 	}
 
 	ret = rstc->rcdev->ops->reset(rstc->rcdev, rstc->id);
-	if (rstc->shared && !ret)
+	if (rstc->shared && ret)
 		atomic_dec(&rstc->triggered_count);
 
 	return ret;
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index c93c5a8fba32..5dc673dc9487 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -1551,12 +1551,15 @@ config RTC_DRV_MPC5121
 	  will be called rtc-mpc5121.
 
 config RTC_DRV_JZ4740
-	bool "Ingenic JZ4740 SoC"
+	tristate "Ingenic JZ4740 SoC"
 	depends on MACH_INGENIC || COMPILE_TEST
 	help
 	  If you say yes here you get support for the Ingenic JZ47xx SoCs RTC
 	  controllers.
 
+	  This driver can also be buillt as a module. If so, the module
+	  will be called rtc-jz4740.
+
 config RTC_DRV_LPC24XX
 	tristate "NXP RTC for LPC178x/18xx/408x/43xx"
 	depends on ARCH_LPC18XX || COMPILE_TEST
diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c
index 72918c1ba092..64989afffa3d 100644
--- a/drivers/rtc/rtc-jz4740.c
+++ b/drivers/rtc/rtc-jz4740.c
@@ -17,6 +17,7 @@
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/reboot.h>
@@ -294,7 +295,7 @@ static void jz4740_rtc_power_off(void)
 			     JZ_REG_RTC_RESET_COUNTER, reset_counter_ticks);
 
 	jz4740_rtc_poweroff(dev_for_power_off);
-	machine_halt();
+	kernel_halt();
 }
 
 static const struct of_device_id jz4740_rtc_of_match[] = {
@@ -302,6 +303,7 @@ static const struct of_device_id jz4740_rtc_of_match[] = {
 	{ .compatible = "ingenic,jz4780-rtc", .data = (void *)ID_JZ4780 },
 	{},
 };
+MODULE_DEVICE_TABLE(of, jz4740_rtc_of_match);
 
 static int jz4740_rtc_probe(struct platform_device *pdev)
 {
@@ -429,6 +431,7 @@ static const struct platform_device_id jz4740_rtc_ids[] = {
 	{ "jz4780-rtc", ID_JZ4780 },
 	{}
 };
+MODULE_DEVICE_TABLE(platform, jz4740_rtc_ids);
 
 static struct platform_driver jz4740_rtc_driver = {
 	.probe	 = jz4740_rtc_probe,
@@ -440,4 +443,9 @@ static struct platform_driver jz4740_rtc_driver = {
 	.id_table = jz4740_rtc_ids,
 };
 
-builtin_platform_driver(jz4740_rtc_driver);
+module_platform_driver(jz4740_rtc_driver);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RTC driver for the JZ4740 SoC\n");
+MODULE_ALIAS("platform:jz4740-rtc");
diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index 9f16ea6964ec..152de6817875 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -300,13 +300,6 @@ static void scm_blk_request(struct request_queue *rq)
 	struct request *req;
 
 	while ((req = blk_peek_request(rq))) {
-		if (req->cmd_type != REQ_TYPE_FS) {
-			blk_start_request(req);
-			blk_dump_rq_flags(req, KMSG_COMPONENT " bad request");
-			__blk_end_request_all(req, -EIO);
-			continue;
-		}
-
 		if (!scm_permit_request(bdev, req))
 			goto out;
 
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 75f820ca17b7..27ff38f839fc 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -1583,7 +1583,7 @@ out:
 int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 {
 	struct zfcp_qdio *qdio = wka_port->adapter->qdio;
-	struct zfcp_fsf_req *req = NULL;
+	struct zfcp_fsf_req *req;
 	int retval = -EIO;
 
 	spin_lock_irq(&qdio->req_q_lock);
@@ -1612,7 +1612,7 @@ int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 		zfcp_fsf_req_free(req);
 out:
 	spin_unlock_irq(&qdio->req_q_lock);
-	if (req && !IS_ERR(req))
+	if (!retval)
 		zfcp_dbf_rec_run_wka("fsowp_1", wka_port, req->req_id);
 	return retval;
 }
@@ -1638,7 +1638,7 @@ static void zfcp_fsf_close_wka_port_handler(struct zfcp_fsf_req *req)
 int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 {
 	struct zfcp_qdio *qdio = wka_port->adapter->qdio;
-	struct zfcp_fsf_req *req = NULL;
+	struct zfcp_fsf_req *req;
 	int retval = -EIO;
 
 	spin_lock_irq(&qdio->req_q_lock);
@@ -1667,7 +1667,7 @@ int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 		zfcp_fsf_req_free(req);
 out:
 	spin_unlock_irq(&qdio->req_q_lock);
-	if (req && !IS_ERR(req))
+	if (!retval)
 		zfcp_dbf_rec_run_wka("fscwp_1", wka_port, req->req_id);
 	return retval;
 }
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 07ffdbb5107f..0678cf714c0e 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -330,6 +330,7 @@ static struct scsi_host_template zfcp_scsi_host_template = {
 	.module			 = THIS_MODULE,
 	.name			 = "zfcp",
 	.queuecommand		 = zfcp_scsi_queuecommand,
+	.eh_timed_out		 = fc_eh_timed_out,
 	.eh_abort_handler	 = zfcp_scsi_eh_abort_handler,
 	.eh_device_reset_handler = zfcp_scsi_eh_device_reset_handler,
 	.eh_target_reset_handler = zfcp_scsi_eh_target_reset_handler,
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index a4f6b0d95515..d4023bf1e739 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -18,6 +18,7 @@ config SCSI
 	depends on BLOCK
 	select SCSI_DMA if HAS_DMA
 	select SG_POOL
+	select BLK_SCSI_REQUEST
 	---help---
 	  If you want to use a SCSI hard disk, SCSI tape drive, SCSI CD-ROM or
 	  any other SCSI device under Linux, say Y and make sure that you know
diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
index 4f5ca794bb71..acc33440bca0 100644
--- a/drivers/scsi/NCR5380.c
+++ b/drivers/scsi/NCR5380.c
@@ -96,17 +96,6 @@
  * of chips.  To use it, you write an architecture specific functions
  * and macros and include this file in your driver.
  *
- * These macros control options :
- * AUTOSENSE - if defined, REQUEST SENSE will be performed automatically
- * for commands that return with a CHECK CONDITION status.
- *
- * DIFFERENTIAL - if defined, NCR53c81 chips will use external differential
- * transceivers.
- *
- * PSEUDO_DMA - if defined, PSEUDO DMA is used during the data transfer phases.
- *
- * REAL_DMA - if defined, REAL DMA is used during the data transfer phases.
- *
  * These macros MUST be defined :
  *
  * NCR5380_read(register)  - read from the specified register
@@ -347,7 +336,7 @@ static void NCR5380_print_phase(struct Scsi_Host *instance)
 #endif
 
 /**
- * NCR58380_info - report driver and host information
+ * NCR5380_info - report driver and host information
  * @instance: relevant scsi host instance
  *
  * For use as the host template info() handler.
@@ -360,33 +349,6 @@ static const char *NCR5380_info(struct Scsi_Host *instance)
 	return hostdata->info;
 }
 
-static void prepare_info(struct Scsi_Host *instance)
-{
-	struct NCR5380_hostdata *hostdata = shost_priv(instance);
-
-	snprintf(hostdata->info, sizeof(hostdata->info),
-	         "%s, irq %d, "
-		 "io_port 0x%lx, base 0x%lx, "
-	         "can_queue %d, cmd_per_lun %d, "
-	         "sg_tablesize %d, this_id %d, "
-	         "flags { %s%s%s}, "
-	         "options { %s} ",
-	         instance->hostt->name, instance->irq,
-		 hostdata->io_port, hostdata->base,
-	         instance->can_queue, instance->cmd_per_lun,
-	         instance->sg_tablesize, instance->this_id,
-	         hostdata->flags & FLAG_DMA_FIXUP     ? "DMA_FIXUP "     : "",
-	         hostdata->flags & FLAG_NO_PSEUDO_DMA ? "NO_PSEUDO_DMA " : "",
-	         hostdata->flags & FLAG_TOSHIBA_DELAY ? "TOSHIBA_DELAY "  : "",
-#ifdef DIFFERENTIAL
-	         "DIFFERENTIAL "
-#endif
-#ifdef PARITY
-	         "PARITY "
-#endif
-	         "");
-}
-
 /**
  * NCR5380_init - initialise an NCR5380
  * @instance: adapter to configure
@@ -436,7 +398,14 @@ static int NCR5380_init(struct Scsi_Host *instance, int flags)
 	if (!hostdata->work_q)
 		return -ENOMEM;
 
-	prepare_info(instance);
+	snprintf(hostdata->info, sizeof(hostdata->info),
+		"%s, irq %d, io_port 0x%lx, base 0x%lx, can_queue %d, cmd_per_lun %d, sg_tablesize %d, this_id %d, flags { %s%s%s}",
+		instance->hostt->name, instance->irq, hostdata->io_port,
+		hostdata->base, instance->can_queue, instance->cmd_per_lun,
+		instance->sg_tablesize, instance->this_id,
+		hostdata->flags & FLAG_DMA_FIXUP     ? "DMA_FIXUP "     : "",
+		hostdata->flags & FLAG_NO_PSEUDO_DMA ? "NO_PSEUDO_DMA " : "",
+		hostdata->flags & FLAG_TOSHIBA_DELAY ? "TOSHIBA_DELAY " : "");
 
 	NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
 	NCR5380_write(MODE_REG, MR_BASE);
@@ -622,8 +591,9 @@ static inline void maybe_release_dma_irq(struct Scsi_Host *instance)
 	    list_empty(&hostdata->unissued) &&
 	    list_empty(&hostdata->autosense) &&
 	    !hostdata->connected &&
-	    !hostdata->selecting)
+	    !hostdata->selecting) {
 		NCR5380_release_dma_irq(instance);
+	}
 }
 
 /**
@@ -962,6 +932,7 @@ static irqreturn_t __maybe_unused NCR5380_intr(int irq, void *dev_id)
 
 static struct scsi_cmnd *NCR5380_select(struct Scsi_Host *instance,
                                         struct scsi_cmnd *cmd)
+	__releases(&hostdata->lock) __acquires(&hostdata->lock)
 {
 	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	unsigned char tmp[3], phase;
@@ -1194,8 +1165,16 @@ static struct scsi_cmnd *NCR5380_select(struct Scsi_Host *instance,
 	data = tmp;
 	phase = PHASE_MSGOUT;
 	NCR5380_transfer_pio(instance, &phase, &len, &data);
+	if (len) {
+		NCR5380_write(INITIATOR_COMMAND_REG, ICR_BASE);
+		cmd->result = DID_ERROR << 16;
+		complete_cmd(instance, cmd);
+		dsprintk(NDEBUG_SELECTION, instance, "IDENTIFY message transfer failed\n");
+		cmd = NULL;
+		goto out;
+	}
+
 	dsprintk(NDEBUG_SELECTION, instance, "nexus established.\n");
-	/* XXX need to handle errors here */
 
 	hostdata->connected = cmd;
 	hostdata->busy[cmd->device->id] |= 1 << cmd->device->lun;
@@ -1654,6 +1633,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance,
  */
 
 static void NCR5380_information_transfer(struct Scsi_Host *instance)
+	__releases(&hostdata->lock) __acquires(&hostdata->lock)
 {
 	struct NCR5380_hostdata *hostdata = shost_priv(instance);
 	unsigned char msgout = NOP;
diff --git a/drivers/scsi/NCR5380.h b/drivers/scsi/NCR5380.h
index 51a3567a6fb2..d78f0957d865 100644
--- a/drivers/scsi/NCR5380.h
+++ b/drivers/scsi/NCR5380.h
@@ -81,11 +81,7 @@
 #define ICR_ASSERT_ATN		0x02	/* rw Set to assert ATN */
 #define ICR_ASSERT_DATA		0x01	/* rw SCSI_DATA_REG is asserted */
 
-#ifdef DIFFERENTIAL
-#define ICR_BASE		ICR_DIFF_ENABLE
-#else
 #define ICR_BASE		0
-#endif
 
 #define MODE_REG		2
 /*
@@ -102,11 +98,7 @@
 #define MR_DMA_MODE		0x02	/* rw DMA / pseudo DMA mode */
 #define MR_ARBITRATE		0x01	/* rw start arbitration */
 
-#ifdef PARITY
-#define MR_BASE			MR_ENABLE_PAR_CHECK
-#else
 #define MR_BASE			0
-#endif
 
 #define TARGET_COMMAND_REG	3
 #define TCR_LAST_BYTE_SENT	0x80	/* ro DMA done */
@@ -174,11 +166,7 @@
 #define CSR_SCSI_BUF_RDY       0x02	/* ro  SCSI buffer read */
 #define CSR_GATED_53C80_IRQ    0x01	/* ro  Last block xferred */
 
-#if 0
-#define CSR_BASE CSR_SCSI_BUFF_INTR | CSR_53C80_INTR
-#else
 #define CSR_BASE CSR_53C80_INTR
-#endif
 
 /* Note : PHASE_* macros are based on the values of the STATUS register */
 #define PHASE_MASK 	(SR_MSG | SR_CD | SR_IO)
@@ -234,11 +222,9 @@ struct NCR5380_hostdata {
 	unsigned char id_higher_mask;		/* All bits above id_mask */
 	unsigned char last_message;		/* Last Message Out */
 	unsigned long region_size;		/* Size of address/port range */
-	char info[256];
+	char info[168];				/* Host banner message */
 };
 
-#ifdef __KERNEL__
-
 struct NCR5380_cmd {
 	struct list_head list;
 };
@@ -331,5 +317,4 @@ static inline int NCR5380_dma_residual_none(struct NCR5380_hostdata *hostdata)
 	return 0;
 }
 
-#endif				/* __KERNEL__ */
 #endif				/* NCR5380_H */
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index 1ee7c654f7b8..907f1e80665b 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -6,7 +6,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -22,6 +23,11 @@
  * along with this program; see the file COPYING.  If not, write to
  * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
  *
+ * Module Name:
+ *  aachba.c
+ *
+ * Abstract: Contains Interfaces to manage IOs.
+ *
  */
 
 #include <linux/kernel.h>
@@ -62,6 +68,7 @@
 #define SENCODE_END_OF_DATA			0x00
 #define SENCODE_BECOMING_READY			0x04
 #define SENCODE_INIT_CMD_REQUIRED		0x04
+#define SENCODE_UNRECOVERED_READ_ERROR		0x11
 #define SENCODE_PARAM_LIST_LENGTH_ERROR		0x1A
 #define SENCODE_INVALID_COMMAND			0x20
 #define SENCODE_LBA_OUT_OF_RANGE		0x21
@@ -106,6 +113,8 @@
 #define ASENCODE_LUN_FAILED_SELF_CONFIG		0x00
 #define ASENCODE_OVERLAPPED_COMMAND		0x00
 
+#define AAC_STAT_GOOD (DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD)
+
 #define BYTE0(x) (unsigned char)(x)
 #define BYTE1(x) (unsigned char)((x) >> 8)
 #define BYTE2(x) (unsigned char)((x) >> 16)
@@ -164,46 +173,56 @@ struct inquiry_data {
 };
 
 /* Added for VPD 0x83 */
-typedef struct {
-	u8 CodeSet:4;	/* VPD_CODE_SET */
-	u8 Reserved:4;
-	u8 IdentifierType:4;	/* VPD_IDENTIFIER_TYPE */
-	u8 Reserved2:4;
-	u8 Reserved3;
-	u8 IdentifierLength;
-	u8 VendId[8];
-	u8 ProductId[16];
-	u8 SerialNumber[8];	/* SN in ASCII */
-
-} TVPD_ID_Descriptor_Type_1;
+struct  tvpd_id_descriptor_type_1 {
+	u8 codeset:4;		/* VPD_CODE_SET */
+	u8 reserved:4;
+	u8 identifiertype:4;	/* VPD_IDENTIFIER_TYPE */
+	u8 reserved2:4;
+	u8 reserved3;
+	u8 identifierlength;
+	u8 venid[8];
+	u8 productid[16];
+	u8 serialnumber[8];	/* SN in ASCII */
 
-typedef struct {
-	u8 CodeSet:4;	/* VPD_CODE_SET */
-	u8 Reserved:4;
-	u8 IdentifierType:4;	/* VPD_IDENTIFIER_TYPE */
-	u8 Reserved2:4;
-	u8 Reserved3;
-	u8 IdentifierLength;
-	struct TEU64Id {
+};
+
+struct tvpd_id_descriptor_type_2 {
+	u8 codeset:4;		/* VPD_CODE_SET */
+	u8 reserved:4;
+	u8 identifiertype:4;	/* VPD_IDENTIFIER_TYPE */
+	u8 reserved2:4;
+	u8 reserved3;
+	u8 identifierlength;
+	struct teu64id {
 		u32 Serial;
 		 /* The serial number supposed to be 40 bits,
 		  * bit we only support 32, so make the last byte zero. */
-		u8 Reserved;
-		u8 VendId[3];
-	} EU64Id;
+		u8 reserved;
+		u8 venid[3];
+	} eu64id;
 
-} TVPD_ID_Descriptor_Type_2;
+};
 
-typedef struct {
+struct tvpd_id_descriptor_type_3 {
+	u8 codeset : 4;          /* VPD_CODE_SET */
+	u8 reserved : 4;
+	u8 identifiertype : 4;   /* VPD_IDENTIFIER_TYPE */
+	u8 reserved2 : 4;
+	u8 reserved3;
+	u8 identifierlength;
+	u8 Identifier[16];
+};
+
+struct tvpd_page83 {
 	u8 DeviceType:5;
 	u8 DeviceTypeQualifier:3;
 	u8 PageCode;
-	u8 Reserved;
+	u8 reserved;
 	u8 PageLength;
-	TVPD_ID_Descriptor_Type_1 IdDescriptorType1;
-	TVPD_ID_Descriptor_Type_2 IdDescriptorType2;
-
-} TVPD_Page83;
+	struct tvpd_id_descriptor_type_1 type1;
+	struct tvpd_id_descriptor_type_2 type2;
+	struct tvpd_id_descriptor_type_3 type3;
+};
 
 /*
  *              M O D U L E   G L O B A L S
@@ -214,9 +233,13 @@ static long aac_build_sg64(struct scsi_cmnd *scsicmd, struct sgmap64 *psg);
 static long aac_build_sgraw(struct scsi_cmnd *scsicmd, struct sgmapraw *psg);
 static long aac_build_sgraw2(struct scsi_cmnd *scsicmd,
 				struct aac_raw_io2 *rio2, int sg_max);
+static long aac_build_sghba(struct scsi_cmnd *scsicmd,
+				struct aac_hba_cmd_req *hbacmd,
+				int sg_max, u64 sg_address);
 static int aac_convert_sgraw2(struct aac_raw_io2 *rio2,
 				int pages, int nseg, int nseg_new);
 static int aac_send_srb_fib(struct scsi_cmnd* scsicmd);
+static int aac_send_hba_fib(struct scsi_cmnd *scsicmd);
 #ifdef AAC_DETAILED_STATUS_INFO
 static char *aac_get_status_string(u32 status);
 #endif
@@ -327,7 +350,7 @@ static inline int aac_valid_context(struct scsi_cmnd *scsicmd,
 	}
 	scsicmd->SCp.phase = AAC_OWNER_MIDLEVEL;
 	device = scsicmd->device;
-	if (unlikely(!device || !scsi_device_online(device))) {
+	if (unlikely(!device)) {
 		dprintk((KERN_WARNING "aac_valid_context: scsi device corrupt\n"));
 		aac_fib_complete(fibptr);
 		return 0;
@@ -473,16 +496,26 @@ int aac_get_containers(struct aac_dev *dev)
 
 	if (maximum_num_containers < MAXIMUM_NUM_CONTAINERS)
 		maximum_num_containers = MAXIMUM_NUM_CONTAINERS;
-	fsa_dev_ptr = kzalloc(sizeof(*fsa_dev_ptr) * maximum_num_containers,
-			GFP_KERNEL);
-	if (!fsa_dev_ptr)
-		return -ENOMEM;
+	if (dev->fsa_dev == NULL ||
+		dev->maximum_num_containers != maximum_num_containers) {
+
+		fsa_dev_ptr = dev->fsa_dev;
+
+		dev->fsa_dev = kcalloc(maximum_num_containers,
+					sizeof(*fsa_dev_ptr), GFP_KERNEL);
+
+		kfree(fsa_dev_ptr);
+		fsa_dev_ptr = NULL;
 
-	dev->fsa_dev = fsa_dev_ptr;
-	dev->maximum_num_containers = maximum_num_containers;
 
-	for (index = 0; index < dev->maximum_num_containers; ) {
-		fsa_dev_ptr[index].devname[0] = '\0';
+		if (!dev->fsa_dev)
+			return -ENOMEM;
+
+		dev->maximum_num_containers = maximum_num_containers;
+	}
+	for (index = 0; index < dev->maximum_num_containers; index++) {
+		dev->fsa_dev[index].devname[0] = '\0';
+		dev->fsa_dev[index].valid = 0;
 
 		status = aac_probe_container(dev, index);
 
@@ -490,12 +523,6 @@ int aac_get_containers(struct aac_dev *dev)
 			printk(KERN_WARNING "aac_get_containers: SendFIB failed.\n");
 			break;
 		}
-
-		/*
-		 *	If there are no more containers, then stop asking.
-		 */
-		if (++index >= status)
-			break;
 	}
 	return status;
 }
@@ -602,6 +629,7 @@ static void _aac_probe_container2(void * context, struct fib * fibptr)
 	struct fsa_dev_info *fsa_dev_ptr;
 	int (*callback)(struct scsi_cmnd *);
 	struct scsi_cmnd * scsicmd = (struct scsi_cmnd *)context;
+	int i;
 
 
 	if (!aac_valid_context(scsicmd, fibptr))
@@ -624,6 +652,10 @@ static void _aac_probe_container2(void * context, struct fib * fibptr)
 				fsa_dev_ptr->block_size =
 					le32_to_cpu(dresp->mnt[0].fileinfo.bdevinfo.block_size);
 			}
+			for (i = 0; i < 16; i++)
+				fsa_dev_ptr->identifier[i] =
+					dresp->mnt[0].fileinfo.bdevinfo
+								.identifier[i];
 			fsa_dev_ptr->valid = 1;
 			/* sense_key holds the current state of the spin-up */
 			if (dresp->mnt[0].state & cpu_to_le32(FSCS_NOT_READY))
@@ -918,6 +950,28 @@ static void setinqstr(struct aac_dev *dev, void *data, int tindex)
 	inqstrcpy ("V1.0", str->prl);
 }
 
+static void build_vpd83_type3(struct tvpd_page83 *vpdpage83data,
+		struct aac_dev *dev, struct scsi_cmnd *scsicmd)
+{
+	int container;
+
+	vpdpage83data->type3.codeset = 1;
+	vpdpage83data->type3.identifiertype = 3;
+	vpdpage83data->type3.identifierlength = sizeof(vpdpage83data->type3)
+			- 4;
+
+	for (container = 0; container < dev->maximum_num_containers;
+			container++) {
+
+		if (scmd_id(scsicmd) == container) {
+			memcpy(vpdpage83data->type3.Identifier,
+					dev->fsa_dev[container].identifier,
+					16);
+			break;
+		}
+	}
+}
+
 static void get_container_serial_callback(void *context, struct fib * fibptr)
 {
 	struct aac_get_serial_resp * get_serial_reply;
@@ -935,39 +989,47 @@ static void get_container_serial_callback(void *context, struct fib * fibptr)
 		/*Check to see if it's for VPD 0x83 or 0x80 */
 		if (scsicmd->cmnd[2] == 0x83) {
 			/* vpd page 0x83 - Device Identification Page */
+			struct aac_dev *dev;
 			int i;
-			TVPD_Page83 VPDPage83Data;
+			struct tvpd_page83 vpdpage83data;
+
+			dev = (struct aac_dev *)scsicmd->device->host->hostdata;
 
-			memset(((u8 *)&VPDPage83Data), 0,
-			       sizeof(VPDPage83Data));
+			memset(((u8 *)&vpdpage83data), 0,
+			       sizeof(vpdpage83data));
 
 			/* DIRECT_ACCESS_DEVIC */
-			VPDPage83Data.DeviceType = 0;
+			vpdpage83data.DeviceType = 0;
 			/* DEVICE_CONNECTED */
-			VPDPage83Data.DeviceTypeQualifier = 0;
+			vpdpage83data.DeviceTypeQualifier = 0;
 			/* VPD_DEVICE_IDENTIFIERS */
-			VPDPage83Data.PageCode = 0x83;
-			VPDPage83Data.Reserved = 0;
-			VPDPage83Data.PageLength =
-				sizeof(VPDPage83Data.IdDescriptorType1) +
-				sizeof(VPDPage83Data.IdDescriptorType2);
+			vpdpage83data.PageCode = 0x83;
+			vpdpage83data.reserved = 0;
+			vpdpage83data.PageLength =
+				sizeof(vpdpage83data.type1) +
+				sizeof(vpdpage83data.type2);
+
+			/* VPD 83 Type 3 is not supported for ARC */
+			if (dev->sa_firmware)
+				vpdpage83data.PageLength +=
+				sizeof(vpdpage83data.type3);
 
 			/* T10 Vendor Identifier Field Format */
-			/* VpdCodeSetAscii */
-			VPDPage83Data.IdDescriptorType1.CodeSet = 2;
+			/* VpdcodesetAscii */
+			vpdpage83data.type1.codeset = 2;
 			/* VpdIdentifierTypeVendorId */
-			VPDPage83Data.IdDescriptorType1.IdentifierType = 1;
-			VPDPage83Data.IdDescriptorType1.IdentifierLength =
-				sizeof(VPDPage83Data.IdDescriptorType1) - 4;
+			vpdpage83data.type1.identifiertype = 1;
+			vpdpage83data.type1.identifierlength =
+				sizeof(vpdpage83data.type1) - 4;
 
 			/* "ADAPTEC " for adaptec */
-			memcpy(VPDPage83Data.IdDescriptorType1.VendId,
+			memcpy(vpdpage83data.type1.venid,
 				"ADAPTEC ",
-				sizeof(VPDPage83Data.IdDescriptorType1.VendId));
-			memcpy(VPDPage83Data.IdDescriptorType1.ProductId,
+				sizeof(vpdpage83data.type1.venid));
+			memcpy(vpdpage83data.type1.productid,
 				"ARRAY           ",
 				sizeof(
-				VPDPage83Data.IdDescriptorType1.ProductId));
+				vpdpage83data.type1.productid));
 
 			/* Convert to ascii based serial number.
 			 * The LSB is the the end.
@@ -976,32 +1038,41 @@ static void get_container_serial_callback(void *context, struct fib * fibptr)
 				u8 temp =
 					(u8)((get_serial_reply->uid >> ((7 - i) * 4)) & 0xF);
 				if (temp  > 0x9) {
-					VPDPage83Data.IdDescriptorType1.SerialNumber[i] =
+					vpdpage83data.type1.serialnumber[i] =
 							'A' + (temp - 0xA);
 				} else {
-					VPDPage83Data.IdDescriptorType1.SerialNumber[i] =
+					vpdpage83data.type1.serialnumber[i] =
 							'0' + temp;
 				}
 			}
 
 			/* VpdCodeSetBinary */
-			VPDPage83Data.IdDescriptorType2.CodeSet = 1;
-			/* VpdIdentifierTypeEUI64 */
-			VPDPage83Data.IdDescriptorType2.IdentifierType = 2;
-			VPDPage83Data.IdDescriptorType2.IdentifierLength =
-				sizeof(VPDPage83Data.IdDescriptorType2) - 4;
+			vpdpage83data.type2.codeset = 1;
+			/* VpdidentifiertypeEUI64 */
+			vpdpage83data.type2.identifiertype = 2;
+			vpdpage83data.type2.identifierlength =
+				sizeof(vpdpage83data.type2) - 4;
 
-			VPDPage83Data.IdDescriptorType2.EU64Id.VendId[0] = 0xD0;
-			VPDPage83Data.IdDescriptorType2.EU64Id.VendId[1] = 0;
-			VPDPage83Data.IdDescriptorType2.EU64Id.VendId[2] = 0;
+			vpdpage83data.type2.eu64id.venid[0] = 0xD0;
+			vpdpage83data.type2.eu64id.venid[1] = 0;
+			vpdpage83data.type2.eu64id.venid[2] = 0;
 
-			VPDPage83Data.IdDescriptorType2.EU64Id.Serial =
+			vpdpage83data.type2.eu64id.Serial =
 							get_serial_reply->uid;
-			VPDPage83Data.IdDescriptorType2.EU64Id.Reserved = 0;
+			vpdpage83data.type2.eu64id.reserved = 0;
+
+			/*
+			 * VpdIdentifierTypeFCPHName
+			 * VPD 0x83 Type 3 not supported for ARC
+			 */
+			if (dev->sa_firmware) {
+				build_vpd83_type3(&vpdpage83data,
+						dev, scsicmd);
+			}
 
 			/* Move the inquiry data to the response buffer. */
-			scsi_sg_copy_from_buffer(scsicmd, &VPDPage83Data,
-						 sizeof(VPDPage83Data));
+			scsi_sg_copy_from_buffer(scsicmd, &vpdpage83data,
+						 sizeof(vpdpage83data));
 		} else {
 			/* It must be for VPD 0x80 */
 			char sp[13];
@@ -1144,7 +1215,9 @@ static int aac_read_raw_io(struct fib * fib, struct scsi_cmnd * cmd, u64 lba, u3
 	long ret;
 
 	aac_fib_init(fib);
-	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE2 && !dev->sync_mode) {
+	if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE2 ||
+		dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) &&
+		!dev->sync_mode) {
 		struct aac_raw_io2 *readcmd2;
 		readcmd2 = (struct aac_raw_io2 *) fib_data(fib);
 		memset(readcmd2, 0, sizeof(struct aac_raw_io2));
@@ -1270,7 +1343,9 @@ static int aac_write_raw_io(struct fib * fib, struct scsi_cmnd * cmd, u64 lba, u
 	long ret;
 
 	aac_fib_init(fib);
-	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE2 && !dev->sync_mode) {
+	if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE2 ||
+		dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) &&
+		!dev->sync_mode) {
 		struct aac_raw_io2 *writecmd2;
 		writecmd2 = (struct aac_raw_io2 *) fib_data(fib);
 		memset(writecmd2, 0, sizeof(struct aac_raw_io2));
@@ -1435,6 +1510,52 @@ static struct aac_srb * aac_scsi_common(struct fib * fib, struct scsi_cmnd * cmd
 	return srbcmd;
 }
 
+static struct aac_hba_cmd_req *aac_construct_hbacmd(struct fib *fib,
+							struct scsi_cmnd *cmd)
+{
+	struct aac_hba_cmd_req *hbacmd;
+	struct aac_dev *dev;
+	int bus, target;
+	u64 address;
+
+	dev = (struct aac_dev *)cmd->device->host->hostdata;
+
+	hbacmd = (struct aac_hba_cmd_req *)fib->hw_fib_va;
+	memset(hbacmd, 0, 96);	/* sizeof(*hbacmd) is not necessary */
+	/* iu_type is a parameter of aac_hba_send */
+	switch (cmd->sc_data_direction) {
+	case DMA_TO_DEVICE:
+		hbacmd->byte1 = 2;
+		break;
+	case DMA_FROM_DEVICE:
+	case DMA_BIDIRECTIONAL:
+		hbacmd->byte1 = 1;
+		break;
+	case DMA_NONE:
+	default:
+		break;
+	}
+	hbacmd->lun[1] = cpu_to_le32(cmd->device->lun);
+
+	bus = aac_logical_to_phys(scmd_channel(cmd));
+	target = scmd_id(cmd);
+	hbacmd->it_nexus = dev->hba_map[bus][target].rmw_nexus;
+
+	/* we fill in reply_qid later in aac_src_deliver_message */
+	/* we fill in iu_type, request_id later in aac_hba_send */
+	/* we fill in emb_data_desc_count later in aac_build_sghba */
+
+	memcpy(hbacmd->cdb, cmd->cmnd, cmd->cmd_len);
+	hbacmd->data_length = cpu_to_le32(scsi_bufflen(cmd));
+
+	address = (u64)fib->hw_error_pa;
+	hbacmd->error_ptr_hi = cpu_to_le32((u32)(address >> 32));
+	hbacmd->error_ptr_lo = cpu_to_le32((u32)(address & 0xffffffff));
+	hbacmd->error_length = cpu_to_le32(FW_ERROR_BUFFER_SIZE);
+
+	return hbacmd;
+}
+
 static void aac_srb_callback(void *context, struct fib * fibptr);
 
 static int aac_scsi_64(struct fib * fib, struct scsi_cmnd * cmd)
@@ -1505,11 +1626,243 @@ static int aac_scsi_32_64(struct fib * fib, struct scsi_cmnd * cmd)
 	return aac_scsi_32(fib, cmd);
 }
 
+static int aac_adapter_hba(struct fib *fib, struct scsi_cmnd *cmd)
+{
+	struct aac_hba_cmd_req *hbacmd = aac_construct_hbacmd(fib, cmd);
+	struct aac_dev *dev;
+	long ret;
+
+	dev = (struct aac_dev *)cmd->device->host->hostdata;
+
+	ret = aac_build_sghba(cmd, hbacmd,
+		dev->scsi_host_ptr->sg_tablesize, (u64)fib->hw_sgl_pa);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 *	Now send the HBA command to the adapter
+	 */
+	fib->hbacmd_size = 64 + le32_to_cpu(hbacmd->emb_data_desc_count) *
+		sizeof(struct aac_hba_sgl);
+
+	return aac_hba_send(HBA_IU_TYPE_SCSI_CMD_REQ, fib,
+				  (fib_callback) aac_hba_callback,
+				  (void *) cmd);
+}
+
+int aac_issue_bmic_identify(struct aac_dev *dev, u32 bus, u32 target)
+{
+	struct fib *fibptr;
+	struct aac_srb *srbcmd;
+	struct sgmap64 *sg64;
+	struct aac_ciss_identify_pd *identify_resp;
+	dma_addr_t addr;
+	u32 vbus, vid;
+	u16 fibsize, datasize;
+	int rcode = -ENOMEM;
+
+
+	fibptr = aac_fib_alloc(dev);
+	if (!fibptr)
+		goto out;
+
+	fibsize = sizeof(struct aac_srb) -
+			sizeof(struct sgentry) + sizeof(struct sgentry64);
+	datasize = sizeof(struct aac_ciss_identify_pd);
+
+	identify_resp =  pci_alloc_consistent(dev->pdev, datasize, &addr);
+
+	if (!identify_resp)
+		goto fib_free_ptr;
+
+	vbus = (u32)le16_to_cpu(dev->supplement_adapter_info.VirtDeviceBus);
+	vid = (u32)le16_to_cpu(dev->supplement_adapter_info.VirtDeviceTarget);
+
+	aac_fib_init(fibptr);
+
+	srbcmd = (struct aac_srb *) fib_data(fibptr);
+	srbcmd->function = cpu_to_le32(SRBF_ExecuteScsi);
+	srbcmd->channel  = cpu_to_le32(vbus);
+	srbcmd->id       = cpu_to_le32(vid);
+	srbcmd->lun      = 0;
+	srbcmd->flags    = cpu_to_le32(SRB_DataIn);
+	srbcmd->timeout  = cpu_to_le32(10);
+	srbcmd->retry_limit = 0;
+	srbcmd->cdb_size = cpu_to_le32(12);
+	srbcmd->count = cpu_to_le32(datasize);
+
+	memset(srbcmd->cdb, 0, sizeof(srbcmd->cdb));
+	srbcmd->cdb[0] = 0x26;
+	srbcmd->cdb[2] = (u8)((AAC_MAX_LUN + target) & 0x00FF);
+	srbcmd->cdb[6] = CISS_IDENTIFY_PHYSICAL_DEVICE;
+
+	sg64 = (struct sgmap64 *)&srbcmd->sg;
+	sg64->count = cpu_to_le32(1);
+	sg64->sg[0].addr[1] = cpu_to_le32((u32)(((addr) >> 16) >> 16));
+	sg64->sg[0].addr[0] = cpu_to_le32((u32)(addr & 0xffffffff));
+	sg64->sg[0].count = cpu_to_le32(datasize);
+
+	rcode = aac_fib_send(ScsiPortCommand64,
+		fibptr, fibsize, FsaNormal, 1, 1, NULL, NULL);
+
+	if (identify_resp->current_queue_depth_limit <= 0 ||
+		identify_resp->current_queue_depth_limit > 32)
+		dev->hba_map[bus][target].qd_limit = 32;
+	else
+		dev->hba_map[bus][target].qd_limit =
+			identify_resp->current_queue_depth_limit;
+
+	pci_free_consistent(dev->pdev, datasize, (void *)identify_resp, addr);
+
+	aac_fib_complete(fibptr);
+
+fib_free_ptr:
+	aac_fib_free(fibptr);
+out:
+	return rcode;
+}
+
+/**
+ *	aac_update hba_map()-	update current hba map with data from FW
+ *	@dev:	aac_dev structure
+ *	@phys_luns: FW information from report phys luns
+ *
+ *	Update our hba map with the information gathered from the FW
+ */
+void aac_update_hba_map(struct aac_dev *dev,
+		struct aac_ciss_phys_luns_resp *phys_luns, int rescan)
+{
+	/* ok and extended reporting */
+	u32 lun_count, nexus;
+	u32 i, bus, target;
+	u8 expose_flag, attribs;
+	u8 devtype;
+
+	lun_count = ((phys_luns->list_length[0] << 24)
+			+ (phys_luns->list_length[1] << 16)
+			+ (phys_luns->list_length[2] << 8)
+			+ (phys_luns->list_length[3])) / 24;
+
+	for (i = 0; i < lun_count; ++i) {
+
+		bus = phys_luns->lun[i].level2[1] & 0x3f;
+		target = phys_luns->lun[i].level2[0];
+		expose_flag = phys_luns->lun[i].bus >> 6;
+		attribs = phys_luns->lun[i].node_ident[9];
+		nexus = *((u32 *) &phys_luns->lun[i].node_ident[12]);
+
+		if (bus >= AAC_MAX_BUSES || target >= AAC_MAX_TARGETS)
+			continue;
+
+		dev->hba_map[bus][target].expose = expose_flag;
+
+		if (expose_flag != 0) {
+			devtype = AAC_DEVTYPE_RAID_MEMBER;
+			goto update_devtype;
+		}
+
+		if (nexus != 0 && (attribs & 8)) {
+			devtype = AAC_DEVTYPE_NATIVE_RAW;
+			dev->hba_map[bus][target].rmw_nexus =
+					nexus;
+		} else
+			devtype = AAC_DEVTYPE_ARC_RAW;
+
+		if (devtype != AAC_DEVTYPE_NATIVE_RAW)
+			goto update_devtype;
+
+		if (aac_issue_bmic_identify(dev, bus, target) < 0)
+			dev->hba_map[bus][target].qd_limit = 32;
+
+update_devtype:
+		if (rescan == AAC_INIT)
+			dev->hba_map[bus][target].devtype = devtype;
+		else
+			dev->hba_map[bus][target].new_devtype = devtype;
+	}
+}
+
+/**
+ *	aac_report_phys_luns()	Process topology change
+ *	@dev:		aac_dev structure
+ *	@fibptr:	fib pointer
+ *
+ *	Execute a CISS REPORT PHYS LUNS and process the results into
+ *	the current hba_map.
+ */
+int aac_report_phys_luns(struct aac_dev *dev, struct fib *fibptr, int rescan)
+{
+	int fibsize, datasize;
+	struct aac_ciss_phys_luns_resp *phys_luns;
+	struct aac_srb *srbcmd;
+	struct sgmap64 *sg64;
+	dma_addr_t addr;
+	u32 vbus, vid;
+	int rcode = 0;
+
+	/* Thor SA Firmware -> CISS_REPORT_PHYSICAL_LUNS */
+	fibsize = sizeof(struct aac_srb) - sizeof(struct sgentry)
+			+ sizeof(struct sgentry64);
+	datasize = sizeof(struct aac_ciss_phys_luns_resp)
+			+ (AAC_MAX_TARGETS - 1) * sizeof(struct _ciss_lun);
+
+	phys_luns = (struct aac_ciss_phys_luns_resp *) pci_alloc_consistent(
+			dev->pdev, datasize, &addr);
+
+	if (phys_luns == NULL) {
+		rcode = -ENOMEM;
+		goto err_out;
+	}
+
+	vbus = (u32) le16_to_cpu(
+			dev->supplement_adapter_info.VirtDeviceBus);
+	vid = (u32) le16_to_cpu(
+			dev->supplement_adapter_info.VirtDeviceTarget);
+
+	aac_fib_init(fibptr);
+
+	srbcmd = (struct aac_srb *) fib_data(fibptr);
+	srbcmd->function = cpu_to_le32(SRBF_ExecuteScsi);
+	srbcmd->channel = cpu_to_le32(vbus);
+	srbcmd->id = cpu_to_le32(vid);
+	srbcmd->lun = 0;
+	srbcmd->flags = cpu_to_le32(SRB_DataIn);
+	srbcmd->timeout = cpu_to_le32(10);
+	srbcmd->retry_limit = 0;
+	srbcmd->cdb_size = cpu_to_le32(12);
+	srbcmd->count = cpu_to_le32(datasize);
+
+	memset(srbcmd->cdb, 0, sizeof(srbcmd->cdb));
+	srbcmd->cdb[0] = CISS_REPORT_PHYSICAL_LUNS;
+	srbcmd->cdb[1] = 2; /* extended reporting */
+	srbcmd->cdb[8] = (u8)(datasize >> 8);
+	srbcmd->cdb[9] = (u8)(datasize);
+
+	sg64 = (struct sgmap64 *) &srbcmd->sg;
+	sg64->count = cpu_to_le32(1);
+	sg64->sg[0].addr[1] = cpu_to_le32(upper_32_bits(addr));
+	sg64->sg[0].addr[0] = cpu_to_le32(lower_32_bits(addr));
+	sg64->sg[0].count = cpu_to_le32(datasize);
+
+	rcode = aac_fib_send(ScsiPortCommand64, fibptr, fibsize,
+			FsaNormal, 1, 1, NULL, NULL);
+
+	/* analyse data */
+	if (rcode >= 0 && phys_luns->resp_flag == 2) {
+		/* ok and extended reporting */
+		aac_update_hba_map(dev, phys_luns, rescan);
+	}
+
+	pci_free_consistent(dev->pdev, datasize, (void *) phys_luns, addr);
+err_out:
+	return rcode;
+}
+
 int aac_get_adapter_info(struct aac_dev* dev)
 {
 	struct fib* fibptr;
 	int rcode;
-	u32 tmp;
+	u32 tmp, bus, target;
 	struct aac_adapter_info *info;
 	struct aac_bus_info *command;
 	struct aac_bus_info_response *bus_info;
@@ -1540,6 +1893,7 @@ int aac_get_adapter_info(struct aac_dev* dev)
 	}
 	memcpy(&dev->adapter_info, info, sizeof(*info));
 
+	dev->supplement_adapter_info.VirtDeviceBus = 0xffff;
 	if (dev->adapter_info.options & AAC_OPT_SUPPLEMENT_ADAPTER_INFO) {
 		struct aac_supplement_adapter_info * sinfo;
 
@@ -1567,6 +1921,13 @@ int aac_get_adapter_info(struct aac_dev* dev)
 
 	}
 
+	/* reset all previous mapped devices (i.e. for init. after IOP_RESET) */
+	for (bus = 0; bus < AAC_MAX_BUSES; bus++) {
+		for (target = 0; target < AAC_MAX_TARGETS; target++) {
+			dev->hba_map[bus][target].devtype = 0;
+			dev->hba_map[bus][target].qd_limit = 0;
+		}
+	}
 
 	/*
 	 * GetBusInfo
@@ -1599,6 +1960,12 @@ int aac_get_adapter_info(struct aac_dev* dev)
 		dev->maximum_num_channels = le32_to_cpu(bus_info->BusCount);
 	}
 
+	if (!dev->sync_mode && dev->sa_firmware &&
+			dev->supplement_adapter_info.VirtDeviceBus != 0xffff) {
+		/* Thor SA Firmware -> CISS_REPORT_PHYSICAL_LUNS */
+		rcode = aac_report_phys_luns(dev, fibptr, AAC_INIT);
+	}
+
 	if (!dev->in_reset) {
 		char buffer[16];
 		tmp = le32_to_cpu(dev->adapter_info.kernelrev);
@@ -1765,6 +2132,11 @@ int aac_get_adapter_info(struct aac_dev* dev)
 			  (dev->scsi_host_ptr->sg_tablesize * 8) + 112;
 		}
 	}
+	if (!dev->sync_mode && dev->sa_firmware &&
+		dev->scsi_host_ptr->sg_tablesize > HBA_MAX_SG_SEPARATE)
+		dev->scsi_host_ptr->sg_tablesize = dev->sg_tablesize =
+			HBA_MAX_SG_SEPARATE;
+
 	/* FIB should be freed only after getting the response from the F/W */
 	if (rcode != -ERESTARTSYS) {
 		aac_fib_complete(fibptr);
@@ -1845,6 +2217,15 @@ static void io_callback(void *context, struct fib * fibptr)
 		       min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data),
 			     SCSI_SENSE_BUFFERSIZE));
 		break;
+	case ST_MEDERR:
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+			SAM_STAT_CHECK_CONDITION;
+		set_sense(&dev->fsa_dev[cid].sense_data, MEDIUM_ERROR,
+		  SENCODE_UNRECOVERED_READ_ERROR, ASENCODE_NO_SENSE, 0, 0);
+		memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,
+		       min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data),
+			     SCSI_SENSE_BUFFERSIZE));
+		break;
 	default:
 #ifdef AAC_DETAILED_STATUS_INFO
 		printk(KERN_WARNING "io_callback: io failed, status = %d\n",
@@ -2312,7 +2693,7 @@ static int aac_start_stop(struct scsi_cmnd *scsicmd)
 
 int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 {
-	u32 cid;
+	u32 cid, bus;
 	struct Scsi_Host *host = scsicmd->device->host;
 	struct aac_dev *dev = (struct aac_dev *)host->hostdata;
 	struct fsa_dev_info *fsa_dev_ptr = dev->fsa_dev;
@@ -2330,8 +2711,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 			if((cid >= dev->maximum_num_containers) ||
 					(scsicmd->device->lun != 0)) {
 				scsicmd->result = DID_NO_CONNECT << 16;
-				scsicmd->scsi_done(scsicmd);
-				return 0;
+				goto scsi_done_ret;
 			}
 
 			/*
@@ -2359,15 +2739,30 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				}
 			}
 		} else {  /* check for physical non-dasd devices */
-			if (dev->nondasd_support || expose_physicals ||
-					dev->jbod) {
+			bus = aac_logical_to_phys(scmd_channel(scsicmd));
+			if (bus < AAC_MAX_BUSES && cid < AAC_MAX_TARGETS &&
+				(dev->hba_map[bus][cid].expose
+						== AAC_HIDE_DISK)){
+				if (scsicmd->cmnd[0] == INQUIRY) {
+					scsicmd->result = DID_NO_CONNECT << 16;
+					goto scsi_done_ret;
+				}
+			}
+
+			if (bus < AAC_MAX_BUSES && cid < AAC_MAX_TARGETS &&
+				dev->hba_map[bus][cid].devtype
+					== AAC_DEVTYPE_NATIVE_RAW) {
+				if (dev->in_reset)
+					return -1;
+				return aac_send_hba_fib(scsicmd);
+			} else if (dev->nondasd_support || expose_physicals ||
+				dev->jbod) {
 				if (dev->in_reset)
 					return -1;
 				return aac_send_srb_fib(scsicmd);
 			} else {
 				scsicmd->result = DID_NO_CONNECT << 16;
-				scsicmd->scsi_done(scsicmd);
-				return 0;
+				goto scsi_done_ret;
 			}
 		}
 	}
@@ -2385,13 +2780,34 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,
 		       min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data),
 			     SCSI_SENSE_BUFFERSIZE));
-		scsicmd->scsi_done(scsicmd);
-		return 0;
+		goto scsi_done_ret;
 	}
 
-
-	/* Handle commands here that don't really require going out to the adapter */
 	switch (scsicmd->cmnd[0]) {
+	case READ_6:
+	case READ_10:
+	case READ_12:
+	case READ_16:
+		if (dev->in_reset)
+			return -1;
+		return aac_read(scsicmd);
+
+	case WRITE_6:
+	case WRITE_10:
+	case WRITE_12:
+	case WRITE_16:
+		if (dev->in_reset)
+			return -1;
+		return aac_write(scsicmd);
+
+	case SYNCHRONIZE_CACHE:
+		if (((aac_cache & 6) == 6) && dev->cache_protected) {
+			scsicmd->result = AAC_STAT_GOOD;
+			break;
+		}
+		/* Issue FIB to tell Firmware to flush it's cache */
+		if ((aac_cache & 6) != 2)
+			return aac_synchronize(scsicmd);
 	case INQUIRY:
 	{
 		struct inquiry_data inq_data;
@@ -2414,8 +2830,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				arr[1] = scsicmd->cmnd[2];
 				scsi_sg_copy_from_buffer(scsicmd, &inq_data,
 							 sizeof(inq_data));
-				scsicmd->result = DID_OK << 16 |
-				  COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
+				scsicmd->result = AAC_STAT_GOOD;
 			} else if (scsicmd->cmnd[2] == 0x80) {
 				/* unit serial number page */
 				arr[3] = setinqserial(dev, &arr[4],
@@ -2426,8 +2841,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				if (aac_wwn != 2)
 					return aac_get_container_serial(
 						scsicmd);
-				scsicmd->result = DID_OK << 16 |
-				  COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
+				scsicmd->result = AAC_STAT_GOOD;
 			} else if (scsicmd->cmnd[2] == 0x83) {
 				/* vpd page 0x83 - Device Identification Page */
 				char *sno = (char *)&inq_data;
@@ -2436,8 +2850,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				if (aac_wwn != 2)
 					return aac_get_container_serial(
 						scsicmd);
-				scsicmd->result = DID_OK << 16 |
-				  COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
+				scsicmd->result = AAC_STAT_GOOD;
 			} else {
 				/* vpd page not implemented */
 				scsicmd->result = DID_OK << 16 |
@@ -2452,8 +2865,7 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 					sizeof(dev->fsa_dev[cid].sense_data),
 					SCSI_SENSE_BUFFERSIZE));
 			}
-			scsicmd->scsi_done(scsicmd);
-			return 0;
+			break;
 		}
 		inq_data.inqd_ver = 2;	/* claim compliance to SCSI-2 */
 		inq_data.inqd_rdf = 2;	/* A response data format value of two indicates that the data shall be in the format specified in SCSI-2 */
@@ -2469,9 +2881,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 			inq_data.inqd_pdt = INQD_PDT_PROC;	/* Processor device */
 			scsi_sg_copy_from_buffer(scsicmd, &inq_data,
 						 sizeof(inq_data));
-			scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
-			scsicmd->scsi_done(scsicmd);
-			return 0;
+			scsicmd->result = AAC_STAT_GOOD;
+			break;
 		}
 		if (dev->in_reset)
 			return -1;
@@ -2519,10 +2930,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		/* Do not cache partition table for arrays */
 		scsicmd->device->removable = 1;
 
-		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
-		scsicmd->scsi_done(scsicmd);
-
-		return 0;
+		scsicmd->result = AAC_STAT_GOOD;
+		break;
 	}
 
 	case READ_CAPACITY:
@@ -2547,11 +2956,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		scsi_sg_copy_from_buffer(scsicmd, cp, sizeof(cp));
 		/* Do not cache partition table for arrays */
 		scsicmd->device->removable = 1;
-		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
-		  SAM_STAT_GOOD;
-		scsicmd->scsi_done(scsicmd);
-
-		return 0;
+		scsicmd->result = AAC_STAT_GOOD;
+		break;
 	}
 
 	case MODE_SENSE:
@@ -2629,10 +3035,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		scsi_sg_copy_from_buffer(scsicmd,
 					 (char *)&mpd,
 					 mode_buf_length);
-		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
-		scsicmd->scsi_done(scsicmd);
-
-		return 0;
+		scsicmd->result = AAC_STAT_GOOD;
+		break;
 	}
 	case MODE_SENSE_10:
 	{
@@ -2708,18 +3112,17 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 					 (char *)&mpd10,
 					 mode_buf_length);
 
-		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
-		scsicmd->scsi_done(scsicmd);
-
-		return 0;
+		scsicmd->result = AAC_STAT_GOOD;
+		break;
 	}
 	case REQUEST_SENSE:
 		dprintk((KERN_DEBUG "REQUEST SENSE command.\n"));
-		memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data, sizeof (struct sense_data));
-		memset(&dev->fsa_dev[cid].sense_data, 0, sizeof (struct sense_data));
-		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
-		scsicmd->scsi_done(scsicmd);
-		return 0;
+		memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,
+				sizeof(struct sense_data));
+		memset(&dev->fsa_dev[cid].sense_data, 0,
+				sizeof(struct sense_data));
+		scsicmd->result = AAC_STAT_GOOD;
+		break;
 
 	case ALLOW_MEDIUM_REMOVAL:
 		dprintk((KERN_DEBUG "LOCK command.\n"));
@@ -2728,9 +3131,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		else
 			fsa_dev_ptr[cid].locked = 0;
 
-		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
-		scsicmd->scsi_done(scsicmd);
-		return 0;
+		scsicmd->result = AAC_STAT_GOOD;
+		break;
 	/*
 	 *	These commands are all No-Ops
 	 */
@@ -2746,80 +3148,41 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 			       min_t(size_t,
 				     sizeof(dev->fsa_dev[cid].sense_data),
 				     SCSI_SENSE_BUFFERSIZE));
-			scsicmd->scsi_done(scsicmd);
-			return 0;
+		break;
 		}
-		/* FALLTHRU */
 	case RESERVE:
 	case RELEASE:
 	case REZERO_UNIT:
 	case REASSIGN_BLOCKS:
 	case SEEK_10:
-		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
-		scsicmd->scsi_done(scsicmd);
-		return 0;
+		scsicmd->result = AAC_STAT_GOOD;
+		break;
 
 	case START_STOP:
 		return aac_start_stop(scsicmd);
-	}
-
-	switch (scsicmd->cmnd[0])
-	{
-		case READ_6:
-		case READ_10:
-		case READ_12:
-		case READ_16:
-			if (dev->in_reset)
-				return -1;
-			/*
-			 *	Hack to keep track of ordinal number of the device that
-			 *	corresponds to a container. Needed to convert
-			 *	containers to /dev/sd device names
-			 */
-
-			if (scsicmd->request->rq_disk)
-				strlcpy(fsa_dev_ptr[cid].devname,
-				scsicmd->request->rq_disk->disk_name,
-				min(sizeof(fsa_dev_ptr[cid].devname),
-				sizeof(scsicmd->request->rq_disk->disk_name) + 1));
-
-			return aac_read(scsicmd);
 
-		case WRITE_6:
-		case WRITE_10:
-		case WRITE_12:
-		case WRITE_16:
-			if (dev->in_reset)
-				return -1;
-			return aac_write(scsicmd);
-
-		case SYNCHRONIZE_CACHE:
-			if (((aac_cache & 6) == 6) && dev->cache_protected) {
-				scsicmd->result = DID_OK << 16 |
-					COMMAND_COMPLETE << 8 | SAM_STAT_GOOD;
-				scsicmd->scsi_done(scsicmd);
-				return 0;
-			}
-			/* Issue FIB to tell Firmware to flush it's cache */
-			if ((aac_cache & 6) != 2)
-				return aac_synchronize(scsicmd);
-			/* FALLTHRU */
-		default:
-			/*
-			 *	Unhandled commands
-			 */
-			dprintk((KERN_WARNING "Unhandled SCSI Command: 0x%x.\n", scsicmd->cmnd[0]));
-			scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_CHECK_CONDITION;
-			set_sense(&dev->fsa_dev[cid].sense_data,
+	/* FALLTHRU */
+	default:
+	/*
+	 *	Unhandled commands
+	 */
+		dprintk((KERN_WARNING "Unhandled SCSI Command: 0x%x.\n",
+				scsicmd->cmnd[0]));
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				SAM_STAT_CHECK_CONDITION;
+		set_sense(&dev->fsa_dev[cid].sense_data,
 			  ILLEGAL_REQUEST, SENCODE_INVALID_COMMAND,
 			  ASENCODE_INVALID_COMMAND, 0, 0);
-			memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,
+		memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data,
 				min_t(size_t,
 				      sizeof(dev->fsa_dev[cid].sense_data),
 				      SCSI_SENSE_BUFFERSIZE));
-			scsicmd->scsi_done(scsicmd);
-			return 0;
 	}
+
+scsi_done_ret:
+
+	scsicmd->scsi_done(scsicmd);
+	return 0;
 }
 
 static int query_disk(struct aac_dev *dev, void __user *arg)
@@ -2954,16 +3317,11 @@ static void aac_srb_callback(void *context, struct fib * fibptr)
 		return;
 
 	BUG_ON(fibptr == NULL);
-	dev = fibptr->dev;
 
-	scsi_dma_unmap(scsicmd);
-
-	/* expose physical device if expose_physicald flag is on */
-	if (scsicmd->cmnd[0] == INQUIRY && !(scsicmd->cmnd[1] & 0x01)
-	  && expose_physicals > 0)
-		aac_expose_phy_device(scsicmd);
+	dev = fibptr->dev;
 
 	srbreply = (struct aac_srb_reply *) fib_data(fibptr);
+
 	scsicmd->sense_buffer[0] = '\0';  /* Initialize sense valid flag to false */
 
 	if (fibptr->flags & FIB_CONTEXT_FLAG_FASTRESP) {
@@ -2976,158 +3334,176 @@ static void aac_srb_callback(void *context, struct fib * fibptr)
 		 */
 		scsi_set_resid(scsicmd, scsi_bufflen(scsicmd)
 				   - le32_to_cpu(srbreply->data_xfer_length));
-		/*
-		 * First check the fib status
-		 */
+	}
 
-		if (le32_to_cpu(srbreply->status) != ST_OK) {
-			int len;
 
-			printk(KERN_WARNING "aac_srb_callback: srb failed, status = %d\n", le32_to_cpu(srbreply->status));
-			len = min_t(u32, le32_to_cpu(srbreply->sense_data_size),
-				    SCSI_SENSE_BUFFERSIZE);
-			scsicmd->result = DID_ERROR << 16
-						| COMMAND_COMPLETE << 8
-						| SAM_STAT_CHECK_CONDITION;
-			memcpy(scsicmd->sense_buffer,
-					srbreply->sense_data, len);
-		}
+	scsi_dma_unmap(scsicmd);
 
-		/*
-		 * Next check the srb status
-		 */
-		switch ((le32_to_cpu(srbreply->srb_status))&0x3f) {
-		case SRB_STATUS_ERROR_RECOVERY:
-		case SRB_STATUS_PENDING:
-		case SRB_STATUS_SUCCESS:
-			scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8;
-			break;
-		case SRB_STATUS_DATA_OVERRUN:
-			switch (scsicmd->cmnd[0]) {
-			case  READ_6:
-			case  WRITE_6:
-			case  READ_10:
-			case  WRITE_10:
-			case  READ_12:
-			case  WRITE_12:
-			case  READ_16:
-			case  WRITE_16:
-				if (le32_to_cpu(srbreply->data_xfer_length)
-							< scsicmd->underflow)
-					printk(KERN_WARNING"aacraid: SCSI CMD underflow\n");
-				else
-					printk(KERN_WARNING"aacraid: SCSI CMD Data Overrun\n");
-				scsicmd->result = DID_ERROR << 16
-							| COMMAND_COMPLETE << 8;
-				break;
-			case INQUIRY: {
-				scsicmd->result = DID_OK << 16
-							| COMMAND_COMPLETE << 8;
-				break;
-			}
-			default:
-				scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8;
-				break;
-			}
-			break;
-		case SRB_STATUS_ABORTED:
-			scsicmd->result = DID_ABORT << 16 | ABORT << 8;
-			break;
-		case SRB_STATUS_ABORT_FAILED:
-			/*
-			 * Not sure about this one - but assuming the
-			 * hba was trying to abort for some reason
-			 */
-			scsicmd->result = DID_ERROR << 16 | ABORT << 8;
+	/* expose physical device if expose_physicald flag is on */
+	if (scsicmd->cmnd[0] == INQUIRY && !(scsicmd->cmnd[1] & 0x01)
+	  && expose_physicals > 0)
+		aac_expose_phy_device(scsicmd);
+
+	/*
+	 * First check the fib status
+	 */
+
+	if (le32_to_cpu(srbreply->status) != ST_OK) {
+		int len;
+
+		pr_warn("aac_srb_callback: srb failed, status = %d\n",
+				le32_to_cpu(srbreply->status));
+		len = min_t(u32, le32_to_cpu(srbreply->sense_data_size),
+			    SCSI_SENSE_BUFFERSIZE);
+		scsicmd->result = DID_ERROR << 16
+				| COMMAND_COMPLETE << 8
+				| SAM_STAT_CHECK_CONDITION;
+		memcpy(scsicmd->sense_buffer,
+				srbreply->sense_data, len);
+	}
+
+	/*
+	 * Next check the srb status
+	 */
+	switch ((le32_to_cpu(srbreply->srb_status))&0x3f) {
+	case SRB_STATUS_ERROR_RECOVERY:
+	case SRB_STATUS_PENDING:
+	case SRB_STATUS_SUCCESS:
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8;
+		break;
+	case SRB_STATUS_DATA_OVERRUN:
+		switch (scsicmd->cmnd[0]) {
+		case  READ_6:
+		case  WRITE_6:
+		case  READ_10:
+		case  WRITE_10:
+		case  READ_12:
+		case  WRITE_12:
+		case  READ_16:
+		case  WRITE_16:
+			if (le32_to_cpu(srbreply->data_xfer_length)
+						< scsicmd->underflow)
+				pr_warn("aacraid: SCSI CMD underflow\n");
+			else
+				pr_warn("aacraid: SCSI CMD Data Overrun\n");
+			scsicmd->result = DID_ERROR << 16
+					| COMMAND_COMPLETE << 8;
 			break;
-		case SRB_STATUS_PARITY_ERROR:
-			scsicmd->result = DID_PARITY << 16
-						| MSG_PARITY_ERROR << 8;
+		case INQUIRY:
+			scsicmd->result = DID_OK << 16
+					| COMMAND_COMPLETE << 8;
 			break;
-		case SRB_STATUS_NO_DEVICE:
-		case SRB_STATUS_INVALID_PATH_ID:
-		case SRB_STATUS_INVALID_TARGET_ID:
-		case SRB_STATUS_INVALID_LUN:
-		case SRB_STATUS_SELECTION_TIMEOUT:
-			scsicmd->result = DID_NO_CONNECT << 16
-						| COMMAND_COMPLETE << 8;
+		default:
+			scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8;
 			break;
+		}
+		break;
+	case SRB_STATUS_ABORTED:
+		scsicmd->result = DID_ABORT << 16 | ABORT << 8;
+		break;
+	case SRB_STATUS_ABORT_FAILED:
+		/*
+		 * Not sure about this one - but assuming the
+		 * hba was trying to abort for some reason
+		 */
+		scsicmd->result = DID_ERROR << 16 | ABORT << 8;
+		break;
+	case SRB_STATUS_PARITY_ERROR:
+		scsicmd->result = DID_PARITY << 16
+				| MSG_PARITY_ERROR << 8;
+		break;
+	case SRB_STATUS_NO_DEVICE:
+	case SRB_STATUS_INVALID_PATH_ID:
+	case SRB_STATUS_INVALID_TARGET_ID:
+	case SRB_STATUS_INVALID_LUN:
+	case SRB_STATUS_SELECTION_TIMEOUT:
+		scsicmd->result = DID_NO_CONNECT << 16
+				| COMMAND_COMPLETE << 8;
+		break;
 
-		case SRB_STATUS_COMMAND_TIMEOUT:
-		case SRB_STATUS_TIMEOUT:
-			scsicmd->result = DID_TIME_OUT << 16
-						| COMMAND_COMPLETE << 8;
-			break;
+	case SRB_STATUS_COMMAND_TIMEOUT:
+	case SRB_STATUS_TIMEOUT:
+		scsicmd->result = DID_TIME_OUT << 16
+				| COMMAND_COMPLETE << 8;
+		break;
 
-		case SRB_STATUS_BUSY:
-			scsicmd->result = DID_BUS_BUSY << 16
-						| COMMAND_COMPLETE << 8;
-			break;
+	case SRB_STATUS_BUSY:
+		scsicmd->result = DID_BUS_BUSY << 16
+				| COMMAND_COMPLETE << 8;
+		break;
 
-		case SRB_STATUS_BUS_RESET:
-			scsicmd->result = DID_RESET << 16
-						| COMMAND_COMPLETE << 8;
-			break;
+	case SRB_STATUS_BUS_RESET:
+		scsicmd->result = DID_RESET << 16
+				| COMMAND_COMPLETE << 8;
+		break;
 
-		case SRB_STATUS_MESSAGE_REJECTED:
-			scsicmd->result = DID_ERROR << 16
-						| MESSAGE_REJECT << 8;
-			break;
-		case SRB_STATUS_REQUEST_FLUSHED:
-		case SRB_STATUS_ERROR:
-		case SRB_STATUS_INVALID_REQUEST:
-		case SRB_STATUS_REQUEST_SENSE_FAILED:
-		case SRB_STATUS_NO_HBA:
-		case SRB_STATUS_UNEXPECTED_BUS_FREE:
-		case SRB_STATUS_PHASE_SEQUENCE_FAILURE:
-		case SRB_STATUS_BAD_SRB_BLOCK_LENGTH:
-		case SRB_STATUS_DELAYED_RETRY:
-		case SRB_STATUS_BAD_FUNCTION:
-		case SRB_STATUS_NOT_STARTED:
-		case SRB_STATUS_NOT_IN_USE:
-		case SRB_STATUS_FORCE_ABORT:
-		case SRB_STATUS_DOMAIN_VALIDATION_FAIL:
-		default:
+	case SRB_STATUS_MESSAGE_REJECTED:
+		scsicmd->result = DID_ERROR << 16
+				| MESSAGE_REJECT << 8;
+		break;
+	case SRB_STATUS_REQUEST_FLUSHED:
+	case SRB_STATUS_ERROR:
+	case SRB_STATUS_INVALID_REQUEST:
+	case SRB_STATUS_REQUEST_SENSE_FAILED:
+	case SRB_STATUS_NO_HBA:
+	case SRB_STATUS_UNEXPECTED_BUS_FREE:
+	case SRB_STATUS_PHASE_SEQUENCE_FAILURE:
+	case SRB_STATUS_BAD_SRB_BLOCK_LENGTH:
+	case SRB_STATUS_DELAYED_RETRY:
+	case SRB_STATUS_BAD_FUNCTION:
+	case SRB_STATUS_NOT_STARTED:
+	case SRB_STATUS_NOT_IN_USE:
+	case SRB_STATUS_FORCE_ABORT:
+	case SRB_STATUS_DOMAIN_VALIDATION_FAIL:
+	default:
 #ifdef AAC_DETAILED_STATUS_INFO
-			printk(KERN_INFO "aacraid: SRB ERROR(%u) %s scsi cmd 0x%x - scsi status 0x%x\n",
-				le32_to_cpu(srbreply->srb_status) & 0x3F,
-				aac_get_status_string(
-					le32_to_cpu(srbreply->srb_status) & 0x3F),
-				scsicmd->cmnd[0],
-				le32_to_cpu(srbreply->scsi_status));
+		pr_info("aacraid: SRB ERROR(%u) %s scsi cmd 0x%x -scsi status 0x%x\n",
+			le32_to_cpu(srbreply->srb_status) & 0x3F,
+			aac_get_status_string(
+				le32_to_cpu(srbreply->srb_status) & 0x3F),
+			scsicmd->cmnd[0],
+			le32_to_cpu(srbreply->scsi_status));
 #endif
-			if ((scsicmd->cmnd[0] == ATA_12)
-				|| (scsicmd->cmnd[0] == ATA_16)) {
-					if (scsicmd->cmnd[2] & (0x01 << 5)) {
-						scsicmd->result = DID_OK << 16
-							| COMMAND_COMPLETE << 8;
-				break;
-				} else {
-					scsicmd->result = DID_ERROR << 16
-						| COMMAND_COMPLETE << 8;
-					break;
-				}
+		/*
+		 * When the CC bit is SET by the host in ATA pass thru CDB,
+		 *  driver is supposed to return DID_OK
+		 *
+		 * When the CC bit is RESET by the host, driver should
+		 *  return DID_ERROR
+		 */
+		if ((scsicmd->cmnd[0] == ATA_12)
+			|| (scsicmd->cmnd[0] == ATA_16)) {
+
+			if (scsicmd->cmnd[2] & (0x01 << 5)) {
+				scsicmd->result = DID_OK << 16
+					| COMMAND_COMPLETE << 8;
+			break;
 			} else {
 				scsicmd->result = DID_ERROR << 16
 					| COMMAND_COMPLETE << 8;
-				break;
+			break;
 			}
+		} else {
+			scsicmd->result = DID_ERROR << 16
+				| COMMAND_COMPLETE << 8;
+			break;
 		}
-		if (le32_to_cpu(srbreply->scsi_status)
-				== SAM_STAT_CHECK_CONDITION) {
-			int len;
+	}
+	if (le32_to_cpu(srbreply->scsi_status)
+			== SAM_STAT_CHECK_CONDITION) {
+		int len;
 
-			scsicmd->result |= SAM_STAT_CHECK_CONDITION;
-			len = min_t(u32, le32_to_cpu(srbreply->sense_data_size),
-				    SCSI_SENSE_BUFFERSIZE);
+		scsicmd->result |= SAM_STAT_CHECK_CONDITION;
+		len = min_t(u32, le32_to_cpu(srbreply->sense_data_size),
+			    SCSI_SENSE_BUFFERSIZE);
 #ifdef AAC_DETAILED_STATUS_INFO
-			printk(KERN_WARNING "aac_srb_callback: check condition, status = %d len=%d\n",
-						le32_to_cpu(srbreply->status), len);
+		pr_warn("aac_srb_callback: check condition, status = %d len=%d\n",
+					le32_to_cpu(srbreply->status), len);
 #endif
-			memcpy(scsicmd->sense_buffer,
-					srbreply->sense_data, len);
-		}
+		memcpy(scsicmd->sense_buffer,
+				srbreply->sense_data, len);
 	}
+
 	/*
 	 * OR in the scsi status (already shifted up a bit)
 	 */
@@ -3137,9 +3513,152 @@ static void aac_srb_callback(void *context, struct fib * fibptr)
 	scsicmd->scsi_done(scsicmd);
 }
 
+static void hba_resp_task_complete(struct aac_dev *dev,
+					struct scsi_cmnd *scsicmd,
+					struct aac_hba_resp *err) {
+
+	scsicmd->result = err->status;
+	/* set residual count */
+	scsi_set_resid(scsicmd, le32_to_cpu(err->residual_count));
+
+	switch (err->status) {
+	case SAM_STAT_GOOD:
+		scsicmd->result |= DID_OK << 16 | COMMAND_COMPLETE << 8;
+		break;
+	case SAM_STAT_CHECK_CONDITION:
+	{
+		int len;
+
+		len = min_t(u8, err->sense_response_data_len,
+			SCSI_SENSE_BUFFERSIZE);
+		if (len)
+			memcpy(scsicmd->sense_buffer,
+				err->sense_response_buf, len);
+		scsicmd->result |= DID_OK << 16 | COMMAND_COMPLETE << 8;
+		break;
+	}
+	case SAM_STAT_BUSY:
+		scsicmd->result |= DID_BUS_BUSY << 16 | COMMAND_COMPLETE << 8;
+		break;
+	case SAM_STAT_TASK_ABORTED:
+		scsicmd->result |= DID_ABORT << 16 | ABORT << 8;
+		break;
+	case SAM_STAT_RESERVATION_CONFLICT:
+	case SAM_STAT_TASK_SET_FULL:
+	default:
+		scsicmd->result |= DID_ERROR << 16 | COMMAND_COMPLETE << 8;
+		break;
+	}
+}
+
+static void hba_resp_task_failure(struct aac_dev *dev,
+					struct scsi_cmnd *scsicmd,
+					struct aac_hba_resp *err)
+{
+	switch (err->status) {
+	case HBA_RESP_STAT_HBAMODE_DISABLED:
+	{
+		u32 bus, cid;
+
+		bus = aac_logical_to_phys(scmd_channel(scsicmd));
+		cid = scmd_id(scsicmd);
+		if (dev->hba_map[bus][cid].devtype == AAC_DEVTYPE_NATIVE_RAW) {
+			dev->hba_map[bus][cid].devtype = AAC_DEVTYPE_ARC_RAW;
+			dev->hba_map[bus][cid].rmw_nexus = 0xffffffff;
+		}
+		scsicmd->result = DID_NO_CONNECT << 16 | COMMAND_COMPLETE << 8;
+		break;
+	}
+	case HBA_RESP_STAT_IO_ERROR:
+	case HBA_RESP_STAT_NO_PATH_TO_DEVICE:
+		scsicmd->result = DID_OK << 16 |
+			COMMAND_COMPLETE << 8 | SAM_STAT_BUSY;
+		break;
+	case HBA_RESP_STAT_IO_ABORTED:
+		scsicmd->result = DID_ABORT << 16 | ABORT << 8;
+		break;
+	case HBA_RESP_STAT_INVALID_DEVICE:
+		scsicmd->result = DID_NO_CONNECT << 16 | COMMAND_COMPLETE << 8;
+		break;
+	case HBA_RESP_STAT_UNDERRUN:
+		/* UNDERRUN is OK */
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8;
+		break;
+	case HBA_RESP_STAT_OVERRUN:
+	default:
+		scsicmd->result = DID_ERROR << 16 | COMMAND_COMPLETE << 8;
+		break;
+	}
+}
+
+/**
+ *
+ * aac_hba_callback
+ * @context: the context set in the fib - here it is scsi cmd
+ * @fibptr: pointer to the fib
+ *
+ * Handles the completion of a native HBA scsi command
+ *
+ */
+void aac_hba_callback(void *context, struct fib *fibptr)
+{
+	struct aac_dev *dev;
+	struct scsi_cmnd *scsicmd;
+
+	struct aac_hba_resp *err =
+			&((struct aac_native_hba *)fibptr->hw_fib_va)->resp.err;
+
+	scsicmd = (struct scsi_cmnd *) context;
+
+	if (!aac_valid_context(scsicmd, fibptr))
+		return;
+
+	WARN_ON(fibptr == NULL);
+	dev = fibptr->dev;
+
+	if (!(fibptr->flags & FIB_CONTEXT_FLAG_NATIVE_HBA_TMF))
+		scsi_dma_unmap(scsicmd);
+
+	if (fibptr->flags & FIB_CONTEXT_FLAG_FASTRESP) {
+		/* fast response */
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8;
+		goto out;
+	}
+
+	switch (err->service_response) {
+	case HBA_RESP_SVCRES_TASK_COMPLETE:
+		hba_resp_task_complete(dev, scsicmd, err);
+		break;
+	case HBA_RESP_SVCRES_FAILURE:
+		hba_resp_task_failure(dev, scsicmd, err);
+		break;
+	case HBA_RESP_SVCRES_TMF_REJECTED:
+		scsicmd->result = DID_ERROR << 16 | MESSAGE_REJECT << 8;
+		break;
+	case HBA_RESP_SVCRES_TMF_LUN_INVALID:
+		scsicmd->result = DID_NO_CONNECT << 16 | COMMAND_COMPLETE << 8;
+		break;
+	case HBA_RESP_SVCRES_TMF_COMPLETE:
+	case HBA_RESP_SVCRES_TMF_SUCCEEDED:
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8;
+		break;
+	default:
+		scsicmd->result = DID_ERROR << 16 | COMMAND_COMPLETE << 8;
+		break;
+	}
+
+out:
+	aac_fib_complete(fibptr);
+
+	if (fibptr->flags & FIB_CONTEXT_FLAG_NATIVE_HBA_TMF)
+		scsicmd->SCp.sent_command = 1;
+	else
+		scsicmd->scsi_done(scsicmd);
+}
+
 /**
  *
- * aac_send_scb_fib
+ * aac_send_srb_fib
  * @scsicmd: the scsi command block
  *
  * This routine will form a FIB and fill in the aac_srb from the
@@ -3182,6 +3701,54 @@ static int aac_send_srb_fib(struct scsi_cmnd* scsicmd)
 	return -1;
 }
 
+/**
+ *
+ * aac_send_hba_fib
+ * @scsicmd: the scsi command block
+ *
+ * This routine will form a FIB and fill in the aac_hba_cmd_req from the
+ * scsicmd passed in.
+ */
+static int aac_send_hba_fib(struct scsi_cmnd *scsicmd)
+{
+	struct fib *cmd_fibcontext;
+	struct aac_dev *dev;
+	int status;
+
+	dev = shost_priv(scsicmd->device->host);
+	if (scmd_id(scsicmd) >= dev->maximum_num_physicals ||
+			scsicmd->device->lun > AAC_MAX_LUN - 1) {
+		scsicmd->result = DID_NO_CONNECT << 16;
+		scsicmd->scsi_done(scsicmd);
+		return 0;
+	}
+
+	/*
+	 *	Allocate and initialize a Fib then setup a BlockWrite command
+	 */
+	cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd);
+	if (!cmd_fibcontext)
+		return -1;
+
+	status = aac_adapter_hba(cmd_fibcontext, scsicmd);
+
+	/*
+	 *	Check that the command queued to the controller
+	 */
+	if (status == -EINPROGRESS) {
+		scsicmd->SCp.phase = AAC_OWNER_FIRMWARE;
+		return 0;
+	}
+
+	pr_warn("aac_hba_cmd_req: aac_fib_send failed with status: %d\n",
+		status);
+	aac_fib_complete(cmd_fibcontext);
+	aac_fib_free(cmd_fibcontext);
+
+	return -1;
+}
+
+
 static long aac_build_sg(struct scsi_cmnd *scsicmd, struct sgmap *psg)
 {
 	struct aac_dev *dev;
@@ -3434,6 +4001,75 @@ static int aac_convert_sgraw2(struct aac_raw_io2 *rio2, int pages, int nseg, int
 	return 0;
 }
 
+static long aac_build_sghba(struct scsi_cmnd *scsicmd,
+			struct aac_hba_cmd_req *hbacmd,
+			int sg_max,
+			u64 sg_address)
+{
+	unsigned long byte_count = 0;
+	int nseg;
+	struct scatterlist *sg;
+	int i;
+	u32 cur_size;
+	struct aac_hba_sgl *sge;
+
+	nseg = scsi_dma_map(scsicmd);
+	if (nseg <= 0) {
+		byte_count = nseg;
+		goto out;
+	}
+
+	if (nseg > HBA_MAX_SG_EMBEDDED)
+		sge = &hbacmd->sge[2];
+	else
+		sge = &hbacmd->sge[0];
+
+	scsi_for_each_sg(scsicmd, sg, nseg, i) {
+		int count = sg_dma_len(sg);
+		u64 addr = sg_dma_address(sg);
+
+		WARN_ON(i >= sg_max);
+		sge->addr_hi = cpu_to_le32((u32)(addr>>32));
+		sge->addr_lo = cpu_to_le32((u32)(addr & 0xffffffff));
+		cur_size = cpu_to_le32(count);
+		sge->len = cur_size;
+		sge->flags = 0;
+		byte_count += count;
+		sge++;
+	}
+
+	sge--;
+	/* hba wants the size to be exact */
+	if (byte_count > scsi_bufflen(scsicmd)) {
+		u32 temp;
+
+		temp = le32_to_cpu(sge->len) - byte_count
+						- scsi_bufflen(scsicmd);
+		sge->len = cpu_to_le32(temp);
+		byte_count = scsi_bufflen(scsicmd);
+	}
+
+	if (nseg <= HBA_MAX_SG_EMBEDDED) {
+		hbacmd->emb_data_desc_count = cpu_to_le32(nseg);
+		sge->flags = cpu_to_le32(0x40000000);
+	} else {
+		/* not embedded */
+		hbacmd->sge[0].flags = cpu_to_le32(0x80000000);
+		hbacmd->emb_data_desc_count = (u8)cpu_to_le32(1);
+		hbacmd->sge[0].addr_hi = (u32)cpu_to_le32(sg_address >> 32);
+		hbacmd->sge[0].addr_lo =
+			cpu_to_le32((u32)(sg_address & 0xffffffff));
+	}
+
+	/* Check for command underflow */
+	if (scsicmd->underflow && (byte_count < scsicmd->underflow)) {
+		pr_warn("aacraid: cmd len %08lX cmd underflow %08X\n",
+				byte_count, scsicmd->underflow);
+	}
+out:
+	return byte_count;
+}
+
 #ifdef AAC_DETAILED_STATUS_INFO
 
 struct aac_srb_status_info {
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index f059c14efa0c..f2344971e3cb 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -1,3 +1,37 @@
+/*
+ *	Adaptec AAC series RAID controller driver
+ *	(c) Copyright 2001 Red Hat Inc.	<alan@redhat.com>
+ *
+ * based on the old aacraid driver that is..
+ * Adaptec aacraid device driver for Linux.
+ *
+ * Copyright (c) 2000-2010 Adaptec, Inc.
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; see the file COPYING.  If not, write to
+ * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Module Name:
+ *  aacraid.h
+ *
+ * Abstract: Contains all routines for control of the aacraid driver
+ *
+ */
+
+#ifndef _AACRAID_H_
+#define _AACRAID_H_
 #ifndef dprintk
 # define dprintk(x)
 #endif
@@ -63,8 +97,8 @@ enum {
 #define	PMC_GLOBAL_INT_BIT0		0x00000001
 
 #ifndef AAC_DRIVER_BUILD
-# define AAC_DRIVER_BUILD 41066
-# define AAC_DRIVER_BRANCH "-ms"
+# define AAC_DRIVER_BUILD 50740
+# define AAC_DRIVER_BRANCH "-custom"
 #endif
 #define MAXIMUM_NUM_CONTAINERS	32
 
@@ -72,13 +106,311 @@ enum {
 #define AAC_NUM_IO_FIB		(1024 - AAC_NUM_MGT_FIB)
 #define AAC_NUM_FIB		(AAC_NUM_IO_FIB + AAC_NUM_MGT_FIB)
 
-#define AAC_MAX_LUN		(8)
+#define AAC_MAX_LUN		256
 
 #define AAC_MAX_HOSTPHYSMEMPAGES (0xfffff)
 #define AAC_MAX_32BIT_SGBCOUNT	((unsigned short)256)
 
 #define AAC_DEBUG_INSTRUMENT_AIF_DELETE
 
+#define AAC_MAX_NATIVE_TARGETS		1024
+/* Thor: 5 phys. buses: #0: empty, 1-4: 256 targets each */
+#define AAC_MAX_BUSES			5
+#define AAC_MAX_TARGETS		256
+#define AAC_MAX_NATIVE_SIZE		2048
+#define FW_ERROR_BUFFER_SIZE		512
+
+/* Thor AIF events */
+#define SA_AIF_HOTPLUG			(1<<1)
+#define SA_AIF_HARDWARE		(1<<2)
+#define SA_AIF_PDEV_CHANGE		(1<<4)
+#define SA_AIF_LDEV_CHANGE		(1<<5)
+#define SA_AIF_BPSTAT_CHANGE		(1<<30)
+#define SA_AIF_BPCFG_CHANGE		(1<<31)
+
+#define HBA_MAX_SG_EMBEDDED		28
+#define HBA_MAX_SG_SEPARATE		90
+#define HBA_SENSE_DATA_LEN_MAX		32
+#define HBA_REQUEST_TAG_ERROR_FLAG	0x00000002
+#define HBA_SGL_FLAGS_EXT		0x80000000UL
+
+struct aac_hba_sgl {
+	u32		addr_lo; /* Lower 32-bits of SGL element address */
+	u32		addr_hi; /* Upper 32-bits of SGL element address */
+	u32		len;	/* Length of SGL element in bytes */
+	u32		flags;	/* SGL element flags */
+};
+
+enum {
+	HBA_IU_TYPE_SCSI_CMD_REQ		= 0x40,
+	HBA_IU_TYPE_SCSI_TM_REQ			= 0x41,
+	HBA_IU_TYPE_SATA_REQ			= 0x42,
+	HBA_IU_TYPE_RESP			= 0x60,
+	HBA_IU_TYPE_COALESCED_RESP		= 0x61,
+	HBA_IU_TYPE_INT_COALESCING_CFG_REQ	= 0x70
+};
+
+enum {
+	HBA_CMD_BYTE1_DATA_DIR_IN		= 0x1,
+	HBA_CMD_BYTE1_DATA_DIR_OUT		= 0x2,
+	HBA_CMD_BYTE1_DATA_TYPE_DDR		= 0x4,
+	HBA_CMD_BYTE1_CRYPTO_ENABLE		= 0x8
+};
+
+enum {
+	HBA_CMD_BYTE1_BITOFF_DATA_DIR_IN	= 0x0,
+	HBA_CMD_BYTE1_BITOFF_DATA_DIR_OUT,
+	HBA_CMD_BYTE1_BITOFF_DATA_TYPE_DDR,
+	HBA_CMD_BYTE1_BITOFF_CRYPTO_ENABLE
+};
+
+enum {
+	HBA_RESP_DATAPRES_NO_DATA		= 0x0,
+	HBA_RESP_DATAPRES_RESPONSE_DATA,
+	HBA_RESP_DATAPRES_SENSE_DATA
+};
+
+enum {
+	HBA_RESP_SVCRES_TASK_COMPLETE		= 0x0,
+	HBA_RESP_SVCRES_FAILURE,
+	HBA_RESP_SVCRES_TMF_COMPLETE,
+	HBA_RESP_SVCRES_TMF_SUCCEEDED,
+	HBA_RESP_SVCRES_TMF_REJECTED,
+	HBA_RESP_SVCRES_TMF_LUN_INVALID
+};
+
+enum {
+	HBA_RESP_STAT_IO_ERROR			= 0x1,
+	HBA_RESP_STAT_IO_ABORTED,
+	HBA_RESP_STAT_NO_PATH_TO_DEVICE,
+	HBA_RESP_STAT_INVALID_DEVICE,
+	HBA_RESP_STAT_HBAMODE_DISABLED		= 0xE,
+	HBA_RESP_STAT_UNDERRUN			= 0x51,
+	HBA_RESP_STAT_OVERRUN			= 0x75
+};
+
+struct aac_hba_cmd_req {
+	u8	iu_type;	/* HBA information unit type */
+	/*
+	 * byte1:
+	 * [1:0] DIR - 0=No data, 0x1 = IN, 0x2 = OUT
+	 * [2]   TYPE - 0=PCI, 1=DDR
+	 * [3]   CRYPTO_ENABLE - 0=Crypto disabled, 1=Crypto enabled
+	 */
+	u8	byte1;
+	u8	reply_qid;	/* Host reply queue to post response to */
+	u8	reserved1;
+	__le32	it_nexus;	/* Device handle for the request */
+	__le32	request_id;	/* Sender context */
+	/* Lower 32-bits of tweak value for crypto enabled IOs */
+	__le32	tweak_value_lo;
+	u8	cdb[16];	/* SCSI CDB of the command */
+	u8	lun[8];		/* SCSI LUN of the command */
+
+	/* Total data length in bytes to be read/written (if any) */
+	__le32	data_length;
+
+	/* [2:0] Task Attribute, [6:3] Command Priority */
+	u8	attr_prio;
+
+	/* Number of SGL elements embedded in the HBA req */
+	u8	emb_data_desc_count;
+
+	__le16	dek_index;	/* DEK index for crypto enabled IOs */
+
+	/* Lower 32-bits of reserved error data target location on the host */
+	__le32	error_ptr_lo;
+
+	/* Upper 32-bits of reserved error data target location on the host */
+	__le32	error_ptr_hi;
+
+	/* Length of reserved error data area on the host in bytes */
+	__le32	error_length;
+
+	/* Upper 32-bits of tweak value for crypto enabled IOs */
+	__le32	tweak_value_hi;
+
+	struct aac_hba_sgl sge[HBA_MAX_SG_SEPARATE+2]; /* SG list space */
+
+	/*
+	 * structure must not exceed
+	 * AAC_MAX_NATIVE_SIZE-FW_ERROR_BUFFER_SIZE
+	 */
+};
+
+/* Task Management Functions (TMF) */
+#define HBA_TMF_ABORT_TASK	0x01
+#define HBA_TMF_LUN_RESET	0x08
+
+struct aac_hba_tm_req {
+	u8	iu_type;	/* HBA information unit type */
+	u8	reply_qid;	/* Host reply queue to post response to */
+	u8	tmf;		/* Task management function */
+	u8	reserved1;
+
+	__le32	it_nexus;	/* Device handle for the command */
+
+	u8	lun[8];		/* SCSI LUN */
+
+	/* Used to hold sender context. */
+	__le32	request_id;	/* Sender context */
+	__le32	reserved2;
+
+	/* Request identifier of managed task */
+	__le32	managed_request_id;	/* Sender context being managed */
+	__le32	reserved3;
+
+	/* Lower 32-bits of reserved error data target location on the host */
+	__le32	error_ptr_lo;
+	/* Upper 32-bits of reserved error data target location on the host */
+	__le32	error_ptr_hi;
+	/* Length of reserved error data area on the host in bytes */
+	__le32	error_length;
+};
+
+struct aac_hba_reset_req {
+	u8	iu_type;	/* HBA information unit type */
+	/* 0 - reset specified device, 1 - reset all devices */
+	u8	reset_type;
+	u8	reply_qid;	/* Host reply queue to post response to */
+	u8	reserved1;
+
+	__le32	it_nexus;	/* Device handle for the command */
+	__le32	request_id;	/* Sender context */
+	/* Lower 32-bits of reserved error data target location on the host */
+	__le32	error_ptr_lo;
+	/* Upper 32-bits of reserved error data target location on the host */
+	__le32	error_ptr_hi;
+	/* Length of reserved error data area on the host in bytes */
+	__le32	error_length;
+};
+
+struct aac_hba_resp {
+	u8	iu_type;		/* HBA information unit type */
+	u8	reserved1[3];
+	__le32	request_identifier;	/* sender context */
+	__le32	reserved2;
+	u8	service_response;	/* SCSI service response */
+	u8	status;			/* SCSI status */
+	u8	datapres;	/* [1:0] - data present, [7:2] - reserved */
+	u8	sense_response_data_len;	/* Sense/response data length */
+	__le32	residual_count;		/* Residual data length in bytes */
+	/* Sense/response data */
+	u8	sense_response_buf[HBA_SENSE_DATA_LEN_MAX];
+};
+
+struct aac_native_hba {
+	union {
+		struct aac_hba_cmd_req cmd;
+		struct aac_hba_tm_req tmr;
+		u8 cmd_bytes[AAC_MAX_NATIVE_SIZE-FW_ERROR_BUFFER_SIZE];
+	} cmd;
+	union {
+		struct aac_hba_resp err;
+		u8 resp_bytes[FW_ERROR_BUFFER_SIZE];
+	} resp;
+};
+
+#define CISS_REPORT_PHYSICAL_LUNS	0xc3
+#define WRITE_HOST_WELLNESS		0xa5
+#define CISS_IDENTIFY_PHYSICAL_DEVICE	0x15
+#define BMIC_IN			0x26
+#define BMIC_OUT			0x27
+
+struct aac_ciss_phys_luns_resp {
+	u8	list_length[4];		/* LUN list length (N-7, big endian) */
+	u8	resp_flag;		/* extended response_flag */
+	u8	reserved[3];
+	struct _ciss_lun {
+		u8	tid[3];		/* Target ID */
+		u8	bus;		/* Bus, flag (bits 6,7) */
+		u8	level3[2];
+		u8	level2[2];
+		u8	node_ident[16];	/* phys. node identifier */
+	} lun[1];			/* List of phys. devices */
+};
+
+/*
+ * Interrupts
+ */
+#define AAC_MAX_HRRQ		64
+
+struct aac_ciss_identify_pd {
+	u8 scsi_bus;			/* SCSI Bus number on controller */
+	u8 scsi_id;			/* SCSI ID on this bus */
+	u16 block_size;			/* sector size in bytes */
+	u32 total_blocks;		/* number for sectors on drive */
+	u32 reserved_blocks;		/* controller reserved (RIS) */
+	u8 model[40];			/* Physical Drive Model */
+	u8 serial_number[40];		/* Drive Serial Number */
+	u8 firmware_revision[8];	/* drive firmware revision */
+	u8 scsi_inquiry_bits;		/* inquiry byte 7 bits */
+	u8 compaq_drive_stamp;		/* 0 means drive not stamped */
+	u8 last_failure_reason;
+
+	u8  flags;
+	u8  more_flags;
+	u8  scsi_lun;			/* SCSI LUN for phys drive */
+	u8  yet_more_flags;
+	u8  even_more_flags;
+	u32 spi_speed_rules;		/* SPI Speed :Ultra disable diagnose */
+	u8  phys_connector[2];		/* connector number on controller */
+	u8  phys_box_on_bus;		/* phys enclosure this drive resides */
+	u8  phys_bay_in_box;		/* phys drv bay this drive resides */
+	u32 rpm;			/* Drive rotational speed in rpm */
+	u8  device_type;		/* type of drive */
+	u8  sata_version;		/* only valid when drive_type is SATA */
+	u64 big_total_block_count;
+	u64 ris_starting_lba;
+	u32 ris_size;
+	u8  wwid[20];
+	u8  controller_phy_map[32];
+	u16 phy_count;
+	u8  phy_connected_dev_type[256];
+	u8  phy_to_drive_bay_num[256];
+	u16 phy_to_attached_dev_index[256];
+	u8  box_index;
+	u8  spitfire_support;
+	u16 extra_physical_drive_flags;
+	u8  negotiated_link_rate[256];
+	u8  phy_to_phy_map[256];
+	u8  redundant_path_present_map;
+	u8  redundant_path_failure_map;
+	u8  active_path_number;
+	u16 alternate_paths_phys_connector[8];
+	u8  alternate_paths_phys_box_on_port[8];
+	u8  multi_lun_device_lun_count;
+	u8  minimum_good_fw_revision[8];
+	u8  unique_inquiry_bytes[20];
+	u8  current_temperature_degreesC;
+	u8  temperature_threshold_degreesC;
+	u8  max_temperature_degreesC;
+	u8  logical_blocks_per_phys_block_exp;	/* phyblocksize = 512 * 2^exp */
+	u16 current_queue_depth_limit;
+	u8  switch_name[10];
+	u16 switch_port;
+	u8  alternate_paths_switch_name[40];
+	u8  alternate_paths_switch_port[8];
+	u16 power_on_hours;		/* valid only if gas gauge supported */
+	u16 percent_endurance_used;	/* valid only if gas gauge supported. */
+	u8  drive_authentication;
+	u8  smart_carrier_authentication;
+	u8  smart_carrier_app_fw_version;
+	u8  smart_carrier_bootloader_fw_version;
+	u8  SanitizeSecureEraseSupport;
+	u8  DriveKeyFlags;
+	u8  encryption_key_name[64];
+	u32 misc_drive_flags;
+	u16 dek_index;
+	u16 drive_encryption_flags;
+	u8  sanitize_maximum_time[6];
+	u8  connector_info_mode;
+	u8  connector_info_number[4];
+	u8  long_connector_name[64];
+	u8  device_unique_identifier[16];
+	u8  padto_2K[17];
+} __packed;
+
 /*
  * These macros convert from physical channels to virtual channels
  */
@@ -86,6 +418,7 @@ enum {
 #define CONTAINER_TO_CHANNEL(cont)	(CONTAINER_CHANNEL)
 #define CONTAINER_TO_ID(cont)		(cont)
 #define CONTAINER_TO_LUN(cont)		(0)
+#define ENCLOSURE_CHANNEL		(3)
 
 #define PMC_DEVICE_S6	0x28b
 #define PMC_DEVICE_S7	0x28c
@@ -351,10 +684,10 @@ enum aac_queue_types {
 
 /* transport FIB header (PMC) */
 struct aac_fib_xporthdr {
-	u64	HostAddress;	/* FIB host address w/o xport header */
-	u32	Size;		/* FIB size excluding xport header */
-	u32	Handle;		/* driver handle to reference the FIB */
-	u64	Reserved[2];
+	__le64	HostAddress;	/* FIB host address w/o xport header */
+	__le32	Size;		/* FIB size excluding xport header */
+	__le32	Handle;		/* driver handle to reference the FIB */
+	__le64	Reserved[2];
 };
 
 #define		ALIGN32		32
@@ -379,7 +712,7 @@ struct aac_fibhdr {
 		__le32 SenderFibAddressHigh;/* upper 32bit of phys. FIB address */
 		__le32 TimeStamp;	/* otherwise timestamp for FW internal use */
 	} u;
-	u32 Handle;		/* FIB handle used for MSGU commnunication */
+	__le32 Handle;		/* FIB handle used for MSGU commnunication */
 	u32 Previous;		/* FW internal use */
 	u32 Next;		/* FW internal use */
 };
@@ -489,41 +822,64 @@ enum fib_xfer_state {
 #define ADAPTER_INIT_STRUCT_REVISION_4		4 // rocket science
 #define ADAPTER_INIT_STRUCT_REVISION_6		6 /* PMC src */
 #define ADAPTER_INIT_STRUCT_REVISION_7		7 /* Denali */
+#define ADAPTER_INIT_STRUCT_REVISION_8		8 // Thor
 
-struct aac_init
+union aac_init
 {
-	__le32	InitStructRevision;
-	__le32	Sa_MSIXVectors;
-	__le32	fsrev;
-	__le32	CommHeaderAddress;
-	__le32	FastIoCommAreaAddress;
-	__le32	AdapterFibsPhysicalAddress;
-	__le32	AdapterFibsVirtualAddress;
-	__le32	AdapterFibsSize;
-	__le32	AdapterFibAlign;
-	__le32	printfbuf;
-	__le32	printfbufsiz;
-	__le32	HostPhysMemPages;   /* number of 4k pages of host
-				       physical memory */
-	__le32	HostElapsedSeconds; /* number of seconds since 1970. */
-	/*
-	 * ADAPTER_INIT_STRUCT_REVISION_4 begins here
-	 */
-	__le32	InitFlags;	/* flags for supported features */
+	struct _r7 {
+		__le32	init_struct_revision;
+		__le32	no_of_msix_vectors;
+		__le32	fsrev;
+		__le32	comm_header_address;
+		__le32	fast_io_comm_area_address;
+		__le32	adapter_fibs_physical_address;
+		__le32	adapter_fibs_virtual_address;
+		__le32	adapter_fibs_size;
+		__le32	adapter_fib_align;
+		__le32	printfbuf;
+		__le32	printfbufsiz;
+		/* number of 4k pages of host phys. mem. */
+		__le32	host_phys_mem_pages;
+		/* number of seconds since 1970. */
+		__le32	host_elapsed_seconds;
+		/* ADAPTER_INIT_STRUCT_REVISION_4 begins here */
+		__le32	init_flags;	/* flags for supported features */
 #define INITFLAGS_NEW_COMM_SUPPORTED	0x00000001
 #define INITFLAGS_DRIVER_USES_UTC_TIME	0x00000010
 #define INITFLAGS_DRIVER_SUPPORTS_PM	0x00000020
 #define INITFLAGS_NEW_COMM_TYPE1_SUPPORTED	0x00000040
 #define INITFLAGS_FAST_JBOD_SUPPORTED	0x00000080
 #define INITFLAGS_NEW_COMM_TYPE2_SUPPORTED	0x00000100
-	__le32	MaxIoCommands;	/* max outstanding commands */
-	__le32	MaxIoSize;	/* largest I/O command */
-	__le32	MaxFibSize;	/* largest FIB to adapter */
-	/* ADAPTER_INIT_STRUCT_REVISION_5 begins here */
-	__le32	MaxNumAif;	/* max number of aif */
-	/* ADAPTER_INIT_STRUCT_REVISION_6 begins here */
-	__le32	HostRRQ_AddrLow;
-	__le32	HostRRQ_AddrHigh;	/* Host RRQ (response queue) for SRC */
+#define INITFLAGS_DRIVER_SUPPORTS_HBA_MODE  0x00000400
+		__le32	max_io_commands;	/* max outstanding commands */
+		__le32	max_io_size;	/* largest I/O command */
+		__le32	max_fib_size;	/* largest FIB to adapter */
+		/* ADAPTER_INIT_STRUCT_REVISION_5 begins here */
+		__le32	max_num_aif;	/* max number of aif */
+		/* ADAPTER_INIT_STRUCT_REVISION_6 begins here */
+		/* Host RRQ (response queue) for SRC */
+		__le32	host_rrq_addr_low;
+		__le32	host_rrq_addr_high;
+	} r7;
+	struct _r8 {
+		/* ADAPTER_INIT_STRUCT_REVISION_8 */
+		__le32	init_struct_revision;
+		__le32	rr_queue_count;
+		__le32	host_elapsed_seconds; /* number of secs since 1970. */
+		__le32	init_flags;
+		__le32	max_io_size;	/* largest I/O command */
+		__le32	max_num_aif;	/* max number of aif */
+		__le32	reserved1;
+		__le32	reserved2;
+		struct _rrq {
+			__le32	host_addr_low;
+			__le32	host_addr_high;
+			__le16	msix_id;
+			__le16	element_count;
+			__le16	comp_thresh;
+			__le16	unused;
+		} rrq[1];		/* up to 64 RRQ addresses */
+	} r8;
 };
 
 enum aac_log_level {
@@ -554,7 +910,7 @@ struct adapter_ops
 	void (*adapter_enable_int)(struct aac_dev *dev);
 	int  (*adapter_sync_cmd)(struct aac_dev *dev, u32 command, u32 p1, u32 p2, u32 p3, u32 p4, u32 p5, u32 p6, u32 *status, u32 *r1, u32 *r2, u32 *r3, u32 *r4);
 	int  (*adapter_check_health)(struct aac_dev *dev);
-	int  (*adapter_restart)(struct aac_dev *dev, int bled);
+	int  (*adapter_restart)(struct aac_dev *dev, int bled, u8 reset_type);
 	void (*adapter_start)(struct aac_dev *dev);
 	/* Transport operations */
 	int  (*adapter_ioremap)(struct aac_dev * dev, u32 size);
@@ -727,6 +1083,7 @@ struct sa_registers {
 
 
 #define SA_INIT_NUM_MSIXVECTORS		1
+#define SA_MINIPORT_REVISION		SA_INIT_NUM_MSIXVECTORS
 
 #define sa_readw(AEP, CSR)		readl(&((AEP)->regs.sa->CSR))
 #define sa_readl(AEP, CSR)		readl(&((AEP)->regs.sa->CSR))
@@ -820,32 +1177,37 @@ struct rkt_registers {
 #define src_inbound rx_inbound
 
 struct src_mu_registers {
-				/*	PCI*| Name */
-	__le32	reserved0[6];	/*	00h | Reserved */
-	__le32	IOAR[2];	/*	18h | IOA->host interrupt register */
-	__le32	IDR;		/*	20h | Inbound Doorbell Register */
-	__le32	IISR;		/*	24h | Inbound Int. Status Register */
-	__le32	reserved1[3];	/*	28h | Reserved */
-	__le32	OIMR;		/*	34h | Outbound Int. Mask Register */
-	__le32	reserved2[25];	/*	38h | Reserved */
-	__le32	ODR_R;		/*	9ch | Outbound Doorbell Read */
-	__le32	ODR_C;		/*	a0h | Outbound Doorbell Clear */
-	__le32	reserved3[6];	/*	a4h | Reserved */
-	__le32	OMR;		/*	bch | Outbound Message Register */
+				/*  PCI*| Name */
+	__le32	reserved0[6];	/*  00h | Reserved */
+	__le32	IOAR[2];	/*  18h | IOA->host interrupt register */
+	__le32	IDR;		/*  20h | Inbound Doorbell Register */
+	__le32	IISR;		/*  24h | Inbound Int. Status Register */
+	__le32	reserved1[3];	/*  28h | Reserved */
+	__le32	OIMR;		/*  34h | Outbound Int. Mask Register */
+	__le32	reserved2[25];  /*  38h | Reserved */
+	__le32	ODR_R;		/*  9ch | Outbound Doorbell Read */
+	__le32	ODR_C;		/*  a0h | Outbound Doorbell Clear */
+	__le32	reserved3[3];	/*  a4h | Reserved */
+	__le32	SCR0;		/*  b0h | Scratchpad 0 */
+	__le32	reserved4[2];	/*  b4h | Reserved */
+	__le32	OMR;		/*  bch | Outbound Message Register */
 	__le32	IQ_L;		/*  c0h | Inbound Queue (Low address) */
 	__le32	IQ_H;		/*  c4h | Inbound Queue (High address) */
 	__le32	ODR_MSI;	/*  c8h | MSI register for sync./AIF */
+	__le32  reserved5;	/*  cch | Reserved */
+	__le32	IQN_L;		/*  d0h | Inbound (native cmd) low  */
+	__le32	IQN_H;		/*  d4h | Inbound (native cmd) high */
 };
 
 struct src_registers {
 	struct src_mu_registers MUnit;	/* 00h - cbh */
 	union {
 		struct {
-			__le32 reserved1[130789];	/* cch - 7fc5fh */
+			__le32 reserved1[130786];	/* d8h - 7fc5fh */
 			struct src_inbound IndexRegs;	/* 7fc60h */
 		} tupelo;
 		struct {
-			__le32 reserved1[973];		/* cch - fffh */
+			__le32 reserved1[970];		/* d8h - fffh */
 			struct src_inbound IndexRegs;	/* 1000h */
 		} denali;
 	} u;
@@ -930,6 +1292,7 @@ struct fsa_dev_info {
 	char		devname[8];
 	struct sense_data sense_data;
 	u32		block_size;
+	u8		identifier[16];
 };
 
 struct fib {
@@ -958,8 +1321,30 @@ struct fib {
 	struct list_head	fiblink;
 	void			*data;
 	u32			vector_no;
-	struct hw_fib		*hw_fib_va;		/* Actual shared object */
-	dma_addr_t		hw_fib_pa;		/* physical address of hw_fib*/
+	struct hw_fib		*hw_fib_va;	/* also used for native */
+	dma_addr_t		hw_fib_pa;	/* physical address of hw_fib*/
+	dma_addr_t		hw_sgl_pa;	/* extra sgl for native */
+	dma_addr_t		hw_error_pa;	/* error buffer for native */
+	u32			hbacmd_size;	/* cmd size for native */
+};
+
+#define AAC_INIT			0
+#define AAC_RESCAN			1
+
+#define AAC_DEVTYPE_RAID_MEMBER	1
+#define AAC_DEVTYPE_ARC_RAW		2
+#define AAC_DEVTYPE_NATIVE_RAW		3
+#define AAC_EXPOSE_DISK		0
+#define AAC_HIDE_DISK			3
+
+struct aac_hba_map_info {
+	__le32	rmw_nexus;		/* nexus for native HBA devices */
+	u8		devtype;	/* device type */
+	u8		new_devtype;
+	u8		reset_state;	/* 0 - no reset, 1..x - */
+					/* after xth TM LUN reset */
+	u16		qd_limit;
+	u8		expose;		/*checks if to expose or not*/
 };
 
 /*
@@ -1025,7 +1410,28 @@ struct aac_supplement_adapter_info
 	/* StructExpansion == 1 */
 	__le32	FeatureBits3;
 	__le32	SupportedPerformanceModes;
-	__le32	ReservedForFutureGrowth[80];
+	u8	HostBusType;		/* uses HOST_BUS_TYPE_xxx defines */
+	u8	HostBusWidth;		/* actual width in bits or links */
+	u16	HostBusSpeed;		/* actual bus speed/link rate in MHz */
+	u8	MaxRRCDrives;		/* max. number of ITP-RRC drives/pool */
+	u8	MaxDiskXtasks;		/* max. possible num of DiskX Tasks */
+
+	u8	CpldVerLoaded;
+	u8	CpldVerInFlash;
+
+	__le64	MaxRRCCapacity;
+	__le32	CompiledMaxHistLogLevel;
+	u8	CustomBoardName[12];
+	u16	SupportedCntlrMode;	/* identify supported controller mode */
+	u16	ReservedForFuture16;
+	__le32	SupportedOptions3;	/* reserved for future options */
+
+	__le16	VirtDeviceBus;		/* virt. SCSI device for Thor */
+	__le16	VirtDeviceTarget;
+	__le16	VirtDeviceLUN;
+	__le16	Unused;
+	__le32	ReservedForFutureGrowth[68];
+
 };
 #define AAC_FEATURE_FALCON	cpu_to_le32(0x00000010)
 #define AAC_FEATURE_JBOD	cpu_to_le32(0x08000000)
@@ -1099,11 +1505,21 @@ struct aac_bus_info_response {
 #define AAC_OPT_SUPPLEMENT_ADAPTER_INFO	cpu_to_le32(1<<16)
 #define AAC_OPT_NEW_COMM		cpu_to_le32(1<<17)
 #define AAC_OPT_NEW_COMM_64		cpu_to_le32(1<<18)
+#define AAC_OPT_EXTENDED		cpu_to_le32(1<<23)
+#define AAC_OPT_NATIVE_HBA		cpu_to_le32(1<<25)
 #define AAC_OPT_NEW_COMM_TYPE1		cpu_to_le32(1<<28)
 #define AAC_OPT_NEW_COMM_TYPE2		cpu_to_le32(1<<29)
 #define AAC_OPT_NEW_COMM_TYPE3		cpu_to_le32(1<<30)
 #define AAC_OPT_NEW_COMM_TYPE4		cpu_to_le32(1<<31)
 
+#define AAC_COMM_PRODUCER		0
+#define AAC_COMM_MESSAGE		1
+#define AAC_COMM_MESSAGE_TYPE1		3
+#define AAC_COMM_MESSAGE_TYPE2		4
+#define AAC_COMM_MESSAGE_TYPE3		5
+
+#define AAC_EXTOPT_SA_FIRMWARE		cpu_to_le32(1<<1)
+
 /* MSIX context */
 struct aac_msix_ctx {
 	int		vector_no;
@@ -1119,15 +1535,17 @@ struct aac_dev
 	/*
 	 *	negotiated FIB settings
 	 */
-	unsigned		max_fib_size;
-	unsigned		sg_tablesize;
-	unsigned		max_num_aif;
+	unsigned int		max_fib_size;
+	unsigned int		sg_tablesize;
+	unsigned int		max_num_aif;
+
+	unsigned int		max_cmd_size;	/* max_fib_size or MAX_NATIVE */
 
 	/*
 	 *	Map for 128 fib objects (64k)
 	 */
-	dma_addr_t		hw_fib_pa;
-	struct hw_fib		*hw_fib_va;
+	dma_addr_t		hw_fib_pa;	/* also used for native cmd */
+	struct hw_fib		*hw_fib_va;	/* also used for native cmd */
 	struct hw_fib		*aif_base_va;
 	/*
 	 *	Fib Headers
@@ -1157,21 +1575,23 @@ struct aac_dev
 
 	resource_size_t		base_size, dbg_size;	/* Size of
 							 *  mapped in region */
-
-	struct aac_init		*init;		/* Holds initialization info to communicate with adapter */
+	/*
+	 * Holds initialization info
+	 * to communicate with adapter
+	 */
+	union aac_init		*init;
 	dma_addr_t		init_pa;	/* Holds physical address of the init struct */
-
-	u32			*host_rrq;	/* response queue
-						 * if AAC_COMM_MESSAGE_TYPE1 */
-
+	/* response queue (if AAC_COMM_MESSAGE_TYPE1) */
+	__le32			*host_rrq;
 	dma_addr_t		host_rrq_pa;	/* phys. address */
 	/* index into rrq buffer */
 	u32			host_rrq_idx[AAC_MAX_MSIX];
 	atomic_t		rrq_outstanding[AAC_MAX_MSIX];
 	u32			fibs_pushed_no;
 	struct pci_dev		*pdev;		/* Our PCI interface */
-	void *			printfbuf;	/* pointer to buffer used for printf's from the adapter */
-	void *			comm_addr;	/* Base address of Comm area */
+	/* pointer to buffer used for printf's from the adapter */
+	void			*printfbuf;
+	void			*comm_addr;	/* Base address of Comm area */
 	dma_addr_t		comm_phys;	/* Physical Address of Comm area */
 	size_t			comm_size;
 
@@ -1227,15 +1647,12 @@ struct aac_dev
 	u8			needs_dac;
 	u8			raid_scsi_mode;
 	u8			comm_interface;
-#	define AAC_COMM_PRODUCER 0
-#	define AAC_COMM_MESSAGE  1
-#	define AAC_COMM_MESSAGE_TYPE1	3
-#	define AAC_COMM_MESSAGE_TYPE2	4
 	u8			raw_io_interface;
 	u8			raw_io_64;
 	u8			printf_enabled;
 	u8			in_reset;
 	u8			msi;
+	u8			sa_firmware;
 	int			management_fib_count;
 	spinlock_t		manage_lock;
 	spinlock_t		sync_lock;
@@ -1246,7 +1663,10 @@ struct aac_dev
 	u32			max_msix;	/* max. MSI-X vectors */
 	u32			vector_cap;	/* MSI-X vector capab.*/
 	int			msi_enabled;	/* MSI/MSI-X enabled */
+	atomic_t		msix_counter;
+	struct msix_entry	msixentry[AAC_MAX_MSIX];
 	struct aac_msix_ctx	aac_msix[AAC_MAX_MSIX]; /* context */
+	struct aac_hba_map_info	hba_map[AAC_MAX_BUSES][AAC_MAX_TARGETS];
 	u8			adapter_shutdown;
 	u32			handle_pci_error;
 };
@@ -1269,8 +1689,8 @@ struct aac_dev
 #define aac_adapter_check_health(dev) \
 	(dev)->a_ops.adapter_check_health(dev)
 
-#define aac_adapter_restart(dev,bled) \
-	(dev)->a_ops.adapter_restart(dev,bled)
+#define aac_adapter_restart(dev, bled, reset_type) \
+	((dev)->a_ops.adapter_restart(dev, bled, reset_type))
 
 #define aac_adapter_start(dev) \
 	((dev)->a_ops.adapter_start(dev))
@@ -1300,6 +1720,8 @@ struct aac_dev
 #define FIB_CONTEXT_FLAG			(0x00000002)
 #define FIB_CONTEXT_FLAG_WAIT			(0x00000004)
 #define FIB_CONTEXT_FLAG_FASTRESP		(0x00000008)
+#define FIB_CONTEXT_FLAG_NATIVE_HBA		(0x00000010)
+#define FIB_CONTEXT_FLAG_NATIVE_HBA_TMF	(0x00000020)
 
 /*
  *	Define the command values
@@ -1358,6 +1780,7 @@ struct aac_dev
 #define		ST_IO		5
 #define		ST_NXIO		6
 #define		ST_E2BIG	7
+#define		ST_MEDERR	8
 #define		ST_ACCES	13
 #define		ST_EXIST	17
 #define		ST_XDEV		18
@@ -1715,6 +2138,8 @@ struct aac_fsinfo {
 
 struct  aac_blockdevinfo {
 	__le32	block_size;
+	__le32  logical_phys_map;
+	u8	identifier[16];
 };
 
 union aac_contentinfo {
@@ -1940,6 +2365,15 @@ struct revision
 #define FSACTL_FORCE_DELETE_DISK		CTL_CODE(2120, METHOD_NEITHER)
 #define FSACTL_GET_CONTAINERS			2131
 #define FSACTL_SEND_LARGE_FIB			CTL_CODE(2138, METHOD_BUFFERED)
+#define FSACTL_RESET_IOP			CTL_CODE(2140, METHOD_BUFFERED)
+#define FSACTL_GET_HBA_INFO			CTL_CODE(2150, METHOD_BUFFERED)
+/* flags defined for IOP & HW SOFT RESET */
+#define HW_IOP_RESET				0x01
+#define HW_SOFT_RESET				0x02
+#define IOP_HWSOFT_RESET			(HW_IOP_RESET | HW_SOFT_RESET)
+/* HW Soft Reset register offset */
+#define IBW_SWR_OFFSET				0x4000
+#define SOFT_RESET_TIME			60
 
 
 struct aac_common
@@ -1958,6 +2392,8 @@ struct aac_common
 #ifdef DBG
 	u32 FibsSent;
 	u32 FibRecved;
+	u32 NativeSent;
+	u32 NativeRecved;
 	u32 NoResponseSent;
 	u32 NoResponseRecved;
 	u32 AsyncSent;
@@ -1969,6 +2405,56 @@ struct aac_common
 
 extern struct aac_common aac_config;
 
+/*
+ * This is for management ioctl purpose only.
+ */
+struct aac_hba_info {
+
+	u8	driver_name[50];
+	u8	adapter_number;
+	u8	system_io_bus_number;
+	u8	device_number;
+	u32	function_number;
+	u32	vendor_id;
+	u32	device_id;
+	u32	sub_vendor_id;
+	u32	sub_system_id;
+	u32	mapped_base_address_size;
+	u32	base_physical_address_high_part;
+	u32	base_physical_address_low_part;
+
+	u32	max_command_size;
+	u32	max_fib_size;
+	u32	max_scatter_gather_from_os;
+	u32	max_scatter_gather_to_fw;
+	u32	max_outstanding_fibs;
+
+	u32	queue_start_threshold;
+	u32	queue_dump_threshold;
+	u32	max_io_size_queued;
+	u32	outstanding_io;
+
+	u32	firmware_build_number;
+	u32	bios_build_number;
+	u32	driver_build_number;
+	u32	serial_number_high_part;
+	u32	serial_number_low_part;
+	u32	supported_options;
+	u32	feature_bits;
+	u32	currentnumber_ports;
+
+	u8	new_comm_interface:1;
+	u8	new_commands_supported:1;
+	u8	disable_passthrough:1;
+	u8	expose_non_dasd:1;
+	u8	queue_allowed:1;
+	u8	bled_check_enabled:1;
+	u8	reserved1:1;
+	u8	reserted2:1;
+
+	u32	reserved3[10];
+
+};
 
 /*
  *	The following macro is used when sending and receiving FIBs. It is
@@ -2096,9 +2582,10 @@ extern struct aac_common aac_config;
 
 /* PMC NEW COMM: Request the event data */
 #define		AifReqEvent		200
+#define		AifRawDeviceRemove	203	/* RAW device deleted */
+#define		AifNativeDeviceAdd	204	/* native HBA device added */
+#define		AifNativeDeviceRemove	205	/* native HBA device removed */
 
-/* RAW device deleted */
-#define		AifRawDeviceRemove	203
 
 /*
  *	Adapter Initiated FIB command structures. Start with the adapter
@@ -2131,6 +2618,8 @@ static inline unsigned int cap_to_cyls(sector_t capacity, unsigned divisor)
 
 int aac_acquire_irq(struct aac_dev *dev);
 void aac_free_irq(struct aac_dev *dev);
+int aac_report_phys_luns(struct aac_dev *dev, struct fib *fibptr, int rescan);
+int aac_issue_bmic_identify(struct aac_dev *dev, u32 bus, u32 target);
 const char *aac_driverinfo(struct Scsi_Host *);
 void aac_fib_vector_assign(struct aac_dev *dev);
 struct fib *aac_fib_alloc(struct aac_dev *dev);
@@ -2141,9 +2630,12 @@ void aac_fib_free(struct fib * context);
 void aac_fib_init(struct fib * context);
 void aac_printf(struct aac_dev *dev, u32 val);
 int aac_fib_send(u16 command, struct fib * context, unsigned long size, int priority, int wait, int reply, fib_callback callback, void *ctxt);
+int aac_hba_send(u8 command, struct fib *context,
+		fib_callback callback, void *ctxt);
 int aac_consumer_get(struct aac_dev * dev, struct aac_queue * q, struct aac_entry **entry);
 void aac_consumer_free(struct aac_dev * dev, struct aac_queue * q, u32 qnum);
 int aac_fib_complete(struct fib * context);
+void aac_hba_callback(void *context, struct fib *fibptr);
 #define fib_data(fibctx) ((void *)(fibctx)->hw_fib_va->data)
 struct aac_dev *aac_init_adapter(struct aac_dev *dev);
 void aac_src_access_devreg(struct aac_dev *dev, int mode);
@@ -2169,7 +2661,7 @@ unsigned int aac_command_normal(struct aac_queue * q);
 unsigned int aac_intr_normal(struct aac_dev *dev, u32 Index,
 			int isAif, int isFastResponse,
 			struct hw_fib *aif_fib);
-int aac_reset_adapter(struct aac_dev * dev, int forced);
+int aac_reset_adapter(struct aac_dev *dev, int forced, u8 reset_type);
 int aac_check_health(struct aac_dev * dev);
 int aac_command_thread(void *data);
 int aac_close_fib_context(struct aac_dev * dev, struct aac_fib_context *fibctx);
@@ -2183,7 +2675,6 @@ int aac_rx_select_comm(struct aac_dev *dev, int comm);
 int aac_rx_deliver_producer(struct fib * fib);
 char * get_container_type(unsigned type);
 extern int numacb;
-extern int acbsize;
 extern char aac_driver_version[];
 extern int startup_timeout;
 extern int aif_timeout;
@@ -2194,3 +2685,4 @@ extern int aac_commit;
 extern int update_interval;
 extern int check_interval;
 extern int aac_check_reset;
+#endif
diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c
index e1daff230c7d..614842a9eb07 100644
--- a/drivers/scsi/aacraid/commctrl.c
+++ b/drivers/scsi/aacraid/commctrl.c
@@ -6,7 +6,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -477,20 +478,24 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 	struct fib* srbfib;
 	int status;
 	struct aac_srb *srbcmd = NULL;
+	struct aac_hba_cmd_req *hbacmd = NULL;
 	struct user_aac_srb *user_srbcmd = NULL;
 	struct user_aac_srb __user *user_srb = arg;
 	struct aac_srb_reply __user *user_reply;
-	struct aac_srb_reply* reply;
+	u32 chn;
 	u32 fibsize = 0;
 	u32 flags = 0;
 	s32 rcode = 0;
 	u32 data_dir;
-	void __user *sg_user[32];
-	void *sg_list[32];
+	void __user *sg_user[HBA_MAX_SG_EMBEDDED];
+	void *sg_list[HBA_MAX_SG_EMBEDDED];
+	u32 sg_count[HBA_MAX_SG_EMBEDDED];
 	u32 sg_indx = 0;
 	u32 byte_count = 0;
 	u32 actual_fibsize64, actual_fibsize = 0;
 	int i;
+	int is_native_device;
+	u64 address;
 
 
 	if (dev->in_reset) {
@@ -507,11 +512,6 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 	if (!(srbfib = aac_fib_alloc(dev))) {
 		return -ENOMEM;
 	}
-	aac_fib_init(srbfib);
-	/* raw_srb FIB is not FastResponseCapable */
-	srbfib->hw_fib_va->header.XferState &= ~cpu_to_le32(FastResponseCapable);
-
-	srbcmd = (struct aac_srb*) fib_data(srbfib);
 
 	memset(sg_list, 0, sizeof(sg_list)); /* cleanup may take issue */
 	if(copy_from_user(&fibsize, &user_srb->count,sizeof(u32))){
@@ -538,21 +538,7 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 		goto cleanup;
 	}
 
-	user_reply = arg+fibsize;
-
 	flags = user_srbcmd->flags; /* from user in cpu order */
-	// Fix up srb for endian and force some values
-
-	srbcmd->function = cpu_to_le32(SRBF_ExecuteScsi);	// Force this
-	srbcmd->channel	 = cpu_to_le32(user_srbcmd->channel);
-	srbcmd->id	 = cpu_to_le32(user_srbcmd->id);
-	srbcmd->lun	 = cpu_to_le32(user_srbcmd->lun);
-	srbcmd->timeout	 = cpu_to_le32(user_srbcmd->timeout);
-	srbcmd->flags	 = cpu_to_le32(flags);
-	srbcmd->retry_limit = 0; // Obsolete parameter
-	srbcmd->cdb_size = cpu_to_le32(user_srbcmd->cdb_size);
-	memcpy(srbcmd->cdb, user_srbcmd->cdb, sizeof(srbcmd->cdb));
-
 	switch (flags & (SRB_DataIn | SRB_DataOut)) {
 	case SRB_DataOut:
 		data_dir = DMA_TO_DEVICE;
@@ -568,7 +554,12 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 	}
 	if (user_srbcmd->sg.count > ARRAY_SIZE(sg_list)) {
 		dprintk((KERN_DEBUG"aacraid: too many sg entries %d\n",
-		  le32_to_cpu(srbcmd->sg.count)));
+			user_srbcmd->sg.count));
+		rcode = -EINVAL;
+		goto cleanup;
+	}
+	if ((data_dir == DMA_NONE) && user_srbcmd->sg.count) {
+		dprintk((KERN_DEBUG"aacraid:SG with no direction specified\n"));
 		rcode = -EINVAL;
 		goto cleanup;
 	}
@@ -588,13 +579,136 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 		rcode = -EINVAL;
 		goto cleanup;
 	}
-	if ((data_dir == DMA_NONE) && user_srbcmd->sg.count) {
-		dprintk((KERN_DEBUG"aacraid: SG with no direction specified in Raw SRB command\n"));
-		rcode = -EINVAL;
-		goto cleanup;
+
+	chn = aac_logical_to_phys(user_srbcmd->channel);
+	if (chn < AAC_MAX_BUSES && user_srbcmd->id < AAC_MAX_TARGETS &&
+		dev->hba_map[chn][user_srbcmd->id].devtype ==
+		AAC_DEVTYPE_NATIVE_RAW) {
+		is_native_device = 1;
+		hbacmd = (struct aac_hba_cmd_req *)srbfib->hw_fib_va;
+		memset(hbacmd, 0, 96);	/* sizeof(*hbacmd) is not necessary */
+
+		/* iu_type is a parameter of aac_hba_send */
+		switch (data_dir) {
+		case DMA_TO_DEVICE:
+			hbacmd->byte1 = 2;
+			break;
+		case DMA_FROM_DEVICE:
+		case DMA_BIDIRECTIONAL:
+			hbacmd->byte1 = 1;
+			break;
+		case DMA_NONE:
+		default:
+			break;
+		}
+		hbacmd->lun[1] = cpu_to_le32(user_srbcmd->lun);
+		hbacmd->it_nexus = dev->hba_map[chn][user_srbcmd->id].rmw_nexus;
+
+		/*
+		 * we fill in reply_qid later in aac_src_deliver_message
+		 * we fill in iu_type, request_id later in aac_hba_send
+		 * we fill in emb_data_desc_count, data_length later
+		 * in sg list build
+		 */
+
+		memcpy(hbacmd->cdb, user_srbcmd->cdb, sizeof(hbacmd->cdb));
+
+		address = (u64)srbfib->hw_error_pa;
+		hbacmd->error_ptr_hi = cpu_to_le32((u32)(address >> 32));
+		hbacmd->error_ptr_lo = cpu_to_le32((u32)(address & 0xffffffff));
+		hbacmd->error_length = cpu_to_le32(FW_ERROR_BUFFER_SIZE);
+		hbacmd->emb_data_desc_count =
+					cpu_to_le32(user_srbcmd->sg.count);
+		srbfib->hbacmd_size = 64 +
+			user_srbcmd->sg.count * sizeof(struct aac_hba_sgl);
+
+	} else {
+		is_native_device = 0;
+		aac_fib_init(srbfib);
+
+		/* raw_srb FIB is not FastResponseCapable */
+		srbfib->hw_fib_va->header.XferState &=
+			~cpu_to_le32(FastResponseCapable);
+
+		srbcmd = (struct aac_srb *) fib_data(srbfib);
+
+		// Fix up srb for endian and force some values
+
+		srbcmd->function = cpu_to_le32(SRBF_ExecuteScsi); // Force this
+		srbcmd->channel	 = cpu_to_le32(user_srbcmd->channel);
+		srbcmd->id	 = cpu_to_le32(user_srbcmd->id);
+		srbcmd->lun	 = cpu_to_le32(user_srbcmd->lun);
+		srbcmd->timeout	 = cpu_to_le32(user_srbcmd->timeout);
+		srbcmd->flags	 = cpu_to_le32(flags);
+		srbcmd->retry_limit = 0; // Obsolete parameter
+		srbcmd->cdb_size = cpu_to_le32(user_srbcmd->cdb_size);
+		memcpy(srbcmd->cdb, user_srbcmd->cdb, sizeof(srbcmd->cdb));
 	}
+
 	byte_count = 0;
-	if (dev->adapter_info.options & AAC_OPT_SGMAP_HOST64) {
+	if (is_native_device) {
+		struct user_sgmap *usg32 = &user_srbcmd->sg;
+		struct user_sgmap64 *usg64 =
+			(struct user_sgmap64 *)&user_srbcmd->sg;
+
+		for (i = 0; i < usg32->count; i++) {
+			void *p;
+			u64 addr;
+
+			sg_count[i] = (actual_fibsize64 == fibsize) ?
+				usg64->sg[i].count : usg32->sg[i].count;
+			if (sg_count[i] >
+				(dev->scsi_host_ptr->max_sectors << 9)) {
+				pr_err("aacraid: upsg->sg[%d].count=%u>%u\n",
+					i, sg_count[i],
+					dev->scsi_host_ptr->max_sectors << 9);
+				rcode = -EINVAL;
+				goto cleanup;
+			}
+
+			p = kmalloc(sg_count[i], GFP_KERNEL|__GFP_DMA);
+			if (!p) {
+				rcode = -ENOMEM;
+				goto cleanup;
+			}
+
+			if (actual_fibsize64 == fibsize) {
+				addr = (u64)usg64->sg[i].addr[0];
+				addr += ((u64)usg64->sg[i].addr[1]) << 32;
+			} else {
+				addr = (u64)usg32->sg[i].addr;
+			}
+
+			sg_user[i] = (void __user *)(uintptr_t)addr;
+			sg_list[i] = p; // save so we can clean up later
+			sg_indx = i;
+
+			if (flags & SRB_DataOut) {
+				if (copy_from_user(p, sg_user[i],
+					sg_count[i])) {
+					rcode = -EFAULT;
+					goto cleanup;
+				}
+			}
+			addr = pci_map_single(dev->pdev, p, sg_count[i],
+						data_dir);
+			hbacmd->sge[i].addr_hi = cpu_to_le32((u32)(addr>>32));
+			hbacmd->sge[i].addr_lo = cpu_to_le32(
+						(u32)(addr & 0xffffffff));
+			hbacmd->sge[i].len = cpu_to_le32(sg_count[i]);
+			hbacmd->sge[i].flags = 0;
+			byte_count += sg_count[i];
+		}
+
+		if (usg32->count > 0)	/* embedded sglist */
+			hbacmd->sge[usg32->count-1].flags =
+				cpu_to_le32(0x40000000);
+		hbacmd->data_length = cpu_to_le32(byte_count);
+
+		status = aac_hba_send(HBA_IU_TYPE_SCSI_CMD_REQ, srbfib,
+					NULL, NULL);
+
+	} else if (dev->adapter_info.options & AAC_OPT_SGMAP_HOST64) {
 		struct user_sgmap64* upsg = (struct user_sgmap64*)&user_srbcmd->sg;
 		struct sgmap64* psg = (struct sgmap64*)&srbcmd->sg;
 
@@ -606,7 +720,9 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 			for (i = 0; i < upsg->count; i++) {
 				u64 addr;
 				void* p;
-				if (upsg->sg[i].count >
+
+				sg_count[i] = upsg->sg[i].count;
+				if (sg_count[i] >
 				    ((dev->adapter_info.options &
 				     AAC_OPT_NEW_COMM) ?
 				      (dev->scsi_host_ptr->max_sectors << 9) :
@@ -615,10 +731,10 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 					goto cleanup;
 				}
 				/* Does this really need to be GFP_DMA? */
-				p = kmalloc(upsg->sg[i].count,GFP_KERNEL|__GFP_DMA);
+				p = kmalloc(sg_count[i], GFP_KERNEL|__GFP_DMA);
 				if(!p) {
 					dprintk((KERN_DEBUG"aacraid: Could not allocate SG buffer - size = %d buffer number %d of %d\n",
-					  upsg->sg[i].count,i,upsg->count));
+					  sg_count[i], i, upsg->count));
 					rcode = -ENOMEM;
 					goto cleanup;
 				}
@@ -629,18 +745,20 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 				sg_indx = i;
 
 				if (flags & SRB_DataOut) {
-					if(copy_from_user(p,sg_user[i],upsg->sg[i].count)){
+					if (copy_from_user(p, sg_user[i],
+						sg_count[i])){
 						dprintk((KERN_DEBUG"aacraid: Could not copy sg data from user\n"));
 						rcode = -EFAULT;
 						goto cleanup;
 					}
 				}
-				addr = pci_map_single(dev->pdev, p, upsg->sg[i].count, data_dir);
+				addr = pci_map_single(dev->pdev, p,
+							sg_count[i], data_dir);
 
 				psg->sg[i].addr[0] = cpu_to_le32(addr & 0xffffffff);
 				psg->sg[i].addr[1] = cpu_to_le32(addr>>32);
-				byte_count += upsg->sg[i].count;
-				psg->sg[i].count = cpu_to_le32(upsg->sg[i].count);
+				byte_count += sg_count[i];
+				psg->sg[i].count = cpu_to_le32(sg_count[i]);
 			}
 		} else {
 			struct user_sgmap* usg;
@@ -657,7 +775,9 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 			for (i = 0; i < usg->count; i++) {
 				u64 addr;
 				void* p;
-				if (usg->sg[i].count >
+
+				sg_count[i] = usg->sg[i].count;
+				if (sg_count[i] >
 				    ((dev->adapter_info.options &
 				     AAC_OPT_NEW_COMM) ?
 				      (dev->scsi_host_ptr->max_sectors << 9) :
@@ -667,10 +787,10 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 					goto cleanup;
 				}
 				/* Does this really need to be GFP_DMA? */
-				p = kmalloc(usg->sg[i].count,GFP_KERNEL|__GFP_DMA);
+				p = kmalloc(sg_count[i], GFP_KERNEL|__GFP_DMA);
 				if(!p) {
 					dprintk((KERN_DEBUG "aacraid: Could not allocate SG buffer - size = %d buffer number %d of %d\n",
-					  usg->sg[i].count,i,usg->count));
+						sg_count[i], i, usg->count));
 					kfree(usg);
 					rcode = -ENOMEM;
 					goto cleanup;
@@ -680,19 +800,21 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 				sg_indx = i;
 
 				if (flags & SRB_DataOut) {
-					if(copy_from_user(p,sg_user[i],upsg->sg[i].count)){
+					if (copy_from_user(p, sg_user[i],
+						sg_count[i])) {
 						kfree (usg);
 						dprintk((KERN_DEBUG"aacraid: Could not copy sg data from user\n"));
 						rcode = -EFAULT;
 						goto cleanup;
 					}
 				}
-				addr = pci_map_single(dev->pdev, p, usg->sg[i].count, data_dir);
+				addr = pci_map_single(dev->pdev, p,
+							sg_count[i], data_dir);
 
 				psg->sg[i].addr[0] = cpu_to_le32(addr & 0xffffffff);
 				psg->sg[i].addr[1] = cpu_to_le32(addr>>32);
-				byte_count += usg->sg[i].count;
-				psg->sg[i].count = cpu_to_le32(usg->sg[i].count);
+				byte_count += sg_count[i];
+				psg->sg[i].count = cpu_to_le32(sg_count[i]);
 			}
 			kfree (usg);
 		}
@@ -711,7 +833,9 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 			for (i = 0; i < upsg->count; i++) {
 				uintptr_t addr;
 				void* p;
-				if (usg->sg[i].count >
+
+				sg_count[i] = usg->sg[i].count;
+				if (sg_count[i] >
 				    ((dev->adapter_info.options &
 				     AAC_OPT_NEW_COMM) ?
 				      (dev->scsi_host_ptr->max_sectors << 9) :
@@ -720,10 +844,10 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 					goto cleanup;
 				}
 				/* Does this really need to be GFP_DMA? */
-				p = kmalloc(usg->sg[i].count,GFP_KERNEL|__GFP_DMA);
-				if(!p) {
+				p = kmalloc(sg_count[i], GFP_KERNEL|__GFP_DMA);
+				if (!p) {
 					dprintk((KERN_DEBUG"aacraid: Could not allocate SG buffer - size = %d buffer number %d of %d\n",
-					  usg->sg[i].count,i,usg->count));
+						sg_count[i], i, usg->count));
 					rcode = -ENOMEM;
 					goto cleanup;
 				}
@@ -734,7 +858,8 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 				sg_indx = i;
 
 				if (flags & SRB_DataOut) {
-					if(copy_from_user(p,sg_user[i],usg->sg[i].count)){
+					if (copy_from_user(p, sg_user[i],
+						sg_count[i])){
 						dprintk((KERN_DEBUG"aacraid: Could not copy sg data from user\n"));
 						rcode = -EFAULT;
 						goto cleanup;
@@ -744,13 +869,15 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 
 				psg->sg[i].addr = cpu_to_le32(addr & 0xffffffff);
 				byte_count += usg->sg[i].count;
-				psg->sg[i].count = cpu_to_le32(usg->sg[i].count);
+				psg->sg[i].count = cpu_to_le32(sg_count[i]);
 			}
 		} else {
 			for (i = 0; i < upsg->count; i++) {
 				dma_addr_t addr;
 				void* p;
-				if (upsg->sg[i].count >
+
+				sg_count[i] = upsg->sg[i].count;
+				if (sg_count[i] >
 				    ((dev->adapter_info.options &
 				     AAC_OPT_NEW_COMM) ?
 				      (dev->scsi_host_ptr->max_sectors << 9) :
@@ -758,10 +885,10 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 					rcode = -EINVAL;
 					goto cleanup;
 				}
-				p = kmalloc(upsg->sg[i].count, GFP_KERNEL);
+				p = kmalloc(sg_count[i], GFP_KERNEL);
 				if (!p) {
 					dprintk((KERN_DEBUG"aacraid: Could not allocate SG buffer - size = %d buffer number %d of %d\n",
-					  upsg->sg[i].count, i, upsg->count));
+					  sg_count[i], i, upsg->count));
 					rcode = -ENOMEM;
 					goto cleanup;
 				}
@@ -770,19 +897,19 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 				sg_indx = i;
 
 				if (flags & SRB_DataOut) {
-					if(copy_from_user(p, sg_user[i],
-							upsg->sg[i].count)) {
+					if (copy_from_user(p, sg_user[i],
+						sg_count[i])) {
 						dprintk((KERN_DEBUG"aacraid: Could not copy sg data from user\n"));
 						rcode = -EFAULT;
 						goto cleanup;
 					}
 				}
 				addr = pci_map_single(dev->pdev, p,
-					upsg->sg[i].count, data_dir);
+					sg_count[i], data_dir);
 
 				psg->sg[i].addr = cpu_to_le32(addr);
-				byte_count += upsg->sg[i].count;
-				psg->sg[i].count = cpu_to_le32(upsg->sg[i].count);
+				byte_count += sg_count[i];
+				psg->sg[i].count = cpu_to_le32(sg_count[i]);
 			}
 		}
 		srbcmd->count = cpu_to_le32(byte_count);
@@ -792,12 +919,13 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 			psg->count = 0;
 		status = aac_fib_send(ScsiPortCommand, srbfib, actual_fibsize, FsaNormal, 1, 1, NULL, NULL);
 	}
+
 	if (status == -ERESTARTSYS) {
 		rcode = -ERESTARTSYS;
 		goto cleanup;
 	}
 
-	if (status != 0){
+	if (status != 0) {
 		dprintk((KERN_DEBUG"aacraid: Could not send raw srb fib to hba\n"));
 		rcode = -ENXIO;
 		goto cleanup;
@@ -805,11 +933,7 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 
 	if (flags & SRB_DataIn) {
 		for(i = 0 ; i <= sg_indx; i++){
-			byte_count = le32_to_cpu(
-			  (dev->adapter_info.options & AAC_OPT_SGMAP_HOST64)
-			      ? ((struct sgmap64*)&srbcmd->sg)->sg[i].count
-			      : srbcmd->sg.sg[i].count);
-			if(copy_to_user(sg_user[i], sg_list[i], byte_count)){
+			if (copy_to_user(sg_user[i], sg_list[i], sg_count[i])) {
 				dprintk((KERN_DEBUG"aacraid: Could not copy sg data to user\n"));
 				rcode = -EFAULT;
 				goto cleanup;
@@ -818,19 +942,50 @@ static int aac_send_raw_srb(struct aac_dev* dev, void __user * arg)
 		}
 	}
 
-	reply = (struct aac_srb_reply *) fib_data(srbfib);
-	if(copy_to_user(user_reply,reply,sizeof(struct aac_srb_reply))){
-		dprintk((KERN_DEBUG"aacraid: Could not copy reply to user\n"));
-		rcode = -EFAULT;
-		goto cleanup;
+	user_reply = arg + fibsize;
+	if (is_native_device) {
+		struct aac_hba_resp *err =
+			&((struct aac_native_hba *)srbfib->hw_fib_va)->resp.err;
+		struct aac_srb_reply reply;
+
+		reply.status = ST_OK;
+		if (srbfib->flags & FIB_CONTEXT_FLAG_FASTRESP) {
+			/* fast response */
+			reply.srb_status = SRB_STATUS_SUCCESS;
+			reply.scsi_status = 0;
+			reply.data_xfer_length = byte_count;
+		} else {
+			reply.srb_status = err->service_response;
+			reply.scsi_status = err->status;
+			reply.data_xfer_length = byte_count -
+				le32_to_cpu(err->residual_count);
+			reply.sense_data_size = err->sense_response_data_len;
+			memcpy(reply.sense_data, err->sense_response_buf,
+				AAC_SENSE_BUFFERSIZE);
+		}
+		if (copy_to_user(user_reply, &reply,
+			sizeof(struct aac_srb_reply))) {
+			dprintk((KERN_DEBUG"aacraid: Copy to user failed\n"));
+			rcode = -EFAULT;
+			goto cleanup;
+		}
+	} else {
+		struct aac_srb_reply *reply;
+
+		reply = (struct aac_srb_reply *) fib_data(srbfib);
+		if (copy_to_user(user_reply, reply,
+			sizeof(struct aac_srb_reply))) {
+			dprintk((KERN_DEBUG"aacraid: Copy to user failed\n"));
+			rcode = -EFAULT;
+			goto cleanup;
+		}
 	}
 
 cleanup:
 	kfree(user_srbcmd);
-	for(i=0; i <= sg_indx; i++){
-		kfree(sg_list[i]);
-	}
 	if (rcode != -ERESTARTSYS) {
+		for (i = 0; i <= sg_indx; i++)
+			kfree(sg_list[i]);
 		aac_fib_complete(srbfib);
 		aac_fib_free(srbfib);
 	}
@@ -858,6 +1013,44 @@ static int aac_get_pci_info(struct aac_dev* dev, void __user *arg)
 	return 0;
 }
 
+static int aac_get_hba_info(struct aac_dev *dev, void __user *arg)
+{
+	struct aac_hba_info hbainfo;
+
+	hbainfo.adapter_number		= (u8) dev->id;
+	hbainfo.system_io_bus_number	= dev->pdev->bus->number;
+	hbainfo.device_number		= (dev->pdev->devfn >> 3);
+	hbainfo.function_number		= (dev->pdev->devfn & 0x0007);
+
+	hbainfo.vendor_id		= dev->pdev->vendor;
+	hbainfo.device_id		= dev->pdev->device;
+	hbainfo.sub_vendor_id		= dev->pdev->subsystem_vendor;
+	hbainfo.sub_system_id		= dev->pdev->subsystem_device;
+
+	if (copy_to_user(arg, &hbainfo, sizeof(struct aac_hba_info))) {
+		dprintk((KERN_DEBUG "aacraid: Could not copy hba info\n"));
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+struct aac_reset_iop {
+	u8	reset_type;
+};
+
+static int aac_send_reset_adapter(struct aac_dev *dev, void __user *arg)
+{
+	struct aac_reset_iop reset;
+	int retval;
+
+	if (copy_from_user((void *)&reset, arg, sizeof(struct aac_reset_iop)))
+		return -EFAULT;
+
+	retval = aac_reset_adapter(dev, 0, reset.reset_type);
+	return retval;
+
+}
 
 int aac_do_ioctl(struct aac_dev * dev, int cmd, void __user *arg)
 {
@@ -901,6 +1094,13 @@ int aac_do_ioctl(struct aac_dev * dev, int cmd, void __user *arg)
 	case FSACTL_GET_PCI_INFO:
 		status = aac_get_pci_info(dev,arg);
 		break;
+	case FSACTL_GET_HBA_INFO:
+		status = aac_get_hba_info(dev, arg);
+		break;
+	case FSACTL_RESET_IOP:
+		status = aac_send_reset_adapter(dev, arg);
+		break;
+
 	default:
 		status = -ENOTTY;
 		break;
diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
index 4f56b1003cc7..40bfc57b6849 100644
--- a/drivers/scsi/aacraid/comminit.c
+++ b/drivers/scsi/aacraid/comminit.c
@@ -6,7 +6,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -50,9 +51,13 @@ struct aac_common aac_config = {
 
 static inline int aac_is_msix_mode(struct aac_dev *dev)
 {
-	u32 status;
+	u32 status = 0;
 
-	status = src_readl(dev, MUnit.OMR);
+	if (dev->pdev->device == PMC_DEVICE_S6 ||
+		dev->pdev->device == PMC_DEVICE_S7 ||
+		dev->pdev->device == PMC_DEVICE_S8) {
+		status = src_readl(dev, MUnit.OMR);
+	}
 	return (status & AAC_INT_MODE_MSIX);
 }
 
@@ -68,104 +73,175 @@ static int aac_alloc_comm(struct aac_dev *dev, void **commaddr, unsigned long co
 	unsigned long size, align;
 	const unsigned long fibsize = dev->max_fib_size;
 	const unsigned long printfbufsiz = 256;
-	unsigned long host_rrq_size = 0;
-	struct aac_init *init;
+	unsigned long host_rrq_size, aac_init_size;
+	union aac_init *init;
 	dma_addr_t phys;
 	unsigned long aac_max_hostphysmempages;
 
-	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE1 ||
-	    dev->comm_interface == AAC_COMM_MESSAGE_TYPE2)
+	if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE1) ||
+		(dev->comm_interface == AAC_COMM_MESSAGE_TYPE2) ||
+		(dev->comm_interface == AAC_COMM_MESSAGE_TYPE3 &&
+		!dev->sa_firmware)) {
+		host_rrq_size =
+			(dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB)
+				* sizeof(u32);
+		aac_init_size = sizeof(union aac_init);
+	} else if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE3 &&
+		dev->sa_firmware) {
 		host_rrq_size = (dev->scsi_host_ptr->can_queue
-			+ AAC_NUM_MGT_FIB) * sizeof(u32);
-	size = fibsize + sizeof(struct aac_init) + commsize +
-			commalign + printfbufsiz + host_rrq_size;
- 
+			+ AAC_NUM_MGT_FIB) * sizeof(u32)  * AAC_MAX_MSIX;
+		aac_init_size = sizeof(union aac_init) +
+			(AAC_MAX_HRRQ - 1) * sizeof(struct _rrq);
+	} else {
+		host_rrq_size = 0;
+		aac_init_size = sizeof(union aac_init);
+	}
+	size = fibsize + aac_init_size + commsize + commalign +
+			printfbufsiz + host_rrq_size;
+
 	base = pci_alloc_consistent(dev->pdev, size, &phys);
 
-	if(base == NULL)
-	{
+	if (base == NULL) {
 		printk(KERN_ERR "aacraid: unable to create mapping.\n");
 		return 0;
 	}
+
 	dev->comm_addr = (void *)base;
 	dev->comm_phys = phys;
 	dev->comm_size = size;
-	
-	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE1 ||
-	    dev->comm_interface == AAC_COMM_MESSAGE_TYPE2) {
+
+	if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE1) ||
+	    (dev->comm_interface == AAC_COMM_MESSAGE_TYPE2) ||
+	    (dev->comm_interface == AAC_COMM_MESSAGE_TYPE3)) {
 		dev->host_rrq = (u32 *)(base + fibsize);
 		dev->host_rrq_pa = phys + fibsize;
 		memset(dev->host_rrq, 0, host_rrq_size);
 	}
 
-	dev->init = (struct aac_init *)(base + fibsize + host_rrq_size);
+	dev->init = (union aac_init *)(base + fibsize + host_rrq_size);
 	dev->init_pa = phys + fibsize + host_rrq_size;
 
 	init = dev->init;
 
-	init->InitStructRevision = cpu_to_le32(ADAPTER_INIT_STRUCT_REVISION);
-	if (dev->max_fib_size != sizeof(struct hw_fib))
-		init->InitStructRevision = cpu_to_le32(ADAPTER_INIT_STRUCT_REVISION_4);
-	init->Sa_MSIXVectors = cpu_to_le32(SA_INIT_NUM_MSIXVECTORS);
-	init->fsrev = cpu_to_le32(dev->fsrev);
+	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) {
+		int i;
+		u64 addr;
+
+		init->r8.init_struct_revision =
+			cpu_to_le32(ADAPTER_INIT_STRUCT_REVISION_8);
+		init->r8.init_flags = cpu_to_le32(INITFLAGS_NEW_COMM_SUPPORTED |
+					INITFLAGS_DRIVER_USES_UTC_TIME |
+					INITFLAGS_DRIVER_SUPPORTS_PM);
+		init->r8.init_flags |=
+				cpu_to_le32(INITFLAGS_DRIVER_SUPPORTS_HBA_MODE);
+		init->r8.rr_queue_count = cpu_to_le32(dev->max_msix);
+		init->r8.max_io_size =
+			cpu_to_le32(dev->scsi_host_ptr->max_sectors << 9);
+		init->r8.max_num_aif = init->r8.reserved1 =
+			init->r8.reserved2 = 0;
+
+		for (i = 0; i < dev->max_msix; i++) {
+			addr = (u64)dev->host_rrq_pa + dev->vector_cap * i *
+					sizeof(u32);
+			init->r8.rrq[i].host_addr_high = cpu_to_le32(
+						upper_32_bits(addr));
+			init->r8.rrq[i].host_addr_low = cpu_to_le32(
+						lower_32_bits(addr));
+			init->r8.rrq[i].msix_id = i;
+			init->r8.rrq[i].element_count = cpu_to_le16(
+					(u16)dev->vector_cap);
+			init->r8.rrq[i].comp_thresh =
+					init->r8.rrq[i].unused = 0;
+		}
 
-	/*
-	 *	Adapter Fibs are the first thing allocated so that they
-	 *	start page aligned
-	 */
-	dev->aif_base_va = (struct hw_fib *)base;
-	
-	init->AdapterFibsVirtualAddress = 0;
-	init->AdapterFibsPhysicalAddress = cpu_to_le32((u32)phys);
-	init->AdapterFibsSize = cpu_to_le32(fibsize);
-	init->AdapterFibAlign = cpu_to_le32(sizeof(struct hw_fib));
-	/*
-	 * number of 4k pages of host physical memory. The aacraid fw needs
-	 * this number to be less than 4gb worth of pages. New firmware doesn't
-	 * have any issues with the mapping system, but older Firmware did, and
-	 * had *troubles* dealing with the math overloading past 32 bits, thus
-	 * we must limit this field.
-	 */
-	aac_max_hostphysmempages = dma_get_required_mask(&dev->pdev->dev) >> 12;
-	if (aac_max_hostphysmempages < AAC_MAX_HOSTPHYSMEMPAGES)
-		init->HostPhysMemPages = cpu_to_le32(aac_max_hostphysmempages);
-	else
-		init->HostPhysMemPages = cpu_to_le32(AAC_MAX_HOSTPHYSMEMPAGES);
-
-	init->InitFlags = cpu_to_le32(INITFLAGS_DRIVER_USES_UTC_TIME |
-		INITFLAGS_DRIVER_SUPPORTS_PM);
-	init->MaxIoCommands = cpu_to_le32(dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB);
-	init->MaxIoSize = cpu_to_le32(dev->scsi_host_ptr->max_sectors << 9);
-	init->MaxFibSize = cpu_to_le32(dev->max_fib_size);
-	init->MaxNumAif = cpu_to_le32(dev->max_num_aif);
-
-	if (dev->comm_interface == AAC_COMM_MESSAGE) {
-		init->InitFlags |= cpu_to_le32(INITFLAGS_NEW_COMM_SUPPORTED);
-		dprintk((KERN_WARNING"aacraid: New Comm Interface enabled\n"));
-	} else if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE1) {
-		init->InitStructRevision = cpu_to_le32(ADAPTER_INIT_STRUCT_REVISION_6);
-		init->InitFlags |= cpu_to_le32(INITFLAGS_NEW_COMM_SUPPORTED |
-			INITFLAGS_NEW_COMM_TYPE1_SUPPORTED | INITFLAGS_FAST_JBOD_SUPPORTED);
-		init->HostRRQ_AddrHigh = cpu_to_le32((u32)((u64)dev->host_rrq_pa >> 32));
-		init->HostRRQ_AddrLow = cpu_to_le32((u32)(dev->host_rrq_pa & 0xffffffff));
-		dprintk((KERN_WARNING"aacraid: New Comm Interface type1 enabled\n"));
-	} else if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE2) {
-		init->InitStructRevision = cpu_to_le32(ADAPTER_INIT_STRUCT_REVISION_7);
-		init->InitFlags |= cpu_to_le32(INITFLAGS_NEW_COMM_SUPPORTED |
-			INITFLAGS_NEW_COMM_TYPE2_SUPPORTED | INITFLAGS_FAST_JBOD_SUPPORTED);
-		init->HostRRQ_AddrHigh = cpu_to_le32((u32)((u64)dev->host_rrq_pa >> 32));
-		init->HostRRQ_AddrLow = cpu_to_le32((u32)(dev->host_rrq_pa & 0xffffffff));
-		/* number of MSI-X */
-		init->Sa_MSIXVectors = cpu_to_le32(dev->max_msix);
-		dprintk((KERN_WARNING"aacraid: New Comm Interface type2 enabled\n"));
+		pr_warn("aacraid: Comm Interface type3 enabled\n");
+	} else {
+		init->r7.init_struct_revision =
+			cpu_to_le32(ADAPTER_INIT_STRUCT_REVISION);
+		if (dev->max_fib_size != sizeof(struct hw_fib))
+			init->r7.init_struct_revision =
+				cpu_to_le32(ADAPTER_INIT_STRUCT_REVISION_4);
+		init->r7.no_of_msix_vectors = cpu_to_le32(SA_MINIPORT_REVISION);
+		init->r7.fsrev = cpu_to_le32(dev->fsrev);
+
+		/*
+		 *	Adapter Fibs are the first thing allocated so that they
+		 *	start page aligned
+		 */
+		dev->aif_base_va = (struct hw_fib *)base;
+
+		init->r7.adapter_fibs_virtual_address = 0;
+		init->r7.adapter_fibs_physical_address = cpu_to_le32((u32)phys);
+		init->r7.adapter_fibs_size = cpu_to_le32(fibsize);
+		init->r7.adapter_fib_align = cpu_to_le32(sizeof(struct hw_fib));
+
+		/*
+		 * number of 4k pages of host physical memory. The aacraid fw
+		 * needs this number to be less than 4gb worth of pages. New
+		 * firmware doesn't have any issues with the mapping system, but
+		 * older Firmware did, and had *troubles* dealing with the math
+		 * overloading past 32 bits, thus we must limit this field.
+		 */
+		aac_max_hostphysmempages =
+				dma_get_required_mask(&dev->pdev->dev) >> 12;
+		if (aac_max_hostphysmempages < AAC_MAX_HOSTPHYSMEMPAGES)
+			init->r7.host_phys_mem_pages =
+					cpu_to_le32(aac_max_hostphysmempages);
+		else
+			init->r7.host_phys_mem_pages =
+					cpu_to_le32(AAC_MAX_HOSTPHYSMEMPAGES);
+
+		init->r7.init_flags =
+			cpu_to_le32(INITFLAGS_DRIVER_USES_UTC_TIME |
+			INITFLAGS_DRIVER_SUPPORTS_PM);
+		init->r7.max_io_commands =
+			cpu_to_le32(dev->scsi_host_ptr->can_queue +
+					AAC_NUM_MGT_FIB);
+		init->r7.max_io_size =
+			cpu_to_le32(dev->scsi_host_ptr->max_sectors << 9);
+		init->r7.max_fib_size = cpu_to_le32(dev->max_fib_size);
+		init->r7.max_num_aif = cpu_to_le32(dev->max_num_aif);
+
+		if (dev->comm_interface == AAC_COMM_MESSAGE) {
+			init->r7.init_flags |=
+				cpu_to_le32(INITFLAGS_NEW_COMM_SUPPORTED);
+			pr_warn("aacraid: Comm Interface enabled\n");
+		} else if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE1) {
+			init->r7.init_struct_revision =
+				cpu_to_le32(ADAPTER_INIT_STRUCT_REVISION_6);
+			init->r7.init_flags |=
+				cpu_to_le32(INITFLAGS_NEW_COMM_SUPPORTED |
+				INITFLAGS_NEW_COMM_TYPE1_SUPPORTED |
+				INITFLAGS_FAST_JBOD_SUPPORTED);
+			init->r7.host_rrq_addr_high =
+				cpu_to_le32(upper_32_bits(dev->host_rrq_pa));
+			init->r7.host_rrq_addr_low =
+				cpu_to_le32(lower_32_bits(dev->host_rrq_pa));
+			pr_warn("aacraid: Comm Interface type1 enabled\n");
+		} else if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE2) {
+			init->r7.init_struct_revision =
+				cpu_to_le32(ADAPTER_INIT_STRUCT_REVISION_7);
+			init->r7.init_flags |=
+				cpu_to_le32(INITFLAGS_NEW_COMM_SUPPORTED |
+				INITFLAGS_NEW_COMM_TYPE2_SUPPORTED |
+				INITFLAGS_FAST_JBOD_SUPPORTED);
+			init->r7.host_rrq_addr_high =
+				cpu_to_le32(upper_32_bits(dev->host_rrq_pa));
+			init->r7.host_rrq_addr_low =
+				cpu_to_le32(lower_32_bits(dev->host_rrq_pa));
+			init->r7.no_of_msix_vectors =
+				cpu_to_le32(dev->max_msix);
+			/* must be the COMM_PREFERRED_SETTINGS values */
+			pr_warn("aacraid: Comm Interface type2 enabled\n");
+		}
 	}
 
 	/*
 	 * Increment the base address by the amount already used
 	 */
-	base = base + fibsize + host_rrq_size + sizeof(struct aac_init);
+	base = base + fibsize + host_rrq_size + aac_init_size;
 	phys = (dma_addr_t)((ulong)phys + fibsize + host_rrq_size +
-		sizeof(struct aac_init));
+			aac_init_size);
 
 	/*
 	 *	Align the beginning of Headers to commalign
@@ -177,7 +253,8 @@ static int aac_alloc_comm(struct aac_dev *dev, void **commaddr, unsigned long co
 	 *	Fill in addresses of the Comm Area Headers and Queues
 	 */
 	*commaddr = base;
-	init->CommHeaderAddress = cpu_to_le32((u32)phys);
+	if (dev->comm_interface != AAC_COMM_MESSAGE_TYPE3)
+		init->r7.comm_header_address = cpu_to_le32((u32)phys);
 	/*
 	 *	Increment the base address by the size of the CommArea
 	 */
@@ -187,12 +264,14 @@ static int aac_alloc_comm(struct aac_dev *dev, void **commaddr, unsigned long co
 	 *	 Place the Printf buffer area after the Fast I/O comm area.
 	 */
 	dev->printfbuf = (void *)base;
-	init->printfbuf = cpu_to_le32(phys);
-	init->printfbufsiz = cpu_to_le32(printfbufsiz);
+	if (dev->comm_interface != AAC_COMM_MESSAGE_TYPE3) {
+		init->r7.printfbuf = cpu_to_le32(phys);
+		init->r7.printfbufsiz = cpu_to_le32(printfbufsiz);
+	}
 	memset(base, 0, printfbufsiz);
 	return 1;
 }
-    
+
 static void aac_queue_init(struct aac_dev * dev, struct aac_queue * q, u32 *mem, int qsize)
 {
 	atomic_set(&q->numpending, 0);
@@ -400,9 +479,13 @@ void aac_define_int_mode(struct aac_dev *dev)
 		if (dev->max_msix > msi_count)
 			dev->max_msix = msi_count;
 	}
-	dev->vector_cap =
-		(dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB) /
-		msi_count;
+	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE3 && dev->sa_firmware)
+		dev->vector_cap = dev->scsi_host_ptr->can_queue +
+				AAC_NUM_MGT_FIB;
+	else
+		dev->vector_cap = (dev->scsi_host_ptr->can_queue +
+				AAC_NUM_MGT_FIB) / msi_count;
+
 }
 struct aac_dev *aac_init_adapter(struct aac_dev *dev)
 {
@@ -436,30 +519,37 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev)
 
 	if ((!aac_adapter_sync_cmd(dev, GET_ADAPTER_PROPERTIES,
 		0, 0, 0, 0, 0, 0,
-		status+0, status+1, status+2, status+3, NULL)) &&
-	 		(status[0] == 0x00000001)) {
+		status+0, status+1, status+2, status+3, status+4)) &&
+		(status[0] == 0x00000001)) {
 		dev->doorbell_mask = status[3];
-		if (status[1] & le32_to_cpu(AAC_OPT_NEW_COMM_64))
+		if (status[1] & AAC_OPT_NEW_COMM_64)
 			dev->raw_io_64 = 1;
 		dev->sync_mode = aac_sync_mode;
 		if (dev->a_ops.adapter_comm &&
-			(status[1] & le32_to_cpu(AAC_OPT_NEW_COMM))) {
+			(status[1] & AAC_OPT_NEW_COMM)) {
 				dev->comm_interface = AAC_COMM_MESSAGE;
 				dev->raw_io_interface = 1;
-			if ((status[1] & le32_to_cpu(AAC_OPT_NEW_COMM_TYPE1))) {
+			if ((status[1] & AAC_OPT_NEW_COMM_TYPE1)) {
 				/* driver supports TYPE1 (Tupelo) */
 				dev->comm_interface = AAC_COMM_MESSAGE_TYPE1;
-			} else if ((status[1] & le32_to_cpu(AAC_OPT_NEW_COMM_TYPE2))) {
-				/* driver supports TYPE2 (Denali) */
+			} else if (status[1] & AAC_OPT_NEW_COMM_TYPE2) {
+				/* driver supports TYPE2 (Denali, Yosemite) */
 				dev->comm_interface = AAC_COMM_MESSAGE_TYPE2;
-			} else if ((status[1] & le32_to_cpu(AAC_OPT_NEW_COMM_TYPE4)) ||
-				  (status[1] & le32_to_cpu(AAC_OPT_NEW_COMM_TYPE3))) {
-				/* driver doesn't TYPE3 and TYPE4 */
-				/* switch to sync. mode */
+			} else if (status[1] & AAC_OPT_NEW_COMM_TYPE3) {
+				/* driver supports TYPE3 (Yosemite, Thor) */
+				dev->comm_interface = AAC_COMM_MESSAGE_TYPE3;
+			} else if (status[1] & AAC_OPT_NEW_COMM_TYPE4) {
+				/* not supported TYPE - switch to sync. mode */
 				dev->comm_interface = AAC_COMM_MESSAGE_TYPE2;
 				dev->sync_mode = 1;
 			}
 		}
+		if ((status[1] & le32_to_cpu(AAC_OPT_EXTENDED)) &&
+			(status[4] & le32_to_cpu(AAC_EXTOPT_SA_FIRMWARE)))
+			dev->sa_firmware = 1;
+		else
+			dev->sa_firmware = 0;
+
 		if ((dev->comm_interface == AAC_COMM_MESSAGE) &&
 		    (status[2] > dev->base_size)) {
 			aac_adapter_ioremap(dev, 0);
@@ -496,61 +586,25 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev)
 		dev->sg_tablesize = status[2] & 0xFFFF;
 		if (dev->pdev->device == PMC_DEVICE_S7 ||
 		    dev->pdev->device == PMC_DEVICE_S8 ||
-		    dev->pdev->device == PMC_DEVICE_S9)
-			host->can_queue = ((status[3] >> 16) ? (status[3] >> 16) :
-				(status[3] & 0xFFFF)) - AAC_NUM_MGT_FIB;
-		else
-			host->can_queue = (status[3] & 0xFFFF) - AAC_NUM_MGT_FIB;
+		    dev->pdev->device == PMC_DEVICE_S9) {
+			if (host->can_queue > (status[3] >> 16) -
+					AAC_NUM_MGT_FIB)
+				host->can_queue = (status[3] >> 16) -
+					AAC_NUM_MGT_FIB;
+		} else if (host->can_queue > (status[3] & 0xFFFF) -
+				AAC_NUM_MGT_FIB)
+			host->can_queue = (status[3] & 0xFFFF) -
+				AAC_NUM_MGT_FIB;
+
 		dev->max_num_aif = status[4] & 0xFFFF;
-		/*
-		 *	NOTE:
-		 *	All these overrides are based on a fixed internal
-		 *	knowledge and understanding of existing adapters,
-		 *	acbsize should be set with caution.
-		 */
-		if (acbsize == 512) {
-			host->max_sectors = AAC_MAX_32BIT_SGBCOUNT;
-			dev->max_fib_size = 512;
-			dev->sg_tablesize = host->sg_tablesize
-			  = (512 - sizeof(struct aac_fibhdr)
-			    - sizeof(struct aac_write) + sizeof(struct sgentry))
-			     / sizeof(struct sgentry);
-			host->can_queue = AAC_NUM_IO_FIB;
-		} else if (acbsize == 2048) {
-			host->max_sectors = 512;
-			dev->max_fib_size = 2048;
-			host->sg_tablesize = 65;
-			dev->sg_tablesize = 81;
-			host->can_queue = 512 - AAC_NUM_MGT_FIB;
-		} else if (acbsize == 4096) {
-			host->max_sectors = 1024;
-			dev->max_fib_size = 4096;
-			host->sg_tablesize = 129;
-			dev->sg_tablesize = 166;
-			host->can_queue = 256 - AAC_NUM_MGT_FIB;
-		} else if (acbsize == 8192) {
-			host->max_sectors = 2048;
-			dev->max_fib_size = 8192;
-			host->sg_tablesize = 257;
-			dev->sg_tablesize = 337;
-			host->can_queue = 128 - AAC_NUM_MGT_FIB;
-		} else if (acbsize > 0) {
-			printk("Illegal acbsize=%d ignored\n", acbsize);
-		}
 	}
-	{
-
-		if (numacb > 0) {
-			if (numacb < host->can_queue)
-				host->can_queue = numacb;
-			else
-				printk("numacb=%d ignored\n", numacb);
-		}
+	if (numacb > 0) {
+		if (numacb < host->can_queue)
+			host->can_queue = numacb;
+		else
+			pr_warn("numacb=%d ignored\n", numacb);
 	}
 
-	if (host->can_queue > AAC_NUM_IO_FIB)
-		host->can_queue = AAC_NUM_IO_FIB;
-
 	if (dev->pdev->device == PMC_DEVICE_S6 ||
 	    dev->pdev->device == PMC_DEVICE_S7 ||
 	    dev->pdev->device == PMC_DEVICE_S8 ||
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index 9e7551fe4b19..969727b67cdd 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -6,7 +6,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -43,6 +44,7 @@
 #include <linux/kthread.h>
 #include <linux/interrupt.h>
 #include <linux/semaphore.h>
+#include <linux/bcd.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_device.h>
@@ -60,12 +62,22 @@
 
 static int fib_map_alloc(struct aac_dev *dev)
 {
+	if (dev->max_fib_size > AAC_MAX_NATIVE_SIZE)
+		dev->max_cmd_size = AAC_MAX_NATIVE_SIZE;
+	else
+		dev->max_cmd_size = dev->max_fib_size;
+	if (dev->max_fib_size < AAC_MAX_NATIVE_SIZE) {
+		dev->max_cmd_size = AAC_MAX_NATIVE_SIZE;
+	} else {
+		dev->max_cmd_size = dev->max_fib_size;
+	}
+
 	dprintk((KERN_INFO
 	  "allocate hardware fibs pci_alloc_consistent(%p, %d * (%d + %d), %p)\n",
-	  dev->pdev, dev->max_fib_size, dev->scsi_host_ptr->can_queue,
+	  dev->pdev, dev->max_cmd_size, dev->scsi_host_ptr->can_queue,
 	  AAC_NUM_MGT_FIB, &dev->hw_fib_pa));
 	dev->hw_fib_va = pci_alloc_consistent(dev->pdev,
-		(dev->max_fib_size + sizeof(struct aac_fib_xporthdr))
+		(dev->max_cmd_size + sizeof(struct aac_fib_xporthdr))
 		* (dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB) + (ALIGN32 - 1),
 		&dev->hw_fib_pa);
 	if (dev->hw_fib_va == NULL)
@@ -83,9 +95,9 @@ static int fib_map_alloc(struct aac_dev *dev)
 
 void aac_fib_map_free(struct aac_dev *dev)
 {
-	if (dev->hw_fib_va && dev->max_fib_size) {
+	if (dev->hw_fib_va && dev->max_cmd_size) {
 		pci_free_consistent(dev->pdev,
-		(dev->max_fib_size *
+		(dev->max_cmd_size *
 		(dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB)),
 		dev->hw_fib_va, dev->hw_fib_pa);
 	}
@@ -129,11 +141,14 @@ int aac_fib_setup(struct aac_dev * dev)
 	struct hw_fib *hw_fib;
 	dma_addr_t hw_fib_pa;
 	int i;
+	u32 max_cmds;
 
 	while (((i = fib_map_alloc(dev)) == -ENOMEM)
 	 && (dev->scsi_host_ptr->can_queue > (64 - AAC_NUM_MGT_FIB))) {
-		dev->init->MaxIoCommands = cpu_to_le32((dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB) >> 1);
-		dev->scsi_host_ptr->can_queue = le32_to_cpu(dev->init->MaxIoCommands) - AAC_NUM_MGT_FIB;
+		max_cmds = (dev->scsi_host_ptr->can_queue+AAC_NUM_MGT_FIB) >> 1;
+		dev->scsi_host_ptr->can_queue = max_cmds - AAC_NUM_MGT_FIB;
+		if (dev->comm_interface != AAC_COMM_MESSAGE_TYPE3)
+			dev->init->r7.max_io_commands = cpu_to_le32(max_cmds);
 	}
 	if (i<0)
 		return -ENOMEM;
@@ -144,7 +159,7 @@ int aac_fib_setup(struct aac_dev * dev)
 		(hw_fib_pa - dev->hw_fib_pa));
 	dev->hw_fib_pa = hw_fib_pa;
 	memset(dev->hw_fib_va, 0,
-		(dev->max_fib_size + sizeof(struct aac_fib_xporthdr)) *
+		(dev->max_cmd_size + sizeof(struct aac_fib_xporthdr)) *
 		(dev->scsi_host_ptr->can_queue + AAC_NUM_MGT_FIB));
 
 	/* add Xport header */
@@ -170,12 +185,22 @@ int aac_fib_setup(struct aac_dev * dev)
 		sema_init(&fibptr->event_wait, 0);
 		spin_lock_init(&fibptr->event_lock);
 		hw_fib->header.XferState = cpu_to_le32(0xffffffff);
-		hw_fib->header.SenderSize = cpu_to_le16(dev->max_fib_size);
+		hw_fib->header.SenderSize =
+			cpu_to_le16(dev->max_fib_size);	/* ?? max_cmd_size */
 		fibptr->hw_fib_pa = hw_fib_pa;
+		fibptr->hw_sgl_pa = hw_fib_pa +
+			offsetof(struct aac_hba_cmd_req, sge[2]);
+		/*
+		 * one element is for the ptr to the separate sg list,
+		 * second element for 32 byte alignment
+		 */
+		fibptr->hw_error_pa = hw_fib_pa +
+			offsetof(struct aac_native_hba, resp.resp_bytes[0]);
+
 		hw_fib = (struct hw_fib *)((unsigned char *)hw_fib +
-			dev->max_fib_size + sizeof(struct aac_fib_xporthdr));
+			dev->max_cmd_size + sizeof(struct aac_fib_xporthdr));
 		hw_fib_pa = hw_fib_pa +
-			dev->max_fib_size + sizeof(struct aac_fib_xporthdr);
+			dev->max_cmd_size + sizeof(struct aac_fib_xporthdr);
 	}
 
 	/*
@@ -273,7 +298,8 @@ void aac_fib_free(struct fib *fibptr)
 	spin_lock_irqsave(&fibptr->dev->fib_lock, flags);
 	if (unlikely(fibptr->flags & FIB_CONTEXT_FLAG_TIMED_OUT))
 		aac_config.fib_timeouts++;
-	if (fibptr->hw_fib_va->header.XferState != 0) {
+	if (!(fibptr->flags & FIB_CONTEXT_FLAG_NATIVE_HBA) &&
+		fibptr->hw_fib_va->header.XferState != 0) {
 		printk(KERN_WARNING "aac_fib_free, XferState != 0, fibptr = 0x%p, XferState = 0x%x\n",
 			 (void*)fibptr,
 			 le32_to_cpu(fibptr->hw_fib_va->header.XferState));
@@ -501,8 +527,15 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
 	 *	Map the fib into 32bits by using the fib number
 	 */
 
-	hw_fib->header.SenderFibAddress = cpu_to_le32(((u32)(fibptr - dev->fibs)) << 2);
-	hw_fib->header.Handle = (u32)(fibptr - dev->fibs) + 1;
+	hw_fib->header.SenderFibAddress =
+		cpu_to_le32(((u32)(fibptr - dev->fibs)) << 2);
+
+	/* use the same shifted value for handle to be compatible
+	 * with the new native hba command handle
+	 */
+	hw_fib->header.Handle =
+		cpu_to_le32((((u32)(fibptr - dev->fibs)) << 2) + 1);
+
 	/*
 	 *	Set FIB state to indicate where it came from and if we want a
 	 *	response from the adapter. Also load the command from the
@@ -670,6 +703,82 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
 		return 0;
 }
 
+int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback,
+		void *callback_data)
+{
+	struct aac_dev *dev = fibptr->dev;
+	int wait;
+	unsigned long flags = 0;
+	unsigned long mflags = 0;
+
+	fibptr->flags = (FIB_CONTEXT_FLAG | FIB_CONTEXT_FLAG_NATIVE_HBA);
+	if (callback) {
+		wait = 0;
+		fibptr->callback = callback;
+		fibptr->callback_data = callback_data;
+	} else
+		wait = 1;
+
+
+	if (command == HBA_IU_TYPE_SCSI_CMD_REQ) {
+		struct aac_hba_cmd_req *hbacmd =
+			(struct aac_hba_cmd_req *)fibptr->hw_fib_va;
+
+		hbacmd->iu_type = command;
+		/* bit1 of request_id must be 0 */
+		hbacmd->request_id =
+			cpu_to_le32((((u32)(fibptr - dev->fibs)) << 2) + 1);
+	} else
+		return -EINVAL;
+
+
+	if (wait) {
+		spin_lock_irqsave(&dev->manage_lock, mflags);
+		if (dev->management_fib_count >= AAC_NUM_MGT_FIB) {
+			spin_unlock_irqrestore(&dev->manage_lock, mflags);
+			return -EBUSY;
+		}
+		dev->management_fib_count++;
+		spin_unlock_irqrestore(&dev->manage_lock, mflags);
+		spin_lock_irqsave(&fibptr->event_lock, flags);
+	}
+
+	if (aac_adapter_deliver(fibptr) != 0) {
+		if (wait) {
+			spin_unlock_irqrestore(&fibptr->event_lock, flags);
+			spin_lock_irqsave(&dev->manage_lock, mflags);
+			dev->management_fib_count--;
+			spin_unlock_irqrestore(&dev->manage_lock, mflags);
+		}
+		return -EBUSY;
+	}
+	FIB_COUNTER_INCREMENT(aac_config.NativeSent);
+
+	if (wait) {
+		spin_unlock_irqrestore(&fibptr->event_lock, flags);
+		/* Only set for first known interruptable command */
+		if (down_interruptible(&fibptr->event_wait)) {
+			fibptr->done = 2;
+			up(&fibptr->event_wait);
+		}
+		spin_lock_irqsave(&fibptr->event_lock, flags);
+		if ((fibptr->done == 0) || (fibptr->done == 2)) {
+			fibptr->done = 2; /* Tell interrupt we aborted */
+			spin_unlock_irqrestore(&fibptr->event_lock, flags);
+			return -ERESTARTSYS;
+		}
+		spin_unlock_irqrestore(&fibptr->event_lock, flags);
+		WARN_ON(fibptr->done == 0);
+
+		if (unlikely(fibptr->flags & FIB_CONTEXT_FLAG_TIMED_OUT))
+			return -ETIMEDOUT;
+
+		return 0;
+	}
+
+	return -EINPROGRESS;
+}
+
 /**
  *	aac_consumer_get	-	get the top of the queue
  *	@dev: Adapter
@@ -761,7 +870,8 @@ int aac_fib_adapter_complete(struct fib *fibptr, unsigned short size)
 	unsigned long qflags;
 
 	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE1 ||
-	    dev->comm_interface == AAC_COMM_MESSAGE_TYPE2) {
+		dev->comm_interface == AAC_COMM_MESSAGE_TYPE2 ||
+		dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) {
 		kfree(hw_fib);
 		return 0;
 	}
@@ -827,11 +937,17 @@ int aac_fib_complete(struct fib *fibptr)
 {
 	struct hw_fib * hw_fib = fibptr->hw_fib_va;
 
+	if (fibptr->flags & FIB_CONTEXT_FLAG_NATIVE_HBA) {
+		fib_dealloc(fibptr);
+		return 0;
+	}
+
 	/*
-	 *	Check for a fib which has already been completed
+	 *	Check for a fib which has already been completed or with a
+	 *	status wait timeout
 	 */
 
-	if (hw_fib->header.XferState == 0)
+	if (hw_fib->header.XferState == 0 || fibptr->done == 2)
 		return 0;
 	/*
 	 *	If we plan to do anything check the structure type first.
@@ -984,20 +1100,9 @@ static void aac_handle_aif(struct aac_dev * dev, struct fib * fibptr)
 			lun = (container >> 16) & 0xFF;
 			container = (u32)-1;
 			channel = aac_phys_to_logical(channel);
-			device_config_needed =
-			  (((__le32 *)aifcmd->data)[0] ==
-			    cpu_to_le32(AifRawDeviceRemove)) ? DELETE : ADD;
-
-			if (device_config_needed == ADD) {
-				device = scsi_device_lookup(
-					dev->scsi_host_ptr,
-					channel, id, lun);
-				if (device) {
-					scsi_remove_device(device);
-					scsi_device_put(device);
-				}
-			}
+			device_config_needed = DELETE;
 			break;
+
 		/*
 		 *	Morph or Expand complete
 		 */
@@ -1351,7 +1456,7 @@ retry_next:
 	}
 }
 
-static int _aac_reset_adapter(struct aac_dev *aac, int forced)
+static int _aac_reset_adapter(struct aac_dev *aac, int forced, u8 reset_type)
 {
 	int index, quirks;
 	int retval;
@@ -1360,6 +1465,7 @@ static int _aac_reset_adapter(struct aac_dev *aac, int forced)
 	struct scsi_cmnd *command;
 	struct scsi_cmnd *command_list;
 	int jafo = 0;
+	int bled;
 
 	/*
 	 * Assumptions:
@@ -1384,7 +1490,8 @@ static int _aac_reset_adapter(struct aac_dev *aac, int forced)
 	 *	If a positive health, means in a known DEAD PANIC
 	 * state and the adapter could be reset to `try again'.
 	 */
-	retval = aac_adapter_restart(aac, forced ? 0 : aac_adapter_check_health(aac));
+	bled = forced ? 0 : aac_adapter_check_health(aac);
+	retval = aac_adapter_restart(aac, bled, reset_type);
 
 	if (retval)
 		goto out;
@@ -1494,11 +1601,12 @@ out:
 	return retval;
 }
 
-int aac_reset_adapter(struct aac_dev * aac, int forced)
+int aac_reset_adapter(struct aac_dev *aac, int forced, u8 reset_type)
 {
 	unsigned long flagv = 0;
 	int retval;
 	struct Scsi_Host * host;
+	int bled;
 
 	if (spin_trylock_irqsave(&aac->fib_lock, flagv) == 0)
 		return -EBUSY;
@@ -1547,7 +1655,9 @@ int aac_reset_adapter(struct aac_dev * aac, int forced)
 	if (forced < 2)
 		aac_send_shutdown(aac);
 	spin_lock_irqsave(host->host_lock, flagv);
-	retval = _aac_reset_adapter(aac, forced ? forced : ((aac_check_reset != 0) && (aac_check_reset != 1)));
+	bled = forced ? forced :
+			(aac_check_reset != 0 && aac_check_reset != 1);
+	retval = _aac_reset_adapter(aac, bled, reset_type);
 	spin_unlock_irqrestore(host->host_lock, flagv);
 
 	if ((forced < 2) && (retval == -ENODEV)) {
@@ -1593,6 +1703,7 @@ int aac_check_health(struct aac_dev * aac)
 	unsigned long time_now, flagv = 0;
 	struct list_head * entry;
 	struct Scsi_Host * host;
+	int bled;
 
 	/* Extending the scope of fib_lock slightly to protect aac->in_reset */
 	if (spin_trylock_irqsave(&aac->fib_lock, flagv) == 0)
@@ -1710,7 +1821,8 @@ int aac_check_health(struct aac_dev * aac)
 	host = aac->scsi_host_ptr;
 	if (aac->thread->pid != current->pid)
 		spin_lock_irqsave(host->host_lock, flagv);
-	BlinkLED = _aac_reset_adapter(aac, aac_check_reset != 1);
+	bled = aac_check_reset != 1 ? 1 : 0;
+	_aac_reset_adapter(aac, bled, IOP_HWSOFT_RESET);
 	if (aac->thread->pid != current->pid)
 		spin_unlock_irqrestore(host->host_lock, flagv);
 	return BlinkLED;
@@ -1721,6 +1833,552 @@ out:
 }
 
 
+static void aac_resolve_luns(struct aac_dev *dev)
+{
+	int bus, target, channel;
+	struct scsi_device *sdev;
+	u8 devtype;
+	u8 new_devtype;
+
+	for (bus = 0; bus < AAC_MAX_BUSES; bus++) {
+		for (target = 0; target < AAC_MAX_TARGETS; target++) {
+
+			if (aac_phys_to_logical(bus) == ENCLOSURE_CHANNEL)
+				continue;
+
+			if (bus == CONTAINER_CHANNEL)
+				channel = CONTAINER_CHANNEL;
+			else
+				channel = aac_phys_to_logical(bus);
+
+			devtype = dev->hba_map[bus][target].devtype;
+			new_devtype = dev->hba_map[bus][target].new_devtype;
+
+			sdev = scsi_device_lookup(dev->scsi_host_ptr, channel,
+					target, 0);
+
+			if (!sdev && devtype)
+				scsi_add_device(dev->scsi_host_ptr, channel,
+						target, 0);
+			else if (sdev && new_devtype != devtype)
+				scsi_remove_device(sdev);
+			else if (sdev && new_devtype == devtype)
+				scsi_rescan_device(&sdev->sdev_gendev);
+
+			if (sdev)
+				scsi_device_put(sdev);
+
+			dev->hba_map[bus][target].devtype = new_devtype;
+		}
+	}
+}
+
+/**
+ *	aac_handle_sa_aif	Handle a message from the firmware
+ *	@dev: Which adapter this fib is from
+ *	@fibptr: Pointer to fibptr from adapter
+ *
+ *	This routine handles a driver notify fib from the adapter and
+ *	dispatches it to the appropriate routine for handling.
+ */
+static void aac_handle_sa_aif(struct aac_dev *dev, struct fib *fibptr)
+{
+	int i, bus, target, container, rcode = 0;
+	u32 events = 0;
+	struct fib *fib;
+	struct scsi_device *sdev;
+
+	if (fibptr->hbacmd_size & SA_AIF_HOTPLUG)
+		events = SA_AIF_HOTPLUG;
+	else if (fibptr->hbacmd_size & SA_AIF_HARDWARE)
+		events = SA_AIF_HARDWARE;
+	else if (fibptr->hbacmd_size & SA_AIF_PDEV_CHANGE)
+		events = SA_AIF_PDEV_CHANGE;
+	else if (fibptr->hbacmd_size & SA_AIF_LDEV_CHANGE)
+		events = SA_AIF_LDEV_CHANGE;
+	else if (fibptr->hbacmd_size & SA_AIF_BPSTAT_CHANGE)
+		events = SA_AIF_BPSTAT_CHANGE;
+	else if (fibptr->hbacmd_size & SA_AIF_BPCFG_CHANGE)
+		events = SA_AIF_BPCFG_CHANGE;
+
+	switch (events) {
+	case SA_AIF_HOTPLUG:
+	case SA_AIF_HARDWARE:
+	case SA_AIF_PDEV_CHANGE:
+	case SA_AIF_LDEV_CHANGE:
+	case SA_AIF_BPCFG_CHANGE:
+
+		fib = aac_fib_alloc(dev);
+		if (!fib) {
+			pr_err("aac_handle_sa_aif: out of memory\n");
+			return;
+		}
+		for (bus = 0; bus < AAC_MAX_BUSES; bus++)
+			for (target = 0; target < AAC_MAX_TARGETS; target++)
+				dev->hba_map[bus][target].new_devtype = 0;
+
+		rcode = aac_report_phys_luns(dev, fib, AAC_RESCAN);
+
+		if (rcode != -ERESTARTSYS)
+			aac_fib_free(fib);
+
+		aac_resolve_luns(dev);
+
+		if (events == SA_AIF_LDEV_CHANGE ||
+		    events == SA_AIF_BPCFG_CHANGE) {
+			aac_get_containers(dev);
+			for (container = 0; container <
+			dev->maximum_num_containers; ++container) {
+				sdev = scsi_device_lookup(dev->scsi_host_ptr,
+						CONTAINER_CHANNEL,
+						container, 0);
+				if (dev->fsa_dev[container].valid && !sdev) {
+					scsi_add_device(dev->scsi_host_ptr,
+						CONTAINER_CHANNEL,
+						container, 0);
+				} else if (!dev->fsa_dev[container].valid &&
+					sdev) {
+					scsi_remove_device(sdev);
+					scsi_device_put(sdev);
+				} else if (sdev) {
+					scsi_rescan_device(&sdev->sdev_gendev);
+					scsi_device_put(sdev);
+				}
+			}
+		}
+		break;
+
+	case SA_AIF_BPSTAT_CHANGE:
+		/* currently do nothing */
+		break;
+	}
+
+	for (i = 1; i <= 10; ++i) {
+		events = src_readl(dev, MUnit.IDR);
+		if (events & (1<<23)) {
+			pr_warn(" AIF not cleared by firmware - %d/%d)\n",
+				i, 10);
+			ssleep(1);
+		}
+	}
+}
+
+static int get_fib_count(struct aac_dev *dev)
+{
+	unsigned int num = 0;
+	struct list_head *entry;
+	unsigned long flagv;
+
+	/*
+	 * Warning: no sleep allowed while
+	 * holding spinlock. We take the estimate
+	 * and pre-allocate a set of fibs outside the
+	 * lock.
+	 */
+	num = le32_to_cpu(dev->init->r7.adapter_fibs_size)
+			/ sizeof(struct hw_fib); /* some extra */
+	spin_lock_irqsave(&dev->fib_lock, flagv);
+	entry = dev->fib_list.next;
+	while (entry != &dev->fib_list) {
+		entry = entry->next;
+		++num;
+	}
+	spin_unlock_irqrestore(&dev->fib_lock, flagv);
+
+	return num;
+}
+
+static int fillup_pools(struct aac_dev *dev, struct hw_fib **hw_fib_pool,
+						struct fib **fib_pool,
+						unsigned int num)
+{
+	struct hw_fib **hw_fib_p;
+	struct fib **fib_p;
+	int rcode = 1;
+
+	hw_fib_p = hw_fib_pool;
+	fib_p = fib_pool;
+	while (hw_fib_p < &hw_fib_pool[num]) {
+		*(hw_fib_p) = kmalloc(sizeof(struct hw_fib), GFP_KERNEL);
+		if (!(*(hw_fib_p++))) {
+			--hw_fib_p;
+			break;
+		}
+
+		*(fib_p) = kmalloc(sizeof(struct fib), GFP_KERNEL);
+		if (!(*(fib_p++))) {
+			kfree(*(--hw_fib_p));
+			break;
+		}
+	}
+
+	num = hw_fib_p - hw_fib_pool;
+	if (!num)
+		rcode = 0;
+
+	return rcode;
+}
+
+static void wakeup_fibctx_threads(struct aac_dev *dev,
+						struct hw_fib **hw_fib_pool,
+						struct fib **fib_pool,
+						struct fib *fib,
+						struct hw_fib *hw_fib,
+						unsigned int num)
+{
+	unsigned long flagv;
+	struct list_head *entry;
+	struct hw_fib **hw_fib_p;
+	struct fib **fib_p;
+	u32 time_now, time_last;
+	struct hw_fib *hw_newfib;
+	struct fib *newfib;
+	struct aac_fib_context *fibctx;
+
+	time_now = jiffies/HZ;
+	spin_lock_irqsave(&dev->fib_lock, flagv);
+	entry = dev->fib_list.next;
+	/*
+	 * For each Context that is on the
+	 * fibctxList, make a copy of the
+	 * fib, and then set the event to wake up the
+	 * thread that is waiting for it.
+	 */
+
+	hw_fib_p = hw_fib_pool;
+	fib_p = fib_pool;
+	while (entry != &dev->fib_list) {
+		/*
+		 * Extract the fibctx
+		 */
+		fibctx = list_entry(entry, struct aac_fib_context,
+				next);
+		/*
+		 * Check if the queue is getting
+		 * backlogged
+		 */
+		if (fibctx->count > 20) {
+			/*
+			 * It's *not* jiffies folks,
+			 * but jiffies / HZ so do not
+			 * panic ...
+			 */
+			time_last = fibctx->jiffies;
+			/*
+			 * Has it been > 2 minutes
+			 * since the last read off
+			 * the queue?
+			 */
+			if ((time_now - time_last) > aif_timeout) {
+				entry = entry->next;
+				aac_close_fib_context(dev, fibctx);
+				continue;
+			}
+		}
+		/*
+		 * Warning: no sleep allowed while
+		 * holding spinlock
+		 */
+		if (hw_fib_p >= &hw_fib_pool[num]) {
+			pr_warn("aifd: didn't allocate NewFib\n");
+			entry = entry->next;
+			continue;
+		}
+
+		hw_newfib = *hw_fib_p;
+		*(hw_fib_p++) = NULL;
+		newfib = *fib_p;
+		*(fib_p++) = NULL;
+		/*
+		 * Make the copy of the FIB
+		 */
+		memcpy(hw_newfib, hw_fib, sizeof(struct hw_fib));
+		memcpy(newfib, fib, sizeof(struct fib));
+		newfib->hw_fib_va = hw_newfib;
+		/*
+		 * Put the FIB onto the
+		 * fibctx's fibs
+		 */
+		list_add_tail(&newfib->fiblink, &fibctx->fib_list);
+		fibctx->count++;
+		/*
+		 * Set the event to wake up the
+		 * thread that is waiting.
+		 */
+		up(&fibctx->wait_sem);
+
+		entry = entry->next;
+	}
+	/*
+	 *	Set the status of this FIB
+	 */
+	*(__le32 *)hw_fib->data = cpu_to_le32(ST_OK);
+	aac_fib_adapter_complete(fib, sizeof(u32));
+	spin_unlock_irqrestore(&dev->fib_lock, flagv);
+
+}
+
+static void aac_process_events(struct aac_dev *dev)
+{
+	struct hw_fib *hw_fib;
+	struct fib *fib;
+	unsigned long flags;
+	spinlock_t *t_lock;
+	unsigned int rcode;
+
+	t_lock = dev->queues->queue[HostNormCmdQueue].lock;
+	spin_lock_irqsave(t_lock, flags);
+
+	while (!list_empty(&(dev->queues->queue[HostNormCmdQueue].cmdq))) {
+		struct list_head *entry;
+		struct aac_aifcmd *aifcmd;
+		unsigned int  num;
+		struct hw_fib **hw_fib_pool, **hw_fib_p;
+		struct fib **fib_pool, **fib_p;
+
+		set_current_state(TASK_RUNNING);
+
+		entry = dev->queues->queue[HostNormCmdQueue].cmdq.next;
+		list_del(entry);
+
+		t_lock = dev->queues->queue[HostNormCmdQueue].lock;
+		spin_unlock_irqrestore(t_lock, flags);
+
+		fib = list_entry(entry, struct fib, fiblink);
+		hw_fib = fib->hw_fib_va;
+		if (dev->sa_firmware) {
+			/* Thor AIF */
+			aac_handle_sa_aif(dev, fib);
+			aac_fib_adapter_complete(fib, (u16)sizeof(u32));
+			continue;
+		}
+		/*
+		 *	We will process the FIB here or pass it to a
+		 *	worker thread that is TBD. We Really can't
+		 *	do anything at this point since we don't have
+		 *	anything defined for this thread to do.
+		 */
+		memset(fib, 0, sizeof(struct fib));
+		fib->type = FSAFS_NTC_FIB_CONTEXT;
+		fib->size = sizeof(struct fib);
+		fib->hw_fib_va = hw_fib;
+		fib->data = hw_fib->data;
+		fib->dev = dev;
+		/*
+		 *	We only handle AifRequest fibs from the adapter.
+		 */
+
+		aifcmd = (struct aac_aifcmd *) hw_fib->data;
+		if (aifcmd->command == cpu_to_le32(AifCmdDriverNotify)) {
+			/* Handle Driver Notify Events */
+			aac_handle_aif(dev, fib);
+			*(__le32 *)hw_fib->data = cpu_to_le32(ST_OK);
+			aac_fib_adapter_complete(fib, (u16)sizeof(u32));
+			goto free_fib;
+		}
+		/*
+		 * The u32 here is important and intended. We are using
+		 * 32bit wrapping time to fit the adapter field
+		 */
+
+		/* Sniff events */
+		if (aifcmd->command == cpu_to_le32(AifCmdEventNotify)
+		 || aifcmd->command == cpu_to_le32(AifCmdJobProgress)) {
+			aac_handle_aif(dev, fib);
+		}
+
+		/*
+		 * get number of fibs to process
+		 */
+		num = get_fib_count(dev);
+		if (!num)
+			goto free_fib;
+
+		hw_fib_pool = kmalloc_array(num, sizeof(struct hw_fib *),
+						GFP_KERNEL);
+		if (!hw_fib_pool)
+			goto free_fib;
+
+		fib_pool = kmalloc_array(num, sizeof(struct fib *), GFP_KERNEL);
+		if (!fib_pool)
+			goto free_hw_fib_pool;
+
+		/*
+		 * Fill up fib pointer pools with actual fibs
+		 * and hw_fibs
+		 */
+		rcode = fillup_pools(dev, hw_fib_pool, fib_pool, num);
+		if (!rcode)
+			goto free_mem;
+
+		/*
+		 * wakeup the thread that is waiting for
+		 * the response from fw (ioctl)
+		 */
+		wakeup_fibctx_threads(dev, hw_fib_pool, fib_pool,
+							    fib, hw_fib, num);
+
+free_mem:
+		/* Free up the remaining resources */
+		hw_fib_p = hw_fib_pool;
+		fib_p = fib_pool;
+		while (hw_fib_p < &hw_fib_pool[num]) {
+			kfree(*hw_fib_p);
+			kfree(*fib_p);
+			++fib_p;
+			++hw_fib_p;
+		}
+		kfree(fib_pool);
+free_hw_fib_pool:
+		kfree(hw_fib_pool);
+free_fib:
+		kfree(fib);
+		t_lock = dev->queues->queue[HostNormCmdQueue].lock;
+		spin_lock_irqsave(t_lock, flags);
+	}
+	/*
+	 *	There are no more AIF's
+	 */
+	t_lock = dev->queues->queue[HostNormCmdQueue].lock;
+	spin_unlock_irqrestore(t_lock, flags);
+}
+
+static int aac_send_wellness_command(struct aac_dev *dev, char *wellness_str,
+							u32 datasize)
+{
+	struct aac_srb *srbcmd;
+	struct sgmap64 *sg64;
+	dma_addr_t addr;
+	char *dma_buf;
+	struct fib *fibptr;
+	int ret = -ENOMEM;
+	u32 vbus, vid;
+
+	fibptr = aac_fib_alloc(dev);
+	if (!fibptr)
+		goto out;
+
+	dma_buf = pci_alloc_consistent(dev->pdev, datasize, &addr);
+	if (!dma_buf)
+		goto fib_free_out;
+
+	aac_fib_init(fibptr);
+
+	vbus = (u32)le16_to_cpu(dev->supplement_adapter_info.VirtDeviceBus);
+	vid = (u32)le16_to_cpu(dev->supplement_adapter_info.VirtDeviceTarget);
+
+	srbcmd = (struct aac_srb *)fib_data(fibptr);
+
+	srbcmd->function = cpu_to_le32(SRBF_ExecuteScsi);
+	srbcmd->channel = cpu_to_le32(vbus);
+	srbcmd->id = cpu_to_le32(vid);
+	srbcmd->lun = 0;
+	srbcmd->flags = cpu_to_le32(SRB_DataOut);
+	srbcmd->timeout = cpu_to_le32(10);
+	srbcmd->retry_limit = 0;
+	srbcmd->cdb_size = cpu_to_le32(12);
+	srbcmd->count = cpu_to_le32(datasize);
+
+	memset(srbcmd->cdb, 0, sizeof(srbcmd->cdb));
+	srbcmd->cdb[0] = BMIC_OUT;
+	srbcmd->cdb[6] = WRITE_HOST_WELLNESS;
+	memcpy(dma_buf, (char *)wellness_str, datasize);
+
+	sg64 = (struct sgmap64 *)&srbcmd->sg;
+	sg64->count = cpu_to_le32(1);
+	sg64->sg[0].addr[1] = cpu_to_le32((u32)(((addr) >> 16) >> 16));
+	sg64->sg[0].addr[0] = cpu_to_le32((u32)(addr & 0xffffffff));
+	sg64->sg[0].count = cpu_to_le32(datasize);
+
+	ret = aac_fib_send(ScsiPortCommand64, fibptr, sizeof(struct aac_srb),
+				FsaNormal, 1, 1, NULL, NULL);
+
+	pci_free_consistent(dev->pdev, datasize, (void *)dma_buf, addr);
+
+	/*
+	 * Do not set XferState to zero unless
+	 * receives a response from F/W
+	 */
+	if (ret >= 0)
+		aac_fib_complete(fibptr);
+
+	/*
+	 * FIB should be freed only after
+	 * getting the response from the F/W
+	 */
+	if (ret != -ERESTARTSYS)
+		goto fib_free_out;
+
+out:
+	return ret;
+fib_free_out:
+	aac_fib_free(fibptr);
+	goto out;
+}
+
+int aac_send_safw_hostttime(struct aac_dev *dev, struct timeval *now)
+{
+	struct tm cur_tm;
+	char wellness_str[] = "<HW>TD\010\0\0\0\0\0\0\0\0\0DW\0\0ZZ";
+	u32 datasize = sizeof(wellness_str);
+	unsigned long local_time;
+	int ret = -ENODEV;
+
+	if (!dev->sa_firmware)
+		goto out;
+
+	local_time = (u32)(now->tv_sec - (sys_tz.tz_minuteswest * 60));
+	time_to_tm(local_time, 0, &cur_tm);
+	cur_tm.tm_mon += 1;
+	cur_tm.tm_year += 1900;
+	wellness_str[8] = bin2bcd(cur_tm.tm_hour);
+	wellness_str[9] = bin2bcd(cur_tm.tm_min);
+	wellness_str[10] = bin2bcd(cur_tm.tm_sec);
+	wellness_str[12] = bin2bcd(cur_tm.tm_mon);
+	wellness_str[13] = bin2bcd(cur_tm.tm_mday);
+	wellness_str[14] = bin2bcd(cur_tm.tm_year / 100);
+	wellness_str[15] = bin2bcd(cur_tm.tm_year % 100);
+
+	ret = aac_send_wellness_command(dev, wellness_str, datasize);
+
+out:
+	return ret;
+}
+
+int aac_send_hosttime(struct aac_dev *dev, struct timeval *now)
+{
+	int ret = -ENOMEM;
+	struct fib *fibptr;
+	__le32 *info;
+
+	fibptr = aac_fib_alloc(dev);
+	if (!fibptr)
+		goto out;
+
+	aac_fib_init(fibptr);
+	info = (__le32 *)fib_data(fibptr);
+	*info = cpu_to_le32(now->tv_sec);
+	ret = aac_fib_send(SendHostTime, fibptr, sizeof(*info), FsaNormal,
+					1, 1, NULL, NULL);
+
+	/*
+	 * Do not set XferState to zero unless
+	 * receives a response from F/W
+	 */
+	if (ret >= 0)
+		aac_fib_complete(fibptr);
+
+	/*
+	 * FIB should be freed only after
+	 * getting the response from the F/W
+	 */
+	if (ret != -ERESTARTSYS)
+		aac_fib_free(fibptr);
+
+out:
+	return ret;
+}
+
 /**
  *	aac_command_thread	-	command processing thread
  *	@dev: Adapter to monitor
@@ -1734,10 +2392,6 @@ out:
 int aac_command_thread(void *data)
 {
 	struct aac_dev *dev = data;
-	struct hw_fib *hw_fib, *hw_newfib;
-	struct fib *fib, *newfib;
-	struct aac_fib_context *fibctx;
-	unsigned long flags;
 	DECLARE_WAITQUEUE(wait, current);
 	unsigned long next_jiffies = jiffies + HZ;
 	unsigned long next_check_jiffies = next_jiffies;
@@ -1757,196 +2411,8 @@ int aac_command_thread(void *data)
 	set_current_state(TASK_INTERRUPTIBLE);
 	dprintk ((KERN_INFO "aac_command_thread start\n"));
 	while (1) {
-		spin_lock_irqsave(dev->queues->queue[HostNormCmdQueue].lock, flags);
-		while(!list_empty(&(dev->queues->queue[HostNormCmdQueue].cmdq))) {
-			struct list_head *entry;
-			struct aac_aifcmd * aifcmd;
-
-			set_current_state(TASK_RUNNING);
 
-			entry = dev->queues->queue[HostNormCmdQueue].cmdq.next;
-			list_del(entry);
-
-			spin_unlock_irqrestore(dev->queues->queue[HostNormCmdQueue].lock, flags);
-			fib = list_entry(entry, struct fib, fiblink);
-			/*
-			 *	We will process the FIB here or pass it to a
-			 *	worker thread that is TBD. We Really can't
-			 *	do anything at this point since we don't have
-			 *	anything defined for this thread to do.
-			 */
-			hw_fib = fib->hw_fib_va;
-			memset(fib, 0, sizeof(struct fib));
-			fib->type = FSAFS_NTC_FIB_CONTEXT;
-			fib->size = sizeof(struct fib);
-			fib->hw_fib_va = hw_fib;
-			fib->data = hw_fib->data;
-			fib->dev = dev;
-			/*
-			 *	We only handle AifRequest fibs from the adapter.
-			 */
-			aifcmd = (struct aac_aifcmd *) hw_fib->data;
-			if (aifcmd->command == cpu_to_le32(AifCmdDriverNotify)) {
-				/* Handle Driver Notify Events */
-				aac_handle_aif(dev, fib);
-				*(__le32 *)hw_fib->data = cpu_to_le32(ST_OK);
-				aac_fib_adapter_complete(fib, (u16)sizeof(u32));
-			} else {
-				/* The u32 here is important and intended. We are using
-				   32bit wrapping time to fit the adapter field */
-
-				u32 time_now, time_last;
-				unsigned long flagv;
-				unsigned num;
-				struct hw_fib ** hw_fib_pool, ** hw_fib_p;
-				struct fib ** fib_pool, ** fib_p;
-
-				/* Sniff events */
-				if ((aifcmd->command ==
-				     cpu_to_le32(AifCmdEventNotify)) ||
-				    (aifcmd->command ==
-				     cpu_to_le32(AifCmdJobProgress))) {
-					aac_handle_aif(dev, fib);
-				}
-
-				time_now = jiffies/HZ;
-
-				/*
-				 * Warning: no sleep allowed while
-				 * holding spinlock. We take the estimate
-				 * and pre-allocate a set of fibs outside the
-				 * lock.
-				 */
-				num = le32_to_cpu(dev->init->AdapterFibsSize)
-				    / sizeof(struct hw_fib); /* some extra */
-				spin_lock_irqsave(&dev->fib_lock, flagv);
-				entry = dev->fib_list.next;
-				while (entry != &dev->fib_list) {
-					entry = entry->next;
-					++num;
-				}
-				spin_unlock_irqrestore(&dev->fib_lock, flagv);
-				hw_fib_pool = NULL;
-				fib_pool = NULL;
-				if (num
-				 && ((hw_fib_pool = kmalloc(sizeof(struct hw_fib *) * num, GFP_KERNEL)))
-				 && ((fib_pool = kmalloc(sizeof(struct fib *) * num, GFP_KERNEL)))) {
-					hw_fib_p = hw_fib_pool;
-					fib_p = fib_pool;
-					while (hw_fib_p < &hw_fib_pool[num]) {
-						if (!(*(hw_fib_p++) = kmalloc(sizeof(struct hw_fib), GFP_KERNEL))) {
-							--hw_fib_p;
-							break;
-						}
-						if (!(*(fib_p++) = kmalloc(sizeof(struct fib), GFP_KERNEL))) {
-							kfree(*(--hw_fib_p));
-							break;
-						}
-					}
-					if ((num = hw_fib_p - hw_fib_pool) == 0) {
-						kfree(fib_pool);
-						fib_pool = NULL;
-						kfree(hw_fib_pool);
-						hw_fib_pool = NULL;
-					}
-				} else {
-					kfree(hw_fib_pool);
-					hw_fib_pool = NULL;
-				}
-				spin_lock_irqsave(&dev->fib_lock, flagv);
-				entry = dev->fib_list.next;
-				/*
-				 * For each Context that is on the
-				 * fibctxList, make a copy of the
-				 * fib, and then set the event to wake up the
-				 * thread that is waiting for it.
-				 */
-				hw_fib_p = hw_fib_pool;
-				fib_p = fib_pool;
-				while (entry != &dev->fib_list) {
-					/*
-					 * Extract the fibctx
-					 */
-					fibctx = list_entry(entry, struct aac_fib_context, next);
-					/*
-					 * Check if the queue is getting
-					 * backlogged
-					 */
-					if (fibctx->count > 20)
-					{
-						/*
-						 * It's *not* jiffies folks,
-						 * but jiffies / HZ so do not
-						 * panic ...
-						 */
-						time_last = fibctx->jiffies;
-						/*
-						 * Has it been > 2 minutes
-						 * since the last read off
-						 * the queue?
-						 */
-						if ((time_now - time_last) > aif_timeout) {
-							entry = entry->next;
-							aac_close_fib_context(dev, fibctx);
-							continue;
-						}
-					}
-					/*
-					 * Warning: no sleep allowed while
-					 * holding spinlock
-					 */
-					if (hw_fib_p < &hw_fib_pool[num]) {
-						hw_newfib = *hw_fib_p;
-						*(hw_fib_p++) = NULL;
-						newfib = *fib_p;
-						*(fib_p++) = NULL;
-						/*
-						 * Make the copy of the FIB
-						 */
-						memcpy(hw_newfib, hw_fib, sizeof(struct hw_fib));
-						memcpy(newfib, fib, sizeof(struct fib));
-						newfib->hw_fib_va = hw_newfib;
-						/*
-						 * Put the FIB onto the
-						 * fibctx's fibs
-						 */
-						list_add_tail(&newfib->fiblink, &fibctx->fib_list);
-						fibctx->count++;
-						/*
-						 * Set the event to wake up the
-						 * thread that is waiting.
-						 */
-						up(&fibctx->wait_sem);
-					} else {
-						printk(KERN_WARNING "aifd: didn't allocate NewFib.\n");
-					}
-					entry = entry->next;
-				}
-				/*
-				 *	Set the status of this FIB
-				 */
-				*(__le32 *)hw_fib->data = cpu_to_le32(ST_OK);
-				aac_fib_adapter_complete(fib, sizeof(u32));
-				spin_unlock_irqrestore(&dev->fib_lock, flagv);
-				/* Free up the remaining resources */
-				hw_fib_p = hw_fib_pool;
-				fib_p = fib_pool;
-				while (hw_fib_p < &hw_fib_pool[num]) {
-					kfree(*hw_fib_p);
-					kfree(*fib_p);
-					++fib_p;
-					++hw_fib_p;
-				}
-				kfree(hw_fib_pool);
-				kfree(fib_pool);
-			}
-			kfree(fib);
-			spin_lock_irqsave(dev->queues->queue[HostNormCmdQueue].lock, flags);
-		}
-		/*
-		 *	There are no more AIF's
-		 */
-		spin_unlock_irqrestore(dev->queues->queue[HostNormCmdQueue].lock, flags);
+		aac_process_events(dev);
 
 		/*
 		 *	Background activity
@@ -1968,7 +2434,7 @@ int aac_command_thread(void *data)
 
 			/* Don't even try to talk to adapter if its sick */
 			ret = aac_check_health(dev);
-			if (!ret && !dev->queues)
+			if (!dev->queues)
 				break;
 			next_check_jiffies = jiffies
 					   + ((long)(unsigned)check_interval)
@@ -1981,36 +2447,16 @@ int aac_command_thread(void *data)
 				difference = (((1000000 - now.tv_usec) * HZ)
 				  + 500000) / 1000000;
 			else if (ret == 0) {
-				struct fib *fibptr;
-
-				if ((fibptr = aac_fib_alloc(dev))) {
-					int status;
-					__le32 *info;
-
-					aac_fib_init(fibptr);
-
-					info = (__le32 *) fib_data(fibptr);
-					if (now.tv_usec > 500000)
-						++now.tv_sec;
-
-					*info = cpu_to_le32(now.tv_sec);
-
-					status = aac_fib_send(SendHostTime,
-						fibptr,
-						sizeof(*info),
-						FsaNormal,
-						1, 1,
-						NULL,
-						NULL);
-					/* Do not set XferState to zero unless
-					 * receives a response from F/W */
-					if (status >= 0)
-						aac_fib_complete(fibptr);
-					/* FIB should be freed only after
-					 * getting the response from the F/W */
-					if (status != -ERESTARTSYS)
-						aac_fib_free(fibptr);
-				}
+
+				if (now.tv_usec > 500000)
+					++now.tv_sec;
+
+				if (dev->sa_firmware)
+					ret =
+					aac_send_safw_hostttime(dev, &now);
+				else
+					ret = aac_send_hosttime(dev, &now);
+
 				difference = (long)(unsigned)update_interval*HZ;
 			} else {
 				/* retry shortly */
diff --git a/drivers/scsi/aacraid/dpcsup.c b/drivers/scsi/aacraid/dpcsup.c
index 7e836205aef1..417ba349e10e 100644
--- a/drivers/scsi/aacraid/dpcsup.c
+++ b/drivers/scsi/aacraid/dpcsup.c
@@ -6,7 +6,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -122,7 +123,6 @@ unsigned int aac_response_normal(struct aac_queue * q)
 			 *	NOTE:  we cannot touch the fib after this
 			 *	    call, because it may have been deallocated.
 			 */
-			fib->flags &= FIB_CONTEXT_FLAG_FASTRESP;
 			fib->callback(fib->callback_data, fib);
 		} else {
 			unsigned long flagv;
@@ -251,8 +251,9 @@ static void aac_aif_callback(void *context, struct fib * fibptr)
 	BUG_ON(fibptr == NULL);
 	dev = fibptr->dev;
 
-	if (fibptr->hw_fib_va->header.XferState &
-	    cpu_to_le32(NoMoreAifDataAvailable)) {
+	if ((fibptr->hw_fib_va->header.XferState &
+	    cpu_to_le32(NoMoreAifDataAvailable)) ||
+		dev->sa_firmware) {
 		aac_fib_complete(fibptr);
 		aac_fib_free(fibptr);
 		return;
@@ -282,8 +283,8 @@ static void aac_aif_callback(void *context, struct fib * fibptr)
  *	know there is a response on our normal priority queue. We will pull off
  *	all QE there are and wake up all the waiters before exiting.
  */
-unsigned int aac_intr_normal(struct aac_dev *dev, u32 index,
-			int isAif, int isFastResponse, struct hw_fib *aif_fib)
+unsigned int aac_intr_normal(struct aac_dev *dev, u32 index, int isAif,
+	int isFastResponse, struct hw_fib *aif_fib)
 {
 	unsigned long mflags;
 	dprintk((KERN_INFO "aac_intr_normal(%p,%x)\n", dev, index));
@@ -305,12 +306,14 @@ unsigned int aac_intr_normal(struct aac_dev *dev, u32 index,
 			kfree (fib);
 			return 1;
 		}
-		if (aif_fib != NULL) {
+		if (dev->sa_firmware) {
+			fib->hbacmd_size = index;	/* store event type */
+		} else if (aif_fib != NULL) {
 			memcpy(hw_fib, aif_fib, sizeof(struct hw_fib));
 		} else {
-			memcpy(hw_fib,
-				(struct hw_fib *)(((uintptr_t)(dev->regs.sa)) +
-				index), sizeof(struct hw_fib));
+			memcpy(hw_fib, (struct hw_fib *)
+				(((uintptr_t)(dev->regs.sa)) + index),
+				sizeof(struct hw_fib));
 		}
 		INIT_LIST_HEAD(&fib->fiblink);
 		fib->type = FSAFS_NTC_FIB_CONTEXT;
@@ -344,7 +347,7 @@ unsigned int aac_intr_normal(struct aac_dev *dev, u32 index,
 			(fib_callback)aac_aif_callback, fibctx);
 	} else {
 		struct fib *fib = &dev->fibs[index];
-		struct hw_fib * hwfib = fib->hw_fib_va;
+		int start_callback = 0;
 
 		/*
 		 *	Remove this fib from the Outstanding I/O queue.
@@ -362,60 +365,104 @@ unsigned int aac_intr_normal(struct aac_dev *dev, u32 index,
 			return 0;
 		}
 
-		if (isFastResponse) {
-			/*
-			 *	Doctor the fib
-			 */
-			*(__le32 *)hwfib->data = cpu_to_le32(ST_OK);
-			hwfib->header.XferState |= cpu_to_le32(AdapterProcessed);
-			fib->flags |= FIB_CONTEXT_FLAG_FASTRESP;
-		}
-
 		FIB_COUNTER_INCREMENT(aac_config.FibRecved);
 
-		if (hwfib->header.Command == cpu_to_le16(NuFileSystem))
-		{
-			__le32 *pstatus = (__le32 *)hwfib->data;
-			if (*pstatus & cpu_to_le32(0xffff0000))
-				*pstatus = cpu_to_le32(ST_OK);
-		}
-		if (hwfib->header.XferState & cpu_to_le32(NoResponseExpected | Async)) 
-		{
-	        	if (hwfib->header.XferState & cpu_to_le32(NoResponseExpected))
-				FIB_COUNTER_INCREMENT(aac_config.NoResponseRecved);
-			else 
-				FIB_COUNTER_INCREMENT(aac_config.AsyncRecved);
-			/*
-			 *	NOTE:  we cannot touch the fib after this
-			 *	    call, because it may have been deallocated.
-			 */
-			if (likely(fib->callback && fib->callback_data)) {
-				fib->flags &= FIB_CONTEXT_FLAG_FASTRESP;
-				fib->callback(fib->callback_data, fib);
-			} else
-				dev_info(&dev->pdev->dev,
-				"Invalid callback_fib[%d] (*%p)(%p)\n",
-				index, fib->callback, fib->callback_data);
+		if (fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA) {
+
+			if (isFastResponse)
+				fib->flags |= FIB_CONTEXT_FLAG_FASTRESP;
+
+			if (fib->callback) {
+				start_callback = 1;
+			} else {
+				unsigned long flagv;
+				int complete = 0;
+
+				dprintk((KERN_INFO "event_wait up\n"));
+				spin_lock_irqsave(&fib->event_lock, flagv);
+				if (fib->done == 2) {
+					fib->done = 1;
+					complete = 1;
+				} else {
+					fib->done = 1;
+					up(&fib->event_wait);
+				}
+				spin_unlock_irqrestore(&fib->event_lock, flagv);
+
+				spin_lock_irqsave(&dev->manage_lock, mflags);
+				dev->management_fib_count--;
+				spin_unlock_irqrestore(&dev->manage_lock,
+					mflags);
+
+				FIB_COUNTER_INCREMENT(aac_config.NativeRecved);
+				if (complete)
+					aac_fib_complete(fib);
+			}
 		} else {
-			unsigned long flagv;
-	  		dprintk((KERN_INFO "event_wait up\n"));
-			spin_lock_irqsave(&fib->event_lock, flagv);
-			if (!fib->done) {
-				fib->done = 1;
-				up(&fib->event_wait);
+			struct hw_fib *hwfib = fib->hw_fib_va;
+
+			if (isFastResponse) {
+				/* Doctor the fib */
+				*(__le32 *)hwfib->data = cpu_to_le32(ST_OK);
+				hwfib->header.XferState |=
+					cpu_to_le32(AdapterProcessed);
+				fib->flags |= FIB_CONTEXT_FLAG_FASTRESP;
 			}
-			spin_unlock_irqrestore(&fib->event_lock, flagv);
 
-			spin_lock_irqsave(&dev->manage_lock, mflags);
-			dev->management_fib_count--;
-			spin_unlock_irqrestore(&dev->manage_lock, mflags);
+			if (hwfib->header.Command ==
+				cpu_to_le16(NuFileSystem)) {
+				__le32 *pstatus = (__le32 *)hwfib->data;
 
-			FIB_COUNTER_INCREMENT(aac_config.NormalRecved);
-			if (fib->done == 2) {
+				if (*pstatus & cpu_to_le32(0xffff0000))
+					*pstatus = cpu_to_le32(ST_OK);
+			}
+			if (hwfib->header.XferState &
+				cpu_to_le32(NoResponseExpected | Async)) {
+				if (hwfib->header.XferState & cpu_to_le32(
+					NoResponseExpected))
+					FIB_COUNTER_INCREMENT(
+						aac_config.NoResponseRecved);
+				else
+					FIB_COUNTER_INCREMENT(
+						aac_config.AsyncRecved);
+				start_callback = 1;
+			} else {
+				unsigned long flagv;
+				int complete = 0;
+
+				dprintk((KERN_INFO "event_wait up\n"));
 				spin_lock_irqsave(&fib->event_lock, flagv);
-				fib->done = 0;
+				if (fib->done == 2) {
+					fib->done = 1;
+					complete = 1;
+				} else {
+					fib->done = 1;
+					up(&fib->event_wait);
+				}
 				spin_unlock_irqrestore(&fib->event_lock, flagv);
+
+				spin_lock_irqsave(&dev->manage_lock, mflags);
+				dev->management_fib_count--;
+				spin_unlock_irqrestore(&dev->manage_lock,
+					mflags);
+
+				FIB_COUNTER_INCREMENT(aac_config.NormalRecved);
+				if (complete)
+					aac_fib_complete(fib);
+			}
+		}
+
+
+		if (start_callback) {
+			/*
+			 * NOTE:  we cannot touch the fib after this
+			 *  call, because it may have been deallocated.
+			 */
+			if (likely(fib->callback && fib->callback_data)) {
+				fib->callback(fib->callback_data, fib);
+			} else {
 				aac_fib_complete(fib);
+				aac_fib_free(fib);
 			}
 
 		}
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 3ecbf20ca29f..137d22d3a005 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -6,7 +6,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -57,7 +58,7 @@
 
 #include "aacraid.h"
 
-#define AAC_DRIVER_VERSION		"1.2-1"
+#define AAC_DRIVER_VERSION		"1.2.1"
 #ifndef AAC_DRIVER_BRANCH
 #define AAC_DRIVER_BRANCH		""
 #endif
@@ -401,61 +402,89 @@ static int aac_biosparm(struct scsi_device *sdev, struct block_device *bdev,
 static int aac_slave_configure(struct scsi_device *sdev)
 {
 	struct aac_dev *aac = (struct aac_dev *)sdev->host->hostdata;
+	int chn, tid;
+	unsigned int depth = 0;
+	unsigned int set_timeout = 0;
+
+	chn = aac_logical_to_phys(sdev_channel(sdev));
+	tid = sdev_id(sdev);
+	if (chn < AAC_MAX_BUSES && tid < AAC_MAX_TARGETS &&
+		aac->hba_map[chn][tid].devtype == AAC_DEVTYPE_NATIVE_RAW) {
+		depth = aac->hba_map[chn][tid].qd_limit;
+		set_timeout = 1;
+		goto common_config;
+	}
+
+
 	if (aac->jbod && (sdev->type == TYPE_DISK))
 		sdev->removable = 1;
-	if ((sdev->type == TYPE_DISK) &&
-			(sdev_channel(sdev) != CONTAINER_CHANNEL) &&
-			(!aac->jbod || sdev->inq_periph_qual) &&
-			(!aac->raid_scsi_mode || (sdev_channel(sdev) != 2))) {
+
+	if (sdev->type == TYPE_DISK
+	 && sdev_channel(sdev) != CONTAINER_CHANNEL
+	 && (!aac->jbod || sdev->inq_periph_qual)
+	 && (!aac->raid_scsi_mode || (sdev_channel(sdev) != 2))) {
+
 		if (expose_physicals == 0)
 			return -ENXIO;
+
 		if (expose_physicals < 0)
 			sdev->no_uld_attach = 1;
 	}
-	if (sdev->tagged_supported && (sdev->type == TYPE_DISK) &&
-			(!aac->raid_scsi_mode || (sdev_channel(sdev) != 2)) &&
-			!sdev->no_uld_attach) {
+
+	if (sdev->tagged_supported
+	 &&  sdev->type == TYPE_DISK
+	 &&  (!aac->raid_scsi_mode || (sdev_channel(sdev) != 2))
+	 && !sdev->no_uld_attach) {
+
 		struct scsi_device * dev;
 		struct Scsi_Host *host = sdev->host;
 		unsigned num_lsu = 0;
 		unsigned num_one = 0;
-		unsigned depth;
 		unsigned cid;
 
-		/*
-		 * Firmware has an individual device recovery time typically
-		 * of 35 seconds, give us a margin.
-		 */
-		if (sdev->request_queue->rq_timeout < (45 * HZ))
-			blk_queue_rq_timeout(sdev->request_queue, 45*HZ);
+		set_timeout = 1;
+
 		for (cid = 0; cid < aac->maximum_num_containers; ++cid)
 			if (aac->fsa_dev[cid].valid)
 				++num_lsu;
+
 		__shost_for_each_device(dev, host) {
-			if (dev->tagged_supported && (dev->type == TYPE_DISK) &&
-					(!aac->raid_scsi_mode ||
-						(sdev_channel(sdev) != 2)) &&
-					!dev->no_uld_attach) {
+			if (dev->tagged_supported
+			 && dev->type == TYPE_DISK
+			 && (!aac->raid_scsi_mode || (sdev_channel(sdev) != 2))
+			 && !dev->no_uld_attach) {
 				if ((sdev_channel(dev) != CONTAINER_CHANNEL)
-				 || !aac->fsa_dev[sdev_id(dev)].valid)
+				 || !aac->fsa_dev[sdev_id(dev)].valid) {
 					++num_lsu;
-			} else
+				}
+			} else {
 				++num_one;
+			}
 		}
+
 		if (num_lsu == 0)
 			++num_lsu;
-		depth = (host->can_queue - num_one) / num_lsu;
-		if (depth > 256)
-			depth = 256;
-		else if (depth < 2)
-			depth = 2;
-		scsi_change_queue_depth(sdev, depth);
-	} else {
-		scsi_change_queue_depth(sdev, 1);
 
-		sdev->tagged_supported = 1;
+		depth = (host->can_queue - num_one) / num_lsu;
 	}
 
+common_config:
+	/*
+	 * Firmware has an individual device recovery time typically
+	 * of 35 seconds, give us a margin.
+	 */
+	if (set_timeout && sdev->request_queue->rq_timeout < (45 * HZ))
+		blk_queue_rq_timeout(sdev->request_queue, 45*HZ);
+
+	if (depth > 256)
+		depth = 256;
+	else if (depth < 1)
+		depth = 1;
+
+	scsi_change_queue_depth(sdev, depth);
+
+	sdev->tagged_supported = 1;
+
 	return 0;
 }
 
@@ -470,6 +499,15 @@ static int aac_slave_configure(struct scsi_device *sdev)
 
 static int aac_change_queue_depth(struct scsi_device *sdev, int depth)
 {
+	struct aac_dev *aac = (struct aac_dev *)(sdev->host->hostdata);
+	int chn, tid, is_native_device = 0;
+
+	chn = aac_logical_to_phys(sdev_channel(sdev));
+	tid = sdev_id(sdev);
+	if (chn < AAC_MAX_BUSES && tid < AAC_MAX_TARGETS &&
+		aac->hba_map[chn][tid].devtype == AAC_DEVTYPE_NATIVE_RAW)
+		is_native_device = 1;
+
 	if (sdev->tagged_supported && (sdev->type == TYPE_DISK) &&
 	    (sdev_channel(sdev) == CONTAINER_CHANNEL)) {
 		struct scsi_device * dev;
@@ -491,9 +529,12 @@ static int aac_change_queue_depth(struct scsi_device *sdev, int depth)
 		else if (depth < 2)
 			depth = 2;
 		return scsi_change_queue_depth(sdev, depth);
+	} else if (is_native_device) {
+		scsi_change_queue_depth(sdev, aac->hba_map[chn][tid].qd_limit);
+	} else {
+		scsi_change_queue_depth(sdev, 1);
 	}
-
-	return scsi_change_queue_depth(sdev, 1);
+	return sdev->queue_depth;
 }
 
 static ssize_t aac_show_raid_level(struct device *dev, struct device_attribute *attr, char *buf)
@@ -516,8 +557,39 @@ static struct device_attribute aac_raid_level_attr = {
 	.show = aac_show_raid_level
 };
 
+static ssize_t aac_show_unique_id(struct device *dev,
+	     struct device_attribute *attr, char *buf)
+{
+	struct scsi_device *sdev = to_scsi_device(dev);
+	struct aac_dev *aac = (struct aac_dev *)(sdev->host->hostdata);
+	unsigned char sn[16];
+
+	memset(sn, 0, sizeof(sn));
+
+	if (sdev_channel(sdev) == CONTAINER_CHANNEL)
+		memcpy(sn, aac->fsa_dev[sdev_id(sdev)].identifier, sizeof(sn));
+
+	return snprintf(buf, 16 * 2 + 2,
+		"%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X\n",
+		sn[0], sn[1], sn[2], sn[3],
+		sn[4], sn[5], sn[6], sn[7],
+		sn[8], sn[9], sn[10], sn[11],
+		sn[12], sn[13], sn[14], sn[15]);
+}
+
+static struct device_attribute aac_unique_id_attr = {
+	.attr = {
+		.name = "unique_id",
+		.mode = 0444,
+	},
+	.show = aac_show_unique_id
+};
+
+
+
 static struct device_attribute *aac_dev_attrs[] = {
 	&aac_raid_level_attr,
+	&aac_unique_id_attr,
 	NULL,
 };
 
@@ -534,46 +606,136 @@ static int aac_eh_abort(struct scsi_cmnd* cmd)
 	struct scsi_device * dev = cmd->device;
 	struct Scsi_Host * host = dev->host;
 	struct aac_dev * aac = (struct aac_dev *)host->hostdata;
-	int count;
+	int count, found;
+	u32 bus, cid;
 	int ret = FAILED;
 
-	printk(KERN_ERR "%s: Host adapter abort request (%d,%d,%d,%llu)\n",
-		AAC_DRIVERNAME,
-		host->host_no, sdev_channel(dev), sdev_id(dev), dev->lun);
-	switch (cmd->cmnd[0]) {
-	case SERVICE_ACTION_IN_16:
-		if (!(aac->raw_io_interface) ||
-		    !(aac->raw_io_64) ||
-		    ((cmd->cmnd[1] & 0x1f) != SAI_READ_CAPACITY_16))
-			break;
-	case INQUIRY:
-	case READ_CAPACITY:
-		/* Mark associated FIB to not complete, eh handler does this */
+	bus = aac_logical_to_phys(scmd_channel(cmd));
+	cid = scmd_id(cmd);
+	if (aac->hba_map[bus][cid].devtype == AAC_DEVTYPE_NATIVE_RAW) {
+		struct fib *fib;
+		struct aac_hba_tm_req *tmf;
+		int status;
+		u64 address;
+		__le32 managed_request_id;
+
+		pr_err("%s: Host adapter abort request (%d,%d,%d,%d)\n",
+		 AAC_DRIVERNAME,
+		 host->host_no, sdev_channel(dev), sdev_id(dev), (int)dev->lun);
+
+		found = 0;
 		for (count = 0; count < (host->can_queue + AAC_NUM_MGT_FIB); ++count) {
-			struct fib * fib = &aac->fibs[count];
-			if (fib->hw_fib_va->header.XferState &&
-			  (fib->flags & FIB_CONTEXT_FLAG) &&
-			  (fib->callback_data == cmd)) {
-				fib->flags |= FIB_CONTEXT_FLAG_TIMED_OUT;
-				cmd->SCp.phase = AAC_OWNER_ERROR_HANDLER;
+			fib = &aac->fibs[count];
+			if (*(u8 *)fib->hw_fib_va != 0 &&
+				(fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA) &&
+				(fib->callback_data == cmd)) {
+				found = 1;
+				managed_request_id = ((struct aac_hba_cmd_req *)
+					fib->hw_fib_va)->request_id;
+				break;
+			}
+		}
+		if (!found)
+			return ret;
+
+		/* start a HBA_TMF_ABORT_TASK TMF request */
+		fib = aac_fib_alloc(aac);
+		if (!fib)
+			return ret;
+
+		tmf = (struct aac_hba_tm_req *)fib->hw_fib_va;
+		memset(tmf, 0, sizeof(*tmf));
+		tmf->tmf = HBA_TMF_ABORT_TASK;
+		tmf->it_nexus = aac->hba_map[bus][cid].rmw_nexus;
+		tmf->lun[1] = cmd->device->lun;
+
+		address = (u64)fib->hw_error_pa;
+		tmf->error_ptr_hi = cpu_to_le32((u32)(address >> 32));
+		tmf->error_ptr_lo = cpu_to_le32((u32)(address & 0xffffffff));
+		tmf->error_length = cpu_to_le32(FW_ERROR_BUFFER_SIZE);
+
+		fib->hbacmd_size = sizeof(*tmf);
+		cmd->SCp.sent_command = 0;
+
+		status = aac_hba_send(HBA_IU_TYPE_SCSI_TM_REQ, fib,
+				  (fib_callback) aac_hba_callback,
+				  (void *) cmd);
+
+		/* Wait up to 2 minutes for completion */
+		for (count = 0; count < 120; ++count) {
+			if (cmd->SCp.sent_command) {
 				ret = SUCCESS;
+				break;
 			}
+			msleep(1000);
 		}
-		break;
-	case TEST_UNIT_READY:
-		/* Mark associated FIB to not complete, eh handler does this */
-		for (count = 0; count < (host->can_queue + AAC_NUM_MGT_FIB); ++count) {
-			struct scsi_cmnd * command;
-			struct fib * fib = &aac->fibs[count];
-			if ((fib->hw_fib_va->header.XferState & cpu_to_le32(Async | NoResponseExpected)) &&
-			  (fib->flags & FIB_CONTEXT_FLAG) &&
-			  ((command = fib->callback_data)) &&
-			  (command->device == cmd->device)) {
-				fib->flags |= FIB_CONTEXT_FLAG_TIMED_OUT;
-				command->SCp.phase = AAC_OWNER_ERROR_HANDLER;
-				if (command == cmd)
+
+		if (ret != SUCCESS)
+			pr_err("%s: Host adapter abort request timed out\n",
+			AAC_DRIVERNAME);
+	} else {
+		pr_err(
+			"%s: Host adapter abort request.\n"
+			"%s: Outstanding commands on (%d,%d,%d,%d):\n",
+			AAC_DRIVERNAME, AAC_DRIVERNAME,
+			host->host_no, sdev_channel(dev), sdev_id(dev),
+			(int)dev->lun);
+		switch (cmd->cmnd[0]) {
+		case SERVICE_ACTION_IN_16:
+			if (!(aac->raw_io_interface) ||
+			    !(aac->raw_io_64) ||
+			    ((cmd->cmnd[1] & 0x1f) != SAI_READ_CAPACITY_16))
+				break;
+		case INQUIRY:
+		case READ_CAPACITY:
+			/*
+			 * Mark associated FIB to not complete,
+			 * eh handler does this
+			 */
+			for (count = 0;
+				count < (host->can_queue + AAC_NUM_MGT_FIB);
+				++count) {
+				struct fib *fib = &aac->fibs[count];
+
+				if (fib->hw_fib_va->header.XferState &&
+				(fib->flags & FIB_CONTEXT_FLAG) &&
+				(fib->callback_data == cmd)) {
+					fib->flags |=
+						FIB_CONTEXT_FLAG_TIMED_OUT;
+					cmd->SCp.phase =
+						AAC_OWNER_ERROR_HANDLER;
 					ret = SUCCESS;
+				}
+			}
+			break;
+		case TEST_UNIT_READY:
+			/*
+			 * Mark associated FIB to not complete,
+			 * eh handler does this
+			 */
+			for (count = 0;
+				count < (host->can_queue + AAC_NUM_MGT_FIB);
+				++count) {
+				struct scsi_cmnd *command;
+				struct fib *fib = &aac->fibs[count];
+
+				command = fib->callback_data;
+
+				if ((fib->hw_fib_va->header.XferState &
+					cpu_to_le32
+					(Async | NoResponseExpected)) &&
+					(fib->flags & FIB_CONTEXT_FLAG) &&
+					((command)) &&
+					(command->device == cmd->device)) {
+					fib->flags |=
+						FIB_CONTEXT_FLAG_TIMED_OUT;
+					command->SCp.phase =
+						AAC_OWNER_ERROR_HANDLER;
+					if (command == cmd)
+						ret = SUCCESS;
+				}
 			}
+			break;
 		}
 	}
 	return ret;
@@ -588,70 +750,165 @@ static int aac_eh_reset(struct scsi_cmnd* cmd)
 {
 	struct scsi_device * dev = cmd->device;
 	struct Scsi_Host * host = dev->host;
-	struct scsi_cmnd * command;
-	int count;
 	struct aac_dev * aac = (struct aac_dev *)host->hostdata;
-	unsigned long flags;
-
-	/* Mark the associated FIB to not complete, eh handler does this */
-	for (count = 0; count < (host->can_queue + AAC_NUM_MGT_FIB); ++count) {
-		struct fib * fib = &aac->fibs[count];
-		if (fib->hw_fib_va->header.XferState &&
-		  (fib->flags & FIB_CONTEXT_FLAG) &&
-		  (fib->callback_data == cmd)) {
-			fib->flags |= FIB_CONTEXT_FLAG_TIMED_OUT;
-			cmd->SCp.phase = AAC_OWNER_ERROR_HANDLER;
+	int count;
+	u32 bus, cid;
+	int ret = FAILED;
+
+	bus = aac_logical_to_phys(scmd_channel(cmd));
+	cid = scmd_id(cmd);
+	if (bus < AAC_MAX_BUSES && cid < AAC_MAX_TARGETS &&
+		aac->hba_map[bus][cid].devtype == AAC_DEVTYPE_NATIVE_RAW) {
+		struct fib *fib;
+		int status;
+		u64 address;
+		u8 command;
+
+		pr_err("%s: Host adapter reset request. SCSI hang ?\n",
+			AAC_DRIVERNAME);
+
+		fib = aac_fib_alloc(aac);
+		if (!fib)
+			return ret;
+
+
+		if (aac->hba_map[bus][cid].reset_state == 0) {
+			struct aac_hba_tm_req *tmf;
+
+			/* start a HBA_TMF_LUN_RESET TMF request */
+			tmf = (struct aac_hba_tm_req *)fib->hw_fib_va;
+			memset(tmf, 0, sizeof(*tmf));
+			tmf->tmf = HBA_TMF_LUN_RESET;
+			tmf->it_nexus = aac->hba_map[bus][cid].rmw_nexus;
+			tmf->lun[1] = cmd->device->lun;
+
+			address = (u64)fib->hw_error_pa;
+			tmf->error_ptr_hi = cpu_to_le32
+					((u32)(address >> 32));
+			tmf->error_ptr_lo = cpu_to_le32
+					((u32)(address & 0xffffffff));
+			tmf->error_length = cpu_to_le32(FW_ERROR_BUFFER_SIZE);
+			fib->hbacmd_size = sizeof(*tmf);
+
+			command = HBA_IU_TYPE_SCSI_TM_REQ;
+			aac->hba_map[bus][cid].reset_state++;
+		} else if (aac->hba_map[bus][cid].reset_state >= 1) {
+			struct aac_hba_reset_req *rst;
+
+			/* already tried, start a hard reset now */
+			rst = (struct aac_hba_reset_req *)fib->hw_fib_va;
+			memset(rst, 0, sizeof(*rst));
+			/* reset_type is already zero... */
+			rst->it_nexus = aac->hba_map[bus][cid].rmw_nexus;
+
+			address = (u64)fib->hw_error_pa;
+			rst->error_ptr_hi = cpu_to_le32((u32)(address >> 32));
+			rst->error_ptr_lo = cpu_to_le32
+				((u32)(address & 0xffffffff));
+			rst->error_length = cpu_to_le32(FW_ERROR_BUFFER_SIZE);
+			fib->hbacmd_size = sizeof(*rst);
+
+			command = HBA_IU_TYPE_SATA_REQ;
+			aac->hba_map[bus][cid].reset_state = 0;
 		}
-	}
-	printk(KERN_ERR "%s: Host adapter reset request. SCSI hang ?\n",
-					AAC_DRIVERNAME);
+		cmd->SCp.sent_command = 0;
 
-	if ((count = aac_check_health(aac)))
-		return count;
-	/*
-	 * Wait for all commands to complete to this specific
-	 * target (block maximum 60 seconds).
-	 */
-	for (count = 60; count; --count) {
-		int active = aac->in_reset;
+		status = aac_hba_send(command, fib,
+				  (fib_callback) aac_hba_callback,
+				  (void *) cmd);
 
-		if (active == 0)
-		__shost_for_each_device(dev, host) {
-			spin_lock_irqsave(&dev->list_lock, flags);
-			list_for_each_entry(command, &dev->cmd_list, list) {
-				if ((command != cmd) &&
-				    (command->SCp.phase == AAC_OWNER_FIRMWARE)) {
-					active++;
-					break;
-				}
-			}
-			spin_unlock_irqrestore(&dev->list_lock, flags);
-			if (active)
+		/* Wait up to 2 minutes for completion */
+		for (count = 0; count < 120; ++count) {
+			if (cmd->SCp.sent_command) {
+				ret = SUCCESS;
 				break;
+			}
+			msleep(1000);
+		}
 
+		if (ret != SUCCESS)
+			pr_err("%s: Host adapter reset request timed out\n",
+			AAC_DRIVERNAME);
+	} else {
+		struct scsi_cmnd *command;
+		unsigned long flags;
+
+		/* Mark the assoc. FIB to not complete, eh handler does this */
+		for (count = 0;
+			count < (host->can_queue + AAC_NUM_MGT_FIB);
+			++count) {
+			struct fib *fib = &aac->fibs[count];
+
+			if (fib->hw_fib_va->header.XferState &&
+				(fib->flags & FIB_CONTEXT_FLAG) &&
+				(fib->callback_data == cmd)) {
+				fib->flags |= FIB_CONTEXT_FLAG_TIMED_OUT;
+				cmd->SCp.phase = AAC_OWNER_ERROR_HANDLER;
+			}
 		}
+
+		pr_err("%s: Host adapter reset request. SCSI hang ?\n",
+					AAC_DRIVERNAME);
+
+		count = aac_check_health(aac);
+		if (count)
+			return count;
 		/*
-		 * We can exit If all the commands are complete
+		 * Wait for all commands to complete to this specific
+		 * target (block maximum 60 seconds).
 		 */
-		if (active == 0)
-			return SUCCESS;
-		ssleep(1);
+		for (count = 60; count; --count) {
+			int active = aac->in_reset;
+
+			if (active == 0)
+			__shost_for_each_device(dev, host) {
+				spin_lock_irqsave(&dev->list_lock, flags);
+				list_for_each_entry(command, &dev->cmd_list,
+					list) {
+					if ((command != cmd) &&
+					(command->SCp.phase ==
+					AAC_OWNER_FIRMWARE)) {
+						active++;
+						break;
+					}
+				}
+				spin_unlock_irqrestore(&dev->list_lock, flags);
+				if (active)
+					break;
+
+			}
+			/*
+			 * We can exit If all the commands are complete
+			 */
+			if (active == 0)
+				return SUCCESS;
+			ssleep(1);
+		}
+		pr_err("%s: SCSI bus appears hung\n", AAC_DRIVERNAME);
+
+		/*
+		 * This adapter needs a blind reset, only do so for
+		 * Adapters that support a register, instead of a commanded,
+		 * reset.
+		 */
+		if (((aac->supplement_adapter_info.SupportedOptions2 &
+			  AAC_OPTION_MU_RESET) ||
+			  (aac->supplement_adapter_info.SupportedOptions2 &
+			  AAC_OPTION_DOORBELL_RESET)) &&
+			  aac_check_reset &&
+			  ((aac_check_reset != 1) ||
+			   !(aac->supplement_adapter_info.SupportedOptions2 &
+			    AAC_OPTION_IGNORE_RESET))) {
+			/* Bypass wait for command quiesce */
+			aac_reset_adapter(aac, 2, IOP_HWSOFT_RESET);
+		}
+		ret = SUCCESS;
 	}
-	printk(KERN_ERR "%s: SCSI bus appears hung\n", AAC_DRIVERNAME);
 	/*
-	 * This adapter needs a blind reset, only do so for Adapters that
-	 * support a register, instead of a commanded, reset.
+	 * Cause an immediate retry of the command with a ten second delay
+	 * after successful tur
 	 */
-	if (((aac->supplement_adapter_info.SupportedOptions2 &
-	  AAC_OPTION_MU_RESET) ||
-	  (aac->supplement_adapter_info.SupportedOptions2 &
-	  AAC_OPTION_DOORBELL_RESET)) &&
-	  aac_check_reset &&
-	  ((aac_check_reset != 1) ||
-	   !(aac->supplement_adapter_info.SupportedOptions2 &
-	    AAC_OPTION_IGNORE_RESET)))
-		aac_reset_adapter(aac, 2); /* Bypass wait for command quiesce */
-	return SUCCESS; /* Cause an immediate retry of the command with a ten second delay after successful tur */
+	return ret;
 }
 
 /**
@@ -911,10 +1168,16 @@ static ssize_t aac_store_reset_adapter(struct device *device,
 				       const char *buf, size_t count)
 {
 	int retval = -EACCES;
+	int bled = 0;
+	struct aac_dev *aac;
+
 
 	if (!capable(CAP_SYS_ADMIN))
 		return retval;
-	retval = aac_reset_adapter((struct aac_dev*)class_to_shost(device)->hostdata, buf[0] == '!');
+
+	aac = (struct aac_dev *)class_to_shost(device)->hostdata;
+	bled = buf[0] == '!' ? 1:0;
+	retval = aac_reset_adapter(aac, bled, IOP_HWSOFT_RESET);
 	if (retval >= 0)
 		retval = count;
 	return retval;
@@ -1070,6 +1333,7 @@ static void __aac_shutdown(struct aac_dev * aac)
 {
 	int i;
 
+	aac->adapter_shutdown = 1;
 	aac_send_shutdown(aac);
 
 	if (aac->aif_thread) {
@@ -1285,7 +1549,7 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	else
 		shost->this_id = shost->max_id;
 
-	if (aac_drivers[index].quirks & AAC_QUIRK_SRC)
+	if (!aac->sa_firmware && aac_drivers[index].quirks & AAC_QUIRK_SRC)
 		aac_intr_normal(aac, 0, 2, 0, NULL);
 
 	/*
@@ -1327,35 +1591,12 @@ static int aac_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 
 static void aac_release_resources(struct aac_dev *aac)
 {
-	int i;
-
 	aac_adapter_disable_int(aac);
-	if (aac->pdev->device == PMC_DEVICE_S6 ||
-	    aac->pdev->device == PMC_DEVICE_S7 ||
-	    aac->pdev->device == PMC_DEVICE_S8 ||
-	    aac->pdev->device == PMC_DEVICE_S9) {
-		if (aac->max_msix > 1) {
-			for (i = 0; i < aac->max_msix; i++)
-				free_irq(pci_irq_vector(aac->pdev, i),
-					&(aac->aac_msix[i]));
-		} else {
-			free_irq(aac->pdev->irq, &(aac->aac_msix[0]));
-		}
-	} else {
-		free_irq(aac->pdev->irq, aac);
-	}
-	if (aac->msi)
-		pci_disable_msi(aac->pdev);
-	else if (aac->max_msix > 1)
-		pci_disable_msix(aac->pdev);
-
+	aac_free_irq(aac);
 }
 
 static int aac_acquire_resources(struct aac_dev *dev)
 {
-	int i, j;
-	int instance = dev->id;
-	const char *name = dev->name;
 	unsigned long status;
 	/*
 	 *	First clear out all interrupts.  Then enable the one's that we
@@ -1377,37 +1618,8 @@ static int aac_acquire_resources(struct aac_dev *dev)
 	if (dev->msi_enabled)
 		aac_src_access_devreg(dev, AAC_ENABLE_MSIX);
 
-	if (!dev->sync_mode && dev->msi_enabled && dev->max_msix > 1) {
-		for (i = 0; i < dev->max_msix; i++) {
-			dev->aac_msix[i].vector_no = i;
-			dev->aac_msix[i].dev = dev;
-
-			if (request_irq(pci_irq_vector(dev->pdev, i),
-					dev->a_ops.adapter_intr,
-					0, "aacraid", &(dev->aac_msix[i]))) {
-				printk(KERN_ERR "%s%d: Failed to register IRQ for vector %d.\n",
-						name, instance, i);
-				for (j = 0 ; j < i ; j++)
-					free_irq(pci_irq_vector(dev->pdev, j),
-						 &(dev->aac_msix[j]));
-				pci_disable_msix(dev->pdev);
-				goto error_iounmap;
-			}
-		}
-	} else {
-		dev->aac_msix[0].vector_no = 0;
-		dev->aac_msix[0].dev = dev;
-
-		if (request_irq(dev->pdev->irq, dev->a_ops.adapter_intr,
-			IRQF_SHARED, "aacraid",
-			&(dev->aac_msix[0])) < 0) {
-			if (dev->msi)
-				pci_disable_msi(dev->pdev);
-			printk(KERN_ERR "%s%d: Interrupt unavailable.\n",
-					name, instance);
-			goto error_iounmap;
-		}
-	}
+	if (aac_acquire_irq(dev))
+		goto error_iounmap;
 
 	aac_adapter_enable_int(dev);
 
@@ -1420,7 +1632,7 @@ static int aac_acquire_resources(struct aac_dev *dev)
 		/* After EEH recovery or suspend resume, max_msix count
 		 * may change, therfore updating in init as well.
 		 */
-		dev->init->Sa_MSIXVectors = cpu_to_le32(dev->max_msix);
+		dev->init->r7.no_of_msix_vectors = cpu_to_le32(dev->max_msix);
 		aac_adapter_start(dev);
 	}
 	return 0;
diff --git a/drivers/scsi/aacraid/nark.c b/drivers/scsi/aacraid/nark.c
index 6c53b1d8b2ba..c59074e782d6 100644
--- a/drivers/scsi/aacraid/nark.c
+++ b/drivers/scsi/aacraid/nark.c
@@ -5,7 +5,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
diff --git a/drivers/scsi/aacraid/rkt.c b/drivers/scsi/aacraid/rkt.c
index 7d8013feedde..a1bc5bbf7a34 100644
--- a/drivers/scsi/aacraid/rkt.c
+++ b/drivers/scsi/aacraid/rkt.c
@@ -6,7 +6,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -60,7 +61,7 @@ static int aac_rkt_select_comm(struct aac_dev *dev, int comm)
 		 * case warrants this half baked, but convenient, check here.
 		 */
 		if (dev->scsi_host_ptr->can_queue > AAC_NUM_IO_FIB_RKT) {
-			dev->init->MaxIoCommands =
+			dev->init->r7.max_io_commands =
 				cpu_to_le32(AAC_NUM_IO_FIB_RKT + AAC_NUM_MGT_FIB);
 			dev->scsi_host_ptr->can_queue = AAC_NUM_IO_FIB_RKT;
 		}
diff --git a/drivers/scsi/aacraid/rx.c b/drivers/scsi/aacraid/rx.c
index ac1638069335..0e69a80c3275 100644
--- a/drivers/scsi/aacraid/rx.c
+++ b/drivers/scsi/aacraid/rx.c
@@ -6,7 +6,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -315,10 +316,10 @@ static void aac_rx_notify_adapter(struct aac_dev *dev, u32 event)
 
 static void aac_rx_start_adapter(struct aac_dev *dev)
 {
-	struct aac_init *init;
+	union aac_init *init;
 
 	init = dev->init;
-	init->HostElapsedSeconds = cpu_to_le32(get_seconds());
+	init->r7.host_elapsed_seconds = cpu_to_le32(get_seconds());
 	// We can only use a 32 bit address here
 	rx_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS, (u32)(ulong)dev->init_pa,
 	  0, 0, 0, 0, 0, NULL, NULL, NULL, NULL, NULL);
@@ -470,7 +471,7 @@ static int aac_rx_ioremap(struct aac_dev * dev, u32 size)
 	return 0;
 }
 
-static int aac_rx_restart_adapter(struct aac_dev *dev, int bled)
+static int aac_rx_restart_adapter(struct aac_dev *dev, int bled, u8 reset_type)
 {
 	u32 var = 0;
 
@@ -559,7 +560,7 @@ int _aac_rx_init(struct aac_dev *dev)
 	dev->a_ops.adapter_enable_int = aac_rx_disable_interrupt;
 	dev->OIMR = status = rx_readb (dev, MUnit.OIMR);
 	if ((((status & 0x0c) != 0x0c) || aac_reset_devices || reset_devices) &&
-	  !aac_rx_restart_adapter(dev, 0))
+	  !aac_rx_restart_adapter(dev, 0, IOP_HWSOFT_RESET))
 		/* Make sure the Hardware FIFO is empty */
 		while ((++restart < 512) &&
 		  (rx_readl(dev, MUnit.OutboundQueue) != 0xFFFFFFFFL));
@@ -568,7 +569,8 @@ int _aac_rx_init(struct aac_dev *dev)
 	 */
 	status = rx_readl(dev, MUnit.OMRx[0]);
 	if (status & KERNEL_PANIC) {
-		if (aac_rx_restart_adapter(dev, aac_rx_check_health(dev)))
+		if (aac_rx_restart_adapter(dev,
+			aac_rx_check_health(dev), IOP_HWSOFT_RESET))
 			goto error_iounmap;
 		++restart;
 	}
@@ -606,7 +608,8 @@ int _aac_rx_init(struct aac_dev *dev)
 		  ((startup_timeout > 60)
 		    ? (startup_timeout - 60)
 		    : (startup_timeout / 2))))) {
-			if (likely(!aac_rx_restart_adapter(dev, aac_rx_check_health(dev))))
+			if (likely(!aac_rx_restart_adapter(dev,
+				aac_rx_check_health(dev), IOP_HWSOFT_RESET)))
 				start = jiffies;
 			++restart;
 		}
diff --git a/drivers/scsi/aacraid/sa.c b/drivers/scsi/aacraid/sa.c
index 869aea23c041..553922fed524 100644
--- a/drivers/scsi/aacraid/sa.c
+++ b/drivers/scsi/aacraid/sa.c
@@ -6,7 +6,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -245,19 +246,19 @@ static void aac_sa_interrupt_adapter (struct aac_dev *dev)
 
 static void aac_sa_start_adapter(struct aac_dev *dev)
 {
-	struct aac_init *init;
+	union aac_init *init;
 	/*
 	 * Fill in the remaining pieces of the init.
 	 */
 	init = dev->init;
-	init->HostElapsedSeconds = cpu_to_le32(get_seconds());
+	init->r7.host_elapsed_seconds = cpu_to_le32(get_seconds());
 	/* We can only use a 32 bit address here */
 	sa_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS, 
 			(u32)(ulong)dev->init_pa, 0, 0, 0, 0, 0,
 			NULL, NULL, NULL, NULL, NULL);
 }
 
-static int aac_sa_restart_adapter(struct aac_dev *dev, int bled)
+static int aac_sa_restart_adapter(struct aac_dev *dev, int bled, u8 reset_type)
 {
 	return -EINVAL;
 }
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 0c453880f214..8e4e2ddbafd7 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -6,7 +6,8 @@
  * Adaptec aacraid device driver for Linux.
  *
  * Copyright (c) 2000-2010 Adaptec, Inc.
- *               2010 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *               2010-2015 PMC-Sierra, Inc. (aacraid@pmc-sierra.com)
+ *		 2016-2017 Microsemi Corp. (aacraid@microsemi.com)
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -135,8 +136,16 @@ static irqreturn_t aac_src_intr_message(int irq, void *dev_id)
 
 	if (mode & AAC_INT_MODE_AIF) {
 		/* handle AIF */
-		if (dev->aif_thread && dev->fsa_dev)
-			aac_intr_normal(dev, 0, 2, 0, NULL);
+		if (dev->sa_firmware) {
+			u32 events = src_readl(dev, MUnit.SCR0);
+
+			aac_intr_normal(dev, events, 1, 0, NULL);
+			writel(events, &dev->IndexRegs->Mailbox[0]);
+			src_writel(dev, MUnit.IDR, 1 << 23);
+		} else {
+			if (dev->aif_thread && dev->fsa_dev)
+				aac_intr_normal(dev, 0, 2, 0, NULL);
+		}
 		if (dev->msi_enabled)
 			aac_src_access_devreg(dev, AAC_CLEAR_AIF_BIT);
 		mode = 0;
@@ -148,17 +157,19 @@ static irqreturn_t aac_src_intr_message(int irq, void *dev_id)
 		for (;;) {
 			isFastResponse = 0;
 			/* remove toggle bit (31) */
-			handle = (dev->host_rrq[index] & 0x7fffffff);
-			/* check fast response bit (30) */
+			handle = le32_to_cpu((dev->host_rrq[index])
+				& 0x7fffffff);
+			/* check fast response bits (30, 1) */
 			if (handle & 0x40000000)
 				isFastResponse = 1;
 			handle &= 0x0000ffff;
 			if (handle == 0)
 				break;
+			handle >>= 2;
 			if (dev->msi_enabled && dev->max_msix > 1)
 				atomic_dec(&dev->rrq_outstanding[vector_no]);
+			aac_intr_normal(dev, handle, 0, isFastResponse, NULL);
 			dev->host_rrq[index++] = 0;
-			aac_intr_normal(dev, handle-1, 0, isFastResponse, NULL);
 			if (index == (vector_no + 1) * dev->vector_cap)
 				index = vector_no * dev->vector_cap;
 			dev->host_rrq_idx[vector_no] = index;
@@ -384,7 +395,7 @@ static void aac_src_notify_adapter(struct aac_dev *dev, u32 event)
 
 static void aac_src_start_adapter(struct aac_dev *dev)
 {
-	struct aac_init *init;
+	union aac_init *init;
 	int i;
 
 	 /* reset host_rrq_idx first */
@@ -392,14 +403,26 @@ static void aac_src_start_adapter(struct aac_dev *dev)
 		dev->host_rrq_idx[i] = i * dev->vector_cap;
 		atomic_set(&dev->rrq_outstanding[i], 0);
 	}
+	atomic_set(&dev->msix_counter, 0);
 	dev->fibs_pushed_no = 0;
 
 	init = dev->init;
-	init->HostElapsedSeconds = cpu_to_le32(get_seconds());
+	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) {
+		init->r8.host_elapsed_seconds = cpu_to_le32(get_seconds());
+		src_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS,
+			lower_32_bits(dev->init_pa),
+			upper_32_bits(dev->init_pa),
+			sizeof(struct _r8) +
+			(AAC_MAX_HRRQ - 1) * sizeof(struct _rrq),
+			0, 0, 0, NULL, NULL, NULL, NULL, NULL);
+	} else {
+		init->r7.host_elapsed_seconds = cpu_to_le32(get_seconds());
+		// We can only use a 32 bit address here
+		src_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS,
+			(u32)(ulong)dev->init_pa, 0, 0, 0, 0, 0,
+			NULL, NULL, NULL, NULL, NULL);
+	}
 
-	/* We can only use a 32 bit address here */
-	src_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS, (u32)(ulong)dev->init_pa,
-	  0, 0, 0, 0, 0, NULL, NULL, NULL, NULL, NULL);
 }
 
 /**
@@ -435,6 +458,11 @@ static int aac_src_check_health(struct aac_dev *dev)
 	return 0;
 }
 
+static inline u32 aac_get_vector(struct aac_dev *dev)
+{
+	return atomic_inc_return(&dev->msix_counter)%dev->max_msix;
+}
+
 /**
  *	aac_src_deliver_message
  *	@fib: fib to issue
@@ -448,66 +476,125 @@ static int aac_src_deliver_message(struct fib *fib)
 	u32 fibsize;
 	dma_addr_t address;
 	struct aac_fib_xporthdr *pFibX;
+	int native_hba;
 #if !defined(writeq)
 	unsigned long flags;
 #endif
 
-	u16 hdr_size = le16_to_cpu(fib->hw_fib_va->header.Size);
 	u16 vector_no;
 
 	atomic_inc(&q->numpending);
 
-	if (dev->msi_enabled && fib->hw_fib_va->header.Command != AifRequest &&
-	    dev->max_msix > 1) {
-		vector_no = fib->vector_no;
-		fib->hw_fib_va->header.Handle += (vector_no << 16);
+	native_hba = (fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA) ? 1 : 0;
+
+
+	if (dev->msi_enabled && dev->max_msix > 1 &&
+		(native_hba || fib->hw_fib_va->header.Command != AifRequest)) {
+
+		if ((dev->comm_interface == AAC_COMM_MESSAGE_TYPE3)
+			&& dev->sa_firmware)
+			vector_no = aac_get_vector(dev);
+		else
+			vector_no = fib->vector_no;
+
+		if (native_hba) {
+			if (fib->flags & FIB_CONTEXT_FLAG_NATIVE_HBA_TMF) {
+				struct aac_hba_tm_req *tm_req;
+
+				tm_req = (struct aac_hba_tm_req *)
+						fib->hw_fib_va;
+				if (tm_req->iu_type ==
+					HBA_IU_TYPE_SCSI_TM_REQ) {
+					((struct aac_hba_tm_req *)
+						fib->hw_fib_va)->reply_qid
+							= vector_no;
+					((struct aac_hba_tm_req *)
+						fib->hw_fib_va)->request_id
+							+= (vector_no << 16);
+				} else {
+					((struct aac_hba_reset_req *)
+						fib->hw_fib_va)->reply_qid
+							= vector_no;
+					((struct aac_hba_reset_req *)
+						fib->hw_fib_va)->request_id
+							+= (vector_no << 16);
+				}
+			} else {
+				((struct aac_hba_cmd_req *)
+					fib->hw_fib_va)->reply_qid
+						= vector_no;
+				((struct aac_hba_cmd_req *)
+					fib->hw_fib_va)->request_id
+						+= (vector_no << 16);
+			}
+		} else {
+			fib->hw_fib_va->header.Handle += (vector_no << 16);
+		}
 	} else {
 		vector_no = 0;
 	}
 
 	atomic_inc(&dev->rrq_outstanding[vector_no]);
 
-	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE2) {
-		/* Calculate the amount to the fibsize bits */
-		fibsize = (hdr_size + 127) / 128 - 1;
-		if (fibsize > (ALIGN32 - 1))
-			return -EMSGSIZE;
-		/* New FIB header, 32-bit */
+	if (native_hba) {
 		address = fib->hw_fib_pa;
-		fib->hw_fib_va->header.StructType = FIB_MAGIC2;
-		fib->hw_fib_va->header.SenderFibAddress = (u32)address;
-		fib->hw_fib_va->header.u.TimeStamp = 0;
-		BUG_ON(upper_32_bits(address) != 0L);
+		fibsize = (fib->hbacmd_size + 127) / 128 - 1;
+		if (fibsize > 31)
+			fibsize = 31;
 		address |= fibsize;
+#if defined(writeq)
+		src_writeq(dev, MUnit.IQN_L, (u64)address);
+#else
+		spin_lock_irqsave(&fib->dev->iq_lock, flags);
+		src_writel(dev, MUnit.IQN_H,
+			upper_32_bits(address) & 0xffffffff);
+		src_writel(dev, MUnit.IQN_L, address & 0xffffffff);
+		spin_unlock_irqrestore(&fib->dev->iq_lock, flags);
+#endif
 	} else {
-		/* Calculate the amount to the fibsize bits */
-		fibsize = (sizeof(struct aac_fib_xporthdr) + hdr_size + 127) / 128 - 1;
-		if (fibsize > (ALIGN32 - 1))
-			return -EMSGSIZE;
-
-		/* Fill XPORT header */
-		pFibX = (void *)fib->hw_fib_va - sizeof(struct aac_fib_xporthdr);
-		pFibX->Handle = cpu_to_le32(fib->hw_fib_va->header.Handle);
-		pFibX->HostAddress = cpu_to_le64(fib->hw_fib_pa);
-		pFibX->Size = cpu_to_le32(hdr_size);
-
-		/*
-		 * The xport header has been 32-byte aligned for us so that fibsize
-		 * can be masked out of this address by hardware. -- BenC
-		 */
-		address = fib->hw_fib_pa - sizeof(struct aac_fib_xporthdr);
-		if (address & (ALIGN32 - 1))
-			return -EINVAL;
+		if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE2 ||
+			dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) {
+			/* Calculate the amount to the fibsize bits */
+			fibsize = (le16_to_cpu(fib->hw_fib_va->header.Size)
+				+ 127) / 128 - 1;
+			/* New FIB header, 32-bit */
+			address = fib->hw_fib_pa;
+			fib->hw_fib_va->header.StructType = FIB_MAGIC2;
+			fib->hw_fib_va->header.SenderFibAddress =
+				cpu_to_le32((u32)address);
+			fib->hw_fib_va->header.u.TimeStamp = 0;
+			WARN_ON(upper_32_bits(address) != 0L);
+		} else {
+			/* Calculate the amount to the fibsize bits */
+			fibsize = (sizeof(struct aac_fib_xporthdr) +
+				le16_to_cpu(fib->hw_fib_va->header.Size)
+				+ 127) / 128 - 1;
+			/* Fill XPORT header */
+			pFibX = (struct aac_fib_xporthdr *)
+				((unsigned char *)fib->hw_fib_va -
+				sizeof(struct aac_fib_xporthdr));
+			pFibX->Handle = fib->hw_fib_va->header.Handle;
+			pFibX->HostAddress =
+				cpu_to_le64((u64)fib->hw_fib_pa);
+			pFibX->Size = cpu_to_le32(
+				le16_to_cpu(fib->hw_fib_va->header.Size));
+			address = fib->hw_fib_pa -
+				(u64)sizeof(struct aac_fib_xporthdr);
+		}
+		if (fibsize > 31)
+			fibsize = 31;
 		address |= fibsize;
-	}
+
 #if defined(writeq)
-	src_writeq(dev, MUnit.IQ_L, (u64)address);
+		src_writeq(dev, MUnit.IQ_L, (u64)address);
 #else
-	spin_lock_irqsave(&fib->dev->iq_lock, flags);
-	src_writel(dev, MUnit.IQ_H, upper_32_bits(address) & 0xffffffff);
-	src_writel(dev, MUnit.IQ_L, address & 0xffffffff);
-	spin_unlock_irqrestore(&fib->dev->iq_lock, flags);
+		spin_lock_irqsave(&fib->dev->iq_lock, flags);
+		src_writel(dev, MUnit.IQ_H,
+			upper_32_bits(address) & 0xffffffff);
+		src_writel(dev, MUnit.IQ_L, address & 0xffffffff);
+		spin_unlock_irqrestore(&fib->dev->iq_lock, flags);
 #endif
+	}
 	return 0;
 }
 
@@ -553,52 +640,117 @@ static int aac_srcv_ioremap(struct aac_dev *dev, u32 size)
 		dev->base = dev->regs.src.bar0 = NULL;
 		return 0;
 	}
+
+	dev->regs.src.bar1 =
+	ioremap(pci_resource_start(dev->pdev, 2), AAC_MIN_SRCV_BAR1_SIZE);
+	dev->base = NULL;
+	if (dev->regs.src.bar1 == NULL)
+		return -1;
 	dev->base = dev->regs.src.bar0 = ioremap(dev->base_start, size);
-	if (dev->base == NULL)
+	if (dev->base == NULL) {
+		iounmap(dev->regs.src.bar1);
+		dev->regs.src.bar1 = NULL;
 		return -1;
+	}
 	dev->IndexRegs = &((struct src_registers __iomem *)
 		dev->base)->u.denali.IndexRegs;
 	return 0;
 }
 
-static int aac_src_restart_adapter(struct aac_dev *dev, int bled)
+static void aac_set_intx_mode(struct aac_dev *dev)
+{
+	if (dev->msi_enabled) {
+		aac_src_access_devreg(dev, AAC_ENABLE_INTX);
+		dev->msi_enabled = 0;
+		msleep(5000); /* Delay 5 seconds */
+	}
+}
+
+static void aac_send_iop_reset(struct aac_dev *dev, int bled)
 {
 	u32 var, reset_mask;
 
-	if (bled >= 0) {
-		if (bled)
-			printk(KERN_ERR "%s%d: adapter kernel panic'd %x.\n",
+	bled = aac_adapter_sync_cmd(dev, IOP_RESET_ALWAYS,
+				    0, 0, 0, 0, 0, 0, &var,
+				    &reset_mask, NULL, NULL, NULL);
+
+	if ((bled || var != 0x00000001) && !dev->doorbell_mask)
+		bled = -EINVAL;
+	else if (dev->doorbell_mask) {
+		reset_mask = dev->doorbell_mask;
+		bled = 0;
+		var = 0x00000001;
+	}
+
+	aac_set_intx_mode(dev);
+
+	if (!bled && (dev->supplement_adapter_info.SupportedOptions2 &
+	    AAC_OPTION_DOORBELL_RESET)) {
+		src_writel(dev, MUnit.IDR, reset_mask);
+	} else {
+		src_writel(dev, MUnit.IDR, 0x100);
+	}
+	msleep(30000);
+}
+
+static void aac_send_hardware_soft_reset(struct aac_dev *dev)
+{
+	u_int32_t val;
+
+	val = readl(((char *)(dev->base) + IBW_SWR_OFFSET));
+	val |= 0x01;
+	writel(val, ((char *)(dev->base) + IBW_SWR_OFFSET));
+	msleep_interruptible(20000);
+}
+
+static int aac_src_restart_adapter(struct aac_dev *dev, int bled, u8 reset_type)
+{
+	unsigned long status, start;
+
+	if (bled < 0)
+		goto invalid_out;
+
+	if (bled)
+		pr_err("%s%d: adapter kernel panic'd %x.\n",
 				dev->name, dev->id, bled);
-		dev->a_ops.adapter_enable_int = aac_src_disable_interrupt;
-		bled = aac_adapter_sync_cmd(dev, IOP_RESET_ALWAYS,
-			0, 0, 0, 0, 0, 0, &var, &reset_mask, NULL, NULL, NULL);
-		if ((bled || (var != 0x00000001)) &&
-		    !dev->doorbell_mask)
-			return -EINVAL;
-		else if (dev->doorbell_mask) {
-			reset_mask = dev->doorbell_mask;
-			bled = 0;
-			var = 0x00000001;
-		}
 
-		if ((dev->pdev->device == PMC_DEVICE_S7 ||
-		    dev->pdev->device == PMC_DEVICE_S8 ||
-		    dev->pdev->device == PMC_DEVICE_S9) && dev->msi_enabled) {
-			aac_src_access_devreg(dev, AAC_ENABLE_INTX);
-			dev->msi_enabled = 0;
-			msleep(5000); /* Delay 5 seconds */
-		}
+	dev->a_ops.adapter_enable_int = aac_src_disable_interrupt;
 
-		if (!bled && (dev->supplement_adapter_info.SupportedOptions2 &
-		    AAC_OPTION_DOORBELL_RESET)) {
-			src_writel(dev, MUnit.IDR, reset_mask);
-			ssleep(45);
-		} else {
-			src_writel(dev, MUnit.IDR, 0x100);
-			ssleep(45);
+	switch (reset_type) {
+	case IOP_HWSOFT_RESET:
+		aac_send_iop_reset(dev, bled);
+		/*
+		 * Check to see if KERNEL_UP_AND_RUNNING
+		 * Wait for the adapter to be up and running.
+		 * If !KERNEL_UP_AND_RUNNING issue HW Soft Reset
+		 */
+		status = src_readl(dev, MUnit.OMR);
+		if (dev->sa_firmware
+		 && !(status & KERNEL_UP_AND_RUNNING)) {
+			start = jiffies;
+			do {
+				status = src_readl(dev, MUnit.OMR);
+				if (time_after(jiffies,
+				 start+HZ*SOFT_RESET_TIME)) {
+					aac_send_hardware_soft_reset(dev);
+					start = jiffies;
+				}
+			} while (!(status & KERNEL_UP_AND_RUNNING));
 		}
+		break;
+	case HW_SOFT_RESET:
+		if (dev->sa_firmware) {
+			aac_send_hardware_soft_reset(dev);
+			aac_set_intx_mode(dev);
+		}
+		break;
+	default:
+		aac_send_iop_reset(dev, bled);
+		break;
 	}
 
+invalid_out:
+
 	if (src_readl(dev, MUnit.OMR) & KERNEL_PANIC)
 		return -ENODEV;
 
@@ -653,14 +805,15 @@ int aac_src_init(struct aac_dev *dev)
 	dev->a_ops.adapter_sync_cmd = src_sync_cmd;
 	dev->a_ops.adapter_enable_int = aac_src_disable_interrupt;
 	if ((aac_reset_devices || reset_devices) &&
-		!aac_src_restart_adapter(dev, 0))
+		!aac_src_restart_adapter(dev, 0, IOP_HWSOFT_RESET))
 		++restart;
 	/*
 	 *	Check to see if the board panic'd while booting.
 	 */
 	status = src_readl(dev, MUnit.OMR);
 	if (status & KERNEL_PANIC) {
-		if (aac_src_restart_adapter(dev, aac_src_check_health(dev)))
+		if (aac_src_restart_adapter(dev,
+			aac_src_check_health(dev), IOP_HWSOFT_RESET))
 			goto error_iounmap;
 		++restart;
 	}
@@ -701,7 +854,7 @@ int aac_src_init(struct aac_dev *dev)
 		    ? (startup_timeout - 60)
 		    : (startup_timeout / 2))))) {
 			if (likely(!aac_src_restart_adapter(dev,
-			    aac_src_check_health(dev))))
+				aac_src_check_health(dev), IOP_HWSOFT_RESET)))
 				start = jiffies;
 			++restart;
 		}
@@ -798,7 +951,7 @@ int aac_srcv_init(struct aac_dev *dev)
 	dev->a_ops.adapter_sync_cmd = src_sync_cmd;
 	dev->a_ops.adapter_enable_int = aac_src_disable_interrupt;
 	if ((aac_reset_devices || reset_devices) &&
-		!aac_src_restart_adapter(dev, 0))
+		!aac_src_restart_adapter(dev, 0, IOP_HWSOFT_RESET))
 		++restart;
 	/*
 	 *	Check to see if flash update is running.
@@ -827,7 +980,8 @@ int aac_srcv_init(struct aac_dev *dev)
 	 */
 	status = src_readl(dev, MUnit.OMR);
 	if (status & KERNEL_PANIC) {
-		if (aac_src_restart_adapter(dev, aac_src_check_health(dev)))
+		if (aac_src_restart_adapter(dev,
+			aac_src_check_health(dev), IOP_HWSOFT_RESET))
 			goto error_iounmap;
 		++restart;
 	}
@@ -866,7 +1020,8 @@ int aac_srcv_init(struct aac_dev *dev)
 		  ((startup_timeout > 60)
 		    ? (startup_timeout - 60)
 		    : (startup_timeout / 2))))) {
-			if (likely(!aac_src_restart_adapter(dev, aac_src_check_health(dev))))
+			if (likely(!aac_src_restart_adapter(dev,
+				aac_src_check_health(dev), IOP_HWSOFT_RESET)))
 				start = jiffies;
 			++restart;
 		}
@@ -897,7 +1052,8 @@ int aac_srcv_init(struct aac_dev *dev)
 
 	if (aac_init_adapter(dev) == NULL)
 		goto error_iounmap;
-	if (dev->comm_interface != AAC_COMM_MESSAGE_TYPE2)
+	if ((dev->comm_interface != AAC_COMM_MESSAGE_TYPE2) &&
+		(dev->comm_interface != AAC_COMM_MESSAGE_TYPE3))
 		goto error_iounmap;
 	if (dev->msi_enabled)
 		aac_src_access_devreg(dev, AAC_ENABLE_MSIX);
@@ -905,9 +1061,9 @@ int aac_srcv_init(struct aac_dev *dev)
 	if (aac_acquire_irq(dev))
 		goto error_iounmap;
 
-	dev->dbg_base = dev->base_start;
-	dev->dbg_base_mapped = dev->base;
-	dev->dbg_size = dev->base_size;
+	dev->dbg_base = pci_resource_start(dev->pdev, 2);
+	dev->dbg_base_mapped = dev->regs.src.bar1;
+	dev->dbg_size = AAC_MIN_SRCV_BAR1_SIZE;
 	dev->a_ops.adapter_enable_int = aac_src_enable_interrupt_message;
 
 	aac_adapter_enable_int(dev);
diff --git a/drivers/scsi/atari_scsi.c b/drivers/scsi/atari_scsi.c
index 105b35393ce9..f792420c533e 100644
--- a/drivers/scsi/atari_scsi.c
+++ b/drivers/scsi/atari_scsi.c
@@ -178,37 +178,6 @@ static int scsi_dma_is_ignored_buserr(unsigned char dma_stat)
 }
 
 
-#if 0
-/* Dead code... wasn't called anyway :-) and causes some trouble, because at
- * end-of-DMA, both SCSI ints are triggered simultaneously, so the NCR int has
- * to clear the DMA int pending bit before it allows other level 6 interrupts.
- */
-static void scsi_dma_buserr(int irq, void *dummy)
-{
-	unsigned char dma_stat = tt_scsi_dma.dma_ctrl;
-
-	/* Don't do anything if a NCR interrupt is pending. Probably it's just
-	 * masked... */
-	if (atari_irq_pending(IRQ_TT_MFP_SCSI))
-		return;
-
-	printk("Bad SCSI DMA interrupt! dma_addr=0x%08lx dma_stat=%02x dma_cnt=%08lx\n",
-	       SCSI_DMA_READ_P(dma_addr), dma_stat, SCSI_DMA_READ_P(dma_cnt));
-	if (dma_stat & 0x80) {
-		if (!scsi_dma_is_ignored_buserr(dma_stat))
-			printk("SCSI DMA bus error -- bad DMA programming!\n");
-	} else {
-		/* Under normal circumstances we never should get to this point,
-		 * since both interrupts are triggered simultaneously and the 5380
-		 * int has higher priority. When this irq is handled, that DMA
-		 * interrupt is cleared. So a warning message is printed here.
-		 */
-		printk("SCSI DMA intr ?? -- this shouldn't happen!\n");
-	}
-}
-#endif
-
-
 static irqreturn_t scsi_tt_intr(int irq, void *dev)
 {
 	struct Scsi_Host *instance = dev;
@@ -713,7 +682,8 @@ static int atari_scsi_bus_reset(struct scsi_cmnd *cmd)
 	if (IS_A_TT()) {
 		tt_scsi_dma.dma_ctrl = 0;
 	} else {
-		st_dma.dma_mode_status = 0x90;
+		if (stdma_is_locked_by(scsi_falcon_intr))
+			st_dma.dma_mode_status = 0x90;
 		atari_dma_active = 0;
 		atari_dma_orig_addr = NULL;
 	}
@@ -813,7 +783,7 @@ static int __init atari_scsi_probe(struct platform_device *pdev)
 			return -ENOMEM;
 		}
 		atari_dma_phys_buffer = atari_stram_to_phys(atari_dma_buffer);
-		atari_dma_orig_addr = 0;
+		atari_dma_orig_addr = NULL;
 	}
 
 	instance = scsi_host_alloc(&atari_scsi_template,
diff --git a/drivers/scsi/be2iscsi/be.h b/drivers/scsi/be2iscsi/be.h
index b1d0fdc5d5e1..ca9440fb2325 100644
--- a/drivers/scsi/be2iscsi/be.h
+++ b/drivers/scsi/be2iscsi/be.h
@@ -84,7 +84,6 @@ static inline void queue_tail_inc(struct be_queue_info *q)
 /*ISCSI */
 
 struct be_aic_obj {		/* Adaptive interrupt coalescing (AIC) info */
-	bool enable;
 	u32 min_eqd;		/* in usecs */
 	u32 max_eqd;		/* in usecs */
 	u32 prev_eqd;		/* in usecs */
@@ -94,8 +93,6 @@ struct be_aic_obj {		/* Adaptive interrupt coalescing (AIC) info */
 };
 
 struct be_eq_obj {
-	bool todo_mcc_cq;
-	bool todo_cq;
 	u32 cq_count;
 	struct be_queue_info q;
 	struct beiscsi_hba *phba;
diff --git a/drivers/scsi/be2iscsi/be_cmds.c b/drivers/scsi/be2iscsi/be_cmds.c
index be65da2988fb..5d59e2630ce6 100644
--- a/drivers/scsi/be2iscsi/be_cmds.c
+++ b/drivers/scsi/be2iscsi/be_cmds.c
@@ -676,10 +676,10 @@ void be_wrb_hdr_prepare(struct be_mcc_wrb *wrb, int payload_len,
 				bool embedded, u8 sge_cnt)
 {
 	if (embedded)
-		wrb->embedded |= MCC_WRB_EMBEDDED_MASK;
+		wrb->emb_sgecnt_special |= MCC_WRB_EMBEDDED_MASK;
 	else
-		wrb->embedded |= (sge_cnt & MCC_WRB_SGE_CNT_MASK) <<
-						MCC_WRB_SGE_CNT_SHIFT;
+		wrb->emb_sgecnt_special |= (sge_cnt & MCC_WRB_SGE_CNT_MASK) <<
+					   MCC_WRB_SGE_CNT_SHIFT;
 	wrb->payload_length = payload_len;
 	be_dws_cpu_to_le(wrb, 8);
 }
@@ -1599,7 +1599,7 @@ int beiscsi_cmd_function_reset(struct beiscsi_hba *phba)
 {
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct be_mcc_wrb *wrb = wrb_from_mbox(&ctrl->mbox_mem);
-	struct be_post_sgl_pages_req *req = embedded_payload(wrb);
+	struct be_post_sgl_pages_req *req;
 	int status;
 
 	mutex_lock(&ctrl->mbox_lock);
@@ -1700,31 +1700,34 @@ int beiscsi_cmd_iscsi_cleanup(struct beiscsi_hba *phba, unsigned short ulp)
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct iscsi_cleanup_req_v1 *req_v1;
 	struct iscsi_cleanup_req *req;
+	u16 hdr_ring_id, data_ring_id;
 	struct be_mcc_wrb *wrb;
 	int status;
 
 	mutex_lock(&ctrl->mbox_lock);
 	wrb = wrb_from_mbox(&ctrl->mbox_mem);
-	req = embedded_payload(wrb);
-	be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
-	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
-			   OPCODE_COMMON_ISCSI_CLEANUP, sizeof(*req));
 
-       /**
-	* TODO: Check with FW folks the chute value to be set.
-	* For now, use the ULP_MASK as the chute value.
-	*/
+	hdr_ring_id = HWI_GET_DEF_HDRQ_ID(phba, ulp);
+	data_ring_id = HWI_GET_DEF_BUFQ_ID(phba, ulp);
 	if (is_chip_be2_be3r(phba)) {
+		req = embedded_payload(wrb);
+		be_wrb_hdr_prepare(wrb, sizeof(*req), true, 0);
+		be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
+				   OPCODE_COMMON_ISCSI_CLEANUP, sizeof(*req));
 		req->chute = (1 << ulp);
-		req->hdr_ring_id = HWI_GET_DEF_HDRQ_ID(phba, ulp);
-		req->data_ring_id = HWI_GET_DEF_BUFQ_ID(phba, ulp);
+		/* BE2/BE3 FW creates 8-bit ring id */
+		req->hdr_ring_id = hdr_ring_id;
+		req->data_ring_id = data_ring_id;
 	} else {
-		req_v1 = (struct iscsi_cleanup_req_v1 *)req;
+		req_v1 = embedded_payload(wrb);
+		be_wrb_hdr_prepare(wrb, sizeof(*req_v1), true, 0);
+		be_cmd_hdr_prepare(&req_v1->hdr, CMD_SUBSYSTEM_ISCSI,
+				   OPCODE_COMMON_ISCSI_CLEANUP,
+				   sizeof(*req_v1));
 		req_v1->hdr.version = 1;
-		req_v1->hdr_ring_id = cpu_to_le16(HWI_GET_DEF_HDRQ_ID(phba,
-								      ulp));
-		req_v1->data_ring_id = cpu_to_le16(HWI_GET_DEF_BUFQ_ID(phba,
-								       ulp));
+		req_v1->chute = (1 << ulp);
+		req_v1->hdr_ring_id = cpu_to_le16(hdr_ring_id);
+		req_v1->data_ring_id = cpu_to_le16(data_ring_id);
 	}
 
 	status = be_mbox_notify(ctrl);
diff --git a/drivers/scsi/be2iscsi/be_cmds.h b/drivers/scsi/be2iscsi/be_cmds.h
index 328fb5b973cd..1d40e83b0790 100644
--- a/drivers/scsi/be2iscsi/be_cmds.h
+++ b/drivers/scsi/be2iscsi/be_cmds.h
@@ -31,10 +31,16 @@ struct be_sge {
 	__le32 len;
 };
 
-#define MCC_WRB_SGE_CNT_SHIFT 3	/* bits 3 - 7 of dword 0 */
-#define MCC_WRB_SGE_CNT_MASK 0x1F	/* bits 3 - 7 of dword 0 */
 struct be_mcc_wrb {
-	u32 embedded;		/* dword 0 */
+	u32 emb_sgecnt_special;	/* dword 0 */
+	/* bits 0 - embedded    */
+	/* bits 1 - 2 reserved	*/
+	/* bits 3 - 7 sge count	*/
+	/* bits 8 - 23 reserved	*/
+	/* bits 24 - 31 special	*/
+#define MCC_WRB_EMBEDDED_MASK 1
+#define MCC_WRB_SGE_CNT_SHIFT 3
+#define MCC_WRB_SGE_CNT_MASK 0x1F
 	u32 payload_length;	/* dword 1 */
 	u32 tag0;		/* dword 2 */
 	u32 tag1;		/* dword 3 */
@@ -1133,11 +1139,6 @@ struct tcp_connect_and_offload_out {
 
 } __packed;
 
-struct be_mcc_wrb_context {
-	struct MCC_WRB *wrb;
-	int *users_final_status;
-} __packed;
-
 #define DB_DEF_PDU_RING_ID_MASK	0x3FFF	/* bits 0 - 13 */
 #define DB_DEF_PDU_CQPROC_MASK		0x3FFF	/* bits 16 - 29 */
 #define DB_DEF_PDU_REARM_SHIFT		14
diff --git a/drivers/scsi/be2iscsi/be_iscsi.c b/drivers/scsi/be2iscsi/be_iscsi.c
index ba258217614e..a4844578e357 100644
--- a/drivers/scsi/be2iscsi/be_iscsi.c
+++ b/drivers/scsi/be2iscsi/be_iscsi.c
@@ -166,33 +166,6 @@ beiscsi_conn_create(struct iscsi_cls_session *cls_session, u32 cid)
 }
 
 /**
- * beiscsi_bindconn_cid - Bind the beiscsi_conn with phba connection table
- * @beiscsi_conn: The pointer to  beiscsi_conn structure
- * @phba: The phba instance
- * @cid: The cid to free
- */
-static int beiscsi_bindconn_cid(struct beiscsi_hba *phba,
-				struct beiscsi_conn *beiscsi_conn,
-				unsigned int cid)
-{
-	uint16_t cri_index = BE_GET_CRI_FROM_CID(cid);
-
-	if (phba->conn_table[cri_index]) {
-		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
-			    "BS_%d : Connection table already occupied. Detected clash\n");
-
-		return -EINVAL;
-	} else {
-		beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
-			    "BS_%d : phba->conn_table[%d]=%p(beiscsi_conn)\n",
-			    cri_index, beiscsi_conn);
-
-		phba->conn_table[cri_index] = beiscsi_conn;
-	}
-	return 0;
-}
-
-/**
  * beiscsi_conn_bind - Binds iscsi session/connection with TCP connection
  * @cls_session: pointer to iscsi cls session
  * @cls_conn: pointer to iscsi cls conn
@@ -212,6 +185,7 @@ int beiscsi_conn_bind(struct iscsi_cls_session *cls_session,
 	struct hwi_wrb_context *pwrb_context;
 	struct beiscsi_endpoint *beiscsi_ep;
 	struct iscsi_endpoint *ep;
+	uint16_t cri_index;
 
 	ep = iscsi_lookup_endpoint(transport_fd);
 	if (!ep)
@@ -229,20 +203,34 @@ int beiscsi_conn_bind(struct iscsi_cls_session *cls_session,
 
 		return -EEXIST;
 	}
-
-	pwrb_context = &phwi_ctrlr->wrb_context[BE_GET_CRI_FROM_CID(
-						beiscsi_ep->ep_cid)];
+	cri_index = BE_GET_CRI_FROM_CID(beiscsi_ep->ep_cid);
+	if (phba->conn_table[cri_index]) {
+		if (beiscsi_conn != phba->conn_table[cri_index] ||
+		    beiscsi_ep != phba->conn_table[cri_index]->ep) {
+			__beiscsi_log(phba, KERN_ERR,
+				      "BS_%d : conn_table not empty at %u: cid %u conn %p:%p\n",
+				      cri_index,
+				      beiscsi_ep->ep_cid,
+				      beiscsi_conn,
+				      phba->conn_table[cri_index]);
+			return -EINVAL;
+		}
+	}
 
 	beiscsi_conn->beiscsi_conn_cid = beiscsi_ep->ep_cid;
 	beiscsi_conn->ep = beiscsi_ep;
 	beiscsi_ep->conn = beiscsi_conn;
+	/**
+	 * Each connection is associated with a WRBQ kept in wrb_context.
+	 * Store doorbell offset for transmit path.
+	 */
+	pwrb_context = &phwi_ctrlr->wrb_context[cri_index];
 	beiscsi_conn->doorbell_offset = pwrb_context->doorbell_offset;
-
 	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
-		    "BS_%d : beiscsi_conn=%p conn=%p ep_cid=%d\n",
-		    beiscsi_conn, conn, beiscsi_ep->ep_cid);
-
-	return beiscsi_bindconn_cid(phba, beiscsi_conn, beiscsi_ep->ep_cid);
+		    "BS_%d : cid %d phba->conn_table[%u]=%p\n",
+		    beiscsi_ep->ep_cid, cri_index, beiscsi_conn);
+	phba->conn_table[cri_index] = beiscsi_conn;
+	return 0;
 }
 
 static int beiscsi_iface_create_ipv4(struct beiscsi_hba *phba)
@@ -973,9 +961,9 @@ int beiscsi_conn_start(struct iscsi_cls_conn *cls_conn)
  */
 static int beiscsi_get_cid(struct beiscsi_hba *phba)
 {
-	unsigned short cid = 0xFFFF, cid_from_ulp;
-	struct ulp_cid_info *cid_info = NULL;
 	uint16_t cid_avlbl_ulp0, cid_avlbl_ulp1;
+	unsigned short cid, cid_from_ulp;
+	struct ulp_cid_info *cid_info;
 
 	/* Find the ULP which has more CID available */
 	cid_avlbl_ulp0 = (phba->cid_array_info[BEISCSI_ULP0]) ?
@@ -984,20 +972,27 @@ static int beiscsi_get_cid(struct beiscsi_hba *phba)
 			  BEISCSI_ULP1_AVLBL_CID(phba) : 0;
 	cid_from_ulp = (cid_avlbl_ulp0 > cid_avlbl_ulp1) ?
 			BEISCSI_ULP0 : BEISCSI_ULP1;
-
-	if (test_bit(cid_from_ulp, (void *)&phba->fw_config.ulp_supported)) {
-		cid_info = phba->cid_array_info[cid_from_ulp];
-		if (!cid_info->avlbl_cids)
-			return cid;
-
-		cid = cid_info->cid_array[cid_info->cid_alloc++];
-
-		if (cid_info->cid_alloc == BEISCSI_GET_CID_COUNT(
-					   phba, cid_from_ulp))
-			cid_info->cid_alloc = 0;
-
-		cid_info->avlbl_cids--;
+	/**
+	 * If iSCSI protocol is loaded only on ULP 0, and when cid_avlbl_ulp
+	 * is ZERO for both, ULP 1 is returned.
+	 * Check if ULP is loaded before getting new CID.
+	 */
+	if (!test_bit(cid_from_ulp, (void *)&phba->fw_config.ulp_supported))
+		return BE_INVALID_CID;
+
+	cid_info = phba->cid_array_info[cid_from_ulp];
+	cid = cid_info->cid_array[cid_info->cid_alloc];
+	if (!cid_info->avlbl_cids || cid == BE_INVALID_CID) {
+		__beiscsi_log(phba, KERN_ERR,
+				"BS_%d : failed to get cid: available %u:%u\n",
+				cid_info->avlbl_cids, cid_info->cid_free);
+		return BE_INVALID_CID;
 	}
+	/* empty the slot */
+	cid_info->cid_array[cid_info->cid_alloc++] = BE_INVALID_CID;
+	if (cid_info->cid_alloc == BEISCSI_GET_CID_COUNT(phba, cid_from_ulp))
+		cid_info->cid_alloc = 0;
+	cid_info->avlbl_cids--;
 	return cid;
 }
 
@@ -1008,22 +1003,28 @@ static int beiscsi_get_cid(struct beiscsi_hba *phba)
  */
 static void beiscsi_put_cid(struct beiscsi_hba *phba, unsigned short cid)
 {
-	uint16_t cid_post_ulp;
-	struct hwi_controller *phwi_ctrlr;
-	struct hwi_wrb_context *pwrb_context;
-	struct ulp_cid_info *cid_info = NULL;
 	uint16_t cri_index = BE_GET_CRI_FROM_CID(cid);
+	struct hwi_wrb_context *pwrb_context;
+	struct hwi_controller *phwi_ctrlr;
+	struct ulp_cid_info *cid_info;
+	uint16_t cid_post_ulp;
 
 	phwi_ctrlr = phba->phwi_ctrlr;
 	pwrb_context = &phwi_ctrlr->wrb_context[cri_index];
 	cid_post_ulp = pwrb_context->ulp_num;
 
 	cid_info = phba->cid_array_info[cid_post_ulp];
-	cid_info->avlbl_cids++;
-
+	/* fill only in empty slot */
+	if (cid_info->cid_array[cid_info->cid_free] != BE_INVALID_CID) {
+		__beiscsi_log(phba, KERN_ERR,
+			      "BS_%d : failed to put cid %u: available %u:%u\n",
+			      cid, cid_info->avlbl_cids, cid_info->cid_free);
+		return;
+	}
 	cid_info->cid_array[cid_info->cid_free++] = cid;
 	if (cid_info->cid_free == BEISCSI_GET_CID_COUNT(phba, cid_post_ulp))
 		cid_info->cid_free = 0;
+	cid_info->avlbl_cids++;
 }
 
 /**
@@ -1037,8 +1038,8 @@ static void beiscsi_free_ep(struct beiscsi_endpoint *beiscsi_ep)
 
 	beiscsi_put_cid(phba, beiscsi_ep->ep_cid);
 	beiscsi_ep->phba = NULL;
-	phba->ep_array[BE_GET_CRI_FROM_CID
-		       (beiscsi_ep->ep_cid)] = NULL;
+	/* clear this to track freeing in beiscsi_ep_disconnect */
+	phba->ep_array[BE_GET_CRI_FROM_CID(beiscsi_ep->ep_cid)] = NULL;
 
 	/**
 	 * Check if any connection resource allocated by driver
@@ -1049,6 +1050,11 @@ static void beiscsi_free_ep(struct beiscsi_endpoint *beiscsi_ep)
 		return;
 
 	beiscsi_conn = beiscsi_ep->conn;
+	/**
+	 * Break ep->conn link here so that completions after
+	 * this are ignored.
+	 */
+	beiscsi_ep->conn = NULL;
 	if (beiscsi_conn->login_in_progress) {
 		beiscsi_free_mgmt_task_handles(beiscsi_conn,
 					       beiscsi_conn->task);
@@ -1079,7 +1085,7 @@ static int beiscsi_open_conn(struct iscsi_endpoint *ep,
 		    "BS_%d : In beiscsi_open_conn\n");
 
 	beiscsi_ep->ep_cid = beiscsi_get_cid(phba);
-	if (beiscsi_ep->ep_cid == 0xFFFF) {
+	if (beiscsi_ep->ep_cid == BE_INVALID_CID) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
 			    "BS_%d : No free cid available\n");
 		return ret;
@@ -1114,7 +1120,7 @@ static int beiscsi_open_conn(struct iscsi_endpoint *ep,
 	nonemb_cmd.size = req_memsize;
 	memset(nonemb_cmd.va, 0, nonemb_cmd.size);
 	tag = mgmt_open_connection(phba, dst_addr, beiscsi_ep, &nonemb_cmd);
-	if (tag <= 0) {
+	if (!tag) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_CONFIG,
 			    "BS_%d : mgmt_open_connection Failed for cid=%d\n",
 			    beiscsi_ep->ep_cid);
@@ -1285,26 +1291,6 @@ static int beiscsi_close_conn(struct  beiscsi_endpoint *beiscsi_ep, int flag)
 }
 
 /**
- * beiscsi_unbind_conn_to_cid - Unbind the beiscsi_conn from phba conn table
- * @phba: The phba instance
- * @cid: The cid to free
- */
-static int beiscsi_unbind_conn_to_cid(struct beiscsi_hba *phba,
-				      unsigned int cid)
-{
-	uint16_t cri_index = BE_GET_CRI_FROM_CID(cid);
-
-	if (phba->conn_table[cri_index])
-		phba->conn_table[cri_index] = NULL;
-	else {
-		beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
-			    "BS_%d : Connection table Not occupied.\n");
-		return -EINVAL;
-	}
-	return 0;
-}
-
-/**
  * beiscsi_ep_disconnect - Tears down the TCP connection
  * @ep:	endpoint to be used
  *
@@ -1318,13 +1304,23 @@ void beiscsi_ep_disconnect(struct iscsi_endpoint *ep)
 	unsigned int tag;
 	uint8_t mgmt_invalidate_flag, tcp_upload_flag;
 	unsigned short savecfg_flag = CMD_ISCSI_SESSION_SAVE_CFG_ON_FLASH;
+	uint16_t cri_index;
 
 	beiscsi_ep = ep->dd_data;
 	phba = beiscsi_ep->phba;
 	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_CONFIG,
-		    "BS_%d : In beiscsi_ep_disconnect for ep_cid = %d\n",
+		    "BS_%d : In beiscsi_ep_disconnect for ep_cid = %u\n",
 		    beiscsi_ep->ep_cid);
 
+	cri_index = BE_GET_CRI_FROM_CID(beiscsi_ep->ep_cid);
+	if (!phba->ep_array[cri_index]) {
+		__beiscsi_log(phba, KERN_ERR,
+			      "BS_%d : ep_array at %u cid %u empty\n",
+			      cri_index,
+			      beiscsi_ep->ep_cid);
+		return;
+	}
+
 	if (beiscsi_ep->conn) {
 		beiscsi_conn = beiscsi_ep->conn;
 		iscsi_suspend_queue(beiscsi_conn->conn);
@@ -1356,7 +1352,12 @@ void beiscsi_ep_disconnect(struct iscsi_endpoint *ep)
 free_ep:
 	msleep(BEISCSI_LOGOUT_SYNC_DELAY);
 	beiscsi_free_ep(beiscsi_ep);
-	beiscsi_unbind_conn_to_cid(phba, beiscsi_ep->ep_cid);
+	if (!phba->conn_table[cri_index])
+		__beiscsi_log(phba, KERN_ERR,
+				"BS_%d : conn_table empty at %u: cid %u\n",
+				cri_index,
+				beiscsi_ep->ep_cid);
+	phba->conn_table[cri_index] = NULL;
 	iscsi_destroy_endpoint(beiscsi_ep->openiscsi_ep);
 }
 
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index b5112d6d7e73..32b2713cec93 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -67,8 +67,6 @@ beiscsi_##_name##_disp(struct device *dev,\
 {	\
 	struct Scsi_Host *shost = class_to_shost(dev);\
 	struct beiscsi_hba *phba = iscsi_host_priv(shost); \
-	uint32_t param_val = 0;	\
-	param_val = phba->attr_##_name;\
 	return snprintf(buf, PAGE_SIZE, "%d\n",\
 			phba->attr_##_name);\
 }
@@ -218,160 +216,156 @@ static int beiscsi_slave_configure(struct scsi_device *sdev)
 
 static int beiscsi_eh_abort(struct scsi_cmnd *sc)
 {
+	struct iscsi_task *abrt_task = (struct iscsi_task *)sc->SCp.ptr;
 	struct iscsi_cls_session *cls_session;
-	struct iscsi_task *aborted_task = (struct iscsi_task *)sc->SCp.ptr;
-	struct beiscsi_io_task *aborted_io_task;
-	struct iscsi_conn *conn;
+	struct beiscsi_io_task *abrt_io_task;
 	struct beiscsi_conn *beiscsi_conn;
-	struct beiscsi_hba *phba;
 	struct iscsi_session *session;
-	struct invalidate_command_table *inv_tbl;
-	struct be_dma_mem nonemb_cmd;
-	unsigned int cid, tag, num_invalidate;
+	struct invldt_cmd_tbl inv_tbl;
+	struct beiscsi_hba *phba;
+	struct iscsi_conn *conn;
 	int rc;
 
 	cls_session = starget_to_session(scsi_target(sc->device));
 	session = cls_session->dd_data;
 
-	spin_lock_bh(&session->frwd_lock);
-	if (!aborted_task || !aborted_task->sc) {
-		/* we raced */
-		spin_unlock_bh(&session->frwd_lock);
-		return SUCCESS;
-	}
-
-	aborted_io_task = aborted_task->dd_data;
-	if (!aborted_io_task->scsi_cmnd) {
-		/* raced or invalid command */
-		spin_unlock_bh(&session->frwd_lock);
+	/* check if we raced, task just got cleaned up under us */
+	spin_lock_bh(&session->back_lock);
+	if (!abrt_task || !abrt_task->sc) {
+		spin_unlock_bh(&session->back_lock);
 		return SUCCESS;
 	}
-	spin_unlock_bh(&session->frwd_lock);
-	/* Invalidate WRB Posted for this Task */
-	AMAP_SET_BITS(struct amap_iscsi_wrb, invld,
-		      aborted_io_task->pwrb_handle->pwrb,
-		      1);
-
-	conn = aborted_task->conn;
+	/* get a task ref till FW processes the req for the ICD used */
+	__iscsi_get_task(abrt_task);
+	abrt_io_task = abrt_task->dd_data;
+	conn = abrt_task->conn;
 	beiscsi_conn = conn->dd_data;
 	phba = beiscsi_conn->phba;
-
-	/* invalidate iocb */
-	cid = beiscsi_conn->beiscsi_conn_cid;
-	inv_tbl = phba->inv_tbl;
-	memset(inv_tbl, 0x0, sizeof(*inv_tbl));
-	inv_tbl->cid = cid;
-	inv_tbl->icd = aborted_io_task->psgl_handle->sgl_index;
-	num_invalidate = 1;
-	nonemb_cmd.va = pci_alloc_consistent(phba->ctrl.pdev,
-				sizeof(struct invalidate_commands_params_in),
-				&nonemb_cmd.dma);
-	if (nonemb_cmd.va == NULL) {
-		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_EH,
-			    "BM_%d : Failed to allocate memory for"
-			    "mgmt_invalidate_icds\n");
-		return FAILED;
+	/* mark WRB invalid which have been not processed by FW yet */
+	if (is_chip_be2_be3r(phba)) {
+		AMAP_SET_BITS(struct amap_iscsi_wrb, invld,
+			      abrt_io_task->pwrb_handle->pwrb, 1);
+	} else {
+		AMAP_SET_BITS(struct amap_iscsi_wrb_v2, invld,
+			      abrt_io_task->pwrb_handle->pwrb, 1);
 	}
-	nonemb_cmd.size = sizeof(struct invalidate_commands_params_in);
+	inv_tbl.cid = beiscsi_conn->beiscsi_conn_cid;
+	inv_tbl.icd = abrt_io_task->psgl_handle->sgl_index;
+	spin_unlock_bh(&session->back_lock);
 
-	tag = mgmt_invalidate_icds(phba, inv_tbl, num_invalidate,
-				   cid, &nonemb_cmd);
-	if (!tag) {
+	rc = beiscsi_mgmt_invalidate_icds(phba, &inv_tbl, 1);
+	iscsi_put_task(abrt_task);
+	if (rc) {
 		beiscsi_log(phba, KERN_WARNING, BEISCSI_LOG_EH,
-			    "BM_%d : mgmt_invalidate_icds could not be"
-			    "submitted\n");
-		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
-				    nonemb_cmd.va, nonemb_cmd.dma);
-
+			    "BM_%d : sc %p invalidation failed %d\n",
+			    sc, rc);
 		return FAILED;
 	}
 
-	rc = beiscsi_mccq_compl_wait(phba, tag, NULL, &nonemb_cmd);
-	if (rc != -EBUSY)
-		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
-				    nonemb_cmd.va, nonemb_cmd.dma);
-
 	return iscsi_eh_abort(sc);
 }
 
 static int beiscsi_eh_device_reset(struct scsi_cmnd *sc)
 {
-	struct iscsi_task *abrt_task;
-	struct beiscsi_io_task *abrt_io_task;
-	struct iscsi_conn *conn;
+	struct beiscsi_invldt_cmd_tbl {
+		struct invldt_cmd_tbl tbl[BE_INVLDT_CMD_TBL_SZ];
+		struct iscsi_task *task[BE_INVLDT_CMD_TBL_SZ];
+	} *inv_tbl;
+	struct iscsi_cls_session *cls_session;
 	struct beiscsi_conn *beiscsi_conn;
-	struct beiscsi_hba *phba;
+	struct beiscsi_io_task *io_task;
 	struct iscsi_session *session;
-	struct iscsi_cls_session *cls_session;
-	struct invalidate_command_table *inv_tbl;
-	struct be_dma_mem nonemb_cmd;
-	unsigned int cid, tag, i, num_invalidate;
-	int rc;
+	struct beiscsi_hba *phba;
+	struct iscsi_conn *conn;
+	struct iscsi_task *task;
+	unsigned int i, nents;
+	int rc, more = 0;
 
-	/* invalidate iocbs */
 	cls_session = starget_to_session(scsi_target(sc->device));
 	session = cls_session->dd_data;
+
 	spin_lock_bh(&session->frwd_lock);
 	if (!session->leadconn || session->state != ISCSI_STATE_LOGGED_IN) {
 		spin_unlock_bh(&session->frwd_lock);
 		return FAILED;
 	}
+
 	conn = session->leadconn;
 	beiscsi_conn = conn->dd_data;
 	phba = beiscsi_conn->phba;
-	cid = beiscsi_conn->beiscsi_conn_cid;
-	inv_tbl = phba->inv_tbl;
-	memset(inv_tbl, 0x0, sizeof(*inv_tbl) * BE2_CMDS_PER_CXN);
-	num_invalidate = 0;
+
+	inv_tbl = kzalloc(sizeof(*inv_tbl), GFP_ATOMIC);
+	if (!inv_tbl) {
+		spin_unlock_bh(&session->frwd_lock);
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_EH,
+			    "BM_%d : invldt_cmd_tbl alloc failed\n");
+		return FAILED;
+	}
+	nents = 0;
+	/* take back_lock to prevent task from getting cleaned up under us */
+	spin_lock(&session->back_lock);
 	for (i = 0; i < conn->session->cmds_max; i++) {
-		abrt_task = conn->session->cmds[i];
-		abrt_io_task = abrt_task->dd_data;
-		if (!abrt_task->sc || abrt_task->state == ISCSI_TASK_FREE)
+		task = conn->session->cmds[i];
+		if (!task->sc)
 			continue;
 
-		if (sc->device->lun != abrt_task->sc->device->lun)
+		if (sc->device->lun != task->sc->device->lun)
 			continue;
+		/**
+		 * Can't fit in more cmds? Normally this won't happen b'coz
+		 * BEISCSI_CMD_PER_LUN is same as BE_INVLDT_CMD_TBL_SZ.
+		 */
+		if (nents == BE_INVLDT_CMD_TBL_SZ) {
+			more = 1;
+			break;
+		}
 
-		/* Invalidate WRB Posted for this Task */
-		AMAP_SET_BITS(struct amap_iscsi_wrb, invld,
-			      abrt_io_task->pwrb_handle->pwrb,
-			      1);
+		/* get a task ref till FW processes the req for the ICD used */
+		__iscsi_get_task(task);
+		io_task = task->dd_data;
+		/* mark WRB invalid which have been not processed by FW yet */
+		if (is_chip_be2_be3r(phba)) {
+			AMAP_SET_BITS(struct amap_iscsi_wrb, invld,
+				      io_task->pwrb_handle->pwrb, 1);
+		} else {
+			AMAP_SET_BITS(struct amap_iscsi_wrb_v2, invld,
+				      io_task->pwrb_handle->pwrb, 1);
+		}
 
-		inv_tbl->cid = cid;
-		inv_tbl->icd = abrt_io_task->psgl_handle->sgl_index;
-		num_invalidate++;
-		inv_tbl++;
+		inv_tbl->tbl[nents].cid = beiscsi_conn->beiscsi_conn_cid;
+		inv_tbl->tbl[nents].icd = io_task->psgl_handle->sgl_index;
+		inv_tbl->task[nents] = task;
+		nents++;
 	}
+	spin_unlock_bh(&session->back_lock);
 	spin_unlock_bh(&session->frwd_lock);
-	inv_tbl = phba->inv_tbl;
 
-	nonemb_cmd.va = pci_alloc_consistent(phba->ctrl.pdev,
-				sizeof(struct invalidate_commands_params_in),
-				&nonemb_cmd.dma);
-	if (nonemb_cmd.va == NULL) {
+	rc = SUCCESS;
+	if (!nents)
+		goto end_reset;
+
+	if (more) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_EH,
-			    "BM_%d : Failed to allocate memory for"
-			    "mgmt_invalidate_icds\n");
-		return FAILED;
+			    "BM_%d : number of cmds exceeds size of invalidation table\n");
+		rc = FAILED;
+		goto end_reset;
 	}
-	nonemb_cmd.size = sizeof(struct invalidate_commands_params_in);
-	memset(nonemb_cmd.va, 0, nonemb_cmd.size);
-	tag = mgmt_invalidate_icds(phba, inv_tbl, num_invalidate,
-				   cid, &nonemb_cmd);
-	if (!tag) {
+
+	if (beiscsi_mgmt_invalidate_icds(phba, &inv_tbl->tbl[0], nents)) {
 		beiscsi_log(phba, KERN_WARNING, BEISCSI_LOG_EH,
-			    "BM_%d : mgmt_invalidate_icds could not be"
-			    " submitted\n");
-		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
-				    nonemb_cmd.va, nonemb_cmd.dma);
-		return FAILED;
+			    "BM_%d : cid %u scmds invalidation failed\n",
+			    beiscsi_conn->beiscsi_conn_cid);
+		rc = FAILED;
 	}
 
-	rc = beiscsi_mccq_compl_wait(phba, tag, NULL, &nonemb_cmd);
-	if (rc != -EBUSY)
-		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
-				    nonemb_cmd.va, nonemb_cmd.dma);
-	return iscsi_eh_device_reset(sc);
+end_reset:
+	for (i = 0; i < nents; i++)
+		iscsi_put_task(inv_tbl->task[i]);
+	kfree(inv_tbl);
+
+	if (rc == SUCCESS)
+		rc = iscsi_eh_device_reset(sc);
+	return rc;
 }
 
 /*------------------- PCI Driver operations and data ----------------- */
@@ -395,6 +389,7 @@ static struct scsi_host_template beiscsi_sht = {
 	.change_queue_depth = scsi_change_queue_depth,
 	.slave_configure = beiscsi_slave_configure,
 	.target_alloc = iscsi_target_alloc,
+	.eh_timed_out = iscsi_eh_cmd_timed_out,
 	.eh_abort_handler = beiscsi_eh_abort,
 	.eh_device_reset_handler = beiscsi_eh_device_reset,
 	.eh_target_reset_handler = iscsi_eh_session_reset,
@@ -646,7 +641,6 @@ static void beiscsi_get_params(struct beiscsi_hba *phba)
 	phba->params.num_sge_per_io = BE2_SGE;
 	phba->params.defpdu_hdr_sz = BE2_DEFPDU_HDR_SZ;
 	phba->params.defpdu_data_sz = BE2_DEFPDU_DATA_SZ;
-	phba->params.eq_timer = 64;
 	phba->params.num_eq_entries = 1024;
 	phba->params.num_cq_entries = 1024;
 	phba->params.wrbs_per_cxn = 256;
@@ -964,6 +958,10 @@ beiscsi_get_wrb_handle(struct hwi_wrb_context *pwrb_context,
 	unsigned long flags;
 
 	spin_lock_irqsave(&pwrb_context->wrb_lock, flags);
+	if (!pwrb_context->wrb_handles_available) {
+		spin_unlock_irqrestore(&pwrb_context->wrb_lock, flags);
+		return NULL;
+	}
 	pwrb_handle = pwrb_context->pwrb_handle_base[pwrb_context->alloc_index];
 	pwrb_context->wrb_handles_available--;
 	if (pwrb_context->alloc_index == (wrbs_per_cxn - 1))
@@ -1014,6 +1012,7 @@ beiscsi_put_wrb_handle(struct hwi_wrb_context *pwrb_context,
 		pwrb_context->free_index = 0;
 	else
 		pwrb_context->free_index++;
+	pwrb_handle->pio_handle = NULL;
 	spin_unlock_irqrestore(&pwrb_context->wrb_lock, flags);
 }
 
@@ -1224,6 +1223,7 @@ hwi_complete_drvr_msgs(struct beiscsi_conn *beiscsi_conn,
 	uint16_t wrb_index, cid, cri_index;
 	struct hwi_controller *phwi_ctrlr;
 	struct wrb_handle *pwrb_handle;
+	struct iscsi_session *session;
 	struct iscsi_task *task;
 
 	phwi_ctrlr = phba->phwi_ctrlr;
@@ -1242,8 +1242,12 @@ hwi_complete_drvr_msgs(struct beiscsi_conn *beiscsi_conn,
 	cri_index = BE_GET_CRI_FROM_CID(cid);
 	pwrb_context = &phwi_ctrlr->wrb_context[cri_index];
 	pwrb_handle = pwrb_context->pwrb_handle_basestd[wrb_index];
+	session = beiscsi_conn->conn->session;
+	spin_lock_bh(&session->back_lock);
 	task = pwrb_handle->pio_handle;
-	iscsi_put_task(task);
+	if (task)
+		__iscsi_put_task(task);
+	spin_unlock_bh(&session->back_lock);
 }
 
 static void
@@ -1323,16 +1327,15 @@ static void adapter_get_sol_cqe(struct beiscsi_hba *phba,
 static void hwi_complete_cmd(struct beiscsi_conn *beiscsi_conn,
 			     struct beiscsi_hba *phba, struct sol_cqe *psol)
 {
-	struct hwi_wrb_context *pwrb_context;
-	struct wrb_handle *pwrb_handle;
-	struct iscsi_wrb *pwrb = NULL;
-	struct hwi_controller *phwi_ctrlr;
-	struct iscsi_task *task;
-	unsigned int type;
 	struct iscsi_conn *conn = beiscsi_conn->conn;
 	struct iscsi_session *session = conn->session;
 	struct common_sol_cqe csol_cqe = {0};
+	struct hwi_wrb_context *pwrb_context;
+	struct hwi_controller *phwi_ctrlr;
+	struct wrb_handle *pwrb_handle;
+	struct iscsi_task *task;
 	uint16_t cri_index = 0;
+	uint8_t type;
 
 	phwi_ctrlr = phba->phwi_ctrlr;
 
@@ -1345,11 +1348,14 @@ static void hwi_complete_cmd(struct beiscsi_conn *beiscsi_conn,
 	pwrb_handle = pwrb_context->pwrb_handle_basestd[
 		      csol_cqe.wrb_index];
 
+	spin_lock_bh(&session->back_lock);
 	task = pwrb_handle->pio_handle;
-	pwrb = pwrb_handle->pwrb;
+	if (!task) {
+		spin_unlock_bh(&session->back_lock);
+		return;
+	}
 	type = ((struct beiscsi_io_task *)task->dd_data)->wrb_type;
 
-	spin_lock_bh(&session->back_lock);
 	switch (type) {
 	case HWH_TYPE_IO:
 	case HWH_TYPE_IO_RD:
@@ -1711,13 +1717,12 @@ beiscsi_hdq_post_handles(struct beiscsi_hba *phba,
 	struct list_head *hfree_list;
 	struct phys_addr *pasync_sge;
 	u32 ring_id, doorbell = 0;
-	u16 index, num_entries;
 	u32 doorbell_offset;
 	u16 prod = 0, cons;
+	u16 index;
 
 	phwi_ctrlr = phba->phwi_ctrlr;
 	pasync_ctx = HWI_GET_ASYNC_PDU_CTX(phwi_ctrlr, ulp_num);
-	num_entries = pasync_ctx->num_entries;
 	if (header) {
 		cons = pasync_ctx->async_header.free_entries;
 		hfree_list = &pasync_ctx->async_header.free_list;
@@ -2374,13 +2379,10 @@ static int hwi_write_buffer(struct iscsi_wrb *pwrb, struct iscsi_task *task)
 static void beiscsi_find_mem_req(struct beiscsi_hba *phba)
 {
 	uint8_t mem_descr_index, ulp_num;
-	unsigned int num_cq_pages, num_async_pdu_buf_pages;
+	unsigned int num_async_pdu_buf_pages;
 	unsigned int num_async_pdu_data_pages, wrb_sz_per_cxn;
 	unsigned int num_async_pdu_buf_sgl_pages, num_async_pdu_data_sgl_pages;
 
-	num_cq_pages = PAGES_REQUIRED(phba->params.num_cq_entries * \
-				      sizeof(struct sol_cqe));
-
 	phba->params.hwi_ws_sz = sizeof(struct hwi_controller);
 
 	phba->mem_req[ISCSI_MEM_GLOBAL_HEADER] = 2 *
@@ -2737,7 +2739,7 @@ static int hwi_init_async_pdu_ctx(struct beiscsi_hba *phba)
 
 	for (ulp_num = 0; ulp_num < BEISCSI_ULP_COUNT; ulp_num++) {
 		if (test_bit(ulp_num, &phba->fw_config.ulp_supported)) {
-			 /* get async_ctx for each ULP */
+			/* get async_ctx for each ULP */
 			mem_descr = (struct be_mem_descriptor *)phba->init_mem;
 			mem_descr += (HWI_MEM_ASYNC_PDU_CONTEXT_ULP0 +
 				     (ulp_num * MEM_DESCR_OFFSET));
@@ -3367,7 +3369,7 @@ beiscsi_create_wrb_rings(struct beiscsi_hba *phba,
 			 struct hwi_context_memory *phwi_context,
 			 struct hwi_controller *phwi_ctrlr)
 {
-	unsigned int wrb_mem_index, offset, size, num_wrb_rings;
+	unsigned int num_wrb_rings;
 	u64 pa_addr_lo;
 	unsigned int idx, num, i, ulp_num;
 	struct mem_array *pwrb_arr;
@@ -3432,10 +3434,6 @@ beiscsi_create_wrb_rings(struct beiscsi_hba *phba,
 		}
 
 	for (i = 0; i < phba->params.cxns_per_ctrl; i++) {
-		wrb_mem_index = 0;
-		offset = 0;
-		size = 0;
-
 		if (ulp_count > 1) {
 			ulp_base_num = (ulp_base_num + 1) % BEISCSI_ULP_COUNT;
 
@@ -3663,7 +3661,6 @@ static void hwi_cleanup_port(struct beiscsi_hba *phba)
 	struct be_ctrl_info *ctrl = &phba->ctrl;
 	struct hwi_controller *phwi_ctrlr;
 	struct hwi_context_memory *phwi_context;
-	struct hd_async_context *pasync_ctx;
 	int i, eq_for_mcc, ulp_num;
 
 	for (ulp_num = 0; ulp_num < BEISCSI_ULP_COUNT; ulp_num++)
@@ -3700,8 +3697,6 @@ static void hwi_cleanup_port(struct beiscsi_hba *phba)
 			q = &phwi_context->be_def_dataq[ulp_num];
 			if (q->created)
 				beiscsi_cmd_q_destroy(ctrl, q, QTYPE_DPDUQ);
-
-			pasync_ctx = phwi_ctrlr->phwi_ctxt->pasync_ctx[ulp_num];
 		}
 	}
 
@@ -3804,7 +3799,6 @@ static int hwi_init_port(struct beiscsi_hba *phba)
 			/**
 			 * Now that the default PDU rings have been created,
 			 * let EP know about it.
-			 * Call beiscsi_cmd_iscsi_cleanup before posting?
 			 */
 			beiscsi_hdq_post_handles(phba, BEISCSI_DEFQ_HDR,
 						 ulp_num);
@@ -3850,14 +3844,6 @@ static int hwi_init_port(struct beiscsi_hba *phba)
 					phwi_ctrlr->wrb_context[cri].cid] =
 					async_arr_idx++;
 			}
-			/**
-			 * Now that the default PDU rings have been created,
-			 * let EP know about it.
-			 */
-			beiscsi_hdq_post_handles(phba, BEISCSI_DEFQ_HDR,
-						 ulp_num);
-			beiscsi_hdq_post_handles(phba, BEISCSI_DEFQ_DATA,
-						 ulp_num);
 		}
 	}
 
@@ -3934,31 +3920,6 @@ static void beiscsi_free_mem(struct beiscsi_hba *phba)
 	kfree(phba->phwi_ctrlr);
 }
 
-static int beiscsi_init_controller(struct beiscsi_hba *phba)
-{
-	int ret = -ENOMEM;
-
-	ret = beiscsi_get_memory(phba);
-	if (ret < 0) {
-		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BM_%d : beiscsi_dev_probe -"
-			    "Failed in beiscsi_alloc_memory\n");
-		return ret;
-	}
-
-	ret = hwi_init_controller(phba);
-	if (ret)
-		goto free_init;
-	beiscsi_log(phba, KERN_INFO, BEISCSI_LOG_INIT,
-		    "BM_%d : Return success from beiscsi_init_controller");
-
-	return 0;
-
-free_init:
-	beiscsi_free_mem(phba);
-	return ret;
-}
-
 static int beiscsi_init_sgl_handle(struct beiscsi_hba *phba)
 {
 	struct be_mem_descriptor *mem_descr_sglh, *mem_descr_sg;
@@ -4089,9 +4050,10 @@ static int hba_setup_cid_tbls(struct beiscsi_hba *phba)
 			}
 
 			/* Allocate memory for CID array */
-			ptr_cid_info->cid_array = kzalloc(sizeof(void *) *
-						  BEISCSI_GET_CID_COUNT(phba,
-						  ulp_num), GFP_KERNEL);
+			ptr_cid_info->cid_array =
+				kcalloc(BEISCSI_GET_CID_COUNT(phba, ulp_num),
+					sizeof(*ptr_cid_info->cid_array),
+					GFP_KERNEL);
 			if (!ptr_cid_info->cid_array) {
 				beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
 					    "BM_%d : Failed to allocate memory"
@@ -4231,33 +4193,30 @@ static int beiscsi_init_port(struct beiscsi_hba *phba)
 {
 	int ret;
 
-	ret = beiscsi_init_controller(phba);
+	ret = hwi_init_controller(phba);
 	if (ret < 0) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BM_%d : beiscsi_dev_probe - Failed in"
-			    "beiscsi_init_controller\n");
+			    "BM_%d : init controller failed\n");
 		return ret;
 	}
 	ret = beiscsi_init_sgl_handle(phba);
 	if (ret < 0) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BM_%d : beiscsi_dev_probe - Failed in"
-			    "beiscsi_init_sgl_handle\n");
-		goto do_cleanup_ctrlr;
+			    "BM_%d : init sgl handles failed\n");
+		goto cleanup_port;
 	}
 
 	ret = hba_setup_cid_tbls(phba);
 	if (ret < 0) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BM_%d : Failed in hba_setup_cid_tbls\n");
+			    "BM_%d : setup CID table failed\n");
 		kfree(phba->io_sgl_hndl_base);
 		kfree(phba->eh_sgl_hndl_base);
-		goto do_cleanup_ctrlr;
+		goto cleanup_port;
 	}
-
 	return ret;
 
-do_cleanup_ctrlr:
+cleanup_port:
 	hwi_cleanup_port(phba);
 	return ret;
 }
@@ -5417,10 +5376,10 @@ static int beiscsi_enable_port(struct beiscsi_hba *phba)
 
 	phba->shost->max_id = phba->params.cxns_per_ctrl;
 	phba->shost->can_queue = phba->params.ios_per_ctrl;
-	ret = hwi_init_controller(phba);
-	if (ret) {
+	ret = beiscsi_init_port(phba);
+	if (ret < 0) {
 		__beiscsi_log(phba, KERN_ERR,
-			      "BM_%d : init controller failed %d\n", ret);
+			      "BM_%d : init port failed\n");
 		goto disable_msix;
 	}
 
@@ -5526,6 +5485,7 @@ static void beiscsi_disable_port(struct beiscsi_hba *phba, int unload)
 		cancel_work_sync(&pbe_eq->mcc_work);
 	}
 	hwi_cleanup_port(phba);
+	beiscsi_cleanup_port(phba);
 }
 
 static void beiscsi_sess_work(struct work_struct *work)
@@ -5638,11 +5598,12 @@ static void beiscsi_eeh_resume(struct pci_dev *pdev)
 static int beiscsi_dev_probe(struct pci_dev *pcidev,
 			     const struct pci_device_id *id)
 {
-	struct beiscsi_hba *phba = NULL;
-	struct hwi_controller *phwi_ctrlr;
 	struct hwi_context_memory *phwi_context;
+	struct hwi_controller *phwi_ctrlr;
+	struct beiscsi_hba *phba = NULL;
 	struct be_eq_obj *pbe_eq;
 	unsigned int s_handle;
+	char wq_name[20];
 	int ret, i;
 
 	ret = beiscsi_enable_pci(pcidev);
@@ -5680,6 +5641,8 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 	case OC_DEVICE_ID2:
 		phba->generation = BE_GEN2;
 		phba->iotask_fn = beiscsi_iotask;
+		dev_warn(&pcidev->dev,
+			 "Obsolete/Unsupported BE2 Adapter Family\n");
 		break;
 	case BE_DEVICE_ID2:
 	case OC_DEVICE_ID3:
@@ -5735,11 +5698,18 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 
 	phba->shost->max_id = phba->params.cxns_per_ctrl;
 	phba->shost->can_queue = phba->params.ios_per_ctrl;
+	ret = beiscsi_get_memory(phba);
+	if (ret < 0) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
+			    "BM_%d : alloc host mem failed\n");
+		goto free_port;
+	}
+
 	ret = beiscsi_init_port(phba);
 	if (ret < 0) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
-			    "BM_%d : beiscsi_dev_probe-"
-			    "Failed in beiscsi_init_port\n");
+			    "BM_%d : init port failed\n");
+		beiscsi_free_mem(phba);
 		goto free_port;
 	}
 
@@ -5754,9 +5724,9 @@ static int beiscsi_dev_probe(struct pci_dev *pcidev,
 
 	phba->ctrl.mcc_alloc_index = phba->ctrl.mcc_free_index = 0;
 
-	snprintf(phba->wq_name, sizeof(phba->wq_name), "beiscsi_%02x_wq",
+	snprintf(wq_name, sizeof(wq_name), "beiscsi_%02x_wq",
 		 phba->shost->host_no);
-	phba->wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, phba->wq_name);
+	phba->wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, wq_name);
 	if (!phba->wq) {
 		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_INIT,
 			    "BM_%d : beiscsi_dev_probe-"
@@ -5881,7 +5851,6 @@ static void beiscsi_remove(struct pci_dev *pcidev)
 
 	/* free all resources */
 	destroy_workqueue(phba->wq);
-	beiscsi_cleanup_port(phba);
 	beiscsi_free_mem(phba);
 
 	/* ctrl uninit */
diff --git a/drivers/scsi/be2iscsi/be_main.h b/drivers/scsi/be2iscsi/be_main.h
index 6376657e45f7..218857926566 100644
--- a/drivers/scsi/be2iscsi/be_main.h
+++ b/drivers/scsi/be2iscsi/be_main.h
@@ -36,7 +36,7 @@
 #include <scsi/scsi_transport_iscsi.h>
 
 #define DRV_NAME		"be2iscsi"
-#define BUILD_STR		"11.2.0.0"
+#define BUILD_STR		"11.2.1.0"
 #define BE_NAME			"Emulex OneConnect" \
 				"Open-iSCSI Driver version" BUILD_STR
 #define DRV_DESC		BE_NAME " " "Driver"
@@ -57,7 +57,6 @@
 
 #define BE2_IO_DEPTH		1024
 #define BE2_MAX_SESSIONS	256
-#define BE2_CMDS_PER_CXN	128
 #define BE2_TMFS		16
 #define BE2_NOPOUT_REQ		16
 #define BE2_SGE			32
@@ -72,8 +71,13 @@
 
 #define BEISCSI_SGLIST_ELEMENTS	30
 
-#define BEISCSI_CMD_PER_LUN	128 /* scsi_host->cmd_per_lun */
-#define BEISCSI_MAX_SECTORS	1024 /* scsi_host->max_sectors */
+/**
+ * BE_INVLDT_CMD_TBL_SZ is 128 which is total number commands that can
+ * be invalidated at a time, consider it before changing the value of
+ * BEISCSI_CMD_PER_LUN.
+ */
+#define BEISCSI_CMD_PER_LUN	128	/* scsi_host->cmd_per_lun */
+#define BEISCSI_MAX_SECTORS	1024	/* scsi_host->max_sectors */
 #define BEISCSI_TEMPLATE_HDR_PER_CXN_SIZE 128 /* Template size per cxn */
 
 #define BEISCSI_MAX_CMD_LEN	16	/* scsi_host->max_cmd_len */
@@ -239,19 +243,7 @@ struct hba_parameters {
 	unsigned int num_cq_entries;
 	unsigned int num_eq_entries;
 	unsigned int wrbs_per_cxn;
-	unsigned int crashmode;
-	unsigned int hba_num;
-
-	unsigned int mgmt_ws_sz;
 	unsigned int hwi_ws_sz;
-
-	unsigned int eto;
-	unsigned int ldto;
-
-	unsigned int dbg_flags;
-	unsigned int num_cxn;
-
-	unsigned int eq_timer;
 	/**
 	 * These are calculated from other params. They're here
 	 * for debug purposes
@@ -272,11 +264,6 @@ struct hba_parameters {
 	unsigned int num_sge;
 };
 
-struct invalidate_command_table {
-	unsigned short icd;
-	unsigned short cid;
-} __packed;
-
 #define BEISCSI_GET_ULP_FROM_CRI(phwi_ctrlr, cri) \
 	(phwi_ctrlr->wrb_context[cri].ulp_num)
 struct hwi_wrb_context {
@@ -334,7 +321,6 @@ struct beiscsi_hba {
 	struct be_bus_address pci_pa;	/* CSR */
 	/* PCI representation of our HBA */
 	struct pci_dev *pcidev;
-	unsigned short asic_revision;
 	unsigned int num_cpus;
 	unsigned int nxt_cqid;
 	struct msix_entry msix_entries[MAX_CPUS];
@@ -355,9 +341,9 @@ struct beiscsi_hba {
 	spinlock_t io_sgl_lock;
 	spinlock_t mgmt_sgl_lock;
 	spinlock_t async_pdu_lock;
-	unsigned int age;
 	struct list_head hba_queue;
 #define BE_MAX_SESSION 2048
+#define BE_INVALID_CID 0xffff
 #define BE_SET_CID_TO_CRI(cri_index, cid) \
 			  (phba->cid_to_cri_map[cid] = cri_index)
 #define BE_GET_CRI_FROM_CID(cid) (phba->cid_to_cri_map[cid])
@@ -425,12 +411,10 @@ struct beiscsi_hba {
 	u8 port_name;
 	u8 port_speed;
 	char fw_ver_str[BEISCSI_VER_STRLEN];
-	char wq_name[20];
 	struct workqueue_struct *wq;	/* The actuak work queue */
 	struct be_ctrl_info ctrl;
 	unsigned int generation;
 	unsigned int interface_handle;
-	struct invalidate_command_table inv_tbl[128];
 
 	struct be_aic_obj aic_obj[MAX_CPUS];
 	unsigned int attr_log_enable;
@@ -525,10 +509,6 @@ struct beiscsi_io_task {
 	struct scsi_cmnd *scsi_cmnd;
 	int num_sg;
 	struct hwi_wrb_context *pwrb_context;
-	unsigned int cmd_sn;
-	unsigned int flags;
-	unsigned short cid;
-	unsigned short header_len;
 	itt_t libiscsi_itt;
 	struct be_cmd_bhs *cmd_bhs;
 	struct be_bus_address bhs_pa;
@@ -842,7 +822,7 @@ struct amap_iscsi_wrb_v2 {
 	u8 diff_enbl;   /* DWORD 11 */
 	u8 u_run;       /* DWORD 11 */
 	u8 o_run;       /* DWORD 11 */
-	u8 invalid;     /* DWORD 11 */
+	u8 invld;     /* DWORD 11 */
 	u8 dsp;         /* DWORD 11 */
 	u8 dmsg;        /* DWORD 11 */
 	u8 rsvd4;       /* DWORD 11 */
@@ -1042,10 +1022,8 @@ struct hwi_controller {
 	struct list_head io_sgl_list;
 	struct list_head eh_sgl_list;
 	struct sgl_handle *psgl_handle_base;
-	unsigned int wrb_mem_index;
 
 	struct hwi_wrb_context *wrb_context;
-	struct mcc_wrb *pmcc_wrb_base;
 	struct be_ring default_pdu_hdr[BEISCSI_ULP_COUNT];
 	struct be_ring default_pdu_data[BEISCSI_ULP_COUNT];
 	struct hwi_context_memory *phwi_ctxt;
@@ -1062,9 +1040,7 @@ enum hwh_type_enum {
 };
 
 struct wrb_handle {
-	enum hwh_type_enum type;
 	unsigned short wrb_index;
-
 	struct iscsi_task *pio_handle;
 	struct iscsi_wrb *pwrb;
 };
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index ac05317bba7f..2f6d5c2ac329 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -66,7 +66,6 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 					 struct bsg_job *job,
 					 struct be_dma_mem *nonemb_cmd)
 {
-	struct be_cmd_resp_hdr *resp;
 	struct be_mcc_wrb *wrb;
 	struct be_sge *mcc_sge;
 	unsigned int tag = 0;
@@ -76,7 +75,6 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 
 	nonemb_cmd->size = job->request_payload.payload_len;
 	memset(nonemb_cmd->va, 0, nonemb_cmd->size);
-	resp = nonemb_cmd->va;
 	region =  bsg_req->rqst_data.h_vendor.vendor_cmd[1];
 	sector_size =  bsg_req->rqst_data.h_vendor.vendor_cmd[2];
 	sector =  bsg_req->rqst_data.h_vendor.vendor_cmd[3];
@@ -128,50 +126,6 @@ unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 	return tag;
 }
 
-unsigned int  mgmt_invalidate_icds(struct beiscsi_hba *phba,
-				struct invalidate_command_table *inv_tbl,
-				unsigned int num_invalidate, unsigned int cid,
-				struct be_dma_mem *nonemb_cmd)
-
-{
-	struct be_ctrl_info *ctrl = &phba->ctrl;
-	struct be_mcc_wrb *wrb;
-	struct be_sge *sge;
-	struct invalidate_commands_params_in *req;
-	unsigned int i, tag;
-
-	mutex_lock(&ctrl->mbox_lock);
-	wrb = alloc_mcc_wrb(phba, &tag);
-	if (!wrb) {
-		mutex_unlock(&ctrl->mbox_lock);
-		return 0;
-	}
-
-	req = nonemb_cmd->va;
-	memset(req, 0, sizeof(*req));
-	sge = nonembedded_sgl(wrb);
-
-	be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1);
-	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
-			OPCODE_COMMON_ISCSI_ERROR_RECOVERY_INVALIDATE_COMMANDS,
-			sizeof(*req));
-	req->ref_handle = 0;
-	req->cleanup_type = CMD_ISCSI_COMMAND_INVALIDATE;
-	for (i = 0; i < num_invalidate; i++) {
-		req->table[i].icd = inv_tbl->icd;
-		req->table[i].cid = inv_tbl->cid;
-		req->icd_count++;
-		inv_tbl++;
-	}
-	sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd->dma));
-	sge->pa_lo = cpu_to_le32(nonemb_cmd->dma & 0xFFFFFFFF);
-	sge->len = cpu_to_le32(nonemb_cmd->size);
-
-	be_mcc_notify(phba, tag);
-	mutex_unlock(&ctrl->mbox_lock);
-	return tag;
-}
-
 unsigned int mgmt_invalidate_connection(struct beiscsi_hba *phba,
 					 struct beiscsi_endpoint *beiscsi_ep,
 					 unsigned short cid,
@@ -1066,7 +1020,6 @@ unsigned int beiscsi_boot_reopen_sess(struct beiscsi_hba *phba)
 unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba)
 {
 	struct be_ctrl_info *ctrl = &phba->ctrl;
-	struct be_cmd_get_session_resp *resp;
 	struct be_cmd_get_session_req *req;
 	struct be_dma_mem *nonemb_cmd;
 	struct be_mcc_wrb *wrb;
@@ -1081,7 +1034,7 @@ unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba)
 	}
 
 	nonemb_cmd = &phba->boot_struct.nonemb_cmd;
-	nonemb_cmd->size = sizeof(*resp);
+	nonemb_cmd->size = sizeof(struct be_cmd_get_session_resp);
 	nonemb_cmd->va = pci_alloc_consistent(phba->ctrl.pdev,
 					      nonemb_cmd->size,
 					      &nonemb_cmd->dma);
@@ -1096,7 +1049,7 @@ unsigned int beiscsi_boot_get_sinfo(struct beiscsi_hba *phba)
 	be_wrb_hdr_prepare(wrb, sizeof(*req), false, 1);
 	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI_INI,
 			   OPCODE_ISCSI_INI_SESSION_GET_A_SESSION,
-			   sizeof(*resp));
+			   sizeof(struct be_cmd_get_session_resp));
 	req->session_handle = phba->boot_struct.s_handle;
 	sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd->dma));
 	sge->pa_lo = cpu_to_le32(nonemb_cmd->dma & 0xFFFFFFFF);
@@ -1309,7 +1262,8 @@ beiscsi_adap_family_disp(struct device *dev, struct device_attribute *attr,
 	case BE_DEVICE_ID1:
 	case OC_DEVICE_ID1:
 	case OC_DEVICE_ID2:
-		return snprintf(buf, PAGE_SIZE, "BE2 Adapter Family\n");
+		return snprintf(buf, PAGE_SIZE,
+				"Obsolete/Unsupported BE2 Adapter Family\n");
 		break;
 	case BE_DEVICE_ID2:
 	case OC_DEVICE_ID3:
@@ -1341,7 +1295,7 @@ beiscsi_phys_port_disp(struct device *dev, struct device_attribute *attr,
 	struct Scsi_Host *shost = class_to_shost(dev);
 	struct beiscsi_hba *phba = iscsi_host_priv(shost);
 
-	return snprintf(buf, PAGE_SIZE, "Port Identifier : %d\n",
+	return snprintf(buf, PAGE_SIZE, "Port Identifier : %u\n",
 			phba->fw_config.phys_port);
 }
 
@@ -1494,3 +1448,64 @@ void beiscsi_offload_cxn_v2(struct beiscsi_offload_params *params,
 		     (params->dw[offsetof(struct amap_beiscsi_offload_params,
 		      exp_statsn) / 32] + 1));
 }
+
+int beiscsi_mgmt_invalidate_icds(struct beiscsi_hba *phba,
+				 struct invldt_cmd_tbl *inv_tbl,
+				 unsigned int nents)
+{
+	struct be_ctrl_info *ctrl = &phba->ctrl;
+	struct invldt_cmds_params_in *req;
+	struct be_dma_mem nonemb_cmd;
+	struct be_mcc_wrb *wrb;
+	unsigned int i, tag;
+	struct be_sge *sge;
+	int rc;
+
+	if (!nents || nents > BE_INVLDT_CMD_TBL_SZ)
+		return -EINVAL;
+
+	nonemb_cmd.size = sizeof(union be_invldt_cmds_params);
+	nonemb_cmd.va = pci_zalloc_consistent(phba->ctrl.pdev,
+					      nonemb_cmd.size,
+					      &nonemb_cmd.dma);
+	if (!nonemb_cmd.va) {
+		beiscsi_log(phba, KERN_ERR, BEISCSI_LOG_EH,
+			    "BM_%d : invldt_cmds_params alloc failed\n");
+		return -ENOMEM;
+	}
+
+	mutex_lock(&ctrl->mbox_lock);
+	wrb = alloc_mcc_wrb(phba, &tag);
+	if (!wrb) {
+		mutex_unlock(&ctrl->mbox_lock);
+		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
+				    nonemb_cmd.va, nonemb_cmd.dma);
+		return -ENOMEM;
+	}
+
+	req = nonemb_cmd.va;
+	be_wrb_hdr_prepare(wrb, nonemb_cmd.size, false, 1);
+	be_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_ISCSI,
+			OPCODE_COMMON_ISCSI_ERROR_RECOVERY_INVALIDATE_COMMANDS,
+			sizeof(*req));
+	req->ref_handle = 0;
+	req->cleanup_type = CMD_ISCSI_COMMAND_INVALIDATE;
+	for (i = 0; i < nents; i++) {
+		req->table[i].icd = inv_tbl[i].icd;
+		req->table[i].cid = inv_tbl[i].cid;
+		req->icd_count++;
+	}
+	sge = nonembedded_sgl(wrb);
+	sge->pa_hi = cpu_to_le32(upper_32_bits(nonemb_cmd.dma));
+	sge->pa_lo = cpu_to_le32(lower_32_bits(nonemb_cmd.dma));
+	sge->len = cpu_to_le32(nonemb_cmd.size);
+
+	be_mcc_notify(phba, tag);
+	mutex_unlock(&ctrl->mbox_lock);
+
+	rc = beiscsi_mccq_compl_wait(phba, tag, NULL, &nonemb_cmd);
+	if (rc != -EBUSY)
+		pci_free_consistent(phba->ctrl.pdev, nonemb_cmd.size,
+				    nonemb_cmd.va, nonemb_cmd.dma);
+	return rc;
+}
diff --git a/drivers/scsi/be2iscsi/be_mgmt.h b/drivers/scsi/be2iscsi/be_mgmt.h
index b897cfd57c72..308f1472f98a 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.h
+++ b/drivers/scsi/be2iscsi/be_mgmt.h
@@ -36,66 +36,6 @@
 #define PCICFG_UE_STATUS_MASK_LOW       0xA8
 #define PCICFG_UE_STATUS_MASK_HI        0xAC
 
-/**
- * Pseudo amap definition in which each bit of the actual structure is defined
- * as a byte: used to calculate offset/shift/mask of each field
- */
-struct amap_mcc_sge {
-	u8 pa_lo[32];		/* dword 0 */
-	u8 pa_hi[32];		/* dword 1 */
-	u8 length[32];		/* DWORD 2 */
-} __packed;
-
-/**
- * Pseudo amap definition in which each bit of the actual structure is defined
- * as a byte: used to calculate offset/shift/mask of each field
- */
-struct amap_mcc_wrb_payload {
-	union {
-		struct amap_mcc_sge sgl[19];
-		u8 embedded[59 * 32];	/* DWORDS 57 to 115 */
-	} u;
-} __packed;
-
-/**
- * Pseudo amap definition in which each bit of the actual structure is defined
- * as a byte: used to calculate offset/shift/mask of each field
- */
-struct amap_mcc_wrb {
-	u8 embedded;		/* DWORD 0 */
-	u8 rsvd0[2];		/* DWORD 0 */
-	u8 sge_count[5];	/* DWORD 0 */
-	u8 rsvd1[16];		/* DWORD 0 */
-	u8 special[8];		/* DWORD 0 */
-	u8 payload_length[32];
-	u8 tag[64];		/* DWORD 2 */
-	u8 rsvd2[32];		/* DWORD 4 */
-	struct amap_mcc_wrb_payload payload;
-};
-
-struct mcc_sge {
-	u32 pa_lo;		/* dword 0 */
-	u32 pa_hi;		/* dword 1 */
-	u32 length;		/* DWORD 2 */
-} __packed;
-
-struct mcc_wrb_payload {
-	union {
-		struct mcc_sge sgl[19];
-		u32 embedded[59];	/* DWORDS 57 to 115 */
-	} u;
-} __packed;
-
-#define MCC_WRB_EMBEDDED_MASK                0x00000001
-
-struct mcc_wrb {
-	u32 dw[0];		/* DWORD 0 */
-	u32 payload_length;
-	u32 tag[2];		/* DWORD 2 */
-	u32 rsvd2[1];		/* DWORD 4 */
-	struct mcc_wrb_payload payload;
-};
-
 int mgmt_open_connection(struct beiscsi_hba *phba,
 			 struct sockaddr *dst_addr,
 			 struct beiscsi_endpoint *beiscsi_ep,
@@ -104,10 +44,6 @@ int mgmt_open_connection(struct beiscsi_hba *phba,
 unsigned int mgmt_upload_connection(struct beiscsi_hba *phba,
 				     unsigned short cid,
 				     unsigned int upload_flag);
-unsigned int mgmt_invalidate_icds(struct beiscsi_hba *phba,
-				struct invalidate_command_table *inv_tbl,
-				unsigned int num_invalidate, unsigned int cid,
-				struct be_dma_mem *nonemb_cmd);
 unsigned int mgmt_vendor_specific_fw_cmd(struct be_ctrl_info *ctrl,
 					 struct beiscsi_hba *phba,
 					 struct bsg_job *job,
@@ -134,24 +70,31 @@ union iscsi_invalidate_connection_params {
 	struct iscsi_invalidate_connection_params_out response;
 } __packed;
 
-struct invalidate_commands_params_in {
+#define BE_INVLDT_CMD_TBL_SZ	128
+struct invldt_cmd_tbl {
+	unsigned short icd;
+	unsigned short cid;
+} __packed;
+
+struct invldt_cmds_params_in {
 	struct be_cmd_req_hdr hdr;
 	unsigned int ref_handle;
 	unsigned int icd_count;
-	struct invalidate_command_table table[128];
+	struct invldt_cmd_tbl table[BE_INVLDT_CMD_TBL_SZ];
 	unsigned short cleanup_type;
 	unsigned short unused;
 } __packed;
 
-struct invalidate_commands_params_out {
+struct invldt_cmds_params_out {
+	struct be_cmd_resp_hdr hdr;
 	unsigned int ref_handle;
 	unsigned int icd_count;
-	unsigned int icd_status[128];
+	unsigned int icd_status[BE_INVLDT_CMD_TBL_SZ];
 } __packed;
 
-union invalidate_commands_params {
-	struct invalidate_commands_params_in request;
-	struct invalidate_commands_params_out response;
+union be_invldt_cmds_params {
+	struct invldt_cmds_params_in request;
+	struct invldt_cmds_params_out response;
 } __packed;
 
 struct mgmt_hba_attributes {
@@ -231,16 +174,6 @@ struct be_bsg_vendor_cmd {
 
 #define GET_MGMT_CONTROLLER_WS(phba)    (phba->pmgmt_ws)
 
-/* MGMT CMD flags */
-
-#define MGMT_CMDH_FREE                (1<<0)
-
-/*  --- MGMT_ERROR_CODES --- */
-/*  Error Codes returned in the status field of the CMD response header */
-#define MGMT_STATUS_SUCCESS 0	/* The CMD completed without errors */
-#define MGMT_STATUS_FAILED 1	/* Error status in the Status field of */
-				/* the CMD_RESPONSE_HEADER  */
-
 #define ISCSI_GET_PDU_TEMPLATE_ADDRESS(pc, pa) {\
 	pa->lo = phba->init_mem[ISCSI_MEM_GLOBAL_HEADER].mem_array[0].\
 					bus_address.u.a32.address_lo;  \
@@ -270,6 +203,9 @@ unsigned int mgmt_invalidate_connection(struct beiscsi_hba *phba,
 					 unsigned short cid,
 					 unsigned short issue_reset,
 					 unsigned short savecfg_flag);
+int beiscsi_mgmt_invalidate_icds(struct beiscsi_hba *phba,
+				 struct invldt_cmd_tbl *inv_tbl,
+				 unsigned int nents);
 
 int beiscsi_if_en_dhcp(struct beiscsi_hba *phba, u32 ip_type);
 
diff --git a/drivers/scsi/bfa/bfa_fcs.c b/drivers/scsi/bfa/bfa_fcs.c
index 1e7e139d71ea..4aa61e20e82d 100644
--- a/drivers/scsi/bfa/bfa_fcs.c
+++ b/drivers/scsi/bfa/bfa_fcs.c
@@ -28,24 +28,6 @@
 BFA_TRC_FILE(FCS, FCS);
 
 /*
- * FCS sub-modules
- */
-struct bfa_fcs_mod_s {
-	void		(*attach) (struct bfa_fcs_s *fcs);
-	void		(*modinit) (struct bfa_fcs_s *fcs);
-	void		(*modexit) (struct bfa_fcs_s *fcs);
-};
-
-#define BFA_FCS_MODULE(_mod) { _mod ## _modinit, _mod ## _modexit }
-
-static struct bfa_fcs_mod_s fcs_modules[] = {
-	{ bfa_fcs_port_attach, NULL, NULL },
-	{ bfa_fcs_uf_attach, NULL, NULL },
-	{ bfa_fcs_fabric_attach, bfa_fcs_fabric_modinit,
-	  bfa_fcs_fabric_modexit },
-};
-
-/*
  *  fcs_api BFA FCS API
  */
 
@@ -58,52 +40,19 @@ bfa_fcs_exit_comp(void *fcs_cbarg)
 	complete(&bfad->comp);
 }
 
-
-
 /*
- *  fcs_api BFA FCS API
- */
-
-/*
- * fcs attach -- called once to initialize data structures at driver attach time
+ * fcs initialization, called once after bfa initialization is complete
  */
 void
-bfa_fcs_attach(struct bfa_fcs_s *fcs, struct bfa_s *bfa, struct bfad_s *bfad,
-	       bfa_boolean_t min_cfg)
+bfa_fcs_init(struct bfa_fcs_s *fcs)
 {
-	int		i;
-	struct bfa_fcs_mod_s  *mod;
-
-	fcs->bfa = bfa;
-	fcs->bfad = bfad;
-	fcs->min_cfg = min_cfg;
-	fcs->num_rport_logins = 0;
-
-	bfa->fcs = BFA_TRUE;
-	fcbuild_init();
-
-	for (i = 0; i < ARRAY_SIZE(fcs_modules); i++) {
-		mod = &fcs_modules[i];
-		if (mod->attach)
-			mod->attach(fcs);
-	}
+	bfa_sm_send_event(&fcs->fabric, BFA_FCS_FABRIC_SM_CREATE);
+	bfa_trc(fcs, 0);
 }
 
 /*
- * fcs initialization, called once after bfa initialization is complete
+ *  fcs_api BFA FCS API
  */
-void
-bfa_fcs_init(struct bfa_fcs_s *fcs)
-{
-	int	i;
-	struct bfa_fcs_mod_s  *mod;
-
-	for (i = 0; i < ARRAY_SIZE(fcs_modules); i++) {
-		mod = &fcs_modules[i];
-		if (mod->modinit)
-			mod->modinit(fcs);
-	}
-}
 
 /*
  * FCS update cfg - reset the pwwn/nwwn of fabric base logical port
@@ -180,26 +129,14 @@ bfa_fcs_driver_info_init(struct bfa_fcs_s *fcs,
 void
 bfa_fcs_exit(struct bfa_fcs_s *fcs)
 {
-	struct bfa_fcs_mod_s  *mod;
-	int		nmods, i;
-
 	bfa_wc_init(&fcs->wc, bfa_fcs_exit_comp, fcs);
-
-	nmods = ARRAY_SIZE(fcs_modules);
-
-	for (i = 0; i < nmods; i++) {
-
-		mod = &fcs_modules[i];
-		if (mod->modexit) {
-			bfa_wc_up(&fcs->wc);
-			mod->modexit(fcs);
-		}
-	}
-
+	bfa_wc_up(&fcs->wc);
+	bfa_trc(fcs, 0);
+	bfa_lps_delete(fcs->fabric.lps);
+	bfa_sm_send_event(&fcs->fabric, BFA_FCS_FABRIC_SM_DELETE);
 	bfa_wc_wait(&fcs->wc);
 }
 
-
 /*
  * Fabric module implementation.
  */
@@ -1128,62 +1065,6 @@ bfa_fcs_fabric_stop_comp(void *cbarg)
  */
 
 /*
- * Attach time initialization.
- */
-void
-bfa_fcs_fabric_attach(struct bfa_fcs_s *fcs)
-{
-	struct bfa_fcs_fabric_s *fabric;
-
-	fabric = &fcs->fabric;
-	memset(fabric, 0, sizeof(struct bfa_fcs_fabric_s));
-
-	/*
-	 * Initialize base fabric.
-	 */
-	fabric->fcs = fcs;
-	INIT_LIST_HEAD(&fabric->vport_q);
-	INIT_LIST_HEAD(&fabric->vf_q);
-	fabric->lps = bfa_lps_alloc(fcs->bfa);
-	WARN_ON(!fabric->lps);
-
-	/*
-	 * Initialize fabric delete completion handler. Fabric deletion is
-	 * complete when the last vport delete is complete.
-	 */
-	bfa_wc_init(&fabric->wc, bfa_fcs_fabric_delete_comp, fabric);
-	bfa_wc_up(&fabric->wc); /* For the base port */
-
-	bfa_sm_set_state(fabric, bfa_fcs_fabric_sm_uninit);
-	bfa_fcs_lport_attach(&fabric->bport, fabric->fcs, FC_VF_ID_NULL, NULL);
-}
-
-void
-bfa_fcs_fabric_modinit(struct bfa_fcs_s *fcs)
-{
-	bfa_sm_send_event(&fcs->fabric, BFA_FCS_FABRIC_SM_CREATE);
-	bfa_trc(fcs, 0);
-}
-
-/*
- *   Module cleanup
- */
-void
-bfa_fcs_fabric_modexit(struct bfa_fcs_s *fcs)
-{
-	struct bfa_fcs_fabric_s *fabric;
-
-	bfa_trc(fcs, 0);
-
-	/*
-	 * Cleanup base fabric.
-	 */
-	fabric = &fcs->fabric;
-	bfa_lps_delete(fabric->lps);
-	bfa_sm_send_event(fabric, BFA_FCS_FABRIC_SM_DELETE);
-}
-
-/*
  * Fabric module stop -- stop FCS actions
  */
 void
@@ -1633,12 +1514,6 @@ bfa_fcs_port_event_handler(void *cbarg, enum bfa_port_linkstate event)
 	}
 }
 
-void
-bfa_fcs_port_attach(struct bfa_fcs_s *fcs)
-{
-	bfa_fcport_event_register(fcs->bfa, bfa_fcs_port_event_handler, fcs);
-}
-
 /*
  * BFA FCS UF ( Unsolicited Frames)
  */
@@ -1706,8 +1581,44 @@ bfa_fcs_uf_recv(void *cbarg, struct bfa_uf_s *uf)
 	bfa_uf_free(uf);
 }
 
+/*
+ * fcs attach -- called once to initialize data structures at driver attach time
+ */
 void
-bfa_fcs_uf_attach(struct bfa_fcs_s *fcs)
+bfa_fcs_attach(struct bfa_fcs_s *fcs, struct bfa_s *bfa, struct bfad_s *bfad,
+	       bfa_boolean_t min_cfg)
 {
+	struct bfa_fcs_fabric_s *fabric = &fcs->fabric;
+
+	fcs->bfa = bfa;
+	fcs->bfad = bfad;
+	fcs->min_cfg = min_cfg;
+	fcs->num_rport_logins = 0;
+
+	bfa->fcs = BFA_TRUE;
+	fcbuild_init();
+
+	bfa_fcport_event_register(fcs->bfa, bfa_fcs_port_event_handler, fcs);
 	bfa_uf_recv_register(fcs->bfa, bfa_fcs_uf_recv, fcs);
+
+	memset(fabric, 0, sizeof(struct bfa_fcs_fabric_s));
+
+	/*
+	 * Initialize base fabric.
+	 */
+	fabric->fcs = fcs;
+	INIT_LIST_HEAD(&fabric->vport_q);
+	INIT_LIST_HEAD(&fabric->vf_q);
+	fabric->lps = bfa_lps_alloc(fcs->bfa);
+	WARN_ON(!fabric->lps);
+
+	/*
+	 * Initialize fabric delete completion handler. Fabric deletion is
+	 * complete when the last vport delete is complete.
+	 */
+	bfa_wc_init(&fabric->wc, bfa_fcs_fabric_delete_comp, fabric);
+	bfa_wc_up(&fabric->wc); /* For the base port */
+
+	bfa_sm_set_state(fabric, bfa_fcs_fabric_sm_uninit);
+	bfa_fcs_lport_attach(&fabric->bport, fabric->fcs, FC_VF_ID_NULL, NULL);
 }
diff --git a/drivers/scsi/bfa/bfa_fcs.h b/drivers/scsi/bfa/bfa_fcs.h
index 0f797a55d504..e60f72b766ea 100644
--- a/drivers/scsi/bfa/bfa_fcs.h
+++ b/drivers/scsi/bfa/bfa_fcs.h
@@ -808,9 +808,7 @@ void bfa_fcs_vf_get_ports(bfa_fcs_vf_t *vf, wwn_t vpwwn[], int *nports);
 /*
  * fabric protected interface functions
  */
-void bfa_fcs_fabric_attach(struct bfa_fcs_s *fcs);
 void bfa_fcs_fabric_modinit(struct bfa_fcs_s *fcs);
-void bfa_fcs_fabric_modexit(struct bfa_fcs_s *fcs);
 void bfa_fcs_fabric_link_up(struct bfa_fcs_fabric_s *fabric);
 void bfa_fcs_fabric_link_down(struct bfa_fcs_fabric_s *fabric);
 void bfa_fcs_fabric_addvport(struct bfa_fcs_fabric_s *fabric,
@@ -827,8 +825,6 @@ void	bfa_fcs_fabric_nsymb_init(struct bfa_fcs_fabric_s *fabric);
 void bfa_fcs_fabric_set_fabric_name(struct bfa_fcs_fabric_s *fabric,
 	       wwn_t fabric_name);
 u16 bfa_fcs_fabric_get_switch_oui(struct bfa_fcs_fabric_s *fabric);
-void bfa_fcs_uf_attach(struct bfa_fcs_s *fcs);
-void bfa_fcs_port_attach(struct bfa_fcs_s *fcs);
 void bfa_fcs_fabric_modstop(struct bfa_fcs_s *fcs);
 void bfa_fcs_fabric_sm_online(struct bfa_fcs_fabric_s *fabric,
 			enum bfa_fcs_fabric_event event);
diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c
index 02d806012fa1..7eb0eef18fdd 100644
--- a/drivers/scsi/bfa/bfad_im.c
+++ b/drivers/scsi/bfa/bfad_im.c
@@ -813,6 +813,7 @@ struct scsi_host_template bfad_im_scsi_host_template = {
 	.name = BFAD_DRIVER_NAME,
 	.info = bfad_im_info,
 	.queuecommand = bfad_im_queuecommand,
+	.eh_timed_out = fc_eh_timed_out,
 	.eh_abort_handler = bfad_im_abort_handler,
 	.eh_device_reset_handler = bfad_im_reset_lun_handler,
 	.eh_bus_reset_handler = bfad_im_reset_bus_handler,
@@ -835,6 +836,7 @@ struct scsi_host_template bfad_im_vport_template = {
 	.name = BFAD_DRIVER_NAME,
 	.info = bfad_im_info,
 	.queuecommand = bfad_im_queuecommand,
+	.eh_timed_out = fc_eh_timed_out,
 	.eh_abort_handler = bfad_im_abort_handler,
 	.eh_device_reset_handler = bfad_im_reset_lun_handler,
 	.eh_bus_reset_handler = bfad_im_reset_bus_handler,
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index c639d5a02656..b1e39f985ec9 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -2947,6 +2947,7 @@ static struct scsi_host_template bnx2fc_shost_template = {
 	.module			= THIS_MODULE,
 	.name			= "QLogic Offload FCoE Initiator",
 	.queuecommand		= bnx2fc_queuecommand,
+	.eh_timed_out		= fc_eh_timed_out,
 	.eh_abort_handler	= bnx2fc_eh_abort,	  /* abts */
 	.eh_device_reset_handler = bnx2fc_eh_device_reset, /* lun reset */
 	.eh_target_reset_handler = bnx2fc_eh_target_reset, /* tgt reset */
diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c
index f501095f91ac..898461b146cc 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_io.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_io.c
@@ -74,7 +74,7 @@ static void bnx2fc_cmd_timeout(struct work_struct *work)
 				    &io_req->req_flags)) {
 			/* Handle internally generated ABTS timeout */
 			BNX2FC_IO_DBG(io_req, "ABTS timed out refcnt = %d\n",
-					io_req->refcount.refcount.counter);
+					kref_read(&io_req->refcount));
 			if (!(test_and_set_bit(BNX2FC_FLAG_ABTS_DONE,
 					       &io_req->req_flags))) {
 				/*
@@ -1141,7 +1141,7 @@ int bnx2fc_eh_abort(struct scsi_cmnd *sc_cmd)
 		return SUCCESS;
 	}
 	BNX2FC_IO_DBG(io_req, "eh_abort - refcnt = %d\n",
-		      io_req->refcount.refcount.counter);
+		      kref_read(&io_req->refcount));
 
 	/* Hold IO request across abort processing */
 	kref_get(&io_req->refcount);
@@ -1299,7 +1299,7 @@ void bnx2fc_process_cleanup_compl(struct bnx2fc_cmd *io_req,
 {
 	BNX2FC_IO_DBG(io_req, "Entered process_cleanup_compl "
 			      "refcnt = %d, cmd_type = %d\n",
-		   io_req->refcount.refcount.counter, io_req->cmd_type);
+		   kref_read(&io_req->refcount), io_req->cmd_type);
 	bnx2fc_scsi_done(io_req, DID_ERROR);
 	kref_put(&io_req->refcount, bnx2fc_cmd_release);
 	if (io_req->wait_for_comp)
@@ -1318,7 +1318,7 @@ void bnx2fc_process_abts_compl(struct bnx2fc_cmd *io_req,
 	BNX2FC_IO_DBG(io_req, "Entered process_abts_compl xid = 0x%x"
 			      "refcnt = %d, cmd_type = %d\n",
 		   io_req->xid,
-		   io_req->refcount.refcount.counter, io_req->cmd_type);
+		   kref_read(&io_req->refcount), io_req->cmd_type);
 
 	if (test_and_set_bit(BNX2FC_FLAG_ABTS_DONE,
 				       &io_req->req_flags)) {
diff --git a/drivers/scsi/bnx2i/bnx2i_iscsi.c b/drivers/scsi/bnx2i/bnx2i_iscsi.c
index 133901fd3e35..f32a66f89d25 100644
--- a/drivers/scsi/bnx2i/bnx2i_iscsi.c
+++ b/drivers/scsi/bnx2i/bnx2i_iscsi.c
@@ -2259,6 +2259,7 @@ static struct scsi_host_template bnx2i_host_template = {
 	.name			= "QLogic Offload iSCSI Initiator",
 	.proc_name		= "bnx2i",
 	.queuecommand		= iscsi_queuecommand,
+	.eh_timed_out		= iscsi_eh_cmd_timed_out,
 	.eh_abort_handler	= iscsi_eh_abort,
 	.eh_device_reset_handler = iscsi_eh_device_reset,
 	.eh_target_reset_handler = iscsi_eh_recover_target,
diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c
index 89a52b941ea8..a1ff75f1384f 100644
--- a/drivers/scsi/csiostor/csio_scsi.c
+++ b/drivers/scsi/csiostor/csio_scsi.c
@@ -2270,6 +2270,7 @@ struct scsi_host_template csio_fcoe_shost_template = {
 	.name			= CSIO_DRV_DESC,
 	.proc_name		= KBUILD_MODNAME,
 	.queuecommand		= csio_queuecommand,
+	.eh_timed_out		= fc_eh_timed_out,
 	.eh_abort_handler	= csio_eh_abort_handler,
 	.eh_device_reset_handler = csio_eh_lun_reset_handler,
 	.slave_alloc		= csio_slave_alloc,
@@ -2289,6 +2290,7 @@ struct scsi_host_template csio_fcoe_shost_vport_template = {
 	.name			= CSIO_DRV_DESC,
 	.proc_name		= KBUILD_MODNAME,
 	.queuecommand		= csio_queuecommand,
+	.eh_timed_out		= fc_eh_timed_out,
 	.eh_abort_handler	= csio_eh_abort_handler,
 	.eh_device_reset_handler = csio_eh_lun_reset_handler,
 	.slave_alloc		= csio_slave_alloc,
diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
index 33e83464e091..1880eb6c68f7 100644
--- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
+++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
@@ -90,6 +90,7 @@ static struct scsi_host_template cxgb3i_host_template = {
 	.sg_tablesize	= SG_ALL,
 	.max_sectors	= 0xFFFF,
 	.cmd_per_lun	= ISCSI_DEF_CMD_PER_LUN,
+	.eh_timed_out	= iscsi_eh_cmd_timed_out,
 	.eh_abort_handler = iscsi_eh_abort,
 	.eh_device_reset_handler = iscsi_eh_device_reset,
 	.eh_target_reset_handler = iscsi_eh_recover_target,
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 9a2fdc305cf2..3fb3f5708ff7 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -103,6 +103,7 @@ static struct scsi_host_template cxgb4i_host_template = {
 	.sg_tablesize	= SG_ALL,
 	.max_sectors	= 0xFFFF,
 	.cmd_per_lun	= ISCSI_DEF_CMD_PER_LUN,
+	.eh_timed_out	= iscsi_eh_cmd_timed_out,
 	.eh_abort_handler = iscsi_eh_abort,
 	.eh_device_reset_handler = iscsi_eh_device_reset,
 	.eh_target_reset_handler = iscsi_eh_recover_target,
diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h
index 95ba99044c3e..18e0ea83d361 100644
--- a/drivers/scsi/cxgbi/libcxgbi.h
+++ b/drivers/scsi/cxgbi/libcxgbi.h
@@ -301,7 +301,7 @@ static inline void __cxgbi_sock_put(const char *fn, struct cxgbi_sock *csk)
 {
 	log_debug(1 << CXGBI_DBG_SOCK,
 		"%s, put csk 0x%p, ref %u-1.\n",
-		fn, csk, atomic_read(&csk->refcnt.refcount));
+		fn, csk, kref_read(&csk->refcnt));
 	kref_put(&csk->refcnt, cxgbi_sock_free);
 }
 #define cxgbi_sock_put(csk)	__cxgbi_sock_put(__func__, csk)
@@ -310,7 +310,7 @@ static inline void __cxgbi_sock_get(const char *fn, struct cxgbi_sock *csk)
 {
 	log_debug(1 << CXGBI_DBG_SOCK,
 		"%s, get csk 0x%p, ref %u+1.\n",
-		fn, csk, atomic_read(&csk->refcnt.refcount));
+		fn, csk, kref_read(&csk->refcnt));
 	kref_get(&csk->refcnt);
 }
 #define cxgbi_sock_get(csk)	__cxgbi_sock_get(__func__, csk)
diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h
index 0e9de5d62da2..d11dcc59ff46 100644
--- a/drivers/scsi/cxlflash/common.h
+++ b/drivers/scsi/cxlflash/common.h
@@ -54,6 +54,9 @@ extern const struct file_operations cxlflash_cxl_fops;
 /* RRQ for master issued cmds */
 #define NUM_RRQ_ENTRY                   CXLFLASH_MAX_CMDS
 
+/* SQ for master issued cmds */
+#define NUM_SQ_ENTRY			CXLFLASH_MAX_CMDS
+
 
 static inline void check_sizes(void)
 {
@@ -155,8 +158,8 @@ static inline struct afu_cmd *sc_to_afucz(struct scsi_cmnd *sc)
 
 struct afu {
 	/* Stuff requiring alignment go first. */
-
-	u64 rrq_entry[NUM_RRQ_ENTRY];	/* 2K RRQ */
+	struct sisl_ioarcb sq[NUM_SQ_ENTRY];		/* 16K SQ */
+	u64 rrq_entry[NUM_RRQ_ENTRY];			/* 2K RRQ */
 
 	/* Beware of alignment till here. Preferably introduce new
 	 * fields after this point
@@ -171,9 +174,13 @@ struct afu {
 	struct sisl_host_map __iomem *host_map;		/* MC host map */
 	struct sisl_ctrl_map __iomem *ctrl_map;		/* MC control map */
 
-	struct kref mapcount;
-
 	ctx_hndl_t ctx_hndl;	/* master's context handle */
+
+	atomic_t hsq_credits;
+	spinlock_t hsq_slock;
+	struct sisl_ioarcb *hsq_start;
+	struct sisl_ioarcb *hsq_end;
+	struct sisl_ioarcb *hsq_curr;
 	u64 *hrrq_start;
 	u64 *hrrq_end;
 	u64 *hrrq_curr;
@@ -191,6 +198,23 @@ struct afu {
 
 };
 
+static inline bool afu_is_cmd_mode(struct afu *afu, u64 cmd_mode)
+{
+	u64 afu_cap = afu->interface_version >> SISL_INTVER_CAP_SHIFT;
+
+	return afu_cap & cmd_mode;
+}
+
+static inline bool afu_is_sq_cmd_mode(struct afu *afu)
+{
+	return afu_is_cmd_mode(afu, SISL_INTVER_CAP_SQ_CMD_MODE);
+}
+
+static inline bool afu_is_ioarrin_cmd_mode(struct afu *afu)
+{
+	return afu_is_cmd_mode(afu, SISL_INTVER_CAP_IOARRIN_CMD_MODE);
+}
+
 static inline u64 lun_to_lunid(u64 lun)
 {
 	__be64 lun_id;
diff --git a/drivers/scsi/cxlflash/lunmgt.c b/drivers/scsi/cxlflash/lunmgt.c
index 6c318db90c85..0efed177cc8b 100644
--- a/drivers/scsi/cxlflash/lunmgt.c
+++ b/drivers/scsi/cxlflash/lunmgt.c
@@ -32,11 +32,13 @@
  */
 static struct llun_info *create_local(struct scsi_device *sdev, u8 *wwid)
 {
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = NULL;
 
 	lli = kzalloc(sizeof(*lli), GFP_KERNEL);
 	if (unlikely(!lli)) {
-		pr_err("%s: could not allocate lli\n", __func__);
+		dev_err(dev, "%s: could not allocate lli\n", __func__);
 		goto out;
 	}
 
@@ -58,11 +60,13 @@ out:
  */
 static struct glun_info *create_global(struct scsi_device *sdev, u8 *wwid)
 {
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct glun_info *gli = NULL;
 
 	gli = kzalloc(sizeof(*gli), GFP_KERNEL);
 	if (unlikely(!gli)) {
-		pr_err("%s: could not allocate gli\n", __func__);
+		dev_err(dev, "%s: could not allocate gli\n", __func__);
 		goto out;
 	}
 
@@ -129,10 +133,10 @@ static struct glun_info *lookup_global(u8 *wwid)
  */
 static struct llun_info *find_and_create_lun(struct scsi_device *sdev, u8 *wwid)
 {
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = NULL;
 	struct glun_info *gli = NULL;
-	struct Scsi_Host *shost = sdev->host;
-	struct cxlflash_cfg *cfg = shost_priv(shost);
 
 	if (unlikely(!wwid))
 		goto out;
@@ -165,7 +169,7 @@ static struct llun_info *find_and_create_lun(struct scsi_device *sdev, u8 *wwid)
 	list_add(&gli->list, &global.gluns);
 
 out:
-	pr_debug("%s: returning %p\n", __func__, lli);
+	dev_dbg(dev, "%s: returning lli=%p, gli=%p\n", __func__, lli, gli);
 	return lli;
 }
 
@@ -225,17 +229,18 @@ void cxlflash_term_global_luns(void)
 int cxlflash_manage_lun(struct scsi_device *sdev,
 			struct dk_cxlflash_manage_lun *manage)
 {
-	int rc = 0;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = NULL;
+	int rc = 0;
 	u64 flags = manage->hdr.flags;
 	u32 chan = sdev->channel;
 
 	mutex_lock(&global.mutex);
 	lli = find_and_create_lun(sdev, manage->wwid);
-	pr_debug("%s: ENTER: WWID = %016llX%016llX, flags = %016llX li = %p\n",
-		 __func__, get_unaligned_be64(&manage->wwid[0]),
-		 get_unaligned_be64(&manage->wwid[8]),
-		 manage->hdr.flags, lli);
+	dev_dbg(dev, "%s: WWID=%016llx%016llx, flags=%016llx lli=%p\n",
+		__func__, get_unaligned_be64(&manage->wwid[0]),
+		get_unaligned_be64(&manage->wwid[8]), manage->hdr.flags, lli);
 	if (unlikely(!lli)) {
 		rc = -ENOMEM;
 		goto out;
@@ -265,11 +270,11 @@ int cxlflash_manage_lun(struct scsi_device *sdev,
 		}
 	}
 
-	pr_debug("%s: port_sel = %08X chan = %u lun_id = %016llX\n", __func__,
-		 lli->port_sel, chan, lli->lun_id[chan]);
+	dev_dbg(dev, "%s: port_sel=%08x chan=%u lun_id=%016llx\n",
+		__func__, lli->port_sel, chan, lli->lun_id[chan]);
 
 out:
 	mutex_unlock(&global.mutex);
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c
index b17ebf6d0a7e..7069639e92bc 100644
--- a/drivers/scsi/cxlflash/main.c
+++ b/drivers/scsi/cxlflash/main.c
@@ -43,6 +43,9 @@ MODULE_LICENSE("GPL");
  */
 static void process_cmd_err(struct afu_cmd *cmd, struct scsi_cmnd *scp)
 {
+	struct afu *afu = cmd->parent;
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_ioarcb *ioarcb;
 	struct sisl_ioasa *ioasa;
 	u32 resid;
@@ -56,21 +59,20 @@ static void process_cmd_err(struct afu_cmd *cmd, struct scsi_cmnd *scp)
 	if (ioasa->rc.flags & SISL_RC_FLAGS_UNDERRUN) {
 		resid = ioasa->resid;
 		scsi_set_resid(scp, resid);
-		pr_debug("%s: cmd underrun cmd = %p scp = %p, resid = %d\n",
-			 __func__, cmd, scp, resid);
+		dev_dbg(dev, "%s: cmd underrun cmd = %p scp = %p, resid = %d\n",
+			__func__, cmd, scp, resid);
 	}
 
 	if (ioasa->rc.flags & SISL_RC_FLAGS_OVERRUN) {
-		pr_debug("%s: cmd underrun cmd = %p scp = %p\n",
-			 __func__, cmd, scp);
+		dev_dbg(dev, "%s: cmd underrun cmd = %p scp = %p\n",
+			__func__, cmd, scp);
 		scp->result = (DID_ERROR << 16);
 	}
 
-	pr_debug("%s: cmd failed afu_rc=%d scsi_rc=%d fc_rc=%d "
-		 "afu_extra=0x%X, scsi_extra=0x%X, fc_extra=0x%X\n",
-		 __func__, ioasa->rc.afu_rc, ioasa->rc.scsi_rc,
-		 ioasa->rc.fc_rc, ioasa->afu_extra, ioasa->scsi_extra,
-		 ioasa->fc_extra);
+	dev_dbg(dev, "%s: cmd failed afu_rc=%02x scsi_rc=%02x fc_rc=%02x "
+		"afu_extra=%02x scsi_extra=%02x fc_extra=%02x\n", __func__,
+		ioasa->rc.afu_rc, ioasa->rc.scsi_rc, ioasa->rc.fc_rc,
+		ioasa->afu_extra, ioasa->scsi_extra, ioasa->fc_extra);
 
 	if (ioasa->rc.scsi_rc) {
 		/* We have a SCSI status */
@@ -159,6 +161,7 @@ static void cmd_complete(struct afu_cmd *cmd)
 	ulong lock_flags;
 	struct afu *afu = cmd->parent;
 	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	bool cmd_is_tmf;
 
 	if (cmd->scp) {
@@ -170,9 +173,8 @@ static void cmd_complete(struct afu_cmd *cmd)
 
 		cmd_is_tmf = cmd->cmd_tmf;
 
-		pr_debug_ratelimited("%s: calling scsi_done scp=%p result=%X "
-				     "ioasc=%d\n", __func__, scp, scp->result,
-				     cmd->sa.ioasc);
+		dev_dbg_ratelimited(dev, "%s:scp=%p result=%08x ioasc=%08x\n",
+				    __func__, scp, scp->result, cmd->sa.ioasc);
 
 		scsi_dma_unmap(scp);
 		scp->scsi_done(scp);
@@ -188,10 +190,11 @@ static void cmd_complete(struct afu_cmd *cmd)
 }
 
 /**
- * context_reset_ioarrin() - reset command owner context via IOARRIN register
+ * context_reset() - reset command owner context via specified register
  * @cmd:	AFU command that timed out.
+ * @reset_reg:	MMIO register to perform reset.
  */
-static void context_reset_ioarrin(struct afu_cmd *cmd)
+static void context_reset(struct afu_cmd *cmd, __be64 __iomem *reset_reg)
 {
 	int nretry = 0;
 	u64 rrin = 0x1;
@@ -199,22 +202,44 @@ static void context_reset_ioarrin(struct afu_cmd *cmd)
 	struct cxlflash_cfg *cfg = afu->parent;
 	struct device *dev = &cfg->dev->dev;
 
-	pr_debug("%s: cmd=%p\n", __func__, cmd);
+	dev_dbg(dev, "%s: cmd=%p\n", __func__, cmd);
 
-	writeq_be(rrin, &afu->host_map->ioarrin);
+	writeq_be(rrin, reset_reg);
 	do {
-		rrin = readq_be(&afu->host_map->ioarrin);
+		rrin = readq_be(reset_reg);
 		if (rrin != 0x1)
 			break;
 		/* Double delay each time */
 		udelay(1 << nretry);
 	} while (nretry++ < MC_ROOM_RETRY_CNT);
 
-	dev_dbg(dev, "%s: returning rrin=0x%016llX nretry=%d\n",
+	dev_dbg(dev, "%s: returning rrin=%016llx nretry=%d\n",
 		__func__, rrin, nretry);
 }
 
 /**
+ * context_reset_ioarrin() - reset command owner context via IOARRIN register
+ * @cmd:	AFU command that timed out.
+ */
+static void context_reset_ioarrin(struct afu_cmd *cmd)
+{
+	struct afu *afu = cmd->parent;
+
+	context_reset(cmd, &afu->host_map->ioarrin);
+}
+
+/**
+ * context_reset_sq() - reset command owner context w/ SQ Context Reset register
+ * @cmd:	AFU command that timed out.
+ */
+static void context_reset_sq(struct afu_cmd *cmd)
+{
+	struct afu *afu = cmd->parent;
+
+	context_reset(cmd, &afu->host_map->sq_ctx_reset);
+}
+
+/**
  * send_cmd_ioarrin() - sends an AFU command via IOARRIN register
  * @afu:	AFU associated with the host.
  * @cmd:	AFU command to send.
@@ -251,8 +276,51 @@ static int send_cmd_ioarrin(struct afu *afu, struct afu_cmd *cmd)
 	writeq_be((u64)&cmd->rcb, &afu->host_map->ioarrin);
 out:
 	spin_unlock_irqrestore(&afu->rrin_slock, lock_flags);
-	pr_devel("%s: cmd=%p len=%d ea=%p rc=%d\n", __func__, cmd,
-		 cmd->rcb.data_len, (void *)cmd->rcb.data_ea, rc);
+	dev_dbg(dev, "%s: cmd=%p len=%u ea=%016llx rc=%d\n", __func__,
+		cmd, cmd->rcb.data_len, cmd->rcb.data_ea, rc);
+	return rc;
+}
+
+/**
+ * send_cmd_sq() - sends an AFU command via SQ ring
+ * @afu:	AFU associated with the host.
+ * @cmd:	AFU command to send.
+ *
+ * Return:
+ *	0 on success, SCSI_MLQUEUE_HOST_BUSY on failure
+ */
+static int send_cmd_sq(struct afu *afu, struct afu_cmd *cmd)
+{
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
+	int rc = 0;
+	int newval;
+	ulong lock_flags;
+
+	newval = atomic_dec_if_positive(&afu->hsq_credits);
+	if (newval <= 0) {
+		rc = SCSI_MLQUEUE_HOST_BUSY;
+		goto out;
+	}
+
+	cmd->rcb.ioasa = &cmd->sa;
+
+	spin_lock_irqsave(&afu->hsq_slock, lock_flags);
+
+	*afu->hsq_curr = cmd->rcb;
+	if (afu->hsq_curr < afu->hsq_end)
+		afu->hsq_curr++;
+	else
+		afu->hsq_curr = afu->hsq_start;
+	writeq_be((u64)afu->hsq_curr, &afu->host_map->sq_tail);
+
+	spin_unlock_irqrestore(&afu->hsq_slock, lock_flags);
+out:
+	dev_dbg(dev, "%s: cmd=%p len=%u ea=%016llx ioasa=%p rc=%d curr=%p "
+	       "head=%016llx tail=%016llx\n", __func__, cmd, cmd->rcb.data_len,
+	       cmd->rcb.data_ea, cmd->rcb.ioasa, rc, afu->hsq_curr,
+	       readq_be(&afu->host_map->sq_head),
+	       readq_be(&afu->host_map->sq_tail));
 	return rc;
 }
 
@@ -266,6 +334,8 @@ out:
  */
 static int wait_resp(struct afu *afu, struct afu_cmd *cmd)
 {
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
 	ulong timeout = msecs_to_jiffies(cmd->rcb.timeout * 2 * 1000);
 
@@ -276,10 +346,8 @@ static int wait_resp(struct afu *afu, struct afu_cmd *cmd)
 	}
 
 	if (unlikely(cmd->sa.ioasc != 0)) {
-		pr_err("%s: CMD 0x%X failed, IOASC: flags 0x%X, afu_rc 0x%X, "
-		       "scsi_rc 0x%X, fc_rc 0x%X\n", __func__, cmd->rcb.cdb[0],
-		       cmd->sa.rc.flags, cmd->sa.rc.afu_rc, cmd->sa.rc.scsi_rc,
-		       cmd->sa.rc.fc_rc);
+		dev_err(dev, "%s: cmd %02x failed, ioasc=%08x\n",
+			__func__, cmd->rcb.cdb[0], cmd->sa.ioasc);
 		rc = -1;
 	}
 
@@ -298,8 +366,7 @@ static int wait_resp(struct afu *afu, struct afu_cmd *cmd)
 static int send_tmf(struct afu *afu, struct scsi_cmnd *scp, u64 tmfcmd)
 {
 	u32 port_sel = scp->device->channel + 1;
-	struct Scsi_Host *host = scp->device->host;
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(scp->device->host);
 	struct afu_cmd *cmd = sc_to_afucz(scp);
 	struct device *dev = &cfg->dev->dev;
 	ulong lock_flags;
@@ -344,7 +411,7 @@ static int send_tmf(struct afu *afu, struct scsi_cmnd *scp, u64 tmfcmd)
 						       to);
 	if (!to) {
 		cfg->tmf_active = false;
-		dev_err(dev, "%s: TMF timed out!\n", __func__);
+		dev_err(dev, "%s: TMF timed out\n", __func__);
 		rc = -1;
 	}
 	spin_unlock_irqrestore(&cfg->tmf_slock, lock_flags);
@@ -352,16 +419,6 @@ out:
 	return rc;
 }
 
-static void afu_unmap(struct kref *ref)
-{
-	struct afu *afu = container_of(ref, struct afu, mapcount);
-
-	if (likely(afu->afu_map)) {
-		cxl_psa_unmap((void __iomem *)afu->afu_map);
-		afu->afu_map = NULL;
-	}
-}
-
 /**
  * cxlflash_driver_info() - information handler for this host driver
  * @host:	SCSI host associated with device.
@@ -382,7 +439,7 @@ static const char *cxlflash_driver_info(struct Scsi_Host *host)
  */
 static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(host);
 	struct afu *afu = cfg->afu;
 	struct device *dev = &cfg->dev->dev;
 	struct afu_cmd *cmd = sc_to_afucz(scp);
@@ -392,10 +449,9 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 	ulong lock_flags;
 	int nseg = 0;
 	int rc = 0;
-	int kref_got = 0;
 
 	dev_dbg_ratelimited(dev, "%s: (scp=%p) %d/%d/%d/%llu "
-			    "cdb=(%08X-%08X-%08X-%08X)\n",
+			    "cdb=(%08x-%08x-%08x-%08x)\n",
 			    __func__, scp, host->host_no, scp->device->channel,
 			    scp->device->id, scp->device->lun,
 			    get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
@@ -417,11 +473,11 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 
 	switch (cfg->state) {
 	case STATE_RESET:
-		dev_dbg_ratelimited(dev, "%s: device is in reset!\n", __func__);
+		dev_dbg_ratelimited(dev, "%s: device is in reset\n", __func__);
 		rc = SCSI_MLQUEUE_HOST_BUSY;
 		goto out;
 	case STATE_FAILTERM:
-		dev_dbg_ratelimited(dev, "%s: device has failed!\n", __func__);
+		dev_dbg_ratelimited(dev, "%s: device has failed\n", __func__);
 		scp->result = (DID_NO_CONNECT << 16);
 		scp->scsi_done(scp);
 		rc = 0;
@@ -430,13 +486,10 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 		break;
 	}
 
-	kref_get(&cfg->afu->mapcount);
-	kref_got = 1;
-
 	if (likely(sg)) {
 		nseg = scsi_dma_map(scp);
 		if (unlikely(nseg < 0)) {
-			dev_err(dev, "%s: Fail DMA map!\n", __func__);
+			dev_err(dev, "%s: Fail DMA map\n", __func__);
 			rc = SCSI_MLQUEUE_HOST_BUSY;
 			goto out;
 		}
@@ -463,9 +516,6 @@ static int cxlflash_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scp)
 	if (unlikely(rc))
 		scsi_dma_unmap(scp);
 out:
-	if (kref_got)
-		kref_put(&afu->mapcount, afu_unmap);
-	pr_devel("%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -503,13 +553,15 @@ static void free_mem(struct cxlflash_cfg *cfg)
  *
  * Safe to call with AFU in a partially allocated/initialized state.
  *
- * Waits for any active internal AFU commands to timeout and then unmaps
- * the MMIO space.
+ * Cancels scheduled worker threads, waits for any active internal AFU
+ * commands to timeout and then unmaps the MMIO space.
  */
 static void stop_afu(struct cxlflash_cfg *cfg)
 {
 	struct afu *afu = cfg->afu;
 
+	cancel_work_sync(&cfg->work_q);
+
 	if (likely(afu)) {
 		while (atomic_read(&afu->cmds_active))
 			ssleep(1);
@@ -517,7 +569,6 @@ static void stop_afu(struct cxlflash_cfg *cfg)
 			cxl_psa_unmap((void __iomem *)afu->afu_map);
 			afu->afu_map = NULL;
 		}
-		kref_put(&afu->mapcount, afu_unmap);
 	}
 }
 
@@ -585,6 +636,8 @@ static void term_mc(struct cxlflash_cfg *cfg)
  */
 static void term_afu(struct cxlflash_cfg *cfg)
 {
+	struct device *dev = &cfg->dev->dev;
+
 	/*
 	 * Tear down is carefully orchestrated to ensure
 	 * no interrupts can come in when the problem state
@@ -600,7 +653,7 @@ static void term_afu(struct cxlflash_cfg *cfg)
 
 	term_mc(cfg);
 
-	pr_debug("%s: returning\n", __func__);
+	dev_dbg(dev, "%s: returning\n", __func__);
 }
 
 /**
@@ -627,8 +680,7 @@ static void notify_shutdown(struct cxlflash_cfg *cfg, bool wait)
 		return;
 
 	if (!afu || !afu->afu_map) {
-		dev_dbg(dev, "%s: The problem state area is not mapped\n",
-			__func__);
+		dev_dbg(dev, "%s: Problem state area not mapped\n", __func__);
 		return;
 	}
 
@@ -670,10 +722,11 @@ static void notify_shutdown(struct cxlflash_cfg *cfg, bool wait)
 static void cxlflash_remove(struct pci_dev *pdev)
 {
 	struct cxlflash_cfg *cfg = pci_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
 	ulong lock_flags;
 
 	if (!pci_is_enabled(pdev)) {
-		pr_debug("%s: Device is disabled\n", __func__);
+		dev_dbg(dev, "%s: Device is disabled\n", __func__);
 		return;
 	}
 
@@ -699,7 +752,6 @@ static void cxlflash_remove(struct pci_dev *pdev)
 		scsi_remove_host(cfg->host);
 		/* fall through */
 	case INIT_STATE_AFU:
-		cancel_work_sync(&cfg->work_q);
 		term_afu(cfg);
 	case INIT_STATE_PCI:
 		pci_disable_device(pdev);
@@ -709,7 +761,7 @@ static void cxlflash_remove(struct pci_dev *pdev)
 		break;
 	}
 
-	pr_debug("%s: returning\n", __func__);
+	dev_dbg(dev, "%s: returning\n", __func__);
 }
 
 /**
@@ -727,7 +779,7 @@ static int alloc_mem(struct cxlflash_cfg *cfg)
 	int rc = 0;
 	struct device *dev = &cfg->dev->dev;
 
-	/* AFU is ~12k, i.e. only one 64k page or up to four 4k pages */
+	/* AFU is ~28k, i.e. only one 64k page or up to seven 4k pages */
 	cfg->afu = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
 					    get_order(sizeof(struct afu)));
 	if (unlikely(!cfg->afu)) {
@@ -751,6 +803,7 @@ out:
 static int init_pci(struct cxlflash_cfg *cfg)
 {
 	struct pci_dev *pdev = cfg->dev;
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
 
 	rc = pci_enable_device(pdev);
@@ -761,15 +814,14 @@ static int init_pci(struct cxlflash_cfg *cfg)
 		}
 
 		if (rc) {
-			dev_err(&pdev->dev, "%s: Cannot enable adapter\n",
-				__func__);
+			dev_err(dev, "%s: Cannot enable adapter\n", __func__);
 			cxlflash_wait_for_pci_err_recovery(cfg);
 			goto out;
 		}
 	}
 
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -782,19 +834,19 @@ out:
 static int init_scsi(struct cxlflash_cfg *cfg)
 {
 	struct pci_dev *pdev = cfg->dev;
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
 
 	rc = scsi_add_host(cfg->host, &pdev->dev);
 	if (rc) {
-		dev_err(&pdev->dev, "%s: scsi_add_host failed (rc=%d)\n",
-			__func__, rc);
+		dev_err(dev, "%s: scsi_add_host failed rc=%d\n", __func__, rc);
 		goto out;
 	}
 
 	scsi_scan_host(cfg->host);
 
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -844,16 +896,12 @@ static void set_port_offline(__be64 __iomem *fc_regs)
  * Return:
  *	TRUE (1) when the specified port is online
  *	FALSE (0) when the specified port fails to come online after timeout
- *	-EINVAL when @delay_us is less than 1000
  */
-static int wait_port_online(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
+static bool wait_port_online(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
 {
 	u64 status;
 
-	if (delay_us < 1000) {
-		pr_err("%s: invalid delay specified %d\n", __func__, delay_us);
-		return -EINVAL;
-	}
+	WARN_ON(delay_us < 1000);
 
 	do {
 		msleep(delay_us / 1000);
@@ -877,16 +925,12 @@ static int wait_port_online(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
  * Return:
  *	TRUE (1) when the specified port is offline
  *	FALSE (0) when the specified port fails to go offline after timeout
- *	-EINVAL when @delay_us is less than 1000
  */
-static int wait_port_offline(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
+static bool wait_port_offline(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
 {
 	u64 status;
 
-	if (delay_us < 1000) {
-		pr_err("%s: invalid delay specified %d\n", __func__, delay_us);
-		return -EINVAL;
-	}
+	WARN_ON(delay_us < 1000);
 
 	do {
 		msleep(delay_us / 1000);
@@ -915,11 +959,14 @@ static int wait_port_offline(__be64 __iomem *fc_regs, u32 delay_us, u32 nretry)
 static void afu_set_wwpn(struct afu *afu, int port, __be64 __iomem *fc_regs,
 			 u64 wwpn)
 {
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
+
 	set_port_offline(fc_regs);
 	if (!wait_port_offline(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
 			       FC_PORT_STATUS_RETRY_CNT)) {
-		pr_debug("%s: wait on port %d to go offline timed out\n",
-			 __func__, port);
+		dev_dbg(dev, "%s: wait on port %d to go offline timed out\n",
+			__func__, port);
 	}
 
 	writeq_be(wwpn, &fc_regs[FC_PNAME / 8]);
@@ -927,8 +974,8 @@ static void afu_set_wwpn(struct afu *afu, int port, __be64 __iomem *fc_regs,
 	set_port_online(fc_regs);
 	if (!wait_port_online(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
 			      FC_PORT_STATUS_RETRY_CNT)) {
-		pr_debug("%s: wait on port %d to go online timed out\n",
-			 __func__, port);
+		dev_dbg(dev, "%s: wait on port %d to go online timed out\n",
+			__func__, port);
 	}
 }
 
@@ -947,6 +994,8 @@ static void afu_set_wwpn(struct afu *afu, int port, __be64 __iomem *fc_regs,
  */
 static void afu_link_reset(struct afu *afu, int port, __be64 __iomem *fc_regs)
 {
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	u64 port_sel;
 
 	/* first switch the AFU to the other links, if any */
@@ -958,21 +1007,21 @@ static void afu_link_reset(struct afu *afu, int port, __be64 __iomem *fc_regs)
 	set_port_offline(fc_regs);
 	if (!wait_port_offline(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
 			       FC_PORT_STATUS_RETRY_CNT))
-		pr_err("%s: wait on port %d to go offline timed out\n",
-		       __func__, port);
+		dev_err(dev, "%s: wait on port %d to go offline timed out\n",
+			__func__, port);
 
 	set_port_online(fc_regs);
 	if (!wait_port_online(fc_regs, FC_PORT_STATUS_RETRY_INTERVAL_US,
 			      FC_PORT_STATUS_RETRY_CNT))
-		pr_err("%s: wait on port %d to go online timed out\n",
-		       __func__, port);
+		dev_err(dev, "%s: wait on port %d to go online timed out\n",
+			__func__, port);
 
 	/* switch back to include this port */
 	port_sel |= (1ULL << port);
 	writeq_be(port_sel, &afu->afu_map->global.regs.afu_port_sel);
 	cxlflash_afu_sync(afu, 0, 0, AFU_GSYNC);
 
-	pr_debug("%s: returning port_sel=%lld\n", __func__, port_sel);
+	dev_dbg(dev, "%s: returning port_sel=%016llx\n", __func__, port_sel);
 }
 
 /*
@@ -1082,6 +1131,8 @@ static void afu_err_intr_init(struct afu *afu)
 static irqreturn_t cxlflash_sync_err_irq(int irq, void *data)
 {
 	struct afu *afu = (struct afu *)data;
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	u64 reg;
 	u64 reg_unmasked;
 
@@ -1089,18 +1140,17 @@ static irqreturn_t cxlflash_sync_err_irq(int irq, void *data)
 	reg_unmasked = (reg & SISL_ISTATUS_UNMASK);
 
 	if (reg_unmasked == 0UL) {
-		pr_err("%s: %llX: spurious interrupt, intr_status %016llX\n",
-		       __func__, (u64)afu, reg);
+		dev_err(dev, "%s: spurious interrupt, intr_status=%016llx\n",
+			__func__, reg);
 		goto cxlflash_sync_err_irq_exit;
 	}
 
-	pr_err("%s: %llX: unexpected interrupt, intr_status %016llX\n",
-	       __func__, (u64)afu, reg);
+	dev_err(dev, "%s: unexpected interrupt, intr_status=%016llx\n",
+		__func__, reg);
 
 	writeq_be(reg_unmasked, &afu->host_map->intr_clear);
 
 cxlflash_sync_err_irq_exit:
-	pr_debug("%s: returning rc=%d\n", __func__, IRQ_HANDLED);
 	return IRQ_HANDLED;
 }
 
@@ -1115,6 +1165,8 @@ static irqreturn_t cxlflash_rrq_irq(int irq, void *data)
 {
 	struct afu *afu = (struct afu *)data;
 	struct afu_cmd *cmd;
+	struct sisl_ioasa *ioasa;
+	struct sisl_ioarcb *ioarcb;
 	bool toggle = afu->toggle;
 	u64 entry,
 	    *hrrq_start = afu->hrrq_start,
@@ -1128,7 +1180,16 @@ static irqreturn_t cxlflash_rrq_irq(int irq, void *data)
 		if ((entry & SISL_RESP_HANDLE_T_BIT) != toggle)
 			break;
 
-		cmd = (struct afu_cmd *)(entry & ~SISL_RESP_HANDLE_T_BIT);
+		entry &= ~SISL_RESP_HANDLE_T_BIT;
+
+		if (afu_is_sq_cmd_mode(afu)) {
+			ioasa = (struct sisl_ioasa *)entry;
+			cmd = container_of(ioasa, struct afu_cmd, sa);
+		} else {
+			ioarcb = (struct sisl_ioarcb *)entry;
+			cmd = container_of(ioarcb, struct afu_cmd, rcb);
+		}
+
 		cmd_complete(cmd);
 
 		/* Advance to next entry or wrap and flip the toggle bit */
@@ -1138,6 +1199,8 @@ static irqreturn_t cxlflash_rrq_irq(int irq, void *data)
 			hrrq_curr = hrrq_start;
 			toggle ^= SISL_RESP_HANDLE_T_BIT;
 		}
+
+		atomic_inc(&afu->hsq_credits);
 	}
 
 	afu->hrrq_curr = hrrq_curr;
@@ -1169,7 +1232,7 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 	reg_unmasked = (reg & SISL_ASTATUS_UNMASK);
 
 	if (reg_unmasked == 0) {
-		dev_err(dev, "%s: spurious interrupt, aintr_status 0x%016llX\n",
+		dev_err(dev, "%s: spurious interrupt, aintr_status=%016llx\n",
 			__func__, reg);
 		goto out;
 	}
@@ -1185,7 +1248,7 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 
 		port = info->port;
 
-		dev_err(dev, "%s: FC Port %d -> %s, fc_status 0x%08llX\n",
+		dev_err(dev, "%s: FC Port %d -> %s, fc_status=%016llx\n",
 			__func__, port, info->desc,
 		       readq_be(&global->fc_regs[port][FC_STATUS / 8]));
 
@@ -1198,7 +1261,6 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 				__func__, port);
 			cfg->lr_state = LINK_RESET_REQUIRED;
 			cfg->lr_port = port;
-			kref_get(&cfg->afu->mapcount);
 			schedule_work(&cfg->work_q);
 		}
 
@@ -1210,7 +1272,7 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 			 * should be the same and tracing one is sufficient.
 			 */
 
-			dev_err(dev, "%s: fc %d: clearing fc_error 0x%08llX\n",
+			dev_err(dev, "%s: fc %d: clearing fc_error=%016llx\n",
 				__func__, port, reg);
 
 			writeq_be(reg, &global->fc_regs[port][FC_ERROR / 8]);
@@ -1219,13 +1281,11 @@ static irqreturn_t cxlflash_async_err_irq(int irq, void *data)
 
 		if (info->action & SCAN_HOST) {
 			atomic_inc(&cfg->scan_host_needed);
-			kref_get(&cfg->afu->mapcount);
 			schedule_work(&cfg->work_q);
 		}
 	}
 
 out:
-	dev_dbg(dev, "%s: returning IRQ_HANDLED, afu=%p\n", __func__, afu);
 	return IRQ_HANDLED;
 }
 
@@ -1237,13 +1297,14 @@ out:
  */
 static int start_context(struct cxlflash_cfg *cfg)
 {
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
 
 	rc = cxl_start_context(cfg->mcctx,
 			       cfg->afu->work.work_element_descriptor,
 			       NULL);
 
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1256,7 +1317,8 @@ static int start_context(struct cxlflash_cfg *cfg)
  */
 static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 {
-	struct pci_dev *dev = cfg->dev;
+	struct device *dev = &cfg->dev->dev;
+	struct pci_dev *pdev = cfg->dev;
 	int rc = 0;
 	int ro_start, ro_size, i, j, k;
 	ssize_t vpd_size;
@@ -1265,10 +1327,10 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 	char *wwpn_vpd_tags[NUM_FC_PORTS] = { "V5", "V6" };
 
 	/* Get the VPD data from the device */
-	vpd_size = cxl_read_adapter_vpd(dev, vpd_data, sizeof(vpd_data));
+	vpd_size = cxl_read_adapter_vpd(pdev, vpd_data, sizeof(vpd_data));
 	if (unlikely(vpd_size <= 0)) {
-		dev_err(&dev->dev, "%s: Unable to read VPD (size = %ld)\n",
-		       __func__, vpd_size);
+		dev_err(dev, "%s: Unable to read VPD (size = %ld)\n",
+			__func__, vpd_size);
 		rc = -ENODEV;
 		goto out;
 	}
@@ -1277,8 +1339,7 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 	ro_start = pci_vpd_find_tag(vpd_data, 0, vpd_size,
 				    PCI_VPD_LRDT_RO_DATA);
 	if (unlikely(ro_start < 0)) {
-		dev_err(&dev->dev, "%s: VPD Read-only data not found\n",
-			__func__);
+		dev_err(dev, "%s: VPD Read-only data not found\n", __func__);
 		rc = -ENODEV;
 		goto out;
 	}
@@ -1288,8 +1349,8 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 	j = ro_size;
 	i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
 	if (unlikely((i + j) > vpd_size)) {
-		pr_debug("%s: Might need to read more VPD (%d > %ld)\n",
-			 __func__, (i + j), vpd_size);
+		dev_dbg(dev, "%s: Might need to read more VPD (%d > %ld)\n",
+			__func__, (i + j), vpd_size);
 		ro_size = vpd_size - i;
 	}
 
@@ -1307,8 +1368,8 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 
 		i = pci_vpd_find_info_keyword(vpd_data, i, j, wwpn_vpd_tags[k]);
 		if (unlikely(i < 0)) {
-			dev_err(&dev->dev, "%s: Port %d WWPN not found "
-				"in VPD\n", __func__, k);
+			dev_err(dev, "%s: Port %d WWPN not found in VPD\n",
+				__func__, k);
 			rc = -ENODEV;
 			goto out;
 		}
@@ -1316,9 +1377,8 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 		j = pci_vpd_info_field_size(&vpd_data[i]);
 		i += PCI_VPD_INFO_FLD_HDR_SIZE;
 		if (unlikely((i + j > vpd_size) || (j != WWPN_LEN))) {
-			dev_err(&dev->dev, "%s: Port %d WWPN incomplete or "
-				"VPD corrupt\n",
-			       __func__, k);
+			dev_err(dev, "%s: Port %d WWPN incomplete or bad VPD\n",
+				__func__, k);
 			rc = -ENODEV;
 			goto out;
 		}
@@ -1326,15 +1386,15 @@ static int read_vpd(struct cxlflash_cfg *cfg, u64 wwpn[])
 		memcpy(tmp_buf, &vpd_data[i], WWPN_LEN);
 		rc = kstrtoul(tmp_buf, WWPN_LEN, (ulong *)&wwpn[k]);
 		if (unlikely(rc)) {
-			dev_err(&dev->dev, "%s: Fail to convert port %d WWPN "
-				"to integer\n", __func__, k);
+			dev_err(dev, "%s: WWPN conversion failed for port %d\n",
+				__func__, k);
 			rc = -ENODEV;
 			goto out;
 		}
 	}
 
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1388,12 +1448,18 @@ static int init_global(struct cxlflash_cfg *cfg)
 		goto out;
 	}
 
-	pr_debug("%s: wwpn0=0x%llX wwpn1=0x%llX\n", __func__, wwpn[0], wwpn[1]);
+	dev_dbg(dev, "%s: wwpn0=%016llx wwpn1=%016llx\n",
+		__func__, wwpn[0], wwpn[1]);
 
-	/* Set up RRQ in AFU for master issued cmds */
+	/* Set up RRQ and SQ in AFU for master issued cmds */
 	writeq_be((u64) afu->hrrq_start, &afu->host_map->rrq_start);
 	writeq_be((u64) afu->hrrq_end, &afu->host_map->rrq_end);
 
+	if (afu_is_sq_cmd_mode(afu)) {
+		writeq_be((u64)afu->hsq_start, &afu->host_map->sq_start);
+		writeq_be((u64)afu->hsq_end, &afu->host_map->sq_end);
+	}
+
 	/* AFU configuration */
 	reg = readq_be(&afu->afu_map->global.regs.afu_config);
 	reg |= SISL_AFUCONF_AR_ALL|SISL_AFUCONF_ENDIAN;
@@ -1443,7 +1509,6 @@ static int init_global(struct cxlflash_cfg *cfg)
 		  &afu->ctrl_map->ctx_cap);
 	/* Initialize heartbeat */
 	afu->hb = readq_be(&afu->afu_map->global.regs.afu_hb);
-
 out:
 	return rc;
 }
@@ -1455,6 +1520,7 @@ out:
 static int start_afu(struct cxlflash_cfg *cfg)
 {
 	struct afu *afu = cfg->afu;
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
 
 	init_pcr(cfg);
@@ -1468,9 +1534,20 @@ static int start_afu(struct cxlflash_cfg *cfg)
 	afu->hrrq_curr = afu->hrrq_start;
 	afu->toggle = 1;
 
+	/* Initialize SQ */
+	if (afu_is_sq_cmd_mode(afu)) {
+		memset(&afu->sq, 0, sizeof(afu->sq));
+		afu->hsq_start = &afu->sq[0];
+		afu->hsq_end = &afu->sq[NUM_SQ_ENTRY - 1];
+		afu->hsq_curr = afu->hsq_start;
+
+		spin_lock_init(&afu->hsq_slock);
+		atomic_set(&afu->hsq_credits, NUM_SQ_ENTRY - 1);
+	}
+
 	rc = init_global(cfg);
 
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1490,7 +1567,7 @@ static enum undo_level init_intr(struct cxlflash_cfg *cfg,
 
 	rc = cxl_allocate_afu_irqs(ctx, 3);
 	if (unlikely(rc)) {
-		dev_err(dev, "%s: call to allocate_afu_irqs failed rc=%d!\n",
+		dev_err(dev, "%s: allocate_afu_irqs failed rc=%d\n",
 			__func__, rc);
 		level = UNDO_NOOP;
 		goto out;
@@ -1499,8 +1576,7 @@ static enum undo_level init_intr(struct cxlflash_cfg *cfg,
 	rc = cxl_map_afu_irq(ctx, 1, cxlflash_sync_err_irq, afu,
 			     "SISL_MSI_SYNC_ERROR");
 	if (unlikely(rc <= 0)) {
-		dev_err(dev, "%s: IRQ 1 (SISL_MSI_SYNC_ERROR) map failed!\n",
-			__func__);
+		dev_err(dev, "%s: SISL_MSI_SYNC_ERROR map failed\n", __func__);
 		level = FREE_IRQ;
 		goto out;
 	}
@@ -1508,8 +1584,7 @@ static enum undo_level init_intr(struct cxlflash_cfg *cfg,
 	rc = cxl_map_afu_irq(ctx, 2, cxlflash_rrq_irq, afu,
 			     "SISL_MSI_RRQ_UPDATED");
 	if (unlikely(rc <= 0)) {
-		dev_err(dev, "%s: IRQ 2 (SISL_MSI_RRQ_UPDATED) map failed!\n",
-			__func__);
+		dev_err(dev, "%s: SISL_MSI_RRQ_UPDATED map failed\n", __func__);
 		level = UNMAP_ONE;
 		goto out;
 	}
@@ -1517,8 +1592,7 @@ static enum undo_level init_intr(struct cxlflash_cfg *cfg,
 	rc = cxl_map_afu_irq(ctx, 3, cxlflash_async_err_irq, afu,
 			     "SISL_MSI_ASYNC_ERROR");
 	if (unlikely(rc <= 0)) {
-		dev_err(dev, "%s: IRQ 3 (SISL_MSI_ASYNC_ERROR) map failed!\n",
-			__func__);
+		dev_err(dev, "%s: SISL_MSI_ASYNC_ERROR map failed\n", __func__);
 		level = UNMAP_TWO;
 		goto out;
 	}
@@ -1552,15 +1626,13 @@ static int init_mc(struct cxlflash_cfg *cfg)
 	/* During initialization reset the AFU to start from a clean slate */
 	rc = cxl_afu_reset(cfg->mcctx);
 	if (unlikely(rc)) {
-		dev_err(dev, "%s: initial AFU reset failed rc=%d\n",
-			__func__, rc);
+		dev_err(dev, "%s: AFU reset failed rc=%d\n", __func__, rc);
 		goto ret;
 	}
 
 	level = init_intr(cfg, ctx);
 	if (unlikely(level)) {
-		dev_err(dev, "%s: setting up interrupts failed rc=%d\n",
-			__func__, rc);
+		dev_err(dev, "%s: interrupt init failed rc=%d\n", __func__, rc);
 		goto out;
 	}
 
@@ -1575,7 +1647,7 @@ static int init_mc(struct cxlflash_cfg *cfg)
 		goto out;
 	}
 ret:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 out:
 	term_intr(cfg, level);
@@ -1602,7 +1674,7 @@ static int init_afu(struct cxlflash_cfg *cfg)
 
 	rc = init_mc(cfg);
 	if (rc) {
-		dev_err(dev, "%s: call to init_mc failed, rc=%d!\n",
+		dev_err(dev, "%s: init_mc failed rc=%d\n",
 			__func__, rc);
 		goto out;
 	}
@@ -1610,11 +1682,10 @@ static int init_afu(struct cxlflash_cfg *cfg)
 	/* Map the entire MMIO space of the AFU */
 	afu->afu_map = cxl_psa_map(cfg->mcctx);
 	if (!afu->afu_map) {
-		dev_err(dev, "%s: call to cxl_psa_map failed!\n", __func__);
+		dev_err(dev, "%s: cxl_psa_map failed\n", __func__);
 		rc = -ENOMEM;
 		goto err1;
 	}
-	kref_init(&afu->mapcount);
 
 	/* No byte reverse on reading afu_version or string will be backwards */
 	reg = readq(&afu->afu_map->global.regs.afu_version);
@@ -1622,24 +1693,28 @@ static int init_afu(struct cxlflash_cfg *cfg)
 	afu->interface_version =
 	    readq_be(&afu->afu_map->global.regs.interface_version);
 	if ((afu->interface_version + 1) == 0) {
-		pr_err("Back level AFU, please upgrade. AFU version %s "
-		       "interface version 0x%llx\n", afu->version,
+		dev_err(dev, "Back level AFU, please upgrade. AFU version %s "
+			"interface version %016llx\n", afu->version,
 		       afu->interface_version);
 		rc = -EINVAL;
-		goto err2;
+		goto err1;
 	}
 
-	afu->send_cmd = send_cmd_ioarrin;
-	afu->context_reset = context_reset_ioarrin;
+	if (afu_is_sq_cmd_mode(afu)) {
+		afu->send_cmd = send_cmd_sq;
+		afu->context_reset = context_reset_sq;
+	} else {
+		afu->send_cmd = send_cmd_ioarrin;
+		afu->context_reset = context_reset_ioarrin;
+	}
 
-	pr_debug("%s: afu version %s, interface version 0x%llX\n", __func__,
-		 afu->version, afu->interface_version);
+	dev_dbg(dev, "%s: afu_ver=%s interface_ver=%016llx\n", __func__,
+		afu->version, afu->interface_version);
 
 	rc = start_afu(cfg);
 	if (rc) {
-		dev_err(dev, "%s: call to start_afu failed, rc=%d!\n",
-			__func__, rc);
-		goto err2;
+		dev_err(dev, "%s: start_afu failed, rc=%d\n", __func__, rc);
+		goto err1;
 	}
 
 	afu_err_intr_init(cfg->afu);
@@ -1649,11 +1724,9 @@ static int init_afu(struct cxlflash_cfg *cfg)
 	/* Restore the LUN mappings */
 	cxlflash_restore_luntable(cfg);
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 
-err2:
-	kref_put(&afu->mapcount, afu_unmap);
 err1:
 	term_intr(cfg, UNMAP_THREE);
 	term_mc(cfg);
@@ -1693,7 +1766,8 @@ int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
 	static DEFINE_MUTEX(sync_active);
 
 	if (cfg->state != STATE_NORMAL) {
-		pr_debug("%s: Sync not required! (%u)\n", __func__, cfg->state);
+		dev_dbg(dev, "%s: Sync not required state=%u\n",
+			__func__, cfg->state);
 		return 0;
 	}
 
@@ -1710,7 +1784,7 @@ int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t ctx_hndl_u,
 	init_completion(&cmd->cevent);
 	cmd->parent = afu;
 
-	pr_debug("%s: afu=%p cmd=%p %d\n", __func__, afu, cmd, ctx_hndl_u);
+	dev_dbg(dev, "%s: afu=%p cmd=%p %d\n", __func__, afu, cmd, ctx_hndl_u);
 
 	cmd->rcb.req_flags = SISL_REQ_FLAGS_AFU_CMD;
 	cmd->rcb.ctx_id = afu->ctx_hndl;
@@ -1735,7 +1809,7 @@ out:
 	atomic_dec(&afu->cmds_active);
 	mutex_unlock(&sync_active);
 	kfree(buf);
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1747,16 +1821,17 @@ out:
  */
 static int afu_reset(struct cxlflash_cfg *cfg)
 {
+	struct device *dev = &cfg->dev->dev;
 	int rc = 0;
+
 	/* Stop the context before the reset. Since the context is
 	 * no longer available restart it after the reset is complete
 	 */
-
 	term_afu(cfg);
 
 	rc = init_afu(cfg);
 
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1785,18 +1860,18 @@ static int cxlflash_eh_device_reset_handler(struct scsi_cmnd *scp)
 {
 	int rc = SUCCESS;
 	struct Scsi_Host *host = scp->device->host;
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(host);
+	struct device *dev = &cfg->dev->dev;
 	struct afu *afu = cfg->afu;
 	int rcr = 0;
 
-	pr_debug("%s: (scp=%p) %d/%d/%d/%llu "
-		 "cdb=(%08X-%08X-%08X-%08X)\n", __func__, scp,
-		 host->host_no, scp->device->channel,
-		 scp->device->id, scp->device->lun,
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
+	dev_dbg(dev, "%s: (scp=%p) %d/%d/%d/%llu "
+		"cdb=(%08x-%08x-%08x-%08x)\n", __func__, scp, host->host_no,
+		scp->device->channel, scp->device->id, scp->device->lun,
+		get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
 
 retry:
 	switch (cfg->state) {
@@ -1813,7 +1888,7 @@ retry:
 		break;
 	}
 
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1835,16 +1910,16 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp)
 	int rc = SUCCESS;
 	int rcr = 0;
 	struct Scsi_Host *host = scp->device->host;
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(host);
+	struct device *dev = &cfg->dev->dev;
 
-	pr_debug("%s: (scp=%p) %d/%d/%d/%llu "
-		 "cdb=(%08X-%08X-%08X-%08X)\n", __func__, scp,
-		 host->host_no, scp->device->channel,
-		 scp->device->id, scp->device->lun,
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
-		 get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
+	dev_dbg(dev, "%s: (scp=%p) %d/%d/%d/%llu "
+		"cdb=(%08x-%08x-%08x-%08x)\n", __func__, scp, host->host_no,
+		scp->device->channel, scp->device->id, scp->device->lun,
+		get_unaligned_be32(&((u32 *)scp->cmnd)[0]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[1]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[2]),
+		get_unaligned_be32(&((u32 *)scp->cmnd)[3]));
 
 	switch (cfg->state) {
 	case STATE_NORMAL:
@@ -1870,7 +1945,7 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp)
 		break;
 	}
 
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -1936,8 +2011,7 @@ static ssize_t port0_show(struct device *dev,
 			  struct device_attribute *attr,
 			  char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(class_to_shost(dev));
 	struct afu *afu = cfg->afu;
 
 	return cxlflash_show_port_status(0, afu, buf);
@@ -1955,8 +2029,7 @@ static ssize_t port1_show(struct device *dev,
 			  struct device_attribute *attr,
 			  char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(class_to_shost(dev));
 	struct afu *afu = cfg->afu;
 
 	return cxlflash_show_port_status(1, afu, buf);
@@ -1973,8 +2046,7 @@ static ssize_t port1_show(struct device *dev,
 static ssize_t lun_mode_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(class_to_shost(dev));
 	struct afu *afu = cfg->afu;
 
 	return scnprintf(buf, PAGE_SIZE, "%u\n", afu->internal_lun);
@@ -2007,7 +2079,7 @@ static ssize_t lun_mode_store(struct device *dev,
 			      const char *buf, size_t count)
 {
 	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(shost);
 	struct afu *afu = cfg->afu;
 	int rc;
 	u32 lun_mode;
@@ -2069,7 +2141,7 @@ static ssize_t cxlflash_show_port_lun_table(u32 port,
 
 	for (i = 0; i < CXLFLASH_NUM_VLUNS; i++)
 		bytes += scnprintf(buf + bytes, PAGE_SIZE - bytes,
-				   "%03d: %016llX\n", i, readq_be(&fc_port[i]));
+				   "%03d: %016llx\n", i, readq_be(&fc_port[i]));
 	return bytes;
 }
 
@@ -2085,8 +2157,7 @@ static ssize_t port0_lun_table_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(class_to_shost(dev));
 	struct afu *afu = cfg->afu;
 
 	return cxlflash_show_port_lun_table(0, afu, buf);
@@ -2104,8 +2175,7 @@ static ssize_t port1_lun_table_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
 {
-	struct Scsi_Host *shost = class_to_shost(dev);
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)shost->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(class_to_shost(dev));
 	struct afu *afu = cfg->afu;
 
 	return cxlflash_show_port_lun_table(1, afu, buf);
@@ -2250,7 +2320,6 @@ static void cxlflash_worker_thread(struct work_struct *work)
 
 	if (atomic_dec_if_positive(&cfg->scan_host_needed) >= 0)
 		scsi_scan_host(cfg->host);
-	kref_put(&afu->mapcount, afu_unmap);
 }
 
 /**
@@ -2265,6 +2334,7 @@ static int cxlflash_probe(struct pci_dev *pdev,
 {
 	struct Scsi_Host *host;
 	struct cxlflash_cfg *cfg = NULL;
+	struct device *dev = &pdev->dev;
 	struct dev_dependent_vals *ddv;
 	int rc = 0;
 
@@ -2276,8 +2346,7 @@ static int cxlflash_probe(struct pci_dev *pdev,
 
 	host = scsi_host_alloc(&driver_template, sizeof(struct cxlflash_cfg));
 	if (!host) {
-		dev_err(&pdev->dev, "%s: call to scsi_host_alloc failed!\n",
-			__func__);
+		dev_err(dev, "%s: scsi_host_alloc failed\n", __func__);
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -2288,12 +2357,11 @@ static int cxlflash_probe(struct pci_dev *pdev,
 	host->unique_id = host->host_no;
 	host->max_cmd_len = CXLFLASH_MAX_CDB_LEN;
 
-	cfg = (struct cxlflash_cfg *)host->hostdata;
+	cfg = shost_priv(host);
 	cfg->host = host;
 	rc = alloc_mem(cfg);
 	if (rc) {
-		dev_err(&pdev->dev, "%s: call to alloc_mem failed!\n",
-			__func__);
+		dev_err(dev, "%s: alloc_mem failed\n", __func__);
 		rc = -ENOMEM;
 		scsi_host_put(cfg->host);
 		goto out;
@@ -2334,30 +2402,27 @@ static int cxlflash_probe(struct pci_dev *pdev,
 
 	rc = init_pci(cfg);
 	if (rc) {
-		dev_err(&pdev->dev, "%s: call to init_pci "
-			"failed rc=%d!\n", __func__, rc);
+		dev_err(dev, "%s: init_pci failed rc=%d\n", __func__, rc);
 		goto out_remove;
 	}
 	cfg->init_state = INIT_STATE_PCI;
 
 	rc = init_afu(cfg);
 	if (rc) {
-		dev_err(&pdev->dev, "%s: call to init_afu "
-			"failed rc=%d!\n", __func__, rc);
+		dev_err(dev, "%s: init_afu failed rc=%d\n", __func__, rc);
 		goto out_remove;
 	}
 	cfg->init_state = INIT_STATE_AFU;
 
 	rc = init_scsi(cfg);
 	if (rc) {
-		dev_err(&pdev->dev, "%s: call to init_scsi "
-			"failed rc=%d!\n", __func__, rc);
+		dev_err(dev, "%s: init_scsi failed rc=%d\n", __func__, rc);
 		goto out_remove;
 	}
 	cfg->init_state = INIT_STATE_SCSI;
 
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 
 out_remove:
@@ -2395,7 +2460,7 @@ static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev,
 		drain_ioctls(cfg);
 		rc = cxlflash_mark_contexts_error(cfg);
 		if (unlikely(rc))
-			dev_err(dev, "%s: Failed to mark user contexts!(%d)\n",
+			dev_err(dev, "%s: Failed to mark user contexts rc=%d\n",
 				__func__, rc);
 		term_afu(cfg);
 		return PCI_ERS_RESULT_NEED_RESET;
@@ -2429,7 +2494,7 @@ static pci_ers_result_t cxlflash_pci_slot_reset(struct pci_dev *pdev)
 
 	rc = init_afu(cfg);
 	if (unlikely(rc)) {
-		dev_err(dev, "%s: EEH recovery failed! (%d)\n", __func__, rc);
+		dev_err(dev, "%s: EEH recovery failed rc=%d\n", __func__, rc);
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
@@ -2477,8 +2542,6 @@ static struct pci_driver cxlflash_driver = {
  */
 static int __init init_cxlflash(void)
 {
-	pr_info("%s: %s\n", __func__, CXLFLASH_ADAPTER_NAME);
-
 	cxlflash_list_init();
 
 	return pci_register_driver(&cxlflash_driver);
diff --git a/drivers/scsi/cxlflash/sislite.h b/drivers/scsi/cxlflash/sislite.h
index 1a2d09c148b3..a6e48a893fef 100644
--- a/drivers/scsi/cxlflash/sislite.h
+++ b/drivers/scsi/cxlflash/sislite.h
@@ -72,7 +72,10 @@ struct sisl_ioarcb {
 	u16 timeout;		/* in units specified by req_flags */
 	u32 rsvd1;
 	u8 cdb[16];		/* must be in big endian */
-	u64 reserved;		/* Reserved area */
+	union {
+		u64 reserved;			/* Reserved for IOARRIN mode */
+		struct sisl_ioasa *ioasa;	/* IOASA EA for SQ Mode */
+	};
 } __packed;
 
 struct sisl_rc {
@@ -260,6 +263,11 @@ struct sisl_host_map {
 	__be64 cmd_room;
 	__be64 ctx_ctrl;	/* least significant byte or b56:63 is LISN# */
 	__be64 mbox_w;		/* restricted use */
+	__be64 sq_start;	/* Submission Queue (R/W): write sequence and */
+	__be64 sq_end;		/* inclusion semantics are the same as RRQ    */
+	__be64 sq_head;		/* Submission Queue Head (R): for debugging   */
+	__be64 sq_tail;		/* Submission Queue TAIL (R/W): next IOARCB   */
+	__be64 sq_ctx_reset;	/* Submission Queue Context Reset (R/W)	      */
 };
 
 /* per context provisioning & control MMIO */
@@ -348,6 +356,15 @@ struct sisl_global_regs {
 	__be64 rsvd[0xf8];
 	__le64 afu_version;
 	__be64 interface_version;
+#define SISL_INTVER_CAP_SHIFT			16
+#define SISL_INTVER_MAJ_SHIFT			8
+#define SISL_INTVER_CAP_MASK			0xFFFFFFFF00000000ULL
+#define SISL_INTVER_MAJ_MASK			0x00000000FFFF0000ULL
+#define SISL_INTVER_MIN_MASK			0x000000000000FFFFULL
+#define SISL_INTVER_CAP_IOARRIN_CMD_MODE	0x800000000000ULL
+#define SISL_INTVER_CAP_SQ_CMD_MODE		0x400000000000ULL
+#define SISL_INTVER_CAP_RESERVED_CMD_MODE_A	0x200000000000ULL
+#define SISL_INTVER_CAP_RESERVED_CMD_MODE_B	0x100000000000ULL
 };
 
 #define CXLFLASH_NUM_FC_PORTS   2
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index 9636970d9611..90869cee2b20 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -212,7 +212,7 @@ struct ctx_info *get_context(struct cxlflash_cfg *cfg, u64 rctxid,
 	}
 
 out:
-	dev_dbg(dev, "%s: rctxid=%016llX ctxinfo=%p ctxpid=%u pid=%u "
+	dev_dbg(dev, "%s: rctxid=%016llx ctxinfo=%p ctxpid=%u pid=%u "
 		"ctx_ctrl=%u\n", __func__, rctxid, ctxi, ctxpid, pid,
 		ctx_ctrl);
 
@@ -260,7 +260,7 @@ static int afu_attach(struct cxlflash_cfg *cfg, struct ctx_info *ctxi)
 	writeq_be(val, &ctrl_map->ctx_cap);
 	val = readq_be(&ctrl_map->ctx_cap);
 	if (val != (SISL_CTX_CAP_READ_CMD | SISL_CTX_CAP_WRITE_CMD)) {
-		dev_err(dev, "%s: ctx may be closed val=%016llX\n",
+		dev_err(dev, "%s: ctx may be closed val=%016llx\n",
 			__func__, val);
 		rc = -EAGAIN;
 		goto out;
@@ -302,7 +302,7 @@ out:
  */
 static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct glun_info *gli = lli->parent;
 	u8 *cmd_buf = NULL;
@@ -326,7 +326,7 @@ retry:
 	scsi_cmd[1] = SAI_READ_CAPACITY_16;	/* service action */
 	put_unaligned_be32(CMD_BUFSIZE, &scsi_cmd[10]);
 
-	dev_dbg(dev, "%s: %ssending cmd(0x%x)\n", __func__,
+	dev_dbg(dev, "%s: %ssending cmd(%02x)\n", __func__,
 		retry_cnt ? "re" : "", scsi_cmd[0]);
 
 	/* Drop the ioctl read semahpore across lengthy call */
@@ -336,7 +336,7 @@ retry:
 	down_read(&cfg->ioctl_rwsem);
 	rc = check_state(cfg);
 	if (rc) {
-		dev_err(dev, "%s: Failed state! result=0x08%X\n",
+		dev_err(dev, "%s: Failed state result=%08x\n",
 			__func__, result);
 		rc = -ENODEV;
 		goto out;
@@ -378,7 +378,7 @@ retry:
 	}
 
 	if (result) {
-		dev_err(dev, "%s: command failed, result=0x%x\n",
+		dev_err(dev, "%s: command failed, result=%08x\n",
 			__func__, result);
 		rc = -EIO;
 		goto out;
@@ -415,29 +415,32 @@ out:
 struct sisl_rht_entry *get_rhte(struct ctx_info *ctxi, res_hndl_t rhndl,
 				struct llun_info *lli)
 {
+	struct cxlflash_cfg *cfg = ctxi->cfg;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_rht_entry *rhte = NULL;
 
 	if (unlikely(!ctxi->rht_start)) {
-		pr_debug("%s: Context does not have allocated RHT!\n",
+		dev_dbg(dev, "%s: Context does not have allocated RHT\n",
 			 __func__);
 		goto out;
 	}
 
 	if (unlikely(rhndl >= MAX_RHT_PER_CONTEXT)) {
-		pr_debug("%s: Bad resource handle! (%d)\n", __func__, rhndl);
+		dev_dbg(dev, "%s: Bad resource handle rhndl=%d\n",
+			__func__, rhndl);
 		goto out;
 	}
 
 	if (unlikely(ctxi->rht_lun[rhndl] != lli)) {
-		pr_debug("%s: Bad resource handle LUN! (%d)\n",
-			 __func__, rhndl);
+		dev_dbg(dev, "%s: Bad resource handle LUN rhndl=%d\n",
+			__func__, rhndl);
 		goto out;
 	}
 
 	rhte = &ctxi->rht_start[rhndl];
 	if (unlikely(rhte->nmask == 0)) {
-		pr_debug("%s: Unopened resource handle! (%d)\n",
-			 __func__, rhndl);
+		dev_dbg(dev, "%s: Unopened resource handle rhndl=%d\n",
+			__func__, rhndl);
 		rhte = NULL;
 		goto out;
 	}
@@ -456,6 +459,8 @@ out:
 struct sisl_rht_entry *rhte_checkout(struct ctx_info *ctxi,
 				     struct llun_info *lli)
 {
+	struct cxlflash_cfg *cfg = ctxi->cfg;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_rht_entry *rhte = NULL;
 	int i;
 
@@ -470,7 +475,7 @@ struct sisl_rht_entry *rhte_checkout(struct ctx_info *ctxi,
 	if (likely(rhte))
 		ctxi->rht_lun[i] = lli;
 
-	pr_debug("%s: returning rhte=%p (%d)\n", __func__, rhte, i);
+	dev_dbg(dev, "%s: returning rhte=%p index=%d\n", __func__, rhte, i);
 	return rhte;
 }
 
@@ -547,7 +552,7 @@ int cxlflash_lun_attach(struct glun_info *gli, enum lun_mode mode, bool locked)
 	if (gli->mode == MODE_NONE)
 		gli->mode = mode;
 	else if (gli->mode != mode) {
-		pr_debug("%s: LUN operating in mode %d, requested mode %d\n",
+		pr_debug("%s: gli_mode=%d requested_mode=%d\n",
 			 __func__, gli->mode, mode);
 		rc = -EINVAL;
 		goto out;
@@ -605,7 +610,7 @@ int _cxlflash_disk_release(struct scsi_device *sdev,
 			   struct ctx_info *ctxi,
 			   struct dk_cxlflash_release *release)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -622,13 +627,13 @@ int _cxlflash_disk_release(struct scsi_device *sdev,
 	struct sisl_rht_entry *rhte;
 	struct sisl_rht_entry_f1 *rhte_f1;
 
-	dev_dbg(dev, "%s: ctxid=%llu rhndl=0x%llx gli->mode=%u gli->users=%u\n",
+	dev_dbg(dev, "%s: ctxid=%llu rhndl=%llu gli->mode=%u gli->users=%u\n",
 		__func__, ctxid, release->rsrc_handle, gli->mode, gli->users);
 
 	if (!ctxi) {
 		ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
 		if (unlikely(!ctxi)) {
-			dev_dbg(dev, "%s: Bad context! (%llu)\n",
+			dev_dbg(dev, "%s: Bad context ctxid=%llu\n",
 				__func__, ctxid);
 			rc = -EINVAL;
 			goto out;
@@ -639,7 +644,7 @@ int _cxlflash_disk_release(struct scsi_device *sdev,
 
 	rhte = get_rhte(ctxi, rhndl, lli);
 	if (unlikely(!rhte)) {
-		dev_dbg(dev, "%s: Bad resource handle! (%d)\n",
+		dev_dbg(dev, "%s: Bad resource handle rhndl=%d\n",
 			__func__, rhndl);
 		rc = -EINVAL;
 		goto out;
@@ -758,13 +763,13 @@ static struct ctx_info *create_context(struct cxlflash_cfg *cfg)
 	lli = kzalloc((MAX_RHT_PER_CONTEXT * sizeof(*lli)), GFP_KERNEL);
 	ws = kzalloc((MAX_RHT_PER_CONTEXT * sizeof(*ws)), GFP_KERNEL);
 	if (unlikely(!ctxi || !lli || !ws)) {
-		dev_err(dev, "%s: Unable to allocate context!\n", __func__);
+		dev_err(dev, "%s: Unable to allocate context\n", __func__);
 		goto err;
 	}
 
 	rhte = (struct sisl_rht_entry *)get_zeroed_page(GFP_KERNEL);
 	if (unlikely(!rhte)) {
-		dev_err(dev, "%s: Unable to allocate RHT!\n", __func__);
+		dev_err(dev, "%s: Unable to allocate RHT\n", __func__);
 		goto err;
 	}
 
@@ -858,7 +863,7 @@ static int _cxlflash_disk_detach(struct scsi_device *sdev,
 				 struct ctx_info *ctxi,
 				 struct dk_cxlflash_detach *detach)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct lun_access *lun_access, *t;
@@ -875,7 +880,7 @@ static int _cxlflash_disk_detach(struct scsi_device *sdev,
 	if (!ctxi) {
 		ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
 		if (unlikely(!ctxi)) {
-			dev_dbg(dev, "%s: Bad context! (%llu)\n",
+			dev_dbg(dev, "%s: Bad context ctxid=%llu\n",
 				__func__, ctxid);
 			rc = -EINVAL;
 			goto out;
@@ -964,7 +969,7 @@ static int cxlflash_cxl_release(struct inode *inode, struct file *file)
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely(ctxid < 0)) {
-		dev_err(dev, "%s: Context %p was closed! (%d)\n",
+		dev_err(dev, "%s: Context %p was closed ctxid=%d\n",
 			__func__, ctx, ctxid);
 		goto out;
 	}
@@ -973,18 +978,18 @@ static int cxlflash_cxl_release(struct inode *inode, struct file *file)
 	if (unlikely(!ctxi)) {
 		ctxi = get_context(cfg, ctxid, file, ctrl | CTX_CTRL_CLONE);
 		if (!ctxi) {
-			dev_dbg(dev, "%s: Context %d already free!\n",
+			dev_dbg(dev, "%s: ctxid=%d already free\n",
 				__func__, ctxid);
 			goto out_release;
 		}
 
-		dev_dbg(dev, "%s: Another process owns context %d!\n",
+		dev_dbg(dev, "%s: Another process owns ctxid=%d\n",
 			__func__, ctxid);
 		put_context(ctxi);
 		goto out;
 	}
 
-	dev_dbg(dev, "%s: close for context %d\n", __func__, ctxid);
+	dev_dbg(dev, "%s: close for ctxid=%d\n", __func__, ctxid);
 
 	detach.context_id = ctxi->ctxid;
 	list_for_each_entry_safe(lun_access, t, &ctxi->luns, list)
@@ -1011,17 +1016,20 @@ static void unmap_context(struct ctx_info *ctxi)
 
 /**
  * get_err_page() - obtains and allocates the error notification page
+ * @cfg:	Internal structure associated with the host.
  *
  * Return: error notification page on success, NULL on failure
  */
-static struct page *get_err_page(void)
+static struct page *get_err_page(struct cxlflash_cfg *cfg)
 {
 	struct page *err_page = global.err_page;
+	struct device *dev = &cfg->dev->dev;
 
 	if (unlikely(!err_page)) {
 		err_page = alloc_page(GFP_KERNEL);
 		if (unlikely(!err_page)) {
-			pr_err("%s: Unable to allocate err_page!\n", __func__);
+			dev_err(dev, "%s: Unable to allocate err_page\n",
+				__func__);
 			goto out;
 		}
 
@@ -1039,7 +1047,7 @@ static struct page *get_err_page(void)
 	}
 
 out:
-	pr_debug("%s: returning err_page=%p\n", __func__, err_page);
+	dev_dbg(dev, "%s: returning err_page=%p\n", __func__, err_page);
 	return err_page;
 }
 
@@ -1074,14 +1082,14 @@ static int cxlflash_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely(ctxid < 0)) {
-		dev_err(dev, "%s: Context %p was closed! (%d)\n",
+		dev_err(dev, "%s: Context %p was closed ctxid=%d\n",
 			__func__, ctx, ctxid);
 		goto err;
 	}
 
 	ctxi = get_context(cfg, ctxid, file, ctrl);
 	if (unlikely(!ctxi)) {
-		dev_dbg(dev, "%s: Bad context! (%d)\n", __func__, ctxid);
+		dev_dbg(dev, "%s: Bad context ctxid=%d\n", __func__, ctxid);
 		goto err;
 	}
 
@@ -1091,13 +1099,12 @@ static int cxlflash_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 		rc = ctxi->cxl_mmap_vmops->fault(vma, vmf);
 	} else {
-		dev_dbg(dev, "%s: err recovery active, use err_page!\n",
+		dev_dbg(dev, "%s: err recovery active, use err_page\n",
 			__func__);
 
-		err_page = get_err_page();
+		err_page = get_err_page(cfg);
 		if (unlikely(!err_page)) {
-			dev_err(dev, "%s: Could not obtain error page!\n",
-				__func__);
+			dev_err(dev, "%s: Could not get err_page\n", __func__);
 			rc = VM_FAULT_RETRY;
 			goto out;
 		}
@@ -1147,7 +1154,7 @@ static int cxlflash_cxl_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely(ctxid < 0)) {
-		dev_err(dev, "%s: Context %p was closed! (%d)\n",
+		dev_err(dev, "%s: Context %p was closed ctxid=%d\n",
 			__func__, ctx, ctxid);
 		rc = -EIO;
 		goto out;
@@ -1155,7 +1162,7 @@ static int cxlflash_cxl_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ctxi = get_context(cfg, ctxid, file, ctrl);
 	if (unlikely(!ctxi)) {
-		dev_dbg(dev, "%s: Bad context! (%d)\n", __func__, ctxid);
+		dev_dbg(dev, "%s: Bad context ctxid=%d\n", __func__, ctxid);
 		rc = -EIO;
 		goto out;
 	}
@@ -1251,7 +1258,7 @@ retry:
 			break;
 		goto retry;
 	case STATE_FAILTERM:
-		dev_dbg(dev, "%s: Failed/Terminating!\n", __func__);
+		dev_dbg(dev, "%s: Failed/Terminating\n", __func__);
 		rc = -ENODEV;
 		break;
 	default:
@@ -1276,7 +1283,7 @@ retry:
 static int cxlflash_disk_attach(struct scsi_device *sdev,
 				struct dk_cxlflash_attach *attach)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct afu *afu = cfg->afu;
 	struct llun_info *lli = sdev->hostdata;
@@ -1287,6 +1294,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 	int rc = 0;
 	u32 perms;
 	int ctxid = -1;
+	u64 flags = 0UL;
 	u64 rctxid = 0UL;
 	struct file *file = NULL;
 
@@ -1302,24 +1310,24 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 	}
 
 	if (gli->max_lba == 0) {
-		dev_dbg(dev, "%s: No capacity info for this LUN (%016llX)\n",
+		dev_dbg(dev, "%s: No capacity info for LUN=%016llx\n",
 			__func__, lli->lun_id[sdev->channel]);
 		rc = read_cap16(sdev, lli);
 		if (rc) {
-			dev_err(dev, "%s: Invalid device! (%d)\n",
+			dev_err(dev, "%s: Invalid device rc=%d\n",
 				__func__, rc);
 			rc = -ENODEV;
 			goto out;
 		}
-		dev_dbg(dev, "%s: LBA = %016llX\n", __func__, gli->max_lba);
-		dev_dbg(dev, "%s: BLK_LEN = %08X\n", __func__, gli->blk_len);
+		dev_dbg(dev, "%s: LBA = %016llx\n", __func__, gli->max_lba);
+		dev_dbg(dev, "%s: BLK_LEN = %08x\n", __func__, gli->blk_len);
 	}
 
 	if (attach->hdr.flags & DK_CXLFLASH_ATTACH_REUSE_CONTEXT) {
 		rctxid = attach->context_id;
 		ctxi = get_context(cfg, rctxid, NULL, 0);
 		if (!ctxi) {
-			dev_dbg(dev, "%s: Bad context! (%016llX)\n",
+			dev_dbg(dev, "%s: Bad context rctxid=%016llx\n",
 				__func__, rctxid);
 			rc = -EINVAL;
 			goto out;
@@ -1327,7 +1335,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 		list_for_each_entry(lun_access, &ctxi->luns, list)
 			if (lun_access->lli == lli) {
-				dev_dbg(dev, "%s: Already attached!\n",
+				dev_dbg(dev, "%s: Already attached\n",
 					__func__);
 				rc = -EINVAL;
 				goto out;
@@ -1336,13 +1344,13 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 	rc = scsi_device_get(sdev);
 	if (unlikely(rc)) {
-		dev_err(dev, "%s: Unable to get sdev reference!\n", __func__);
+		dev_err(dev, "%s: Unable to get sdev reference\n", __func__);
 		goto out;
 	}
 
 	lun_access = kzalloc(sizeof(*lun_access), GFP_KERNEL);
 	if (unlikely(!lun_access)) {
-		dev_err(dev, "%s: Unable to allocate lun_access!\n", __func__);
+		dev_err(dev, "%s: Unable to allocate lun_access\n", __func__);
 		rc = -ENOMEM;
 		goto err;
 	}
@@ -1352,7 +1360,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 	/* Non-NULL context indicates reuse (another context reference) */
 	if (ctxi) {
-		dev_dbg(dev, "%s: Reusing context for LUN! (%016llX)\n",
+		dev_dbg(dev, "%s: Reusing context for LUN rctxid=%016llx\n",
 			__func__, rctxid);
 		kref_get(&ctxi->kref);
 		list_add(&lun_access->list, &ctxi->luns);
@@ -1361,7 +1369,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 	ctxi = create_context(cfg);
 	if (unlikely(!ctxi)) {
-		dev_err(dev, "%s: Failed to create context! (%d)\n",
+		dev_err(dev, "%s: Failed to create context ctxid=%d\n",
 			__func__, ctxid);
 		goto err;
 	}
@@ -1387,7 +1395,7 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
-		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
+		dev_err(dev, "%s: ctxid=%d invalid\n", __func__, ctxid);
 		rc = -EPERM;
 		goto err;
 	}
@@ -1426,10 +1434,11 @@ static int cxlflash_disk_attach(struct scsi_device *sdev,
 
 out_attach:
 	if (fd != -1)
-		attach->hdr.return_flags = DK_CXLFLASH_APP_CLOSE_ADAP_FD;
-	else
-		attach->hdr.return_flags = 0;
+		flags |= DK_CXLFLASH_APP_CLOSE_ADAP_FD;
+	if (afu_is_sq_cmd_mode(afu))
+		flags |= DK_CXLFLASH_CONTEXT_SQ_CMD_MODE;
 
+	attach->hdr.return_flags = flags;
 	attach->context_id = ctxi->ctxid;
 	attach->block_size = gli->blk_len;
 	attach->mmio_size = sizeof(afu->afu_map->hosts[0].harea);
@@ -1520,7 +1529,7 @@ static int recover_context(struct cxlflash_cfg *cfg,
 
 	ctxid = cxl_process_element(ctx);
 	if (unlikely((ctxid >= MAX_CONTEXT) || (ctxid < 0))) {
-		dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid);
+		dev_err(dev, "%s: ctxid=%d invalid\n", __func__, ctxid);
 		rc = -EPERM;
 		goto err2;
 	}
@@ -1611,12 +1620,13 @@ err1:
 static int cxlflash_afu_recover(struct scsi_device *sdev,
 				struct dk_cxlflash_recover_afu *recover)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct afu *afu = cfg->afu;
 	struct ctx_info *ctxi = NULL;
 	struct mutex *mutex = &cfg->ctx_recovery_mutex;
+	u64 flags;
 	u64 ctxid = DECODE_CTXID(recover->context_id),
 	    rctxid = recover->context_id;
 	long reg;
@@ -1632,19 +1642,19 @@ static int cxlflash_afu_recover(struct scsi_device *sdev,
 		goto out;
 	rc = check_state(cfg);
 	if (rc) {
-		dev_err(dev, "%s: Failed state! rc=%d\n", __func__, rc);
+		dev_err(dev, "%s: Failed state rc=%d\n", __func__, rc);
 		rc = -ENODEV;
 		goto out;
 	}
 
-	dev_dbg(dev, "%s: reason 0x%016llX rctxid=%016llX\n",
+	dev_dbg(dev, "%s: reason=%016llx rctxid=%016llx\n",
 		__func__, recover->reason, rctxid);
 
 retry:
 	/* Ensure that this process is attached to the context */
 	ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
 	if (unlikely(!ctxi)) {
-		dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+		dev_dbg(dev, "%s: Bad context ctxid=%llu\n", __func__, ctxid);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -1653,12 +1663,12 @@ retry:
 retry_recover:
 		rc = recover_context(cfg, ctxi, &new_adap_fd);
 		if (unlikely(rc)) {
-			dev_err(dev, "%s: Recovery failed for context %llu (rc=%d)\n",
+			dev_err(dev, "%s: Recovery failed ctxid=%llu rc=%d\n",
 				__func__, ctxid, rc);
 			if ((rc == -ENODEV) &&
 			    ((atomic_read(&cfg->recovery_threads) > 1) ||
 			     (lretry--))) {
-				dev_dbg(dev, "%s: Going to try again!\n",
+				dev_dbg(dev, "%s: Going to try again\n",
 					__func__);
 				mutex_unlock(mutex);
 				msleep(100);
@@ -1672,11 +1682,16 @@ retry_recover:
 		}
 
 		ctxi->err_recovery_active = false;
+
+		flags = DK_CXLFLASH_APP_CLOSE_ADAP_FD |
+			DK_CXLFLASH_RECOVER_AFU_CONTEXT_RESET;
+		if (afu_is_sq_cmd_mode(afu))
+			flags |= DK_CXLFLASH_CONTEXT_SQ_CMD_MODE;
+
+		recover->hdr.return_flags = flags;
 		recover->context_id = ctxi->ctxid;
 		recover->adap_fd = new_adap_fd;
 		recover->mmio_size = sizeof(afu->afu_map->hosts[0].harea);
-		recover->hdr.return_flags = DK_CXLFLASH_APP_CLOSE_ADAP_FD |
-			DK_CXLFLASH_RECOVER_AFU_CONTEXT_RESET;
 		goto out;
 	}
 
@@ -1699,7 +1714,7 @@ retry_recover:
 		goto retry;
 	}
 
-	dev_dbg(dev, "%s: MMIO working, no recovery required!\n", __func__);
+	dev_dbg(dev, "%s: MMIO working, no recovery required\n", __func__);
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
@@ -1718,7 +1733,7 @@ out:
 static int process_sense(struct scsi_device *sdev,
 			 struct dk_cxlflash_verify *verify)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -1729,7 +1744,7 @@ static int process_sense(struct scsi_device *sdev,
 	rc = scsi_normalize_sense((const u8 *)&verify->sense_data,
 				  DK_CXLFLASH_VERIFY_SENSE_LEN, &sshdr);
 	if (!rc) {
-		dev_err(dev, "%s: Failed to normalize sense data!\n", __func__);
+		dev_err(dev, "%s: Failed to normalize sense data\n", __func__);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -1785,7 +1800,7 @@ static int cxlflash_disk_verify(struct scsi_device *sdev,
 {
 	int rc = 0;
 	struct ctx_info *ctxi = NULL;
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -1795,20 +1810,20 @@ static int cxlflash_disk_verify(struct scsi_device *sdev,
 	    rctxid = verify->context_id;
 	u64 last_lba = 0;
 
-	dev_dbg(dev, "%s: ctxid=%llu rhndl=%016llX, hint=%016llX, "
-		"flags=%016llX\n", __func__, ctxid, verify->rsrc_handle,
+	dev_dbg(dev, "%s: ctxid=%llu rhndl=%016llx, hint=%016llx, "
+		"flags=%016llx\n", __func__, ctxid, verify->rsrc_handle,
 		verify->hint, verify->hdr.flags);
 
 	ctxi = get_context(cfg, rctxid, lli, 0);
 	if (unlikely(!ctxi)) {
-		dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+		dev_dbg(dev, "%s: Bad context ctxid=%llu\n", __func__, ctxid);
 		rc = -EINVAL;
 		goto out;
 	}
 
 	rhte = get_rhte(ctxi, rhndl, lli);
 	if (unlikely(!rhte)) {
-		dev_dbg(dev, "%s: Bad resource handle! (%d)\n",
+		dev_dbg(dev, "%s: Bad resource handle rhndl=%d\n",
 			__func__, rhndl);
 		rc = -EINVAL;
 		goto out;
@@ -1855,7 +1870,7 @@ static int cxlflash_disk_verify(struct scsi_device *sdev,
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
-	dev_dbg(dev, "%s: returning rc=%d llba=%llX\n",
+	dev_dbg(dev, "%s: returning rc=%d llba=%llx\n",
 		__func__, rc, verify->last_lba);
 	return rc;
 }
@@ -1907,7 +1922,7 @@ static char *decode_ioctl(int cmd)
  */
 static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct afu *afu = cfg->afu;
 	struct llun_info *lli = sdev->hostdata;
@@ -1927,25 +1942,25 @@ static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg)
 	struct ctx_info *ctxi = NULL;
 	struct sisl_rht_entry *rhte = NULL;
 
-	pr_debug("%s: ctxid=%llu ls=0x%llx\n", __func__, ctxid, lun_size);
+	dev_dbg(dev, "%s: ctxid=%llu ls=%llu\n", __func__, ctxid, lun_size);
 
 	rc = cxlflash_lun_attach(gli, MODE_PHYSICAL, false);
 	if (unlikely(rc)) {
-		dev_dbg(dev, "%s: Failed to attach to LUN! (PHYSICAL)\n",
-			__func__);
+		dev_dbg(dev, "%s: Failed attach to LUN (PHYSICAL)\n", __func__);
 		goto out;
 	}
 
 	ctxi = get_context(cfg, rctxid, lli, 0);
 	if (unlikely(!ctxi)) {
-		dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+		dev_dbg(dev, "%s: Bad context ctxid=%llu\n", __func__, ctxid);
 		rc = -EINVAL;
 		goto err1;
 	}
 
 	rhte = rhte_checkout(ctxi, lli);
 	if (unlikely(!rhte)) {
-		dev_dbg(dev, "%s: too many opens for this context\n", __func__);
+		dev_dbg(dev, "%s: Too many opens ctxid=%lld\n",
+			__func__, ctxid);
 		rc = -EMFILE;	/* too many opens  */
 		goto err1;
 	}
@@ -1963,7 +1978,7 @@ static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg)
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
-	dev_dbg(dev, "%s: returning handle 0x%llx rc=%d llba %lld\n",
+	dev_dbg(dev, "%s: returning handle=%llu rc=%d llba=%llu\n",
 		__func__, rsrc_handle, rc, last_lba);
 	return rc;
 
@@ -1985,7 +2000,7 @@ err1:
  */
 static int ioctl_common(struct scsi_device *sdev, int cmd)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	int rc = 0;
@@ -2002,7 +2017,7 @@ static int ioctl_common(struct scsi_device *sdev, int cmd)
 		case DK_CXLFLASH_VLUN_RESIZE:
 		case DK_CXLFLASH_RELEASE:
 		case DK_CXLFLASH_DETACH:
-			dev_dbg(dev, "%s: Command override! (%d)\n",
+			dev_dbg(dev, "%s: Command override rc=%d\n",
 				__func__, rc);
 			rc = 0;
 			break;
@@ -2032,7 +2047,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 {
 	typedef int (*sioctl) (struct scsi_device *, void *);
 
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct afu *afu = cfg->afu;
 	struct dk_cxlflash_hdr *hdr;
@@ -2111,7 +2126,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 	}
 
 	if (unlikely(copy_from_user(&buf, arg, size))) {
-		dev_err(dev, "%s: copy_from_user() fail! "
+		dev_err(dev, "%s: copy_from_user() fail "
 			"size=%lu cmd=%d (%s) arg=%p\n",
 			__func__, size, cmd, decode_ioctl(cmd), arg);
 		rc = -EFAULT;
@@ -2127,7 +2142,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 	}
 
 	if (hdr->rsvd[0] || hdr->rsvd[1] || hdr->rsvd[2] || hdr->return_flags) {
-		dev_dbg(dev, "%s: Reserved/rflags populated!\n", __func__);
+		dev_dbg(dev, "%s: Reserved/rflags populated\n", __func__);
 		rc = -EINVAL;
 		goto cxlflash_ioctl_exit;
 	}
@@ -2135,7 +2150,7 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 	rc = do_ioctl(sdev, (void *)&buf);
 	if (likely(!rc))
 		if (unlikely(copy_to_user(arg, &buf, size))) {
-			dev_err(dev, "%s: copy_to_user() fail! "
+			dev_err(dev, "%s: copy_to_user() fail "
 				"size=%lu cmd=%d (%s) arg=%p\n",
 				__func__, size, cmd, decode_ioctl(cmd), arg);
 			rc = -EFAULT;
diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c
index 90c5d7f5278e..8fcc804dbef9 100644
--- a/drivers/scsi/cxlflash/vlun.c
+++ b/drivers/scsi/cxlflash/vlun.c
@@ -66,8 +66,8 @@ static int ba_init(struct ba_lun *ba_lun)
 	int last_word_underflow = 0;
 	u64 *lam;
 
-	pr_debug("%s: Initializing LUN: lun_id = %llX, "
-		 "ba_lun->lsize = %lX, ba_lun->au_size = %lX\n",
+	pr_debug("%s: Initializing LUN: lun_id=%016llx "
+		 "ba_lun->lsize=%lx ba_lun->au_size=%lX\n",
 		__func__, ba_lun->lun_id, ba_lun->lsize, ba_lun->au_size);
 
 	/* Calculate bit map size */
@@ -80,7 +80,7 @@ static int ba_init(struct ba_lun *ba_lun)
 	/* Allocate lun information container */
 	bali = kzalloc(sizeof(struct ba_lun_info), GFP_KERNEL);
 	if (unlikely(!bali)) {
-		pr_err("%s: Failed to allocate lun_info for lun_id %llX\n",
+		pr_err("%s: Failed to allocate lun_info lun_id=%016llx\n",
 		       __func__, ba_lun->lun_id);
 		return -ENOMEM;
 	}
@@ -96,7 +96,7 @@ static int ba_init(struct ba_lun *ba_lun)
 				      GFP_KERNEL);
 	if (unlikely(!bali->lun_alloc_map)) {
 		pr_err("%s: Failed to allocate lun allocation map: "
-		       "lun_id = %llX\n", __func__, ba_lun->lun_id);
+		       "lun_id=%016llx\n", __func__, ba_lun->lun_id);
 		kfree(bali);
 		return -ENOMEM;
 	}
@@ -125,7 +125,7 @@ static int ba_init(struct ba_lun *ba_lun)
 	bali->aun_clone_map = kzalloc((bali->total_aus * sizeof(u8)),
 				      GFP_KERNEL);
 	if (unlikely(!bali->aun_clone_map)) {
-		pr_err("%s: Failed to allocate clone map: lun_id = %llX\n",
+		pr_err("%s: Failed to allocate clone map: lun_id=%016llx\n",
 		       __func__, ba_lun->lun_id);
 		kfree(bali->lun_alloc_map);
 		kfree(bali);
@@ -136,7 +136,7 @@ static int ba_init(struct ba_lun *ba_lun)
 	ba_lun->ba_lun_handle = bali;
 
 	pr_debug("%s: Successfully initialized the LUN: "
-		 "lun_id = %llX, bitmap size = %X, free_aun_cnt = %llX\n",
+		 "lun_id=%016llx bitmap size=%x, free_aun_cnt=%llx\n",
 		__func__, ba_lun->lun_id, bali->lun_bmap_size,
 		bali->free_aun_cnt);
 	return 0;
@@ -165,10 +165,9 @@ static int find_free_range(u32 low,
 			num_bits = (sizeof(*lam) * BITS_PER_BYTE);
 			bit_pos = find_first_bit(lam, num_bits);
 
-			pr_devel("%s: Found free bit %llX in LUN "
-				 "map entry %llX at bitmap index = %X\n",
-				 __func__, bit_pos, bali->lun_alloc_map[i],
-				 i);
+			pr_devel("%s: Found free bit %llu in LUN "
+				 "map entry %016llx at bitmap index = %d\n",
+				 __func__, bit_pos, bali->lun_alloc_map[i], i);
 
 			*bit_word = i;
 			bali->free_aun_cnt--;
@@ -194,11 +193,11 @@ static u64 ba_alloc(struct ba_lun *ba_lun)
 	bali = ba_lun->ba_lun_handle;
 
 	pr_debug("%s: Received block allocation request: "
-		 "lun_id = %llX, free_aun_cnt = %llX\n",
+		 "lun_id=%016llx free_aun_cnt=%llx\n",
 		 __func__, ba_lun->lun_id, bali->free_aun_cnt);
 
 	if (bali->free_aun_cnt == 0) {
-		pr_debug("%s: No space left on LUN: lun_id = %llX\n",
+		pr_debug("%s: No space left on LUN: lun_id=%016llx\n",
 			 __func__, ba_lun->lun_id);
 		return -1ULL;
 	}
@@ -212,7 +211,7 @@ static u64 ba_alloc(struct ba_lun *ba_lun)
 					  bali, &bit_word);
 		if (bit_pos == -1) {
 			pr_debug("%s: Could not find an allocation unit on LUN:"
-				 " lun_id = %llX\n", __func__, ba_lun->lun_id);
+				 " lun_id=%016llx\n", __func__, ba_lun->lun_id);
 			return -1ULL;
 		}
 	}
@@ -223,8 +222,8 @@ static u64 ba_alloc(struct ba_lun *ba_lun)
 	else
 		bali->free_curr_idx = bit_word;
 
-	pr_debug("%s: Allocating AU number %llX, on lun_id %llX, "
-		 "free_aun_cnt = %llX\n", __func__,
+	pr_debug("%s: Allocating AU number=%llx lun_id=%016llx "
+		 "free_aun_cnt=%llx\n", __func__,
 		 ((bit_word * BITS_PER_LONG) + bit_pos), ba_lun->lun_id,
 		 bali->free_aun_cnt);
 
@@ -266,18 +265,18 @@ static int ba_free(struct ba_lun *ba_lun, u64 to_free)
 	bali = ba_lun->ba_lun_handle;
 
 	if (validate_alloc(bali, to_free)) {
-		pr_debug("%s: The AUN %llX is not allocated on lun_id %llX\n",
+		pr_debug("%s: AUN %llx is not allocated on lun_id=%016llx\n",
 			 __func__, to_free, ba_lun->lun_id);
 		return -1;
 	}
 
-	pr_debug("%s: Received a request to free AU %llX on lun_id %llX, "
-		 "free_aun_cnt = %llX\n", __func__, to_free, ba_lun->lun_id,
+	pr_debug("%s: Received a request to free AU=%llx lun_id=%016llx "
+		 "free_aun_cnt=%llx\n", __func__, to_free, ba_lun->lun_id,
 		 bali->free_aun_cnt);
 
 	if (bali->aun_clone_map[to_free] > 0) {
-		pr_debug("%s: AUN %llX on lun_id %llX has been cloned. Clone "
-			 "count = %X\n", __func__, to_free, ba_lun->lun_id,
+		pr_debug("%s: AUN %llx lun_id=%016llx cloned. Clone count=%x\n",
+			 __func__, to_free, ba_lun->lun_id,
 			 bali->aun_clone_map[to_free]);
 		bali->aun_clone_map[to_free]--;
 		return 0;
@@ -294,8 +293,8 @@ static int ba_free(struct ba_lun *ba_lun, u64 to_free)
 	else if (idx > bali->free_high_idx)
 		bali->free_high_idx = idx;
 
-	pr_debug("%s: Successfully freed AU at bit_pos %X, bit map index %X on "
-		 "lun_id %llX, free_aun_cnt = %llX\n", __func__, bit_pos, idx,
+	pr_debug("%s: Successfully freed AU bit_pos=%x bit map index=%x "
+		 "lun_id=%016llx free_aun_cnt=%llx\n", __func__, bit_pos, idx,
 		 ba_lun->lun_id, bali->free_aun_cnt);
 
 	return 0;
@@ -313,16 +312,16 @@ static int ba_clone(struct ba_lun *ba_lun, u64 to_clone)
 	struct ba_lun_info *bali = ba_lun->ba_lun_handle;
 
 	if (validate_alloc(bali, to_clone)) {
-		pr_debug("%s: AUN %llX is not allocated on lun_id %llX\n",
+		pr_debug("%s: AUN=%llx not allocated on lun_id=%016llx\n",
 			 __func__, to_clone, ba_lun->lun_id);
 		return -1;
 	}
 
-	pr_debug("%s: Received a request to clone AUN %llX on lun_id %llX\n",
+	pr_debug("%s: Received a request to clone AUN %llx on lun_id=%016llx\n",
 		 __func__, to_clone, ba_lun->lun_id);
 
 	if (bali->aun_clone_map[to_clone] == MAX_AUN_CLONE_CNT) {
-		pr_debug("%s: AUN %llX on lun_id %llX hit max clones already\n",
+		pr_debug("%s: AUN %llx on lun_id=%016llx hit max clones already\n",
 			 __func__, to_clone, ba_lun->lun_id);
 		return -1;
 	}
@@ -433,7 +432,7 @@ static int write_same16(struct scsi_device *sdev,
 	u64 offset = lba;
 	int left = nblks;
 	u32 to = sdev->request_queue->rq_timeout;
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
@@ -459,7 +458,7 @@ static int write_same16(struct scsi_device *sdev,
 		down_read(&cfg->ioctl_rwsem);
 		rc = check_state(cfg);
 		if (rc) {
-			dev_err(dev, "%s: Failed state! result=0x08%X\n",
+			dev_err(dev, "%s: Failed state result=%08x\n",
 				__func__, result);
 			rc = -ENODEV;
 			goto out;
@@ -467,7 +466,7 @@ static int write_same16(struct scsi_device *sdev,
 
 		if (result) {
 			dev_err_ratelimited(dev, "%s: command failed for "
-					    "offset %lld result=0x%x\n",
+					    "offset=%lld result=%08x\n",
 					    __func__, offset, result);
 			rc = -EIO;
 			goto out;
@@ -480,7 +479,7 @@ out:
 	kfree(cmd_buf);
 	kfree(scsi_cmd);
 	kfree(sense_buf);
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -508,6 +507,8 @@ static int grow_lxt(struct afu *afu,
 		    struct sisl_rht_entry *rhte,
 		    u64 *new_size)
 {
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_lxt_entry *lxt = NULL, *lxt_old = NULL;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -527,7 +528,8 @@ static int grow_lxt(struct afu *afu,
 	mutex_lock(&blka->mutex);
 	av_size = ba_space(&blka->ba_lun);
 	if (unlikely(av_size <= 0)) {
-		pr_debug("%s: ba_space error: av_size %d\n", __func__, av_size);
+		dev_dbg(dev, "%s: ba_space error av_size=%d\n",
+			__func__, av_size);
 		mutex_unlock(&blka->mutex);
 		rc = -ENOSPC;
 		goto out;
@@ -568,8 +570,8 @@ static int grow_lxt(struct afu *afu,
 		 */
 		aun = ba_alloc(&blka->ba_lun);
 		if ((aun == -1ULL) || (aun >= blka->nchunk))
-			pr_debug("%s: ba_alloc error: allocated chunk# %llX, "
-				 "max %llX\n", __func__, aun, blka->nchunk - 1);
+			dev_dbg(dev, "%s: ba_alloc error allocated chunk=%llu "
+				"max=%llu\n", __func__, aun, blka->nchunk - 1);
 
 		/* select both ports, use r/w perms from RHT */
 		lxt[i].rlba_base = ((aun << MC_CHUNK_SHIFT) |
@@ -599,7 +601,7 @@ static int grow_lxt(struct afu *afu,
 		kfree(lxt_old);
 	*new_size = my_new_size;
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -621,6 +623,8 @@ static int shrink_lxt(struct afu *afu,
 		      struct ctx_info *ctxi,
 		      u64 *new_size)
 {
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_lxt_entry *lxt, *lxt_old;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -706,7 +710,7 @@ static int shrink_lxt(struct afu *afu,
 		kfree(lxt_old);
 	*new_size = my_new_size;
 out:
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -728,7 +732,8 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 			  struct ctx_info *ctxi,
 			  struct dk_cxlflash_resize *resize)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
 	struct afu *afu = cfg->afu;
@@ -751,13 +756,13 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 	nsectors = (resize->req_size * CXLFLASH_BLOCK_SIZE) / gli->blk_len;
 	new_size = DIV_ROUND_UP(nsectors, MC_CHUNK_SIZE);
 
-	pr_debug("%s: ctxid=%llu rhndl=0x%llx, req_size=0x%llx,"
-		 "new_size=%llx\n", __func__, ctxid, resize->rsrc_handle,
-		 resize->req_size, new_size);
+	dev_dbg(dev, "%s: ctxid=%llu rhndl=%llu req_size=%llu new_size=%llu\n",
+		__func__, ctxid, resize->rsrc_handle, resize->req_size,
+		new_size);
 
 	if (unlikely(gli->mode != MODE_VIRTUAL)) {
-		pr_debug("%s: LUN mode does not support resize! (%d)\n",
-			 __func__, gli->mode);
+		dev_dbg(dev, "%s: LUN mode does not support resize mode=%d\n",
+			__func__, gli->mode);
 		rc = -EINVAL;
 		goto out;
 
@@ -766,7 +771,8 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 	if (!ctxi) {
 		ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK);
 		if (unlikely(!ctxi)) {
-			pr_debug("%s: Bad context! (%llu)\n", __func__, ctxid);
+			dev_dbg(dev, "%s: Bad context ctxid=%llu\n",
+				__func__, ctxid);
 			rc = -EINVAL;
 			goto out;
 		}
@@ -776,7 +782,8 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 
 	rhte = get_rhte(ctxi, rhndl, lli);
 	if (unlikely(!rhte)) {
-		pr_debug("%s: Bad resource handle! (%u)\n", __func__, rhndl);
+		dev_dbg(dev, "%s: Bad resource handle rhndl=%u\n",
+			__func__, rhndl);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -794,8 +801,8 @@ int _cxlflash_vlun_resize(struct scsi_device *sdev,
 out:
 	if (put_ctx)
 		put_context(ctxi);
-	pr_debug("%s: resized to %lld returning rc=%d\n",
-		 __func__, resize->last_lba, rc);
+	dev_dbg(dev, "%s: resized to %llu returning rc=%d\n",
+		__func__, resize->last_lba, rc);
 	return rc;
 }
 
@@ -815,6 +822,7 @@ void cxlflash_restore_luntable(struct cxlflash_cfg *cfg)
 	u32 chan;
 	u32 lind;
 	struct afu *afu = cfg->afu;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_global_map __iomem *agm = &afu->afu_map->global;
 
 	mutex_lock(&global.mutex);
@@ -828,15 +836,15 @@ void cxlflash_restore_luntable(struct cxlflash_cfg *cfg)
 		if (lli->port_sel == BOTH_PORTS) {
 			writeq_be(lli->lun_id[0], &agm->fc_port[0][lind]);
 			writeq_be(lli->lun_id[1], &agm->fc_port[1][lind]);
-			pr_debug("%s: Virtual LUN on slot %d  id0=%llx, "
-				 "id1=%llx\n", __func__, lind,
-				 lli->lun_id[0], lli->lun_id[1]);
+			dev_dbg(dev, "%s: Virtual LUN on slot %d  id0=%llx "
+				"id1=%llx\n", __func__, lind,
+				lli->lun_id[0], lli->lun_id[1]);
 		} else {
 			chan = PORT2CHAN(lli->port_sel);
 			writeq_be(lli->lun_id[chan], &agm->fc_port[chan][lind]);
-			pr_debug("%s: Virtual LUN on slot %d chan=%d, "
-				 "id=%llx\n", __func__, lind, chan,
-				 lli->lun_id[chan]);
+			dev_dbg(dev, "%s: Virtual LUN on slot %d chan=%d "
+				"id=%llx\n", __func__, lind, chan,
+				lli->lun_id[chan]);
 		}
 	}
 
@@ -860,6 +868,7 @@ static int init_luntable(struct cxlflash_cfg *cfg, struct llun_info *lli)
 	u32 lind;
 	int rc = 0;
 	struct afu *afu = cfg->afu;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_global_map __iomem *agm = &afu->afu_map->global;
 
 	mutex_lock(&global.mutex);
@@ -882,8 +891,8 @@ static int init_luntable(struct cxlflash_cfg *cfg, struct llun_info *lli)
 		writeq_be(lli->lun_id[0], &agm->fc_port[0][lind]);
 		writeq_be(lli->lun_id[1], &agm->fc_port[1][lind]);
 		cfg->promote_lun_index++;
-		pr_debug("%s: Virtual LUN on slot %d  id0=%llx, id1=%llx\n",
-			 __func__, lind, lli->lun_id[0], lli->lun_id[1]);
+		dev_dbg(dev, "%s: Virtual LUN on slot %d  id0=%llx id1=%llx\n",
+			__func__, lind, lli->lun_id[0], lli->lun_id[1]);
 	} else {
 		/*
 		 * If this LUN is visible only from one port, we will put
@@ -898,14 +907,14 @@ static int init_luntable(struct cxlflash_cfg *cfg, struct llun_info *lli)
 		lind = lli->lun_index = cfg->last_lun_index[chan];
 		writeq_be(lli->lun_id[chan], &agm->fc_port[chan][lind]);
 		cfg->last_lun_index[chan]--;
-		pr_debug("%s: Virtual LUN on slot %d  chan=%d, id=%llx\n",
-			 __func__, lind, chan, lli->lun_id[chan]);
+		dev_dbg(dev, "%s: Virtual LUN on slot %d  chan=%d id=%llx\n",
+			__func__, lind, chan, lli->lun_id[chan]);
 	}
 
 	lli->in_table = true;
 out:
 	mutex_unlock(&global.mutex);
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
 
@@ -923,7 +932,7 @@ out:
  */
 int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
 	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
@@ -942,14 +951,14 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 	struct ctx_info *ctxi = NULL;
 	struct sisl_rht_entry *rhte = NULL;
 
-	pr_debug("%s: ctxid=%llu ls=0x%llx\n", __func__, ctxid, lun_size);
+	dev_dbg(dev, "%s: ctxid=%llu ls=%llu\n", __func__, ctxid, lun_size);
 
 	/* Setup the LUNs block allocator on first call */
 	mutex_lock(&gli->mutex);
 	if (gli->mode == MODE_NONE) {
 		rc = init_vlun(lli);
 		if (rc) {
-			dev_err(dev, "%s: call to init_vlun failed rc=%d!\n",
+			dev_err(dev, "%s: init_vlun failed rc=%d\n",
 				__func__, rc);
 			rc = -ENOMEM;
 			goto err0;
@@ -958,29 +967,28 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 
 	rc = cxlflash_lun_attach(gli, MODE_VIRTUAL, true);
 	if (unlikely(rc)) {
-		dev_err(dev, "%s: Failed to attach to LUN! (VIRTUAL)\n",
-			__func__);
+		dev_err(dev, "%s: Failed attach to LUN (VIRTUAL)\n", __func__);
 		goto err0;
 	}
 	mutex_unlock(&gli->mutex);
 
 	rc = init_luntable(cfg, lli);
 	if (rc) {
-		dev_err(dev, "%s: call to init_luntable failed rc=%d!\n",
-			__func__, rc);
+		dev_err(dev, "%s: init_luntable failed rc=%d\n", __func__, rc);
 		goto err1;
 	}
 
 	ctxi = get_context(cfg, rctxid, lli, 0);
 	if (unlikely(!ctxi)) {
-		dev_err(dev, "%s: Bad context! (%llu)\n", __func__, ctxid);
+		dev_err(dev, "%s: Bad context ctxid=%llu\n", __func__, ctxid);
 		rc = -EINVAL;
 		goto err1;
 	}
 
 	rhte = rhte_checkout(ctxi, lli);
 	if (unlikely(!rhte)) {
-		dev_err(dev, "%s: too many opens for this context\n", __func__);
+		dev_err(dev, "%s: too many opens ctxid=%llu\n",
+			__func__, ctxid);
 		rc = -EMFILE;	/* too many opens  */
 		goto err1;
 	}
@@ -996,7 +1004,7 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 	resize.rsrc_handle = rsrc_handle;
 	rc = _cxlflash_vlun_resize(sdev, ctxi, &resize);
 	if (rc) {
-		dev_err(dev, "%s: resize failed rc %d\n", __func__, rc);
+		dev_err(dev, "%s: resize failed rc=%d\n", __func__, rc);
 		goto err2;
 	}
 	last_lba = resize.last_lba;
@@ -1013,8 +1021,8 @@ int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg)
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
-	pr_debug("%s: returning handle 0x%llx rc=%d llba %lld\n",
-		 __func__, rsrc_handle, rc, last_lba);
+	dev_dbg(dev, "%s: returning handle=%llu rc=%d llba=%llu\n",
+		__func__, rsrc_handle, rc, last_lba);
 	return rc;
 
 err2:
@@ -1047,6 +1055,8 @@ static int clone_lxt(struct afu *afu,
 		     struct sisl_rht_entry *rhte,
 		     struct sisl_rht_entry *rhte_src)
 {
+	struct cxlflash_cfg *cfg = afu->parent;
+	struct device *dev = &cfg->dev->dev;
 	struct sisl_lxt_entry *lxt;
 	u32 ngrps;
 	u64 aun;		/* chunk# allocated by block allocator */
@@ -1101,7 +1111,7 @@ static int clone_lxt(struct afu *afu,
 
 	cxlflash_afu_sync(afu, ctxid, rhndl, AFU_LW_SYNC);
 
-	pr_debug("%s: returning\n", __func__);
+	dev_dbg(dev, "%s: returning\n", __func__);
 	return 0;
 }
 
@@ -1120,7 +1130,8 @@ static int clone_lxt(struct afu *afu,
 int cxlflash_disk_clone(struct scsi_device *sdev,
 			struct dk_cxlflash_clone *clone)
 {
-	struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata;
+	struct cxlflash_cfg *cfg = shost_priv(sdev->host);
+	struct device *dev = &cfg->dev->dev;
 	struct llun_info *lli = sdev->hostdata;
 	struct glun_info *gli = lli->parent;
 	struct blka *blka = &gli->blka;
@@ -1140,8 +1151,8 @@ int cxlflash_disk_clone(struct scsi_device *sdev,
 	bool found;
 	LIST_HEAD(sidecar);
 
-	pr_debug("%s: ctxid_src=%llu ctxid_dst=%llu\n",
-		 __func__, ctxid_src, ctxid_dst);
+	dev_dbg(dev, "%s: ctxid_src=%llu ctxid_dst=%llu\n",
+		__func__, ctxid_src, ctxid_dst);
 
 	/* Do not clone yourself */
 	if (unlikely(rctxid_src == rctxid_dst)) {
@@ -1151,16 +1162,16 @@ int cxlflash_disk_clone(struct scsi_device *sdev,
 
 	if (unlikely(gli->mode != MODE_VIRTUAL)) {
 		rc = -EINVAL;
-		pr_debug("%s: Clone not supported on physical LUNs! (%d)\n",
-			 __func__, gli->mode);
+		dev_dbg(dev, "%s: Only supported on virtual LUNs mode=%u\n",
+			__func__, gli->mode);
 		goto out;
 	}
 
 	ctxi_src = get_context(cfg, rctxid_src, lli, CTX_CTRL_CLONE);
 	ctxi_dst = get_context(cfg, rctxid_dst, lli, 0);
 	if (unlikely(!ctxi_src || !ctxi_dst)) {
-		pr_debug("%s: Bad context! (%llu,%llu)\n", __func__,
-			 ctxid_src, ctxid_dst);
+		dev_dbg(dev, "%s: Bad context ctxid_src=%llu ctxid_dst=%llu\n",
+			__func__, ctxid_src, ctxid_dst);
 		rc = -EINVAL;
 		goto out;
 	}
@@ -1185,8 +1196,8 @@ int cxlflash_disk_clone(struct scsi_device *sdev,
 			lun_access_dst = kzalloc(sizeof(*lun_access_dst),
 						 GFP_KERNEL);
 			if (unlikely(!lun_access_dst)) {
-				pr_err("%s: Unable to allocate lun_access!\n",
-				       __func__);
+				dev_err(dev, "%s: lun_access allocation fail\n",
+					__func__);
 				rc = -ENOMEM;
 				goto out;
 			}
@@ -1197,7 +1208,7 @@ int cxlflash_disk_clone(struct scsi_device *sdev,
 	}
 
 	if (unlikely(!ctxi_src->rht_out)) {
-		pr_debug("%s: Nothing to clone!\n", __func__);
+		dev_dbg(dev, "%s: Nothing to clone\n", __func__);
 		goto out_success;
 	}
 
@@ -1256,7 +1267,7 @@ out:
 		put_context(ctxi_src);
 	if (ctxi_dst)
 		put_context(ctxi_dst);
-	pr_debug("%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 
 err:
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index 5b80746980b8..4a7679f6c73d 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -88,12 +88,6 @@ struct clariion_dh_data {
 	 */
 	unsigned char buffer[CLARIION_BUFFER_SIZE];
 	/*
-	 * SCSI sense buffer for commands -- assumes serial issuance
-	 * and completion sequence of all commands for same multipath.
-	 */
-	unsigned char sense[SCSI_SENSE_BUFFERSIZE];
-	unsigned int senselen;
-	/*
 	 * LUN state
 	 */
 	int lun_state;
@@ -116,44 +110,38 @@ struct clariion_dh_data {
 /*
  * Parse MODE_SELECT cmd reply.
  */
-static int trespass_endio(struct scsi_device *sdev, char *sense)
+static int trespass_endio(struct scsi_device *sdev,
+			  struct scsi_sense_hdr *sshdr)
 {
 	int err = SCSI_DH_IO;
-	struct scsi_sense_hdr sshdr;
-
-	if (!scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, &sshdr)) {
-		sdev_printk(KERN_ERR, sdev, "%s: Found valid sense data 0x%2x, "
-			    "0x%2x, 0x%2x while sending CLARiiON trespass "
-			    "command.\n", CLARIION_NAME, sshdr.sense_key,
-			    sshdr.asc, sshdr.ascq);
 
-		if ((sshdr.sense_key == 0x05) && (sshdr.asc == 0x04) &&
-		     (sshdr.ascq == 0x00)) {
-			/*
-			 * Array based copy in progress -- do not send
-			 * mode_select or copy will be aborted mid-stream.
-			 */
-			sdev_printk(KERN_INFO, sdev, "%s: Array Based Copy in "
-				    "progress while sending CLARiiON trespass "
-				    "command.\n", CLARIION_NAME);
-			err = SCSI_DH_DEV_TEMP_BUSY;
-		} else if ((sshdr.sense_key == 0x02) && (sshdr.asc == 0x04) &&
-			    (sshdr.ascq == 0x03)) {
-			/*
-			 * LUN Not Ready - Manual Intervention Required
-			 * indicates in-progress ucode upgrade (NDU).
-			 */
-			sdev_printk(KERN_INFO, sdev, "%s: Detected in-progress "
-				    "ucode upgrade NDU operation while sending "
-				    "CLARiiON trespass command.\n", CLARIION_NAME);
-			err = SCSI_DH_DEV_TEMP_BUSY;
-		} else
-			err = SCSI_DH_DEV_FAILED;
-	} else {
-		sdev_printk(KERN_INFO, sdev,
-			    "%s: failed to send MODE SELECT, no sense available\n",
-			    CLARIION_NAME);
-	}
+	sdev_printk(KERN_ERR, sdev, "%s: Found valid sense data 0x%2x, "
+		    "0x%2x, 0x%2x while sending CLARiiON trespass "
+		    "command.\n", CLARIION_NAME, sshdr->sense_key,
+		    sshdr->asc, sshdr->ascq);
+
+	if (sshdr->sense_key == 0x05 && sshdr->asc == 0x04 &&
+	    sshdr->ascq == 0x00) {
+		/*
+		 * Array based copy in progress -- do not send
+		 * mode_select or copy will be aborted mid-stream.
+		 */
+		sdev_printk(KERN_INFO, sdev, "%s: Array Based Copy in "
+			    "progress while sending CLARiiON trespass "
+			    "command.\n", CLARIION_NAME);
+		err = SCSI_DH_DEV_TEMP_BUSY;
+	} else if (sshdr->sense_key == 0x02 && sshdr->asc == 0x04 &&
+		   sshdr->ascq == 0x03) {
+		/*
+		 * LUN Not Ready - Manual Intervention Required
+		 * indicates in-progress ucode upgrade (NDU).
+		 */
+		sdev_printk(KERN_INFO, sdev, "%s: Detected in-progress "
+			    "ucode upgrade NDU operation while sending "
+			    "CLARiiON trespass command.\n", CLARIION_NAME);
+		err = SCSI_DH_DEV_TEMP_BUSY;
+	} else
+		err = SCSI_DH_DEV_FAILED;
 	return err;
 }
 
@@ -257,103 +245,15 @@ out:
 	return sp_model;
 }
 
-/*
- * Get block request for REQ_BLOCK_PC command issued to path.  Currently
- * limited to MODE_SELECT (trespass) and INQUIRY (VPD page 0xC0) commands.
- *
- * Uses data and sense buffers in hardware handler context structure and
- * assumes serial servicing of commands, both issuance and completion.
- */
-static struct request *get_req(struct scsi_device *sdev, int cmd,
-				unsigned char *buffer)
-{
-	struct request *rq;
-	int len = 0;
-
-	rq = blk_get_request(sdev->request_queue,
-			(cmd != INQUIRY) ? WRITE : READ, GFP_NOIO);
-	if (IS_ERR(rq)) {
-		sdev_printk(KERN_INFO, sdev, "get_req: blk_get_request failed");
-		return NULL;
-	}
-
-	blk_rq_set_block_pc(rq);
-	rq->cmd_len = COMMAND_SIZE(cmd);
-	rq->cmd[0] = cmd;
-
-	switch (cmd) {
-	case MODE_SELECT:
-		len = sizeof(short_trespass);
-		rq->cmd[1] = 0x10;
-		rq->cmd[4] = len;
-		break;
-	case MODE_SELECT_10:
-		len = sizeof(long_trespass);
-		rq->cmd[1] = 0x10;
-		rq->cmd[8] = len;
-		break;
-	case INQUIRY:
-		len = CLARIION_BUFFER_SIZE;
-		rq->cmd[4] = len;
-		memset(buffer, 0, len);
-		break;
-	default:
-		BUG_ON(1);
-		break;
-	}
-
-	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
-			 REQ_FAILFAST_DRIVER;
-	rq->timeout = CLARIION_TIMEOUT;
-	rq->retries = CLARIION_RETRIES;
-
-	if (blk_rq_map_kern(rq->q, rq, buffer, len, GFP_NOIO)) {
-		blk_put_request(rq);
-		return NULL;
-	}
-
-	return rq;
-}
-
-static int send_inquiry_cmd(struct scsi_device *sdev, int page,
-			    struct clariion_dh_data *csdev)
-{
-	struct request *rq = get_req(sdev, INQUIRY, csdev->buffer);
-	int err;
-
-	if (!rq)
-		return SCSI_DH_RES_TEMP_UNAVAIL;
-
-	rq->sense = csdev->sense;
-	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
-	rq->sense_len = csdev->senselen = 0;
-
-	rq->cmd[0] = INQUIRY;
-	if (page != 0) {
-		rq->cmd[1] = 1;
-		rq->cmd[2] = page;
-	}
-	err = blk_execute_rq(sdev->request_queue, NULL, rq, 1);
-	if (err == -EIO) {
-		sdev_printk(KERN_INFO, sdev,
-			    "%s: failed to send %s INQUIRY: %x\n",
-			    CLARIION_NAME, page?"EVPD":"standard",
-			    rq->errors);
-		csdev->senselen = rq->sense_len;
-		err = SCSI_DH_IO;
-	}
-
-	blk_put_request(rq);
-
-	return err;
-}
-
 static int send_trespass_cmd(struct scsi_device *sdev,
 			    struct clariion_dh_data *csdev)
 {
-	struct request *rq;
 	unsigned char *page22;
-	int err, len, cmd;
+	unsigned char cdb[COMMAND_SIZE(MODE_SELECT)];
+	int err, res = SCSI_DH_OK, len;
+	struct scsi_sense_hdr sshdr;
+	u64 req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+		REQ_FAILFAST_DRIVER;
 
 	if (csdev->flags & CLARIION_SHORT_TRESPASS) {
 		page22 = short_trespass;
@@ -361,40 +261,37 @@ static int send_trespass_cmd(struct scsi_device *sdev,
 			/* Set Honor Reservations bit */
 			page22[6] |= 0x80;
 		len = sizeof(short_trespass);
-		cmd = MODE_SELECT;
+		cdb[0] = MODE_SELECT;
+		cdb[1] = 0x10;
+		cdb[4] = len;
 	} else {
 		page22 = long_trespass;
 		if (!(csdev->flags & CLARIION_HONOR_RESERVATIONS))
 			/* Set Honor Reservations bit */
 			page22[10] |= 0x80;
 		len = sizeof(long_trespass);
-		cmd = MODE_SELECT_10;
+		cdb[0] = MODE_SELECT_10;
+		cdb[8] = len;
 	}
 	BUG_ON((len > CLARIION_BUFFER_SIZE));
 	memcpy(csdev->buffer, page22, len);
 
-	rq = get_req(sdev, cmd, csdev->buffer);
-	if (!rq)
-		return SCSI_DH_RES_TEMP_UNAVAIL;
-
-	rq->sense = csdev->sense;
-	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
-	rq->sense_len = csdev->senselen = 0;
-
-	err = blk_execute_rq(sdev->request_queue, NULL, rq, 1);
-	if (err == -EIO) {
-		if (rq->sense_len) {
-			err = trespass_endio(sdev, csdev->sense);
-		} else {
+	err = scsi_execute_req_flags(sdev, cdb, DMA_TO_DEVICE,
+				     csdev->buffer, len, &sshdr,
+				     CLARIION_TIMEOUT * HZ, CLARIION_RETRIES,
+				     NULL, req_flags, 0);
+	if (err) {
+		if (scsi_sense_valid(&sshdr))
+			res = trespass_endio(sdev, &sshdr);
+		else {
 			sdev_printk(KERN_INFO, sdev,
 				    "%s: failed to send MODE SELECT: %x\n",
-				    CLARIION_NAME, rq->errors);
+				    CLARIION_NAME, err);
+			res = SCSI_DH_IO;
 		}
 	}
 
-	blk_put_request(rq);
-
-	return err;
+	return res;
 }
 
 static int clariion_check_sense(struct scsi_device *sdev,
@@ -464,21 +361,7 @@ static int clariion_std_inquiry(struct scsi_device *sdev,
 	int err;
 	char *sp_model;
 
-	err = send_inquiry_cmd(sdev, 0, csdev);
-	if (err != SCSI_DH_OK && csdev->senselen) {
-		struct scsi_sense_hdr sshdr;
-
-		if (scsi_normalize_sense(csdev->sense, SCSI_SENSE_BUFFERSIZE,
-					 &sshdr)) {
-			sdev_printk(KERN_ERR, sdev, "%s: INQUIRY sense code "
-				    "%02x/%02x/%02x\n", CLARIION_NAME,
-				    sshdr.sense_key, sshdr.asc, sshdr.ascq);
-		}
-		err = SCSI_DH_IO;
-		goto out;
-	}
-
-	sp_model = parse_sp_model(sdev, csdev->buffer);
+	sp_model = parse_sp_model(sdev, sdev->inquiry);
 	if (!sp_model) {
 		err = SCSI_DH_DEV_UNSUPP;
 		goto out;
@@ -500,30 +383,12 @@ out:
 static int clariion_send_inquiry(struct scsi_device *sdev,
 				 struct clariion_dh_data *csdev)
 {
-	int err, retry = CLARIION_RETRIES;
-
-retry:
-	err = send_inquiry_cmd(sdev, 0xC0, csdev);
-	if (err != SCSI_DH_OK && csdev->senselen) {
-		struct scsi_sense_hdr sshdr;
-
-		err = scsi_normalize_sense(csdev->sense, SCSI_SENSE_BUFFERSIZE,
-					   &sshdr);
-		if (!err)
-			return SCSI_DH_IO;
-
-		err = clariion_check_sense(sdev, &sshdr);
-		if (retry > 0 && err == ADD_TO_MLQUEUE) {
-			retry--;
-			goto retry;
-		}
-		sdev_printk(KERN_ERR, sdev, "%s: INQUIRY sense code "
-			    "%02x/%02x/%02x\n", CLARIION_NAME,
-			      sshdr.sense_key, sshdr.asc, sshdr.ascq);
-		err = SCSI_DH_IO;
-	} else {
+	int err = SCSI_DH_IO;
+
+	if (!scsi_get_vpd_page(sdev, 0xC0, csdev->buffer,
+			       CLARIION_BUFFER_SIZE))
 		err = parse_sp_info_reply(sdev, csdev);
-	}
+
 	return err;
 }
 
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index 308e87195dc1..be43c940636d 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -38,13 +38,10 @@
 #define HP_SW_PATH_PASSIVE		1
 
 struct hp_sw_dh_data {
-	unsigned char sense[SCSI_SENSE_BUFFERSIZE];
 	int path_state;
 	int retries;
 	int retry_cnt;
 	struct scsi_device *sdev;
-	activate_complete	callback_fn;
-	void			*callback_data;
 };
 
 static int hp_sw_start_stop(struct hp_sw_dh_data *);
@@ -56,43 +53,34 @@ static int hp_sw_start_stop(struct hp_sw_dh_data *);
  *
  * Returns SCSI_DH_DEV_OFFLINED if the sdev is on the passive path
  */
-static int tur_done(struct scsi_device *sdev, unsigned char *sense)
+static int tur_done(struct scsi_device *sdev, struct hp_sw_dh_data *h,
+		    struct scsi_sense_hdr *sshdr)
 {
-	struct scsi_sense_hdr sshdr;
-	int ret;
+	int ret = SCSI_DH_IO;
 
-	ret = scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, &sshdr);
-	if (!ret) {
-		sdev_printk(KERN_WARNING, sdev,
-			    "%s: sending tur failed, no sense available\n",
-			    HP_SW_NAME);
-		ret = SCSI_DH_IO;
-		goto done;
-	}
-	switch (sshdr.sense_key) {
+	switch (sshdr->sense_key) {
 	case UNIT_ATTENTION:
 		ret = SCSI_DH_IMM_RETRY;
 		break;
 	case NOT_READY:
-		if ((sshdr.asc == 0x04) && (sshdr.ascq == 2)) {
+		if (sshdr->asc == 0x04 && sshdr->ascq == 2) {
 			/*
 			 * LUN not ready - Initialization command required
 			 *
 			 * This is the passive path
 			 */
-			ret = SCSI_DH_DEV_OFFLINED;
+			h->path_state = HP_SW_PATH_PASSIVE;
+			ret = SCSI_DH_OK;
 			break;
 		}
 		/* Fallthrough */
 	default:
 		sdev_printk(KERN_WARNING, sdev,
 			   "%s: sending tur failed, sense %x/%x/%x\n",
-			   HP_SW_NAME, sshdr.sense_key, sshdr.asc,
-			   sshdr.ascq);
+			   HP_SW_NAME, sshdr->sense_key, sshdr->asc,
+			   sshdr->ascq);
 		break;
 	}
-
-done:
 	return ret;
 }
 
@@ -105,131 +93,36 @@ done:
  */
 static int hp_sw_tur(struct scsi_device *sdev, struct hp_sw_dh_data *h)
 {
-	struct request *req;
-	int ret;
+	unsigned char cmd[6] = { TEST_UNIT_READY };
+	struct scsi_sense_hdr sshdr;
+	int ret = SCSI_DH_OK, res;
+	u64 req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+		REQ_FAILFAST_DRIVER;
 
 retry:
-	req = blk_get_request(sdev->request_queue, WRITE, GFP_NOIO);
-	if (IS_ERR(req))
-		return SCSI_DH_RES_TEMP_UNAVAIL;
-
-	blk_rq_set_block_pc(req);
-	req->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
-			  REQ_FAILFAST_DRIVER;
-	req->cmd_len = COMMAND_SIZE(TEST_UNIT_READY);
-	req->cmd[0] = TEST_UNIT_READY;
-	req->timeout = HP_SW_TIMEOUT;
-	req->sense = h->sense;
-	memset(req->sense, 0, SCSI_SENSE_BUFFERSIZE);
-	req->sense_len = 0;
-
-	ret = blk_execute_rq(req->q, NULL, req, 1);
-	if (ret == -EIO) {
-		if (req->sense_len > 0) {
-			ret = tur_done(sdev, h->sense);
-		} else {
+	res = scsi_execute_req_flags(sdev, cmd, DMA_NONE, NULL, 0, &sshdr,
+				     HP_SW_TIMEOUT, HP_SW_RETRIES,
+				     NULL, req_flags, 0);
+	if (res) {
+		if (scsi_sense_valid(&sshdr))
+			ret = tur_done(sdev, h, &sshdr);
+		else {
 			sdev_printk(KERN_WARNING, sdev,
 				    "%s: sending tur failed with %x\n",
-				    HP_SW_NAME, req->errors);
+				    HP_SW_NAME, res);
 			ret = SCSI_DH_IO;
 		}
 	} else {
 		h->path_state = HP_SW_PATH_ACTIVE;
 		ret = SCSI_DH_OK;
 	}
-	if (ret == SCSI_DH_IMM_RETRY) {
-		blk_put_request(req);
+	if (ret == SCSI_DH_IMM_RETRY)
 		goto retry;
-	}
-	if (ret == SCSI_DH_DEV_OFFLINED) {
-		h->path_state = HP_SW_PATH_PASSIVE;
-		ret = SCSI_DH_OK;
-	}
-
-	blk_put_request(req);
 
 	return ret;
 }
 
 /*
- * start_done - Handle START STOP UNIT return status
- * @sdev: sdev the command has been sent to
- * @errors: blk error code
- */
-static int start_done(struct scsi_device *sdev, unsigned char *sense)
-{
-	struct scsi_sense_hdr sshdr;
-	int rc;
-
-	rc = scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, &sshdr);
-	if (!rc) {
-		sdev_printk(KERN_WARNING, sdev,
-			    "%s: sending start_stop_unit failed, "
-			    "no sense available\n",
-			    HP_SW_NAME);
-		return SCSI_DH_IO;
-	}
-	switch (sshdr.sense_key) {
-	case NOT_READY:
-		if ((sshdr.asc == 0x04) && (sshdr.ascq == 3)) {
-			/*
-			 * LUN not ready - manual intervention required
-			 *
-			 * Switch-over in progress, retry.
-			 */
-			rc = SCSI_DH_RETRY;
-			break;
-		}
-		/* fall through */
-	default:
-		sdev_printk(KERN_WARNING, sdev,
-			   "%s: sending start_stop_unit failed, sense %x/%x/%x\n",
-			   HP_SW_NAME, sshdr.sense_key, sshdr.asc,
-			   sshdr.ascq);
-		rc = SCSI_DH_IO;
-	}
-
-	return rc;
-}
-
-static void start_stop_endio(struct request *req, int error)
-{
-	struct hp_sw_dh_data *h = req->end_io_data;
-	unsigned err = SCSI_DH_OK;
-
-	if (error || host_byte(req->errors) != DID_OK ||
-			msg_byte(req->errors) != COMMAND_COMPLETE) {
-		sdev_printk(KERN_WARNING, h->sdev,
-			    "%s: sending start_stop_unit failed with %x\n",
-			    HP_SW_NAME, req->errors);
-		err = SCSI_DH_IO;
-		goto done;
-	}
-
-	if (req->sense_len > 0) {
-		err = start_done(h->sdev, h->sense);
-		if (err == SCSI_DH_RETRY) {
-			err = SCSI_DH_IO;
-			if (--h->retry_cnt) {
-				blk_put_request(req);
-				err = hp_sw_start_stop(h);
-				if (err == SCSI_DH_OK)
-					return;
-			}
-		}
-	}
-done:
-	req->end_io_data = NULL;
-	__blk_put_request(req->q, req);
-	if (h->callback_fn) {
-		h->callback_fn(h->callback_data, err);
-		h->callback_fn = h->callback_data = NULL;
-	}
-	return;
-
-}
-
-/*
  * hp_sw_start_stop - Send START STOP UNIT command
  * @sdev: sdev command should be sent to
  *
@@ -237,26 +130,48 @@ done:
  */
 static int hp_sw_start_stop(struct hp_sw_dh_data *h)
 {
-	struct request *req;
-
-	req = blk_get_request(h->sdev->request_queue, WRITE, GFP_ATOMIC);
-	if (IS_ERR(req))
-		return SCSI_DH_RES_TEMP_UNAVAIL;
-
-	blk_rq_set_block_pc(req);
-	req->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
-			  REQ_FAILFAST_DRIVER;
-	req->cmd_len = COMMAND_SIZE(START_STOP);
-	req->cmd[0] = START_STOP;
-	req->cmd[4] = 1;	/* Start spin cycle */
-	req->timeout = HP_SW_TIMEOUT;
-	req->sense = h->sense;
-	memset(req->sense, 0, SCSI_SENSE_BUFFERSIZE);
-	req->sense_len = 0;
-	req->end_io_data = h;
+	unsigned char cmd[6] = { START_STOP, 0, 0, 0, 1, 0 };
+	struct scsi_sense_hdr sshdr;
+	struct scsi_device *sdev = h->sdev;
+	int res, rc = SCSI_DH_OK;
+	int retry_cnt = HP_SW_RETRIES;
+	u64 req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+		REQ_FAILFAST_DRIVER;
 
-	blk_execute_rq_nowait(req->q, NULL, req, 1, start_stop_endio);
-	return SCSI_DH_OK;
+retry:
+	res = scsi_execute_req_flags(sdev, cmd, DMA_NONE, NULL, 0, &sshdr,
+				     HP_SW_TIMEOUT, HP_SW_RETRIES,
+				     NULL, req_flags, 0);
+	if (res) {
+		if (!scsi_sense_valid(&sshdr)) {
+			sdev_printk(KERN_WARNING, sdev,
+				    "%s: sending start_stop_unit failed, "
+				    "no sense available\n", HP_SW_NAME);
+			return SCSI_DH_IO;
+		}
+		switch (sshdr.sense_key) {
+		case NOT_READY:
+			if (sshdr.asc == 0x04 && sshdr.ascq == 3) {
+				/*
+				 * LUN not ready - manual intervention required
+				 *
+				 * Switch-over in progress, retry.
+				 */
+				if (--retry_cnt)
+					goto retry;
+				rc = SCSI_DH_RETRY;
+				break;
+			}
+			/* fall through */
+		default:
+			sdev_printk(KERN_WARNING, sdev,
+				    "%s: sending start_stop_unit failed, "
+				    "sense %x/%x/%x\n", HP_SW_NAME,
+				    sshdr.sense_key, sshdr.asc, sshdr.ascq);
+			rc = SCSI_DH_IO;
+		}
+	}
+	return rc;
 }
 
 static int hp_sw_prep_fn(struct scsi_device *sdev, struct request *req)
@@ -290,15 +205,8 @@ static int hp_sw_activate(struct scsi_device *sdev,
 
 	ret = hp_sw_tur(sdev, h);
 
-	if (ret == SCSI_DH_OK && h->path_state == HP_SW_PATH_PASSIVE) {
-		h->retry_cnt = h->retries;
-		h->callback_fn = fn;
-		h->callback_data = data;
+	if (ret == SCSI_DH_OK && h->path_state == HP_SW_PATH_PASSIVE)
 		ret = hp_sw_start_stop(h);
-		if (ret == SCSI_DH_OK)
-			return 0;
-		h->callback_fn = h->callback_data = NULL;
-	}
 
 	if (fn)
 		fn(data, ret);
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index 00d9c326158e..b64eaae8533d 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -205,7 +205,6 @@ struct rdac_dh_data {
 #define RDAC_NON_PREFERRED	1
 	char			preferred;
 
-	unsigned char		sense[SCSI_SENSE_BUFFERSIZE];
 	union			{
 		struct c2_inquiry c2;
 		struct c4_inquiry c4;
@@ -262,40 +261,12 @@ do { \
 		sdev_printk(KERN_INFO, sdev, RDAC_NAME ": " f "\n", ## arg); \
 } while (0);
 
-static struct request *get_rdac_req(struct scsi_device *sdev,
-			void *buffer, unsigned buflen, int rw)
+static unsigned int rdac_failover_get(struct rdac_controller *ctlr,
+				      struct list_head *list,
+				      unsigned char *cdb)
 {
-	struct request *rq;
-	struct request_queue *q = sdev->request_queue;
-
-	rq = blk_get_request(q, rw, GFP_NOIO);
-
-	if (IS_ERR(rq)) {
-		sdev_printk(KERN_INFO, sdev,
-				"get_rdac_req: blk_get_request failed.\n");
-		return NULL;
-	}
-	blk_rq_set_block_pc(rq);
-
-	if (buflen && blk_rq_map_kern(q, rq, buffer, buflen, GFP_NOIO)) {
-		blk_put_request(rq);
-		sdev_printk(KERN_INFO, sdev,
-				"get_rdac_req: blk_rq_map_kern failed.\n");
-		return NULL;
-	}
-
-	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
-			 REQ_FAILFAST_DRIVER;
-	rq->retries = RDAC_RETRIES;
-	rq->timeout = RDAC_TIMEOUT;
-
-	return rq;
-}
-
-static struct request *rdac_failover_get(struct scsi_device *sdev,
-			struct rdac_dh_data *h, struct list_head *list)
-{
-	struct request *rq;
+	struct scsi_device *sdev = ctlr->ms_sdev;
+	struct rdac_dh_data *h = sdev->handler_data;
 	struct rdac_mode_common *common;
 	unsigned data_size;
 	struct rdac_queue_data *qdata;
@@ -332,27 +303,17 @@ static struct request *rdac_failover_get(struct scsi_device *sdev,
 		lun_table[qdata->h->lun] = 0x81;
 	}
 
-	/* get request for block layer packet command */
-	rq = get_rdac_req(sdev, &h->ctlr->mode_select, data_size, WRITE);
-	if (!rq)
-		return NULL;
-
 	/* Prepare the command. */
 	if (h->ctlr->use_ms10) {
-		rq->cmd[0] = MODE_SELECT_10;
-		rq->cmd[7] = data_size >> 8;
-		rq->cmd[8] = data_size & 0xff;
+		cdb[0] = MODE_SELECT_10;
+		cdb[7] = data_size >> 8;
+		cdb[8] = data_size & 0xff;
 	} else {
-		rq->cmd[0] = MODE_SELECT;
-		rq->cmd[4] = data_size;
+		cdb[0] = MODE_SELECT;
+		cdb[4] = data_size;
 	}
-	rq->cmd_len = COMMAND_SIZE(rq->cmd[0]);
-
-	rq->sense = h->sense;
-	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
-	rq->sense_len = 0;
 
-	return rq;
+	return data_size;
 }
 
 static void release_controller(struct kref *kref)
@@ -400,46 +361,14 @@ static struct rdac_controller *get_controller(int index, char *array_name,
 	return ctlr;
 }
 
-static int submit_inquiry(struct scsi_device *sdev, int page_code,
-			  unsigned int len, struct rdac_dh_data *h)
-{
-	struct request *rq;
-	struct request_queue *q = sdev->request_queue;
-	int err = SCSI_DH_RES_TEMP_UNAVAIL;
-
-	rq = get_rdac_req(sdev, &h->inq, len, READ);
-	if (!rq)
-		goto done;
-
-	/* Prepare the command. */
-	rq->cmd[0] = INQUIRY;
-	rq->cmd[1] = 1;
-	rq->cmd[2] = page_code;
-	rq->cmd[4] = len;
-	rq->cmd_len = COMMAND_SIZE(INQUIRY);
-
-	rq->sense = h->sense;
-	memset(rq->sense, 0, SCSI_SENSE_BUFFERSIZE);
-	rq->sense_len = 0;
-
-	err = blk_execute_rq(q, NULL, rq, 1);
-	if (err == -EIO)
-		err = SCSI_DH_IO;
-
-	blk_put_request(rq);
-done:
-	return err;
-}
-
 static int get_lun_info(struct scsi_device *sdev, struct rdac_dh_data *h,
 			char *array_name, u8 *array_id)
 {
-	int err, i;
-	struct c8_inquiry *inqp;
+	int err = SCSI_DH_IO, i;
+	struct c8_inquiry *inqp = &h->inq.c8;
 
-	err = submit_inquiry(sdev, 0xC8, sizeof(struct c8_inquiry), h);
-	if (err == SCSI_DH_OK) {
-		inqp = &h->inq.c8;
+	if (!scsi_get_vpd_page(sdev, 0xC8, (unsigned char *)inqp,
+			       sizeof(struct c8_inquiry))) {
 		if (inqp->page_code != 0xc8)
 			return SCSI_DH_NOSYS;
 		if (inqp->page_id[0] != 'e' || inqp->page_id[1] != 'd' ||
@@ -453,20 +382,20 @@ static int get_lun_info(struct scsi_device *sdev, struct rdac_dh_data *h,
 		*(array_name+ARRAY_LABEL_LEN-1) = '\0';
 		memset(array_id, 0, UNIQUE_ID_LEN);
 		memcpy(array_id, inqp->array_unique_id, inqp->array_uniq_id_len);
+		err = SCSI_DH_OK;
 	}
 	return err;
 }
 
 static int check_ownership(struct scsi_device *sdev, struct rdac_dh_data *h)
 {
-	int err, access_state;
+	int err = SCSI_DH_IO, access_state;
 	struct rdac_dh_data *tmp;
-	struct c9_inquiry *inqp;
+	struct c9_inquiry *inqp = &h->inq.c9;
 
 	h->state = RDAC_STATE_ACTIVE;
-	err = submit_inquiry(sdev, 0xC9, sizeof(struct c9_inquiry), h);
-	if (err == SCSI_DH_OK) {
-		inqp = &h->inq.c9;
+	if (!scsi_get_vpd_page(sdev, 0xC9, (unsigned char *)inqp,
+			       sizeof(struct c9_inquiry))) {
 		/* detect the operating mode */
 		if ((inqp->avte_cvp >> 5) & 0x1)
 			h->mode = RDAC_MODE_IOSHIP; /* LUN in IOSHIP mode */
@@ -501,6 +430,7 @@ static int check_ownership(struct scsi_device *sdev, struct rdac_dh_data *h)
 			tmp->sdev->access_state = access_state;
 		}
 		rcu_read_unlock();
+		err = SCSI_DH_OK;
 	}
 
 	return err;
@@ -509,12 +439,11 @@ static int check_ownership(struct scsi_device *sdev, struct rdac_dh_data *h)
 static int initialize_controller(struct scsi_device *sdev,
 		struct rdac_dh_data *h, char *array_name, u8 *array_id)
 {
-	int err, index;
-	struct c4_inquiry *inqp;
+	int err = SCSI_DH_IO, index;
+	struct c4_inquiry *inqp = &h->inq.c4;
 
-	err = submit_inquiry(sdev, 0xC4, sizeof(struct c4_inquiry), h);
-	if (err == SCSI_DH_OK) {
-		inqp = &h->inq.c4;
+	if (!scsi_get_vpd_page(sdev, 0xC4, (unsigned char *)inqp,
+			       sizeof(struct c4_inquiry))) {
 		/* get the controller index */
 		if (inqp->slot_id[1] == 0x31)
 			index = 0;
@@ -530,18 +459,18 @@ static int initialize_controller(struct scsi_device *sdev,
 			h->sdev = sdev;
 		}
 		spin_unlock(&list_lock);
+		err = SCSI_DH_OK;
 	}
 	return err;
 }
 
 static int set_mode_select(struct scsi_device *sdev, struct rdac_dh_data *h)
 {
-	int err;
-	struct c2_inquiry *inqp;
+	int err = SCSI_DH_IO;
+	struct c2_inquiry *inqp = &h->inq.c2;
 
-	err = submit_inquiry(sdev, 0xC2, sizeof(struct c2_inquiry), h);
-	if (err == SCSI_DH_OK) {
-		inqp = &h->inq.c2;
+	if (!scsi_get_vpd_page(sdev, 0xC2, (unsigned char *)inqp,
+			       sizeof(struct c2_inquiry))) {
 		/*
 		 * If more than MODE6_MAX_LUN luns are supported, use
 		 * mode select 10
@@ -550,36 +479,35 @@ static int set_mode_select(struct scsi_device *sdev, struct rdac_dh_data *h)
 			h->ctlr->use_ms10 = 1;
 		else
 			h->ctlr->use_ms10 = 0;
+		err = SCSI_DH_OK;
 	}
 	return err;
 }
 
 static int mode_select_handle_sense(struct scsi_device *sdev,
-					unsigned char *sensebuf)
+				    struct scsi_sense_hdr *sense_hdr)
 {
-	struct scsi_sense_hdr sense_hdr;
-	int err = SCSI_DH_IO, ret;
+	int err = SCSI_DH_IO;
 	struct rdac_dh_data *h = sdev->handler_data;
 
-	ret = scsi_normalize_sense(sensebuf, SCSI_SENSE_BUFFERSIZE, &sense_hdr);
-	if (!ret)
+	if (!scsi_sense_valid(sense_hdr))
 		goto done;
 
-	switch (sense_hdr.sense_key) {
+	switch (sense_hdr->sense_key) {
 	case NO_SENSE:
 	case ABORTED_COMMAND:
 	case UNIT_ATTENTION:
 		err = SCSI_DH_RETRY;
 		break;
 	case NOT_READY:
-		if (sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x01)
+		if (sense_hdr->asc == 0x04 && sense_hdr->ascq == 0x01)
 			/* LUN Not Ready and is in the Process of Becoming
 			 * Ready
 			 */
 			err = SCSI_DH_RETRY;
 		break;
 	case ILLEGAL_REQUEST:
-		if (sense_hdr.asc == 0x91 && sense_hdr.ascq == 0x36)
+		if (sense_hdr->asc == 0x91 && sense_hdr->ascq == 0x36)
 			/*
 			 * Command Lock contention
 			 */
@@ -592,7 +520,7 @@ static int mode_select_handle_sense(struct scsi_device *sdev,
 	RDAC_LOG(RDAC_LOG_FAILOVER, sdev, "array %s, ctlr %d, "
 		"MODE_SELECT returned with sense %02x/%02x/%02x",
 		(char *) h->ctlr->array_name, h->ctlr->index,
-		sense_hdr.sense_key, sense_hdr.asc, sense_hdr.ascq);
+		sense_hdr->sense_key, sense_hdr->asc, sense_hdr->ascq);
 
 done:
 	return err;
@@ -602,13 +530,16 @@ static void send_mode_select(struct work_struct *work)
 {
 	struct rdac_controller *ctlr =
 		container_of(work, struct rdac_controller, ms_work);
-	struct request *rq;
 	struct scsi_device *sdev = ctlr->ms_sdev;
 	struct rdac_dh_data *h = sdev->handler_data;
-	struct request_queue *q = sdev->request_queue;
-	int err, retry_cnt = RDAC_RETRY_COUNT;
+	int err = SCSI_DH_OK, retry_cnt = RDAC_RETRY_COUNT;
 	struct rdac_queue_data *tmp, *qdata;
 	LIST_HEAD(list);
+	unsigned char cdb[COMMAND_SIZE(MODE_SELECT_10)];
+	struct scsi_sense_hdr sshdr;
+	unsigned int data_size;
+	u64 req_flags = REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+		REQ_FAILFAST_DRIVER;
 
 	spin_lock(&ctlr->ms_lock);
 	list_splice_init(&ctlr->ms_head, &list);
@@ -616,21 +547,19 @@ static void send_mode_select(struct work_struct *work)
 	ctlr->ms_sdev = NULL;
 	spin_unlock(&ctlr->ms_lock);
 
-retry:
-	err = SCSI_DH_RES_TEMP_UNAVAIL;
-	rq = rdac_failover_get(sdev, h, &list);
-	if (!rq)
-		goto done;
+ retry:
+	data_size = rdac_failover_get(ctlr, &list, cdb);
 
 	RDAC_LOG(RDAC_LOG_FAILOVER, sdev, "array %s, ctlr %d, "
 		"%s MODE_SELECT command",
 		(char *) h->ctlr->array_name, h->ctlr->index,
 		(retry_cnt == RDAC_RETRY_COUNT) ? "queueing" : "retrying");
 
-	err = blk_execute_rq(q, NULL, rq, 1);
-	blk_put_request(rq);
-	if (err != SCSI_DH_OK) {
-		err = mode_select_handle_sense(sdev, h->sense);
+	if (scsi_execute_req_flags(sdev, cdb, DMA_TO_DEVICE,
+				   &h->ctlr->mode_select, data_size, &sshdr,
+				   RDAC_TIMEOUT * HZ,
+				   RDAC_RETRIES, NULL, req_flags, 0)) {
+		err = mode_select_handle_sense(sdev, &sshdr);
 		if (err == SCSI_DH_RETRY && retry_cnt--)
 			goto retry;
 		if (err == SCSI_DH_IMM_RETRY)
@@ -643,7 +572,6 @@ retry:
 				(char *) h->ctlr->array_name, h->ctlr->index);
 	}
 
-done:
 	list_for_each_entry_safe(qdata, tmp, &list, entry) {
 		list_del(&qdata->entry);
 		if (err == SCSI_DH_OK)
diff --git a/drivers/scsi/dpt_i2o.c b/drivers/scsi/dpt_i2o.c
index 5f75e638ec95..256dd6791fcc 100644
--- a/drivers/scsi/dpt_i2o.c
+++ b/drivers/scsi/dpt_i2o.c
@@ -2768,16 +2768,12 @@ static int adpt_i2o_activate_hba(adpt_hba* pHba)
  
 static int adpt_i2o_online_hba(adpt_hba* pHba)
 {
-	if (adpt_i2o_systab_send(pHba) < 0) {
-		adpt_i2o_delete_hba(pHba);
+	if (adpt_i2o_systab_send(pHba) < 0)
 		return -1;
-	}
 	/* In READY state */
 
-	if (adpt_i2o_enable_hba(pHba) < 0) {
-		adpt_i2o_delete_hba(pHba);
+	if (adpt_i2o_enable_hba(pHba) < 0)
 		return -1;
-	}
 
 	/* In OPERATIONAL state  */
 	return 0;
diff --git a/drivers/scsi/esas2r/esas2r_init.c b/drivers/scsi/esas2r/esas2r_init.c
index d6e53aee2295..6432a50b26d8 100644
--- a/drivers/scsi/esas2r/esas2r_init.c
+++ b/drivers/scsi/esas2r/esas2r_init.c
@@ -237,7 +237,7 @@ static void esas2r_claim_interrupts(struct esas2r_adapter *a)
 		flags |= IRQF_SHARED;
 
 	esas2r_log(ESAS2R_LOG_INFO,
-		   "esas2r_claim_interrupts irq=%d (%p, %s, %x)",
+		   "esas2r_claim_interrupts irq=%d (%p, %s, %lx)",
 		   a->pcid->irq, a, a->name, flags);
 
 	if (request_irq(a->pcid->irq,
diff --git a/drivers/scsi/esas2r/esas2r_ioctl.c b/drivers/scsi/esas2r/esas2r_ioctl.c
index 3e8483410f61..b35ed3829421 100644
--- a/drivers/scsi/esas2r/esas2r_ioctl.c
+++ b/drivers/scsi/esas2r/esas2r_ioctl.c
@@ -1301,7 +1301,7 @@ int esas2r_ioctl_handler(void *hostdata, int cmd, void __user *arg)
 	ioctl = kzalloc(sizeof(struct atto_express_ioctl), GFP_KERNEL);
 	if (ioctl == NULL) {
 		esas2r_log(ESAS2R_LOG_WARN,
-			   "ioctl_handler kzalloc failed for %d bytes",
+			   "ioctl_handler kzalloc failed for %zu bytes",
 			   sizeof(struct atto_express_ioctl));
 		return -ENOMEM;
 	}
diff --git a/drivers/scsi/esas2r/esas2r_log.h b/drivers/scsi/esas2r/esas2r_log.h
index 7b6397bb5b94..75b9d23cd736 100644
--- a/drivers/scsi/esas2r/esas2r_log.h
+++ b/drivers/scsi/esas2r/esas2r_log.h
@@ -61,8 +61,8 @@ enum {
 #endif
 };
 
-int esas2r_log(const long level, const char *format, ...);
-int esas2r_log_dev(const long level,
+__printf(2, 3) int esas2r_log(const long level, const char *format, ...);
+__printf(3, 4) int esas2r_log_dev(const long level,
 		   const struct device *dev,
 		   const char *format,
 		   ...);
diff --git a/drivers/scsi/esas2r/esas2r_main.c b/drivers/scsi/esas2r/esas2r_main.c
index 5092c821d088..f2e9d8aa979c 100644
--- a/drivers/scsi/esas2r/esas2r_main.c
+++ b/drivers/scsi/esas2r/esas2r_main.c
@@ -198,7 +198,7 @@ static ssize_t write_hw(struct file *file, struct kobject *kobj,
 					      GFP_KERNEL);
 		if (a->local_atto_ioctl == NULL) {
 			esas2r_log(ESAS2R_LOG_WARN,
-				   "write_hw kzalloc failed for %d bytes",
+				   "write_hw kzalloc failed for %zu bytes",
 				   sizeof(struct atto_ioctl));
 			return -ENOMEM;
 		}
@@ -1186,7 +1186,7 @@ retry:
 		} else {
 			esas2r_log(ESAS2R_LOG_CRIT,
 				   "unable to allocate a request for a "
-				   "device reset (%d:%d)!",
+				   "device reset (%d:%llu)!",
 				   cmd->device->id,
 				   cmd->device->lun);
 		}
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 59150cad0353..86af57f7c11a 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -277,6 +277,7 @@ static struct scsi_host_template fcoe_shost_template = {
 	.name = "FCoE Driver",
 	.proc_name = FCOE_NAME,
 	.queuecommand = fc_queuecommand,
+	.eh_timed_out = fc_eh_timed_out,
 	.eh_abort_handler = fc_eh_abort,
 	.eh_device_reset_handler = fc_eh_device_reset,
 	.eh_host_reset_handler = fc_eh_host_reset,
diff --git a/drivers/scsi/fnic/fnic_main.c b/drivers/scsi/fnic/fnic_main.c
index 58ce9020d69c..ba58b7953263 100644
--- a/drivers/scsi/fnic/fnic_main.c
+++ b/drivers/scsi/fnic/fnic_main.c
@@ -106,6 +106,7 @@ static struct scsi_host_template fnic_host_template = {
 	.module = THIS_MODULE,
 	.name = DRV_NAME,
 	.queuecommand = fnic_queuecommand,
+	.eh_timed_out = fc_eh_timed_out,
 	.eh_abort_handler = fnic_abort_cmd,
 	.eh_device_reset_handler = fnic_device_reset,
 	.eh_host_reset_handler = fnic_host_reset,
diff --git a/drivers/scsi/g_NCR5380.c b/drivers/scsi/g_NCR5380.c
index 6f9665d50d84..67c8dac321ad 100644
--- a/drivers/scsi/g_NCR5380.c
+++ b/drivers/scsi/g_NCR5380.c
@@ -26,14 +26,55 @@
 #include <linux/blkdev.h>
 #include <linux/module.h>
 #include <scsi/scsi_host.h>
-#include "g_NCR5380.h"
-#include "NCR5380.h"
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/isa.h>
 #include <linux/pnp.h>
 #include <linux/interrupt.h>
 
+/* Definitions for the core NCR5380 driver. */
+
+#define NCR5380_read(reg) \
+	ioread8(hostdata->io + hostdata->offset + (reg))
+#define NCR5380_write(reg, value) \
+	iowrite8(value, hostdata->io + hostdata->offset + (reg))
+
+#define NCR5380_implementation_fields \
+	int offset; \
+	int c400_ctl_status; \
+	int c400_blk_cnt; \
+	int c400_host_buf; \
+	int io_width
+
+#define NCR5380_dma_xfer_len            generic_NCR5380_dma_xfer_len
+#define NCR5380_dma_recv_setup          generic_NCR5380_pread
+#define NCR5380_dma_send_setup          generic_NCR5380_pwrite
+#define NCR5380_dma_residual            NCR5380_dma_residual_none
+
+#define NCR5380_intr                    generic_NCR5380_intr
+#define NCR5380_queue_command           generic_NCR5380_queue_command
+#define NCR5380_abort                   generic_NCR5380_abort
+#define NCR5380_bus_reset               generic_NCR5380_bus_reset
+#define NCR5380_info                    generic_NCR5380_info
+
+#define NCR5380_io_delay(x)             udelay(x)
+
+#include "NCR5380.h"
+
+#define DRV_MODULE_NAME "g_NCR5380"
+
+#define NCR53C400_mem_base 0x3880
+#define NCR53C400_host_buffer 0x3900
+#define NCR53C400_region_size 0x3a00
+
+#define BOARD_NCR5380 0
+#define BOARD_NCR53C400 1
+#define BOARD_NCR53C400A 2
+#define BOARD_DTC3181E 3
+#define BOARD_HP_C2502 4
+
+#define IRQ_AUTO 254
+
 #define MAX_CARDS 8
 
 /* old-style parameters for compatibility */
diff --git a/drivers/scsi/g_NCR5380.h b/drivers/scsi/g_NCR5380.h
deleted file mode 100644
index 81b22d989648..000000000000
--- a/drivers/scsi/g_NCR5380.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * Generic Generic NCR5380 driver defines
- *
- * Copyright 1993, Drew Eckhardt
- *	Visionary Computing
- *	(Unix and Linux consulting and custom programming)
- *	drew@colorado.edu
- *      +1 (303) 440-4894
- *
- * NCR53C400 extensions (c) 1994,1995,1996, Kevin Lentin
- *    K.Lentin@cs.monash.edu.au
- */
-
-#ifndef GENERIC_NCR5380_H
-#define GENERIC_NCR5380_H
-
-#define DRV_MODULE_NAME "g_NCR5380"
-
-#define NCR5380_read(reg) \
-	ioread8(hostdata->io + hostdata->offset + (reg))
-#define NCR5380_write(reg, value) \
-	iowrite8(value, hostdata->io + hostdata->offset + (reg))
-
-#define NCR5380_implementation_fields \
-	int offset; \
-	int c400_ctl_status; \
-	int c400_blk_cnt; \
-	int c400_host_buf; \
-	int io_width;
-
-#define NCR53C400_mem_base 0x3880
-#define NCR53C400_host_buffer 0x3900
-#define NCR53C400_region_size 0x3a00
-
-#define NCR5380_dma_xfer_len		generic_NCR5380_dma_xfer_len
-#define NCR5380_dma_recv_setup		generic_NCR5380_pread
-#define NCR5380_dma_send_setup		generic_NCR5380_pwrite
-#define NCR5380_dma_residual		NCR5380_dma_residual_none
-
-#define NCR5380_intr generic_NCR5380_intr
-#define NCR5380_queue_command generic_NCR5380_queue_command
-#define NCR5380_abort generic_NCR5380_abort
-#define NCR5380_bus_reset generic_NCR5380_bus_reset
-#define NCR5380_info generic_NCR5380_info
-
-#define NCR5380_io_delay(x)		udelay(x)
-
-#define BOARD_NCR5380	0
-#define BOARD_NCR53C400	1
-#define BOARD_NCR53C400A 2
-#define BOARD_DTC3181E	3
-#define BOARD_HP_C2502	4
-
-#define IRQ_AUTO	254
-
-#endif /* GENERIC_NCR5380_H */
diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index c0cd505a9ef7..9216deaa3ff5 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -95,6 +95,7 @@ struct hisi_sas_port {
 
 struct hisi_sas_cq {
 	struct hisi_hba *hisi_hba;
+	struct tasklet_struct tasklet;
 	int	rd_point;
 	int	id;
 };
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index d50e9cfefd24..53637a941b94 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -71,6 +71,8 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 			     struct hisi_sas_slot *slot)
 {
 	struct device *dev = &hisi_hba->pdev->dev;
+	struct domain_device *device = task->dev;
+	struct hisi_sas_device *sas_dev = device->lldd_dev;
 
 	if (!slot->task)
 		return;
@@ -97,6 +99,8 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 	slot->task = NULL;
 	slot->port = NULL;
 	hisi_sas_slot_index_free(hisi_hba, slot->idx);
+	if (sas_dev)
+		atomic64_dec(&sas_dev->running_req);
 	/* slot memory is fully zeroed when it is reused */
 }
 EXPORT_SYMBOL_GPL(hisi_sas_slot_task_free);
@@ -141,11 +145,10 @@ static void hisi_sas_slot_abort(struct work_struct *work)
 	struct hisi_hba *hisi_hba = dev_to_hisi_hba(task->dev);
 	struct scsi_cmnd *cmnd = task->uldd_task;
 	struct hisi_sas_tmf_task tmf_task;
-	struct domain_device *device = task->dev;
-	struct hisi_sas_device *sas_dev = device->lldd_dev;
 	struct scsi_lun lun;
 	struct device *dev = &hisi_hba->pdev->dev;
 	int tag = abort_slot->idx;
+	unsigned long flags;
 
 	if (!(task->task_proto & SAS_PROTOCOL_SSP)) {
 		dev_err(dev, "cannot abort slot for non-ssp task\n");
@@ -159,11 +162,11 @@ static void hisi_sas_slot_abort(struct work_struct *work)
 	hisi_sas_debug_issue_ssp_tmf(task->dev, lun.scsi_lun, &tmf_task);
 out:
 	/* Do cleanup for this task */
+	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_task_free(hisi_hba, task, abort_slot);
+	spin_unlock_irqrestore(&hisi_hba->lock, flags);
 	if (task->task_done)
 		task->task_done(task);
-	if (sas_dev)
-		atomic64_dec(&sas_dev->running_req);
 }
 
 static int hisi_sas_task_prep(struct sas_task *task, struct hisi_hba *hisi_hba,
@@ -1118,7 +1121,7 @@ hisi_sas_internal_task_abort(struct hisi_hba *hisi_hba,
 	}
 
 exit:
-	dev_info(dev, "internal task abort: task to dev %016llx task=%p "
+	dev_dbg(dev, "internal task abort: task to dev %016llx task=%p "
 		"resp: 0x%x sts 0x%x\n",
 		SAS_ADDR(device->sas_addr),
 		task,
@@ -1450,7 +1453,7 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev,
 
 	refclk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(refclk))
-		dev_info(dev, "no ref clk property\n");
+		dev_dbg(dev, "no ref clk property\n");
 	else
 		hisi_hba->refclk_frequency_mhz = clk_get_rate(refclk) / 1000000;
 
@@ -1549,10 +1552,6 @@ int hisi_sas_probe(struct platform_device *pdev,
 
 	hisi_sas_init_add(hisi_hba);
 
-	rc = hisi_hba->hw->hw_init(hisi_hba);
-	if (rc)
-		goto err_out_ha;
-
 	rc = scsi_add_host(shost, &pdev->dev);
 	if (rc)
 		goto err_out_ha;
@@ -1561,6 +1560,10 @@ int hisi_sas_probe(struct platform_device *pdev,
 	if (rc)
 		goto err_out_register_ha;
 
+	rc = hisi_hba->hw->hw_init(hisi_hba);
+	if (rc)
+		goto err_out_register_ha;
+
 	scsi_scan_host(shost);
 
 	return 0;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 8a1be0ba8a22..854fbeaade3e 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1596,6 +1596,7 @@ static irqreturn_t cq_interrupt_v1_hw(int irq, void *p)
 			hisi_hba->complete_hdr[queue];
 	u32 irq_value, rd_point = cq->rd_point, wr_point;
 
+	spin_lock(&hisi_hba->lock);
 	irq_value = hisi_sas_read32(hisi_hba, OQ_INT_SRC);
 
 	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
@@ -1628,6 +1629,7 @@ static irqreturn_t cq_interrupt_v1_hw(int irq, void *p)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+	spin_unlock(&hisi_hba->lock);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index b934aec1eebb..1b214450dcb5 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -207,6 +207,8 @@
 #define TXID_AUTO			(PORT_BASE + 0xb8)
 #define TXID_AUTO_CT3_OFF		1
 #define TXID_AUTO_CT3_MSK		(0x1 << TXID_AUTO_CT3_OFF)
+#define TX_HARDRST_OFF          2
+#define TX_HARDRST_MSK          (0x1 << TX_HARDRST_OFF)
 #define RX_IDAF_DWORD0			(PORT_BASE + 0xc4)
 #define RX_IDAF_DWORD1			(PORT_BASE + 0xc8)
 #define RX_IDAF_DWORD2			(PORT_BASE + 0xcc)
@@ -215,6 +217,7 @@
 #define RX_IDAF_DWORD5			(PORT_BASE + 0xd8)
 #define RX_IDAF_DWORD6			(PORT_BASE + 0xdc)
 #define RXOP_CHECK_CFG_H		(PORT_BASE + 0xfc)
+#define CON_CONTROL			(PORT_BASE + 0x118)
 #define DONE_RECEIVED_TIME		(PORT_BASE + 0x11c)
 #define CHL_INT0			(PORT_BASE + 0x1b4)
 #define CHL_INT0_HOTPLUG_TOUT_OFF	0
@@ -333,6 +336,11 @@
 #define ITCT_HDR_MCR_MSK		(0xf << ITCT_HDR_MCR_OFF)
 #define ITCT_HDR_VLN_OFF		9
 #define ITCT_HDR_VLN_MSK		(0xf << ITCT_HDR_VLN_OFF)
+#define ITCT_HDR_SMP_TIMEOUT_OFF	16
+#define ITCT_HDR_SMP_TIMEOUT_8US	1
+#define ITCT_HDR_SMP_TIMEOUT		(ITCT_HDR_SMP_TIMEOUT_8US * \
+					 250) /* 2ms */
+#define ITCT_HDR_AWT_CONTINUE_OFF	25
 #define ITCT_HDR_PORT_ID_OFF		28
 #define ITCT_HDR_PORT_ID_MSK		(0xf << ITCT_HDR_PORT_ID_OFF)
 /* qw2 */
@@ -526,6 +534,8 @@ enum {
 #define SATA_PROTOCOL_FPDMA		0x8
 #define SATA_PROTOCOL_ATAPI		0x10
 
+static void hisi_sas_link_timeout_disable_link(unsigned long data);
+
 static u32 hisi_sas_read32(struct hisi_hba *hisi_hba, u32 off)
 {
 	void __iomem *regs = hisi_hba->regs + off;
@@ -693,6 +703,8 @@ static void setup_itct_v2_hw(struct hisi_hba *hisi_hba,
 	qw0 |= ((1 << ITCT_HDR_VALID_OFF) |
 		(device->linkrate << ITCT_HDR_MCR_OFF) |
 		(1 << ITCT_HDR_VLN_OFF) |
+		(ITCT_HDR_SMP_TIMEOUT << ITCT_HDR_SMP_TIMEOUT_OFF) |
+		(1 << ITCT_HDR_AWT_CONTINUE_OFF) |
 		(port->id << ITCT_HDR_PORT_ID_OFF));
 	itct->qw0 = cpu_to_le64(qw0);
 
@@ -702,7 +714,7 @@ static void setup_itct_v2_hw(struct hisi_hba *hisi_hba,
 
 	/* qw2 */
 	if (!dev_is_sata(device))
-		itct->qw2 = cpu_to_le64((500ULL << ITCT_HDR_INLT_OFF) |
+		itct->qw2 = cpu_to_le64((5000ULL << ITCT_HDR_INLT_OFF) |
 					(0x1ULL << ITCT_HDR_BITLT_OFF) |
 					(0x32ULL << ITCT_HDR_MCTLT_OFF) |
 					(0x1ULL << ITCT_HDR_RTOLT_OFF));
@@ -711,7 +723,7 @@ static void setup_itct_v2_hw(struct hisi_hba *hisi_hba,
 static void free_device_v2_hw(struct hisi_hba *hisi_hba,
 			      struct hisi_sas_device *sas_dev)
 {
-	u64 qw0, dev_id = sas_dev->device_id;
+	u64 dev_id = sas_dev->device_id;
 	struct device *dev = &hisi_hba->pdev->dev;
 	struct hisi_sas_itct *itct = &hisi_hba->itct[dev_id];
 	u32 reg_val = hisi_sas_read32(hisi_hba, ENT_INT_SRC3);
@@ -735,8 +747,7 @@ static void free_device_v2_hw(struct hisi_hba *hisi_hba,
 			dev_dbg(dev, "got clear ITCT done interrupt\n");
 
 			/* invalid the itct state*/
-			qw0 = cpu_to_le64(itct->qw0);
-			qw0 &= ~(1 << ITCT_HDR_VALID_OFF);
+			memset(itct, 0, sizeof(struct hisi_sas_itct));
 			hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
 					 ENT_INT_SRC3_ITC_INT_MSK);
 
@@ -978,6 +989,50 @@ static void init_reg_v2_hw(struct hisi_hba *hisi_hba)
 			 upper_32_bits(hisi_hba->initial_fis_dma));
 }
 
+static void hisi_sas_link_timeout_enable_link(unsigned long data)
+{
+	struct hisi_hba *hisi_hba = (struct hisi_hba *)data;
+	int i, reg_val;
+
+	for (i = 0; i < hisi_hba->n_phy; i++) {
+		reg_val = hisi_sas_phy_read32(hisi_hba, i, CON_CONTROL);
+		if (!(reg_val & BIT(0))) {
+			hisi_sas_phy_write32(hisi_hba, i,
+					CON_CONTROL, 0x7);
+			break;
+		}
+	}
+
+	hisi_hba->timer.function = hisi_sas_link_timeout_disable_link;
+	mod_timer(&hisi_hba->timer, jiffies + msecs_to_jiffies(900));
+}
+
+static void hisi_sas_link_timeout_disable_link(unsigned long data)
+{
+	struct hisi_hba *hisi_hba = (struct hisi_hba *)data;
+	int i, reg_val;
+
+	reg_val = hisi_sas_read32(hisi_hba, PHY_STATE);
+	for (i = 0; i < hisi_hba->n_phy && reg_val; i++) {
+		if (reg_val & BIT(i)) {
+			hisi_sas_phy_write32(hisi_hba, i,
+					CON_CONTROL, 0x6);
+			break;
+		}
+	}
+
+	hisi_hba->timer.function = hisi_sas_link_timeout_enable_link;
+	mod_timer(&hisi_hba->timer, jiffies + msecs_to_jiffies(100));
+}
+
+static void set_link_timer_quirk(struct hisi_hba *hisi_hba)
+{
+	hisi_hba->timer.data = (unsigned long)hisi_hba;
+	hisi_hba->timer.function = hisi_sas_link_timeout_disable_link;
+	hisi_hba->timer.expires = jiffies + msecs_to_jiffies(1000);
+	add_timer(&hisi_hba->timer);
+}
+
 static int hw_init_v2_hw(struct hisi_hba *hisi_hba)
 {
 	struct device *dev = &hisi_hba->pdev->dev;
@@ -1025,14 +1080,21 @@ static void stop_phy_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 
 static void phy_hard_reset_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
 {
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	u32 txid_auto;
+
 	stop_phy_v2_hw(hisi_hba, phy_no);
+	if (phy->identify.device_type == SAS_END_DEVICE) {
+		txid_auto = hisi_sas_phy_read32(hisi_hba, phy_no, TXID_AUTO);
+		hisi_sas_phy_write32(hisi_hba, phy_no, TXID_AUTO,
+					txid_auto | TX_HARDRST_MSK);
+	}
 	msleep(100);
 	start_phy_v2_hw(hisi_hba, phy_no);
 }
 
-static void start_phys_v2_hw(unsigned long data)
+static void start_phys_v2_hw(struct hisi_hba *hisi_hba)
 {
-	struct hisi_hba *hisi_hba = (struct hisi_hba *)data;
 	int i;
 
 	for (i = 0; i < hisi_hba->n_phy; i++)
@@ -1041,10 +1103,7 @@ static void start_phys_v2_hw(unsigned long data)
 
 static void phys_init_v2_hw(struct hisi_hba *hisi_hba)
 {
-	struct timer_list *timer = &hisi_hba->timer;
-
-	setup_timer(timer, start_phys_v2_hw, (unsigned long)hisi_hba);
-	mod_timer(timer, jiffies + HZ);
+	start_phys_v2_hw(hisi_hba);
 }
 
 static void sl_notify_v2_hw(struct hisi_hba *hisi_hba, int phy_no)
@@ -1771,8 +1830,6 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot,
 	}
 
 out:
-	if (sas_dev)
-		atomic64_dec(&sas_dev->running_req);
 
 	hisi_sas_slot_task_free(hisi_hba, task, slot);
 	sts = ts->stat;
@@ -2020,9 +2077,12 @@ static int phy_up_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 	if (phy->identify.device_type == SAS_END_DEVICE)
 		phy->identify.target_port_protocols =
 			SAS_PROTOCOL_SSP;
-	else if (phy->identify.device_type != SAS_PHY_UNUSED)
+	else if (phy->identify.device_type != SAS_PHY_UNUSED) {
 		phy->identify.target_port_protocols =
 			SAS_PROTOCOL_SMP;
+		if (!timer_pending(&hisi_hba->timer))
+			set_link_timer_quirk(hisi_hba);
+	}
 	queue_work(hisi_hba->wq, &phy->phyup_ws);
 
 end:
@@ -2033,10 +2093,23 @@ end:
 	return res;
 }
 
+static bool check_any_wideports_v2_hw(struct hisi_hba *hisi_hba)
+{
+	u32 port_state;
+
+	port_state = hisi_sas_read32(hisi_hba, PORT_STATE);
+	if (port_state & 0x1ff)
+		return true;
+
+	return false;
+}
+
 static int phy_down_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 {
 	int res = 0;
 	u32 phy_state, sl_ctrl, txid_auto;
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
+	struct hisi_sas_port *port = phy->port;
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHYCTRL_NOT_RDY_MSK, 1);
 
@@ -2046,6 +2119,10 @@ static int phy_down_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 	sl_ctrl = hisi_sas_phy_read32(hisi_hba, phy_no, SL_CONTROL);
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_CONTROL,
 			     sl_ctrl & ~SL_CONTROL_CTA_MSK);
+	if (port && !get_wideport_bitmap_v2_hw(hisi_hba, port->id))
+		if (!check_any_wideports_v2_hw(hisi_hba) &&
+				timer_pending(&hisi_hba->timer))
+			del_timer(&hisi_hba->timer);
 
 	txid_auto = hisi_sas_phy_read32(hisi_hba, phy_no, TXID_AUTO);
 	hisi_sas_phy_write32(hisi_hba, phy_no, TXID_AUTO,
@@ -2481,21 +2558,19 @@ static irqreturn_t fatal_axi_int_v2_hw(int irq_no, void *p)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
+static void cq_tasklet_v2_hw(unsigned long val)
 {
-	struct hisi_sas_cq *cq = p;
+	struct hisi_sas_cq *cq = (struct hisi_sas_cq *)val;
 	struct hisi_hba *hisi_hba = cq->hisi_hba;
 	struct hisi_sas_slot *slot;
 	struct hisi_sas_itct *itct;
 	struct hisi_sas_complete_v2_hdr *complete_queue;
-	u32 irq_value, rd_point = cq->rd_point, wr_point, dev_id;
+	u32 rd_point = cq->rd_point, wr_point, dev_id;
 	int queue = cq->id;
 
 	complete_queue = hisi_hba->complete_hdr[queue];
-	irq_value = hisi_sas_read32(hisi_hba, OQ_INT_SRC);
-
-	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
 
+	spin_lock(&hisi_hba->lock);
 	wr_point = hisi_sas_read32(hisi_hba, COMPL_Q_0_WR_PTR +
 				   (0x14 * queue));
 
@@ -2545,6 +2620,19 @@ static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
+	spin_unlock(&hisi_hba->lock);
+}
+
+static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)
+{
+	struct hisi_sas_cq *cq = p;
+	struct hisi_hba *hisi_hba = cq->hisi_hba;
+	int queue = cq->id;
+
+	hisi_sas_write32(hisi_hba, OQ_INT_SRC, 1 << queue);
+
+	tasklet_schedule(&cq->tasklet);
+
 	return IRQ_HANDLED;
 }
 
@@ -2726,6 +2814,8 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 
 	for (i = 0; i < hisi_hba->queue_count; i++) {
 		int idx = i + 96; /* First cq interrupt is irq96 */
+		struct hisi_sas_cq *cq = &hisi_hba->cq[i];
+		struct tasklet_struct *t = &cq->tasklet;
 
 		irq = irq_map[idx];
 		if (!irq) {
@@ -2742,6 +2832,7 @@ static int interrupt_init_v2_hw(struct hisi_hba *hisi_hba)
 				irq, rc);
 			return -ENOENT;
 		}
+		tasklet_init(t, cq_tasklet_v2_hw, (unsigned long)cq);
 	}
 
 	return 0;
@@ -2807,6 +2898,12 @@ static int hisi_sas_v2_probe(struct platform_device *pdev)
 
 static int hisi_sas_v2_remove(struct platform_device *pdev)
 {
+	struct sas_ha_struct *sha = platform_get_drvdata(pdev);
+	struct hisi_hba *hisi_hba = sha->lldd_ha;
+
+	if (timer_pending(&hisi_hba->timer))
+		del_timer(&hisi_hba->timer);
+
 	return hisi_sas_remove(pdev);
 }
 
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 258a3f9a2519..831a1c8b9f89 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -213,6 +213,10 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 		goto fail;
 	}
 
+	error = scsi_init_sense_cache(shost);
+	if (error)
+		goto fail;
+
 	if (shost_use_blk_mq(shost)) {
 		error = scsi_mq_setup_tags(shost);
 		if (error)
@@ -226,19 +230,6 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 		}
 	}
 
-	/*
-	 * Note that we allocate the freelist even for the MQ case for now,
-	 * as we need a command set aside for scsi_reset_provider.  Having
-	 * the full host freelist and one command available for that is a
-	 * little heavy-handed, but avoids introducing a special allocator
-	 * just for this.  Eventually the structure of scsi_reset_provider
-	 * will need a major overhaul.
-	 */
-	error = scsi_setup_command_freelist(shost);
-	if (error)
-		goto out_destroy_tags;
-
-
 	if (!shost->shost_gendev.parent)
 		shost->shost_gendev.parent = dev ? dev : &platform_bus;
 	if (!dma_dev)
@@ -258,7 +249,7 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 
 	error = device_add(&shost->shost_gendev);
 	if (error)
-		goto out_destroy_freelist;
+		goto out_disable_runtime_pm;
 
 	scsi_host_set_state(shost, SHOST_RUNNING);
 	get_device(shost->shost_gendev.parent);
@@ -308,13 +299,11 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
 	device_del(&shost->shost_dev);
  out_del_gendev:
 	device_del(&shost->shost_gendev);
- out_destroy_freelist:
+ out_disable_runtime_pm:
 	device_disable_async_suspend(&shost->shost_gendev);
 	pm_runtime_disable(&shost->shost_gendev);
 	pm_runtime_set_suspended(&shost->shost_gendev);
 	pm_runtime_put_noidle(&shost->shost_gendev);
-	scsi_destroy_command_freelist(shost);
- out_destroy_tags:
 	if (shost_use_blk_mq(shost))
 		scsi_mq_destroy_tags(shost);
  fail:
@@ -355,7 +344,6 @@ static void scsi_host_dev_release(struct device *dev)
 		kfree(dev_name(&shost->shost_dev));
 	}
 
-	scsi_destroy_command_freelist(shost);
 	if (shost_use_blk_mq(shost)) {
 		if (shost->tag_set.tags)
 			scsi_mq_destroy_tags(shost);
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index cbc0c5fe5a60..524a0c755ed7 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -5539,8 +5539,8 @@ static int hpsa_scsi_queue_command(struct Scsi_Host *sh, struct scsi_cmnd *cmd)
 	 * Retries always go down the normal I/O path.
 	 */
 	if (likely(cmd->retries == 0 &&
-		cmd->request->cmd_type == REQ_TYPE_FS &&
-		h->acciopath_status)) {
+			!blk_rq_is_passthrough(cmd->request) &&
+			h->acciopath_status)) {
 		rc = hpsa_ioaccel_submit(h, c, cmd, scsi3addr);
 		if (rc == 0)
 			return 0;
@@ -9263,13 +9263,9 @@ static int hpsa_enter_performant_mode(struct ctlr_info *h, u32 trans_support)
 		access = SA5_ioaccel_mode1_access;
 		writel(10, &h->cfgtable->HostWrite.CoalIntDelay);
 		writel(4, &h->cfgtable->HostWrite.CoalIntCount);
-	} else {
-		if (trans_support & CFGTBL_Trans_io_accel2) {
+	} else
+		if (trans_support & CFGTBL_Trans_io_accel2)
 			access = SA5_ioaccel_mode2_access;
-			writel(10, &h->cfgtable->HostWrite.CoalIntDelay);
-			writel(4, &h->cfgtable->HostWrite.CoalIntCount);
-		}
-	}
 	writel(CFGTBL_ChangeReq, h->vaddr + SA5_DOORBELL);
 	if (hpsa_wait_for_mode_change_ack(h)) {
 		dev_err(&h->pdev->dev,
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index 64e98295b707..bf6cdc106654 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -578,38 +578,38 @@ static unsigned long SA5_ioaccel_mode1_completed(struct ctlr_info *h, u8 q)
 }
 
 static struct access_method SA5_access = {
-	SA5_submit_command,
-	SA5_intr_mask,
-	SA5_intr_pending,
-	SA5_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5_intr_mask,
+	.intr_pending = SA5_intr_pending,
+	.command_completed = SA5_completed,
 };
 
 static struct access_method SA5_ioaccel_mode1_access = {
-	SA5_submit_command,
-	SA5_performant_intr_mask,
-	SA5_ioaccel_mode1_intr_pending,
-	SA5_ioaccel_mode1_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5_performant_intr_mask,
+	.intr_pending = SA5_ioaccel_mode1_intr_pending,
+	.command_completed = SA5_ioaccel_mode1_completed,
 };
 
 static struct access_method SA5_ioaccel_mode2_access = {
-	SA5_submit_command_ioaccel2,
-	SA5_performant_intr_mask,
-	SA5_performant_intr_pending,
-	SA5_performant_completed,
+	.submit_command = SA5_submit_command_ioaccel2,
+	.set_intr_mask = SA5_performant_intr_mask,
+	.intr_pending = SA5_performant_intr_pending,
+	.command_completed = SA5_performant_completed,
 };
 
 static struct access_method SA5_performant_access = {
-	SA5_submit_command,
-	SA5_performant_intr_mask,
-	SA5_performant_intr_pending,
-	SA5_performant_completed,
+	.submit_command = SA5_submit_command,
+	.set_intr_mask = SA5_performant_intr_mask,
+	.intr_pending = SA5_performant_intr_pending,
+	.command_completed = SA5_performant_completed,
 };
 
 static struct access_method SA5_performant_access_no_read = {
-	SA5_submit_command_no_read,
-	SA5_performant_intr_mask,
-	SA5_performant_intr_pending,
-	SA5_performant_completed,
+	.submit_command = SA5_submit_command_no_read,
+	.set_intr_mask = SA5_performant_intr_mask,
+	.intr_pending = SA5_performant_intr_pending,
+	.command_completed = SA5_performant_completed,
 };
 
 struct board_type {
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 78b72c28a55d..2c92dabb55f6 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -3090,6 +3090,7 @@ static struct scsi_host_template driver_template = {
 	.name = "IBM POWER Virtual FC Adapter",
 	.proc_name = IBMVFC_NAME,
 	.queuecommand = ibmvfc_queuecommand,
+	.eh_timed_out = fc_eh_timed_out,
 	.eh_abort_handler = ibmvfc_eh_abort_handler,
 	.eh_device_reset_handler = ibmvfc_eh_device_reset_handler,
 	.eh_target_reset_handler = ibmvfc_eh_target_reset_handler,
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 50cd01165e35..1deb0a9f14a6 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -2072,6 +2072,7 @@ static struct scsi_host_template driver_template = {
 	.name = "IBM POWER Virtual SCSI Adapter " IBMVSCSI_VERSION,
 	.proc_name = "ibmvscsi",
 	.queuecommand = ibmvscsi_queuecommand,
+	.eh_timed_out = srp_timed_out,
 	.eh_abort_handler = ibmvscsi_eh_abort_handler,
 	.eh_device_reset_handler = ibmvscsi_eh_device_reset_handler,
 	.eh_host_reset_handler = ibmvscsi_eh_host_reset_handler,
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 99b747cedbeb..0f807798c624 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -3816,6 +3816,7 @@ static struct configfs_attribute *ibmvscsis_tpg_attrs[] = {
 static const struct target_core_fabric_ops ibmvscsis_ops = {
 	.module				= THIS_MODULE,
 	.name				= "ibmvscsis",
+	.max_data_sg_nents		= MAX_TXU / PAGE_SIZE,
 	.get_fabric_name		= ibmvscsis_get_fabric_name,
 	.tpg_get_wwn			= ibmvscsis_get_fabric_wwn,
 	.tpg_get_tag			= ibmvscsis_get_tag,
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index ace4f1f41b8e..4228aba1f654 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -967,6 +967,7 @@ static struct scsi_host_template iscsi_sw_tcp_sht = {
 	.sg_tablesize		= 4096,
 	.max_sectors		= 0xFFFF,
 	.cmd_per_lun		= ISCSI_DEF_CMD_PER_LUN,
+	.eh_timed_out		= iscsi_eh_cmd_timed_out,
 	.eh_abort_handler       = iscsi_eh_abort,
 	.eh_device_reset_handler= iscsi_eh_device_reset,
 	.eh_target_reset_handler = iscsi_eh_recover_target,
diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c
index 919736a74ffa..aa76f36abe03 100644
--- a/drivers/scsi/libfc/fc_lport.c
+++ b/drivers/scsi/libfc/fc_lport.c
@@ -2095,7 +2095,7 @@ int fc_lport_bsg_request(struct bsg_job *job)
 
 	bsg_reply->reply_payload_rcv_len = 0;
 	if (rsp)
-		rsp->resid_len = job->reply_payload.payload_len;
+		scsi_req(rsp)->resid_len = job->reply_payload.payload_len;
 
 	mutex_lock(&lport->lp_mutex);
 
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index f9b6fba689ff..834d1212b6d5 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1930,7 +1930,7 @@ static int iscsi_has_ping_timed_out(struct iscsi_conn *conn)
 		return 0;
 }
 
-static enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
+enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc)
 {
 	enum blk_eh_timer_return rc = BLK_EH_NOT_HANDLED;
 	struct iscsi_task *task = NULL, *running_task;
@@ -2063,6 +2063,7 @@ done:
 		     "timer reset" : "nh");
 	return rc;
 }
+EXPORT_SYMBOL_GPL(iscsi_eh_cmd_timed_out);
 
 static void iscsi_check_transport_timeouts(unsigned long data)
 {
@@ -2585,8 +2586,6 @@ int iscsi_host_add(struct Scsi_Host *shost, struct device *pdev)
 	if (!shost->cmd_per_lun)
 		shost->cmd_per_lun = ISCSI_DEF_CMD_PER_LUN;
 
-	if (!shost->transportt->eh_timed_out)
-		shost->transportt->eh_timed_out = iscsi_eh_cmd_timed_out;
 	return scsi_add_host(shost, pdev);
 }
 EXPORT_SYMBOL_GPL(iscsi_host_add);
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index 022bb6e10d98..570b2cb2da43 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -2174,12 +2174,12 @@ int sas_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 			       bio_data(rsp->bio), blk_rq_bytes(rsp));
 	if (ret > 0) {
 		/* positive number is the untransferred residual */
-		rsp->resid_len = ret;
-		req->resid_len = 0;
+		scsi_req(rsp)->resid_len = ret;
+		scsi_req(req)->resid_len = 0;
 		ret = 0;
 	} else if (ret == 0) {
-		rsp->resid_len = 0;
-		req->resid_len = 0;
+		scsi_req(rsp)->resid_len = 0;
+		scsi_req(req)->resid_len = 0;
 	}
 
 	return ret;
diff --git a/drivers/scsi/libsas/sas_host_smp.c b/drivers/scsi/libsas/sas_host_smp.c
index d24792575169..45cbbc44f4d7 100644
--- a/drivers/scsi/libsas/sas_host_smp.c
+++ b/drivers/scsi/libsas/sas_host_smp.c
@@ -274,15 +274,15 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 
 	switch (req_data[1]) {
 	case SMP_REPORT_GENERAL:
-		req->resid_len -= 8;
-		rsp->resid_len -= 32;
+		scsi_req(req)->resid_len -= 8;
+		scsi_req(rsp)->resid_len -= 32;
 		resp_data[2] = SMP_RESP_FUNC_ACC;
 		resp_data[9] = sas_ha->num_phys;
 		break;
 
 	case SMP_REPORT_MANUF_INFO:
-		req->resid_len -= 8;
-		rsp->resid_len -= 64;
+		scsi_req(req)->resid_len -= 8;
+		scsi_req(rsp)->resid_len -= 64;
 		resp_data[2] = SMP_RESP_FUNC_ACC;
 		memcpy(resp_data + 12, shost->hostt->name,
 		       SAS_EXPANDER_VENDOR_ID_LEN);
@@ -295,13 +295,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 		break;
 
 	case SMP_DISCOVER:
-		req->resid_len -= 16;
-		if ((int)req->resid_len < 0) {
-			req->resid_len = 0;
+		scsi_req(req)->resid_len -= 16;
+		if ((int)scsi_req(req)->resid_len < 0) {
+			scsi_req(req)->resid_len = 0;
 			error = -EINVAL;
 			goto out;
 		}
-		rsp->resid_len -= 56;
+		scsi_req(rsp)->resid_len -= 56;
 		sas_host_smp_discover(sas_ha, resp_data, req_data[9]);
 		break;
 
@@ -311,13 +311,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 		break;
 
 	case SMP_REPORT_PHY_SATA:
-		req->resid_len -= 16;
-		if ((int)req->resid_len < 0) {
-			req->resid_len = 0;
+		scsi_req(req)->resid_len -= 16;
+		if ((int)scsi_req(req)->resid_len < 0) {
+			scsi_req(req)->resid_len = 0;
 			error = -EINVAL;
 			goto out;
 		}
-		rsp->resid_len -= 60;
+		scsi_req(rsp)->resid_len -= 60;
 		sas_report_phy_sata(sas_ha, resp_data, req_data[9]);
 		break;
 
@@ -331,15 +331,15 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 		int to_write = req_data[4];
 
 		if (blk_rq_bytes(req) < base_frame_size + to_write * 4 ||
-		    req->resid_len < base_frame_size + to_write * 4) {
+		    scsi_req(req)->resid_len < base_frame_size + to_write * 4) {
 			resp_data[2] = SMP_RESP_INV_FRM_LEN;
 			break;
 		}
 
 		to_write = sas_host_smp_write_gpio(sas_ha, resp_data, req_data[2],
 						   req_data[3], to_write, &req_data[8]);
-		req->resid_len -= base_frame_size + to_write * 4;
-		rsp->resid_len -= 8;
+		scsi_req(req)->resid_len -= base_frame_size + to_write * 4;
+		scsi_req(rsp)->resid_len -= 8;
 		break;
 	}
 
@@ -348,13 +348,13 @@ int sas_smp_host_handler(struct Scsi_Host *shost, struct request *req,
 		break;
 
 	case SMP_PHY_CONTROL:
-		req->resid_len -= 44;
-		if ((int)req->resid_len < 0) {
-			req->resid_len = 0;
+		scsi_req(req)->resid_len -= 44;
+		if ((int)scsi_req(req)->resid_len < 0) {
+			scsi_req(req)->resid_len = 0;
 			error = -EINVAL;
 			goto out;
 		}
-		rsp->resid_len -= 8;
+		scsi_req(rsp)->resid_len -= 8;
 		sas_phy_control(sas_ha, req_data[9], req_data[10],
 				req_data[32] >> 4, req_data[33] >> 4,
 				resp_data);
diff --git a/drivers/scsi/libsas/sas_init.c b/drivers/scsi/libsas/sas_init.c
index 362da44f2948..15ef8e2e685c 100644
--- a/drivers/scsi/libsas/sas_init.c
+++ b/drivers/scsi/libsas/sas_init.c
@@ -560,7 +560,6 @@ sas_domain_attach_transport(struct sas_domain_function_template *dft)
 	i = to_sas_internal(stt);
 	i->dft = dft;
 	stt->create_work_queue = 1;
-	stt->eh_timed_out = sas_scsi_timed_out;
 	stt->eh_strategy_handler = sas_scsi_recover_host;
 
 	return stt;
diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h
index 9cf0bc260b0e..b306b7843d99 100644
--- a/drivers/scsi/libsas/sas_internal.h
+++ b/drivers/scsi/libsas/sas_internal.h
@@ -64,8 +64,6 @@ void sas_unregister_phys(struct sas_ha_struct *sas_ha);
 int  sas_register_ports(struct sas_ha_struct *sas_ha);
 void sas_unregister_ports(struct sas_ha_struct *sas_ha);
 
-enum blk_eh_timer_return sas_scsi_timed_out(struct scsi_cmnd *);
-
 int  sas_init_events(struct sas_ha_struct *sas_ha);
 void sas_disable_revalidation(struct sas_ha_struct *ha);
 void sas_enable_revalidation(struct sas_ha_struct *ha);
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index 519dac4e341e..9bd55bce83af 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -803,13 +803,6 @@ out:
 		    shost->host_failed, tries);
 }
 
-enum blk_eh_timer_return sas_scsi_timed_out(struct scsi_cmnd *cmd)
-{
-	scmd_dbg(cmd, "command %p timed out\n", cmd);
-
-	return BLK_EH_NOT_HANDLED;
-}
-
 int sas_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 {
 	struct domain_device *dev = sdev_to_domain_dev(sdev);
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 8a20b4e86224..6593b073c524 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -727,7 +727,6 @@ struct lpfc_hba {
 	uint32_t cfg_fcp_io_channel;
 	uint32_t cfg_total_seg_cnt;
 	uint32_t cfg_sg_seg_cnt;
-	uint32_t cfg_prot_sg_seg_cnt;
 	uint32_t cfg_sg_dma_buf_size;
 	uint64_t cfg_soft_wwnn;
 	uint64_t cfg_soft_wwpn;
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index c84775562c65..50cf402dea29 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -2073,6 +2073,13 @@ lpfc_soft_wwn_enable_store(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 
 	phba->soft_wwn_enable = 1;
+
+	dev_printk(KERN_WARNING, &phba->pcidev->dev,
+		   "lpfc%d: soft_wwpn assignment has been enabled.\n",
+		   phba->brd_no);
+	dev_printk(KERN_WARNING, &phba->pcidev->dev,
+		   "  The soft_wwpn feature is not supported by Broadcom.");
+
 	return count;
 }
 static DEVICE_ATTR(lpfc_soft_wwn_enable, S_IWUSR, NULL,
@@ -2143,7 +2150,7 @@ lpfc_soft_wwpn_store(struct device *dev, struct device_attribute *attr,
 	phba->soft_wwn_enable = 0;
 
 	rc = lpfc_wwn_set(buf, cnt, wwpn);
-	if (!rc) {
+	if (rc) {
 		/* not able to set wwpn, unlock it */
 		phba->soft_wwn_enable = 1;
 		return rc;
@@ -2224,7 +2231,7 @@ lpfc_soft_wwnn_store(struct device *dev, struct device_attribute *attr,
 		return -EINVAL;
 
 	rc = lpfc_wwn_set(buf, cnt, wwnn);
-	if (!rc) {
+	if (rc) {
 		/* Allow wwnn to be set many times, as long as the enable
 		 * is set. However, once the wwpn is set, everything locks.
 		 */
@@ -2435,7 +2442,8 @@ lpfc_oas_vpt_store(struct device *dev, struct device_attribute *attr,
 	else
 		phba->cfg_oas_flags &= ~OAS_FIND_ANY_VPORT;
 	phba->cfg_oas_flags &= ~OAS_LUN_VALID;
-	phba->cfg_oas_priority = phba->cfg_XLanePriority;
+	if (phba->cfg_oas_priority == 0)
+		phba->cfg_oas_priority = phba->cfg_XLanePriority;
 	phba->sli4_hba.oas_next_lun = FIND_FIRST_OAS_LUN;
 	return count;
 }
@@ -2561,7 +2569,7 @@ lpfc_oas_lun_state_set(struct lpfc_hba *phba, uint8_t vpt_wwpn[],
 			rc = -ENOMEM;
 	} else {
 		lpfc_disable_oas_lun(phba, (struct lpfc_name *)vpt_wwpn,
-				     (struct lpfc_name *)tgt_wwpn, lun);
+				     (struct lpfc_name *)tgt_wwpn, lun, pri);
 	}
 	return rc;
 
@@ -2585,7 +2593,8 @@ lpfc_oas_lun_state_set(struct lpfc_hba *phba, uint8_t vpt_wwpn[],
  */
 static uint64_t
 lpfc_oas_lun_get_next(struct lpfc_hba *phba, uint8_t vpt_wwpn[],
-		      uint8_t tgt_wwpn[], uint32_t *lun_status)
+		      uint8_t tgt_wwpn[], uint32_t *lun_status,
+		      uint32_t *lun_pri)
 {
 	uint64_t found_lun;
 
@@ -2598,7 +2607,7 @@ lpfc_oas_lun_get_next(struct lpfc_hba *phba, uint8_t vpt_wwpn[],
 				   &phba->sli4_hba.oas_next_lun,
 				   (struct lpfc_name *)vpt_wwpn,
 				   (struct lpfc_name *)tgt_wwpn,
-				   &found_lun, lun_status))
+				   &found_lun, lun_status, lun_pri))
 		return found_lun;
 	else
 		return NOT_OAS_ENABLED_LUN;
@@ -2670,7 +2679,8 @@ lpfc_oas_lun_show(struct device *dev, struct device_attribute *attr,
 
 	oas_lun = lpfc_oas_lun_get_next(phba, phba->cfg_oas_vpt_wwpn,
 					phba->cfg_oas_tgt_wwpn,
-					&phba->cfg_oas_lun_status);
+					&phba->cfg_oas_lun_status,
+					&phba->cfg_oas_priority);
 	if (oas_lun != NOT_OAS_ENABLED_LUN)
 		phba->cfg_oas_flags |= OAS_LUN_VALID;
 
@@ -2701,6 +2711,7 @@ lpfc_oas_lun_store(struct device *dev, struct device_attribute *attr,
 	struct Scsi_Host *shost = class_to_shost(dev);
 	struct lpfc_hba *phba = ((struct lpfc_vport *)shost->hostdata)->phba;
 	uint64_t scsi_lun;
+	uint32_t pri;
 	ssize_t rc;
 
 	if (!phba->cfg_fof)
@@ -2718,17 +2729,20 @@ lpfc_oas_lun_store(struct device *dev, struct device_attribute *attr,
 	if (sscanf(buf, "0x%llx", &scsi_lun) != 1)
 		return -EINVAL;
 
+	pri = phba->cfg_oas_priority;
+	if (pri == 0)
+		pri = phba->cfg_XLanePriority;
+
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT,
 			"3372 Try to set vport 0x%llx target 0x%llx lun:0x%llx "
 			"priority 0x%x with oas state %d\n",
 			wwn_to_u64(phba->cfg_oas_vpt_wwpn),
 			wwn_to_u64(phba->cfg_oas_tgt_wwpn), scsi_lun,
-			phba->cfg_oas_priority, phba->cfg_oas_lun_state);
+			pri, phba->cfg_oas_lun_state);
 
 	rc = lpfc_oas_lun_state_change(phba, phba->cfg_oas_vpt_wwpn,
 				       phba->cfg_oas_tgt_wwpn, scsi_lun,
-				       phba->cfg_oas_lun_state,
-				       phba->cfg_oas_priority);
+				       phba->cfg_oas_lun_state, pri);
 	if (rc)
 		return rc;
 
@@ -4670,14 +4684,6 @@ LPFC_ATTR_R(sg_seg_cnt, LPFC_DEFAULT_SG_SEG_CNT, LPFC_DEFAULT_SG_SEG_CNT,
 	    LPFC_MAX_SG_SEG_CNT, "Max Scatter Gather Segment Count");
 
 /*
- * This parameter will be depricated, the driver cannot limit the
- * protection data s/g list.
- */
-LPFC_ATTR_R(prot_sg_seg_cnt, LPFC_DEFAULT_SG_SEG_CNT,
-	    LPFC_DEFAULT_SG_SEG_CNT, LPFC_MAX_SG_SEG_CNT,
-	    "Max Protection Scatter Gather Segment Count");
-
-/*
  * lpfc_enable_mds_diags: Enable MDS Diagnostics
  *       0  = MDS Diagnostics disabled (default)
  *       1  = MDS Diagnostics enabled
@@ -4766,7 +4772,6 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_sg_seg_cnt,
 	&dev_attr_lpfc_max_scsicmpl_time,
 	&dev_attr_lpfc_stat_data_ctrl,
-	&dev_attr_lpfc_prot_sg_seg_cnt,
 	&dev_attr_lpfc_aer_support,
 	&dev_attr_lpfc_aer_state_cleanup,
 	&dev_attr_lpfc_sriov_nr_virtfn,
@@ -5061,6 +5066,19 @@ lpfc_free_sysfs_attr(struct lpfc_vport *vport)
  */
 
 /**
+ * lpfc_get_host_symbolic_name - Copy symbolic name into the scsi host
+ * @shost: kernel scsi host pointer.
+ **/
+static void
+lpfc_get_host_symbolic_name(struct Scsi_Host *shost)
+{
+	struct lpfc_vport *vport = (struct lpfc_vport *)shost->hostdata;
+
+	lpfc_vport_symbolic_node_name(vport, fc_host_symbolic_name(shost),
+				      sizeof fc_host_symbolic_name(shost));
+}
+
+/**
  * lpfc_get_host_port_id - Copy the vport DID into the scsi host port id
  * @shost: kernel scsi host pointer.
  **/
@@ -5597,6 +5615,8 @@ struct fc_function_template lpfc_transport_functions = {
 	.show_host_supported_fc4s = 1,
 	.show_host_supported_speeds = 1,
 	.show_host_maxframe_size = 1,
+
+	.get_host_symbolic_name = lpfc_get_host_symbolic_name,
 	.show_host_symbolic_name = 1,
 
 	/* dynamic attributes the driver supports */
@@ -5664,6 +5684,8 @@ struct fc_function_template lpfc_vport_transport_functions = {
 	.show_host_supported_fc4s = 1,
 	.show_host_supported_speeds = 1,
 	.show_host_maxframe_size = 1,
+
+	.get_host_symbolic_name = lpfc_get_host_symbolic_name,
 	.show_host_symbolic_name = 1,
 
 	/* dynamic attributes the driver supports */
@@ -5768,7 +5790,6 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	phba->cfg_soft_wwnn = 0L;
 	phba->cfg_soft_wwpn = 0L;
 	lpfc_sg_seg_cnt_init(phba, lpfc_sg_seg_cnt);
-	lpfc_prot_sg_seg_cnt_init(phba, lpfc_prot_sg_seg_cnt);
 	lpfc_hba_queue_depth_init(phba, lpfc_hba_queue_depth);
 	lpfc_hba_log_verbose_init(phba, lpfc_log_verbose);
 	lpfc_aer_support_init(phba, lpfc_aer_support);
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 15d2bfdf582d..309643a2c55c 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -480,7 +480,7 @@ void lpfc_sli4_offline_eratt(struct lpfc_hba *);
 struct lpfc_device_data *lpfc_create_device_data(struct lpfc_hba *,
 						struct lpfc_name *,
 						struct lpfc_name *,
-						uint64_t, bool);
+						uint64_t, uint32_t,  bool);
 void lpfc_delete_device_data(struct lpfc_hba *, struct lpfc_device_data*);
 struct lpfc_device_data *__lpfc_get_device_data(struct lpfc_hba *,
 					struct list_head *list,
@@ -489,9 +489,10 @@ struct lpfc_device_data *__lpfc_get_device_data(struct lpfc_hba *,
 bool lpfc_enable_oas_lun(struct lpfc_hba *, struct lpfc_name *,
 			 struct lpfc_name *, uint64_t, uint8_t);
 bool lpfc_disable_oas_lun(struct lpfc_hba *, struct lpfc_name *,
-			  struct lpfc_name *, uint64_t);
+			  struct lpfc_name *, uint64_t, uint8_t);
 bool lpfc_find_next_oas_lun(struct lpfc_hba *, struct lpfc_name *,
 			    struct lpfc_name *, uint64_t *, struct lpfc_name *,
-			    struct lpfc_name *, uint64_t *, uint32_t *);
+			    struct lpfc_name *, uint64_t *,
+			    uint32_t *, uint32_t *);
 int lpfc_sli4_dump_page_a0(struct lpfc_hba *phba, struct lpfcMboxq *mbox);
 void lpfc_mbx_cmpl_rdp_page_a0(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb);
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.c b/drivers/scsi/lpfc/lpfc_debugfs.c
index a63542bac153..caa7a7b0ec53 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.c
+++ b/drivers/scsi/lpfc/lpfc_debugfs.c
@@ -607,7 +607,7 @@ lpfc_debugfs_nodelist_data(struct lpfc_vport *vport, char *buf, int size)
 		len += snprintf(buf+len, size-len, "usgmap:%x ",
 			ndlp->nlp_usg_map);
 		len += snprintf(buf+len, size-len, "refcnt:%x",
-			atomic_read(&ndlp->kref.refcount));
+			kref_read(&ndlp->kref));
 		len +=  snprintf(buf+len, size-len, "\n");
 	}
 	spin_unlock_irq(shost->host_lock);
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 7b6bd8ed0d0b..3a1f1a2a2b55 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -1999,6 +1999,9 @@ lpfc_issue_els_plogi(struct lpfc_vport *vport, uint32_t did, uint8_t retry)
 	if (sp->cmn.fcphHigh < FC_PH3)
 		sp->cmn.fcphHigh = FC_PH3;
 
+	sp->cmn.valid_vendor_ver_level = 0;
+	memset(sp->vendorVersion, 0, sizeof(sp->vendorVersion));
+
 	lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_CMD,
 		"Issue PLOGI:     did:x%x",
 		did, 0, 0);
@@ -3690,7 +3693,7 @@ lpfc_mbx_cmpl_dflt_rpi(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 		lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NODE,
 				 "0006 rpi%x DID:%x flg:%x %d map:%x %p\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
-				 atomic_read(&ndlp->kref.refcount),
+				 kref_read(&ndlp->kref),
 				 ndlp->nlp_usg_map, ndlp);
 		if (NLP_CHK_NODE_ACT(ndlp)) {
 			lpfc_nlp_put(ndlp);
@@ -3990,6 +3993,9 @@ lpfc_els_rsp_acc(struct lpfc_vport *vport, uint32_t flag,
 		} else {
 			memcpy(pcmd, &vport->fc_sparam,
 			       sizeof(struct serv_parm));
+
+			sp->cmn.valid_vendor_ver_level = 0;
+			memset(sp->vendorVersion, 0, sizeof(sp->vendorVersion));
 		}
 
 		lpfc_debugfs_disc_trc(vport, LPFC_DISC_TRC_ELS_RSP,
@@ -8851,8 +8857,7 @@ lpfc_cmpl_fabric_iocb(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 {
 	struct ls_rjt stat;
 
-	if ((cmdiocb->iocb_flag & LPFC_IO_FABRIC) != LPFC_IO_FABRIC)
-		BUG();
+	BUG_ON((cmdiocb->iocb_flag & LPFC_IO_FABRIC) != LPFC_IO_FABRIC);
 
 	switch (rspiocb->iocb.ulpStatus) {
 		case IOSTAT_NPORT_RJT:
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index ed223937798a..82047070cdc9 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -3440,7 +3440,7 @@ lpfc_mbx_cmpl_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
 			 "0002 rpi:%x DID:%x flg:%x %d map:%x %p\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
-			 atomic_read(&ndlp->kref.refcount),
+			 kref_read(&ndlp->kref),
 			 ndlp->nlp_usg_map, ndlp);
 	if (ndlp->nlp_flag & NLP_REG_LOGIN_SEND)
 		ndlp->nlp_flag &= ~NLP_REG_LOGIN_SEND;
@@ -3861,7 +3861,7 @@ out:
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
 			 "0003 rpi:%x DID:%x flg:%x %d map%x %p\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
-			 atomic_read(&ndlp->kref.refcount),
+			 kref_read(&ndlp->kref),
 			 ndlp->nlp_usg_map, ndlp);
 
 	if (vport->port_state < LPFC_VPORT_READY) {
@@ -4238,7 +4238,7 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				"0277 lpfc_enable_node: ndlp:x%p "
 				"usgmap:x%x refcnt:%d\n",
 				(void *)ndlp, ndlp->nlp_usg_map,
-				atomic_read(&ndlp->kref.refcount));
+				kref_read(&ndlp->kref));
 		return NULL;
 	}
 	/* The ndlp should not already be in active mode */
@@ -4248,7 +4248,7 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				"0278 lpfc_enable_node: ndlp:x%p "
 				"usgmap:x%x refcnt:%d\n",
 				(void *)ndlp, ndlp->nlp_usg_map,
-				atomic_read(&ndlp->kref.refcount));
+				kref_read(&ndlp->kref));
 		return NULL;
 	}
 
@@ -4272,7 +4272,7 @@ lpfc_enable_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				 "0008 rpi:%x DID:%x flg:%x refcnt:%d "
 				 "map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID,
 				 ndlp->nlp_flag,
-				 atomic_read(&ndlp->kref.refcount),
+				 kref_read(&ndlp->kref),
 				 ndlp->nlp_usg_map, ndlp);
 	}
 
@@ -4546,7 +4546,7 @@ lpfc_unreg_rpi(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 				    (bf_get(lpfc_sli_intf_if_type,
 				     &phba->sli4_hba.sli_intf) ==
 				      LPFC_SLI_INTF_IF_TYPE_2) &&
-				    (atomic_read(&ndlp->kref.refcount) > 0)) {
+				    (kref_read(&ndlp->kref) > 0)) {
 					mbox->context1 = lpfc_nlp_get(ndlp);
 					mbox->mbox_cmpl =
 						lpfc_sli4_unreg_rpi_cmpl_clr;
@@ -4695,14 +4695,14 @@ lpfc_cleanup_node(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 				"0280 lpfc_cleanup_node: ndlp:x%p "
 				"usgmap:x%x refcnt:%d\n",
 				(void *)ndlp, ndlp->nlp_usg_map,
-				atomic_read(&ndlp->kref.refcount));
+				kref_read(&ndlp->kref));
 		lpfc_dequeue_node(vport, ndlp);
 	} else {
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_NODE,
 				"0281 lpfc_cleanup_node: ndlp:x%p "
 				"usgmap:x%x refcnt:%d\n",
 				(void *)ndlp, ndlp->nlp_usg_map,
-				atomic_read(&ndlp->kref.refcount));
+				kref_read(&ndlp->kref));
 		lpfc_disable_node(vport, ndlp);
 	}
 
@@ -4791,7 +4791,7 @@ lpfc_nlp_remove(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NODE,
 				 "0005 rpi:%x DID:%x flg:%x %d map:%x %p\n",
 				 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
-				 atomic_read(&ndlp->kref.refcount),
+				 kref_read(&ndlp->kref),
 				 ndlp->nlp_usg_map, ndlp);
 		if ((mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL))
 			!= NULL) {
@@ -5557,7 +5557,7 @@ lpfc_mbx_cmpl_fdmi_reg_login(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
 			 "0004 rpi:%x DID:%x flg:%x %d map:%x %p\n",
 			 ndlp->nlp_rpi, ndlp->nlp_DID, ndlp->nlp_flag,
-			 atomic_read(&ndlp->kref.refcount),
+			 kref_read(&ndlp->kref),
 			 ndlp->nlp_usg_map, ndlp);
 	/*
 	 * Start issuing Fabric-Device Management Interface (FDMI) command to
@@ -5728,7 +5728,7 @@ lpfc_nlp_init(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 				 "0007 rpi:%x DID:%x flg:%x refcnt:%d "
 				 "map:%x %p\n", ndlp->nlp_rpi, ndlp->nlp_DID,
 				 ndlp->nlp_flag,
-				 atomic_read(&ndlp->kref.refcount),
+				 kref_read(&ndlp->kref),
 				 ndlp->nlp_usg_map, ndlp);
 
 		ndlp->active_rrqs_xri_bitmap =
@@ -5767,7 +5767,7 @@ lpfc_nlp_release(struct kref *kref)
 			"0279 lpfc_nlp_release: ndlp:x%p did %x "
 			"usgmap:x%x refcnt:%d rpi:%x\n",
 			(void *)ndlp, ndlp->nlp_DID, ndlp->nlp_usg_map,
-			atomic_read(&ndlp->kref.refcount), ndlp->nlp_rpi);
+			kref_read(&ndlp->kref), ndlp->nlp_rpi);
 
 	/* remove ndlp from action. */
 	lpfc_nlp_remove(ndlp->vport, ndlp);
@@ -5804,7 +5804,7 @@ lpfc_nlp_get(struct lpfc_nodelist *ndlp)
 		lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE,
 			"node get:        did:x%x flg:x%x refcnt:x%x",
 			ndlp->nlp_DID, ndlp->nlp_flag,
-			atomic_read(&ndlp->kref.refcount));
+			kref_read(&ndlp->kref));
 		/* The check of ndlp usage to prevent incrementing the
 		 * ndlp reference count that is in the process of being
 		 * released.
@@ -5817,7 +5817,7 @@ lpfc_nlp_get(struct lpfc_nodelist *ndlp)
 				"0276 lpfc_nlp_get: ndlp:x%p "
 				"usgmap:x%x refcnt:%d\n",
 				(void *)ndlp, ndlp->nlp_usg_map,
-				atomic_read(&ndlp->kref.refcount));
+				kref_read(&ndlp->kref));
 			return NULL;
 		} else
 			kref_get(&ndlp->kref);
@@ -5844,7 +5844,7 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp)
 	lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE,
 	"node put:        did:x%x flg:x%x refcnt:x%x",
 		ndlp->nlp_DID, ndlp->nlp_flag,
-		atomic_read(&ndlp->kref.refcount));
+		kref_read(&ndlp->kref));
 	phba = ndlp->phba;
 	spin_lock_irqsave(&phba->ndlp_lock, flags);
 	/* Check the ndlp memory free acknowledge flag to avoid the
@@ -5857,7 +5857,7 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp)
 				"0274 lpfc_nlp_put: ndlp:x%p "
 				"usgmap:x%x refcnt:%d\n",
 				(void *)ndlp, ndlp->nlp_usg_map,
-				atomic_read(&ndlp->kref.refcount));
+				kref_read(&ndlp->kref));
 		return 1;
 	}
 	/* Check the ndlp inactivate log flag to avoid the possible
@@ -5870,7 +5870,7 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp)
 				"0275 lpfc_nlp_put: ndlp:x%p "
 				"usgmap:x%x refcnt:%d\n",
 				(void *)ndlp, ndlp->nlp_usg_map,
-				atomic_read(&ndlp->kref.refcount));
+				kref_read(&ndlp->kref));
 		return 1;
 	}
 	/* For last put, mark the ndlp usage flags to make sure no
@@ -5878,7 +5878,7 @@ lpfc_nlp_put(struct lpfc_nodelist *ndlp)
 	 * in between the process when the final kref_put has been
 	 * invoked on this ndlp.
 	 */
-	if (atomic_read(&ndlp->kref.refcount) == 1) {
+	if (kref_read(&ndlp->kref) == 1) {
 		/* Indicate ndlp is put to inactive state. */
 		NLP_SET_IACT_REQ(ndlp);
 		/* Acknowledge ndlp memory free has been seen. */
@@ -5906,8 +5906,8 @@ lpfc_nlp_not_used(struct lpfc_nodelist *ndlp)
 	lpfc_debugfs_disc_trc(ndlp->vport, LPFC_DISC_TRC_NODE,
 		"node not used:   did:x%x flg:x%x refcnt:x%x",
 		ndlp->nlp_DID, ndlp->nlp_flag,
-		atomic_read(&ndlp->kref.refcount));
-	if (atomic_read(&ndlp->kref.refcount) == 1)
+		kref_read(&ndlp->kref));
+	if (kref_read(&ndlp->kref) == 1)
 		if (lpfc_nlp_put(ndlp))
 			return 1;
 	return 0;
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 822654322e67..3b970d370600 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -360,6 +360,12 @@ struct csp {
  * Word 1 Bit 30 in PLOGI request is random offset
  */
 #define virtual_fabric_support randomOffset /* Word 1, bit 30 */
+/*
+ * Word 1 Bit 29 in common service parameter is overloaded.
+ * Word 1 Bit 29 in FLOGI response is multiple NPort assignment
+ * Word 1 Bit 29 in FLOGI/PLOGI request is Valid Vendor Version Level
+ */
+#define valid_vendor_ver_level response_multiple_NPort /* Word 1, bit 29 */
 #ifdef __BIG_ENDIAN_BITFIELD
 	uint16_t request_multiple_Nport:1;	/* FC Word 1, bit 31 */
 	uint16_t randomOffset:1;	/* FC Word 1, bit 30 */
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 4776fd85514f..64717c171b15 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -2660,8 +2660,7 @@ lpfc_cleanup(struct lpfc_vport *vport)
 						"usgmap:x%x refcnt:%d\n",
 						ndlp->nlp_DID, (void *)ndlp,
 						ndlp->nlp_usg_map,
-						atomic_read(
-							&ndlp->kref.refcount));
+						kref_read(&ndlp->kref));
 			}
 			break;
 		}
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index ad350d969bdc..1180a22beb43 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -5452,7 +5452,9 @@ lpfc_slave_alloc(struct scsi_device *sdev)
 			device_data = lpfc_create_device_data(phba,
 							&vport->fc_portname,
 							&target_wwpn,
-							sdev->lun, true);
+							sdev->lun,
+							phba->cfg_XLanePriority,
+							true);
 			if (!device_data)
 				return -ENOMEM;
 			spin_lock_irqsave(&phba->devicelock, flags);
@@ -5587,7 +5589,7 @@ lpfc_slave_destroy(struct scsi_device *sdev)
 struct lpfc_device_data*
 lpfc_create_device_data(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 			struct lpfc_name *target_wwpn, uint64_t lun,
-			bool atomic_create)
+			uint32_t pri, bool atomic_create)
 {
 
 	struct lpfc_device_data *lun_info;
@@ -5614,7 +5616,7 @@ lpfc_create_device_data(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 	       sizeof(struct lpfc_name));
 	lun_info->device_id.lun = lun;
 	lun_info->oas_enabled = false;
-	lun_info->priority = phba->cfg_XLanePriority;
+	lun_info->priority = pri;
 	lun_info->available = false;
 	return lun_info;
 }
@@ -5716,7 +5718,8 @@ lpfc_find_next_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 		       struct lpfc_name *found_vport_wwpn,
 		       struct lpfc_name *found_target_wwpn,
 		       uint64_t *found_lun,
-		       uint32_t *found_lun_status)
+		       uint32_t *found_lun_status,
+		       uint32_t *found_lun_pri)
 {
 
 	unsigned long flags;
@@ -5763,6 +5766,7 @@ lpfc_find_next_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 						OAS_LUN_STATUS_EXISTS;
 				else
 					*found_lun_status = 0;
+				*found_lun_pri = lun_info->priority;
 				if (phba->cfg_oas_flags & OAS_FIND_ANY_VPORT)
 					memset(vport_wwpn, 0x0,
 					       sizeof(struct lpfc_name));
@@ -5824,13 +5828,14 @@ lpfc_enable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 	if (lun_info) {
 		if (!lun_info->oas_enabled)
 			lun_info->oas_enabled = true;
+		lun_info->priority = pri;
 		spin_unlock_irqrestore(&phba->devicelock, flags);
 		return true;
 	}
 
 	/* Create an lun info structure and add to list of luns */
 	lun_info = lpfc_create_device_data(phba, vport_wwpn, target_wwpn, lun,
-					   false);
+					   pri, false);
 	if (lun_info) {
 		lun_info->oas_enabled = true;
 		lun_info->priority = pri;
@@ -5864,7 +5869,7 @@ lpfc_enable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
  **/
 bool
 lpfc_disable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
-		     struct lpfc_name *target_wwpn, uint64_t lun)
+		     struct lpfc_name *target_wwpn, uint64_t lun, uint8_t pri)
 {
 
 	struct lpfc_device_data *lun_info;
@@ -5882,6 +5887,7 @@ lpfc_disable_oas_lun(struct lpfc_hba *phba, struct lpfc_name *vport_wwpn,
 					  target_wwpn, lun);
 	if (lun_info) {
 		lun_info->oas_enabled = false;
+		lun_info->priority = pri;
 		if (!lun_info->available)
 			lpfc_delete_device_data(phba, lun_info);
 		spin_unlock_irqrestore(&phba->devicelock, flags);
@@ -5923,6 +5929,7 @@ struct scsi_host_template lpfc_template = {
 	.proc_name		= LPFC_DRIVER_NAME,
 	.info			= lpfc_info,
 	.queuecommand		= lpfc_queuecommand,
+	.eh_timed_out		= fc_eh_timed_out,
 	.eh_abort_handler	= lpfc_abort_handler,
 	.eh_device_reset_handler = lpfc_device_reset_handler,
 	.eh_target_reset_handler = lpfc_target_reset_handler,
@@ -5949,6 +5956,7 @@ struct scsi_host_template lpfc_vport_template = {
 	.proc_name		= LPFC_DRIVER_NAME,
 	.info			= lpfc_info,
 	.queuecommand		= lpfc_queuecommand,
+	.eh_timed_out		= fc_eh_timed_out,
 	.eh_abort_handler	= lpfc_abort_handler,
 	.eh_device_reset_handler = lpfc_device_reset_handler,
 	.eh_target_reset_handler = lpfc_target_reset_handler,
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index a78a3df68f67..d977a472f89f 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -120,6 +120,8 @@ lpfc_sli4_wq_put(struct lpfc_queue *q, union lpfc_wqe *wqe)
 	if (q->phba->sli3_options & LPFC_SLI4_PHWQ_ENABLED)
 		bf_set(wqe_wqid, &wqe->generic.wqe_com, q->queue_id);
 	lpfc_sli_pcimem_bcopy(wqe, temp_wqe, q->entry_size);
+	/* ensure WQE bcopy flushed before doorbell write */
+	wmb();
 
 	/* Update the host index before invoking device */
 	host_index = q->host_index;
@@ -6313,7 +6315,8 @@ lpfc_set_host_data(struct lpfc_hba *phba, LPFC_MBOXQ_t *mbox)
 			 LPFC_SLI4_MBX_EMBED);
 
 	mbox->u.mqe.un.set_host_data.param_id = LPFC_SET_HOST_OS_DRIVER_VERSION;
-	mbox->u.mqe.un.set_host_data.param_len = 8;
+	mbox->u.mqe.un.set_host_data.param_len =
+					LPFC_HOST_OS_DRIVER_VERSION_SIZE;
 	snprintf(mbox->u.mqe.un.set_host_data.data,
 		 LPFC_HOST_OS_DRIVER_VERSION_SIZE,
 		 "Linux %s v"LPFC_DRIVER_VERSION,
@@ -10035,6 +10038,7 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 		iabt->ulpCommand = CMD_CLOSE_XRI_CN;
 
 	abtsiocbp->iocb_cmpl = lpfc_sli_abort_els_cmpl;
+	abtsiocbp->vport = vport;
 
 	lpfc_printf_vlog(vport, KERN_INFO, LOG_SLI,
 			 "0339 Abort xri x%x, original iotag x%x, "
@@ -17226,7 +17230,8 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 	unsigned long iflags = 0;
 	char *fail_msg = NULL;
 	struct lpfc_sglq *sglq;
-	union lpfc_wqe wqe;
+	union lpfc_wqe128 wqe128;
+	union lpfc_wqe *wqe = (union lpfc_wqe *) &wqe128;
 	uint32_t txq_cnt = 0;
 
 	spin_lock_irqsave(&pring->ring_lock, iflags);
@@ -17265,9 +17270,9 @@ lpfc_drain_txq(struct lpfc_hba *phba)
 		piocbq->sli4_xritag = sglq->sli4_xritag;
 		if (NO_XRI == lpfc_sli4_bpl2sgl(phba, piocbq, sglq))
 			fail_msg = "to convert bpl to sgl";
-		else if (lpfc_sli4_iocb2wqe(phba, piocbq, &wqe))
+		else if (lpfc_sli4_iocb2wqe(phba, piocbq, wqe))
 			fail_msg = "to convert iocb to wqe";
-		else if (lpfc_sli4_wq_put(phba->sli4_hba.els_wq, &wqe))
+		else if (lpfc_sli4_wq_put(phba->sli4_hba.els_wq, wqe))
 			fail_msg = " - Wq is full";
 		else
 			lpfc_sli_ringtxcmpl_put(phba, pring, piocbq);
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 50bfc43ebcb0..0ee0623a354c 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -18,7 +18,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "11.2.0.2"
+#define LPFC_DRIVER_VERSION "11.2.0.4"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index c27f4b724547..e18bbc66e83b 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -537,6 +537,12 @@ enable_vport(struct fc_vport *fc_vport)
 
 	spin_lock_irq(shost->host_lock);
 	vport->load_flag |= FC_LOADING;
+	if (vport->fc_flag & FC_VPORT_NEEDS_INIT_VPI) {
+		spin_unlock_irq(shost->host_lock);
+		lpfc_issue_init_vpi(vport);
+		goto out;
+	}
+
 	vport->fc_flag |= FC_VPORT_NEEDS_REG_VPI;
 	spin_unlock_irq(shost->host_lock);
 
@@ -557,6 +563,8 @@ enable_vport(struct fc_vport *fc_vport)
 	} else {
 		lpfc_vport_set_state(vport, FC_VPORT_FAILED);
 	}
+
+out:
 	lpfc_printf_vlog(vport, KERN_ERR, LOG_VPORT,
 			 "1827 Vport Enabled.\n");
 	return VPORT_OK;
diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c
index ccb68d12692c..196acc79714b 100644
--- a/drivers/scsi/mac_scsi.c
+++ b/drivers/scsi/mac_scsi.c
@@ -154,7 +154,7 @@ __asm__ __volatile__					\
 static inline int macscsi_pread(struct NCR5380_hostdata *hostdata,
                                 unsigned char *dst, int len)
 {
-	unsigned char *s = hostdata->pdma_io + (INPUT_DATA_REG << 4);
+	u8 __iomem *s = hostdata->pdma_io + (INPUT_DATA_REG << 4);
 	unsigned char *d = dst;
 	int n = len;
 	int transferred;
@@ -257,7 +257,7 @@ static inline int macscsi_pwrite(struct NCR5380_hostdata *hostdata,
                                  unsigned char *src, int len)
 {
 	unsigned char *s = src;
-	unsigned char *d = hostdata->pdma_io + (OUTPUT_DATA_REG << 4);
+	u8 __iomem *d = hostdata->pdma_io + (OUTPUT_DATA_REG << 4);
 	int n = len;
 	int transferred;
 
@@ -381,10 +381,10 @@ static int __init mac_scsi_probe(struct platform_device *pdev)
 
 	hostdata = shost_priv(instance);
 	hostdata->base = pio_mem->start;
-	hostdata->io = (void *)pio_mem->start;
+	hostdata->io = (u8 __iomem *)pio_mem->start;
 
 	if (pdma_mem && setup_use_pdma)
-		hostdata->pdma_io = (void *)pdma_mem->start;
+		hostdata->pdma_io = (u8 __iomem *)pdma_mem->start;
 	else
 		host_flags |= FLAG_NO_PSEUDO_DMA;
 
diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index fdd519c1dd57..e7e5974e1a2c 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -35,8 +35,8 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"06.812.07.00-rc1"
-#define MEGASAS_RELDATE				"August 22, 2016"
+#define MEGASAS_VERSION				"07.701.16.00-rc1"
+#define MEGASAS_RELDATE				"February 2, 2017"
 
 /*
  * Device IDs
@@ -56,6 +56,11 @@
 #define PCI_DEVICE_ID_LSI_INTRUDER_24		0x00cf
 #define PCI_DEVICE_ID_LSI_CUTLASS_52		0x0052
 #define PCI_DEVICE_ID_LSI_CUTLASS_53		0x0053
+#define PCI_DEVICE_ID_LSI_VENTURA		    0x0014
+#define PCI_DEVICE_ID_LSI_HARPOON		    0x0016
+#define PCI_DEVICE_ID_LSI_TOMCAT		    0x0017
+#define PCI_DEVICE_ID_LSI_VENTURA_4PORT		0x001B
+#define PCI_DEVICE_ID_LSI_CRUSADER_4PORT	0x001C
 
 /*
  * Intel HBA SSDIDs
@@ -100,7 +105,7 @@
  */
 
 /*
- * MFI stands for  MegaRAID SAS FW Interface. This is just a moniker for 
+ * MFI stands for  MegaRAID SAS FW Interface. This is just a moniker for
  * protocol between the software and firmware. Commands are issued using
  * "message frames"
  */
@@ -690,6 +695,18 @@ struct  MR_PD_INFO {
 	u8 reserved1[512-428];
 } __packed;
 
+/*
+ * Definition of structure used to expose attributes of VD or JBOD
+ * (this structure is to be filled by firmware when MR_DCMD_DRV_GET_TARGET_PROP
+ * is fired by driver)
+ */
+struct MR_TARGET_PROPERTIES {
+	u32    max_io_size_kb;
+	u32    device_qdepth;
+	u32    sector_size;
+	u8     reserved[500];
+} __packed;
+
  /*
  * defines the physical drive address structure
  */
@@ -728,7 +745,6 @@ struct megasas_pd_list {
 	u16             tid;
 	u8             driveType;
 	u8             driveState;
-	u8             interface;
 } __packed;
 
  /*
@@ -1312,7 +1328,55 @@ struct megasas_ctrl_info {
 #endif
 	} adapterOperations3;
 
-	u8          pad[0x800-0x7EC];
+	struct {
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8 reserved:7;
+	/* Indicates whether the CPLD image is part of
+	 *  the package and stored in flash
+	 */
+	u8 cpld_in_flash:1;
+#else
+	u8 cpld_in_flash:1;
+	u8 reserved:7;
+#endif
+	u8 reserved1[3];
+	/* Null terminated string. Has the version
+	 *  information if cpld_in_flash = FALSE
+	 */
+	u8 userCodeDefinition[12];
+	} cpld;  /* Valid only if upgradableCPLD is TRUE */
+
+	struct {
+	#if defined(__BIG_ENDIAN_BITFIELD)
+		u16 reserved:8;
+		u16 fw_swaps_bbu_vpd_info:1;
+		u16 support_pd_map_target_id:1;
+		u16 support_ses_ctrl_in_multipathcfg:1;
+		u16 image_upload_supported:1;
+		u16 support_encrypted_mfc:1;
+		u16 supported_enc_algo:1;
+		u16 support_ibutton_less:1;
+		u16 ctrl_info_ext_supported:1;
+	#else
+
+		u16 ctrl_info_ext_supported:1;
+		u16 support_ibutton_less:1;
+		u16 supported_enc_algo:1;
+		u16 support_encrypted_mfc:1;
+		u16 image_upload_supported:1;
+		/* FW supports LUN based association and target port based */
+		u16 support_ses_ctrl_in_multipathcfg:1;
+		/* association for the SES device connected in multipath mode */
+		/* FW defines Jbod target Id within MR_PD_CFG_SEQ */
+		u16 support_pd_map_target_id:1;
+		/* FW swaps relevant fields in MR_BBU_VPD_INFO_FIXED to
+		 *  provide the data in little endian order
+		 */
+		u16 fw_swaps_bbu_vpd_info:1;
+		u16 reserved:8;
+	#endif
+		} adapter_operations4;
+	u8 pad[0x800 - 0x7FE]; /* 0x7FE pad to 2K for expansion */
 } __packed;
 
 /*
@@ -1339,12 +1403,15 @@ struct megasas_ctrl_info {
 
 #define MEGASAS_FW_BUSY				1
 
-#define VD_EXT_DEBUG 0
+/* Driver's internal Logging levels*/
+#define OCR_LOGS    (1 << 0)
 
 #define SCAN_PD_CHANNEL	0x1
 #define SCAN_VD_CHANNEL	0x2
 
 #define MEGASAS_KDUMP_QUEUE_DEPTH               100
+#define MR_LARGE_IO_MIN_SIZE			(32 * 1024)
+#define MR_R1_LDIO_PIGGYBACK_DEFAULT		4
 
 enum MR_SCSI_CMD_TYPE {
 	READ_WRITE_LDIO = 0,
@@ -1391,7 +1458,7 @@ enum FW_BOOT_CONTEXT {
  */
 #define MEGASAS_INT_CMDS			32
 #define MEGASAS_SKINNY_INT_CMDS			5
-#define MEGASAS_FUSION_INTERNAL_CMDS		5
+#define MEGASAS_FUSION_INTERNAL_CMDS		8
 #define MEGASAS_FUSION_IOCTL_CMDS		3
 #define MEGASAS_MFI_IOCTL_CMDS			27
 
@@ -1429,13 +1496,19 @@ enum FW_BOOT_CONTEXT {
 #define MR_MAX_REPLY_QUEUES_EXT_OFFSET_SHIFT    14
 #define MR_MAX_MSIX_REG_ARRAY                   16
 #define MR_RDPQ_MODE_OFFSET			0X00800000
+
+#define MR_MAX_RAID_MAP_SIZE_OFFSET_SHIFT	16
+#define MR_MAX_RAID_MAP_SIZE_MASK		0x1FF
+#define MR_MIN_MAP_SIZE				0x10000
+/* 64k */
+
 #define MR_CAN_HANDLE_SYNC_CACHE_OFFSET		0X01000000
 
 /*
 * register set for both 1068 and 1078 controllers
 * structure extended for 1078 registers
 */
- 
+
 struct megasas_register_set {
 	u32	doorbell;                       /*0000h*/
 	u32	fusion_seq_offset;		/*0004h*/
@@ -1471,14 +1544,14 @@ struct megasas_register_set {
 	u32 	outbound_scratch_pad ;		/*00B0h*/
 	u32	outbound_scratch_pad_2;         /*00B4h*/
 	u32	outbound_scratch_pad_3;         /*00B8h*/
+	u32	outbound_scratch_pad_4;         /*00BCh*/
 
-	u32	reserved_4;			/*00BCh*/
 
 	u32 	inbound_low_queue_port ;	/*00C0h*/
 
 	u32 	inbound_high_queue_port ;	/*00C4h*/
 
-	u32 	reserved_5;			/*00C8h*/
+	u32 inbound_single_queue_port;	/*00C8h*/
 	u32	res_6[11];			/*CCh*/
 	u32	host_diag;
 	u32	seq_offset;
@@ -1544,33 +1617,35 @@ union megasas_sgl_frame {
 typedef union _MFI_CAPABILITIES {
 	struct {
 #if   defined(__BIG_ENDIAN_BITFIELD)
-		u32     reserved:20;
-		u32     support_qd_throttling:1;
-		u32     support_fp_rlbypass:1;
-		u32     support_vfid_in_ioframe:1;
-		u32     support_ext_io_size:1;
-		u32	support_ext_queue_depth:1;
-		u32     security_protocol_cmds_fw:1;
-		u32     support_core_affinity:1;
-		u32     support_ndrive_r1_lb:1;
-		u32	support_max_255lds:1;
-		u32	support_fastpath_wb:1;
-		u32     support_additional_msix:1;
-		u32     support_fp_remote_lun:1;
+	u32     reserved:19;
+	u32 support_pd_map_target_id:1;
+	u32     support_qd_throttling:1;
+	u32     support_fp_rlbypass:1;
+	u32     support_vfid_in_ioframe:1;
+	u32     support_ext_io_size:1;
+	u32		support_ext_queue_depth:1;
+	u32     security_protocol_cmds_fw:1;
+	u32     support_core_affinity:1;
+	u32     support_ndrive_r1_lb:1;
+	u32		support_max_255lds:1;
+	u32		support_fastpath_wb:1;
+	u32     support_additional_msix:1;
+	u32     support_fp_remote_lun:1;
 #else
-		u32     support_fp_remote_lun:1;
-		u32     support_additional_msix:1;
-		u32	support_fastpath_wb:1;
-		u32	support_max_255lds:1;
-		u32     support_ndrive_r1_lb:1;
-		u32     support_core_affinity:1;
-		u32     security_protocol_cmds_fw:1;
-		u32	support_ext_queue_depth:1;
-		u32     support_ext_io_size:1;
-		u32     support_vfid_in_ioframe:1;
-		u32     support_fp_rlbypass:1;
-		u32     support_qd_throttling:1;
-		u32     reserved:20;
+	u32     support_fp_remote_lun:1;
+	u32     support_additional_msix:1;
+	u32		support_fastpath_wb:1;
+	u32		support_max_255lds:1;
+	u32     support_ndrive_r1_lb:1;
+	u32     support_core_affinity:1;
+	u32     security_protocol_cmds_fw:1;
+	u32		support_ext_queue_depth:1;
+	u32     support_ext_io_size:1;
+	u32     support_vfid_in_ioframe:1;
+	u32     support_fp_rlbypass:1;
+	u32     support_qd_throttling:1;
+	u32	support_pd_map_target_id:1;
+	u32     reserved:19;
 #endif
 	} mfi_capabilities;
 	__le32		reg;
@@ -1803,6 +1878,8 @@ union megasas_frame {
 struct MR_PRIV_DEVICE {
 	bool is_tm_capable;
 	bool tm_busy;
+	atomic_t r1_ldio_hint;
+	u8   interface_type;
 };
 struct megasas_cmd;
 
@@ -1994,17 +2071,24 @@ struct MR_DRV_SYSTEM_INFO {
 };
 
 enum MR_PD_TYPE {
-		 UNKNOWN_DRIVE = 0,
-		 PARALLEL_SCSI = 1,
-		 SAS_PD = 2,
-		 SATA_PD = 3,
-		 FC_PD = 4,
+	UNKNOWN_DRIVE = 0,
+	PARALLEL_SCSI = 1,
+	SAS_PD = 2,
+	SATA_PD = 3,
+	FC_PD = 4,
+	NVME_PD = 5,
 };
 
 /* JBOD Queue depth definitions */
 #define MEGASAS_SATA_QD	32
 #define MEGASAS_SAS_QD	64
 #define MEGASAS_DEFAULT_PD_QD	64
+#define MEGASAS_NVME_QD		32
+
+#define MR_DEFAULT_NVME_PAGE_SIZE	4096
+#define MR_DEFAULT_NVME_PAGE_SHIFT	12
+#define MR_DEFAULT_NVME_MDTS_KB		128
+#define MR_NVME_PAGE_SIZE_MASK		0x000000FF
 
 struct megasas_instance {
 
@@ -2022,6 +2106,8 @@ struct megasas_instance {
 	dma_addr_t hb_host_mem_h;
 	struct MR_PD_INFO *pd_info;
 	dma_addr_t pd_info_h;
+	struct MR_TARGET_PROPERTIES *tgt_prop;
+	dma_addr_t tgt_prop_h;
 
 	__le32 *reply_queue;
 	dma_addr_t reply_queue_h;
@@ -2039,6 +2125,7 @@ struct megasas_instance {
 	u32 crash_dump_drv_support;
 	u32 crash_dump_app_support;
 	u32 secure_jbod_support;
+	u32 support_morethan256jbod; /* FW support for more than 256 PD/JBOD */
 	bool use_seqnum_jbod_fp;   /* Added for PD sequence */
 	spinlock_t crashdump_lock;
 
@@ -2051,6 +2138,7 @@ struct megasas_instance {
 
 	u16 max_num_sge;
 	u16 max_fw_cmds;
+	u16 max_mpt_cmds;
 	u16 max_mfi_cmds;
 	u16 max_scsi_cmds;
 	u16 ldio_threshold;
@@ -2065,6 +2153,7 @@ struct megasas_instance {
 	/* used to sync fire the cmd to fw */
 	spinlock_t hba_lock;
 	/* used to synch producer, consumer ptrs in dpc */
+	spinlock_t stream_lock;
 	spinlock_t completion_lock;
 	struct dma_pool *frame_dma_pool;
 	struct dma_pool *sense_dma_pool;
@@ -2087,6 +2176,11 @@ struct megasas_instance {
 	atomic_t fw_outstanding;
 	atomic_t ldio_outstanding;
 	atomic_t fw_reset_no_pci_access;
+	atomic_t ieee_sgl;
+	atomic_t prp_sgl;
+	atomic_t sge_holes_type1;
+	atomic_t sge_holes_type2;
+	atomic_t sge_holes_type3;
 
 	struct megasas_instance_template *instancet;
 	struct tasklet_struct isr_tasklet;
@@ -2142,6 +2236,13 @@ struct megasas_instance {
 	u8 is_rdpq;
 	bool dev_handle;
 	bool fw_sync_cache_support;
+	u32 mfi_frame_size;
+	bool is_ventura;
+	bool msix_combined;
+	u16 max_raid_mapsize;
+	/* preffered count to send as LDIO irrspective of FP capable.*/
+	u8  r1_ldio_hint_default;
+	u32 nvme_page_size;
 };
 struct MR_LD_VF_MAP {
 	u32 size;
@@ -2230,12 +2331,12 @@ struct megasas_instance_template {
 	u32 (*init_adapter)(struct megasas_instance *);
 	u32 (*build_and_issue_cmd) (struct megasas_instance *,
 				    struct scsi_cmnd *);
-	int (*issue_dcmd)(struct megasas_instance *instance,
+	void (*issue_dcmd)(struct megasas_instance *instance,
 			    struct megasas_cmd *cmd);
 };
 
-#define MEGASAS_IS_LOGICAL(scp)						\
-	((scp->device->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1)
+#define MEGASAS_IS_LOGICAL(sdev)					\
+	((sdev->channel < MEGASAS_MAX_PD_CHANNELS) ? 0 : 1)
 
 #define MEGASAS_DEV_INDEX(scp)						\
 	(((scp->device->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL) +	\
@@ -2346,7 +2447,7 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 		    struct IO_REQUEST_INFO *io_info,
 		    struct RAID_CONTEXT *pRAID_Context,
 		    struct MR_DRV_RAID_MAP_ALL *map, u8 **raidLUN);
-u8 MR_TargetIdToLdGet(u32 ldTgtId, struct MR_DRV_RAID_MAP_ALL *map);
+u16 MR_TargetIdToLdGet(u32 ldTgtId, struct MR_DRV_RAID_MAP_ALL *map);
 struct MR_LD_RAID *MR_LdRaidGet(u32 ld, struct MR_DRV_RAID_MAP_ALL *map);
 u16 MR_ArPdGet(u32 ar, u32 arm, struct MR_DRV_RAID_MAP_ALL *map);
 u16 MR_LdSpanArrayGet(u32 ld, u32 span, struct MR_DRV_RAID_MAP_ALL *map);
@@ -2354,13 +2455,16 @@ __le16 MR_PdDevHandleGet(u32 pd, struct MR_DRV_RAID_MAP_ALL *map);
 u16 MR_GetLDTgtId(u32 ld, struct MR_DRV_RAID_MAP_ALL *map);
 
 __le16 get_updated_dev_handle(struct megasas_instance *instance,
-	struct LD_LOAD_BALANCE_INFO *lbInfo, struct IO_REQUEST_INFO *in_info);
+			      struct LD_LOAD_BALANCE_INFO *lbInfo,
+			      struct IO_REQUEST_INFO *in_info,
+			      struct MR_DRV_RAID_MAP_ALL *drv_map);
 void mr_update_load_balance_params(struct MR_DRV_RAID_MAP_ALL *map,
 	struct LD_LOAD_BALANCE_INFO *lbInfo);
 int megasas_get_ctrl_info(struct megasas_instance *instance);
 /* PD sequence */
 int
 megasas_sync_pd_seq_num(struct megasas_instance *instance, bool pend);
+void megasas_set_dynamic_target_properties(struct scsi_device *sdev);
 int megasas_set_crash_dump_params(struct megasas_instance *instance,
 	u8 crash_buf_state);
 void megasas_free_host_crash_buffer(struct megasas_instance *instance);
@@ -2382,4 +2486,7 @@ void megasas_update_sdev_properties(struct scsi_device *sdev);
 int megasas_reset_fusion(struct Scsi_Host *shost, int reason);
 int megasas_task_abort_fusion(struct scsi_cmnd *scmd);
 int megasas_reset_target_fusion(struct scsi_cmnd *scmd);
+u32 mega_mod64(u64 dividend, u32 divisor);
+int megasas_alloc_fusion_context(struct megasas_instance *instance);
+void megasas_free_fusion_context(struct megasas_instance *instance);
 #endif				/*LSI_MEGARAID_SAS_H */
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index d5cf15eb8c5e..7ac9a9ee9bd4 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -43,6 +43,7 @@
 #include <linux/uio.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <asm/unaligned.h>
 #include <linux/fs.h>
 #include <linux/compat.h>
 #include <linux/blkdev.h>
@@ -116,8 +117,10 @@ static int megasas_ld_list_query(struct megasas_instance *instance,
 static int megasas_issue_init_mfi(struct megasas_instance *instance);
 static int megasas_register_aen(struct megasas_instance *instance,
 				u32 seq_num, u32 class_locale_word);
-static int
-megasas_get_pd_info(struct megasas_instance *instance, u16 device_id);
+static void megasas_get_pd_info(struct megasas_instance *instance,
+				struct scsi_device *sdev);
+static int megasas_get_target_prop(struct megasas_instance *instance,
+				   struct scsi_device *sdev);
 /*
  * PCI ID table for all supported controllers
  */
@@ -155,6 +158,12 @@ static struct pci_device_id megasas_pci_table[] = {
 	/* Intruder 24 port*/
 	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_CUTLASS_52)},
 	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_CUTLASS_53)},
+	/* VENTURA */
+	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_VENTURA)},
+	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_HARPOON)},
+	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_TOMCAT)},
+	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_VENTURA_4PORT)},
+	{PCI_DEVICE(PCI_VENDOR_ID_LSI_LOGIC, PCI_DEVICE_ID_LSI_CRUSADER_4PORT)},
 	{}
 };
 
@@ -196,12 +205,12 @@ void megasas_fusion_ocr_wq(struct work_struct *work);
 static int megasas_get_ld_vf_affiliation(struct megasas_instance *instance,
 					 int initial);
 
-int
+void
 megasas_issue_dcmd(struct megasas_instance *instance, struct megasas_cmd *cmd)
 {
 	instance->instancet->fire_cmd(instance,
 		cmd->frame_phys_addr, 0, instance->reg_set);
-	return 0;
+	return;
 }
 
 /**
@@ -259,6 +268,8 @@ megasas_return_cmd(struct megasas_instance *instance, struct megasas_cmd *cmd)
 	cmd->scmd = NULL;
 	cmd->frame_count = 0;
 	cmd->flags = 0;
+	memset(cmd->frame, 0, instance->mfi_frame_size);
+	cmd->frame->io.context = cpu_to_le32(cmd->index);
 	if (!fusion && reset_devices)
 		cmd->frame->hdr.cmd = MFI_CMD_INVALID;
 	list_add(&cmd->list, (&instance->cmd_pool)->next);
@@ -989,13 +1000,14 @@ megasas_issue_polled(struct megasas_instance *instance, struct megasas_cmd *cmd)
 	frame_hdr->cmd_status = MFI_STAT_INVALID_STATUS;
 	frame_hdr->flags |= cpu_to_le16(MFI_FRAME_DONT_POST_IN_REPLY_QUEUE);
 
-	if ((atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) ||
-		(instance->instancet->issue_dcmd(instance, cmd))) {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
 			__func__, __LINE__);
 		return DCMD_NOT_FIRED;
 	}
 
+	instance->instancet->issue_dcmd(instance, cmd);
+
 	return wait_and_poll(instance, cmd, instance->requestorId ?
 			MEGASAS_ROUTINE_WAIT_TIME_VF : MFI_IO_TIMEOUT_SECS);
 }
@@ -1017,13 +1029,14 @@ megasas_issue_blocked_cmd(struct megasas_instance *instance,
 	int ret = 0;
 	cmd->cmd_status_drv = MFI_STAT_INVALID_STATUS;
 
-	if ((atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) ||
-		(instance->instancet->issue_dcmd(instance, cmd))) {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
 			__func__, __LINE__);
 		return DCMD_NOT_FIRED;
 	}
 
+	instance->instancet->issue_dcmd(instance, cmd);
+
 	if (timeout) {
 		ret = wait_event_timeout(instance->int_cmd_wait_q,
 				cmd->cmd_status_drv != MFI_STAT_INVALID_STATUS, timeout * HZ);
@@ -1081,13 +1094,14 @@ megasas_issue_blocked_abort_cmd(struct megasas_instance *instance,
 	cmd->sync_cmd = 1;
 	cmd->cmd_status_drv = MFI_STAT_INVALID_STATUS;
 
-	if ((atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) ||
-		(instance->instancet->issue_dcmd(instance, cmd))) {
+	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR) {
 		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
 			__func__, __LINE__);
 		return DCMD_NOT_FIRED;
 	}
 
+	instance->instancet->issue_dcmd(instance, cmd);
+
 	if (timeout) {
 		ret = wait_event_timeout(instance->abort_cmd_wait_q,
 				cmd->cmd_status_drv != MFI_STAT_INVALID_STATUS, timeout * HZ);
@@ -1273,7 +1287,7 @@ megasas_build_dcdb(struct megasas_instance *instance, struct scsi_cmnd *scp,
 	u16 flags = 0;
 	struct megasas_pthru_frame *pthru;
 
-	is_logical = MEGASAS_IS_LOGICAL(scp);
+	is_logical = MEGASAS_IS_LOGICAL(scp->device);
 	device_id = MEGASAS_DEV_INDEX(scp);
 	pthru = (struct megasas_pthru_frame *)cmd->frame;
 
@@ -1513,11 +1527,11 @@ inline int megasas_cmd_type(struct scsi_cmnd *cmd)
 	case WRITE_6:
 	case READ_16:
 	case WRITE_16:
-		ret = (MEGASAS_IS_LOGICAL(cmd)) ?
+		ret = (MEGASAS_IS_LOGICAL(cmd->device)) ?
 			READ_WRITE_LDIO : READ_WRITE_SYSPDIO;
 		break;
 	default:
-		ret = (MEGASAS_IS_LOGICAL(cmd)) ?
+		ret = (MEGASAS_IS_LOGICAL(cmd->device)) ?
 			NON_READ_WRITE_LDIO : NON_READ_WRITE_SYSPDIO;
 	}
 	return ret;
@@ -1537,7 +1551,7 @@ megasas_dump_pending_frames(struct megasas_instance *instance)
 	struct megasas_io_frame *ldio;
 	struct megasas_pthru_frame *pthru;
 	u32 sgcount;
-	u32 max_cmd = instance->max_fw_cmds;
+	u16 max_cmd = instance->max_fw_cmds;
 
 	dev_err(&instance->pdev->dev, "[%d]: Dumping Frame Phys Address of all pending cmds in FW\n",instance->host->host_no);
 	dev_err(&instance->pdev->dev, "[%d]: Total OS Pending cmds : %d\n",instance->host->host_no,atomic_read(&instance->fw_outstanding));
@@ -1662,7 +1676,7 @@ megasas_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	/* Check for an mpio path and adjust behavior */
 	if (atomic_read(&instance->adprecovery) == MEGASAS_ADPRESET_SM_INFAULT) {
 		if (megasas_check_mpio_paths(instance, scmd) ==
-		    (DID_RESET << 16)) {
+		    (DID_REQUEUE << 16)) {
 			return SCSI_MLQUEUE_HOST_BUSY;
 		} else {
 			scmd->result = DID_NO_CONNECT << 16;
@@ -1693,15 +1707,16 @@ megasas_queue_command(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 
 	scmd->result = 0;
 
-	if (MEGASAS_IS_LOGICAL(scmd) &&
+	if (MEGASAS_IS_LOGICAL(scmd->device) &&
 	    (scmd->device->id >= instance->fw_supported_vd_count ||
 		scmd->device->lun)) {
 		scmd->result = DID_BAD_TARGET << 16;
 		goto out_done;
 	}
 
-	if ((scmd->cmnd[0] == SYNCHRONIZE_CACHE) && MEGASAS_IS_LOGICAL(scmd) &&
-		(!instance->fw_sync_cache_support)) {
+	if ((scmd->cmnd[0] == SYNCHRONIZE_CACHE) &&
+	    MEGASAS_IS_LOGICAL(scmd->device) &&
+	    (!instance->fw_sync_cache_support)) {
 		scmd->result = DID_OK << 16;
 		goto out_done;
 	}
@@ -1728,16 +1743,21 @@ static struct megasas_instance *megasas_lookup_instance(u16 host_no)
 }
 
 /*
-* megasas_update_sdev_properties - Update sdev structure based on controller's FW capabilities
+* megasas_set_dynamic_target_properties -
+* Device property set by driver may not be static and it is required to be
+* updated after OCR
+*
+* set tm_capable.
+* set dma alignment (only for eedp protection enable vd).
 *
 * @sdev: OS provided scsi device
 *
 * Returns void
 */
-void megasas_update_sdev_properties(struct scsi_device *sdev)
+void megasas_set_dynamic_target_properties(struct scsi_device *sdev)
 {
-	u16 pd_index = 0;
-	u32 device_id, ld;
+	u16 pd_index = 0, ld;
+	u32 device_id;
 	struct megasas_instance *instance;
 	struct fusion_context *fusion;
 	struct MR_PRIV_DEVICE *mr_device_priv_data;
@@ -1749,67 +1769,129 @@ void megasas_update_sdev_properties(struct scsi_device *sdev)
 	fusion = instance->ctrl_context;
 	mr_device_priv_data = sdev->hostdata;
 
-	if (!fusion)
+	if (!fusion || !mr_device_priv_data)
 		return;
 
-	if (sdev->channel < MEGASAS_MAX_PD_CHANNELS &&
-		instance->use_seqnum_jbod_fp) {
-		pd_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) +
-			sdev->id;
-		pd_sync = (void *)fusion->pd_seq_sync
-				[(instance->pd_seq_map_id - 1) & 1];
-		mr_device_priv_data->is_tm_capable =
-			pd_sync->seq[pd_index].capability.tmCapable;
-	} else {
+	if (MEGASAS_IS_LOGICAL(sdev)) {
 		device_id = ((sdev->channel % 2) * MEGASAS_MAX_DEV_PER_CHANNEL)
 					+ sdev->id;
 		local_map_ptr = fusion->ld_drv_map[(instance->map_id & 1)];
 		ld = MR_TargetIdToLdGet(device_id, local_map_ptr);
+		if (ld >= instance->fw_supported_vd_count)
+			return;
 		raid = MR_LdRaidGet(ld, local_map_ptr);
 
 		if (raid->capability.ldPiMode == MR_PROT_INFO_TYPE_CONTROLLER)
 		blk_queue_update_dma_alignment(sdev->request_queue, 0x7);
+
 		mr_device_priv_data->is_tm_capable =
 			raid->capability.tmCapable;
+	} else if (instance->use_seqnum_jbod_fp) {
+		pd_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) +
+			sdev->id;
+		pd_sync = (void *)fusion->pd_seq_sync
+				[(instance->pd_seq_map_id - 1) & 1];
+		mr_device_priv_data->is_tm_capable =
+			pd_sync->seq[pd_index].capability.tmCapable;
 	}
 }
 
-static void megasas_set_device_queue_depth(struct scsi_device *sdev)
+/*
+ * megasas_set_nvme_device_properties -
+ * set nomerges=2
+ * set virtual page boundary = 4K (current mr_nvme_pg_size is 4K).
+ * set maximum io transfer = MDTS of NVME device provided by MR firmware.
+ *
+ * MR firmware provides value in KB. Caller of this function converts
+ * kb into bytes.
+ *
+ * e.a MDTS=5 means 2^5 * nvme page size. (In case of 4K page size,
+ * MR firmware provides value 128 as (32 * 4K) = 128K.
+ *
+ * @sdev:				scsi device
+ * @max_io_size:				maximum io transfer size
+ *
+ */
+static inline void
+megasas_set_nvme_device_properties(struct scsi_device *sdev, u32 max_io_size)
 {
-	u16				pd_index = 0;
-	int		ret = DCMD_FAILED;
 	struct megasas_instance *instance;
+	u32 mr_nvme_pg_size;
 
-	instance = megasas_lookup_instance(sdev->host->host_no);
+	instance = (struct megasas_instance *)sdev->host->hostdata;
+	mr_nvme_pg_size = max_t(u32, instance->nvme_page_size,
+				MR_DEFAULT_NVME_PAGE_SIZE);
 
-	if (sdev->channel < MEGASAS_MAX_PD_CHANNELS) {
-		pd_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) + sdev->id;
+	blk_queue_max_hw_sectors(sdev->request_queue, (max_io_size / 512));
 
-		if (instance->pd_info) {
-			mutex_lock(&instance->hba_mutex);
-			ret = megasas_get_pd_info(instance, pd_index);
-			mutex_unlock(&instance->hba_mutex);
-		}
+	queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, sdev->request_queue);
+	blk_queue_virt_boundary(sdev->request_queue, mr_nvme_pg_size - 1);
+}
 
-		if (ret != DCMD_SUCCESS)
-			return;
 
-		if (instance->pd_list[pd_index].driveState == MR_PD_STATE_SYSTEM) {
+/*
+ * megasas_set_static_target_properties -
+ * Device property set by driver are static and it is not required to be
+ * updated after OCR.
+ *
+ * set io timeout
+ * set device queue depth
+ * set nvme device properties. see - megasas_set_nvme_device_properties
+ *
+ * @sdev:				scsi device
+ * @is_target_prop			true, if fw provided target properties.
+ */
+static void megasas_set_static_target_properties(struct scsi_device *sdev,
+						 bool is_target_prop)
+{
+	u16	target_index = 0;
+	u8 interface_type;
+	u32 device_qd = MEGASAS_DEFAULT_CMD_PER_LUN;
+	u32 max_io_size_kb = MR_DEFAULT_NVME_MDTS_KB;
+	u32 tgt_device_qd;
+	struct megasas_instance *instance;
+	struct MR_PRIV_DEVICE *mr_device_priv_data;
 
-			switch (instance->pd_list[pd_index].interface) {
-			case SAS_PD:
-				scsi_change_queue_depth(sdev, MEGASAS_SAS_QD);
-				break;
+	instance = megasas_lookup_instance(sdev->host->host_no);
+	mr_device_priv_data = sdev->hostdata;
+	interface_type  = mr_device_priv_data->interface_type;
 
-			case SATA_PD:
-				scsi_change_queue_depth(sdev, MEGASAS_SATA_QD);
-				break;
+	/*
+	 * The RAID firmware may require extended timeouts.
+	 */
+	blk_queue_rq_timeout(sdev->request_queue, scmd_timeout * HZ);
 
-			default:
-				scsi_change_queue_depth(sdev, MEGASAS_DEFAULT_PD_QD);
-			}
-		}
+	target_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) + sdev->id;
+
+	switch (interface_type) {
+	case SAS_PD:
+		device_qd = MEGASAS_SAS_QD;
+		break;
+	case SATA_PD:
+		device_qd = MEGASAS_SATA_QD;
+		break;
+	case NVME_PD:
+		device_qd = MEGASAS_NVME_QD;
+		break;
+	}
+
+	if (is_target_prop) {
+		tgt_device_qd = le32_to_cpu(instance->tgt_prop->device_qdepth);
+		if (tgt_device_qd &&
+		    (tgt_device_qd <= instance->host->can_queue))
+			device_qd = tgt_device_qd;
+
+		/* max_io_size_kb will be set to non zero for
+		 * nvme based vd and syspd.
+		 */
+		max_io_size_kb = le32_to_cpu(instance->tgt_prop->max_io_size_kb);
 	}
+
+	if (instance->nvme_page_size && max_io_size_kb)
+		megasas_set_nvme_device_properties(sdev, (max_io_size_kb << 10));
+
+	scsi_change_queue_depth(sdev, device_qd);
+
 }
 
 
@@ -1817,11 +1899,12 @@ static int megasas_slave_configure(struct scsi_device *sdev)
 {
 	u16 pd_index = 0;
 	struct megasas_instance *instance;
+	int ret_target_prop = DCMD_FAILED;
+	bool is_target_prop = false;
 
 	instance = megasas_lookup_instance(sdev->host->host_no);
 	if (instance->pd_list_not_supported) {
-		if (sdev->channel < MEGASAS_MAX_PD_CHANNELS &&
-			sdev->type == TYPE_DISK) {
+		if (!MEGASAS_IS_LOGICAL(sdev) && sdev->type == TYPE_DISK) {
 			pd_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) +
 				sdev->id;
 			if (instance->pd_list[pd_index].driveState !=
@@ -1829,14 +1912,25 @@ static int megasas_slave_configure(struct scsi_device *sdev)
 				return -ENXIO;
 		}
 	}
-	megasas_set_device_queue_depth(sdev);
-	megasas_update_sdev_properties(sdev);
 
-	/*
-	 * The RAID firmware may require extended timeouts.
+	mutex_lock(&instance->hba_mutex);
+	/* Send DCMD to Firmware and cache the information */
+	if ((instance->pd_info) && !MEGASAS_IS_LOGICAL(sdev))
+		megasas_get_pd_info(instance, sdev);
+
+	/* Some ventura firmware may not have instance->nvme_page_size set.
+	 * Do not send MR_DCMD_DRV_GET_TARGET_PROP
 	 */
-	blk_queue_rq_timeout(sdev->request_queue,
-		scmd_timeout * HZ);
+	if ((instance->tgt_prop) && (instance->nvme_page_size))
+		ret_target_prop = megasas_get_target_prop(instance, sdev);
+
+	is_target_prop = (ret_target_prop == DCMD_SUCCESS) ? true : false;
+	megasas_set_static_target_properties(sdev, is_target_prop);
+
+	mutex_unlock(&instance->hba_mutex);
+
+	/* This sdev property may change post OCR */
+	megasas_set_dynamic_target_properties(sdev);
 
 	return 0;
 }
@@ -1848,7 +1942,7 @@ static int megasas_slave_alloc(struct scsi_device *sdev)
 	struct MR_PRIV_DEVICE *mr_device_priv_data;
 
 	instance = megasas_lookup_instance(sdev->host->host_no);
-	if (sdev->channel < MEGASAS_MAX_PD_CHANNELS) {
+	if (!MEGASAS_IS_LOGICAL(sdev)) {
 		/*
 		 * Open the OS scan to the SYSTEM PD
 		 */
@@ -2483,7 +2577,7 @@ static int megasas_wait_for_outstanding(struct megasas_instance *instance)
 						struct megasas_cmd, list);
 			list_del_init(&reset_cmd->list);
 			if (reset_cmd->scmd) {
-				reset_cmd->scmd->result = DID_RESET << 16;
+				reset_cmd->scmd->result = DID_REQUEUE << 16;
 				dev_notice(&instance->pdev->dev, "%d:%p reset [%02x]\n",
 					reset_index, reset_cmd,
 					reset_cmd->scmd->cmnd[0]);
@@ -2651,6 +2745,24 @@ blk_eh_timer_return megasas_reset_timer(struct scsi_cmnd *scmd)
 }
 
 /**
+ * megasas_dump_frame -	This function will dump MPT/MFI frame
+ */
+static inline void
+megasas_dump_frame(void *mpi_request, int sz)
+{
+	int i;
+	__le32 *mfp = (__le32 *)mpi_request;
+
+	printk(KERN_INFO "IO request frame:\n\t");
+	for (i = 0; i < sz / sizeof(__le32); i++) {
+		if (i && ((i % 8) == 0))
+			printk("\n\t");
+		printk("%08x ", le32_to_cpu(mfp[i]));
+	}
+	printk("\n");
+}
+
+/**
  * megasas_reset_bus_host -	Bus & host reset handler entry point
  */
 static int megasas_reset_bus_host(struct scsi_cmnd *scmd)
@@ -2660,12 +2772,26 @@ static int megasas_reset_bus_host(struct scsi_cmnd *scmd)
 
 	instance = (struct megasas_instance *)scmd->device->host->hostdata;
 
+	scmd_printk(KERN_INFO, scmd,
+		"Controller reset is requested due to IO timeout\n"
+		"SCSI command pointer: (%p)\t SCSI host state: %d\t"
+		" SCSI host busy: %d\t FW outstanding: %d\n",
+		scmd, scmd->device->host->shost_state,
+		atomic_read((atomic_t *)&scmd->device->host->host_busy),
+		atomic_read(&instance->fw_outstanding));
+
 	/*
 	 * First wait for all commands to complete
 	 */
-	if (instance->ctrl_context)
-		ret = megasas_reset_fusion(scmd->device->host, 1);
-	else
+	if (instance->ctrl_context) {
+		struct megasas_cmd_fusion *cmd;
+		cmd = (struct megasas_cmd_fusion *)scmd->SCp.ptr;
+		if (cmd)
+			megasas_dump_frame(cmd->io_request,
+				sizeof(struct MPI2_RAID_SCSI_IO_REQUEST));
+		ret = megasas_reset_fusion(scmd->device->host,
+				SCSIIO_TIMEOUT_OCR);
+	} else
 		ret = megasas_generic_reset(scmd);
 
 	return ret;
@@ -3343,7 +3469,7 @@ megasas_internal_reset_defer_cmds(struct megasas_instance *instance)
 {
 	struct megasas_cmd *cmd;
 	int i;
-	u32 max_cmd = instance->max_fw_cmds;
+	u16 max_cmd = instance->max_fw_cmds;
 	u32 defer_index;
 	unsigned long flags;
 
@@ -3719,7 +3845,7 @@ megasas_transition_to_ready(struct megasas_instance *instance, int ocr)
 static void megasas_teardown_frame_pool(struct megasas_instance *instance)
 {
 	int i;
-	u32 max_cmd = instance->max_mfi_cmds;
+	u16 max_cmd = instance->max_mfi_cmds;
 	struct megasas_cmd *cmd;
 
 	if (!instance->frame_dma_pool)
@@ -3763,9 +3889,8 @@ static void megasas_teardown_frame_pool(struct megasas_instance *instance)
 static int megasas_create_frame_pool(struct megasas_instance *instance)
 {
 	int i;
-	u32 max_cmd;
+	u16 max_cmd;
 	u32 sge_sz;
-	u32 total_sz;
 	u32 frame_count;
 	struct megasas_cmd *cmd;
 
@@ -3793,12 +3918,13 @@ static int megasas_create_frame_pool(struct megasas_instance *instance)
 	 * Total 192 byte (3 MFI frame of 64 byte)
 	 */
 	frame_count = instance->ctrl_context ? (3 + 1) : (15 + 1);
-	total_sz = MEGAMFI_FRAME_SIZE * frame_count;
+	instance->mfi_frame_size = MEGAMFI_FRAME_SIZE * frame_count;
 	/*
 	 * Use DMA pool facility provided by PCI layer
 	 */
 	instance->frame_dma_pool = pci_pool_create("megasas frame pool",
-					instance->pdev, total_sz, 256, 0);
+					instance->pdev, instance->mfi_frame_size,
+					256, 0);
 
 	if (!instance->frame_dma_pool) {
 		dev_printk(KERN_DEBUG, &instance->pdev->dev, "failed to setup frame pool\n");
@@ -3842,7 +3968,7 @@ static int megasas_create_frame_pool(struct megasas_instance *instance)
 			return -ENOMEM;
 		}
 
-		memset(cmd->frame, 0, total_sz);
+		memset(cmd->frame, 0, instance->mfi_frame_size);
 		cmd->frame->io.context = cpu_to_le32(cmd->index);
 		cmd->frame->io.pad_0 = 0;
 		if (!instance->ctrl_context && reset_devices)
@@ -3897,7 +4023,7 @@ int megasas_alloc_cmds(struct megasas_instance *instance)
 {
 	int i;
 	int j;
-	u32 max_cmd;
+	u16 max_cmd;
 	struct megasas_cmd *cmd;
 	struct fusion_context *fusion;
 
@@ -3974,18 +4100,22 @@ dcmd_timeout_ocr_possible(struct megasas_instance *instance) {
 		return INITIATE_OCR;
 }
 
-static int
-megasas_get_pd_info(struct megasas_instance *instance, u16 device_id)
+static void
+megasas_get_pd_info(struct megasas_instance *instance, struct scsi_device *sdev)
 {
 	int ret;
 	struct megasas_cmd *cmd;
 	struct megasas_dcmd_frame *dcmd;
 
+	struct MR_PRIV_DEVICE *mr_device_priv_data;
+	u16 device_id = 0;
+
+	device_id = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) + sdev->id;
 	cmd = megasas_get_cmd(instance);
 
 	if (!cmd) {
 		dev_err(&instance->pdev->dev, "Failed to get cmd %s\n", __func__);
-		return -ENOMEM;
+		return;
 	}
 
 	dcmd = &cmd->frame->dcmd;
@@ -4012,7 +4142,9 @@ megasas_get_pd_info(struct megasas_instance *instance, u16 device_id)
 
 	switch (ret) {
 	case DCMD_SUCCESS:
-		instance->pd_list[device_id].interface =
+		mr_device_priv_data = sdev->hostdata;
+		le16_to_cpus((u16 *)&instance->pd_info->state.ddf.pdType);
+		mr_device_priv_data->interface_type =
 				instance->pd_info->state.ddf.pdType.intf;
 		break;
 
@@ -4039,7 +4171,7 @@ megasas_get_pd_info(struct megasas_instance *instance, u16 device_id)
 	if (ret != DCMD_TIMEOUT)
 		megasas_return_cmd(instance, cmd);
 
-	return ret;
+	return;
 }
 /*
  * megasas_get_pd_list_info -	Returns FW's pd_list structure
@@ -4418,8 +4550,7 @@ megasas_ld_list_query(struct megasas_instance *instance, u8 query_type)
 static void megasas_update_ext_vd_details(struct megasas_instance *instance)
 {
 	struct fusion_context *fusion;
-	u32 old_map_sz;
-	u32 new_map_sz;
+	u32 ventura_map_sz = 0;
 
 	fusion = instance->ctrl_context;
 	/* For MFI based controllers return dummy success */
@@ -4449,21 +4580,27 @@ static void megasas_update_ext_vd_details(struct megasas_instance *instance)
 		instance->supportmax256vd ? "Extended VD(240 VD)firmware" :
 		"Legacy(64 VD) firmware");
 
-	old_map_sz = sizeof(struct MR_FW_RAID_MAP) +
-				(sizeof(struct MR_LD_SPAN_MAP) *
-				(instance->fw_supported_vd_count - 1));
-	new_map_sz = sizeof(struct MR_FW_RAID_MAP_EXT);
-	fusion->drv_map_sz = sizeof(struct MR_DRV_RAID_MAP) +
-				(sizeof(struct MR_LD_SPAN_MAP) *
-				(instance->drv_supported_vd_count - 1));
-
-	fusion->max_map_sz = max(old_map_sz, new_map_sz);
+	if (instance->max_raid_mapsize) {
+		ventura_map_sz = instance->max_raid_mapsize *
+						MR_MIN_MAP_SIZE; /* 64k */
+		fusion->current_map_sz = ventura_map_sz;
+		fusion->max_map_sz = ventura_map_sz;
+	} else {
+		fusion->old_map_sz =  sizeof(struct MR_FW_RAID_MAP) +
+					(sizeof(struct MR_LD_SPAN_MAP) *
+					(instance->fw_supported_vd_count - 1));
+		fusion->new_map_sz =  sizeof(struct MR_FW_RAID_MAP_EXT);
 
+		fusion->max_map_sz =
+			max(fusion->old_map_sz, fusion->new_map_sz);
 
-	if (instance->supportmax256vd)
-		fusion->current_map_sz = new_map_sz;
-	else
-		fusion->current_map_sz = old_map_sz;
+		if (instance->supportmax256vd)
+			fusion->current_map_sz = fusion->new_map_sz;
+		else
+			fusion->current_map_sz = fusion->old_map_sz;
+	}
+	/* irrespective of FW raid maps, driver raid map is constant */
+	fusion->drv_map_sz = sizeof(struct MR_DRV_RAID_MAP_ALL);
 }
 
 /**
@@ -4533,6 +4670,7 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 		le32_to_cpus((u32 *)&ctrl_info->properties.OnOffProperties);
 		le32_to_cpus((u32 *)&ctrl_info->adapterOperations2);
 		le32_to_cpus((u32 *)&ctrl_info->adapterOperations3);
+		le16_to_cpus((u16 *)&ctrl_info->adapter_operations4);
 
 		/* Update the latest Ext VD info.
 		 * From Init path, store current firmware details.
@@ -4542,6 +4680,8 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 		megasas_update_ext_vd_details(instance);
 		instance->use_seqnum_jbod_fp =
 			ctrl_info->adapterOperations3.useSeqNumJbodFP;
+		instance->support_morethan256jbod =
+			ctrl_info->adapter_operations4.support_pd_map_target_id;
 
 		/*Check whether controller is iMR or MR */
 		instance->is_imr = (ctrl_info->memory_size ? 0 : 1);
@@ -4989,13 +5129,13 @@ skip_alloc:
 static int megasas_init_fw(struct megasas_instance *instance)
 {
 	u32 max_sectors_1;
-	u32 max_sectors_2;
-	u32 tmp_sectors, msix_enable, scratch_pad_2;
+	u32 max_sectors_2, tmp_sectors, msix_enable;
+	u32 scratch_pad_2, scratch_pad_3, scratch_pad_4;
 	resource_size_t base_addr;
 	struct megasas_register_set __iomem *reg_set;
 	struct megasas_ctrl_info *ctrl_info = NULL;
 	unsigned long bar_list;
-	int i, loop, fw_msix_count = 0;
+	int i, j, loop, fw_msix_count = 0;
 	struct IOV_111 *iovPtr;
 	struct fusion_context *fusion;
 
@@ -5020,34 +5160,29 @@ static int megasas_init_fw(struct megasas_instance *instance)
 
 	reg_set = instance->reg_set;
 
-	switch (instance->pdev->device) {
-	case PCI_DEVICE_ID_LSI_FUSION:
-	case PCI_DEVICE_ID_LSI_PLASMA:
-	case PCI_DEVICE_ID_LSI_INVADER:
-	case PCI_DEVICE_ID_LSI_FURY:
-	case PCI_DEVICE_ID_LSI_INTRUDER:
-	case PCI_DEVICE_ID_LSI_INTRUDER_24:
-	case PCI_DEVICE_ID_LSI_CUTLASS_52:
-	case PCI_DEVICE_ID_LSI_CUTLASS_53:
+	if (fusion)
 		instance->instancet = &megasas_instance_template_fusion;
-		break;
-	case PCI_DEVICE_ID_LSI_SAS1078R:
-	case PCI_DEVICE_ID_LSI_SAS1078DE:
-		instance->instancet = &megasas_instance_template_ppc;
-		break;
-	case PCI_DEVICE_ID_LSI_SAS1078GEN2:
-	case PCI_DEVICE_ID_LSI_SAS0079GEN2:
-		instance->instancet = &megasas_instance_template_gen2;
-		break;
-	case PCI_DEVICE_ID_LSI_SAS0073SKINNY:
-	case PCI_DEVICE_ID_LSI_SAS0071SKINNY:
-		instance->instancet = &megasas_instance_template_skinny;
-		break;
-	case PCI_DEVICE_ID_LSI_SAS1064R:
-	case PCI_DEVICE_ID_DELL_PERC5:
-	default:
-		instance->instancet = &megasas_instance_template_xscale;
-		break;
+	else {
+		switch (instance->pdev->device) {
+		case PCI_DEVICE_ID_LSI_SAS1078R:
+		case PCI_DEVICE_ID_LSI_SAS1078DE:
+			instance->instancet = &megasas_instance_template_ppc;
+			break;
+		case PCI_DEVICE_ID_LSI_SAS1078GEN2:
+		case PCI_DEVICE_ID_LSI_SAS0079GEN2:
+			instance->instancet = &megasas_instance_template_gen2;
+			break;
+		case PCI_DEVICE_ID_LSI_SAS0073SKINNY:
+		case PCI_DEVICE_ID_LSI_SAS0071SKINNY:
+			instance->instancet = &megasas_instance_template_skinny;
+			break;
+		case PCI_DEVICE_ID_LSI_SAS1064R:
+		case PCI_DEVICE_ID_DELL_PERC5:
+		default:
+			instance->instancet = &megasas_instance_template_xscale;
+			instance->pd_list_not_supported = 1;
+			break;
+		}
 	}
 
 	if (megasas_transition_to_ready(instance, 0)) {
@@ -5066,13 +5201,13 @@ static int megasas_init_fw(struct megasas_instance *instance)
 			goto fail_ready_state;
 	}
 
-	/*
-	 * MSI-X host index 0 is common for all adapter.
-	 * It is used for all MPT based Adapters.
-	 */
-	instance->reply_post_host_index_addr[0] =
-		(u32 __iomem *)((u8 __iomem *)instance->reg_set +
-		MPI2_REPLY_POST_HOST_INDEX_OFFSET);
+	if (instance->is_ventura) {
+		scratch_pad_3 =
+			readl(&instance->reg_set->outbound_scratch_pad_3);
+		instance->max_raid_mapsize = ((scratch_pad_3 >>
+			MR_MAX_RAID_MAP_SIZE_OFFSET_SHIFT) &
+			MR_MAX_RAID_MAP_SIZE_MASK);
+	}
 
 	/* Check if MSI-X is supported while in ready state */
 	msix_enable = (instance->instancet->read_fw_status_reg(reg_set) &
@@ -5092,6 +5227,9 @@ static int megasas_init_fw(struct megasas_instance *instance)
 				instance->msix_vectors = ((scratch_pad_2
 					& MR_MAX_REPLY_QUEUES_EXT_OFFSET)
 					>> MR_MAX_REPLY_QUEUES_EXT_OFFSET_SHIFT) + 1;
+				if (instance->msix_vectors > 16)
+					instance->msix_combined = true;
+
 				if (rdpq_enable)
 					instance->is_rdpq = (scratch_pad_2 & MR_RDPQ_MODE_OFFSET) ?
 								1 : 0;
@@ -5125,6 +5263,20 @@ static int megasas_init_fw(struct megasas_instance *instance)
 		else
 			instance->msix_vectors = 0;
 	}
+	/*
+	 * MSI-X host index 0 is common for all adapter.
+	 * It is used for all MPT based Adapters.
+	 */
+	if (instance->msix_combined) {
+		instance->reply_post_host_index_addr[0] =
+				(u32 *)((u8 *)instance->reg_set +
+				MPI2_SUP_REPLY_POST_HOST_INDEX_OFFSET);
+	} else {
+		instance->reply_post_host_index_addr[0] =
+			(u32 *)((u8 *)instance->reg_set +
+			MPI2_REPLY_POST_HOST_INDEX_OFFSET);
+	}
+
 	i = pci_alloc_irq_vectors(instance->pdev, 1, 1, PCI_IRQ_LEGACY);
 	if (i < 0)
 		goto fail_setup_irqs;
@@ -5155,6 +5307,18 @@ static int megasas_init_fw(struct megasas_instance *instance)
 	if (instance->instancet->init_adapter(instance))
 		goto fail_init_adapter;
 
+	if (instance->is_ventura) {
+		scratch_pad_4 =
+			readl(&instance->reg_set->outbound_scratch_pad_4);
+		if ((scratch_pad_4 & MR_NVME_PAGE_SIZE_MASK) >=
+			MR_DEFAULT_NVME_PAGE_SHIFT)
+			instance->nvme_page_size =
+				(1 << (scratch_pad_4 & MR_NVME_PAGE_SIZE_MASK));
+
+		dev_info(&instance->pdev->dev,
+			 "NVME page size\t: (%d)\n", instance->nvme_page_size);
+	}
+
 	if (instance->msix_vectors ?
 		megasas_setup_irqs_msix(instance, 1) :
 		megasas_setup_irqs_ioapic(instance))
@@ -5173,13 +5337,43 @@ static int megasas_init_fw(struct megasas_instance *instance)
 		(MEGASAS_MAX_PD * sizeof(struct megasas_pd_list)));
 	if (megasas_get_pd_list(instance) < 0) {
 		dev_err(&instance->pdev->dev, "failed to get PD list\n");
-		goto fail_get_pd_list;
+		goto fail_get_ld_pd_list;
 	}
 
 	memset(instance->ld_ids, 0xff, MEGASAS_MAX_LD_IDS);
+
+	/* stream detection initialization */
+	if (instance->is_ventura && fusion) {
+		fusion->stream_detect_by_ld =
+			kzalloc(sizeof(struct LD_STREAM_DETECT *)
+			* MAX_LOGICAL_DRIVES_EXT,
+			GFP_KERNEL);
+		if (!fusion->stream_detect_by_ld) {
+			dev_err(&instance->pdev->dev,
+				"unable to allocate stream detection for pool of LDs\n");
+			goto fail_get_ld_pd_list;
+		}
+		for (i = 0; i < MAX_LOGICAL_DRIVES_EXT; ++i) {
+			fusion->stream_detect_by_ld[i] =
+				kmalloc(sizeof(struct LD_STREAM_DETECT),
+				GFP_KERNEL);
+			if (!fusion->stream_detect_by_ld[i]) {
+				dev_err(&instance->pdev->dev,
+					"unable to allocate stream detect by LD\n ");
+				for (j = 0; j < i; ++j)
+					kfree(fusion->stream_detect_by_ld[j]);
+				kfree(fusion->stream_detect_by_ld);
+				fusion->stream_detect_by_ld = NULL;
+				goto fail_get_ld_pd_list;
+			}
+			fusion->stream_detect_by_ld[i]->mru_bit_map
+				= MR_STREAM_BITMAP;
+		}
+	}
+
 	if (megasas_ld_list_query(instance,
 				  MR_LD_QUERY_TYPE_EXPOSED_TO_HOST))
-		megasas_get_ld_list(instance);
+		goto fail_get_ld_pd_list;
 
 	/*
 	 * Compute the max allowed sectors per IO: The controller info has two
@@ -5296,7 +5490,7 @@ static int megasas_init_fw(struct megasas_instance *instance)
 
 	return 0;
 
-fail_get_pd_list:
+fail_get_ld_pd_list:
 	instance->instancet->disable_intr(instance);
 fail_init_adapter:
 	megasas_destroy_irqs(instance);
@@ -5309,9 +5503,11 @@ fail_ready_state:
 	instance->ctrl_info = NULL;
 	iounmap(instance->reg_set);
 
-      fail_ioremap:
+fail_ioremap:
 	pci_release_selected_regions(instance->pdev, 1<<instance->bar);
 
+	dev_err(&instance->pdev->dev, "Failed from %s %d\n",
+		__func__, __LINE__);
 	return -EINVAL;
 }
 
@@ -5531,6 +5727,98 @@ megasas_register_aen(struct megasas_instance *instance, u32 seq_num,
 	return 0;
 }
 
+/* megasas_get_target_prop - Send DCMD with below details to firmware.
+ *
+ * This DCMD will fetch few properties of LD/system PD defined
+ * in MR_TARGET_DEV_PROPERTIES. eg. Queue Depth, MDTS value.
+ *
+ * DCMD send by drivers whenever new target is added to the OS.
+ *
+ * dcmd.opcode         - MR_DCMD_DEV_GET_TARGET_PROP
+ * dcmd.mbox.b[0]      - DCMD is to be fired for LD or system PD.
+ *                       0 = system PD, 1 = LD.
+ * dcmd.mbox.s[1]      - TargetID for LD/system PD.
+ * dcmd.sge IN         - Pointer to return MR_TARGET_DEV_PROPERTIES.
+ *
+ * @instance:		Adapter soft state
+ * @sdev:		OS provided scsi device
+ *
+ * Returns 0 on success non-zero on failure.
+ */
+static int
+megasas_get_target_prop(struct megasas_instance *instance,
+			struct scsi_device *sdev)
+{
+	int ret;
+	struct megasas_cmd *cmd;
+	struct megasas_dcmd_frame *dcmd;
+	u16 targetId = (sdev->channel % 2) + sdev->id;
+
+	cmd = megasas_get_cmd(instance);
+
+	if (!cmd) {
+		dev_err(&instance->pdev->dev,
+			"Failed to get cmd %s\n", __func__);
+		return -ENOMEM;
+	}
+
+	dcmd = &cmd->frame->dcmd;
+
+	memset(instance->tgt_prop, 0, sizeof(*instance->tgt_prop));
+	memset(dcmd->mbox.b, 0, MFI_MBOX_SIZE);
+	dcmd->mbox.b[0] = MEGASAS_IS_LOGICAL(sdev);
+
+	dcmd->mbox.s[1] = cpu_to_le16(targetId);
+	dcmd->cmd = MFI_CMD_DCMD;
+	dcmd->cmd_status = 0xFF;
+	dcmd->sge_count = 1;
+	dcmd->flags = cpu_to_le16(MFI_FRAME_DIR_READ);
+	dcmd->timeout = 0;
+	dcmd->pad_0 = 0;
+	dcmd->data_xfer_len =
+		cpu_to_le32(sizeof(struct MR_TARGET_PROPERTIES));
+	dcmd->opcode = cpu_to_le32(MR_DCMD_DRV_GET_TARGET_PROP);
+	dcmd->sgl.sge32[0].phys_addr =
+		cpu_to_le32(instance->tgt_prop_h);
+	dcmd->sgl.sge32[0].length =
+		cpu_to_le32(sizeof(struct MR_TARGET_PROPERTIES));
+
+	if (instance->ctrl_context && !instance->mask_interrupts)
+		ret = megasas_issue_blocked_cmd(instance,
+						cmd, MFI_IO_TIMEOUT_SECS);
+	else
+		ret = megasas_issue_polled(instance, cmd);
+
+	switch (ret) {
+	case DCMD_TIMEOUT:
+		switch (dcmd_timeout_ocr_possible(instance)) {
+		case INITIATE_OCR:
+			cmd->flags |= DRV_DCMD_SKIP_REFIRE;
+			megasas_reset_fusion(instance->host,
+					     MFI_IO_TIMEOUT_OCR);
+			break;
+		case KILL_ADAPTER:
+			megaraid_sas_kill_hba(instance);
+			break;
+		case IGNORE_TIMEOUT:
+			dev_info(&instance->pdev->dev,
+				 "Ignore DCMD timeout: %s %d\n",
+				 __func__, __LINE__);
+			break;
+		}
+		break;
+
+	default:
+		megasas_return_cmd(instance, cmd);
+	}
+	if (ret != DCMD_SUCCESS)
+		dev_err(&instance->pdev->dev,
+			"return from %s %d return value %d\n",
+			__func__, __LINE__, ret);
+
+	return ret;
+}
+
 /**
  * megasas_start_aen -	Subscribes to AEN during driver load time
  * @instance:		Adapter soft state
@@ -5714,6 +6002,12 @@ static int megasas_probe_one(struct pci_dev *pdev,
 	instance->pdev = pdev;
 
 	switch (instance->pdev->device) {
+	case PCI_DEVICE_ID_LSI_VENTURA:
+	case PCI_DEVICE_ID_LSI_HARPOON:
+	case PCI_DEVICE_ID_LSI_TOMCAT:
+	case PCI_DEVICE_ID_LSI_VENTURA_4PORT:
+	case PCI_DEVICE_ID_LSI_CRUSADER_4PORT:
+	     instance->is_ventura = true;
 	case PCI_DEVICE_ID_LSI_FUSION:
 	case PCI_DEVICE_ID_LSI_PLASMA:
 	case PCI_DEVICE_ID_LSI_INVADER:
@@ -5723,21 +6017,17 @@ static int megasas_probe_one(struct pci_dev *pdev,
 	case PCI_DEVICE_ID_LSI_CUTLASS_52:
 	case PCI_DEVICE_ID_LSI_CUTLASS_53:
 	{
-		instance->ctrl_context_pages =
-			get_order(sizeof(struct fusion_context));
-		instance->ctrl_context = (void *)__get_free_pages(GFP_KERNEL,
-				instance->ctrl_context_pages);
-		if (!instance->ctrl_context) {
-			dev_printk(KERN_DEBUG, &pdev->dev, "Failed to allocate "
-			       "memory for Fusion context info\n");
+		if (megasas_alloc_fusion_context(instance)) {
+			megasas_free_fusion_context(instance);
 			goto fail_alloc_dma_buf;
 		}
 		fusion = instance->ctrl_context;
-		memset(fusion, 0,
-			((1 << PAGE_SHIFT) << instance->ctrl_context_pages));
+
 		if ((instance->pdev->device == PCI_DEVICE_ID_LSI_FUSION) ||
 			(instance->pdev->device == PCI_DEVICE_ID_LSI_PLASMA))
 			fusion->adapter_type = THUNDERBOLT_SERIES;
+		else if (instance->is_ventura)
+			fusion->adapter_type = VENTURA_SERIES;
 		else
 			fusion->adapter_type = INVADER_SERIES;
 	}
@@ -5799,9 +6089,17 @@ static int megasas_probe_one(struct pci_dev *pdev,
 		instance->pd_info = pci_alloc_consistent(pdev,
 			sizeof(struct MR_PD_INFO), &instance->pd_info_h);
 
+		instance->pd_info = pci_alloc_consistent(pdev,
+			sizeof(struct MR_PD_INFO), &instance->pd_info_h);
+		instance->tgt_prop = pci_alloc_consistent(pdev,
+			sizeof(struct MR_TARGET_PROPERTIES), &instance->tgt_prop_h);
+
 		if (!instance->pd_info)
 			dev_err(&instance->pdev->dev, "Failed to alloc mem for pd_info\n");
 
+		if (!instance->tgt_prop)
+			dev_err(&instance->pdev->dev, "Failed to alloc mem for tgt_prop\n");
+
 		instance->crash_dump_buf = pci_alloc_consistent(pdev,
 						CRASH_DMA_BUF_SIZE,
 						&instance->crash_dump_h);
@@ -5823,6 +6121,7 @@ static int megasas_probe_one(struct pci_dev *pdev,
 
 	spin_lock_init(&instance->mfi_pool_lock);
 	spin_lock_init(&instance->hba_lock);
+	spin_lock_init(&instance->stream_lock);
 	spin_lock_init(&instance->completion_lock);
 
 	mutex_init(&instance->reset_mutex);
@@ -5945,6 +6244,10 @@ fail_alloc_dma_buf:
 		pci_free_consistent(pdev, sizeof(struct MR_PD_INFO),
 					instance->pd_info,
 					instance->pd_info_h);
+	if (instance->tgt_prop)
+		pci_free_consistent(pdev, sizeof(struct MR_TARGET_PROPERTIES),
+					instance->tgt_prop,
+					instance->tgt_prop_h);
 	if (instance->producer)
 		pci_free_consistent(pdev, sizeof(u32), instance->producer,
 				    instance->producer_h);
@@ -6217,6 +6520,10 @@ fail_init_mfi:
 		pci_free_consistent(pdev, sizeof(struct MR_PD_INFO),
 					instance->pd_info,
 					instance->pd_info_h);
+	if (instance->tgt_prop)
+		pci_free_consistent(pdev, sizeof(struct MR_TARGET_PROPERTIES),
+					instance->tgt_prop,
+					instance->tgt_prop_h);
 	if (instance->producer)
 		pci_free_consistent(pdev, sizeof(u32), instance->producer,
 				instance->producer_h);
@@ -6330,6 +6637,14 @@ skip_firing_dcmds:
 	if (instance->msix_vectors)
 		pci_free_irq_vectors(instance->pdev);
 
+	if (instance->is_ventura) {
+		for (i = 0; i < MAX_LOGICAL_DRIVES_EXT; ++i)
+			kfree(fusion->stream_detect_by_ld[i]);
+		kfree(fusion->stream_detect_by_ld);
+		fusion->stream_detect_by_ld = NULL;
+	}
+
+
 	if (instance->ctrl_context) {
 		megasas_release_fusion(instance);
 			pd_seq_map_sz = sizeof(struct MR_PD_CFG_SEQ_NUM_SYNC) +
@@ -6350,8 +6665,7 @@ skip_firing_dcmds:
 					fusion->pd_seq_sync[i],
 					fusion->pd_seq_phys[i]);
 		}
-		free_pages((ulong)instance->ctrl_context,
-			instance->ctrl_context_pages);
+		megasas_free_fusion_context(instance);
 	} else {
 		megasas_release_mfi(instance);
 		pci_free_consistent(pdev, sizeof(u32),
@@ -6367,11 +6681,14 @@ skip_firing_dcmds:
 	if (instance->evt_detail)
 		pci_free_consistent(pdev, sizeof(struct megasas_evt_detail),
 				instance->evt_detail, instance->evt_detail_h);
-
 	if (instance->pd_info)
 		pci_free_consistent(pdev, sizeof(struct MR_PD_INFO),
 					instance->pd_info,
 					instance->pd_info_h);
+	if (instance->tgt_prop)
+		pci_free_consistent(pdev, sizeof(struct MR_TARGET_PROPERTIES),
+					instance->tgt_prop,
+					instance->tgt_prop_h);
 	if (instance->vf_affiliation)
 		pci_free_consistent(pdev, (MAX_LOGICAL_DRIVES + 1) *
 				    sizeof(struct MR_LD_VF_AFFILIATION),
@@ -6570,6 +6887,13 @@ megasas_mgmt_fw_ioctl(struct megasas_instance *instance,
 					       MFI_FRAME_SGL64 |
 					       MFI_FRAME_SENSE64));
 
+	if (cmd->frame->dcmd.opcode == MR_DCMD_CTRL_SHUTDOWN) {
+		if (megasas_get_ctrl_info(instance) != DCMD_SUCCESS) {
+			megasas_return_cmd(instance, cmd);
+			return -1;
+		}
+	}
+
 	if (cmd->frame->dcmd.opcode == MR_DRIVER_SET_APP_CRASHDUMP_MODE) {
 		error = megasas_set_crash_dump_params_ioctl(cmd);
 		megasas_return_cmd(instance, cmd);
@@ -6678,7 +7002,8 @@ megasas_mgmt_fw_ioctl(struct megasas_instance *instance,
 		sense_ptr = (unsigned long *) ((unsigned long)ioc->frame.raw +
 				ioc->sense_off);
 
-		if (copy_to_user((void __user *)((unsigned long)(*sense_ptr)),
+		if (copy_to_user((void __user *)((unsigned long)
+				 get_unaligned((unsigned long *)sense_ptr)),
 				 sense, ioc->sense_len)) {
 			dev_err(&instance->pdev->dev, "Failed to copy out to user "
 					"sense data\n");
@@ -7047,6 +7372,13 @@ megasas_sysfs_set_dbg_lvl(struct device_driver *dd, const char *buf, size_t coun
 static DRIVER_ATTR(dbg_lvl, S_IRUGO|S_IWUSR, megasas_sysfs_show_dbg_lvl,
 		megasas_sysfs_set_dbg_lvl);
 
+static inline void megasas_remove_scsi_device(struct scsi_device *sdev)
+{
+	sdev_printk(KERN_INFO, sdev, "SCSI device is removed\n");
+	scsi_remove_device(sdev);
+	scsi_device_put(sdev);
+}
+
 static void
 megasas_aen_polling(struct work_struct *work)
 {
@@ -7151,10 +7483,8 @@ megasas_aen_polling(struct work_struct *work)
 					else
 						scsi_device_put(sdev1);
 				} else {
-					if (sdev1) {
-						scsi_remove_device(sdev1);
-						scsi_device_put(sdev1);
-					}
+					if (sdev1)
+						megasas_remove_scsi_device(sdev1);
 				}
 			}
 		}
@@ -7171,10 +7501,8 @@ megasas_aen_polling(struct work_struct *work)
 					else
 						scsi_device_put(sdev1);
 				} else {
-					if (sdev1) {
-						scsi_remove_device(sdev1);
-						scsi_device_put(sdev1);
-					}
+					if (sdev1)
+						megasas_remove_scsi_device(sdev1);
 				}
 			}
 		}
diff --git a/drivers/scsi/megaraid/megaraid_sas_fp.c b/drivers/scsi/megaraid/megaraid_sas_fp.c
index f237d0003df3..62affa76133d 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fp.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fp.c
@@ -77,7 +77,6 @@ MODULE_PARM_DESC(lb_pending_cmds, "Change raid-1 load balancing outstanding "
 #endif
 #define TRUE 1
 
-#define SPAN_DEBUG 0
 #define SPAN_ROW_SIZE(map, ld, index_) (MR_LdSpanPtrGet(ld, index_, map)->spanRowSize)
 #define SPAN_ROW_DATA_SIZE(map_, ld, index_)   (MR_LdSpanPtrGet(ld, index_, map)->spanRowDataSize)
 #define SPAN_INVALID  0xff
@@ -155,12 +154,17 @@ __le16 MR_PdDevHandleGet(u32 pd, struct MR_DRV_RAID_MAP_ALL *map)
 	return map->raidMap.devHndlInfo[pd].curDevHdl;
 }
 
+static u8 MR_PdInterfaceTypeGet(u32 pd, struct MR_DRV_RAID_MAP_ALL *map)
+{
+	return map->raidMap.devHndlInfo[pd].interfaceType;
+}
+
 u16 MR_GetLDTgtId(u32 ld, struct MR_DRV_RAID_MAP_ALL *map)
 {
 	return le16_to_cpu(map->raidMap.ldSpanMap[ld].ldRaid.targetId);
 }
 
-u8 MR_TargetIdToLdGet(u32 ldTgtId, struct MR_DRV_RAID_MAP_ALL *map)
+u16 MR_TargetIdToLdGet(u32 ldTgtId, struct MR_DRV_RAID_MAP_ALL *map)
 {
 	return map->raidMap.ldTgtIdToLd[ldTgtId];
 }
@@ -179,18 +183,108 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 	struct fusion_context *fusion = instance->ctrl_context;
 	struct MR_FW_RAID_MAP_ALL     *fw_map_old    = NULL;
 	struct MR_FW_RAID_MAP         *pFwRaidMap    = NULL;
-	int i;
+	int i, j;
 	u16 ld_count;
+	struct MR_FW_RAID_MAP_DYNAMIC *fw_map_dyn;
+	struct MR_FW_RAID_MAP_EXT *fw_map_ext;
+	struct MR_RAID_MAP_DESC_TABLE *desc_table;
 
 
 	struct MR_DRV_RAID_MAP_ALL *drv_map =
 			fusion->ld_drv_map[(instance->map_id & 1)];
 	struct MR_DRV_RAID_MAP *pDrvRaidMap = &drv_map->raidMap;
+	void *raid_map_data = NULL;
+
+	memset(drv_map, 0, fusion->drv_map_sz);
+	memset(pDrvRaidMap->ldTgtIdToLd,
+	       0xff, (sizeof(u16) * MAX_LOGICAL_DRIVES_DYN));
+
+	if (instance->max_raid_mapsize) {
+		fw_map_dyn = fusion->ld_map[(instance->map_id & 1)];
+		desc_table =
+		(struct MR_RAID_MAP_DESC_TABLE *)((void *)fw_map_dyn + le32_to_cpu(fw_map_dyn->desc_table_offset));
+		if (desc_table != fw_map_dyn->raid_map_desc_table)
+			dev_dbg(&instance->pdev->dev, "offsets of desc table are not matching desc %p original %p\n",
+				desc_table, fw_map_dyn->raid_map_desc_table);
+
+		ld_count = (u16)le16_to_cpu(fw_map_dyn->ld_count);
+		pDrvRaidMap->ldCount = (__le16)cpu_to_le16(ld_count);
+		pDrvRaidMap->fpPdIoTimeoutSec =
+			fw_map_dyn->fp_pd_io_timeout_sec;
+		pDrvRaidMap->totalSize =
+			cpu_to_le32(sizeof(struct MR_DRV_RAID_MAP_ALL));
+		/* point to actual data starting point*/
+		raid_map_data = (void *)fw_map_dyn +
+			le32_to_cpu(fw_map_dyn->desc_table_offset) +
+			le32_to_cpu(fw_map_dyn->desc_table_size);
+
+		for (i = 0; i < le32_to_cpu(fw_map_dyn->desc_table_num_elements); ++i) {
+			switch (le32_to_cpu(desc_table->raid_map_desc_type)) {
+			case RAID_MAP_DESC_TYPE_DEVHDL_INFO:
+				fw_map_dyn->dev_hndl_info =
+				(struct MR_DEV_HANDLE_INFO *)(raid_map_data + le32_to_cpu(desc_table->raid_map_desc_offset));
+				memcpy(pDrvRaidMap->devHndlInfo,
+					fw_map_dyn->dev_hndl_info,
+					sizeof(struct MR_DEV_HANDLE_INFO) *
+					le32_to_cpu(desc_table->raid_map_desc_elements));
+			break;
+			case RAID_MAP_DESC_TYPE_TGTID_INFO:
+				fw_map_dyn->ld_tgt_id_to_ld =
+					(u16 *)(raid_map_data +
+					le32_to_cpu(desc_table->raid_map_desc_offset));
+				for (j = 0; j < le32_to_cpu(desc_table->raid_map_desc_elements); j++) {
+					pDrvRaidMap->ldTgtIdToLd[j] =
+						le16_to_cpu(fw_map_dyn->ld_tgt_id_to_ld[j]);
+				}
+			break;
+			case RAID_MAP_DESC_TYPE_ARRAY_INFO:
+				fw_map_dyn->ar_map_info =
+					(struct MR_ARRAY_INFO *)
+					(raid_map_data + le32_to_cpu(desc_table->raid_map_desc_offset));
+				memcpy(pDrvRaidMap->arMapInfo,
+				       fw_map_dyn->ar_map_info,
+				       sizeof(struct MR_ARRAY_INFO) *
+				       le32_to_cpu(desc_table->raid_map_desc_elements));
+			break;
+			case RAID_MAP_DESC_TYPE_SPAN_INFO:
+				fw_map_dyn->ld_span_map =
+					(struct MR_LD_SPAN_MAP *)
+					(raid_map_data +
+					le32_to_cpu(desc_table->raid_map_desc_offset));
+				memcpy(pDrvRaidMap->ldSpanMap,
+				       fw_map_dyn->ld_span_map,
+				       sizeof(struct MR_LD_SPAN_MAP) *
+				       le32_to_cpu(desc_table->raid_map_desc_elements));
+			break;
+			default:
+				dev_dbg(&instance->pdev->dev, "wrong number of desctableElements %d\n",
+					fw_map_dyn->desc_table_num_elements);
+			}
+			++desc_table;
+		}
+
+	} else if (instance->supportmax256vd) {
+		fw_map_ext =
+			(struct MR_FW_RAID_MAP_EXT *)fusion->ld_map[(instance->map_id & 1)];
+		ld_count = (u16)le16_to_cpu(fw_map_ext->ldCount);
+		if (ld_count > MAX_LOGICAL_DRIVES_EXT) {
+			dev_dbg(&instance->pdev->dev, "megaraid_sas: LD count exposed in RAID map in not valid\n");
+			return;
+		}
+
+		pDrvRaidMap->ldCount = (__le16)cpu_to_le16(ld_count);
+		pDrvRaidMap->fpPdIoTimeoutSec = fw_map_ext->fpPdIoTimeoutSec;
+		for (i = 0; i < (MAX_LOGICAL_DRIVES_EXT); i++)
+			pDrvRaidMap->ldTgtIdToLd[i] =
+				(u16)fw_map_ext->ldTgtIdToLd[i];
+		memcpy(pDrvRaidMap->ldSpanMap, fw_map_ext->ldSpanMap,
+		       sizeof(struct MR_LD_SPAN_MAP) * ld_count);
+		memcpy(pDrvRaidMap->arMapInfo, fw_map_ext->arMapInfo,
+		       sizeof(struct MR_ARRAY_INFO) * MAX_API_ARRAYS_EXT);
+		memcpy(pDrvRaidMap->devHndlInfo, fw_map_ext->devHndlInfo,
+		       sizeof(struct MR_DEV_HANDLE_INFO) *
+		       MAX_RAIDMAP_PHYSICAL_DEVICES);
 
-	if (instance->supportmax256vd) {
-		memcpy(fusion->ld_drv_map[instance->map_id & 1],
-			fusion->ld_map[instance->map_id & 1],
-			fusion->current_map_sz);
 		/* New Raid map will not set totalSize, so keep expected value
 		 * for legacy code in ValidateMapInfo
 		 */
@@ -201,50 +295,14 @@ void MR_PopulateDrvRaidMap(struct megasas_instance *instance)
 			fusion->ld_map[(instance->map_id & 1)];
 		pFwRaidMap = &fw_map_old->raidMap;
 		ld_count = (u16)le32_to_cpu(pFwRaidMap->ldCount);
-
-#if VD_EXT_DEBUG
-		for (i = 0; i < ld_count; i++) {
-			dev_dbg(&instance->pdev->dev, "(%d) :Index 0x%x "
-				"Target Id 0x%x Seq Num 0x%x Size 0/%llx\n",
-				instance->unique_id, i,
-				fw_map_old->raidMap.ldSpanMap[i].ldRaid.targetId,
-				fw_map_old->raidMap.ldSpanMap[i].ldRaid.seqNum,
-				fw_map_old->raidMap.ldSpanMap[i].ldRaid.size);
-		}
-#endif
-
-		memset(drv_map, 0, fusion->drv_map_sz);
 		pDrvRaidMap->totalSize = pFwRaidMap->totalSize;
 		pDrvRaidMap->ldCount = (__le16)cpu_to_le16(ld_count);
 		pDrvRaidMap->fpPdIoTimeoutSec = pFwRaidMap->fpPdIoTimeoutSec;
 		for (i = 0; i < MAX_RAIDMAP_LOGICAL_DRIVES + MAX_RAIDMAP_VIEWS; i++)
 			pDrvRaidMap->ldTgtIdToLd[i] =
 				(u8)pFwRaidMap->ldTgtIdToLd[i];
-		for (i = (MAX_RAIDMAP_LOGICAL_DRIVES + MAX_RAIDMAP_VIEWS);
-			i < MAX_LOGICAL_DRIVES_EXT; i++)
-			pDrvRaidMap->ldTgtIdToLd[i] = 0xff;
 		for (i = 0; i < ld_count; i++) {
 			pDrvRaidMap->ldSpanMap[i] = pFwRaidMap->ldSpanMap[i];
-#if VD_EXT_DEBUG
-			dev_dbg(&instance->pdev->dev,
-				"pFwRaidMap->ldSpanMap[%d].ldRaid.targetId 0x%x "
-				"pFwRaidMap->ldSpanMap[%d].ldRaid.seqNum 0x%x "
-				"size 0x%x\n", i, i,
-				pFwRaidMap->ldSpanMap[i].ldRaid.targetId,
-				pFwRaidMap->ldSpanMap[i].ldRaid.seqNum,
-				(u32)pFwRaidMap->ldSpanMap[i].ldRaid.rowSize);
-			dev_dbg(&instance->pdev->dev,
-				"pDrvRaidMap->ldSpanMap[%d].ldRaid.targetId 0x%x "
-				"pDrvRaidMap->ldSpanMap[%d].ldRaid.seqNum 0x%x "
-				"size 0x%x\n", i, i,
-				pDrvRaidMap->ldSpanMap[i].ldRaid.targetId,
-				pDrvRaidMap->ldSpanMap[i].ldRaid.seqNum,
-				(u32)pDrvRaidMap->ldSpanMap[i].ldRaid.rowSize);
-			dev_dbg(&instance->pdev->dev, "Driver raid map all %p "
-				"raid map %p LD RAID MAP %p/%p\n", drv_map,
-				pDrvRaidMap, &pFwRaidMap->ldSpanMap[i].ldRaid,
-				&pDrvRaidMap->ldSpanMap[i].ldRaid);
-#endif
 		}
 		memcpy(pDrvRaidMap->arMapInfo, pFwRaidMap->arMapInfo,
 			sizeof(struct MR_ARRAY_INFO) * MAX_RAIDMAP_ARRAYS);
@@ -265,7 +323,7 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance)
 	struct LD_LOAD_BALANCE_INFO *lbInfo;
 	PLD_SPAN_INFO ldSpanInfo;
 	struct MR_LD_RAID         *raid;
-	u16 ldCount, num_lds;
+	u16 num_lds, i;
 	u16 ld;
 	u32 expected_size;
 
@@ -279,7 +337,9 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance)
 	lbInfo = fusion->load_balance_info;
 	ldSpanInfo = fusion->log_to_span;
 
-	if (instance->supportmax256vd)
+	if (instance->max_raid_mapsize)
+		expected_size = sizeof(struct MR_DRV_RAID_MAP_ALL);
+	else if (instance->supportmax256vd)
 		expected_size = sizeof(struct MR_FW_RAID_MAP_EXT);
 	else
 		expected_size =
@@ -287,8 +347,10 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance)
 			(sizeof(struct MR_LD_SPAN_MAP) * le16_to_cpu(pDrvRaidMap->ldCount)));
 
 	if (le32_to_cpu(pDrvRaidMap->totalSize) != expected_size) {
-		dev_err(&instance->pdev->dev, "map info structure size 0x%x is not matching with ld count\n",
-		       (unsigned int) expected_size);
+		dev_dbg(&instance->pdev->dev, "megasas: map info structure size 0x%x",
+			le32_to_cpu(pDrvRaidMap->totalSize));
+		dev_dbg(&instance->pdev->dev, "is not matching expected size 0x%x\n",
+			(unsigned int)expected_size);
 		dev_err(&instance->pdev->dev, "megasas: span map %x, pDrvRaidMap->totalSize : %x\n",
 			(unsigned int)sizeof(struct MR_LD_SPAN_MAP),
 			le32_to_cpu(pDrvRaidMap->totalSize));
@@ -298,15 +360,23 @@ u8 MR_ValidateMapInfo(struct megasas_instance *instance)
 	if (instance->UnevenSpanSupport)
 		mr_update_span_set(drv_map, ldSpanInfo);
 
-	mr_update_load_balance_params(drv_map, lbInfo);
+	if (lbInfo)
+		mr_update_load_balance_params(drv_map, lbInfo);
 
 	num_lds = le16_to_cpu(drv_map->raidMap.ldCount);
 
 	/*Convert Raid capability values to CPU arch */
-	for (ldCount = 0; ldCount < num_lds; ldCount++) {
-		ld = MR_TargetIdToLdGet(ldCount, drv_map);
+	for (i = 0; (num_lds > 0) && (i < MAX_LOGICAL_DRIVES_EXT); i++) {
+		ld = MR_TargetIdToLdGet(i, drv_map);
+
+		/* For non existing VDs, iterate to next VD*/
+		if (ld >= (MAX_LOGICAL_DRIVES_EXT - 1))
+			continue;
+
 		raid = MR_LdRaidGet(ld, drv_map);
 		le32_to_cpus((u32 *)&raid->capability);
+
+		num_lds--;
 	}
 
 	return 1;
@@ -348,91 +418,6 @@ u32 MR_GetSpanBlock(u32 ld, u64 row, u64 *span_blk,
 /*
 ******************************************************************************
 *
-* Function to print info about span set created in driver from FW raid map
-*
-* Inputs :
-* map    - LD map
-* ldSpanInfo - ldSpanInfo per HBA instance
-*/
-#if SPAN_DEBUG
-static int getSpanInfo(struct MR_DRV_RAID_MAP_ALL *map,
-	PLD_SPAN_INFO ldSpanInfo)
-{
-
-	u8   span;
-	u32    element;
-	struct MR_LD_RAID *raid;
-	LD_SPAN_SET *span_set;
-	struct MR_QUAD_ELEMENT    *quad;
-	int ldCount;
-	u16 ld;
-
-	for (ldCount = 0; ldCount < MAX_LOGICAL_DRIVES_EXT; ldCount++) {
-		ld = MR_TargetIdToLdGet(ldCount, map);
-			if (ld >= (MAX_LOGICAL_DRIVES_EXT - 1))
-				continue;
-		raid = MR_LdRaidGet(ld, map);
-		dev_dbg(&instance->pdev->dev, "LD %x: span_depth=%x\n",
-			ld, raid->spanDepth);
-		for (span = 0; span < raid->spanDepth; span++)
-			dev_dbg(&instance->pdev->dev, "Span=%x,"
-			" number of quads=%x\n", span,
-			le32_to_cpu(map->raidMap.ldSpanMap[ld].spanBlock[span].
-			block_span_info.noElements));
-		for (element = 0; element < MAX_QUAD_DEPTH; element++) {
-			span_set = &(ldSpanInfo[ld].span_set[element]);
-			if (span_set->span_row_data_width == 0)
-				break;
-
-			dev_dbg(&instance->pdev->dev, "Span Set %x:"
-				"width=%x, diff=%x\n", element,
-				(unsigned int)span_set->span_row_data_width,
-				(unsigned int)span_set->diff);
-			dev_dbg(&instance->pdev->dev, "logical LBA"
-				"start=0x%08lx, end=0x%08lx\n",
-				(long unsigned int)span_set->log_start_lba,
-				(long unsigned int)span_set->log_end_lba);
-			dev_dbg(&instance->pdev->dev, "span row start=0x%08lx,"
-				" end=0x%08lx\n",
-				(long unsigned int)span_set->span_row_start,
-				(long unsigned int)span_set->span_row_end);
-			dev_dbg(&instance->pdev->dev, "data row start=0x%08lx,"
-				" end=0x%08lx\n",
-				(long unsigned int)span_set->data_row_start,
-				(long unsigned int)span_set->data_row_end);
-			dev_dbg(&instance->pdev->dev, "data strip start=0x%08lx,"
-				" end=0x%08lx\n",
-				(long unsigned int)span_set->data_strip_start,
-				(long unsigned int)span_set->data_strip_end);
-
-			for (span = 0; span < raid->spanDepth; span++) {
-				if (le32_to_cpu(map->raidMap.ldSpanMap[ld].spanBlock[span].
-					block_span_info.noElements) >=
-					element + 1) {
-					quad = &map->raidMap.ldSpanMap[ld].
-						spanBlock[span].block_span_info.
-						quad[element];
-				dev_dbg(&instance->pdev->dev, "Span=%x,"
-					"Quad=%x, diff=%x\n", span,
-					element, le32_to_cpu(quad->diff));
-				dev_dbg(&instance->pdev->dev,
-					"offset_in_span=0x%08lx\n",
-					(long unsigned int)le64_to_cpu(quad->offsetInSpan));
-				dev_dbg(&instance->pdev->dev,
-					"logical start=0x%08lx, end=0x%08lx\n",
-					(long unsigned int)le64_to_cpu(quad->logStart),
-					(long unsigned int)le64_to_cpu(quad->logEnd));
-				}
-			}
-		}
-	}
-	return 0;
-}
-#endif
-
-/*
-******************************************************************************
-*
 * This routine calculates the Span block for given row using spanset.
 *
 * Inputs :
@@ -543,19 +528,7 @@ static u64  get_row_from_strip(struct megasas_instance *instance,
 				else
 					break;
 			}
-#if SPAN_DEBUG
-		dev_info(&instance->pdev->dev, "Strip 0x%llx,"
-			"span_set_Strip 0x%llx, span_set_Row 0x%llx"
-			"data width 0x%llx span offset 0x%x\n", strip,
-			(unsigned long long)span_set_Strip,
-			(unsigned long long)span_set_Row,
-			(unsigned long long)span_set->span_row_data_width,
-			span_offset);
-		dev_info(&instance->pdev->dev, "For strip 0x%llx"
-			"row is 0x%llx\n", strip,
-			(unsigned long long) span_set->data_row_start +
-			(unsigned long long) span_set_Row + (span_offset - 1));
-#endif
+
 		retval = (span_set->data_row_start + span_set_Row +
 				(span_offset - 1));
 		return retval;
@@ -672,11 +645,7 @@ static u32 get_arm_from_strip(struct megasas_instance *instance,
 				else
 					break;
 			}
-#if SPAN_DEBUG
-		dev_info(&instance->pdev->dev, "get_arm_from_strip:"
-			"for ld=0x%x strip=0x%lx arm is  0x%x\n", ld,
-			(long unsigned int)strip, (strip_offset - span_offset));
-#endif
+
 		retval = (strip_offset - span_offset);
 		return retval;
 	}
@@ -737,16 +706,18 @@ static u8 mr_spanset_get_phy_params(struct megasas_instance *instance, u32 ld,
 		struct MR_DRV_RAID_MAP_ALL *map)
 {
 	struct MR_LD_RAID  *raid = MR_LdRaidGet(ld, map);
-	u32     pd, arRef;
+	u32     pd, arRef, r1_alt_pd;
 	u8      physArm, span;
 	u64     row;
 	u8	retval = TRUE;
 	u64	*pdBlock = &io_info->pdBlock;
 	__le16	*pDevHandle = &io_info->devHandle;
+	u8	*pPdInterface = &io_info->pd_interface;
 	u32	logArm, rowMod, armQ, arm;
 	struct fusion_context *fusion;
 
 	fusion = instance->ctrl_context;
+	*pDevHandle = cpu_to_le16(MR_DEVHANDLE_INVALID);
 
 	/*Get row and span from io_info for Uneven Span IO.*/
 	row	    = io_info->start_row;
@@ -772,27 +743,46 @@ static u8 mr_spanset_get_phy_params(struct megasas_instance *instance, u32 ld,
 	arRef       = MR_LdSpanArrayGet(ld, span, map);
 	pd          = MR_ArPdGet(arRef, physArm, map);
 
-	if (pd != MR_PD_INVALID)
+	if (pd != MR_PD_INVALID) {
 		*pDevHandle = MR_PdDevHandleGet(pd, map);
-	else {
-		*pDevHandle = cpu_to_le16(MR_PD_INVALID);
+		*pPdInterface = MR_PdInterfaceTypeGet(pd, map);
+		/* get second pd also for raid 1/10 fast path writes*/
+		if (instance->is_ventura &&
+		    (raid->level == 1) &&
+		    !io_info->isRead) {
+			r1_alt_pd = MR_ArPdGet(arRef, physArm + 1, map);
+			if (r1_alt_pd != MR_PD_INVALID)
+				io_info->r1_alt_dev_handle =
+				MR_PdDevHandleGet(r1_alt_pd, map);
+		}
+	} else {
 		if ((raid->level >= 5) &&
 			((fusion->adapter_type == THUNDERBOLT_SERIES)  ||
 			((fusion->adapter_type == INVADER_SERIES) &&
 			(raid->regTypeReqOnRead != REGION_TYPE_UNUSED))))
-			pRAID_Context->regLockFlags = REGION_TYPE_EXCLUSIVE;
+			pRAID_Context->reg_lock_flags = REGION_TYPE_EXCLUSIVE;
 		else if (raid->level == 1) {
 			physArm = physArm + 1;
 			pd = MR_ArPdGet(arRef, physArm, map);
-			if (pd != MR_PD_INVALID)
+			if (pd != MR_PD_INVALID) {
 				*pDevHandle = MR_PdDevHandleGet(pd, map);
+				*pPdInterface = MR_PdInterfaceTypeGet(pd, map);
+			}
 		}
 	}
 
 	*pdBlock += stripRef + le64_to_cpu(MR_LdSpanPtrGet(ld, span, map)->startBlk);
-	pRAID_Context->spanArm = (span << RAID_CTX_SPANARM_SPAN_SHIFT) |
-					physArm;
-	io_info->span_arm = pRAID_Context->spanArm;
+	if (instance->is_ventura) {
+		((struct RAID_CONTEXT_G35 *)pRAID_Context)->span_arm =
+			(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+		io_info->span_arm =
+			(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+	} else {
+		pRAID_Context->span_arm =
+			(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+		io_info->span_arm = pRAID_Context->span_arm;
+	}
+	io_info->pd_after_lb = pd;
 	return retval;
 }
 
@@ -819,16 +809,17 @@ u8 MR_GetPhyParams(struct megasas_instance *instance, u32 ld, u64 stripRow,
 		struct MR_DRV_RAID_MAP_ALL *map)
 {
 	struct MR_LD_RAID  *raid = MR_LdRaidGet(ld, map);
-	u32         pd, arRef;
+	u32         pd, arRef, r1_alt_pd;
 	u8          physArm, span;
 	u64         row;
 	u8	    retval = TRUE;
 	u64	    *pdBlock = &io_info->pdBlock;
 	__le16	    *pDevHandle = &io_info->devHandle;
+	u8	    *pPdInterface = &io_info->pd_interface;
 	struct fusion_context *fusion;
 
 	fusion = instance->ctrl_context;
-
+	*pDevHandle = cpu_to_le16(MR_DEVHANDLE_INVALID);
 
 	row =  mega_div64_32(stripRow, raid->rowDataSize);
 
@@ -867,31 +858,49 @@ u8 MR_GetPhyParams(struct megasas_instance *instance, u32 ld, u64 stripRow,
 	arRef       = MR_LdSpanArrayGet(ld, span, map);
 	pd          = MR_ArPdGet(arRef, physArm, map); /* Get the pd */
 
-	if (pd != MR_PD_INVALID)
+	if (pd != MR_PD_INVALID) {
 		/* Get dev handle from Pd. */
 		*pDevHandle = MR_PdDevHandleGet(pd, map);
-	else {
-		/* set dev handle as invalid. */
-		*pDevHandle = cpu_to_le16(MR_PD_INVALID);
+		*pPdInterface = MR_PdInterfaceTypeGet(pd, map);
+		/* get second pd also for raid 1/10 fast path writes*/
+		if (instance->is_ventura &&
+		    (raid->level == 1) &&
+		    !io_info->isRead) {
+			r1_alt_pd = MR_ArPdGet(arRef, physArm + 1, map);
+			if (r1_alt_pd != MR_PD_INVALID)
+				io_info->r1_alt_dev_handle =
+					MR_PdDevHandleGet(r1_alt_pd, map);
+		}
+	} else {
 		if ((raid->level >= 5) &&
 			((fusion->adapter_type == THUNDERBOLT_SERIES)  ||
 			((fusion->adapter_type == INVADER_SERIES) &&
 			(raid->regTypeReqOnRead != REGION_TYPE_UNUSED))))
-			pRAID_Context->regLockFlags = REGION_TYPE_EXCLUSIVE;
+			pRAID_Context->reg_lock_flags = REGION_TYPE_EXCLUSIVE;
 		else if (raid->level == 1) {
 			/* Get alternate Pd. */
 			physArm = physArm + 1;
 			pd = MR_ArPdGet(arRef, physArm, map);
-			if (pd != MR_PD_INVALID)
+			if (pd != MR_PD_INVALID) {
 				/* Get dev handle from Pd */
 				*pDevHandle = MR_PdDevHandleGet(pd, map);
+				*pPdInterface = MR_PdInterfaceTypeGet(pd, map);
+			}
 		}
 	}
 
 	*pdBlock += stripRef + le64_to_cpu(MR_LdSpanPtrGet(ld, span, map)->startBlk);
-	pRAID_Context->spanArm = (span << RAID_CTX_SPANARM_SPAN_SHIFT) |
-		physArm;
-	io_info->span_arm = pRAID_Context->spanArm;
+	if (instance->is_ventura) {
+		((struct RAID_CONTEXT_G35 *)pRAID_Context)->span_arm =
+				(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+		io_info->span_arm =
+				(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+	} else {
+		pRAID_Context->span_arm =
+			(span << RAID_CTX_SPANARM_SPAN_SHIFT) | physArm;
+		io_info->span_arm = pRAID_Context->span_arm;
+	}
+	io_info->pd_after_lb = pd;
 	return retval;
 }
 
@@ -912,7 +921,7 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 {
 	struct fusion_context *fusion;
 	struct MR_LD_RAID  *raid;
-	u32         ld, stripSize, stripe_mask;
+	u32         stripSize, stripe_mask;
 	u64         endLba, endStrip, endRow, start_row, start_strip;
 	u64         regStart;
 	u32         regSize;
@@ -924,6 +933,7 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 	u8	    retval = 0;
 	u8	    startlba_span = SPAN_INVALID;
 	u64 *pdBlock = &io_info->pdBlock;
+	u16	    ld;
 
 	ldStartBlock = io_info->ldStartBlock;
 	numBlocks = io_info->numBlocks;
@@ -935,6 +945,8 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 
 	ld = MR_TargetIdToLdGet(ldTgtId, map);
 	raid = MR_LdRaidGet(ld, map);
+	/*check read ahead bit*/
+	io_info->ra_capable = raid->capability.ra_capable;
 
 	/*
 	 * if rowDataSize @RAID map and spanRowDataSize @SPAN INFO are zero
@@ -996,17 +1008,6 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 		}
 		io_info->start_span	= startlba_span;
 		io_info->start_row	= start_row;
-#if SPAN_DEBUG
-		dev_dbg(&instance->pdev->dev, "Check Span number from %s %d"
-			"for row 0x%llx, start strip 0x%llx end strip 0x%llx"
-			" span 0x%x\n", __func__, __LINE__,
-			(unsigned long long)start_row,
-			(unsigned long long)start_strip,
-			(unsigned long long)endStrip, startlba_span);
-		dev_dbg(&instance->pdev->dev, "start_row 0x%llx endRow 0x%llx"
-			"Start span 0x%x\n", (unsigned long long)start_row,
-			(unsigned long long)endRow, startlba_span);
-#endif
 	} else {
 		start_row = mega_div64_32(start_strip, raid->rowDataSize);
 		endRow    = mega_div64_32(endStrip, raid->rowDataSize);
@@ -1093,20 +1094,20 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 			regSize += stripSize;
 	}
 
-	pRAID_Context->timeoutValue =
+	pRAID_Context->timeout_value =
 		cpu_to_le16(raid->fpIoTimeoutForLd ?
 			    raid->fpIoTimeoutForLd :
 			    map->raidMap.fpPdIoTimeoutSec);
 	if (fusion->adapter_type == INVADER_SERIES)
-		pRAID_Context->regLockFlags = (isRead) ?
+		pRAID_Context->reg_lock_flags = (isRead) ?
 			raid->regTypeReqOnRead : raid->regTypeReqOnWrite;
-	else
-		pRAID_Context->regLockFlags = (isRead) ?
+	else if (!instance->is_ventura)
+		pRAID_Context->reg_lock_flags = (isRead) ?
 			REGION_TYPE_SHARED_READ : raid->regTypeReqOnWrite;
-	pRAID_Context->VirtualDiskTgtId = raid->targetId;
-	pRAID_Context->regLockRowLBA    = cpu_to_le64(regStart);
-	pRAID_Context->regLockLength    = cpu_to_le32(regSize);
-	pRAID_Context->configSeqNum	= raid->seqNum;
+	pRAID_Context->virtual_disk_tgt_id = raid->targetId;
+	pRAID_Context->reg_lock_row_lba    = cpu_to_le64(regStart);
+	pRAID_Context->reg_lock_length    = cpu_to_le32(regSize);
+	pRAID_Context->config_seq_num	= raid->seqNum;
 	/* save pointer to raid->LUN array */
 	*raidLUN = raid->LUN;
 
@@ -1122,7 +1123,7 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 					ref_in_start_stripe, io_info,
 					pRAID_Context, map);
 		/* If IO on an invalid Pd, then FP is not possible.*/
-		if (io_info->devHandle == cpu_to_le16(MR_PD_INVALID))
+		if (io_info->devHandle == MR_DEVHANDLE_INVALID)
 			io_info->fpOkForIo = FALSE;
 		return retval;
 	} else if (isRead) {
@@ -1140,12 +1141,6 @@ MR_BuildRaidContext(struct megasas_instance *instance,
 				return TRUE;
 		}
 	}
-
-#if SPAN_DEBUG
-	/* Just for testing what arm we get for strip.*/
-	if (io_info->IoforUnevenSpan)
-		get_arm_from_strip(instance, ld, start_strip, map);
-#endif
 	return TRUE;
 }
 
@@ -1259,10 +1254,6 @@ void mr_update_span_set(struct MR_DRV_RAID_MAP_ALL *map,
 			break;
 	    }
 	}
-#if SPAN_DEBUG
-	getSpanInfo(map, ldSpanInfo);
-#endif
-
 }
 
 void mr_update_load_balance_params(struct MR_DRV_RAID_MAP_ALL *drv_map,
@@ -1293,11 +1284,12 @@ void mr_update_load_balance_params(struct MR_DRV_RAID_MAP_ALL *drv_map,
 }
 
 u8 megasas_get_best_arm_pd(struct megasas_instance *instance,
-	struct LD_LOAD_BALANCE_INFO *lbInfo, struct IO_REQUEST_INFO *io_info)
+			   struct LD_LOAD_BALANCE_INFO *lbInfo,
+			   struct IO_REQUEST_INFO *io_info,
+			   struct MR_DRV_RAID_MAP_ALL *drv_map)
 {
-	struct fusion_context *fusion;
 	struct MR_LD_RAID  *raid;
-	struct MR_DRV_RAID_MAP_ALL *drv_map;
+	u16	pd1_dev_handle;
 	u16     pend0, pend1, ld;
 	u64     diff0, diff1;
 	u8      bestArm, pd0, pd1, span, arm;
@@ -1310,9 +1302,6 @@ u8 megasas_get_best_arm_pd(struct megasas_instance *instance,
 			>> RAID_CTX_SPANARM_SPAN_SHIFT);
 	arm = (io_info->span_arm & RAID_CTX_SPANARM_ARM_MASK);
 
-
-	fusion = instance->ctrl_context;
-	drv_map = fusion->ld_drv_map[(instance->map_id & 1)];
 	ld = MR_TargetIdToLdGet(io_info->ldTgtId, drv_map);
 	raid = MR_LdRaidGet(ld, drv_map);
 	span_row_size = instance->UnevenSpanSupport ?
@@ -1323,47 +1312,52 @@ u8 megasas_get_best_arm_pd(struct megasas_instance *instance,
 	pd1 = MR_ArPdGet(arRef, (arm + 1) >= span_row_size ?
 		(arm + 1 - span_row_size) : arm + 1, drv_map);
 
-	/* get the pending cmds for the data and mirror arms */
-	pend0 = atomic_read(&lbInfo->scsi_pending_cmds[pd0]);
-	pend1 = atomic_read(&lbInfo->scsi_pending_cmds[pd1]);
+	/* Get PD1 Dev Handle */
+
+	pd1_dev_handle = MR_PdDevHandleGet(pd1, drv_map);
 
-	/* Determine the disk whose head is nearer to the req. block */
-	diff0 = ABS_DIFF(block, lbInfo->last_accessed_block[pd0]);
-	diff1 = ABS_DIFF(block, lbInfo->last_accessed_block[pd1]);
-	bestArm = (diff0 <= diff1 ? arm : arm ^ 1);
+	if (pd1_dev_handle == MR_DEVHANDLE_INVALID) {
+		bestArm = arm;
+	} else {
+		/* get the pending cmds for the data and mirror arms */
+		pend0 = atomic_read(&lbInfo->scsi_pending_cmds[pd0]);
+		pend1 = atomic_read(&lbInfo->scsi_pending_cmds[pd1]);
 
-	if ((bestArm == arm && pend0 > pend1 + lb_pending_cmds)  ||
-			(bestArm != arm && pend1 > pend0 + lb_pending_cmds))
-		bestArm ^= 1;
+		/* Determine the disk whose head is nearer to the req. block */
+		diff0 = ABS_DIFF(block, lbInfo->last_accessed_block[pd0]);
+		diff1 = ABS_DIFF(block, lbInfo->last_accessed_block[pd1]);
+		bestArm = (diff0 <= diff1 ? arm : arm ^ 1);
+
+		/* Make balance count from 16 to 4 to
+		 *  keep driver in sync with Firmware
+		 */
+		if ((bestArm == arm && pend0 > pend1 + lb_pending_cmds)  ||
+		    (bestArm != arm && pend1 > pend0 + lb_pending_cmds))
+			bestArm ^= 1;
+
+		/* Update the last accessed block on the correct pd */
+		io_info->span_arm =
+			(span << RAID_CTX_SPANARM_SPAN_SHIFT) | bestArm;
+		io_info->pd_after_lb = (bestArm == arm) ? pd0 : pd1;
+	}
 
-	/* Update the last accessed block on the correct pd */
-	io_info->pd_after_lb = (bestArm == arm) ? pd0 : pd1;
 	lbInfo->last_accessed_block[io_info->pd_after_lb] = block + count - 1;
-	io_info->span_arm = (span << RAID_CTX_SPANARM_SPAN_SHIFT) | bestArm;
-#if SPAN_DEBUG
-	if (arm != bestArm)
-		dev_dbg(&instance->pdev->dev, "LSI Debug R1 Load balance "
-			"occur - span 0x%x arm 0x%x bestArm 0x%x "
-			"io_info->span_arm 0x%x\n",
-			span, arm, bestArm, io_info->span_arm);
-#endif
 	return io_info->pd_after_lb;
 }
 
 __le16 get_updated_dev_handle(struct megasas_instance *instance,
-	struct LD_LOAD_BALANCE_INFO *lbInfo, struct IO_REQUEST_INFO *io_info)
+			      struct LD_LOAD_BALANCE_INFO *lbInfo,
+			      struct IO_REQUEST_INFO *io_info,
+			      struct MR_DRV_RAID_MAP_ALL *drv_map)
 {
 	u8 arm_pd;
 	__le16 devHandle;
-	struct fusion_context *fusion;
-	struct MR_DRV_RAID_MAP_ALL *drv_map;
-
-	fusion = instance->ctrl_context;
-	drv_map = fusion->ld_drv_map[(instance->map_id & 1)];
 
 	/* get best new arm (PD ID) */
-	arm_pd  = megasas_get_best_arm_pd(instance, lbInfo, io_info);
+	arm_pd  = megasas_get_best_arm_pd(instance, lbInfo, io_info, drv_map);
 	devHandle = MR_PdDevHandleGet(arm_pd, drv_map);
+	io_info->pd_interface = MR_PdInterfaceTypeGet(arm_pd, drv_map);
 	atomic_inc(&lbInfo->scsi_pending_cmds[arm_pd]);
+
 	return devHandle;
 }
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 24778ba4b6e8..29650ba669da 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -47,6 +47,7 @@
 #include <linux/blkdev.h>
 #include <linux/mutex.h>
 #include <linux/poll.h>
+#include <linux/vmalloc.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -181,32 +182,44 @@ inline void megasas_return_cmd_fusion(struct megasas_instance *instance,
 	struct megasas_cmd_fusion *cmd)
 {
 	cmd->scmd = NULL;
-	memset(cmd->io_request, 0, sizeof(struct MPI2_RAID_SCSI_IO_REQUEST));
+	memset(cmd->io_request, 0, MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE);
+	cmd->r1_alt_dev_handle = MR_DEVHANDLE_INVALID;
+	cmd->cmd_completed = false;
 }
 
 /**
  * megasas_fire_cmd_fusion -	Sends command to the FW
+ * @instance:			Adapter soft state
+ * @req_desc:			32bit or 64bit Request descriptor
+ *
+ * Perform PCI Write. Ventura supports 32 bit Descriptor.
+ * Prior to Ventura (12G) MR controller supports 64 bit Descriptor.
  */
+
 static void
 megasas_fire_cmd_fusion(struct megasas_instance *instance,
 		union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc)
 {
+	if (instance->is_ventura)
+		writel(le32_to_cpu(req_desc->u.low),
+			&instance->reg_set->inbound_single_queue_port);
+	else {
 #if defined(writeq) && defined(CONFIG_64BIT)
-	u64 req_data = (((u64)le32_to_cpu(req_desc->u.high) << 32) |
-			le32_to_cpu(req_desc->u.low));
+		u64 req_data = (((u64)le32_to_cpu(req_desc->u.high) << 32) |
+				le32_to_cpu(req_desc->u.low));
 
-	writeq(req_data, &instance->reg_set->inbound_low_queue_port);
+		writeq(req_data, &instance->reg_set->inbound_low_queue_port);
 #else
-	unsigned long flags;
-
-	spin_lock_irqsave(&instance->hba_lock, flags);
-	writel(le32_to_cpu(req_desc->u.low),
-		&instance->reg_set->inbound_low_queue_port);
-	writel(le32_to_cpu(req_desc->u.high),
-		&instance->reg_set->inbound_high_queue_port);
-	mmiowb();
-	spin_unlock_irqrestore(&instance->hba_lock, flags);
+		unsigned long flags;
+		spin_lock_irqsave(&instance->hba_lock, flags);
+		writel(le32_to_cpu(req_desc->u.low),
+			&instance->reg_set->inbound_low_queue_port);
+		writel(le32_to_cpu(req_desc->u.high),
+			&instance->reg_set->inbound_high_queue_port);
+		mmiowb();
+		spin_unlock_irqrestore(&instance->hba_lock, flags);
 #endif
+	}
 }
 
 /**
@@ -229,7 +242,10 @@ megasas_fusion_update_can_queue(struct megasas_instance *instance, int fw_boot_c
 
 	reg_set = instance->reg_set;
 
-	cur_max_fw_cmds = readl(&instance->reg_set->outbound_scratch_pad_3) & 0x00FFFF;
+	/* ventura FW does not fill outbound_scratch_pad_3 with queue depth */
+	if (!instance->is_ventura)
+		cur_max_fw_cmds =
+		readl(&instance->reg_set->outbound_scratch_pad_3) & 0x00FFFF;
 
 	if (dual_qdepth_disable || !cur_max_fw_cmds)
 		cur_max_fw_cmds = instance->instancet->read_fw_status_reg(reg_set) & 0x00FFFF;
@@ -243,7 +259,7 @@ megasas_fusion_update_can_queue(struct megasas_instance *instance, int fw_boot_c
 
 	if (fw_boot_context == OCR_CONTEXT) {
 		cur_max_fw_cmds = cur_max_fw_cmds - 1;
-		if (cur_max_fw_cmds <= instance->max_fw_cmds) {
+		if (cur_max_fw_cmds < instance->max_fw_cmds) {
 			instance->cur_can_queue =
 				cur_max_fw_cmds - (MEGASAS_FUSION_INTERNAL_CMDS +
 						MEGASAS_FUSION_IOCTL_CMDS);
@@ -255,7 +271,8 @@ megasas_fusion_update_can_queue(struct megasas_instance *instance, int fw_boot_c
 		instance->ldio_threshold = ldio_threshold;
 
 		if (!instance->is_rdpq)
-			instance->max_fw_cmds = min_t(u16, instance->max_fw_cmds, 1024);
+			instance->max_fw_cmds =
+				min_t(u16, instance->max_fw_cmds, 1024);
 
 		if (reset_devices)
 			instance->max_fw_cmds = min(instance->max_fw_cmds,
@@ -271,7 +288,14 @@ megasas_fusion_update_can_queue(struct megasas_instance *instance, int fw_boot_c
 				(MEGASAS_FUSION_INTERNAL_CMDS +
 				MEGASAS_FUSION_IOCTL_CMDS);
 		instance->cur_can_queue = instance->max_scsi_cmds;
+		instance->host->can_queue = instance->cur_can_queue;
 	}
+
+	if (instance->is_ventura)
+		instance->max_mpt_cmds =
+		instance->max_fw_cmds * RAID_1_PEER_CMDS;
+	else
+		instance->max_mpt_cmds = instance->max_fw_cmds;
 }
 /**
  * megasas_free_cmds_fusion -	Free all the cmds in the free cmd pool
@@ -285,7 +309,7 @@ megasas_free_cmds_fusion(struct megasas_instance *instance)
 	struct megasas_cmd_fusion *cmd;
 
 	/* SG, Sense */
-	for (i = 0; i < instance->max_fw_cmds; i++) {
+	for (i = 0; i < instance->max_mpt_cmds; i++) {
 		cmd = fusion->cmd_list[i];
 		if (cmd) {
 			if (cmd->sg_frame)
@@ -329,7 +353,7 @@ megasas_free_cmds_fusion(struct megasas_instance *instance)
 
 
 	/* cmd_list */
-	for (i = 0; i < instance->max_fw_cmds; i++)
+	for (i = 0; i < instance->max_mpt_cmds; i++)
 		kfree(fusion->cmd_list[i]);
 
 	kfree(fusion->cmd_list);
@@ -343,7 +367,7 @@ megasas_free_cmds_fusion(struct megasas_instance *instance)
 static int megasas_create_sg_sense_fusion(struct megasas_instance *instance)
 {
 	int i;
-	u32 max_cmd;
+	u16 max_cmd;
 	struct fusion_context *fusion;
 	struct megasas_cmd_fusion *cmd;
 
@@ -353,7 +377,8 @@ static int megasas_create_sg_sense_fusion(struct megasas_instance *instance)
 
 	fusion->sg_dma_pool =
 			pci_pool_create("mr_sg", instance->pdev,
-				instance->max_chain_frame_sz, 4, 0);
+				instance->max_chain_frame_sz,
+				MR_DEFAULT_NVME_PAGE_SIZE, 0);
 	/* SCSI_SENSE_BUFFERSIZE  = 96 bytes */
 	fusion->sense_dma_pool =
 			pci_pool_create("mr_sense", instance->pdev,
@@ -381,33 +406,47 @@ static int megasas_create_sg_sense_fusion(struct megasas_instance *instance)
 			return -ENOMEM;
 		}
 	}
+
+	/* create sense buffer for the raid 1/10 fp */
+	for (i = max_cmd; i < instance->max_mpt_cmds; i++) {
+		cmd = fusion->cmd_list[i];
+		cmd->sense = pci_pool_alloc(fusion->sense_dma_pool,
+			GFP_KERNEL, &cmd->sense_phys_addr);
+		if (!cmd->sense) {
+			dev_err(&instance->pdev->dev,
+				"Failed from %s %d\n",  __func__, __LINE__);
+			return -ENOMEM;
+		}
+	}
+
 	return 0;
 }
 
 int
 megasas_alloc_cmdlist_fusion(struct megasas_instance *instance)
 {
-	u32 max_cmd, i;
+	u32 max_mpt_cmd, i;
 	struct fusion_context *fusion;
 
 	fusion = instance->ctrl_context;
 
-	max_cmd = instance->max_fw_cmds;
+	max_mpt_cmd = instance->max_mpt_cmds;
 
 	/*
 	 * fusion->cmd_list is an array of struct megasas_cmd_fusion pointers.
 	 * Allocate the dynamic array first and then allocate individual
 	 * commands.
 	 */
-	fusion->cmd_list = kzalloc(sizeof(struct megasas_cmd_fusion *) * max_cmd,
-						GFP_KERNEL);
+	fusion->cmd_list =
+		kzalloc(sizeof(struct megasas_cmd_fusion *) * max_mpt_cmd,
+			GFP_KERNEL);
 	if (!fusion->cmd_list) {
 		dev_err(&instance->pdev->dev,
 			"Failed from %s %d\n",  __func__, __LINE__);
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < max_cmd; i++) {
+	for (i = 0; i < max_mpt_cmd; i++) {
 		fusion->cmd_list[i] = kzalloc(sizeof(struct megasas_cmd_fusion),
 					      GFP_KERNEL);
 		if (!fusion->cmd_list[i]) {
@@ -539,7 +578,7 @@ megasas_alloc_rdpq_fusion(struct megasas_instance *instance)
 		}
 
 		fusion->rdpq_virt[i].RDPQBaseAddress =
-			fusion->reply_frames_desc_phys[i];
+			cpu_to_le64(fusion->reply_frames_desc_phys[i]);
 
 		reply_desc = fusion->reply_frames_desc[i];
 		for (j = 0; j < fusion->reply_q_depth; j++, reply_desc++)
@@ -642,13 +681,14 @@ megasas_alloc_cmds_fusion(struct megasas_instance *instance)
 	 */
 
 	/* SMID 0 is reserved. Set SMID/index from 1 */
-	for (i = 0; i < instance->max_fw_cmds; i++) {
+	for (i = 0; i < instance->max_mpt_cmds; i++) {
 		cmd = fusion->cmd_list[i];
 		offset = MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE * i;
 		memset(cmd, 0, sizeof(struct megasas_cmd_fusion));
 		cmd->index = i + 1;
 		cmd->scmd = NULL;
-		cmd->sync_cmd_idx = (i >= instance->max_scsi_cmds) ?
+		cmd->sync_cmd_idx =
+		(i >= instance->max_scsi_cmds && i < instance->max_fw_cmds) ?
 				(i - instance->max_scsi_cmds) :
 				(u32)ULONG_MAX; /* Set to Invalid */
 		cmd->instance = instance;
@@ -658,6 +698,7 @@ megasas_alloc_cmds_fusion(struct megasas_instance *instance)
 		memset(cmd->io_request, 0,
 		       sizeof(struct MPI2_RAID_SCSI_IO_REQUEST));
 		cmd->io_request_phys_addr = io_req_base_phys + offset;
+		cmd->r1_alt_dev_handle = MR_DEVHANDLE_INVALID;
 	}
 
 	if (megasas_create_sg_sense_fusion(instance))
@@ -725,6 +766,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 	const char *sys_info;
 	MFI_CAPABILITIES *drv_ops;
 	u32 scratch_pad_2;
+	unsigned long flags;
 
 	fusion = instance->ctrl_context;
 
@@ -781,6 +823,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 			MPI2_IOCINIT_MSGFLAG_RDPQ_ARRAY_MODE : 0;
 	IOCInitMessage->SystemRequestFrameBaseAddress = cpu_to_le64(fusion->io_request_frames_phys);
 	IOCInitMessage->HostMSIxVectors = instance->msix_vectors;
+	IOCInitMessage->HostPageSize = MR_DEFAULT_NVME_PAGE_SHIFT;
 	init_frame = (struct megasas_init_frame *)cmd->frame;
 	memset(init_frame, 0, MEGAMFI_FRAME_SIZE);
 
@@ -796,7 +839,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 	drv_ops = (MFI_CAPABILITIES *) &(init_frame->driver_operations);
 
 	/* driver support Extended MSIX */
-	if (fusion->adapter_type == INVADER_SERIES)
+	if (fusion->adapter_type >= INVADER_SERIES)
 		drv_ops->mfi_capabilities.support_additional_msix = 1;
 	/* driver supports HA / Remote LUN over Fast Path interface */
 	drv_ops->mfi_capabilities.support_fp_remote_lun = 1;
@@ -813,6 +856,7 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 		drv_ops->mfi_capabilities.support_ext_queue_depth = 1;
 
 	drv_ops->mfi_capabilities.support_qd_throttling = 1;
+	drv_ops->mfi_capabilities.support_pd_map_target_id = 1;
 	/* Convert capability to LE32 */
 	cpu_to_le32s((u32 *)&init_frame->driver_operations.mfi_capabilities);
 
@@ -850,7 +894,14 @@ megasas_ioc_init_fusion(struct megasas_instance *instance)
 			break;
 	}
 
-	megasas_fire_cmd_fusion(instance, &req_desc);
+	/* For Ventura also IOC INIT required 64 bit Descriptor write. */
+	spin_lock_irqsave(&instance->hba_lock, flags);
+	writel(le32_to_cpu(req_desc.u.low),
+	       &instance->reg_set->inbound_low_queue_port);
+	writel(le32_to_cpu(req_desc.u.high),
+	       &instance->reg_set->inbound_high_queue_port);
+	mmiowb();
+	spin_unlock_irqrestore(&instance->hba_lock, flags);
 
 	wait_and_poll(instance, cmd, MFI_POLL_TIMEOUT_SECS);
 
@@ -1009,11 +1060,6 @@ megasas_get_ld_map_info(struct megasas_instance *instance)
 
 	memset(ci, 0, fusion->max_map_sz);
 	memset(dcmd->mbox.b, 0, MFI_MBOX_SIZE);
-#if VD_EXT_DEBUG
-	dev_dbg(&instance->pdev->dev,
-		"%s sending MR_DCMD_LD_MAP_GET_INFO with size %d\n",
-		__func__, cpu_to_le32(size_map_info));
-#endif
 	dcmd->cmd = MFI_CMD_DCMD;
 	dcmd->cmd_status = 0xFF;
 	dcmd->sge_count = 1;
@@ -1065,10 +1111,11 @@ megasas_get_map_info(struct megasas_instance *instance)
 int
 megasas_sync_map_info(struct megasas_instance *instance)
 {
-	int ret = 0, i;
+	int i;
 	struct megasas_cmd *cmd;
 	struct megasas_dcmd_frame *dcmd;
-	u32 size_sync_info, num_lds;
+	u16 num_lds;
+	u32 size_sync_info;
 	struct fusion_context *fusion;
 	struct MR_LD_TARGET_SYNC *ci = NULL;
 	struct MR_DRV_RAID_MAP_ALL *map;
@@ -1134,7 +1181,7 @@ megasas_sync_map_info(struct megasas_instance *instance)
 
 	instance->instancet->issue_dcmd(instance, cmd);
 
-	return ret;
+	return 0;
 }
 
 /*
@@ -1220,7 +1267,8 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
 {
 	struct megasas_register_set __iomem *reg_set;
 	struct fusion_context *fusion;
-	u32 max_cmd, scratch_pad_2;
+	u16 max_cmd;
+	u32 scratch_pad_2;
 	int i = 0, count;
 
 	fusion = instance->ctrl_context;
@@ -1230,13 +1278,6 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
 	megasas_fusion_update_can_queue(instance, PROBE_CONTEXT);
 
 	/*
-	 * Reduce the max supported cmds by 1. This is to ensure that the
-	 * reply_q_sz (1 more than the max cmd that driver may send)
-	 * does not exceed max cmds that the FW can support
-	 */
-	instance->max_fw_cmds = instance->max_fw_cmds-1;
-
-	/*
 	 * Only Driver's internal DCMDs and IOCTL DCMDs needs to have MFI frames
 	 */
 	instance->max_mfi_cmds =
@@ -1247,12 +1288,12 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
 	fusion->reply_q_depth = 2 * (((max_cmd + 1 + 15)/16)*16);
 
 	fusion->request_alloc_sz =
-		sizeof(union MEGASAS_REQUEST_DESCRIPTOR_UNION) *max_cmd;
+	sizeof(union MEGASAS_REQUEST_DESCRIPTOR_UNION) * instance->max_mpt_cmds;
 	fusion->reply_alloc_sz = sizeof(union MPI2_REPLY_DESCRIPTORS_UNION)
 		*(fusion->reply_q_depth);
 	fusion->io_frames_alloc_sz = MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE +
-		(MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE *
-		 (max_cmd + 1)); /* Extra 1 for SMID 0 */
+		(MEGA_MPI2_RAID_DEFAULT_IO_FRAME_SIZE
+		* (instance->max_mpt_cmds + 1)); /* Extra 1 for SMID 0 */
 
 	scratch_pad_2 = readl(&instance->reg_set->outbound_scratch_pad_2);
 	/* If scratch_pad_2 & MEGASAS_MAX_CHAIN_SIZE_UNITS_MASK is set,
@@ -1302,7 +1343,7 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
 		fusion->last_reply_idx[i] = 0;
 
 	/*
-	 * For fusion adapters, 3 commands for IOCTL and 5 commands
+	 * For fusion adapters, 3 commands for IOCTL and 8 commands
 	 * for driver's internal DCMDs.
 	 */
 	instance->max_scsi_cmds = instance->max_fw_cmds -
@@ -1331,6 +1372,7 @@ megasas_init_adapter_fusion(struct megasas_instance *instance)
 	}
 
 	instance->flag_ieee = 1;
+	instance->r1_ldio_hint_default =  MR_R1_LDIO_PIGGYBACK_DEFAULT;
 	fusion->fast_path_io = 0;
 
 	fusion->drv_map_pages = get_order(fusion->drv_map_sz);
@@ -1388,96 +1430,348 @@ fail_alloc_mfi_cmds:
  */
 
 void
-map_cmd_status(struct megasas_cmd_fusion *cmd, u8 status, u8 ext_status)
+map_cmd_status(struct fusion_context *fusion,
+		struct scsi_cmnd *scmd, u8 status, u8 ext_status,
+		u32 data_length, u8 *sense)
 {
+	u8 cmd_type;
+	int resid;
 
+	cmd_type = megasas_cmd_type(scmd);
 	switch (status) {
 
 	case MFI_STAT_OK:
-		cmd->scmd->result = DID_OK << 16;
+		scmd->result = DID_OK << 16;
 		break;
 
 	case MFI_STAT_SCSI_IO_FAILED:
 	case MFI_STAT_LD_INIT_IN_PROGRESS:
-		cmd->scmd->result = (DID_ERROR << 16) | ext_status;
+		scmd->result = (DID_ERROR << 16) | ext_status;
 		break;
 
 	case MFI_STAT_SCSI_DONE_WITH_ERROR:
 
-		cmd->scmd->result = (DID_OK << 16) | ext_status;
+		scmd->result = (DID_OK << 16) | ext_status;
 		if (ext_status == SAM_STAT_CHECK_CONDITION) {
-			memset(cmd->scmd->sense_buffer, 0,
+			memset(scmd->sense_buffer, 0,
 			       SCSI_SENSE_BUFFERSIZE);
-			memcpy(cmd->scmd->sense_buffer, cmd->sense,
+			memcpy(scmd->sense_buffer, sense,
 			       SCSI_SENSE_BUFFERSIZE);
-			cmd->scmd->result |= DRIVER_SENSE << 24;
+			scmd->result |= DRIVER_SENSE << 24;
 		}
+
+		/*
+		 * If the  IO request is partially completed, then MR FW will
+		 * update "io_request->DataLength" field with actual number of
+		 * bytes transferred.Driver will set residual bytes count in
+		 * SCSI command structure.
+		 */
+		resid = (scsi_bufflen(scmd) - data_length);
+		scsi_set_resid(scmd, resid);
+
+		if (resid &&
+			((cmd_type == READ_WRITE_LDIO) ||
+			(cmd_type == READ_WRITE_SYSPDIO)))
+			scmd_printk(KERN_INFO, scmd, "BRCM Debug mfi stat 0x%x, data len"
+				" requested/completed 0x%x/0x%x\n",
+				status, scsi_bufflen(scmd), data_length);
 		break;
 
 	case MFI_STAT_LD_OFFLINE:
 	case MFI_STAT_DEVICE_NOT_FOUND:
-		cmd->scmd->result = DID_BAD_TARGET << 16;
+		scmd->result = DID_BAD_TARGET << 16;
 		break;
 	case MFI_STAT_CONFIG_SEQ_MISMATCH:
-		cmd->scmd->result = DID_IMM_RETRY << 16;
+		scmd->result = DID_IMM_RETRY << 16;
 		break;
 	default:
-		dev_printk(KERN_DEBUG, &cmd->instance->pdev->dev, "FW status %#x\n", status);
-		cmd->scmd->result = DID_ERROR << 16;
+		scmd->result = DID_ERROR << 16;
 		break;
 	}
 }
 
 /**
+ * megasas_is_prp_possible -
+ * Checks if native NVMe PRPs can be built for the IO
+ *
+ * @instance:		Adapter soft state
+ * @scmd:		SCSI command from the mid-layer
+ * @sge_count:		scatter gather element count.
+ *
+ * Returns:		true: PRPs can be built
+ *			false: IEEE SGLs needs to be built
+ */
+static bool
+megasas_is_prp_possible(struct megasas_instance *instance,
+			struct scsi_cmnd *scmd, int sge_count)
+{
+	struct fusion_context *fusion;
+	int i;
+	u32 data_length = 0;
+	struct scatterlist *sg_scmd;
+	bool build_prp = false;
+	u32 mr_nvme_pg_size;
+
+	mr_nvme_pg_size = max_t(u32, instance->nvme_page_size,
+				MR_DEFAULT_NVME_PAGE_SIZE);
+	fusion = instance->ctrl_context;
+	data_length = scsi_bufflen(scmd);
+	sg_scmd = scsi_sglist(scmd);
+
+	/*
+	 * NVMe uses one PRP for each page (or part of a page)
+	 * look at the data length - if 4 pages or less then IEEE is OK
+	 * if  > 5 pages then we need to build a native SGL
+	 * if > 4 and <= 5 pages, then check physical address of 1st SG entry
+	 * if this first size in the page is >= the residual beyond 4 pages
+	 * then use IEEE, otherwise use native SGL
+	 */
+
+	if (data_length > (mr_nvme_pg_size * 5)) {
+		build_prp = true;
+	} else if ((data_length > (mr_nvme_pg_size * 4)) &&
+			(data_length <= (mr_nvme_pg_size * 5)))  {
+		/* check if 1st SG entry size is < residual beyond 4 pages */
+		if (sg_dma_len(sg_scmd) < (data_length - (mr_nvme_pg_size * 4)))
+			build_prp = true;
+	}
+
+/*
+ * Below code detects gaps/holes in IO data buffers.
+ * What does holes/gaps mean?
+ * Any SGE except first one in a SGL starts at non NVME page size
+ * aligned address OR Any SGE except last one in a SGL ends at
+ * non NVME page size boundary.
+ *
+ * Driver has already informed block layer by setting boundary rules for
+ * bio merging done at NVME page size boundary calling kernel API
+ * blk_queue_virt_boundary inside slave_config.
+ * Still there is possibility of IO coming with holes to driver because of
+ * IO merging done by IO scheduler.
+ *
+ * With SCSI BLK MQ enabled, there will be no IO with holes as there is no
+ * IO scheduling so no IO merging.
+ *
+ * With SCSI BLK MQ disabled, IO scheduler may attempt to merge IOs and
+ * then sending IOs with holes.
+ *
+ * Though driver can request block layer to disable IO merging by calling-
+ * queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, sdev->request_queue) but
+ * user may tune sysfs parameter- nomerges again to 0 or 1.
+ *
+ * If in future IO scheduling is enabled with SCSI BLK MQ,
+ * this algorithm to detect holes will be required in driver
+ * for SCSI BLK MQ enabled case as well.
+ *
+ *
+ */
+	scsi_for_each_sg(scmd, sg_scmd, sge_count, i) {
+		if ((i != 0) && (i != (sge_count - 1))) {
+			if (mega_mod64(sg_dma_len(sg_scmd), mr_nvme_pg_size) ||
+			    mega_mod64(sg_dma_address(sg_scmd),
+				       mr_nvme_pg_size)) {
+				build_prp = false;
+				atomic_inc(&instance->sge_holes_type1);
+				break;
+			}
+		}
+
+		if ((sge_count > 1) && (i == 0)) {
+			if ((mega_mod64((sg_dma_address(sg_scmd) +
+					sg_dma_len(sg_scmd)),
+					mr_nvme_pg_size))) {
+				build_prp = false;
+				atomic_inc(&instance->sge_holes_type2);
+				break;
+			}
+		}
+
+		if ((sge_count > 1) && (i == (sge_count - 1))) {
+			if (mega_mod64(sg_dma_address(sg_scmd),
+				       mr_nvme_pg_size)) {
+				build_prp = false;
+				atomic_inc(&instance->sge_holes_type3);
+				break;
+			}
+		}
+	}
+
+	return build_prp;
+}
+
+/**
+ * megasas_make_prp_nvme -
+ * Prepare PRPs(Physical Region Page)- SGLs specific to NVMe drives only
+ *
+ * @instance:		Adapter soft state
+ * @scmd:		SCSI command from the mid-layer
+ * @sgl_ptr:		SGL to be filled in
+ * @cmd:		Fusion command frame
+ * @sge_count:		scatter gather element count.
+ *
+ * Returns:		true: PRPs are built
+ *			false: IEEE SGLs needs to be built
+ */
+static bool
+megasas_make_prp_nvme(struct megasas_instance *instance, struct scsi_cmnd *scmd,
+		      struct MPI25_IEEE_SGE_CHAIN64 *sgl_ptr,
+		      struct megasas_cmd_fusion *cmd, int sge_count)
+{
+	int sge_len, offset, num_prp_in_chain = 0;
+	struct MPI25_IEEE_SGE_CHAIN64 *main_chain_element, *ptr_first_sgl;
+	u64 *ptr_sgl;
+	dma_addr_t ptr_sgl_phys;
+	u64 sge_addr;
+	u32 page_mask, page_mask_result;
+	struct scatterlist *sg_scmd;
+	u32 first_prp_len;
+	bool build_prp = false;
+	int data_len = scsi_bufflen(scmd);
+	struct fusion_context *fusion;
+	u32 mr_nvme_pg_size = max_t(u32, instance->nvme_page_size,
+					MR_DEFAULT_NVME_PAGE_SIZE);
+
+	fusion = instance->ctrl_context;
+
+	build_prp = megasas_is_prp_possible(instance, scmd, sge_count);
+
+	if (!build_prp)
+		return false;
+
+	/*
+	 * Nvme has a very convoluted prp format.  One prp is required
+	 * for each page or partial page. Driver need to split up OS sg_list
+	 * entries if it is longer than one page or cross a page
+	 * boundary.  Driver also have to insert a PRP list pointer entry as
+	 * the last entry in each physical page of the PRP list.
+	 *
+	 * NOTE: The first PRP "entry" is actually placed in the first
+	 * SGL entry in the main message as IEEE 64 format.  The 2nd
+	 * entry in the main message is the chain element, and the rest
+	 * of the PRP entries are built in the contiguous pcie buffer.
+	 */
+	page_mask = mr_nvme_pg_size - 1;
+	ptr_sgl = (u64 *)cmd->sg_frame;
+	ptr_sgl_phys = cmd->sg_frame_phys_addr;
+	memset(ptr_sgl, 0, instance->max_chain_frame_sz);
+
+	/* Build chain frame element which holds all prps except first*/
+	main_chain_element = (struct MPI25_IEEE_SGE_CHAIN64 *)
+	    ((u8 *)sgl_ptr + sizeof(struct MPI25_IEEE_SGE_CHAIN64));
+
+	main_chain_element->Address = cpu_to_le64(ptr_sgl_phys);
+	main_chain_element->NextChainOffset = 0;
+	main_chain_element->Flags = IEEE_SGE_FLAGS_CHAIN_ELEMENT |
+					IEEE_SGE_FLAGS_SYSTEM_ADDR |
+					MPI26_IEEE_SGE_FLAGS_NSF_NVME_PRP;
+
+	/* Build first prp, sge need not to be page aligned*/
+	ptr_first_sgl = sgl_ptr;
+	sg_scmd = scsi_sglist(scmd);
+	sge_addr = sg_dma_address(sg_scmd);
+	sge_len = sg_dma_len(sg_scmd);
+
+	offset = (u32)(sge_addr & page_mask);
+	first_prp_len = mr_nvme_pg_size - offset;
+
+	ptr_first_sgl->Address = cpu_to_le64(sge_addr);
+	ptr_first_sgl->Length = cpu_to_le32(first_prp_len);
+
+	data_len -= first_prp_len;
+
+	if (sge_len > first_prp_len) {
+		sge_addr += first_prp_len;
+		sge_len -= first_prp_len;
+	} else if (sge_len == first_prp_len) {
+		sg_scmd = sg_next(sg_scmd);
+		sge_addr = sg_dma_address(sg_scmd);
+		sge_len = sg_dma_len(sg_scmd);
+	}
+
+	for (;;) {
+		offset = (u32)(sge_addr & page_mask);
+
+		/* Put PRP pointer due to page boundary*/
+		page_mask_result = (uintptr_t)(ptr_sgl + 1) & page_mask;
+		if (unlikely(!page_mask_result)) {
+			scmd_printk(KERN_NOTICE,
+				    scmd, "page boundary ptr_sgl: 0x%p\n",
+				    ptr_sgl);
+			ptr_sgl_phys += 8;
+			*ptr_sgl = cpu_to_le64(ptr_sgl_phys);
+			ptr_sgl++;
+			num_prp_in_chain++;
+		}
+
+		*ptr_sgl = cpu_to_le64(sge_addr);
+		ptr_sgl++;
+		ptr_sgl_phys += 8;
+		num_prp_in_chain++;
+
+		sge_addr += mr_nvme_pg_size;
+		sge_len -= mr_nvme_pg_size;
+		data_len -= mr_nvme_pg_size;
+
+		if (data_len <= 0)
+			break;
+
+		if (sge_len > 0)
+			continue;
+
+		sg_scmd = sg_next(sg_scmd);
+		sge_addr = sg_dma_address(sg_scmd);
+		sge_len = sg_dma_len(sg_scmd);
+	}
+
+	main_chain_element->Length =
+			cpu_to_le32(num_prp_in_chain * sizeof(u64));
+
+	atomic_inc(&instance->prp_sgl);
+	return build_prp;
+}
+
+/**
  * megasas_make_sgl_fusion -	Prepares 32-bit SGL
  * @instance:		Adapter soft state
  * @scp:		SCSI command from the mid-layer
  * @sgl_ptr:		SGL to be filled in
  * @cmd:		cmd we are working on
+ * @sge_count		sge count
  *
- * If successful, this function returns the number of SG elements.
  */
-static int
+static void
 megasas_make_sgl_fusion(struct megasas_instance *instance,
 			struct scsi_cmnd *scp,
 			struct MPI25_IEEE_SGE_CHAIN64 *sgl_ptr,
-			struct megasas_cmd_fusion *cmd)
+			struct megasas_cmd_fusion *cmd, int sge_count)
 {
-	int i, sg_processed, sge_count;
+	int i, sg_processed;
 	struct scatterlist *os_sgl;
 	struct fusion_context *fusion;
 
 	fusion = instance->ctrl_context;
 
-	if (fusion->adapter_type == INVADER_SERIES) {
+	if (fusion->adapter_type >= INVADER_SERIES) {
 		struct MPI25_IEEE_SGE_CHAIN64 *sgl_ptr_end = sgl_ptr;
 		sgl_ptr_end += fusion->max_sge_in_main_msg - 1;
 		sgl_ptr_end->Flags = 0;
 	}
 
-	sge_count = scsi_dma_map(scp);
-
-	BUG_ON(sge_count < 0);
-
-	if (sge_count > instance->max_num_sge || !sge_count)
-		return sge_count;
-
 	scsi_for_each_sg(scp, os_sgl, sge_count, i) {
 		sgl_ptr->Length = cpu_to_le32(sg_dma_len(os_sgl));
 		sgl_ptr->Address = cpu_to_le64(sg_dma_address(os_sgl));
 		sgl_ptr->Flags = 0;
-		if (fusion->adapter_type == INVADER_SERIES)
+		if (fusion->adapter_type >= INVADER_SERIES)
 			if (i == sge_count - 1)
 				sgl_ptr->Flags = IEEE_SGE_FLAGS_END_OF_LIST;
 		sgl_ptr++;
-
 		sg_processed = i + 1;
 
 		if ((sg_processed ==  (fusion->max_sge_in_main_msg - 1)) &&
 		    (sge_count > fusion->max_sge_in_main_msg)) {
 
 			struct MPI25_IEEE_SGE_CHAIN64 *sg_chain;
-			if (fusion->adapter_type == INVADER_SERIES) {
+			if (fusion->adapter_type >= INVADER_SERIES) {
 				if ((le16_to_cpu(cmd->io_request->IoFlags) &
 					MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH) !=
 					MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH)
@@ -1493,7 +1787,7 @@ megasas_make_sgl_fusion(struct megasas_instance *instance,
 			sg_chain = sgl_ptr;
 			/* Prepare chain element */
 			sg_chain->NextChainOffset = 0;
-			if (fusion->adapter_type == INVADER_SERIES)
+			if (fusion->adapter_type >= INVADER_SERIES)
 				sg_chain->Flags = IEEE_SGE_FLAGS_CHAIN_ELEMENT;
 			else
 				sg_chain->Flags =
@@ -1507,6 +1801,45 @@ megasas_make_sgl_fusion(struct megasas_instance *instance,
 			memset(sgl_ptr, 0, instance->max_chain_frame_sz);
 		}
 	}
+	atomic_inc(&instance->ieee_sgl);
+}
+
+/**
+ * megasas_make_sgl -	Build Scatter Gather List(SGLs)
+ * @scp:		SCSI command pointer
+ * @instance:		Soft instance of controller
+ * @cmd:		Fusion command pointer
+ *
+ * This function will build sgls based on device type.
+ * For nvme drives, there is different way of building sgls in nvme native
+ * format- PRPs(Physical Region Page).
+ *
+ * Returns the number of sg lists actually used, zero if the sg lists
+ * is NULL, or -ENOMEM if the mapping failed
+ */
+static
+int megasas_make_sgl(struct megasas_instance *instance, struct scsi_cmnd *scp,
+		     struct megasas_cmd_fusion *cmd)
+{
+	int sge_count;
+	bool build_prp = false;
+	struct MPI25_IEEE_SGE_CHAIN64 *sgl_chain64;
+
+	sge_count = scsi_dma_map(scp);
+
+	if ((sge_count > instance->max_num_sge) || (sge_count <= 0))
+		return sge_count;
+
+	sgl_chain64 = (struct MPI25_IEEE_SGE_CHAIN64 *)&cmd->io_request->SGL;
+	if ((le16_to_cpu(cmd->io_request->IoFlags) &
+	    MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH) &&
+	    (cmd->pd_interface == NVME_PD))
+		build_prp = megasas_make_prp_nvme(instance, scp, sgl_chain64,
+						  cmd, sge_count);
+
+	if (!build_prp)
+		megasas_make_sgl_fusion(instance, scp, sgl_chain64,
+					cmd, sge_count);
 
 	return sge_count;
 }
@@ -1525,7 +1858,7 @@ megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len,
 		   struct MR_DRV_RAID_MAP_ALL *local_map_ptr, u32 ref_tag)
 {
 	struct MR_LD_RAID *raid;
-	u32 ld;
+	u16 ld;
 	u64 start_blk = io_info->pdBlock;
 	u8 *cdb = io_request->CDB.CDB32;
 	u32 num_blocks = io_info->numBlocks;
@@ -1574,6 +1907,7 @@ megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len,
 				MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG |
 				MPI2_SCSIIO_EEDPFLAGS_CHECK_REMOVE_OP |
 				MPI2_SCSIIO_EEDPFLAGS_CHECK_APPTAG |
+				MPI25_SCSIIO_EEDPFLAGS_DO_NOT_DISABLE_MODE |
 				MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD);
 		} else {
 			io_request->EEDPFlags = cpu_to_le16(
@@ -1688,6 +2022,166 @@ megasas_set_pd_lba(struct MPI2_RAID_SCSI_IO_REQUEST *io_request, u8 cdb_len,
 }
 
 /**
+ * megasas_stream_detect -	stream detection on read and and write IOs
+ * @instance:		Adapter soft state
+ * @cmd:		    Command to be prepared
+ * @io_info:		IO Request info
+ *
+ */
+
+/** stream detection on read and and write IOs */
+static void megasas_stream_detect(struct megasas_instance *instance,
+				  struct megasas_cmd_fusion *cmd,
+				  struct IO_REQUEST_INFO *io_info)
+{
+	struct fusion_context *fusion = instance->ctrl_context;
+	u32 device_id = io_info->ldTgtId;
+	struct LD_STREAM_DETECT *current_ld_sd
+		= fusion->stream_detect_by_ld[device_id];
+	u32 *track_stream = &current_ld_sd->mru_bit_map, stream_num;
+	u32 shifted_values, unshifted_values;
+	u32 index_value_mask, shifted_values_mask;
+	int i;
+	bool is_read_ahead = false;
+	struct STREAM_DETECT *current_sd;
+	/* find possible stream */
+	for (i = 0; i < MAX_STREAMS_TRACKED; ++i) {
+		stream_num = (*track_stream >>
+			(i * BITS_PER_INDEX_STREAM)) &
+			STREAM_MASK;
+		current_sd = &current_ld_sd->stream_track[stream_num];
+		/* if we found a stream, update the raid
+		 *  context and also update the mruBitMap
+		 */
+		/*	boundary condition */
+		if ((current_sd->next_seq_lba) &&
+		    (io_info->ldStartBlock >= current_sd->next_seq_lba) &&
+		    (io_info->ldStartBlock <= (current_sd->next_seq_lba + 32)) &&
+		    (current_sd->is_read == io_info->isRead)) {
+
+			if ((io_info->ldStartBlock != current_sd->next_seq_lba)	&&
+			    ((!io_info->isRead) || (!is_read_ahead)))
+				/*
+				 * Once the API availible we need to change this.
+				 * At this point we are not allowing any gap
+				 */
+				continue;
+
+			SET_STREAM_DETECTED(cmd->io_request->RaidContext.raid_context_g35);
+			current_sd->next_seq_lba =
+			io_info->ldStartBlock + io_info->numBlocks;
+			/*
+			 *	update the mruBitMap LRU
+			 */
+			shifted_values_mask =
+				(1 <<  i * BITS_PER_INDEX_STREAM) - 1;
+			shifted_values = ((*track_stream & shifted_values_mask)
+						<< BITS_PER_INDEX_STREAM);
+			index_value_mask =
+				STREAM_MASK << i * BITS_PER_INDEX_STREAM;
+			unshifted_values =
+				*track_stream & ~(shifted_values_mask |
+				index_value_mask);
+			*track_stream =
+				unshifted_values | shifted_values | stream_num;
+			return;
+		}
+	}
+	/*
+	 * if we did not find any stream, create a new one
+	 * from the least recently used
+	 */
+	stream_num = (*track_stream >>
+		((MAX_STREAMS_TRACKED - 1) * BITS_PER_INDEX_STREAM)) &
+		STREAM_MASK;
+	current_sd = &current_ld_sd->stream_track[stream_num];
+	current_sd->is_read = io_info->isRead;
+	current_sd->next_seq_lba = io_info->ldStartBlock + io_info->numBlocks;
+	*track_stream = (((*track_stream & ZERO_LAST_STREAM) << 4) | stream_num);
+	return;
+}
+
+/**
+ * megasas_set_raidflag_cpu_affinity - This function sets the cpu
+ * affinity (cpu of the controller) and raid_flags in the raid context
+ * based on IO type.
+ *
+ * @praid_context:	IO RAID context
+ * @raid:		LD raid map
+ * @fp_possible:	Is fast path possible?
+ * @is_read:		Is read IO?
+ *
+ */
+static void
+megasas_set_raidflag_cpu_affinity(union RAID_CONTEXT_UNION *praid_context,
+				  struct MR_LD_RAID *raid, bool fp_possible,
+				  u8 is_read, u32 scsi_buff_len)
+{
+	u8 cpu_sel = MR_RAID_CTX_CPUSEL_0;
+	struct RAID_CONTEXT_G35 *rctx_g35;
+
+	rctx_g35 = &praid_context->raid_context_g35;
+	if (fp_possible) {
+		if (is_read) {
+			if ((raid->cpuAffinity.pdRead.cpu0) &&
+			    (raid->cpuAffinity.pdRead.cpu1))
+				cpu_sel = MR_RAID_CTX_CPUSEL_FCFS;
+			else if (raid->cpuAffinity.pdRead.cpu1)
+				cpu_sel = MR_RAID_CTX_CPUSEL_1;
+		} else {
+			if ((raid->cpuAffinity.pdWrite.cpu0) &&
+			    (raid->cpuAffinity.pdWrite.cpu1))
+				cpu_sel = MR_RAID_CTX_CPUSEL_FCFS;
+			else if (raid->cpuAffinity.pdWrite.cpu1)
+				cpu_sel = MR_RAID_CTX_CPUSEL_1;
+			/* Fast path cache by pass capable R0/R1 VD */
+			if ((raid->level <= 1) &&
+			    (raid->capability.fp_cache_bypass_capable)) {
+				rctx_g35->routing_flags |=
+					(1 << MR_RAID_CTX_ROUTINGFLAGS_SLD_SHIFT);
+				rctx_g35->raid_flags =
+					(MR_RAID_FLAGS_IO_SUB_TYPE_CACHE_BYPASS
+					<< MR_RAID_CTX_RAID_FLAGS_IO_SUB_TYPE_SHIFT);
+			}
+		}
+	} else {
+		if (is_read) {
+			if ((raid->cpuAffinity.ldRead.cpu0) &&
+			    (raid->cpuAffinity.ldRead.cpu1))
+				cpu_sel = MR_RAID_CTX_CPUSEL_FCFS;
+			else if (raid->cpuAffinity.ldRead.cpu1)
+				cpu_sel = MR_RAID_CTX_CPUSEL_1;
+		} else {
+			if ((raid->cpuAffinity.ldWrite.cpu0) &&
+			    (raid->cpuAffinity.ldWrite.cpu1))
+				cpu_sel = MR_RAID_CTX_CPUSEL_FCFS;
+			else if (raid->cpuAffinity.ldWrite.cpu1)
+				cpu_sel = MR_RAID_CTX_CPUSEL_1;
+
+			if (is_stream_detected(rctx_g35) &&
+			    (raid->level == 5) &&
+			    (raid->writeMode == MR_RL_WRITE_THROUGH_MODE) &&
+			    (cpu_sel == MR_RAID_CTX_CPUSEL_FCFS))
+				cpu_sel = MR_RAID_CTX_CPUSEL_0;
+		}
+	}
+
+	rctx_g35->routing_flags |=
+		(cpu_sel << MR_RAID_CTX_ROUTINGFLAGS_CPUSEL_SHIFT);
+
+	/* Always give priority to MR_RAID_FLAGS_IO_SUB_TYPE_LDIO_BW_LIMIT
+	 * vs MR_RAID_FLAGS_IO_SUB_TYPE_CACHE_BYPASS.
+	 * IO Subtype is not bitmap.
+	 */
+	if ((raid->level == 1) && (!is_read)) {
+		if (scsi_buff_len > MR_LARGE_IO_MIN_SIZE)
+			praid_context->raid_context_g35.raid_flags =
+				(MR_RAID_FLAGS_IO_SUB_TYPE_LDIO_BW_LIMIT
+				<< MR_RAID_CTX_RAID_FLAGS_IO_SUB_TYPE_SHIFT);
+	}
+}
+
+/**
  * megasas_build_ldio_fusion -	Prepares IOs to devices
  * @instance:		Adapter soft state
  * @scp:		SCSI command
@@ -1701,29 +2195,36 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 			  struct scsi_cmnd *scp,
 			  struct megasas_cmd_fusion *cmd)
 {
-	u8 fp_possible;
+	bool fp_possible;
+	u16 ld;
 	u32 start_lba_lo, start_lba_hi, device_id, datalength = 0;
+	u32 scsi_buff_len;
 	struct MPI2_RAID_SCSI_IO_REQUEST *io_request;
 	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc;
 	struct IO_REQUEST_INFO io_info;
 	struct fusion_context *fusion;
 	struct MR_DRV_RAID_MAP_ALL *local_map_ptr;
 	u8 *raidLUN;
+	unsigned long spinlock_flags;
+	union RAID_CONTEXT_UNION *praid_context;
+	struct MR_LD_RAID *raid = NULL;
+	struct MR_PRIV_DEVICE *mrdev_priv;
 
 	device_id = MEGASAS_DEV_INDEX(scp);
 
 	fusion = instance->ctrl_context;
 
 	io_request = cmd->io_request;
-	io_request->RaidContext.VirtualDiskTgtId = cpu_to_le16(device_id);
-	io_request->RaidContext.status = 0;
-	io_request->RaidContext.exStatus = 0;
+	io_request->RaidContext.raid_context.virtual_disk_tgt_id =
+		cpu_to_le16(device_id);
+	io_request->RaidContext.raid_context.status = 0;
+	io_request->RaidContext.raid_context.ex_status = 0;
 
 	req_desc = (union MEGASAS_REQUEST_DESCRIPTOR_UNION *)cmd->request_desc;
 
 	start_lba_lo = 0;
 	start_lba_hi = 0;
-	fp_possible = 0;
+	fp_possible = false;
 
 	/*
 	 * 6-byte READ(0x08) or WRITE(0x0A) cdb
@@ -1779,22 +2280,27 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 	io_info.ldStartBlock = ((u64)start_lba_hi << 32) | start_lba_lo;
 	io_info.numBlocks = datalength;
 	io_info.ldTgtId = device_id;
-	io_request->DataLength = cpu_to_le32(scsi_bufflen(scp));
+	io_info.r1_alt_dev_handle = MR_DEVHANDLE_INVALID;
+	scsi_buff_len = scsi_bufflen(scp);
+	io_request->DataLength = cpu_to_le32(scsi_buff_len);
 
 	if (scp->sc_data_direction == PCI_DMA_FROMDEVICE)
 		io_info.isRead = 1;
 
 	local_map_ptr = fusion->ld_drv_map[(instance->map_id & 1)];
+	ld = MR_TargetIdToLdGet(device_id, local_map_ptr);
 
-	if ((MR_TargetIdToLdGet(device_id, local_map_ptr) >=
-		instance->fw_supported_vd_count) || (!fusion->fast_path_io)) {
-		io_request->RaidContext.regLockFlags  = 0;
-		fp_possible = 0;
+	if (ld < instance->fw_supported_vd_count)
+		raid = MR_LdRaidGet(ld, local_map_ptr);
+
+	if (!raid || (!fusion->fast_path_io)) {
+		io_request->RaidContext.raid_context.reg_lock_flags  = 0;
+		fp_possible = false;
 	} else {
 		if (MR_BuildRaidContext(instance, &io_info,
-					&io_request->RaidContext,
+					&io_request->RaidContext.raid_context,
 					local_map_ptr, &raidLUN))
-			fp_possible = io_info.fpOkForIo;
+			fp_possible = (io_info.fpOkForIo > 0) ? true : false;
 	}
 
 	/* Use raw_smp_processor_id() for now until cmd->request->cpu is CPU
@@ -1803,6 +2309,54 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 	cmd->request_desc->SCSIIO.MSIxIndex = instance->msix_vectors ?
 		raw_smp_processor_id() % instance->msix_vectors : 0;
 
+	praid_context = &io_request->RaidContext;
+
+	if (instance->is_ventura) {
+		spin_lock_irqsave(&instance->stream_lock, spinlock_flags);
+		megasas_stream_detect(instance, cmd, &io_info);
+		spin_unlock_irqrestore(&instance->stream_lock, spinlock_flags);
+		/* In ventura if stream detected for a read and it is read ahead
+		 *  capable make this IO as LDIO
+		 */
+		if (is_stream_detected(&io_request->RaidContext.raid_context_g35) &&
+		    io_info.isRead && io_info.ra_capable)
+			fp_possible = false;
+
+		/* FP for Optimal raid level 1.
+		 * All large RAID-1 writes (> 32 KiB, both WT and WB modes)
+		 * are built by the driver as LD I/Os.
+		 * All small RAID-1 WT writes (<= 32 KiB) are built as FP I/Os
+		 * (there is never a reason to process these as buffered writes)
+		 * All small RAID-1 WB writes (<= 32 KiB) are built as FP I/Os
+		 * with the SLD bit asserted.
+		 */
+		if (io_info.r1_alt_dev_handle != MR_DEVHANDLE_INVALID) {
+			mrdev_priv = scp->device->hostdata;
+
+			if (atomic_inc_return(&instance->fw_outstanding) >
+				(instance->host->can_queue)) {
+				fp_possible = false;
+				atomic_dec(&instance->fw_outstanding);
+			} else if ((scsi_buff_len > MR_LARGE_IO_MIN_SIZE) ||
+				   atomic_dec_if_positive(&mrdev_priv->r1_ldio_hint)) {
+				fp_possible = false;
+				atomic_dec(&instance->fw_outstanding);
+				if (scsi_buff_len > MR_LARGE_IO_MIN_SIZE)
+					atomic_set(&mrdev_priv->r1_ldio_hint,
+						   instance->r1_ldio_hint_default);
+			}
+		}
+
+		/* If raid is NULL, set CPU affinity to default CPU0 */
+		if (raid)
+			megasas_set_raidflag_cpu_affinity(praid_context,
+				raid, fp_possible, io_info.isRead,
+				scsi_buff_len);
+		else
+			praid_context->raid_context_g35.routing_flags |=
+				(MR_RAID_CTX_CPUSEL_0 << MR_RAID_CTX_ROUTINGFLAGS_CPUSEL_SHIFT);
+	}
+
 	if (fp_possible) {
 		megasas_set_pd_lba(io_request, scp->cmd_len, &io_info, scp,
 				   local_map_ptr, start_lba_lo);
@@ -1811,29 +2365,52 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 			(MPI2_REQ_DESCRIPT_FLAGS_FP_IO
 			 << MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
 		if (fusion->adapter_type == INVADER_SERIES) {
-			if (io_request->RaidContext.regLockFlags ==
+			if (io_request->RaidContext.raid_context.reg_lock_flags ==
 			    REGION_TYPE_UNUSED)
 				cmd->request_desc->SCSIIO.RequestFlags =
 					(MEGASAS_REQ_DESCRIPT_FLAGS_NO_LOCK <<
 					MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
-			io_request->RaidContext.Type = MPI2_TYPE_CUDA;
-			io_request->RaidContext.nseg = 0x1;
+			io_request->RaidContext.raid_context.type
+				= MPI2_TYPE_CUDA;
+			io_request->RaidContext.raid_context.nseg = 0x1;
 			io_request->IoFlags |= cpu_to_le16(MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH);
-			io_request->RaidContext.regLockFlags |=
+			io_request->RaidContext.raid_context.reg_lock_flags |=
 			  (MR_RL_FLAGS_GRANT_DESTINATION_CUDA |
 			   MR_RL_FLAGS_SEQ_NUM_ENABLE);
+		} else if (instance->is_ventura) {
+			io_request->RaidContext.raid_context_g35.nseg_type |=
+						(1 << RAID_CONTEXT_NSEG_SHIFT);
+			io_request->RaidContext.raid_context_g35.nseg_type |=
+						(MPI2_TYPE_CUDA << RAID_CONTEXT_TYPE_SHIFT);
+			io_request->RaidContext.raid_context_g35.routing_flags |=
+						(1 << MR_RAID_CTX_ROUTINGFLAGS_SQN_SHIFT);
+			io_request->IoFlags |=
+				cpu_to_le16(MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH);
 		}
-		if ((fusion->load_balance_info[device_id].loadBalanceFlag) &&
-		    (io_info.isRead)) {
+		if (fusion->load_balance_info &&
+			(fusion->load_balance_info[device_id].loadBalanceFlag) &&
+			(io_info.isRead)) {
 			io_info.devHandle =
 				get_updated_dev_handle(instance,
 					&fusion->load_balance_info[device_id],
-					&io_info);
+					&io_info, local_map_ptr);
 			scp->SCp.Status |= MEGASAS_LOAD_BALANCE_FLAG;
 			cmd->pd_r1_lb = io_info.pd_after_lb;
+			if (instance->is_ventura)
+				io_request->RaidContext.raid_context_g35.span_arm
+					= io_info.span_arm;
+			else
+				io_request->RaidContext.raid_context.span_arm
+					= io_info.span_arm;
+
 		} else
 			scp->SCp.Status &= ~MEGASAS_LOAD_BALANCE_FLAG;
 
+		if (instance->is_ventura)
+			cmd->r1_alt_dev_handle = io_info.r1_alt_dev_handle;
+		else
+			cmd->r1_alt_dev_handle = MR_DEVHANDLE_INVALID;
+
 		if ((raidLUN[0] == 1) &&
 			(local_map_ptr->raidMap.devHndlInfo[io_info.pd_after_lb].validHandles > 1)) {
 			instance->dev_handle = !(instance->dev_handle);
@@ -1843,28 +2420,39 @@ megasas_build_ldio_fusion(struct megasas_instance *instance,
 
 		cmd->request_desc->SCSIIO.DevHandle = io_info.devHandle;
 		io_request->DevHandle = io_info.devHandle;
+		cmd->pd_interface = io_info.pd_interface;
 		/* populate the LUN field */
 		memcpy(io_request->LUN, raidLUN, 8);
 	} else {
-		io_request->RaidContext.timeoutValue =
+		io_request->RaidContext.raid_context.timeout_value =
 			cpu_to_le16(local_map_ptr->raidMap.fpPdIoTimeoutSec);
 		cmd->request_desc->SCSIIO.RequestFlags =
 			(MEGASAS_REQ_DESCRIPT_FLAGS_LD_IO
 			 << MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
 		if (fusion->adapter_type == INVADER_SERIES) {
 			if (io_info.do_fp_rlbypass ||
-				(io_request->RaidContext.regLockFlags == REGION_TYPE_UNUSED))
+			(io_request->RaidContext.raid_context.reg_lock_flags
+					== REGION_TYPE_UNUSED))
 				cmd->request_desc->SCSIIO.RequestFlags =
 					(MEGASAS_REQ_DESCRIPT_FLAGS_NO_LOCK <<
 					MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
-			io_request->RaidContext.Type = MPI2_TYPE_CUDA;
-			io_request->RaidContext.regLockFlags |=
+			io_request->RaidContext.raid_context.type
+				= MPI2_TYPE_CUDA;
+			io_request->RaidContext.raid_context.reg_lock_flags |=
 				(MR_RL_FLAGS_GRANT_DESTINATION_CPU0 |
 				 MR_RL_FLAGS_SEQ_NUM_ENABLE);
-			io_request->RaidContext.nseg = 0x1;
+			io_request->RaidContext.raid_context.nseg = 0x1;
+		} else if (instance->is_ventura) {
+			io_request->RaidContext.raid_context_g35.routing_flags |=
+					(1 << MR_RAID_CTX_ROUTINGFLAGS_SQN_SHIFT);
+			io_request->RaidContext.raid_context_g35.nseg_type |=
+					(1 << RAID_CONTEXT_NSEG_SHIFT);
+			io_request->RaidContext.raid_context_g35.nseg_type |=
+					(MPI2_TYPE_CUDA << RAID_CONTEXT_TYPE_SHIFT);
 		}
 		io_request->Function = MEGASAS_MPI2_FUNCTION_LD_IO_REQUEST;
 		io_request->DevHandle = cpu_to_le16(device_id);
+
 	} /* Not FP */
 }
 
@@ -1881,27 +2469,26 @@ static void megasas_build_ld_nonrw_fusion(struct megasas_instance *instance,
 {
 	u32 device_id;
 	struct MPI2_RAID_SCSI_IO_REQUEST *io_request;
-	u16 pd_index = 0;
+	u16 ld;
 	struct MR_DRV_RAID_MAP_ALL *local_map_ptr;
 	struct fusion_context *fusion = instance->ctrl_context;
 	u8                          span, physArm;
 	__le16                      devHandle;
-	u32                         ld, arRef, pd;
+	u32                         arRef, pd;
 	struct MR_LD_RAID                  *raid;
 	struct RAID_CONTEXT                *pRAID_Context;
 	u8 fp_possible = 1;
 
 	io_request = cmd->io_request;
 	device_id = MEGASAS_DEV_INDEX(scmd);
-	pd_index = MEGASAS_PD_INDEX(scmd);
 	local_map_ptr = fusion->ld_drv_map[(instance->map_id & 1)];
 	io_request->DataLength = cpu_to_le32(scsi_bufflen(scmd));
 	/* get RAID_Context pointer */
-	pRAID_Context = &io_request->RaidContext;
+	pRAID_Context = &io_request->RaidContext.raid_context;
 	/* Check with FW team */
-	pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
-	pRAID_Context->regLockRowLBA    = 0;
-	pRAID_Context->regLockLength    = 0;
+	pRAID_Context->virtual_disk_tgt_id = cpu_to_le16(device_id);
+	pRAID_Context->reg_lock_row_lba    = 0;
+	pRAID_Context->reg_lock_length    = 0;
 
 	if (fusion->fast_path_io && (
 		device_id < instance->fw_supported_vd_count)) {
@@ -1909,10 +2496,11 @@ static void megasas_build_ld_nonrw_fusion(struct megasas_instance *instance,
 		ld = MR_TargetIdToLdGet(device_id, local_map_ptr);
 		if (ld >= instance->fw_supported_vd_count)
 			fp_possible = 0;
-
-		raid = MR_LdRaidGet(ld, local_map_ptr);
-		if (!(raid->capability.fpNonRWCapable))
-			fp_possible = 0;
+		else {
+			raid = MR_LdRaidGet(ld, local_map_ptr);
+			if (!(raid->capability.fpNonRWCapable))
+				fp_possible = 0;
+		}
 	} else
 		fp_possible = 0;
 
@@ -1920,7 +2508,7 @@ static void megasas_build_ld_nonrw_fusion(struct megasas_instance *instance,
 		io_request->Function  = MEGASAS_MPI2_FUNCTION_LD_IO_REQUEST;
 		io_request->DevHandle = cpu_to_le16(device_id);
 		io_request->LUN[1] = scmd->device->lun;
-		pRAID_Context->timeoutValue =
+		pRAID_Context->timeout_value =
 			cpu_to_le16 (scmd->request->timeout / HZ);
 		cmd->request_desc->SCSIIO.RequestFlags =
 			(MPI2_REQ_DESCRIPT_FLAGS_SCSI_IO <<
@@ -1928,9 +2516,11 @@ static void megasas_build_ld_nonrw_fusion(struct megasas_instance *instance,
 	} else {
 
 		/* set RAID context values */
-		pRAID_Context->configSeqNum = raid->seqNum;
-		pRAID_Context->regLockFlags = REGION_TYPE_SHARED_READ;
-		pRAID_Context->timeoutValue = cpu_to_le16(raid->fpIoTimeoutForLd);
+		pRAID_Context->config_seq_num = raid->seqNum;
+		if (!instance->is_ventura)
+			pRAID_Context->reg_lock_flags = REGION_TYPE_SHARED_READ;
+		pRAID_Context->timeout_value =
+			cpu_to_le16(raid->fpIoTimeoutForLd);
 
 		/* get the DevHandle for the PD (since this is
 		   fpNonRWCapable, this is a single disk RAID0) */
@@ -1965,7 +2555,8 @@ static void megasas_build_ld_nonrw_fusion(struct megasas_instance *instance,
  */
 static void
 megasas_build_syspd_fusion(struct megasas_instance *instance,
-	struct scsi_cmnd *scmd, struct megasas_cmd_fusion *cmd, u8 fp_possible)
+	struct scsi_cmnd *scmd, struct megasas_cmd_fusion *cmd,
+	bool fp_possible)
 {
 	u32 device_id;
 	struct MPI2_RAID_SCSI_IO_REQUEST *io_request;
@@ -1975,22 +2566,25 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 	struct MR_DRV_RAID_MAP_ALL *local_map_ptr;
 	struct RAID_CONTEXT	*pRAID_Context;
 	struct MR_PD_CFG_SEQ_NUM_SYNC *pd_sync;
+	struct MR_PRIV_DEVICE *mr_device_priv_data;
 	struct fusion_context *fusion = instance->ctrl_context;
 	pd_sync = (void *)fusion->pd_seq_sync[(instance->pd_seq_map_id - 1) & 1];
 
 	device_id = MEGASAS_DEV_INDEX(scmd);
 	pd_index = MEGASAS_PD_INDEX(scmd);
 	os_timeout_value = scmd->request->timeout / HZ;
+	mr_device_priv_data = scmd->device->hostdata;
+	cmd->pd_interface = mr_device_priv_data->interface_type;
 
 	io_request = cmd->io_request;
 	/* get RAID_Context pointer */
-	pRAID_Context = &io_request->RaidContext;
-	pRAID_Context->regLockFlags = 0;
-	pRAID_Context->regLockRowLBA = 0;
-	pRAID_Context->regLockLength = 0;
+	pRAID_Context = &io_request->RaidContext.raid_context;
+	pRAID_Context->reg_lock_flags = 0;
+	pRAID_Context->reg_lock_row_lba = 0;
+	pRAID_Context->reg_lock_length = 0;
 	io_request->DataLength = cpu_to_le32(scsi_bufflen(scmd));
 	io_request->LUN[1] = scmd->device->lun;
-	pRAID_Context->RAIDFlags = MR_RAID_FLAGS_IO_SUB_TYPE_SYSTEM_PD
+	pRAID_Context->raid_flags = MR_RAID_FLAGS_IO_SUB_TYPE_SYSTEM_PD
 		<< MR_RAID_CTX_RAID_FLAGS_IO_SUB_TYPE_SHIFT;
 
 	/* If FW supports PD sequence number */
@@ -1999,24 +2593,38 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 		/* TgtId must be incremented by 255 as jbod seq number is index
 		 * below raid map
 		 */
-		pRAID_Context->VirtualDiskTgtId =
-			cpu_to_le16(device_id + (MAX_PHYSICAL_DEVICES - 1));
-		pRAID_Context->configSeqNum = pd_sync->seq[pd_index].seqNum;
+		 /* More than 256 PD/JBOD support for Ventura */
+		if (instance->support_morethan256jbod)
+			pRAID_Context->virtual_disk_tgt_id =
+				pd_sync->seq[pd_index].pd_target_id;
+		else
+			pRAID_Context->virtual_disk_tgt_id =
+				cpu_to_le16(device_id + (MAX_PHYSICAL_DEVICES - 1));
+		pRAID_Context->config_seq_num = pd_sync->seq[pd_index].seqNum;
 		io_request->DevHandle = pd_sync->seq[pd_index].devHandle;
-		pRAID_Context->regLockFlags |=
-			(MR_RL_FLAGS_SEQ_NUM_ENABLE|MR_RL_FLAGS_GRANT_DESTINATION_CUDA);
-		pRAID_Context->Type = MPI2_TYPE_CUDA;
-		pRAID_Context->nseg = 0x1;
+		if (instance->is_ventura) {
+			io_request->RaidContext.raid_context_g35.routing_flags |=
+				(1 << MR_RAID_CTX_ROUTINGFLAGS_SQN_SHIFT);
+			io_request->RaidContext.raid_context_g35.nseg_type |=
+							(1 << RAID_CONTEXT_NSEG_SHIFT);
+			io_request->RaidContext.raid_context_g35.nseg_type |=
+							(MPI2_TYPE_CUDA << RAID_CONTEXT_TYPE_SHIFT);
+		} else {
+			pRAID_Context->type = MPI2_TYPE_CUDA;
+			pRAID_Context->nseg = 0x1;
+			pRAID_Context->reg_lock_flags |=
+				(MR_RL_FLAGS_SEQ_NUM_ENABLE|MR_RL_FLAGS_GRANT_DESTINATION_CUDA);
+		}
 	} else if (fusion->fast_path_io) {
-		pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
-		pRAID_Context->configSeqNum = 0;
+		pRAID_Context->virtual_disk_tgt_id = cpu_to_le16(device_id);
+		pRAID_Context->config_seq_num = 0;
 		local_map_ptr = fusion->ld_drv_map[(instance->map_id & 1)];
 		io_request->DevHandle =
 			local_map_ptr->raidMap.devHndlInfo[device_id].curDevHdl;
 	} else {
 		/* Want to send all IO via FW path */
-		pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
-		pRAID_Context->configSeqNum = 0;
+		pRAID_Context->virtual_disk_tgt_id = cpu_to_le16(device_id);
+		pRAID_Context->config_seq_num = 0;
 		io_request->DevHandle = cpu_to_le16(0xFFFF);
 	}
 
@@ -2032,17 +2640,17 @@ megasas_build_syspd_fusion(struct megasas_instance *instance,
 		cmd->request_desc->SCSIIO.RequestFlags =
 			(MPI2_REQ_DESCRIPT_FLAGS_SCSI_IO <<
 				MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
-		pRAID_Context->timeoutValue = cpu_to_le16(os_timeout_value);
-		pRAID_Context->VirtualDiskTgtId = cpu_to_le16(device_id);
+		pRAID_Context->timeout_value = cpu_to_le16(os_timeout_value);
+		pRAID_Context->virtual_disk_tgt_id = cpu_to_le16(device_id);
 	} else {
 		/* system pd Fast Path */
 		io_request->Function = MPI2_FUNCTION_SCSI_IO_REQUEST;
 		timeout_limit = (scmd->device->type == TYPE_DISK) ?
 				255 : 0xFFFF;
-		pRAID_Context->timeoutValue =
+		pRAID_Context->timeout_value =
 			cpu_to_le16((os_timeout_value > timeout_limit) ?
 			timeout_limit : os_timeout_value);
-		if (fusion->adapter_type == INVADER_SERIES)
+		if (fusion->adapter_type >= INVADER_SERIES)
 			io_request->IoFlags |=
 				cpu_to_le16(MPI25_SAS_DEVICE0_FLAGS_ENABLED_FAST_PATH);
 
@@ -2066,9 +2674,11 @@ megasas_build_io_fusion(struct megasas_instance *instance,
 			struct scsi_cmnd *scp,
 			struct megasas_cmd_fusion *cmd)
 {
-	u16 sge_count;
+	int sge_count;
 	u8  cmd_type;
 	struct MPI2_RAID_SCSI_IO_REQUEST *io_request = cmd->io_request;
+	struct MR_PRIV_DEVICE *mr_device_priv_data;
+	mr_device_priv_data = scp->device->hostdata;
 
 	/* Zero out some fields so they don't get reused */
 	memset(io_request->LUN, 0x0, 8);
@@ -2078,9 +2688,9 @@ megasas_build_io_fusion(struct megasas_instance *instance,
 	io_request->Control = 0;
 	io_request->EEDPBlockSize = 0;
 	io_request->ChainOffset = 0;
-	io_request->RaidContext.RAIDFlags = 0;
-	io_request->RaidContext.Type = 0;
-	io_request->RaidContext.nseg = 0;
+	io_request->RaidContext.raid_context.raid_flags = 0;
+	io_request->RaidContext.raid_context.type = 0;
+	io_request->RaidContext.raid_context.nseg = 0;
 
 	memcpy(io_request->CDB.CDB32, scp->cmnd, scp->cmd_len);
 	/*
@@ -2097,12 +2707,14 @@ megasas_build_io_fusion(struct megasas_instance *instance,
 		megasas_build_ld_nonrw_fusion(instance, scp, cmd);
 		break;
 	case READ_WRITE_SYSPDIO:
+		megasas_build_syspd_fusion(instance, scp, cmd, true);
+		break;
 	case NON_READ_WRITE_SYSPDIO:
-		if (instance->secure_jbod_support &&
-			(cmd_type == NON_READ_WRITE_SYSPDIO))
-			megasas_build_syspd_fusion(instance, scp, cmd, 0);
+		if (instance->secure_jbod_support ||
+		    mr_device_priv_data->is_tm_capable)
+			megasas_build_syspd_fusion(instance, scp, cmd, false);
 		else
-			megasas_build_syspd_fusion(instance, scp, cmd, 1);
+			megasas_build_syspd_fusion(instance, scp, cmd, true);
 		break;
 	default:
 		break;
@@ -2112,23 +2724,27 @@ megasas_build_io_fusion(struct megasas_instance *instance,
 	 * Construct SGL
 	 */
 
-	sge_count =
-		megasas_make_sgl_fusion(instance, scp,
-					(struct MPI25_IEEE_SGE_CHAIN64 *)
-					&io_request->SGL, cmd);
+	sge_count = megasas_make_sgl(instance, scp, cmd);
 
-	if (sge_count > instance->max_num_sge) {
-		dev_err(&instance->pdev->dev, "Error. sge_count (0x%x) exceeds "
-		       "max (0x%x) allowed\n", sge_count,
-		       instance->max_num_sge);
+	if (sge_count > instance->max_num_sge || (sge_count < 0)) {
+		dev_err(&instance->pdev->dev,
+			"%s %d sge_count (%d) is out of range. Range is:  0-%d\n",
+			__func__, __LINE__, sge_count, instance->max_num_sge);
 		return 1;
 	}
 
-	/* numSGE store lower 8 bit of sge_count.
-	 * numSGEExt store higher 8 bit of sge_count
-	 */
-	io_request->RaidContext.numSGE = sge_count;
-	io_request->RaidContext.numSGEExt = (u8)(sge_count >> 8);
+	if (instance->is_ventura) {
+		set_num_sge(&io_request->RaidContext.raid_context_g35, sge_count);
+		cpu_to_le16s(&io_request->RaidContext.raid_context_g35.routing_flags);
+		cpu_to_le16s(&io_request->RaidContext.raid_context_g35.nseg_type);
+	} else {
+		/* numSGE store lower 8 bit of sge_count.
+		 * numSGEExt store higher 8 bit of sge_count
+		 */
+		io_request->RaidContext.raid_context.num_sge = sge_count;
+		io_request->RaidContext.raid_context.num_sge_ext =
+			(u8)(sge_count >> 8);
+	}
 
 	io_request->SGLFlags = cpu_to_le16(MPI2_SGE_FLAGS_64_BIT_ADDRESSING);
 
@@ -2149,25 +2765,61 @@ megasas_build_io_fusion(struct megasas_instance *instance,
 	return 0;
 }
 
-union MEGASAS_REQUEST_DESCRIPTOR_UNION *
+static union MEGASAS_REQUEST_DESCRIPTOR_UNION *
 megasas_get_request_descriptor(struct megasas_instance *instance, u16 index)
 {
 	u8 *p;
 	struct fusion_context *fusion;
 
-	if (index >= instance->max_fw_cmds) {
-		dev_err(&instance->pdev->dev, "Invalid SMID (0x%x)request for "
-		       "descriptor for scsi%d\n", index,
-			instance->host->host_no);
-		return NULL;
-	}
 	fusion = instance->ctrl_context;
-	p = fusion->req_frames_desc
-		+sizeof(union MEGASAS_REQUEST_DESCRIPTOR_UNION) *index;
+	p = fusion->req_frames_desc +
+		sizeof(union MEGASAS_REQUEST_DESCRIPTOR_UNION) * index;
 
 	return (union MEGASAS_REQUEST_DESCRIPTOR_UNION *)p;
 }
 
+
+/* megasas_prepate_secondRaid1_IO
+ *  It prepares the raid 1 second IO
+ */
+void megasas_prepare_secondRaid1_IO(struct megasas_instance *instance,
+			    struct megasas_cmd_fusion *cmd,
+			    struct megasas_cmd_fusion *r1_cmd)
+{
+	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc, *req_desc2 = NULL;
+	struct fusion_context *fusion;
+	fusion = instance->ctrl_context;
+	req_desc = cmd->request_desc;
+	/* copy the io request frame as well as 8 SGEs data for r1 command*/
+	memcpy(r1_cmd->io_request, cmd->io_request,
+	       (sizeof(struct MPI2_RAID_SCSI_IO_REQUEST)));
+	memcpy(&r1_cmd->io_request->SGL, &cmd->io_request->SGL,
+	       (fusion->max_sge_in_main_msg * sizeof(union MPI2_SGE_IO_UNION)));
+	/*sense buffer is different for r1 command*/
+	r1_cmd->io_request->SenseBufferLowAddress =
+			cpu_to_le32(r1_cmd->sense_phys_addr);
+	r1_cmd->scmd = cmd->scmd;
+	req_desc2 = megasas_get_request_descriptor(instance,
+						   (r1_cmd->index - 1));
+	req_desc2->Words = 0;
+	r1_cmd->request_desc = req_desc2;
+	req_desc2->SCSIIO.SMID = cpu_to_le16(r1_cmd->index);
+	req_desc2->SCSIIO.RequestFlags = req_desc->SCSIIO.RequestFlags;
+	r1_cmd->request_desc->SCSIIO.DevHandle = cmd->r1_alt_dev_handle;
+	r1_cmd->io_request->DevHandle = cmd->r1_alt_dev_handle;
+	r1_cmd->r1_alt_dev_handle = cmd->io_request->DevHandle;
+	cmd->io_request->RaidContext.raid_context_g35.smid.peer_smid =
+			cpu_to_le16(r1_cmd->index);
+	r1_cmd->io_request->RaidContext.raid_context_g35.smid.peer_smid =
+			cpu_to_le16(cmd->index);
+	/*MSIxIndex of both commands request descriptors should be same*/
+	r1_cmd->request_desc->SCSIIO.MSIxIndex =
+			cmd->request_desc->SCSIIO.MSIxIndex;
+	/*span arm is different for r1 cmd*/
+	r1_cmd->io_request->RaidContext.raid_context_g35.span_arm =
+			cmd->io_request->RaidContext.raid_context_g35.span_arm + 1;
+}
+
 /**
  * megasas_build_and_issue_cmd_fusion -Main routine for building and
  *                                     issuing non IOCTL cmd
@@ -2178,7 +2830,7 @@ static u32
 megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 				   struct scsi_cmnd *scmd)
 {
-	struct megasas_cmd_fusion *cmd;
+	struct megasas_cmd_fusion *cmd, *r1_cmd = NULL;
 	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc;
 	u32 index;
 	struct fusion_context *fusion;
@@ -2193,13 +2845,22 @@ megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 		return SCSI_MLQUEUE_DEVICE_BUSY;
 	}
 
+	if (atomic_inc_return(&instance->fw_outstanding) >
+			instance->host->can_queue) {
+		atomic_dec(&instance->fw_outstanding);
+		return SCSI_MLQUEUE_HOST_BUSY;
+	}
+
 	cmd = megasas_get_cmd_fusion(instance, scmd->request->tag);
 
+	if (!cmd) {
+		atomic_dec(&instance->fw_outstanding);
+		return SCSI_MLQUEUE_HOST_BUSY;
+	}
+
 	index = cmd->index;
 
 	req_desc = megasas_get_request_descriptor(instance, index-1);
-	if (!req_desc)
-		return SCSI_MLQUEUE_HOST_BUSY;
 
 	req_desc->Words = 0;
 	cmd->request_desc = req_desc;
@@ -2208,6 +2869,7 @@ megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 		megasas_return_cmd_fusion(instance, cmd);
 		dev_err(&instance->pdev->dev, "Error building command\n");
 		cmd->request_desc = NULL;
+		atomic_dec(&instance->fw_outstanding);
 		return SCSI_MLQUEUE_HOST_BUSY;
 	}
 
@@ -2218,18 +2880,92 @@ megasas_build_and_issue_cmd_fusion(struct megasas_instance *instance,
 	    cmd->io_request->ChainOffset != 0xF)
 		dev_err(&instance->pdev->dev, "The chain offset value is not "
 		       "correct : %x\n", cmd->io_request->ChainOffset);
+	/*
+	 *	if it is raid 1/10 fp write capable.
+	 *	try to get second command from pool and construct it.
+	 *	From FW, it has confirmed that lba values of two PDs
+	 *	corresponds to single R1/10 LD are always same
+	 *
+	 */
+	/*	driver side count always should be less than max_fw_cmds
+	 *	to get new command
+	 */
+	if (cmd->r1_alt_dev_handle != MR_DEVHANDLE_INVALID) {
+		r1_cmd = megasas_get_cmd_fusion(instance,
+				(scmd->request->tag + instance->max_fw_cmds));
+		megasas_prepare_secondRaid1_IO(instance, cmd, r1_cmd);
+	}
+
 
 	/*
 	 * Issue the command to the FW
 	 */
-	atomic_inc(&instance->fw_outstanding);
 
 	megasas_fire_cmd_fusion(instance, req_desc);
 
+	if (r1_cmd)
+		megasas_fire_cmd_fusion(instance, r1_cmd->request_desc);
+
+
 	return 0;
 }
 
 /**
+ * megasas_complete_r1_command -
+ * completes R1 FP write commands which has valid peer smid
+ * @instance:			Adapter soft state
+ * @cmd_fusion:			MPT command frame
+ *
+ */
+static inline void
+megasas_complete_r1_command(struct megasas_instance *instance,
+			    struct megasas_cmd_fusion *cmd)
+{
+	u8 *sense, status, ex_status;
+	u32 data_length;
+	u16 peer_smid;
+	struct fusion_context *fusion;
+	struct megasas_cmd_fusion *r1_cmd = NULL;
+	struct scsi_cmnd *scmd_local = NULL;
+	struct RAID_CONTEXT_G35 *rctx_g35;
+
+	rctx_g35 = &cmd->io_request->RaidContext.raid_context_g35;
+	fusion = instance->ctrl_context;
+	peer_smid = le16_to_cpu(rctx_g35->smid.peer_smid);
+
+	r1_cmd = fusion->cmd_list[peer_smid - 1];
+	scmd_local = cmd->scmd;
+	status = rctx_g35->status;
+	ex_status = rctx_g35->ex_status;
+	data_length = cmd->io_request->DataLength;
+	sense = cmd->sense;
+
+	cmd->cmd_completed = true;
+
+	/* Check if peer command is completed or not*/
+	if (r1_cmd->cmd_completed) {
+		rctx_g35 = &r1_cmd->io_request->RaidContext.raid_context_g35;
+		if (rctx_g35->status != MFI_STAT_OK) {
+			status = rctx_g35->status;
+			ex_status = rctx_g35->ex_status;
+			data_length = r1_cmd->io_request->DataLength;
+			sense = r1_cmd->sense;
+		}
+
+		megasas_return_cmd_fusion(instance, r1_cmd);
+		map_cmd_status(fusion, scmd_local, status, ex_status,
+			       le32_to_cpu(data_length), sense);
+		if (instance->ldio_threshold &&
+		    megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
+			atomic_dec(&instance->ldio_outstanding);
+		scmd_local->SCp.ptr = NULL;
+		megasas_return_cmd_fusion(instance, cmd);
+		scsi_dma_unmap(scmd_local);
+		scmd_local->scsi_done(scmd_local);
+	}
+}
+
+/**
  * complete_cmd_fusion -	Completes command
  * @instance:			Adapter soft state
  * Completes all commands that is in reply descriptor queue
@@ -2244,8 +2980,8 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 	struct megasas_cmd *cmd_mfi;
 	struct megasas_cmd_fusion *cmd_fusion;
 	u16 smid, num_completed;
-	u8 reply_descript_type;
-	u32 status, extStatus, device_id;
+	u8 reply_descript_type, *sense, status, extStatus;
+	u32 device_id, data_length;
 	union desc_value d_val;
 	struct LD_LOAD_BALANCE_INFO *lbinfo;
 	int threshold_reply_count = 0;
@@ -2275,20 +3011,17 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 
 	while (d_val.u.low != cpu_to_le32(UINT_MAX) &&
 	       d_val.u.high != cpu_to_le32(UINT_MAX)) {
-		smid = le16_to_cpu(reply_desc->SMID);
 
+		smid = le16_to_cpu(reply_desc->SMID);
 		cmd_fusion = fusion->cmd_list[smid - 1];
-
-		scsi_io_req =
-			(struct MPI2_RAID_SCSI_IO_REQUEST *)
-		  cmd_fusion->io_request;
-
-		if (cmd_fusion->scmd)
-			cmd_fusion->scmd->SCp.ptr = NULL;
+		scsi_io_req = (struct MPI2_RAID_SCSI_IO_REQUEST *)
+						cmd_fusion->io_request;
 
 		scmd_local = cmd_fusion->scmd;
-		status = scsi_io_req->RaidContext.status;
-		extStatus = scsi_io_req->RaidContext.exStatus;
+		status = scsi_io_req->RaidContext.raid_context.status;
+		extStatus = scsi_io_req->RaidContext.raid_context.ex_status;
+		sense = cmd_fusion->sense;
+		data_length = scsi_io_req->DataLength;
 
 		switch (scsi_io_req->Function) {
 		case MPI2_FUNCTION_SCSI_TASK_MGMT:
@@ -2303,37 +3036,33 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 			break;
 		case MPI2_FUNCTION_SCSI_IO_REQUEST:  /*Fast Path IO.*/
 			/* Update load balancing info */
-			device_id = MEGASAS_DEV_INDEX(scmd_local);
-			lbinfo = &fusion->load_balance_info[device_id];
-			if (cmd_fusion->scmd->SCp.Status &
-			    MEGASAS_LOAD_BALANCE_FLAG) {
+			if (fusion->load_balance_info &&
+			    (cmd_fusion->scmd->SCp.Status &
+			    MEGASAS_LOAD_BALANCE_FLAG)) {
+				device_id = MEGASAS_DEV_INDEX(scmd_local);
+				lbinfo = &fusion->load_balance_info[device_id];
 				atomic_dec(&lbinfo->scsi_pending_cmds[cmd_fusion->pd_r1_lb]);
-				cmd_fusion->scmd->SCp.Status &=
-					~MEGASAS_LOAD_BALANCE_FLAG;
+				cmd_fusion->scmd->SCp.Status &= ~MEGASAS_LOAD_BALANCE_FLAG;
 			}
-			if (reply_descript_type ==
-			    MPI2_RPY_DESCRIPT_FLAGS_SCSI_IO_SUCCESS) {
-				if (megasas_dbg_lvl == 5)
-					dev_err(&instance->pdev->dev, "\nFAST Path "
-					       "IO Success\n");
-			}
-			/* Fall thru and complete IO */
+			//Fall thru and complete IO
 		case MEGASAS_MPI2_FUNCTION_LD_IO_REQUEST: /* LD-IO Path */
-			/* Map the FW Cmd Status */
-			map_cmd_status(cmd_fusion, status, extStatus);
-			scsi_io_req->RaidContext.status = 0;
-			scsi_io_req->RaidContext.exStatus = 0;
-			if (megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
-				atomic_dec(&instance->ldio_outstanding);
-			megasas_return_cmd_fusion(instance, cmd_fusion);
-			scsi_dma_unmap(scmd_local);
-			scmd_local->scsi_done(scmd_local);
 			atomic_dec(&instance->fw_outstanding);
-
+			if (cmd_fusion->r1_alt_dev_handle == MR_DEVHANDLE_INVALID) {
+				map_cmd_status(fusion, scmd_local, status,
+					       extStatus, le32_to_cpu(data_length),
+					       sense);
+				if (instance->ldio_threshold &&
+				    (megasas_cmd_type(scmd_local) == READ_WRITE_LDIO))
+					atomic_dec(&instance->ldio_outstanding);
+				scmd_local->SCp.ptr = NULL;
+				megasas_return_cmd_fusion(instance, cmd_fusion);
+				scsi_dma_unmap(scmd_local);
+				scmd_local->scsi_done(scmd_local);
+			} else	/* Optimal VD - R1 FP command completion. */
+				megasas_complete_r1_command(instance, cmd_fusion);
 			break;
 		case MEGASAS_MPI2_FUNCTION_PASSTHRU_IO_REQUEST: /*MFI command */
 			cmd_mfi = instance->cmd_list[cmd_fusion->sync_cmd_idx];
-
 			/* Poll mode. Dummy free.
 			 * In case of Interrupt mode, caller has reverse check.
 			 */
@@ -2376,7 +3105,7 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 		 * pending to be completed
 		 */
 		if (threshold_reply_count >= THRESHOLD_REPLY_COUNT) {
-			if (fusion->adapter_type == INVADER_SERIES)
+			if (instance->msix_combined)
 				writel(((MSIxIndex & 0x7) << 24) |
 					fusion->last_reply_idx[MSIxIndex],
 					instance->reply_post_host_index_addr[MSIxIndex/8]);
@@ -2392,7 +3121,7 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 		return IRQ_NONE;
 
 	wmb();
-	if (fusion->adapter_type == INVADER_SERIES)
+	if (instance->msix_combined)
 		writel(((MSIxIndex & 0x7) << 24) |
 			fusion->last_reply_idx[MSIxIndex],
 			instance->reply_post_host_index_addr[MSIxIndex/8]);
@@ -2405,6 +3134,22 @@ complete_cmd_fusion(struct megasas_instance *instance, u32 MSIxIndex)
 }
 
 /**
+ * megasas_sync_irqs -	Synchronizes all IRQs owned by adapter
+ * @instance:			Adapter soft state
+ */
+void megasas_sync_irqs(unsigned long instance_addr)
+{
+	u32 count, i;
+	struct megasas_instance *instance =
+		(struct megasas_instance *)instance_addr;
+
+	count = instance->msix_vectors > 0 ? instance->msix_vectors : 1;
+
+	for (i = 0; i < count; i++)
+		synchronize_irq(pci_irq_vector(instance->pdev, i));
+}
+
+/**
  * megasas_complete_cmd_dpc_fusion -	Completes command
  * @instance:			Adapter soft state
  *
@@ -2489,7 +3234,7 @@ irqreturn_t megasas_isr_fusion(int irq, void *devp)
  * mfi_cmd:			megasas_cmd pointer
  *
  */
-u8
+void
 build_mpt_mfi_pass_thru(struct megasas_instance *instance,
 			struct megasas_cmd *mfi_cmd)
 {
@@ -2518,7 +3263,7 @@ build_mpt_mfi_pass_thru(struct megasas_instance *instance,
 
 	io_req = cmd->io_request;
 
-	if (fusion->adapter_type == INVADER_SERIES) {
+	if (fusion->adapter_type >= INVADER_SERIES) {
 		struct MPI25_IEEE_SGE_CHAIN64 *sgl_ptr_end =
 			(struct MPI25_IEEE_SGE_CHAIN64 *)&io_req->SGL;
 		sgl_ptr_end += fusion->max_sge_in_main_msg - 1;
@@ -2539,8 +3284,6 @@ build_mpt_mfi_pass_thru(struct megasas_instance *instance,
 		MPI2_IEEE_SGE_FLAGS_IOCPLBNTA_ADDR;
 
 	mpi25_ieee_chain->Length = cpu_to_le32(instance->max_chain_frame_sz);
-
-	return 0;
 }
 
 /**
@@ -2552,21 +3295,14 @@ build_mpt_mfi_pass_thru(struct megasas_instance *instance,
 union MEGASAS_REQUEST_DESCRIPTOR_UNION *
 build_mpt_cmd(struct megasas_instance *instance, struct megasas_cmd *cmd)
 {
-	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc;
+	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc = NULL;
 	u16 index;
 
-	if (build_mpt_mfi_pass_thru(instance, cmd)) {
-		dev_err(&instance->pdev->dev, "Couldn't build MFI pass thru cmd\n");
-		return NULL;
-	}
-
+	build_mpt_mfi_pass_thru(instance, cmd);
 	index = cmd->context.smid;
 
 	req_desc = megasas_get_request_descriptor(instance, index - 1);
 
-	if (!req_desc)
-		return NULL;
-
 	req_desc->Words = 0;
 	req_desc->SCSIIO.RequestFlags = (MPI2_REQ_DESCRIPT_FLAGS_SCSI_IO <<
 					 MEGASAS_REQ_DESCRIPT_FLAGS_TYPE_SHIFT);
@@ -2582,21 +3318,16 @@ build_mpt_cmd(struct megasas_instance *instance, struct megasas_cmd *cmd)
  * @cmd:			mfi cmd pointer
  *
  */
-int
+void
 megasas_issue_dcmd_fusion(struct megasas_instance *instance,
 			  struct megasas_cmd *cmd)
 {
 	union MEGASAS_REQUEST_DESCRIPTOR_UNION *req_desc;
 
 	req_desc = build_mpt_cmd(instance, cmd);
-	if (!req_desc) {
-		dev_info(&instance->pdev->dev, "Failed from %s %d\n",
-					__func__, __LINE__);
-		return DCMD_NOT_FIRED;
-	}
 
 	megasas_fire_cmd_fusion(instance, req_desc);
-	return DCMD_SUCCESS;
+	return;
 }
 
 /**
@@ -2771,6 +3502,14 @@ int megasas_wait_for_outstanding_fusion(struct megasas_instance *instance,
 			       " will reset adapter scsi%d.\n",
 				instance->host->host_no);
 			megasas_complete_cmd_dpc_fusion((unsigned long)instance);
+			if (instance->requestorId && reason) {
+				dev_warn(&instance->pdev->dev, "SR-IOV Found FW in FAULT"
+				" state while polling during"
+				" I/O timeout handling for %d\n",
+				instance->host->host_no);
+				*convert = 1;
+			}
+
 			retval = 1;
 			goto out;
 		}
@@ -2790,7 +3529,7 @@ int megasas_wait_for_outstanding_fusion(struct megasas_instance *instance,
 		}
 
 		/* If SR-IOV VF mode & I/O timeout, check for HB timeout */
-		if (instance->requestorId && reason) {
+		if (instance->requestorId && (reason == SCSIIO_TIMEOUT_OCR)) {
 			if (instance->hb_host_mem->HB.fwCounter !=
 			    instance->hb_host_mem->HB.driverCounter) {
 				instance->hb_host_mem->HB.driverCounter =
@@ -3030,12 +3769,6 @@ megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
 
 	req_desc = megasas_get_request_descriptor(instance,
 			(cmd_fusion->index - 1));
-	if (!req_desc) {
-		dev_err(&instance->pdev->dev, "Failed from %s %d\n",
-			__func__, __LINE__);
-		megasas_return_cmd(instance, cmd_mfi);
-		return -ENOMEM;
-	}
 
 	cmd_fusion->request_desc = req_desc;
 	req_desc->Words = 0;
@@ -3092,7 +3825,7 @@ megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
 			break;
 		else {
 			instance->instancet->disable_intr(instance);
-			msleep(1000);
+			megasas_sync_irqs((unsigned long)instance);
 			megasas_complete_cmd_dpc_fusion
 					((unsigned long)instance);
 			instance->instancet->enable_intr(instance);
@@ -3173,13 +3906,13 @@ static u16 megasas_get_tm_devhandle(struct scsi_device *sdev)
 	instance = (struct megasas_instance *)sdev->host->hostdata;
 	fusion = instance->ctrl_context;
 
-	if (sdev->channel < MEGASAS_MAX_PD_CHANNELS) {
+	if (!MEGASAS_IS_LOGICAL(sdev)) {
 		if (instance->use_seqnum_jbod_fp) {
-				pd_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL) +
-						sdev->id;
-				pd_sync = (void *)fusion->pd_seq_sync
-						[(instance->pd_seq_map_id - 1) & 1];
-				devhandle = pd_sync->seq[pd_index].devHandle;
+			pd_index = (sdev->channel * MEGASAS_MAX_DEV_PER_CHANNEL)
+				    + sdev->id;
+			pd_sync = (void *)fusion->pd_seq_sync
+					[(instance->pd_seq_map_id - 1) & 1];
+			devhandle = pd_sync->seq[pd_index].devHandle;
 		} else
 			sdev_printk(KERN_ERR, sdev, "Firmware expose tmCapable"
 				" without JBOD MAP support from %s %d\n", __func__, __LINE__);
@@ -3212,6 +3945,9 @@ int megasas_task_abort_fusion(struct scsi_cmnd *scmd)
 	instance = (struct megasas_instance *)scmd->device->host->hostdata;
 	fusion = instance->ctrl_context;
 
+	scmd_printk(KERN_INFO, scmd, "task abort called for scmd(%p)\n", scmd);
+	scsi_print_command(scmd);
+
 	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
 		dev_err(&instance->pdev->dev, "Controller is not OPERATIONAL,"
 		"SCSI host:%d\n", instance->host->host_no);
@@ -3292,6 +4028,9 @@ int megasas_reset_target_fusion(struct scsi_cmnd *scmd)
 	instance = (struct megasas_instance *)scmd->device->host->hostdata;
 	fusion = instance->ctrl_context;
 
+	sdev_printk(KERN_INFO, scmd->device,
+		    "target reset called for scmd(%p)\n", scmd);
+
 	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
 		dev_err(&instance->pdev->dev, "Controller is not OPERATIONAL,"
 		"SCSI host:%d\n", instance->host->host_no);
@@ -3362,7 +4101,7 @@ int megasas_check_mpio_paths(struct megasas_instance *instance,
 	struct scsi_cmnd *scmd)
 {
 	struct megasas_instance *peer_instance = NULL;
-	int retval = (DID_RESET << 16);
+	int retval = (DID_REQUEUE << 16);
 
 	if (instance->peerIsPresent) {
 		peer_instance = megasas_get_peer_instance(instance);
@@ -3377,9 +4116,9 @@ int megasas_check_mpio_paths(struct megasas_instance *instance,
 /* Core fusion reset function */
 int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 {
-	int retval = SUCCESS, i, convert = 0;
+	int retval = SUCCESS, i, j, convert = 0;
 	struct megasas_instance *instance;
-	struct megasas_cmd_fusion *cmd_fusion;
+	struct megasas_cmd_fusion *cmd_fusion, *r1_cmd;
 	struct fusion_context *fusion;
 	u32 abs_state, status_reg, reset_adapter;
 	u32 io_timeout_in_crash_mode = 0;
@@ -3440,7 +4179,7 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 	set_bit(MEGASAS_FUSION_IN_RESET, &instance->reset_flags);
 	atomic_set(&instance->adprecovery, MEGASAS_ADPRESET_SM_POLLING);
 	instance->instancet->disable_intr(instance);
-	msleep(1000);
+	megasas_sync_irqs((unsigned long)instance);
 
 	/* First try waiting for commands to complete */
 	if (megasas_wait_for_outstanding_fusion(instance, reason,
@@ -3451,23 +4190,40 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 		if (convert)
 			reason = 0;
 
+		if (megasas_dbg_lvl & OCR_LOGS)
+			dev_info(&instance->pdev->dev, "\nPending SCSI commands:\n");
+
 		/* Now return commands back to the OS */
 		for (i = 0 ; i < instance->max_scsi_cmds; i++) {
 			cmd_fusion = fusion->cmd_list[i];
+			/*check for extra commands issued by driver*/
+			if (instance->is_ventura) {
+				r1_cmd = fusion->cmd_list[i + instance->max_fw_cmds];
+				megasas_return_cmd_fusion(instance, r1_cmd);
+			}
 			scmd_local = cmd_fusion->scmd;
 			if (cmd_fusion->scmd) {
+				if (megasas_dbg_lvl & OCR_LOGS) {
+					sdev_printk(KERN_INFO,
+						cmd_fusion->scmd->device, "SMID: 0x%x\n",
+						cmd_fusion->index);
+					scsi_print_command(cmd_fusion->scmd);
+				}
+
 				scmd_local->result =
 					megasas_check_mpio_paths(instance,
 							scmd_local);
-				if (megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
+				if (instance->ldio_threshold &&
+					megasas_cmd_type(scmd_local) == READ_WRITE_LDIO)
 					atomic_dec(&instance->ldio_outstanding);
 				megasas_return_cmd_fusion(instance, cmd_fusion);
 				scsi_dma_unmap(scmd_local);
 				scmd_local->scsi_done(scmd_local);
-				atomic_dec(&instance->fw_outstanding);
 			}
 		}
 
+		atomic_set(&instance->fw_outstanding, 0);
+
 		status_reg = instance->instancet->read_fw_status_reg(
 			instance->reg_set);
 		abs_state = status_reg & MFI_STATE_MASK;
@@ -3528,11 +4284,13 @@ transition_to_ready:
 					__func__, __LINE__);
 				megaraid_sas_kill_hba(instance);
 				retval = FAILED;
+				goto out;
 			}
 			/* Reset load balance info */
-			memset(fusion->load_balance_info, 0,
-			       sizeof(struct LD_LOAD_BALANCE_INFO)
-			       *MAX_LOGICAL_DRIVES_EXT);
+			if (fusion->load_balance_info)
+				memset(fusion->load_balance_info, 0,
+				       (sizeof(struct LD_LOAD_BALANCE_INFO) *
+				       MAX_LOGICAL_DRIVES_EXT));
 
 			if (!megasas_get_map_info(instance))
 				megasas_sync_map_info(instance);
@@ -3540,7 +4298,17 @@ transition_to_ready:
 			megasas_setup_jbod_map(instance);
 
 			shost_for_each_device(sdev, shost)
-				megasas_update_sdev_properties(sdev);
+				megasas_set_dynamic_target_properties(sdev);
+
+			/* reset stream detection array */
+			if (instance->is_ventura) {
+				for (j = 0; j < MAX_LOGICAL_DRIVES_EXT; ++j) {
+					memset(fusion->stream_detect_by_ld[j],
+					0, sizeof(struct LD_STREAM_DETECT));
+				 fusion->stream_detect_by_ld[j]->mru_bit_map
+						= MR_STREAM_BITMAP;
+				}
+			}
 
 			clear_bit(MEGASAS_FUSION_IN_RESET,
 				  &instance->reset_flags);
@@ -3676,6 +4444,64 @@ void megasas_fusion_ocr_wq(struct work_struct *work)
 	megasas_reset_fusion(instance->host, 0);
 }
 
+/* Allocate fusion context */
+int
+megasas_alloc_fusion_context(struct megasas_instance *instance)
+{
+	struct fusion_context *fusion;
+
+	instance->ctrl_context_pages = get_order(sizeof(struct fusion_context));
+	instance->ctrl_context = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+		instance->ctrl_context_pages);
+	if (!instance->ctrl_context) {
+		/* fall back to using vmalloc for fusion_context */
+		instance->ctrl_context = vzalloc(sizeof(struct fusion_context));
+		if (!instance->ctrl_context) {
+			dev_err(&instance->pdev->dev, "Failed from %s %d\n", __func__, __LINE__);
+			return -ENOMEM;
+		}
+	}
+
+	fusion = instance->ctrl_context;
+
+	fusion->load_balance_info_pages = get_order(MAX_LOGICAL_DRIVES_EXT *
+		sizeof(struct LD_LOAD_BALANCE_INFO));
+	fusion->load_balance_info =
+		(struct LD_LOAD_BALANCE_INFO *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+		fusion->load_balance_info_pages);
+	if (!fusion->load_balance_info) {
+		fusion->load_balance_info = vzalloc(MAX_LOGICAL_DRIVES_EXT *
+			sizeof(struct LD_LOAD_BALANCE_INFO));
+		if (!fusion->load_balance_info)
+			dev_err(&instance->pdev->dev, "Failed to allocate load_balance_info, "
+				"continuing without Load Balance support\n");
+	}
+
+	return 0;
+}
+
+void
+megasas_free_fusion_context(struct megasas_instance *instance)
+{
+	struct fusion_context *fusion = instance->ctrl_context;
+
+	if (fusion) {
+		if (fusion->load_balance_info) {
+			if (is_vmalloc_addr(fusion->load_balance_info))
+				vfree(fusion->load_balance_info);
+			else
+				free_pages((ulong)fusion->load_balance_info,
+					fusion->load_balance_info_pages);
+		}
+
+		if (is_vmalloc_addr(fusion))
+			vfree(fusion);
+		else
+			free_pages((ulong)fusion,
+				instance->ctrl_context_pages);
+	}
+}
+
 struct megasas_instance_template megasas_instance_template_fusion = {
 	.enable_intr = megasas_enable_intr_fusion,
 	.disable_intr = megasas_disable_intr_fusion,
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.h b/drivers/scsi/megaraid/megaraid_sas_fusion.h
index e3bee04c1eb1..d78d76112501 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.h
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.h
@@ -59,6 +59,8 @@
 #define	MR_RL_FLAGS_GRANT_DESTINATION_CPU1	    0x10
 #define	MR_RL_FLAGS_GRANT_DESTINATION_CUDA	    0x80
 #define MR_RL_FLAGS_SEQ_NUM_ENABLE		    0x8
+#define MR_RL_WRITE_THROUGH_MODE		    0x00
+#define MR_RL_WRITE_BACK_MODE			    0x01
 
 /* T10 PI defines */
 #define MR_PROT_INFO_TYPE_CONTROLLER                0x8
@@ -81,6 +83,11 @@
 enum MR_RAID_FLAGS_IO_SUB_TYPE {
 	MR_RAID_FLAGS_IO_SUB_TYPE_NONE = 0,
 	MR_RAID_FLAGS_IO_SUB_TYPE_SYSTEM_PD = 1,
+	MR_RAID_FLAGS_IO_SUB_TYPE_RMW_DATA     = 2,
+	MR_RAID_FLAGS_IO_SUB_TYPE_RMW_P        = 3,
+	MR_RAID_FLAGS_IO_SUB_TYPE_RMW_Q        = 4,
+	MR_RAID_FLAGS_IO_SUB_TYPE_CACHE_BYPASS = 6,
+	MR_RAID_FLAGS_IO_SUB_TYPE_LDIO_BW_LIMIT = 7
 };
 
 /*
@@ -94,11 +101,13 @@ enum MR_RAID_FLAGS_IO_SUB_TYPE {
 #define MEGASAS_FP_CMD_LEN	16
 #define MEGASAS_FUSION_IN_RESET 0
 #define THRESHOLD_REPLY_COUNT 50
+#define RAID_1_PEER_CMDS 2
 #define JBOD_MAPS_COUNT	2
 
 enum MR_FUSION_ADAPTER_TYPE {
 	THUNDERBOLT_SERIES = 0,
 	INVADER_SERIES = 1,
+	VENTURA_SERIES = 2,
 };
 
 /*
@@ -108,29 +117,133 @@ enum MR_FUSION_ADAPTER_TYPE {
 
 struct RAID_CONTEXT {
 #if   defined(__BIG_ENDIAN_BITFIELD)
-	u8	nseg:4;
-	u8	Type:4;
+	u8 nseg:4;
+	u8 type:4;
 #else
-	u8	Type:4;
-	u8	nseg:4;
+	u8 type:4;
+	u8 nseg:4;
 #endif
-	u8	resvd0;
-	__le16	timeoutValue;
-	u8      regLockFlags;
-	u8      resvd1;
-	__le16	VirtualDiskTgtId;
-	__le64	regLockRowLBA;
-	__le32	regLockLength;
-	__le16	nextLMId;
-	u8      exStatus;
-	u8      status;
-	u8      RAIDFlags;
-	u8      numSGE;
-	__le16	configSeqNum;
-	u8      spanArm;
-	u8      priority;
-	u8	numSGEExt;
-	u8      resvd2;
+	u8 resvd0;
+	__le16 timeout_value;
+	u8 reg_lock_flags;
+	u8 resvd1;
+	__le16 virtual_disk_tgt_id;
+	__le64 reg_lock_row_lba;
+	__le32 reg_lock_length;
+	__le16 next_lmid;
+	u8 ex_status;
+	u8 status;
+	u8 raid_flags;
+	u8 num_sge;
+	__le16 config_seq_num;
+	u8 span_arm;
+	u8 priority;
+	u8 num_sge_ext;
+	u8 resvd2;
+};
+
+/*
+ * Raid Context structure which describes ventura MegaRAID specific
+ * IO Paramenters ,This resides at offset 0x60 where the SGL normally
+ * starts in MPT IO Frames
+ */
+struct RAID_CONTEXT_G35 {
+	#define RAID_CONTEXT_NSEG_MASK	0x00F0
+	#define RAID_CONTEXT_NSEG_SHIFT	4
+	#define RAID_CONTEXT_TYPE_MASK	0x000F
+	#define RAID_CONTEXT_TYPE_SHIFT	0
+	u16		nseg_type;
+	u16 timeout_value; /* 0x02 -0x03 */
+	u16		routing_flags;	// 0x04 -0x05 routing flags
+	u16 virtual_disk_tgt_id;   /* 0x06 -0x07 */
+	u64 reg_lock_row_lba;      /* 0x08 - 0x0F */
+	u32 reg_lock_length;      /* 0x10 - 0x13 */
+	union {
+		u16 next_lmid; /* 0x14 - 0x15 */
+		u16	peer_smid;	/* used for the raid 1/10 fp writes */
+	} smid;
+	u8 ex_status;       /* 0x16 : OUT */
+	u8 status;          /* 0x17 status */
+	u8 raid_flags;		/* 0x18 resvd[7:6], ioSubType[5:4],
+				 * resvd[3:1], preferredCpu[0]
+				 */
+	u8 span_arm;            /* 0x1C span[7:5], arm[4:0] */
+	u16	config_seq_num;           /* 0x1A -0x1B */
+	union {
+		/*
+		 * Bit format:
+		 *	 ---------------------------------
+		 *	 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 |
+		 *	 ---------------------------------
+		 * Byte0 |    numSGE[7]- numSGE[0]	 |
+		 *	 ---------------------------------
+		 * Byte1 |SD | resvd     | numSGE 8-11   |
+		 *        --------------------------------
+		 */
+		#define NUM_SGE_MASK_LOWER	0xFF
+		#define NUM_SGE_MASK_UPPER	0x0F
+		#define NUM_SGE_SHIFT_UPPER	8
+		#define STREAM_DETECT_SHIFT	7
+		#define STREAM_DETECT_MASK	0x80
+		struct {
+#if   defined(__BIG_ENDIAN_BITFIELD) /* 0x1C - 0x1D */
+			u16 stream_detected:1;
+			u16 reserved:3;
+			u16 num_sge:12;
+#else
+			u16 num_sge:12;
+			u16 reserved:3;
+			u16 stream_detected:1;
+#endif
+		} bits;
+		u8 bytes[2];
+	} u;
+	u8 resvd2[2];          /* 0x1E-0x1F */
+};
+
+#define MR_RAID_CTX_ROUTINGFLAGS_SLD_SHIFT	1
+#define MR_RAID_CTX_ROUTINGFLAGS_C2D_SHIFT	2
+#define MR_RAID_CTX_ROUTINGFLAGS_FWD_SHIFT	3
+#define MR_RAID_CTX_ROUTINGFLAGS_SQN_SHIFT	4
+#define MR_RAID_CTX_ROUTINGFLAGS_SBS_SHIFT	5
+#define MR_RAID_CTX_ROUTINGFLAGS_RW_SHIFT	6
+#define MR_RAID_CTX_ROUTINGFLAGS_LOG_SHIFT	7
+#define MR_RAID_CTX_ROUTINGFLAGS_CPUSEL_SHIFT	8
+#define MR_RAID_CTX_ROUTINGFLAGS_CPUSEL_MASK	0x0F00
+#define MR_RAID_CTX_ROUTINGFLAGS_SETDIVERT_SHIFT	12
+#define MR_RAID_CTX_ROUTINGFLAGS_SETDIVERT_MASK	0xF000
+
+static inline void set_num_sge(struct RAID_CONTEXT_G35 *rctx_g35,
+			       u16 sge_count)
+{
+	rctx_g35->u.bytes[0] = (u8)(sge_count & NUM_SGE_MASK_LOWER);
+	rctx_g35->u.bytes[1] |= (u8)((sge_count >> NUM_SGE_SHIFT_UPPER)
+							& NUM_SGE_MASK_UPPER);
+}
+
+static inline u16 get_num_sge(struct RAID_CONTEXT_G35 *rctx_g35)
+{
+	u16 sge_count;
+
+	sge_count = (u16)(((rctx_g35->u.bytes[1] & NUM_SGE_MASK_UPPER)
+			<< NUM_SGE_SHIFT_UPPER) | (rctx_g35->u.bytes[0]));
+	return sge_count;
+}
+
+#define SET_STREAM_DETECTED(rctx_g35) \
+	(rctx_g35.u.bytes[1] |= STREAM_DETECT_MASK)
+
+#define CLEAR_STREAM_DETECTED(rctx_g35) \
+	(rctx_g35.u.bytes[1] &= ~(STREAM_DETECT_MASK))
+
+static inline bool is_stream_detected(struct RAID_CONTEXT_G35 *rctx_g35)
+{
+	return ((rctx_g35->u.bytes[1] & STREAM_DETECT_MASK));
+}
+
+union RAID_CONTEXT_UNION {
+	struct RAID_CONTEXT raid_context;
+	struct RAID_CONTEXT_G35 raid_context_g35;
 };
 
 #define RAID_CTX_SPANARM_ARM_SHIFT	(0)
@@ -139,6 +252,14 @@ struct RAID_CONTEXT {
 #define RAID_CTX_SPANARM_SPAN_SHIFT	(5)
 #define RAID_CTX_SPANARM_SPAN_MASK	(0xE0)
 
+/* number of bits per index in U32 TrackStream */
+#define BITS_PER_INDEX_STREAM		4
+#define INVALID_STREAM_NUM              16
+#define MR_STREAM_BITMAP		0x76543210
+#define STREAM_MASK			((1 << BITS_PER_INDEX_STREAM) - 1)
+#define ZERO_LAST_STREAM		0x0fffffff
+#define MAX_STREAMS_TRACKED		8
+
 /*
  * define region lock types
  */
@@ -175,6 +296,8 @@ enum REGION_TYPE {
 #define MPI2_SCSIIO_EEDPFLAGS_CHECK_APPTAG          (0x0200)
 #define MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD           (0x0100)
 #define MPI2_SCSIIO_EEDPFLAGS_INSERT_OP             (0x0004)
+/* EEDP escape mode */
+#define MPI25_SCSIIO_EEDPFLAGS_DO_NOT_DISABLE_MODE  (0x0040)
 #define MPI2_FUNCTION_SCSI_IO_REQUEST               (0x00) /* SCSI IO */
 #define MPI2_FUNCTION_SCSI_TASK_MGMT                (0x01)
 #define MPI2_REQ_DESCRIPT_FLAGS_HIGH_PRIORITY       (0x03)
@@ -407,7 +530,7 @@ struct MPI2_RAID_SCSI_IO_REQUEST {
 	u8                      LUN[8];                         /* 0x34 */
 	__le32			Control;                        /* 0x3C */
 	union MPI2_SCSI_IO_CDB_UNION  CDB;			/* 0x40 */
-	struct RAID_CONTEXT	RaidContext;                    /* 0x60 */
+	union RAID_CONTEXT_UNION RaidContext;  /* 0x60 */
 	union MPI2_SGE_IO_UNION       SGL;			/* 0x80 */
 };
 
@@ -563,7 +686,7 @@ struct MPI2_IOC_INIT_REQUEST {
 	__le16			HeaderVersion;                  /* 0x0E */
 	u32                     Reserved5;                      /* 0x10 */
 	__le16			Reserved6;                      /* 0x14 */
-	u8                      Reserved7;                      /* 0x16 */
+	u8                      HostPageSize;                   /* 0x16 */
 	u8                      HostMSIxVectors;                /* 0x17 */
 	__le16			Reserved8;                      /* 0x18 */
 	__le16			SystemRequestFrameSize;         /* 0x1A */
@@ -579,6 +702,7 @@ struct MPI2_IOC_INIT_REQUEST {
 
 /* mrpriv defines */
 #define MR_PD_INVALID 0xFFFF
+#define MR_DEVHANDLE_INVALID 0xFFFF
 #define MAX_SPAN_DEPTH 8
 #define MAX_QUAD_DEPTH	MAX_SPAN_DEPTH
 #define MAX_RAIDMAP_SPAN_DEPTH (MAX_SPAN_DEPTH)
@@ -586,16 +710,20 @@ struct MPI2_IOC_INIT_REQUEST {
 #define MAX_RAIDMAP_ROW_SIZE (MAX_ROW_SIZE)
 #define MAX_LOGICAL_DRIVES 64
 #define MAX_LOGICAL_DRIVES_EXT 256
+#define MAX_LOGICAL_DRIVES_DYN 512
 #define MAX_RAIDMAP_LOGICAL_DRIVES (MAX_LOGICAL_DRIVES)
 #define MAX_RAIDMAP_VIEWS (MAX_LOGICAL_DRIVES)
 #define MAX_ARRAYS 128
 #define MAX_RAIDMAP_ARRAYS (MAX_ARRAYS)
 #define MAX_ARRAYS_EXT	256
 #define MAX_API_ARRAYS_EXT (MAX_ARRAYS_EXT)
+#define MAX_API_ARRAYS_DYN 512
 #define MAX_PHYSICAL_DEVICES 256
 #define MAX_RAIDMAP_PHYSICAL_DEVICES (MAX_PHYSICAL_DEVICES)
+#define MAX_RAIDMAP_PHYSICAL_DEVICES_DYN 512
 #define MR_DCMD_LD_MAP_GET_INFO             0x0300e101
 #define MR_DCMD_SYSTEM_PD_MAP_GET_INFO      0x0200e102
+#define MR_DCMD_DRV_GET_TARGET_PROP         0x0200e103
 #define MR_DCMD_CTRL_SHARED_HOST_MEM_ALLOC  0x010e8485   /* SR-IOV HB alloc*/
 #define MR_DCMD_LD_VF_MAP_GET_ALL_LDS_111   0x03200200
 #define MR_DCMD_LD_VF_MAP_GET_ALL_LDS       0x03150200
@@ -603,7 +731,7 @@ struct MPI2_IOC_INIT_REQUEST {
 struct MR_DEV_HANDLE_INFO {
 	__le16	curDevHdl;
 	u8      validHandles;
-	u8      reserved;
+	u8      interfaceType;
 	__le16	devHandle[2];
 };
 
@@ -640,10 +768,56 @@ struct MR_SPAN_BLOCK_INFO {
 	struct MR_SPAN_INFO block_span_info;
 };
 
+#define MR_RAID_CTX_CPUSEL_0		0
+#define MR_RAID_CTX_CPUSEL_1		1
+#define MR_RAID_CTX_CPUSEL_2		2
+#define MR_RAID_CTX_CPUSEL_3		3
+#define MR_RAID_CTX_CPUSEL_FCFS		0xF
+
+struct MR_CPU_AFFINITY_MASK {
+	union {
+		struct {
+#ifndef MFI_BIG_ENDIAN
+		u8 hw_path:1;
+		u8 cpu0:1;
+		u8 cpu1:1;
+		u8 cpu2:1;
+		u8 cpu3:1;
+		u8 reserved:3;
+#else
+		u8 reserved:3;
+		u8 cpu3:1;
+		u8 cpu2:1;
+		u8 cpu1:1;
+		u8 cpu0:1;
+		u8 hw_path:1;
+#endif
+		};
+		u8 core_mask;
+	};
+};
+
+struct MR_IO_AFFINITY {
+	union {
+		struct {
+			struct MR_CPU_AFFINITY_MASK pdRead;
+			struct MR_CPU_AFFINITY_MASK pdWrite;
+			struct MR_CPU_AFFINITY_MASK ldRead;
+			struct MR_CPU_AFFINITY_MASK ldWrite;
+			};
+		u32 word;
+		};
+	u8 maxCores;    /* Total cores + HW Path in ROC */
+	u8 reserved[3];
+};
+
 struct MR_LD_RAID {
 	struct {
 #if   defined(__BIG_ENDIAN_BITFIELD)
-		u32     reserved4:5;
+		u32 reserved4:2;
+		u32 fp_cache_bypass_capable:1;
+		u32 fp_rmw_capable:1;
+		u32 disable_coalescing:1;
 		u32     fpBypassRegionLock:1;
 		u32     tmCapable:1;
 		u32	fpNonRWCapable:1;
@@ -654,11 +828,13 @@ struct MR_LD_RAID {
 		u32     encryptionType:8;
 		u32     pdPiMode:4;
 		u32     ldPiMode:4;
-		u32     reserved5:3;
+		u32 reserved5:2;
+		u32 ra_capable:1;
 		u32     fpCapable:1;
 #else
 		u32     fpCapable:1;
-		u32     reserved5:3;
+		u32 ra_capable:1;
+		u32 reserved5:2;
 		u32     ldPiMode:4;
 		u32     pdPiMode:4;
 		u32     encryptionType:8;
@@ -669,7 +845,10 @@ struct MR_LD_RAID {
 		u32	fpNonRWCapable:1;
 		u32     tmCapable:1;
 		u32     fpBypassRegionLock:1;
-		u32     reserved4:5;
+		u32 disable_coalescing:1;
+		u32 fp_rmw_capable:1;
+		u32 fp_cache_bypass_capable:1;
+		u32 reserved4:2;
 #endif
 	} capability;
 	__le32     reserved6;
@@ -696,7 +875,36 @@ struct MR_LD_RAID {
 
 	u8	LUN[8]; /* 0x24 8 byte LUN field used for SCSI IO's */
 	u8	fpIoTimeoutForLd;/*0x2C timeout value used by driver in FP IO*/
-	u8      reserved3[0x80-0x2D]; /* 0x2D */
+	/* Ox2D This LD accept priority boost of this type */
+	u8 ld_accept_priority_type;
+	u8 reserved2[2];	        /* 0x2E - 0x2F */
+	/* 0x30 - 0x33, Logical block size for the LD */
+	u32 logical_block_length;
+	struct {
+#ifndef MFI_BIG_ENDIAN
+	/* 0x34, P_I_EXPONENT from READ CAPACITY 16 */
+	u32 ld_pi_exp:4;
+	/* 0x34, LOGICAL BLOCKS PER PHYSICAL
+	 *  BLOCK EXPONENT from READ CAPACITY 16
+	 */
+	u32 ld_logical_block_exp:4;
+	u32 reserved1:24;           /* 0x34 */
+#else
+	u32 reserved1:24;           /* 0x34 */
+	/* 0x34, LOGICAL BLOCKS PER PHYSICAL
+	 *  BLOCK EXPONENT from READ CAPACITY 16
+	 */
+	u32 ld_logical_block_exp:4;
+	/* 0x34, P_I_EXPONENT from READ CAPACITY 16 */
+	u32 ld_pi_exp:4;
+#endif
+	};                               /* 0x34 - 0x37 */
+	 /* 0x38 - 0x3f, This will determine which
+	  *  core will process LD IO and PD IO.
+	  */
+	struct MR_IO_AFFINITY cpuAffinity;
+     /* Bit definiations are specified by MR_IO_AFFINITY */
+	u8 reserved3[0x80 - 0x40];    /* 0x40 - 0x7f */
 };
 
 struct MR_LD_SPAN_MAP {
@@ -735,6 +943,7 @@ struct IO_REQUEST_INFO {
 	u16 ldTgtId;
 	u8 isRead;
 	__le16 devHandle;
+	u8 pd_interface;
 	u64 pdBlock;
 	u8 fpOkForIo;
 	u8 IoforUnevenSpan;
@@ -743,6 +952,8 @@ struct IO_REQUEST_INFO {
 	u64 start_row;
 	u8  span_arm;	/* span[7:5], arm[4:0] */
 	u8  pd_after_lb;
+	u16 r1_alt_dev_handle; /* raid 1/10 only */
+	bool ra_capable;
 };
 
 struct MR_LD_TARGET_SYNC {
@@ -751,6 +962,91 @@ struct MR_LD_TARGET_SYNC {
 	__le16 seqNum;
 };
 
+/*
+ * RAID Map descriptor Types.
+ * Each element should uniquely idetify one data structure in the RAID map
+ */
+enum MR_RAID_MAP_DESC_TYPE {
+	/* MR_DEV_HANDLE_INFO data */
+	RAID_MAP_DESC_TYPE_DEVHDL_INFO    = 0x0,
+	/* target to Ld num Index map */
+	RAID_MAP_DESC_TYPE_TGTID_INFO     = 0x1,
+	/* MR_ARRAY_INFO data */
+	RAID_MAP_DESC_TYPE_ARRAY_INFO     = 0x2,
+	/* MR_LD_SPAN_MAP data */
+	RAID_MAP_DESC_TYPE_SPAN_INFO      = 0x3,
+	RAID_MAP_DESC_TYPE_COUNT,
+};
+
+/*
+ * This table defines the offset, size and num elements  of each descriptor
+ * type in the RAID Map buffer
+ */
+struct MR_RAID_MAP_DESC_TABLE {
+	/* Raid map descriptor type */
+	u32 raid_map_desc_type;
+	/* Offset into the RAID map buffer where
+	 *  descriptor data is saved
+	 */
+	u32 raid_map_desc_offset;
+	/* total size of the
+	 * descriptor buffer
+	 */
+	u32 raid_map_desc_buffer_size;
+	/* Number of elements contained in the
+	 *  descriptor buffer
+	 */
+	u32 raid_map_desc_elements;
+};
+
+/*
+ * Dynamic Raid Map Structure.
+ */
+struct MR_FW_RAID_MAP_DYNAMIC {
+	u32 raid_map_size;   /* total size of RAID Map structure */
+	u32 desc_table_offset;/* Offset of desc table into RAID map*/
+	u32 desc_table_size;  /* Total Size of desc table */
+	/* Total Number of elements in the desc table */
+	u32 desc_table_num_elements;
+	u64	reserved1;
+	u32	reserved2[3];	/*future use */
+	/* timeout value used by driver in FP IOs */
+	u8 fp_pd_io_timeout_sec;
+	u8 reserved3[3];
+	/* when this seqNum increments, driver needs to
+	 *  release RMW buffers asap
+	 */
+	u32 rmw_fp_seq_num;
+	u16 ld_count;	/* count of lds. */
+	u16 ar_count;   /* count of arrays */
+	u16 span_count; /* count of spans */
+	u16 reserved4[3];
+/*
+ * The below structure of pointers is only to be used by the driver.
+ * This is added in the ,API to reduce the amount of code changes
+ * needed in the driver to support dynamic RAID map Firmware should
+ * not update these pointers while preparing the raid map
+ */
+	union {
+		struct {
+			struct MR_DEV_HANDLE_INFO  *dev_hndl_info;
+			u16 *ld_tgt_id_to_ld;
+			struct MR_ARRAY_INFO *ar_map_info;
+			struct MR_LD_SPAN_MAP *ld_span_map;
+			};
+		u64 ptr_structure_size[RAID_MAP_DESC_TYPE_COUNT];
+		};
+/*
+ * RAID Map descriptor table defines the layout of data in the RAID Map.
+ * The size of the descriptor table itself could change.
+ */
+	/* Variable Size descriptor Table. */
+	struct MR_RAID_MAP_DESC_TABLE
+			raid_map_desc_table[RAID_MAP_DESC_TYPE_COUNT];
+	/* Variable Size buffer containing all data */
+	u32 raid_map_desc_data[1];
+}; /* Dynamicaly sized RAID MAp structure */
+
 #define IEEE_SGE_FLAGS_ADDR_MASK            (0x03)
 #define IEEE_SGE_FLAGS_SYSTEM_ADDR          (0x00)
 #define IEEE_SGE_FLAGS_IOCDDR_ADDR          (0x01)
@@ -759,6 +1055,16 @@ struct MR_LD_TARGET_SYNC {
 #define IEEE_SGE_FLAGS_CHAIN_ELEMENT        (0x80)
 #define IEEE_SGE_FLAGS_END_OF_LIST          (0x40)
 
+#define MPI2_SGE_FLAGS_SHIFT                (0x02)
+#define IEEE_SGE_FLAGS_FORMAT_MASK          (0xC0)
+#define IEEE_SGE_FLAGS_FORMAT_IEEE          (0x00)
+#define IEEE_SGE_FLAGS_FORMAT_NVME          (0x02)
+
+#define MPI26_IEEE_SGE_FLAGS_NSF_MASK           (0x1C)
+#define MPI26_IEEE_SGE_FLAGS_NSF_MPI_IEEE       (0x00)
+#define MPI26_IEEE_SGE_FLAGS_NSF_NVME_PRP       (0x08)
+#define MPI26_IEEE_SGE_FLAGS_NSF_NVME_SGL       (0x10)
+
 struct megasas_register_set;
 struct megasas_instance;
 
@@ -795,6 +1101,10 @@ struct megasas_cmd_fusion {
 	u32 index;
 	u8 pd_r1_lb;
 	struct completion done;
+	u8 pd_interface;
+	u16 r1_alt_dev_handle; /* raid 1/10 only*/
+	bool cmd_completed;  /* raid 1/10 fp writes status holder */
+
 };
 
 struct LD_LOAD_BALANCE_INFO {
@@ -856,9 +1166,10 @@ struct MR_DRV_RAID_MAP {
 	__le16                 spanCount;
 	__le16                 reserve3;
 
-	struct MR_DEV_HANDLE_INFO  devHndlInfo[MAX_RAIDMAP_PHYSICAL_DEVICES];
-	u8                  ldTgtIdToLd[MAX_LOGICAL_DRIVES_EXT];
-	struct MR_ARRAY_INFO       arMapInfo[MAX_API_ARRAYS_EXT];
+	struct MR_DEV_HANDLE_INFO
+		devHndlInfo[MAX_RAIDMAP_PHYSICAL_DEVICES_DYN];
+	u16 ldTgtIdToLd[MAX_LOGICAL_DRIVES_DYN];
+	struct MR_ARRAY_INFO arMapInfo[MAX_API_ARRAYS_DYN];
 	struct MR_LD_SPAN_MAP      ldSpanMap[1];
 
 };
@@ -870,7 +1181,7 @@ struct MR_DRV_RAID_MAP {
 struct MR_DRV_RAID_MAP_ALL {
 
 	struct MR_DRV_RAID_MAP raidMap;
-	struct MR_LD_SPAN_MAP      ldSpanMap[MAX_LOGICAL_DRIVES_EXT - 1];
+	struct MR_LD_SPAN_MAP ldSpanMap[MAX_LOGICAL_DRIVES_DYN - 1];
 } __packed;
 
 
@@ -919,7 +1230,8 @@ struct MR_PD_CFG_SEQ {
 		u8     reserved:7;
 #endif
 	} capability;
-	u8  reserved[3];
+	u8  reserved;
+	u16 pd_target_id;
 } __packed;
 
 struct MR_PD_CFG_SEQ_NUM_SYNC {
@@ -928,6 +1240,30 @@ struct MR_PD_CFG_SEQ_NUM_SYNC {
 	struct MR_PD_CFG_SEQ seq[1];
 } __packed;
 
+/* stream detection */
+struct STREAM_DETECT {
+	u64 next_seq_lba; /* next LBA to match sequential access */
+	struct megasas_cmd_fusion *first_cmd_fusion; /* first cmd in group */
+	struct megasas_cmd_fusion *last_cmd_fusion; /* last cmd in group */
+	u32 count_cmds_in_stream; /* count of host commands in this stream */
+	u16 num_sges_in_group; /* total number of SGEs in grouped IOs */
+	u8 is_read; /* SCSI OpCode for this stream */
+	u8 group_depth; /* total number of host commands in group */
+	/* TRUE if cannot add any more commands to this group */
+	bool group_flush;
+	u8 reserved[7]; /* pad to 64-bit alignment */
+};
+
+struct LD_STREAM_DETECT {
+	bool write_back; /* TRUE if WB, FALSE if WT */
+	bool fp_write_enabled;
+	bool members_ssds;
+	bool fp_cache_bypass_capable;
+	u32 mru_bit_map; /* bitmap used to track MRU and LRU stream indicies */
+	/* this is the array of stream detect structures (one per stream) */
+	struct STREAM_DETECT stream_track[MAX_STREAMS_TRACKED];
+};
+
 struct MPI2_IOC_INIT_RDPQ_ARRAY_ENTRY {
 	u64 RDPQBaseAddress;
 	u32 Reserved1;
@@ -965,7 +1301,7 @@ struct fusion_context {
 	u8	chain_offset_io_request;
 	u8	chain_offset_mfi_pthru;
 
-	struct MR_FW_RAID_MAP_ALL *ld_map[2];
+	struct MR_FW_RAID_MAP_DYNAMIC *ld_map[2];
 	dma_addr_t ld_map_phys[2];
 
 	/*Non dma-able memory. Driver local copy.*/
@@ -973,14 +1309,18 @@ struct fusion_context {
 
 	u32 max_map_sz;
 	u32 current_map_sz;
+	u32 old_map_sz;
+	u32 new_map_sz;
 	u32 drv_map_sz;
 	u32 drv_map_pages;
 	struct MR_PD_CFG_SEQ_NUM_SYNC	*pd_seq_sync[JBOD_MAPS_COUNT];
 	dma_addr_t pd_seq_phys[JBOD_MAPS_COUNT];
 	u8 fast_path_io;
-	struct LD_LOAD_BALANCE_INFO load_balance_info[MAX_LOGICAL_DRIVES_EXT];
+	struct LD_LOAD_BALANCE_INFO *load_balance_info;
+	u32 load_balance_info_pages;
 	LD_SPAN_INFO log_to_span[MAX_LOGICAL_DRIVES_EXT];
 	u8 adapter_type;
+	struct LD_STREAM_DETECT **stream_detect_by_ld;
 };
 
 union desc_value {
diff --git a/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h b/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
index 8bae305bc156..af4be403582e 100644
--- a/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
+++ b/drivers/scsi/mpt3sas/mpi/mpi2_ioc.h
@@ -624,6 +624,8 @@ typedef struct _MPI26_EVENT_DATA_ACTIVE_CABLE_EXCEPT {
 
 /* defines for ReasonCode field */
 #define MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER     (0x00)
+#define MPI26_EVENT_ACTIVE_CABLE_PRESENT                (0x01)
+#define MPI26_EVENT_ACTIVE_CABLE_DEGRADED               (0x02)
 
 /*Hard Reset Received Event data */
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index f00ef88a378a..a3fe1fb55c17 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -1040,6 +1040,25 @@ _base_interrupt(int irq, void *bus_id)
 		    reply_q->reply_post_free[reply_q->reply_post_host_index].
 		    Default.ReplyFlags & MPI2_RPY_DESCRIPT_FLAGS_TYPE_MASK;
 		completed_cmds++;
+		/* Update the reply post host index after continuously
+		 * processing the threshold number of Reply Descriptors.
+		 * So that FW can find enough entries to post the Reply
+		 * Descriptors in the reply descriptor post queue.
+		 */
+		if (completed_cmds > ioc->hba_queue_depth/3) {
+			if (ioc->combined_reply_queue) {
+				writel(reply_q->reply_post_host_index |
+						((msix_index  & 7) <<
+						 MPI2_RPHI_MSIX_INDEX_SHIFT),
+				    ioc->replyPostRegisterIndex[msix_index/8]);
+			} else {
+				writel(reply_q->reply_post_host_index |
+						(msix_index <<
+						 MPI2_RPHI_MSIX_INDEX_SHIFT),
+						&ioc->chip->ReplyPostHostIndex);
+			}
+			completed_cmds = 1;
+		}
 		if (request_desript_type == MPI2_RPY_DESCRIPT_FLAGS_UNUSED)
 			goto out;
 		if (!reply_q->reply_post_host_index)
@@ -5522,6 +5541,7 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 		goto out_free_resources;
 
 	ioc->non_operational_loop = 0;
+	ioc->got_task_abort_from_ioctl = 0;
 	return 0;
 
  out_free_resources:
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index dcb33f4fa687..4ab634fc27df 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -73,9 +73,9 @@
 #define MPT3SAS_DRIVER_NAME		"mpt3sas"
 #define MPT3SAS_AUTHOR "Avago Technologies <MPT-FusionLinux.pdl@avagotech.com>"
 #define MPT3SAS_DESCRIPTION	"LSI MPT Fusion SAS 3.0 Device Driver"
-#define MPT3SAS_DRIVER_VERSION		"14.101.00.00"
-#define MPT3SAS_MAJOR_VERSION		14
-#define MPT3SAS_MINOR_VERSION		101
+#define MPT3SAS_DRIVER_VERSION		"15.100.00.00"
+#define MPT3SAS_MAJOR_VERSION		15
+#define MPT3SAS_MINOR_VERSION		100
 #define MPT3SAS_BUILD_VERSION		0
 #define MPT3SAS_RELEASE_VERSION	00
 
@@ -1000,6 +1000,7 @@ struct MPT3SAS_ADAPTER {
 	u8		broadcast_aen_busy;
 	u16		broadcast_aen_pending;
 	u8		shost_recovery;
+	u8		got_task_abort_from_ioctl;
 
 	struct mutex	reset_in_progress_mutex;
 	spinlock_t	ioc_reset_in_progress_lock;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 95f0f24bac05..02fe1c4aae2f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -826,16 +826,18 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 			"TASK_MGMT: handle(0x%04x), task_type(0x%02x)\n",
 			ioc->name,
 		    le16_to_cpu(tm_request->DevHandle), tm_request->TaskType));
-
+		ioc->got_task_abort_from_ioctl = 1;
 		if (tm_request->TaskType ==
 		    MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK ||
 		    tm_request->TaskType ==
 		    MPI2_SCSITASKMGMT_TASKTYPE_QUERY_TASK) {
 			if (_ctl_set_task_mid(ioc, &karg, tm_request)) {
 				mpt3sas_base_free_smid(ioc, smid);
+				ioc->got_task_abort_from_ioctl = 0;
 				goto out;
 			}
 		}
+		ioc->got_task_abort_from_ioctl = 0;
 
 		if (test_bit(device_handle, ioc->device_remove_in_progress)) {
 			dtmprintk(ioc, pr_info(MPT3SAS_FMT
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 75f3fce1c867..46e866c36c8a 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -51,6 +51,7 @@
 #include <linux/workqueue.h>
 #include <linux/delay.h>
 #include <linux/pci.h>
+#include <linux/pci-aspm.h>
 #include <linux/interrupt.h>
 #include <linux/aer.h>
 #include <linux/raid_class.h>
@@ -1074,6 +1075,26 @@ _scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 }
 
 /**
+ * __scsih_scsi_lookup_get_clear - returns scmd entry without
+ *						holding any lock.
+ * @ioc: per adapter object
+ * @smid: system request message index
+ *
+ * Returns the smid stored scmd pointer.
+ * Then will dereference the stored scmd pointer.
+ */
+static inline struct scsi_cmnd *
+__scsih_scsi_lookup_get_clear(struct MPT3SAS_ADAPTER *ioc,
+		u16 smid)
+{
+	struct scsi_cmnd *scmd = NULL;
+
+	swap(scmd, ioc->scsi_lookup[smid - 1].scmd);
+
+	return scmd;
+}
+
+/**
  * _scsih_scsi_lookup_get_clear - returns scmd entry
  * @ioc: per adapter object
  * @smid: system request message index
@@ -1088,8 +1109,7 @@ _scsih_scsi_lookup_get_clear(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 	struct scsi_cmnd *scmd;
 
 	spin_lock_irqsave(&ioc->scsi_lookup_lock, flags);
-	scmd = ioc->scsi_lookup[smid - 1].scmd;
-	ioc->scsi_lookup[smid - 1].scmd = NULL;
+	scmd = __scsih_scsi_lookup_get_clear(ioc, smid);
 	spin_unlock_irqrestore(&ioc->scsi_lookup_lock, flags);
 
 	return scmd;
@@ -4657,9 +4677,16 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	struct MPT3SAS_DEVICE *sas_device_priv_data;
 	u32 response_code = 0;
 	unsigned long flags;
+	unsigned int sector_sz;
 
 	mpi_reply = mpt3sas_base_get_reply_virt_addr(ioc, reply);
-	scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
+
+	if (ioc->broadcast_aen_busy || ioc->pci_error_recovery ||
+			ioc->got_task_abort_from_ioctl)
+		scmd = _scsih_scsi_lookup_get_clear(ioc, smid);
+	else
+		scmd = __scsih_scsi_lookup_get_clear(ioc, smid);
+
 	if (scmd == NULL)
 		return 1;
 
@@ -4715,6 +4742,20 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 	}
 
 	xfer_cnt = le32_to_cpu(mpi_reply->TransferCount);
+
+	/* In case of bogus fw or device, we could end up having
+	 * unaligned partial completion. We can force alignment here,
+	 * then scsi-ml does not need to handle this misbehavior.
+	 */
+	sector_sz = scmd->device->sector_size;
+	if (unlikely(!blk_rq_is_passthrough(scmd->request) && sector_sz &&
+		     xfer_cnt % sector_sz)) {
+		sdev_printk(KERN_INFO, scmd->device,
+		    "unaligned partial completion avoided (xfer_cnt=%u, sector_sz=%u)\n",
+			    xfer_cnt, sector_sz);
+		xfer_cnt = round_down(xfer_cnt, sector_sz);
+	}
+
 	scsi_set_resid(scmd, scsi_bufflen(scmd) - xfer_cnt);
 	if (ioc_status & MPI2_IOCSTATUS_FLAG_LOG_INFO_AVAILABLE)
 		log_info =  le32_to_cpu(mpi_reply->IOCLogInfo);
@@ -8028,15 +8069,24 @@ mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
 	case MPI2_EVENT_ACTIVE_CABLE_EXCEPTION:
 		ActiveCableEventData =
 		    (Mpi26EventDataActiveCableExcept_t *) mpi_reply->EventData;
-		if (ActiveCableEventData->ReasonCode ==
-				MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER) {
-			pr_info(MPT3SAS_FMT "Currently an active cable with ReceptacleID %d",
-			    ioc->name, ActiveCableEventData->ReceptacleID);
-			pr_info("cannot be powered and devices connected to this active cable");
-			pr_info("will not be seen. This active cable");
-			pr_info("requires %d mW of power",
-			    ActiveCableEventData->ActiveCablePowerRequirement);
+		switch (ActiveCableEventData->ReasonCode) {
+		case MPI26_EVENT_ACTIVE_CABLE_INSUFFICIENT_POWER:
+			pr_notice(MPT3SAS_FMT "Receptacle ID %d: This active cable"
+				  " requires %d mW of power\n", ioc->name,
+			     ActiveCableEventData->ReceptacleID,
+			     ActiveCableEventData->ActiveCablePowerRequirement);
+			pr_notice(MPT3SAS_FMT "Receptacle ID %d: Devices connected"
+				  " to this active cable will not be seen\n",
+			     ioc->name, ActiveCableEventData->ReceptacleID);
+			break;
+
+		case MPI26_EVENT_ACTIVE_CABLE_DEGRADED:
+			pr_notice(MPT3SAS_FMT "ReceptacleID %d: This cable",
+				ioc->name, ActiveCableEventData->ReceptacleID);
+			pr_notice(" is not running at an optimal speed(12 Gb/s)\n");
+			break;
 		}
+
 		break;
 
 	default: /* ignore the rest */
@@ -8746,6 +8796,8 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	switch (hba_mpi_version) {
 	case MPI2_VERSION:
+		pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S |
+			PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
 		/* Use mpt2sas driver host template for SAS 2.0 HBA's */
 		shost = scsi_host_alloc(&mpt2sas_driver_template,
 		  sizeof(struct MPT3SAS_ADAPTER));
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index 7f1d5785bc30..e7a7a704a315 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -2057,10 +2057,10 @@ _transport_smp_handler(struct Scsi_Host *shost, struct sas_rphy *rphy,
 		    ioc->name, __func__,
 		    le16_to_cpu(mpi_reply->ResponseDataLength)));
 
-		memcpy(req->sense, mpi_reply, sizeof(*mpi_reply));
-		req->sense_len = sizeof(*mpi_reply);
-		req->resid_len = 0;
-		rsp->resid_len -=
+		memcpy(scsi_req(req)->sense, mpi_reply, sizeof(*mpi_reply));
+		scsi_req(req)->sense_len = sizeof(*mpi_reply);
+		scsi_req(req)->resid_len = 0;
+		scsi_req(rsp)->resid_len -=
 		    le16_to_cpu(mpi_reply->ResponseDataLength);
 
 		/* check if the resp needs to be copied from the allocated
diff --git a/drivers/scsi/mvumi.c b/drivers/scsi/mvumi.c
index 39285070f3b5..247df5e79b71 100644
--- a/drivers/scsi/mvumi.c
+++ b/drivers/scsi/mvumi.c
@@ -2225,15 +2225,12 @@ static struct scsi_host_template mvumi_template = {
 	.name = "Marvell Storage Controller",
 	.slave_configure = mvumi_slave_configure,
 	.queuecommand = mvumi_queue_command,
+	.eh_timed_out = mvumi_timed_out,
 	.eh_host_reset_handler = mvumi_host_reset,
 	.bios_param = mvumi_bios_param,
 	.this_id = -1,
 };
 
-static struct scsi_transport_template mvumi_transport_template = {
-	.eh_timed_out = mvumi_timed_out,
-};
-
 static int mvumi_cfg_hw_reg(struct mvumi_hba *mhba)
 {
 	void *base = NULL;
@@ -2451,7 +2448,6 @@ static int mvumi_io_attach(struct mvumi_hba *mhba)
 	host->cmd_per_lun = (mhba->max_io - 1) ? (mhba->max_io - 1) : 1;
 	host->max_id = mhba->max_target_id;
 	host->max_cmd_len = MAX_COMMAND_SIZE;
-	host->transportt = &mvumi_transport_template;
 
 	ret = scsi_add_host(host, &mhba->pdev->dev);
 	if (ret) {
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index ef99f62831fb..30b905080c61 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -48,6 +48,7 @@
 #include <scsi/osd_sense.h>
 
 #include <scsi/scsi_device.h>
+#include <scsi/scsi_request.h>
 
 #include "osd_debug.h"
 
@@ -477,11 +478,13 @@ static void _set_error_resid(struct osd_request *or, struct request *req,
 {
 	or->async_error = error;
 	or->req_errors = req->errors ? : error;
-	or->sense_len = req->sense_len;
+	or->sense_len = scsi_req(req)->sense_len;
+	if (or->sense_len)
+		memcpy(or->sense, scsi_req(req)->sense, or->sense_len);
 	if (or->out.req)
-		or->out.residual = or->out.req->resid_len;
+		or->out.residual = scsi_req(or->out.req)->resid_len;
 	if (or->in.req)
-		or->in.residual = or->in.req->resid_len;
+		or->in.residual = scsi_req(or->in.req)->resid_len;
 }
 
 int osd_execute_request(struct osd_request *or)
@@ -1562,10 +1565,11 @@ static struct request *_make_request(struct request_queue *q, bool has_write,
 	struct bio *bio = oii->bio;
 	int ret;
 
-	req = blk_get_request(q, has_write ? WRITE : READ, flags);
+	req = blk_get_request(q, has_write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
+			flags);
 	if (IS_ERR(req))
 		return req;
-	blk_rq_set_block_pc(req);
+	scsi_req_init(req);
 
 	for_each_bio(bio) {
 		struct bio *bounce_bio = bio;
@@ -1599,8 +1603,6 @@ static int _init_blk_request(struct osd_request *or,
 
 	req->timeout = or->timeout;
 	req->retries = or->retries;
-	req->sense = or->sense;
-	req->sense_len = 0;
 
 	if (has_out) {
 		or->out.req = req;
@@ -1612,7 +1614,7 @@ static int _init_blk_request(struct osd_request *or,
 				ret = PTR_ERR(req);
 				goto out;
 			}
-			blk_rq_set_block_pc(req);
+			scsi_req_init(req);
 			or->in.req = or->request->next_rq = req;
 		}
 	} else if (has_in)
@@ -1699,8 +1701,8 @@ int osd_finalize_request(struct osd_request *or,
 
 	osd_sec_sign_cdb(&or->cdb, cap_key);
 
-	or->request->cmd = or->cdb.buff;
-	or->request->cmd_len = _osd_req_cdb_len(or);
+	scsi_req(or->request)->cmd = or->cdb.buff;
+	scsi_req(or->request)->cmd_len = _osd_req_cdb_len(or);
 
 	return 0;
 }
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index e8196c55b633..451de6c5e3c9 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -322,6 +322,7 @@ static int osst_chk_result(struct osst_tape * STp, struct osst_request * SRpnt)
 /* Wakeup from interrupt */
 static void osst_end_async(struct request *req, int update)
 {
+	struct scsi_request *rq = scsi_req(req);
 	struct osst_request *SRpnt = req->end_io_data;
 	struct osst_tape *STp = SRpnt->stp;
 	struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data;
@@ -330,6 +331,8 @@ static void osst_end_async(struct request *req, int update)
 #if DEBUG
 	STp->write_pending = 0;
 #endif
+	if (rq->sense_len)
+		memcpy(SRpnt->sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
 	if (SRpnt->waiting)
 		complete(SRpnt->waiting);
 
@@ -357,17 +360,20 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
 			int use_sg, int timeout, int retries)
 {
 	struct request *req;
+	struct scsi_request *rq;
 	struct page **pages = NULL;
 	struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data;
 
 	int err = 0;
 	int write = (data_direction == DMA_TO_DEVICE);
 
-	req = blk_get_request(SRpnt->stp->device->request_queue, write, GFP_KERNEL);
+	req = blk_get_request(SRpnt->stp->device->request_queue,
+			write ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL);
 	if (IS_ERR(req))
 		return DRIVER_ERROR << 24;
 
-	blk_rq_set_block_pc(req);
+	rq = scsi_req(req);
+	scsi_req_init(req);
 	req->rq_flags |= RQF_QUIET;
 
 	SRpnt->bio = NULL;
@@ -404,11 +410,9 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
 			goto free_req;
 	}
 
-	req->cmd_len = cmd_len;
-	memset(req->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
-	memcpy(req->cmd, cmd, req->cmd_len);
-	req->sense = SRpnt->sense;
-	req->sense_len = 0;
+	rq->cmd_len = cmd_len;
+	memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
+	memcpy(rq->cmd, cmd, rq->cmd_len);
 	req->timeout = timeout;
 	req->retries = retries;
 	req->end_io_data = SRpnt;
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 9fc675f57e33..417368ccb686 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -888,7 +888,6 @@ static u32 pm8001_setup_msix(struct pm8001_hba_info *pm8001_ha)
 	u32 i = 0, j = 0;
 	u32 number_of_intr;
 	int flag = 0;
-	u32 max_entry;
 	int rc;
 	static char intr_drvname[PM8001_MAX_MSIX_VEC][sizeof(DRV_NAME)+3];
 
@@ -900,18 +899,14 @@ static u32 pm8001_setup_msix(struct pm8001_hba_info *pm8001_ha)
 		flag &= ~IRQF_SHARED;
 	}
 
-	max_entry = sizeof(pm8001_ha->msix_entries) /
-		sizeof(pm8001_ha->msix_entries[0]);
-	for (i = 0; i < max_entry ; i++)
-		pm8001_ha->msix_entries[i].entry = i;
-	rc = pci_enable_msix_exact(pm8001_ha->pdev, pm8001_ha->msix_entries,
-		number_of_intr);
-	pm8001_ha->number_of_intr = number_of_intr;
-	if (rc)
+	rc = pci_alloc_irq_vectors(pm8001_ha->pdev, number_of_intr,
+			number_of_intr, PCI_IRQ_MSIX);
+	if (rc < 0)
 		return rc;
+	pm8001_ha->number_of_intr = number_of_intr;
 
 	PM8001_INIT_DBG(pm8001_ha, pm8001_printk(
-		"pci_enable_msix_exact request ret:%d no of intr %d\n",
+		"pci_alloc_irq_vectors request ret:%d no of intr %d\n",
 				rc, pm8001_ha->number_of_intr));
 
 	for (i = 0; i < number_of_intr; i++) {
@@ -920,15 +915,15 @@ static u32 pm8001_setup_msix(struct pm8001_hba_info *pm8001_ha)
 		pm8001_ha->irq_vector[i].irq_id = i;
 		pm8001_ha->irq_vector[i].drv_inst = pm8001_ha;
 
-		rc = request_irq(pm8001_ha->msix_entries[i].vector,
+		rc = request_irq(pci_irq_vector(pm8001_ha->pdev, i),
 			pm8001_interrupt_handler_msix, flag,
 			intr_drvname[i], &(pm8001_ha->irq_vector[i]));
 		if (rc) {
 			for (j = 0; j < i; j++) {
-				free_irq(pm8001_ha->msix_entries[j].vector,
+				free_irq(pci_irq_vector(pm8001_ha->pdev, i),
 					&(pm8001_ha->irq_vector[i]));
 			}
-			pci_disable_msix(pm8001_ha->pdev);
+			pci_free_irq_vectors(pm8001_ha->pdev);
 			break;
 		}
 	}
@@ -1102,11 +1097,10 @@ static void pm8001_pci_remove(struct pci_dev *pdev)
 
 #ifdef PM8001_USE_MSIX
 	for (i = 0; i < pm8001_ha->number_of_intr; i++)
-		synchronize_irq(pm8001_ha->msix_entries[i].vector);
+		synchronize_irq(pci_irq_vector(pdev, i));
 	for (i = 0; i < pm8001_ha->number_of_intr; i++)
-		free_irq(pm8001_ha->msix_entries[i].vector,
-				&(pm8001_ha->irq_vector[i]));
-	pci_disable_msix(pdev);
+		free_irq(pci_irq_vector(pdev, i), &pm8001_ha->irq_vector[i]);
+	pci_free_irq_vectors(pdev);
 #else
 	free_irq(pm8001_ha->irq, sha);
 #endif
@@ -1152,11 +1146,10 @@ static int pm8001_pci_suspend(struct pci_dev *pdev, pm_message_t state)
 	PM8001_CHIP_DISP->chip_soft_rst(pm8001_ha);
 #ifdef PM8001_USE_MSIX
 	for (i = 0; i < pm8001_ha->number_of_intr; i++)
-		synchronize_irq(pm8001_ha->msix_entries[i].vector);
+		synchronize_irq(pci_irq_vector(pdev, i));
 	for (i = 0; i < pm8001_ha->number_of_intr; i++)
-		free_irq(pm8001_ha->msix_entries[i].vector,
-				&(pm8001_ha->irq_vector[i]));
-	pci_disable_msix(pdev);
+		free_irq(pci_irq_vector(pdev, i), &pm8001_ha->irq_vector[i]);
+	pci_free_irq_vectors(pdev);
 #else
 	free_irq(pm8001_ha->irq, sha);
 #endif
diff --git a/drivers/scsi/pm8001/pm8001_sas.h b/drivers/scsi/pm8001/pm8001_sas.h
index 6628cc38316c..e81a8fa7ef1a 100644
--- a/drivers/scsi/pm8001/pm8001_sas.h
+++ b/drivers/scsi/pm8001/pm8001_sas.h
@@ -521,8 +521,6 @@ struct pm8001_hba_info {
 	struct pm8001_device	*devices;
 	struct pm8001_ccb_info	*ccb_info;
 #ifdef PM8001_USE_MSIX
-	struct msix_entry	msix_entries[PM8001_MAX_MSIX_VEC];
-					/*for msi-x interrupt*/
 	int			number_of_intr;/*will be used in remove()*/
 #endif
 #ifdef PM8001_USE_TASKLET
diff --git a/drivers/scsi/pmcraid.c b/drivers/scsi/pmcraid.c
index 337982cf3d63..49e70a383afa 100644
--- a/drivers/scsi/pmcraid.c
+++ b/drivers/scsi/pmcraid.c
@@ -4587,16 +4587,14 @@ static void pmcraid_tasklet_function(unsigned long instance)
 static
 void pmcraid_unregister_interrupt_handler(struct pmcraid_instance *pinstance)
 {
+	struct pci_dev *pdev = pinstance->pdev;
 	int i;
 
 	for (i = 0; i < pinstance->num_hrrq; i++)
-		free_irq(pinstance->hrrq_vector[i].vector,
-			 &(pinstance->hrrq_vector[i]));
+		free_irq(pci_irq_vector(pdev, i), &pinstance->hrrq_vector[i]);
 
-	if (pinstance->interrupt_mode) {
-		pci_disable_msix(pinstance->pdev);
-		pinstance->interrupt_mode = 0;
-	}
+	pinstance->interrupt_mode = 0;
+	pci_free_irq_vectors(pdev);
 }
 
 /**
@@ -4609,60 +4607,52 @@ void pmcraid_unregister_interrupt_handler(struct pmcraid_instance *pinstance)
 static int
 pmcraid_register_interrupt_handler(struct pmcraid_instance *pinstance)
 {
-	int rc;
 	struct pci_dev *pdev = pinstance->pdev;
+	unsigned int irq_flag = PCI_IRQ_LEGACY, flag;
+	int num_hrrq, rc, i;
+	irq_handler_t isr;
 
-	if ((pmcraid_enable_msix) &&
-		(pci_find_capability(pdev, PCI_CAP_ID_MSIX))) {
-		int num_hrrq = PMCRAID_NUM_MSIX_VECTORS;
-		struct msix_entry entries[PMCRAID_NUM_MSIX_VECTORS];
-		int i;
-		for (i = 0; i < PMCRAID_NUM_MSIX_VECTORS; i++)
-			entries[i].entry = i;
-
-		num_hrrq = pci_enable_msix_range(pdev, entries, 1, num_hrrq);
-		if (num_hrrq < 0)
-			goto pmcraid_isr_legacy;
-
-		for (i = 0; i < num_hrrq; i++) {
-			pinstance->hrrq_vector[i].hrrq_id = i;
-			pinstance->hrrq_vector[i].drv_inst = pinstance;
-			pinstance->hrrq_vector[i].vector = entries[i].vector;
-			rc = request_irq(pinstance->hrrq_vector[i].vector,
-					pmcraid_isr_msix, 0,
-					PMCRAID_DRIVER_NAME,
-					&(pinstance->hrrq_vector[i]));
-
-			if (rc) {
-				int j;
-				for (j = 0; j < i; j++)
-					free_irq(entries[j].vector,
-						 &(pinstance->hrrq_vector[j]));
-				pci_disable_msix(pdev);
-				goto pmcraid_isr_legacy;
-			}
-		}
+	if (pmcraid_enable_msix)
+		irq_flag |= PCI_IRQ_MSIX;
 
-		pinstance->num_hrrq = num_hrrq;
+	num_hrrq = pci_alloc_irq_vectors(pdev, 1, PMCRAID_NUM_MSIX_VECTORS,
+			irq_flag);
+	if (num_hrrq < 0)
+		return num_hrrq;
+
+	if (pdev->msix_enabled) {
+		flag = 0;
+		isr = pmcraid_isr_msix;
+	} else {
+		flag = IRQF_SHARED;
+		isr = pmcraid_isr;
+	}
+
+	for (i = 0; i < num_hrrq; i++) {
+		struct pmcraid_isr_param *vec = &pinstance->hrrq_vector[i];
+
+		vec->hrrq_id = i;
+		vec->drv_inst = pinstance;
+		rc = request_irq(pci_irq_vector(pdev, i), isr, flag,
+				PMCRAID_DRIVER_NAME, vec);
+		if (rc)
+			goto out_unwind;
+	}
+
+	pinstance->num_hrrq = num_hrrq;
+	if (pdev->msix_enabled) {
 		pinstance->interrupt_mode = 1;
 		iowrite32(DOORBELL_INTR_MODE_MSIX,
 			  pinstance->int_regs.host_ioa_interrupt_reg);
 		ioread32(pinstance->int_regs.host_ioa_interrupt_reg);
-		goto pmcraid_isr_out;
 	}
 
-pmcraid_isr_legacy:
-	/* If MSI-X registration failed fallback to legacy mode, where
-	 * only one hrrq entry will be used
-	 */
-	pinstance->hrrq_vector[0].hrrq_id = 0;
-	pinstance->hrrq_vector[0].drv_inst = pinstance;
-	pinstance->hrrq_vector[0].vector = pdev->irq;
-	pinstance->num_hrrq = 1;
-
-	rc = request_irq(pdev->irq, pmcraid_isr, IRQF_SHARED,
-			 PMCRAID_DRIVER_NAME, &pinstance->hrrq_vector[0]);
-pmcraid_isr_out:
+	return 0;
+
+out_unwind:
+	while (--i > 0)
+		free_irq(pci_irq_vector(pdev, i), &pinstance->hrrq_vector[i]);
+	pci_free_irq_vectors(pdev);
 	return rc;
 }
 
diff --git a/drivers/scsi/pmcraid.h b/drivers/scsi/pmcraid.h
index e1d150f3fd4d..568b18a2f47d 100644
--- a/drivers/scsi/pmcraid.h
+++ b/drivers/scsi/pmcraid.h
@@ -628,7 +628,6 @@ struct pmcraid_interrupts {
 /* ISR parameters LLD allocates (one for each MSI-X if enabled) vectors */
 struct pmcraid_isr_param {
 	struct pmcraid_instance *drv_inst;
-	u16 vector;			/* allocated msi-x vector */
 	u8 hrrq_id;			/* hrrq entry index */
 };
 
diff --git a/drivers/scsi/qedi/qedi_dbg.c b/drivers/scsi/qedi/qedi_dbg.c
index 2bdedb9c39bc..8fd28b056f73 100644
--- a/drivers/scsi/qedi/qedi_dbg.c
+++ b/drivers/scsi/qedi/qedi_dbg.c
@@ -52,7 +52,7 @@ qedi_dbg_warn(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	vaf.va = &va;
 
 	if (!(qedi_dbg_log & QEDI_LOG_WARN))
-		return;
+		goto ret;
 
 	if (likely(qedi) && likely(qedi->pdev))
 		pr_warn("[%s]:[%s:%d]:%d: %pV", dev_name(&qedi->pdev->dev),
@@ -60,6 +60,7 @@ qedi_dbg_warn(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	else
 		pr_warn("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
 
+ret:
 	va_end(va);
 }
 
@@ -80,7 +81,7 @@ qedi_dbg_notice(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	vaf.va = &va;
 
 	if (!(qedi_dbg_log & QEDI_LOG_NOTICE))
-		return;
+		goto ret;
 
 	if (likely(qedi) && likely(qedi->pdev))
 		pr_notice("[%s]:[%s:%d]:%d: %pV",
@@ -89,6 +90,7 @@ qedi_dbg_notice(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	else
 		pr_notice("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
 
+ret:
 	va_end(va);
 }
 
@@ -109,7 +111,7 @@ qedi_dbg_info(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	vaf.va = &va;
 
 	if (!(qedi_dbg_log & level))
-		return;
+		goto ret;
 
 	if (likely(qedi) && likely(qedi->pdev))
 		pr_info("[%s]:[%s:%d]:%d: %pV", dev_name(&qedi->pdev->dev),
@@ -117,6 +119,7 @@ qedi_dbg_info(struct qedi_dbg_ctx *qedi, const char *func, u32 line,
 	else
 		pr_info("[0000:00:00.0]:[%s:%d]: %pV", nfunc, line, &vaf);
 
+ret:
 	va_end(va);
 }
 
diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c
index d6a205433b66..b9f79d36142d 100644
--- a/drivers/scsi/qedi/qedi_iscsi.c
+++ b/drivers/scsi/qedi/qedi_iscsi.c
@@ -48,6 +48,7 @@ struct scsi_host_template qedi_host_template = {
 	.name = "QLogic QEDI 25/40/100Gb iSCSI Initiator Driver",
 	.proc_name = QEDI_MODULE_NAME,
 	.queuecommand = iscsi_queuecommand,
+	.eh_timed_out = iscsi_eh_cmd_timed_out,
 	.eh_abort_handler = iscsi_eh_abort,
 	.eh_device_reset_handler = iscsi_eh_device_reset,
 	.eh_target_reset_handler = iscsi_eh_recover_target,
@@ -453,13 +454,9 @@ static int qedi_iscsi_update_conn(struct qedi_ctx *qedi,
 	if (rval) {
 		rval = -ENXIO;
 		QEDI_ERR(&qedi->dbg_ctx, "Could not update connection\n");
-		goto update_conn_err;
 	}
 
 	kfree(conn_info);
-	rval = 0;
-
-update_conn_err:
 	return rval;
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 1bf8061ff803..40ca75bbcb9d 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -921,7 +921,7 @@ qla2x00_process_loopback(struct bsg_job *bsg_job)
 
 	bsg_job->reply_len = sizeof(struct fc_bsg_reply) +
 	    sizeof(response) + sizeof(uint8_t);
-	fw_sts_ptr = ((uint8_t *)bsg_job->req->sense) +
+	fw_sts_ptr = ((uint8_t *)scsi_req(bsg_job->req)->sense) +
 	    sizeof(struct fc_bsg_reply);
 	memcpy(fw_sts_ptr, response, sizeof(response));
 	fw_sts_ptr += sizeof(response);
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 5b1287a63c49..2f14adfab018 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2248,7 +2248,7 @@ struct ct_fdmiv2_hba_attr {
 		uint32_t num_ports;
 		uint8_t fabric_name[WWN_SIZE];
 		uint8_t bios_name[32];
-		uint8_t vendor_indentifer[8];
+		uint8_t vendor_identifier[8];
 	} a;
 };
 
@@ -2423,7 +2423,7 @@ struct ct_sns_req {
 		} rsnn_nn;
 
 		struct {
-			uint8_t hba_indentifier[8];
+			uint8_t hba_identifier[8];
 		} ghat;
 
 		struct {
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 94e8a8592f69..ee3df8794806 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -1939,15 +1939,15 @@ qla2x00_fdmiv2_rhba(scsi_qla_host_t *vha)
 	/* Vendor Identifier */
 	eiter = entries + size;
 	eiter->type = cpu_to_be16(FDMI_HBA_TYPE_VENDOR_IDENTIFIER);
-	snprintf(eiter->a.vendor_indentifer, sizeof(eiter->a.vendor_indentifer),
+	snprintf(eiter->a.vendor_identifier, sizeof(eiter->a.vendor_identifier),
 	    "%s", "QLGC");
-	alen = strlen(eiter->a.vendor_indentifer);
+	alen = strlen(eiter->a.vendor_identifier);
 	alen += 4 - (alen & 3);
 	eiter->len = cpu_to_be16(4 + alen);
 	size += 4 + alen;
 
 	ql_dbg(ql_dbg_disc, vha, 0x20b1,
-	    "Vendor Identifier = %s.\n", eiter->a.vendor_indentifer);
+	    "Vendor Identifier = %s.\n", eiter->a.vendor_identifier);
 
 	/* Update MS request size. */
 	qla2x00_update_ms_fdmi_iocb(vha, size + 16);
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index dc88a09f9043..edc2264db45b 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1468,7 +1468,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 			    type, sp->handle, comp_status, fw_status[1], fw_status[2],
 			    le16_to_cpu(((struct els_sts_entry_24xx *)
 				pkt)->total_byte_count));
-			fw_sts_ptr = ((uint8_t*)bsg_job->req->sense) + sizeof(struct fc_bsg_reply);
+			fw_sts_ptr = ((uint8_t*)scsi_req(bsg_job->req)->sense) +
+				sizeof(struct fc_bsg_reply);
 			memcpy( fw_sts_ptr, fw_status, sizeof(fw_status));
 		}
 		else {
@@ -1482,7 +1483,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req,
 				    pkt)->error_subcode_2));
 			res = DID_ERROR << 16;
 			bsg_reply->reply_payload_rcv_len = 0;
-			fw_sts_ptr = ((uint8_t*)bsg_job->req->sense) + sizeof(struct fc_bsg_reply);
+			fw_sts_ptr = ((uint8_t*)scsi_req(bsg_job->req)->sense) +
+					sizeof(struct fc_bsg_reply);
 			memcpy( fw_sts_ptr, fw_status, sizeof(fw_status));
 		}
 		ql_dump_buffer(ql_dbg_user + ql_dbg_buffer, vha, 0x5056,
@@ -2995,14 +2997,14 @@ struct qla_init_msix_entry {
 	irq_handler_t handler;
 };
 
-static struct qla_init_msix_entry msix_entries[] = {
+static const struct qla_init_msix_entry msix_entries[] = {
 	{ "qla2xxx (default)", qla24xx_msix_default },
 	{ "qla2xxx (rsp_q)", qla24xx_msix_rsp_q },
 	{ "qla2xxx (atio_q)", qla83xx_msix_atio_q },
 	{ "qla2xxx (qpair_multiq)", qla2xxx_msix_rsp_q },
 };
 
-static struct qla_init_msix_entry qla82xx_msix_entries[] = {
+static const struct qla_init_msix_entry qla82xx_msix_entries[] = {
 	{ "qla2xxx (default)", qla82xx_msix_default },
 	{ "qla2xxx (rsp_q)", qla82xx_msix_rsp_q },
 };
@@ -3076,7 +3078,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		qentry->handle = rsp;
 		rsp->msix = qentry;
 		scnprintf(qentry->name, sizeof(qentry->name),
-		    msix_entries[i].name);
+		    "%s", msix_entries[i].name);
 		if (IS_P3P_TYPE(ha))
 			ret = request_irq(qentry->vector,
 				qla82xx_msix_entries[i].handler,
@@ -3100,7 +3102,7 @@ qla24xx_enable_msix(struct qla_hw_data *ha, struct rsp_que *rsp)
 		rsp->msix = qentry;
 		qentry->handle = rsp;
 		scnprintf(qentry->name, sizeof(qentry->name),
-		    msix_entries[QLA_ATIO_VECTOR].name);
+		    "%s", msix_entries[QLA_ATIO_VECTOR].name);
 		qentry->in_use = 1;
 		ret = request_irq(qentry->vector,
 			msix_entries[QLA_ATIO_VECTOR].handler,
@@ -3242,7 +3244,7 @@ qla2x00_free_irqs(scsi_qla_host_t *vha)
 	 * from a probe failure context.
 	 */
 	if (!ha->rsp_q_map || !ha->rsp_q_map[0])
-		return;
+		goto free_irqs;
 	rsp = ha->rsp_q_map[0];
 
 	if (ha->flags.msix_enabled) {
@@ -3262,13 +3264,14 @@ qla2x00_free_irqs(scsi_qla_host_t *vha)
 		free_irq(pci_irq_vector(ha->pdev, 0), rsp);
 	}
 
+free_irqs:
 	pci_free_irq_vectors(ha->pdev);
 }
 
 int qla25xx_request_irq(struct qla_hw_data *ha, struct qla_qpair *qpair,
 	struct qla_msix_entry *msix, int vector_type)
 {
-	struct qla_init_msix_entry *intr = &msix_entries[vector_type];
+	const struct qla_init_msix_entry *intr = &msix_entries[vector_type];
 	scsi_qla_host_t *vha = pci_get_drvdata(ha->pdev);
 	int ret;
 
diff --git a/drivers/scsi/qla2xxx/qla_mr.c b/drivers/scsi/qla2xxx/qla_mr.c
index 02f1de18bc2b..96c33e292eba 100644
--- a/drivers/scsi/qla2xxx/qla_mr.c
+++ b/drivers/scsi/qla2xxx/qla_mr.c
@@ -2244,7 +2244,7 @@ qlafx00_ioctl_iosb_entry(scsi_qla_host_t *vha, struct req_que *req,
 		memcpy(fstatus.reserved_3,
 		    pkt->reserved_2, 20 * sizeof(uint8_t));
 
-		fw_sts_ptr = ((uint8_t *)bsg_job->req->sense) +
+		fw_sts_ptr = ((uint8_t *)scsi_req(bsg_job->req)->sense) +
 		    sizeof(struct fc_bsg_reply);
 
 		memcpy(fw_sts_ptr, (uint8_t *)&fstatus,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 0a000ecf0881..d01c90c7dd04 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -262,6 +262,7 @@ struct scsi_host_template qla2xxx_driver_template = {
 	.name			= QLA2XXX_DRIVER_NAME,
 	.queuecommand		= qla2xxx_queuecommand,
 
+	.eh_timed_out		= fc_eh_timed_out,
 	.eh_abort_handler	= qla2xxx_eh_abort,
 	.eh_device_reset_handler = qla2xxx_eh_device_reset,
 	.eh_target_reset_handler = qla2xxx_eh_target_reset,
@@ -1616,7 +1617,7 @@ qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
 				/* Don't abort commands in adapter during EEH
 				 * recovery as it's not accessible/responding.
 				 */
-				if (!ha->flags.eeh_busy) {
+				if (GET_CMD_SP(sp) && !ha->flags.eeh_busy) {
 					/* Get a reference to the sp and drop the lock.
 					 * The reference ensures this sp->done() call
 					 * - and not the call in qla2xxx_eh_abort() -
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index d925910be761..3084983c1287 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -371,7 +371,7 @@ static int tcm_qla2xxx_write_pending(struct se_cmd *se_cmd)
 		 */
 		pr_debug("write_pending aborted cmd[%p] refcount %d "
 			"transport_state %x, t_state %x, se_cmd_flags %x\n",
-			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd, kref_read(&cmd->se_cmd.cmd_kref),
 			cmd->se_cmd.transport_state,
 			cmd->se_cmd.t_state,
 			cmd->se_cmd.se_cmd_flags);
@@ -584,7 +584,7 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd)
 		 */
 		pr_debug("queue_data_in aborted cmd[%p] refcount %d "
 			"transport_state %x, t_state %x, se_cmd_flags %x\n",
-			cmd,cmd->se_cmd.cmd_kref.refcount.counter,
+			cmd, kref_read(&cmd->se_cmd.cmd_kref),
 			cmd->se_cmd.transport_state,
 			cmd->se_cmd.t_state,
 			cmd->se_cmd.se_cmd_flags);
diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h
index aeebefb1e9f8..fc233717355f 100644
--- a/drivers/scsi/qla4xxx/ql4_def.h
+++ b/drivers/scsi/qla4xxx/ql4_def.h
@@ -408,9 +408,6 @@ struct qla4_8xxx_legacy_intr_set {
 };
 
 /* MSI-X Support */
-
-#define QLA_MSIX_DEFAULT	0
-#define QLA_MSIX_RSP_Q		1
 #define QLA_MSIX_ENTRIES	2
 
 /*
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 9fbb33fc90c7..ac52150d1569 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -9539,15 +9539,15 @@ exit_host_reset:
  * driver calls the following device driver's callbacks
  *
  * - Fatal Errors - link_reset
- * - Non-Fatal Errors - driver's pci_error_detected() which
+ * - Non-Fatal Errors - driver's error_detected() which
  * returns CAN_RECOVER, NEED_RESET or DISCONNECT.
  *
  * PCI AER driver calls
- * CAN_RECOVER - driver's pci_mmio_enabled(), mmio_enabled
+ * CAN_RECOVER - driver's mmio_enabled(), mmio_enabled()
  *               returns RECOVERED or NEED_RESET if fw_hung
  * NEED_RESET - driver's slot_reset()
  * DISCONNECT - device is dead & cannot recover
- * RECOVERED - driver's pci_resume()
+ * RECOVERED - driver's resume()
  */
 static pci_ers_result_t
 qla4xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 75455d4dab68..7bfbcfa7af40 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -98,176 +98,6 @@ EXPORT_SYMBOL(scsi_sd_probe_domain);
 ASYNC_DOMAIN_EXCLUSIVE(scsi_sd_pm_domain);
 EXPORT_SYMBOL(scsi_sd_pm_domain);
 
-struct scsi_host_cmd_pool {
-	struct kmem_cache	*cmd_slab;
-	struct kmem_cache	*sense_slab;
-	unsigned int		users;
-	char			*cmd_name;
-	char			*sense_name;
-	unsigned int		slab_flags;
-	gfp_t			gfp_mask;
-};
-
-static struct scsi_host_cmd_pool scsi_cmd_pool = {
-	.cmd_name	= "scsi_cmd_cache",
-	.sense_name	= "scsi_sense_cache",
-	.slab_flags	= SLAB_HWCACHE_ALIGN,
-};
-
-static struct scsi_host_cmd_pool scsi_cmd_dma_pool = {
-	.cmd_name	= "scsi_cmd_cache(DMA)",
-	.sense_name	= "scsi_sense_cache(DMA)",
-	.slab_flags	= SLAB_HWCACHE_ALIGN|SLAB_CACHE_DMA,
-	.gfp_mask	= __GFP_DMA,
-};
-
-static DEFINE_MUTEX(host_cmd_pool_mutex);
-
-/**
- * scsi_host_free_command - internal function to release a command
- * @shost:	host to free the command for
- * @cmd:	command to release
- *
- * the command must previously have been allocated by
- * scsi_host_alloc_command.
- */
-static void
-scsi_host_free_command(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
-{
-	struct scsi_host_cmd_pool *pool = shost->cmd_pool;
-
-	if (cmd->prot_sdb)
-		kmem_cache_free(scsi_sdb_cache, cmd->prot_sdb);
-	kmem_cache_free(pool->sense_slab, cmd->sense_buffer);
-	kmem_cache_free(pool->cmd_slab, cmd);
-}
-
-/**
- * scsi_host_alloc_command - internal function to allocate command
- * @shost:	SCSI host whose pool to allocate from
- * @gfp_mask:	mask for the allocation
- *
- * Returns a fully allocated command with sense buffer and protection
- * data buffer (where applicable) or NULL on failure
- */
-static struct scsi_cmnd *
-scsi_host_alloc_command(struct Scsi_Host *shost, gfp_t gfp_mask)
-{
-	struct scsi_host_cmd_pool *pool = shost->cmd_pool;
-	struct scsi_cmnd *cmd;
-
-	cmd = kmem_cache_zalloc(pool->cmd_slab, gfp_mask | pool->gfp_mask);
-	if (!cmd)
-		goto fail;
-
-	cmd->sense_buffer = kmem_cache_alloc(pool->sense_slab,
-					     gfp_mask | pool->gfp_mask);
-	if (!cmd->sense_buffer)
-		goto fail_free_cmd;
-
-	if (scsi_host_get_prot(shost) >= SHOST_DIX_TYPE0_PROTECTION) {
-		cmd->prot_sdb = kmem_cache_zalloc(scsi_sdb_cache, gfp_mask);
-		if (!cmd->prot_sdb)
-			goto fail_free_sense;
-	}
-
-	return cmd;
-
-fail_free_sense:
-	kmem_cache_free(pool->sense_slab, cmd->sense_buffer);
-fail_free_cmd:
-	kmem_cache_free(pool->cmd_slab, cmd);
-fail:
-	return NULL;
-}
-
-/**
- * __scsi_get_command - Allocate a struct scsi_cmnd
- * @shost: host to transmit command
- * @gfp_mask: allocation mask
- *
- * Description: allocate a struct scsi_cmd from host's slab, recycling from the
- *              host's free_list if necessary.
- */
-static struct scsi_cmnd *
-__scsi_get_command(struct Scsi_Host *shost, gfp_t gfp_mask)
-{
-	struct scsi_cmnd *cmd = scsi_host_alloc_command(shost, gfp_mask);
-
-	if (unlikely(!cmd)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&shost->free_list_lock, flags);
-		if (likely(!list_empty(&shost->free_list))) {
-			cmd = list_entry(shost->free_list.next,
-					 struct scsi_cmnd, list);
-			list_del_init(&cmd->list);
-		}
-		spin_unlock_irqrestore(&shost->free_list_lock, flags);
-
-		if (cmd) {
-			void *buf, *prot;
-
-			buf = cmd->sense_buffer;
-			prot = cmd->prot_sdb;
-
-			memset(cmd, 0, sizeof(*cmd));
-
-			cmd->sense_buffer = buf;
-			cmd->prot_sdb = prot;
-		}
-	}
-
-	return cmd;
-}
-
-/**
- * scsi_get_command - Allocate and setup a scsi command block
- * @dev: parent scsi device
- * @gfp_mask: allocator flags
- *
- * Returns:	The allocated scsi command structure.
- */
-struct scsi_cmnd *scsi_get_command(struct scsi_device *dev, gfp_t gfp_mask)
-{
-	struct scsi_cmnd *cmd = __scsi_get_command(dev->host, gfp_mask);
-	unsigned long flags;
-
-	if (unlikely(cmd == NULL))
-		return NULL;
-
-	cmd->device = dev;
-	INIT_LIST_HEAD(&cmd->list);
-	INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler);
-	spin_lock_irqsave(&dev->list_lock, flags);
-	list_add_tail(&cmd->list, &dev->cmd_list);
-	spin_unlock_irqrestore(&dev->list_lock, flags);
-	cmd->jiffies_at_alloc = jiffies;
-	return cmd;
-}
-
-/**
- * __scsi_put_command - Free a struct scsi_cmnd
- * @shost: dev->host
- * @cmd: Command to free
- */
-static void __scsi_put_command(struct Scsi_Host *shost, struct scsi_cmnd *cmd)
-{
-	unsigned long flags;
-
-	if (unlikely(list_empty(&shost->free_list))) {
-		spin_lock_irqsave(&shost->free_list_lock, flags);
-		if (list_empty(&shost->free_list)) {
-			list_add(&cmd->list, &shost->free_list);
-			cmd = NULL;
-		}
-		spin_unlock_irqrestore(&shost->free_list_lock, flags);
-	}
-
-	if (likely(cmd != NULL))
-		scsi_host_free_command(shost, cmd);
-}
-
 /**
  * scsi_put_command - Free a scsi command block
  * @cmd: command block to free
@@ -287,188 +117,6 @@ void scsi_put_command(struct scsi_cmnd *cmd)
 	spin_unlock_irqrestore(&cmd->device->list_lock, flags);
 
 	BUG_ON(delayed_work_pending(&cmd->abort_work));
-
-	__scsi_put_command(cmd->device->host, cmd);
-}
-
-static struct scsi_host_cmd_pool *
-scsi_find_host_cmd_pool(struct Scsi_Host *shost)
-{
-	if (shost->hostt->cmd_size)
-		return shost->hostt->cmd_pool;
-	if (shost->unchecked_isa_dma)
-		return &scsi_cmd_dma_pool;
-	return &scsi_cmd_pool;
-}
-
-static void
-scsi_free_host_cmd_pool(struct scsi_host_cmd_pool *pool)
-{
-	kfree(pool->sense_name);
-	kfree(pool->cmd_name);
-	kfree(pool);
-}
-
-static struct scsi_host_cmd_pool *
-scsi_alloc_host_cmd_pool(struct Scsi_Host *shost)
-{
-	struct scsi_host_template *hostt = shost->hostt;
-	struct scsi_host_cmd_pool *pool;
-
-	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
-	if (!pool)
-		return NULL;
-
-	pool->cmd_name = kasprintf(GFP_KERNEL, "%s_cmd", hostt->proc_name);
-	pool->sense_name = kasprintf(GFP_KERNEL, "%s_sense", hostt->proc_name);
-	if (!pool->cmd_name || !pool->sense_name) {
-		scsi_free_host_cmd_pool(pool);
-		return NULL;
-	}
-
-	pool->slab_flags = SLAB_HWCACHE_ALIGN;
-	if (shost->unchecked_isa_dma) {
-		pool->slab_flags |= SLAB_CACHE_DMA;
-		pool->gfp_mask = __GFP_DMA;
-	}
-
-	if (hostt->cmd_size)
-		hostt->cmd_pool = pool;
-
-	return pool;
-}
-
-static struct scsi_host_cmd_pool *
-scsi_get_host_cmd_pool(struct Scsi_Host *shost)
-{
-	struct scsi_host_template *hostt = shost->hostt;
-	struct scsi_host_cmd_pool *retval = NULL, *pool;
-	size_t cmd_size = sizeof(struct scsi_cmnd) + hostt->cmd_size;
-
-	/*
-	 * Select a command slab for this host and create it if not
-	 * yet existent.
-	 */
-	mutex_lock(&host_cmd_pool_mutex);
-	pool = scsi_find_host_cmd_pool(shost);
-	if (!pool) {
-		pool = scsi_alloc_host_cmd_pool(shost);
-		if (!pool)
-			goto out;
-	}
-
-	if (!pool->users) {
-		pool->cmd_slab = kmem_cache_create(pool->cmd_name, cmd_size, 0,
-						   pool->slab_flags, NULL);
-		if (!pool->cmd_slab)
-			goto out_free_pool;
-
-		pool->sense_slab = kmem_cache_create(pool->sense_name,
-						     SCSI_SENSE_BUFFERSIZE, 0,
-						     pool->slab_flags, NULL);
-		if (!pool->sense_slab)
-			goto out_free_slab;
-	}
-
-	pool->users++;
-	retval = pool;
-out:
-	mutex_unlock(&host_cmd_pool_mutex);
-	return retval;
-
-out_free_slab:
-	kmem_cache_destroy(pool->cmd_slab);
-out_free_pool:
-	if (hostt->cmd_size) {
-		scsi_free_host_cmd_pool(pool);
-		hostt->cmd_pool = NULL;
-	}
-	goto out;
-}
-
-static void scsi_put_host_cmd_pool(struct Scsi_Host *shost)
-{
-	struct scsi_host_template *hostt = shost->hostt;
-	struct scsi_host_cmd_pool *pool;
-
-	mutex_lock(&host_cmd_pool_mutex);
-	pool = scsi_find_host_cmd_pool(shost);
-
-	/*
-	 * This may happen if a driver has a mismatched get and put
-	 * of the command pool; the driver should be implicated in
-	 * the stack trace
-	 */
-	BUG_ON(pool->users == 0);
-
-	if (!--pool->users) {
-		kmem_cache_destroy(pool->cmd_slab);
-		kmem_cache_destroy(pool->sense_slab);
-		if (hostt->cmd_size) {
-			scsi_free_host_cmd_pool(pool);
-			hostt->cmd_pool = NULL;
-		}
-	}
-	mutex_unlock(&host_cmd_pool_mutex);
-}
-
-/**
- * scsi_setup_command_freelist - Setup the command freelist for a scsi host.
- * @shost: host to allocate the freelist for.
- *
- * Description: The command freelist protects against system-wide out of memory
- * deadlock by preallocating one SCSI command structure for each host, so the
- * system can always write to a swap file on a device associated with that host.
- *
- * Returns:	Nothing.
- */
-int scsi_setup_command_freelist(struct Scsi_Host *shost)
-{
-	const gfp_t gfp_mask = shost->unchecked_isa_dma ? GFP_DMA : GFP_KERNEL;
-	struct scsi_cmnd *cmd;
-
-	spin_lock_init(&shost->free_list_lock);
-	INIT_LIST_HEAD(&shost->free_list);
-
-	shost->cmd_pool = scsi_get_host_cmd_pool(shost);
-	if (!shost->cmd_pool)
-		return -ENOMEM;
-
-	/*
-	 * Get one backup command for this host.
-	 */
-	cmd = scsi_host_alloc_command(shost, gfp_mask);
-	if (!cmd) {
-		scsi_put_host_cmd_pool(shost);
-		shost->cmd_pool = NULL;
-		return -ENOMEM;
-	}
-	list_add(&cmd->list, &shost->free_list);
-	return 0;
-}
-
-/**
- * scsi_destroy_command_freelist - Release the command freelist for a scsi host.
- * @shost: host whose freelist is going to be destroyed
- */
-void scsi_destroy_command_freelist(struct Scsi_Host *shost)
-{
-	/*
-	 * If cmd_pool is NULL the free list was not initialized, so
-	 * do not attempt to release resources.
-	 */
-	if (!shost->cmd_pool)
-		return;
-
-	while (!list_empty(&shost->free_list)) {
-		struct scsi_cmnd *cmd;
-
-		cmd = list_entry(shost->free_list.next, struct scsi_cmnd, list);
-		list_del_init(&cmd->list);
-		scsi_host_free_command(shost, cmd);
-	}
-	shost->cmd_pool = NULL;
-	scsi_put_host_cmd_pool(shost);
 }
 
 #ifdef CONFIG_SCSI_LOGGING
@@ -590,7 +238,7 @@ void scsi_finish_command(struct scsi_cmnd *cmd)
 				"(result %x)\n", cmd->result));
 
 	good_bytes = scsi_bufflen(cmd);
-        if (cmd->request->cmd_type != REQ_TYPE_BLOCK_PC) {
+        if (!blk_rq_is_passthrough(cmd->request)) {
 		int old_good_bytes = good_bytes;
 		drv = scsi_cmd_to_driver(cmd);
 		if (drv->done)
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 03051e12a072..17249c3650fe 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -125,6 +125,7 @@ static const char *sdebug_version_date = "20160430";
 #define DEF_OPTS   0
 #define DEF_OPT_BLKS 1024
 #define DEF_PHYSBLK_EXP 0
+#define DEF_OPT_XFERLEN_EXP 0
 #define DEF_PTYPE   TYPE_DISK
 #define DEF_REMOVABLE false
 #define DEF_SCSI_LEVEL   7    /* INQUIRY, byte2 [6->SPC-4; 7->SPC-5] */
@@ -590,6 +591,7 @@ static int sdebug_num_tgts = DEF_NUM_TGTS; /* targets per host */
 static int sdebug_opt_blks = DEF_OPT_BLKS;
 static int sdebug_opts = DEF_OPTS;
 static int sdebug_physblk_exp = DEF_PHYSBLK_EXP;
+static int sdebug_opt_xferlen_exp = DEF_OPT_XFERLEN_EXP;
 static int sdebug_ptype = DEF_PTYPE; /* SCSI peripheral device type */
 static int sdebug_scsi_level = DEF_SCSI_LEVEL;
 static int sdebug_sector_size = DEF_SECTOR_SIZE;
@@ -1205,7 +1207,11 @@ static int inquiry_vpd_b0(unsigned char *arr)
 	memcpy(arr, vpdb0_data, sizeof(vpdb0_data));
 
 	/* Optimal transfer length granularity */
-	gran = 1 << sdebug_physblk_exp;
+	if (sdebug_opt_xferlen_exp != 0 &&
+	    sdebug_physblk_exp < sdebug_opt_xferlen_exp)
+		gran = 1 << sdebug_opt_xferlen_exp;
+	else
+		gran = 1 << sdebug_physblk_exp;
 	put_unaligned_be16(gran, arr + 2);
 
 	/* Maximum Transfer Length */
@@ -4161,6 +4167,7 @@ module_param_named(num_tgts, sdebug_num_tgts, int, S_IRUGO | S_IWUSR);
 module_param_named(opt_blks, sdebug_opt_blks, int, S_IRUGO);
 module_param_named(opts, sdebug_opts, int, S_IRUGO | S_IWUSR);
 module_param_named(physblk_exp, sdebug_physblk_exp, int, S_IRUGO);
+module_param_named(opt_xferlen_exp, sdebug_opt_xferlen_exp, int, S_IRUGO);
 module_param_named(ptype, sdebug_ptype, int, S_IRUGO | S_IWUSR);
 module_param_named(removable, sdebug_removable, bool, S_IRUGO | S_IWUSR);
 module_param_named(scsi_level, sdebug_scsi_level, int, S_IRUGO);
@@ -4212,6 +4219,7 @@ MODULE_PARM_DESC(num_tgts, "number of targets per host to simulate(def=1)");
 MODULE_PARM_DESC(opt_blks, "optimal transfer length in blocks (def=1024)");
 MODULE_PARM_DESC(opts, "1->noise, 2->medium_err, 4->timeout, 8->recovered_err... (def=0)");
 MODULE_PARM_DESC(physblk_exp, "physical block exponent (def=0)");
+MODULE_PARM_DESC(opt_xferlen_exp, "optimal transfer length granularity exponent (def=physblk_exp)");
 MODULE_PARM_DESC(ptype, "SCSI peripheral type(def=0[disk])");
 MODULE_PARM_DESC(removable, "claim to have removable media (def=0)");
 MODULE_PARM_DESC(scsi_level, "SCSI level to simulate(def=7[SPC-5])");
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 996e134d79fa..f2cafae150bc 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -279,9 +279,7 @@ enum blk_eh_timer_return scsi_times_out(struct request *req)
 	if (host->eh_deadline != -1 && !host->last_reset)
 		host->last_reset = jiffies;
 
-	if (host->transportt->eh_timed_out)
-		rtn = host->transportt->eh_timed_out(scmd);
-	else if (host->hostt->eh_timed_out)
+	if (host->hostt->eh_timed_out)
 		rtn = host->hostt->eh_timed_out(scmd);
 
 	if (rtn == BLK_EH_NOT_HANDLED) {
@@ -1106,7 +1104,7 @@ static int scsi_request_sense(struct scsi_cmnd *scmd)
 
 static int scsi_eh_action(struct scsi_cmnd *scmd, int rtn)
 {
-	if (scmd->request->cmd_type != REQ_TYPE_BLOCK_PC) {
+	if (!blk_rq_is_passthrough(scmd->request)) {
 		struct scsi_driver *sdrv = scsi_cmd_to_driver(scmd);
 		if (sdrv->eh_action)
 			rtn = sdrv->eh_action(scmd, rtn);
@@ -1746,7 +1744,7 @@ check_type:
 	 * the check condition was retryable.
 	 */
 	if (scmd->request->cmd_flags & REQ_FAILFAST_DEV ||
-	    scmd->request->cmd_type == REQ_TYPE_BLOCK_PC)
+	    blk_rq_is_passthrough(scmd->request))
 		return 1;
 	else
 		return 0;
@@ -1968,25 +1966,25 @@ static void eh_lock_door_done(struct request *req, int uptodate)
 static void scsi_eh_lock_door(struct scsi_device *sdev)
 {
 	struct request *req;
+	struct scsi_request *rq;
 
 	/*
 	 * blk_get_request with GFP_KERNEL (__GFP_RECLAIM) sleeps until a
 	 * request becomes available
 	 */
-	req = blk_get_request(sdev->request_queue, READ, GFP_KERNEL);
+	req = blk_get_request(sdev->request_queue, REQ_OP_SCSI_IN, GFP_KERNEL);
 	if (IS_ERR(req))
 		return;
+	rq = scsi_req(req);
+	scsi_req_init(req);
 
-	blk_rq_set_block_pc(req);
-
-	req->cmd[0] = ALLOW_MEDIUM_REMOVAL;
-	req->cmd[1] = 0;
-	req->cmd[2] = 0;
-	req->cmd[3] = 0;
-	req->cmd[4] = SCSI_REMOVAL_PREVENT;
-	req->cmd[5] = 0;
-
-	req->cmd_len = COMMAND_SIZE(req->cmd[0]);
+	rq->cmd[0] = ALLOW_MEDIUM_REMOVAL;
+	rq->cmd[1] = 0;
+	rq->cmd[2] = 0;
+	rq->cmd[3] = 0;
+	rq->cmd[4] = SCSI_REMOVAL_PREVENT;
+	rq->cmd[5] = 0;
+	rq->cmd_len = COMMAND_SIZE(rq->cmd[0]);
 
 	req->rq_flags |= RQF_QUIET;
 	req->timeout = 10 * HZ;
@@ -2331,7 +2329,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
 {
 	struct scsi_cmnd *scmd;
 	struct Scsi_Host *shost = dev->host;
-	struct request req;
+	struct request *rq;
 	unsigned long flags;
 	int error = 0, rtn, val;
 
@@ -2346,14 +2344,16 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
 		return -EIO;
 
 	error = -EIO;
-	scmd = scsi_get_command(dev, GFP_KERNEL);
-	if (!scmd)
+	rq = kzalloc(sizeof(struct request) + sizeof(struct scsi_cmnd) +
+			shost->hostt->cmd_size, GFP_KERNEL);
+	if (!rq)
 		goto out_put_autopm_host;
+	blk_rq_init(NULL, rq);
 
-	blk_rq_init(NULL, &req);
-	scmd->request = &req;
-
-	scmd->cmnd = req.cmd;
+	scmd = (struct scsi_cmnd *)(rq + 1);
+	scsi_init_command(dev, scmd);
+	scmd->request = rq;
+	scmd->cmnd = scsi_req(rq)->cmd;
 
 	scmd->scsi_done		= scsi_reset_provider_done_command;
 	memset(&scmd->sdb, 0, sizeof(scmd->sdb));
@@ -2413,6 +2413,7 @@ scsi_ioctl_reset(struct scsi_device *dev, int __user *arg)
 	scsi_run_host_queues(shost);
 
 	scsi_put_command(scmd);
+	kfree(rq);
 
 out_put_autopm_host:
 	scsi_autopm_put_host(shost);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index e9e1e141af9c..912fbc3b4543 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -37,8 +37,59 @@
 #include "scsi_priv.h"
 #include "scsi_logging.h"
 
+static struct kmem_cache *scsi_sdb_cache;
+static struct kmem_cache *scsi_sense_cache;
+static struct kmem_cache *scsi_sense_isadma_cache;
+static DEFINE_MUTEX(scsi_sense_cache_mutex);
 
-struct kmem_cache *scsi_sdb_cache;
+static inline struct kmem_cache *
+scsi_select_sense_cache(struct Scsi_Host *shost)
+{
+	return shost->unchecked_isa_dma ?
+		scsi_sense_isadma_cache : scsi_sense_cache;
+}
+
+static void scsi_free_sense_buffer(struct Scsi_Host *shost,
+		unsigned char *sense_buffer)
+{
+	kmem_cache_free(scsi_select_sense_cache(shost), sense_buffer);
+}
+
+static unsigned char *scsi_alloc_sense_buffer(struct Scsi_Host *shost,
+	gfp_t gfp_mask, int numa_node)
+{
+	return kmem_cache_alloc_node(scsi_select_sense_cache(shost), gfp_mask,
+			numa_node);
+}
+
+int scsi_init_sense_cache(struct Scsi_Host *shost)
+{
+	struct kmem_cache *cache;
+	int ret = 0;
+
+	cache = scsi_select_sense_cache(shost);
+	if (cache)
+		return 0;
+
+	mutex_lock(&scsi_sense_cache_mutex);
+	if (shost->unchecked_isa_dma) {
+		scsi_sense_isadma_cache =
+			kmem_cache_create("scsi_sense_cache(DMA)",
+			SCSI_SENSE_BUFFERSIZE, 0,
+			SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA, NULL);
+		if (!scsi_sense_isadma_cache)
+			ret = -ENOMEM;
+	} else {
+		scsi_sense_cache =
+			kmem_cache_create("scsi_sense_cache",
+			SCSI_SENSE_BUFFERSIZE, 0, SLAB_HWCACHE_ALIGN, NULL);
+		if (!scsi_sense_cache)
+			ret = -ENOMEM;
+	}
+
+	mutex_unlock(&scsi_sense_cache_mutex);
+	return ret;
+}
 
 /*
  * When to reinvoke queueing after a resource shortage. It's 3 msecs to
@@ -168,22 +219,23 @@ static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 req_flags_t rq_flags, int *resid)
 {
 	struct request *req;
-	int write = (data_direction == DMA_TO_DEVICE);
+	struct scsi_request *rq;
 	int ret = DRIVER_ERROR << 24;
 
-	req = blk_get_request(sdev->request_queue, write, __GFP_RECLAIM);
+	req = blk_get_request(sdev->request_queue,
+			data_direction == DMA_TO_DEVICE ?
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM);
 	if (IS_ERR(req))
 		return ret;
-	blk_rq_set_block_pc(req);
+	rq = scsi_req(req);
+	scsi_req_init(req);
 
 	if (bufflen &&	blk_rq_map_kern(sdev->request_queue, req,
 					buffer, bufflen, __GFP_RECLAIM))
 		goto out;
 
-	req->cmd_len = COMMAND_SIZE(cmd[0]);
-	memcpy(req->cmd, cmd, req->cmd_len);
-	req->sense = sense;
-	req->sense_len = 0;
+	rq->cmd_len = COMMAND_SIZE(cmd[0]);
+	memcpy(rq->cmd, cmd, rq->cmd_len);
 	req->retries = retries;
 	req->timeout = timeout;
 	req->cmd_flags |= flags;
@@ -200,11 +252,13 @@ static int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 	 * is invalid.  Prevent the garbage from being misinterpreted
 	 * and prevent security leaks by zeroing out the excess data.
 	 */
-	if (unlikely(req->resid_len > 0 && req->resid_len <= bufflen))
-		memset(buffer + (bufflen - req->resid_len), 0, req->resid_len);
+	if (unlikely(rq->resid_len > 0 && rq->resid_len <= bufflen))
+		memset(buffer + (bufflen - rq->resid_len), 0, rq->resid_len);
 
 	if (resid)
-		*resid = req->resid_len;
+		*resid = rq->resid_len;
+	if (sense && rq->sense_len)
+		memcpy(sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
 	ret = req->errors;
  out:
 	blk_put_request(req);
@@ -529,7 +583,7 @@ void scsi_run_host_queues(struct Scsi_Host *shost)
 
 static void scsi_uninit_cmd(struct scsi_cmnd *cmd)
 {
-	if (cmd->request->cmd_type == REQ_TYPE_FS) {
+	if (!blk_rq_is_passthrough(cmd->request)) {
 		struct scsi_driver *drv = scsi_cmd_to_driver(cmd);
 
 		if (drv->uninit_command)
@@ -645,14 +699,13 @@ static bool scsi_end_request(struct request *req, int error,
 
 		if (bidi_bytes)
 			scsi_release_bidi_buffers(cmd);
+		scsi_release_buffers(cmd);
+		scsi_put_command(cmd);
 
 		spin_lock_irqsave(q->queue_lock, flags);
 		blk_finish_request(req, error);
 		spin_unlock_irqrestore(q->queue_lock, flags);
 
-		scsi_release_buffers(cmd);
-
-		scsi_put_command(cmd);
 		scsi_run_queue(q);
 	}
 
@@ -754,18 +807,15 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 			sense_deferred = scsi_sense_is_deferred(&sshdr);
 	}
 
-	if (req->cmd_type == REQ_TYPE_BLOCK_PC) { /* SG_IO ioctl from block level */
+	if (blk_rq_is_passthrough(req)) {
 		if (result) {
-			if (sense_valid && req->sense) {
+			if (sense_valid) {
 				/*
 				 * SG_IO wants current and deferred errors
 				 */
-				int len = 8 + cmd->sense_buffer[7];
-
-				if (len > SCSI_SENSE_BUFFERSIZE)
-					len = SCSI_SENSE_BUFFERSIZE;
-				memcpy(req->sense, cmd->sense_buffer,  len);
-				req->sense_len = len;
+				scsi_req(req)->sense_len =
+					min(8 + cmd->sense_buffer[7],
+					    SCSI_SENSE_BUFFERSIZE);
 			}
 			if (!sense_deferred)
 				error = __scsi_error_from_host_byte(cmd, result);
@@ -775,14 +825,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		 */
 		req->errors = cmd->result;
 
-		req->resid_len = scsi_get_resid(cmd);
+		scsi_req(req)->resid_len = scsi_get_resid(cmd);
 
 		if (scsi_bidi_cmnd(cmd)) {
 			/*
 			 * Bidi commands Must be complete as a whole,
 			 * both sides at once.
 			 */
-			req->next_rq->resid_len = scsi_in(cmd)->resid;
+			scsi_req(req->next_rq)->resid_len = scsi_in(cmd)->resid;
 			if (scsi_end_request(req, 0, blk_rq_bytes(req),
 					blk_rq_bytes(req->next_rq)))
 				BUG();
@@ -790,15 +840,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		}
 	} else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) {
 		/*
-		 * Certain non BLOCK_PC requests are commands that don't
-		 * actually transfer anything (FLUSH), so cannot use
+		 * Flush commands do not transfers any data, and thus cannot use
 		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
 		 * This sets the error explicitly for the problem case.
 		 */
 		error = __scsi_error_from_host_byte(cmd, result);
 	}
 
-	/* no bidi support for !REQ_TYPE_BLOCK_PC yet */
+	/* no bidi support for !blk_rq_is_passthrough yet */
 	BUG_ON(blk_bidi_rq(req));
 
 	/*
@@ -810,8 +859,8 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		blk_rq_sectors(req), good_bytes));
 
 	/*
-	 * Recovered errors need reporting, but they're always treated
-	 * as success, so fiddle the result code here.  For BLOCK_PC
+	 * Recovered errors need reporting, but they're always treated as
+	 * success, so fiddle the result code here.  For passthrough requests
 	 * we already took a copy of the original into rq->errors which
 	 * is what gets returned to the user
 	 */
@@ -825,7 +874,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		else if (!(req->rq_flags & RQF_QUIET))
 			scsi_print_sense(cmd);
 		result = 0;
-		/* BLOCK_PC may have set error */
+		/* for passthrough error may be set */
 		error = 0;
 	}
 
@@ -1040,7 +1089,8 @@ int scsi_init_io(struct scsi_cmnd *cmd)
 	bool is_mq = (rq->mq_ctx != NULL);
 	int error;
 
-	BUG_ON(!blk_rq_nr_phys_segments(rq));
+	if (WARN_ON_ONCE(!blk_rq_nr_phys_segments(rq)))
+		return -EINVAL;
 
 	error = scsi_init_sgtable(rq, &cmd->sdb);
 	if (error)
@@ -1109,42 +1159,33 @@ err_exit:
 }
 EXPORT_SYMBOL(scsi_init_io);
 
-static struct scsi_cmnd *scsi_get_cmd_from_req(struct scsi_device *sdev,
-		struct request *req)
+void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd)
 {
-	struct scsi_cmnd *cmd;
-
-	if (!req->special) {
-		/* Bail if we can't get a reference to the device */
-		if (!get_device(&sdev->sdev_gendev))
-			return NULL;
-
-		cmd = scsi_get_command(sdev, GFP_ATOMIC);
-		if (unlikely(!cmd)) {
-			put_device(&sdev->sdev_gendev);
-			return NULL;
-		}
-		req->special = cmd;
-	} else {
-		cmd = req->special;
-	}
+	void *buf = cmd->sense_buffer;
+	void *prot = cmd->prot_sdb;
+	unsigned long flags;
 
-	/* pull a tag out of the request if we have one */
-	cmd->tag = req->tag;
-	cmd->request = req;
+	/* zero out the cmd, except for the embedded scsi_request */
+	memset((char *)cmd + sizeof(cmd->req), 0,
+		sizeof(*cmd) - sizeof(cmd->req));
 
-	cmd->cmnd = req->cmd;
-	cmd->prot_op = SCSI_PROT_NORMAL;
+	cmd->device = dev;
+	cmd->sense_buffer = buf;
+	cmd->prot_sdb = prot;
+	INIT_DELAYED_WORK(&cmd->abort_work, scmd_eh_abort_handler);
+	cmd->jiffies_at_alloc = jiffies;
 
-	return cmd;
+	spin_lock_irqsave(&dev->list_lock, flags);
+	list_add_tail(&cmd->list, &dev->cmd_list);
+	spin_unlock_irqrestore(&dev->list_lock, flags);
 }
 
-static int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req)
+static int scsi_setup_scsi_cmnd(struct scsi_device *sdev, struct request *req)
 {
 	struct scsi_cmnd *cmd = req->special;
 
 	/*
-	 * BLOCK_PC requests may transfer data, in which case they must
+	 * Passthrough requests may transfer data, in which case they must
 	 * a bio attached to them.  Or they might contain a SCSI command
 	 * that does not transfer data, in which case they may optionally
 	 * submit a request without an attached bio.
@@ -1159,14 +1200,15 @@ static int scsi_setup_blk_pc_cmnd(struct scsi_device *sdev, struct request *req)
 		memset(&cmd->sdb, 0, sizeof(cmd->sdb));
 	}
 
-	cmd->cmd_len = req->cmd_len;
+	cmd->cmd_len = scsi_req(req)->cmd_len;
+	cmd->cmnd = scsi_req(req)->cmd;
 	cmd->transfersize = blk_rq_bytes(req);
 	cmd->allowed = req->retries;
 	return BLKPREP_OK;
 }
 
 /*
- * Setup a REQ_TYPE_FS command.  These are simple request from filesystems
+ * Setup a normal block command.  These are simple request from filesystems
  * that still need to be translated to SCSI CDBs from the ULD.
  */
 static int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req)
@@ -1179,6 +1221,7 @@ static int scsi_setup_fs_cmnd(struct scsi_device *sdev, struct request *req)
 			return ret;
 	}
 
+	cmd->cmnd = scsi_req(req)->cmd = scsi_req(req)->__cmd;
 	memset(cmd->cmnd, 0, BLK_MAX_CDB);
 	return scsi_cmd_to_driver(cmd)->init_command(cmd);
 }
@@ -1194,14 +1237,10 @@ static int scsi_setup_cmnd(struct scsi_device *sdev, struct request *req)
 	else
 		cmd->sc_data_direction = DMA_FROM_DEVICE;
 
-	switch (req->cmd_type) {
-	case REQ_TYPE_FS:
+	if (blk_rq_is_scsi(req))
+		return scsi_setup_scsi_cmnd(sdev, req);
+	else
 		return scsi_setup_fs_cmnd(sdev, req);
-	case REQ_TYPE_BLOCK_PC:
-		return scsi_setup_blk_pc_cmnd(sdev, req);
-	default:
-		return BLKPREP_KILL;
-	}
 }
 
 static int
@@ -1297,19 +1336,28 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret)
 static int scsi_prep_fn(struct request_queue *q, struct request *req)
 {
 	struct scsi_device *sdev = q->queuedata;
-	struct scsi_cmnd *cmd;
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
 	int ret;
 
 	ret = scsi_prep_state_check(sdev, req);
 	if (ret != BLKPREP_OK)
 		goto out;
 
-	cmd = scsi_get_cmd_from_req(sdev, req);
-	if (unlikely(!cmd)) {
-		ret = BLKPREP_DEFER;
-		goto out;
+	if (!req->special) {
+		/* Bail if we can't get a reference to the device */
+		if (unlikely(!get_device(&sdev->sdev_gendev))) {
+			ret = BLKPREP_DEFER;
+			goto out;
+		}
+
+		scsi_init_command(sdev, cmd);
+		req->special = cmd;
 	}
 
+	cmd->tag = req->tag;
+	cmd->request = req;
+	cmd->prot_op = SCSI_PROT_NORMAL;
+
 	ret = scsi_setup_cmnd(sdev, req);
 out:
 	return scsi_prep_return(q, req, ret);
@@ -1826,7 +1874,9 @@ static int scsi_mq_prep_fn(struct request *req)
 	unsigned char *sense_buf = cmd->sense_buffer;
 	struct scatterlist *sg;
 
-	memset(cmd, 0, sizeof(struct scsi_cmnd));
+	/* zero out the cmd, except for the embedded scsi_request */
+	memset((char *)cmd + sizeof(cmd->req), 0,
+		sizeof(*cmd) - sizeof(cmd->req));
 
 	req->special = cmd;
 
@@ -1836,7 +1886,6 @@ static int scsi_mq_prep_fn(struct request *req)
 
 	cmd->tag = req->tag;
 
-	cmd->cmnd = req->cmd;
 	cmd->prot_op = SCSI_PROT_NORMAL;
 
 	INIT_LIST_HEAD(&cmd->list);
@@ -1911,7 +1960,6 @@ static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (!scsi_host_queue_ready(q, shost, sdev))
 		goto out_dec_target_busy;
 
-
 	if (!(req->rq_flags & RQF_DONTPREP)) {
 		ret = prep_to_mq(scsi_mq_prep_fn(req));
 		if (ret != BLK_MQ_RQ_QUEUE_OK)
@@ -1981,21 +2029,24 @@ static int scsi_init_request(void *data, struct request *rq,
 		unsigned int hctx_idx, unsigned int request_idx,
 		unsigned int numa_node)
 {
+	struct Scsi_Host *shost = data;
 	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
 
-	cmd->sense_buffer = kzalloc_node(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL,
-			numa_node);
+	cmd->sense_buffer =
+		scsi_alloc_sense_buffer(shost, GFP_KERNEL, numa_node);
 	if (!cmd->sense_buffer)
 		return -ENOMEM;
+	cmd->req.sense = cmd->sense_buffer;
 	return 0;
 }
 
 static void scsi_exit_request(void *data, struct request *rq,
 		unsigned int hctx_idx, unsigned int request_idx)
 {
+	struct Scsi_Host *shost = data;
 	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
 
-	kfree(cmd->sense_buffer);
+	scsi_free_sense_buffer(shost, cmd->sense_buffer);
 }
 
 static int scsi_map_queues(struct blk_mq_tag_set *set)
@@ -2028,7 +2079,7 @@ static u64 scsi_calculate_bounce_limit(struct Scsi_Host *shost)
 	return bounce_limit;
 }
 
-static void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
+void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 {
 	struct device *dev = shost->dma_dev;
 
@@ -2063,28 +2114,64 @@ static void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q)
 	 */
 	blk_queue_dma_alignment(q, 0x03);
 }
+EXPORT_SYMBOL_GPL(__scsi_init_queue);
 
-struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
-					 request_fn_proc *request_fn)
+static int scsi_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
 {
-	struct request_queue *q;
+	struct Scsi_Host *shost = q->rq_alloc_data;
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
 
-	q = blk_init_queue(request_fn, NULL);
-	if (!q)
-		return NULL;
-	__scsi_init_queue(shost, q);
-	return q;
+	memset(cmd, 0, sizeof(*cmd));
+
+	cmd->sense_buffer = scsi_alloc_sense_buffer(shost, gfp, NUMA_NO_NODE);
+	if (!cmd->sense_buffer)
+		goto fail;
+	cmd->req.sense = cmd->sense_buffer;
+
+	if (scsi_host_get_prot(shost) >= SHOST_DIX_TYPE0_PROTECTION) {
+		cmd->prot_sdb = kmem_cache_zalloc(scsi_sdb_cache, gfp);
+		if (!cmd->prot_sdb)
+			goto fail_free_sense;
+	}
+
+	return 0;
+
+fail_free_sense:
+	scsi_free_sense_buffer(shost, cmd->sense_buffer);
+fail:
+	return -ENOMEM;
+}
+
+static void scsi_exit_rq(struct request_queue *q, struct request *rq)
+{
+	struct Scsi_Host *shost = q->rq_alloc_data;
+	struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(rq);
+
+	if (cmd->prot_sdb)
+		kmem_cache_free(scsi_sdb_cache, cmd->prot_sdb);
+	scsi_free_sense_buffer(shost, cmd->sense_buffer);
 }
-EXPORT_SYMBOL(__scsi_alloc_queue);
 
 struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
 {
+	struct Scsi_Host *shost = sdev->host;
 	struct request_queue *q;
 
-	q = __scsi_alloc_queue(sdev->host, scsi_request_fn);
+	q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE);
 	if (!q)
 		return NULL;
+	q->cmd_size = sizeof(struct scsi_cmnd) + shost->hostt->cmd_size;
+	q->rq_alloc_data = shost;
+	q->request_fn = scsi_request_fn;
+	q->init_rq_fn = scsi_init_rq;
+	q->exit_rq_fn = scsi_exit_rq;
+
+	if (blk_init_allocated_queue(q) < 0) {
+		blk_cleanup_queue(q);
+		return NULL;
+	}
 
+	__scsi_init_queue(shost, q);
 	blk_queue_prep_rq(q, scsi_prep_fn);
 	blk_queue_unprep_rq(q, scsi_unprep_fn);
 	blk_queue_softirq_done(q, scsi_softirq_done);
@@ -2208,6 +2295,8 @@ int __init scsi_init_queue(void)
 
 void scsi_exit_queue(void)
 {
+	kmem_cache_destroy(scsi_sense_cache);
+	kmem_cache_destroy(scsi_sense_isadma_cache);
 	kmem_cache_destroy(scsi_sdb_cache);
 }
 
diff --git a/drivers/scsi/scsi_priv.h b/drivers/scsi/scsi_priv.h
index 193636a59adf..99bfc985e190 100644
--- a/drivers/scsi/scsi_priv.h
+++ b/drivers/scsi/scsi_priv.h
@@ -30,8 +30,8 @@ extern void scsi_exit_hosts(void);
 
 /* scsi.c */
 extern bool scsi_use_blk_mq;
-extern int scsi_setup_command_freelist(struct Scsi_Host *shost);
-extern void scsi_destroy_command_freelist(struct Scsi_Host *shost);
+int scsi_init_sense_cache(struct Scsi_Host *shost);
+void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd);
 #ifdef CONFIG_SCSI_LOGGING
 void scsi_log_send(struct scsi_cmnd *cmd);
 void scsi_log_completion(struct scsi_cmnd *cmd, int disposition);
@@ -96,7 +96,6 @@ extern void scsi_exit_queue(void);
 extern void scsi_evt_thread(struct work_struct *work);
 struct request_queue;
 struct request;
-extern struct kmem_cache *scsi_sdb_cache;
 
 /* scsi_proc.c */
 #ifdef CONFIG_SCSI_PROC_FS
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 03577bde6ac5..2d753c93e07a 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -2055,7 +2055,7 @@ static int fc_vport_match(struct attribute_container *cont,
 
 
 /**
- * fc_timed_out - FC Transport I/O timeout intercept handler
+ * fc_eh_timed_out - FC Transport I/O timeout intercept handler
  * @scmd:	The SCSI command which timed out
  *
  * This routine protects against error handlers getting invoked while a
@@ -2076,8 +2076,8 @@ static int fc_vport_match(struct attribute_container *cont,
  * Notes:
  *	This routine assumes no locks are held on entry.
  */
-static enum blk_eh_timer_return
-fc_timed_out(struct scsi_cmnd *scmd)
+enum blk_eh_timer_return
+fc_eh_timed_out(struct scsi_cmnd *scmd)
 {
 	struct fc_rport *rport = starget_to_rport(scsi_target(scmd->device));
 
@@ -2086,6 +2086,7 @@ fc_timed_out(struct scsi_cmnd *scmd)
 
 	return BLK_EH_NOT_HANDLED;
 }
+EXPORT_SYMBOL(fc_eh_timed_out);
 
 /*
  * Called by fc_user_scan to locate an rport on the shost that
@@ -2159,19 +2160,6 @@ fc_user_scan(struct Scsi_Host *shost, uint channel, uint id, u64 lun)
 	return 0;
 }
 
-static int fc_tsk_mgmt_response(struct Scsi_Host *shost, u64 nexus, u64 tm_id,
-				int result)
-{
-	struct fc_internal *i = to_fc_internal(shost->transportt);
-	return i->f->tsk_mgmt_response(shost, nexus, tm_id, result);
-}
-
-static int fc_it_nexus_response(struct Scsi_Host *shost, u64 nexus, int result)
-{
-	struct fc_internal *i = to_fc_internal(shost->transportt);
-	return i->f->it_nexus_response(shost, nexus, result);
-}
-
 struct scsi_transport_template *
 fc_attach_transport(struct fc_function_template *ft)
 {
@@ -2211,14 +2199,8 @@ fc_attach_transport(struct fc_function_template *ft)
 	/* Transport uses the shost workq for scsi scanning */
 	i->t.create_work_queue = 1;
 
-	i->t.eh_timed_out = fc_timed_out;
-
 	i->t.user_scan = fc_user_scan;
 
-	/* target-mode drivers' functions */
-	i->t.tsk_mgmt_response = fc_tsk_mgmt_response;
-	i->t.it_nexus_response = fc_it_nexus_response;
-
 	/*
 	 * Setup SCSI Target Attributes.
 	 */
@@ -3765,7 +3747,6 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host)
 	struct device *dev = &shost->shost_gendev;
 	struct fc_internal *i = to_fc_internal(shost->transportt);
 	struct request_queue *q;
-	int err;
 	char bsg_name[20];
 
 	fc_host->rqst_q = NULL;
@@ -3776,23 +3757,14 @@ fc_bsg_hostadd(struct Scsi_Host *shost, struct fc_host_attrs *fc_host)
 	snprintf(bsg_name, sizeof(bsg_name),
 		 "fc_host%d", shost->host_no);
 
-	q = __scsi_alloc_queue(shost, bsg_request_fn);
-	if (!q) {
-		dev_err(dev,
-			"fc_host%d: bsg interface failed to initialize - no request queue\n",
-			shost->host_no);
-		return -ENOMEM;
-	}
-
-	err = bsg_setup_queue(dev, q, bsg_name, fc_bsg_dispatch,
-				 i->f->dd_bsg_size);
-	if (err) {
+	q = bsg_setup_queue(dev, bsg_name, fc_bsg_dispatch, i->f->dd_bsg_size);
+	if (IS_ERR(q)) {
 		dev_err(dev,
 			"fc_host%d: bsg interface failed to initialize - setup queue\n",
 			shost->host_no);
-		blk_cleanup_queue(q);
-		return err;
+		return PTR_ERR(q);
 	}
+	__scsi_init_queue(shost, q);
 	blk_queue_rq_timed_out(q, fc_bsg_job_timeout);
 	blk_queue_rq_timeout(q, FC_DEFAULT_BSG_TIMEOUT);
 	fc_host->rqst_q = q;
@@ -3824,26 +3796,18 @@ fc_bsg_rportadd(struct Scsi_Host *shost, struct fc_rport *rport)
 	struct device *dev = &rport->dev;
 	struct fc_internal *i = to_fc_internal(shost->transportt);
 	struct request_queue *q;
-	int err;
 
 	rport->rqst_q = NULL;
 
 	if (!i->f->bsg_request)
 		return -ENOTSUPP;
 
-	q = __scsi_alloc_queue(shost, bsg_request_fn);
-	if (!q) {
-		dev_err(dev, "bsg interface failed to initialize - no request queue\n");
-		return -ENOMEM;
-	}
-
-	err = bsg_setup_queue(dev, q, NULL, fc_bsg_dispatch, i->f->dd_bsg_size);
-	if (err) {
+	q = bsg_setup_queue(dev, NULL, fc_bsg_dispatch, i->f->dd_bsg_size);
+	if (IS_ERR(q)) {
 		dev_err(dev, "failed to setup bsg queue\n");
-		blk_cleanup_queue(q);
-		return err;
+		return PTR_ERR(q);
 	}
-
+	__scsi_init_queue(shost, q);
 	blk_queue_prep_rq(q, fc_bsg_rport_prep);
 	blk_queue_rq_timed_out(q, fc_bsg_job_timeout);
 	blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 42bca619f854..568c9f26a561 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1537,24 +1537,18 @@ iscsi_bsg_host_add(struct Scsi_Host *shost, struct iscsi_cls_host *ihost)
 	struct iscsi_internal *i = to_iscsi_internal(shost->transportt);
 	struct request_queue *q;
 	char bsg_name[20];
-	int ret;
 
 	if (!i->iscsi_transport->bsg_request)
 		return -ENOTSUPP;
 
 	snprintf(bsg_name, sizeof(bsg_name), "iscsi_host%d", shost->host_no);
-
-	q = __scsi_alloc_queue(shost, bsg_request_fn);
-	if (!q)
-		return -ENOMEM;
-
-	ret = bsg_setup_queue(dev, q, bsg_name, iscsi_bsg_host_dispatch, 0);
-	if (ret) {
+	q = bsg_setup_queue(dev, bsg_name, iscsi_bsg_host_dispatch, 0);
+	if (IS_ERR(q)) {
 		shost_printk(KERN_ERR, shost, "bsg interface failed to "
 			     "initialize - no request queue\n");
-		blk_cleanup_queue(q);
-		return ret;
+		return PTR_ERR(q);
 	}
+	__scsi_init_queue(shost, q);
 
 	ihost->bsg_q = q;
 	return 0;
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 60b651bfaa01..126a5ee00987 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -33,6 +33,7 @@
 #include <linux/bsg.h>
 
 #include <scsi/scsi.h>
+#include <scsi/scsi_request.h>
 #include <scsi/scsi_device.h>
 #include <scsi/scsi_host.h>
 #include <scsi/scsi_transport.h>
@@ -177,6 +178,10 @@ static void sas_smp_request(struct request_queue *q, struct Scsi_Host *shost,
 	while ((req = blk_fetch_request(q)) != NULL) {
 		spin_unlock_irq(q->queue_lock);
 
+		scsi_req(req)->resid_len = blk_rq_bytes(req);
+		if (req->next_rq)
+			scsi_req(req->next_rq)->resid_len =
+				blk_rq_bytes(req->next_rq);
 		handler = to_sas_internal(shost->transportt)->f->smp_handler;
 		ret = handler(shost, rphy, req);
 		req->errors = ret;
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index b87a78673f65..3c5d89852e9f 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -591,7 +591,7 @@ EXPORT_SYMBOL(srp_reconnect_rport);
  * Note: This function is called from soft-IRQ context and with the request
  * queue lock held.
  */
-static enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd)
+enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd)
 {
 	struct scsi_device *sdev = scmd->device;
 	struct Scsi_Host *shost = sdev->host;
@@ -603,6 +603,7 @@ static enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd)
 		i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ?
 		BLK_EH_RESET_TIMER : BLK_EH_NOT_HANDLED;
 }
+EXPORT_SYMBOL(srp_timed_out);
 
 static void srp_rport_release(struct device *dev)
 {
@@ -793,19 +794,6 @@ void srp_stop_rport_timers(struct srp_rport *rport)
 }
 EXPORT_SYMBOL_GPL(srp_stop_rport_timers);
 
-static int srp_tsk_mgmt_response(struct Scsi_Host *shost, u64 nexus, u64 tm_id,
-				 int result)
-{
-	struct srp_internal *i = to_srp_internal(shost->transportt);
-	return i->f->tsk_mgmt_response(shost, nexus, tm_id, result);
-}
-
-static int srp_it_nexus_response(struct Scsi_Host *shost, u64 nexus, int result)
-{
-	struct srp_internal *i = to_srp_internal(shost->transportt);
-	return i->f->it_nexus_response(shost, nexus, result);
-}
-
 /**
  * srp_attach_transport  -  instantiate SRP transport template
  * @ft:		SRP transport class function template
@@ -820,11 +808,6 @@ srp_attach_transport(struct srp_function_template *ft)
 	if (!i)
 		return NULL;
 
-	i->t.eh_timed_out = srp_timed_out;
-
-	i->t.tsk_mgmt_response = srp_tsk_mgmt_response;
-	i->t.it_nexus_response = srp_it_nexus_response;
-
 	i->t.host_size = sizeof(struct srp_host_attrs);
 	i->t.host_attrs.ac.attrs = &i->host_attrs[0];
 	i->t.host_attrs.ac.class = &srp_host_class.class;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 0b09638fa39b..cb6e68dd6df0 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -703,7 +703,7 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 
 /**
  * sd_setup_discard_cmnd - unmap blocks on thinly provisioned device
- * @sdp: scsi device to operate one
+ * @sdp: scsi device to operate on
  * @rq: Request to prepare
  *
  * Will issue either UNMAP or WRITE SAME(16) depending on preference
@@ -781,7 +781,7 @@ static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
 	rq->special_vec.bv_len = len;
 
 	rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
-	rq->resid_len = len;
+	scsi_req(rq)->resid_len = len;
 
 	ret = scsi_init_io(cmd);
 out:
@@ -836,6 +836,7 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 	struct bio *bio = rq->bio;
 	sector_t sector = blk_rq_pos(rq);
 	unsigned int nr_sectors = blk_rq_sectors(rq);
+	unsigned int nr_bytes = blk_rq_bytes(rq);
 	int ret;
 
 	if (sdkp->device->no_write_same)
@@ -868,7 +869,21 @@ static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd)
 
 	cmd->transfersize = sdp->sector_size;
 	cmd->allowed = SD_MAX_RETRIES;
-	return scsi_init_io(cmd);
+
+	/*
+	 * For WRITE SAME the data transferred via the DATA OUT buffer is
+	 * different from the amount of data actually written to the target.
+	 *
+	 * We set up __data_len to the amount of data transferred via the
+	 * DATA OUT buffer so that blk_rq_map_sg sets up the proper S/G list
+	 * to transfer a single sector of data first, but then reset it to
+	 * the amount of data to be written right after so that the I/O path
+	 * knows how much to actually write.
+	 */
+	rq->__data_len = sdp->sector_size;
+	ret = scsi_init_io(cmd);
+	rq->__data_len = nr_bytes;
+	return ret;
 }
 
 static int sd_setup_flush_cmnd(struct scsi_cmnd *cmd)
@@ -1164,7 +1179,7 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt)
 	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
 		__free_page(rq->special_vec.bv_page);
 
-	if (SCpnt->cmnd != rq->cmd) {
+	if (SCpnt->cmnd != scsi_req(rq)->cmd) {
 		mempool_free(SCpnt->cmnd, sd_cdb_pool);
 		SCpnt->cmnd = NULL;
 		SCpnt->cmd_len = 0;
@@ -1735,9 +1750,6 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd)
 	unsigned int transferred = scsi_bufflen(scmd) - scsi_get_resid(scmd);
 	unsigned int good_bytes;
 
-	if (scmd->request->cmd_type != REQ_TYPE_FS)
-		return 0;
-
 	info_valid = scsi_get_sense_info_fld(scmd->sense_buffer,
 					     SCSI_SENSE_BUFFERSIZE,
 					     &bad_lba);
@@ -3067,6 +3079,23 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
 	put_device(&sdkp->dev);
 }
 
+struct sd_devt {
+	int idx;
+	struct disk_devt disk_devt;
+};
+
+void sd_devt_release(struct disk_devt *disk_devt)
+{
+	struct sd_devt *sd_devt = container_of(disk_devt, struct sd_devt,
+			disk_devt);
+
+	spin_lock(&sd_index_lock);
+	ida_remove(&sd_index_ida, sd_devt->idx);
+	spin_unlock(&sd_index_lock);
+
+	kfree(sd_devt);
+}
+
 /**
  *	sd_probe - called during driver initialization and whenever a
  *	new scsi device is attached to the system. It is called once
@@ -3088,6 +3117,7 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
 static int sd_probe(struct device *dev)
 {
 	struct scsi_device *sdp = to_scsi_device(dev);
+	struct sd_devt *sd_devt;
 	struct scsi_disk *sdkp;
 	struct gendisk *gd;
 	int index;
@@ -3113,9 +3143,13 @@ static int sd_probe(struct device *dev)
 	if (!sdkp)
 		goto out;
 
+	sd_devt = kzalloc(sizeof(*sd_devt), GFP_KERNEL);
+	if (!sd_devt)
+		goto out_free;
+
 	gd = alloc_disk(SD_MINORS);
 	if (!gd)
-		goto out_free;
+		goto out_free_devt;
 
 	do {
 		if (!ida_pre_get(&sd_index_ida, GFP_KERNEL))
@@ -3131,6 +3165,11 @@ static int sd_probe(struct device *dev)
 		goto out_put;
 	}
 
+	atomic_set(&sd_devt->disk_devt.count, 1);
+	sd_devt->disk_devt.release = sd_devt_release;
+	sd_devt->idx = index;
+	gd->disk_devt = &sd_devt->disk_devt;
+
 	error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN);
 	if (error) {
 		sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n");
@@ -3170,13 +3209,14 @@ static int sd_probe(struct device *dev)
 	return 0;
 
  out_free_index:
-	spin_lock(&sd_index_lock);
-	ida_remove(&sd_index_ida, index);
-	spin_unlock(&sd_index_lock);
+	put_disk_devt(&sd_devt->disk_devt);
+	sd_devt = NULL;
  out_put:
 	put_disk(gd);
  out_free:
 	kfree(sdkp);
+ out_free_devt:
+	kfree(sd_devt);
  out:
 	scsi_autopm_put_device(sdp);
 	return error;
@@ -3186,7 +3226,7 @@ static int sd_probe(struct device *dev)
  *	sd_remove - called whenever a scsi disk (previously recognized by
  *	sd_probe) is detached from the system. It is called (potentially
  *	multiple times) during sd module unload.
- *	@sdp: pointer to mid level scsi device object
+ *	@dev: pointer to device object
  *
  *	Note: this function is invoked from the scsi mid-level.
  *	This function potentially frees up a device name (e.g. /dev/sdc)
@@ -3235,10 +3275,7 @@ static void scsi_disk_release(struct device *dev)
 	struct scsi_disk *sdkp = to_scsi_disk(dev);
 	struct gendisk *disk = sdkp->disk;
 	
-	spin_lock(&sd_index_lock);
-	ida_remove(&sd_index_ida, sdkp->index);
-	spin_unlock(&sd_index_lock);
-
+	put_disk_devt(disk->disk_devt);
 	disk->private_data = NULL;
 	put_disk(disk);
 	put_device(&sdkp->device->sdev_gendev);
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index dbe5b4b95df0..e831e01f9fa6 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -781,9 +781,7 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp,
 	}
 	if (atomic_read(&sdp->detaching)) {
 		if (srp->bio) {
-			if (srp->rq->cmd != srp->rq->__cmd)
-				kfree(srp->rq->cmd);
-
+			scsi_req_free_cmd(scsi_req(srp->rq));
 			blk_end_request_all(srp->rq, -EIO);
 			srp->rq = NULL;
 		}
@@ -1279,6 +1277,7 @@ static void
 sg_rq_end_io(struct request *rq, int uptodate)
 {
 	struct sg_request *srp = rq->end_io_data;
+	struct scsi_request *req = scsi_req(rq);
 	Sg_device *sdp;
 	Sg_fd *sfp;
 	unsigned long iflags;
@@ -1297,9 +1296,9 @@ sg_rq_end_io(struct request *rq, int uptodate)
 	if (unlikely(atomic_read(&sdp->detaching)))
 		pr_info("%s: device detaching\n", __func__);
 
-	sense = rq->sense;
+	sense = req->sense;
 	result = rq->errors;
-	resid = rq->resid_len;
+	resid = req->resid_len;
 
 	SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp,
 				      "sg_cmd_done: pack_id=%d, res=0x%x\n",
@@ -1333,6 +1332,10 @@ sg_rq_end_io(struct request *rq, int uptodate)
 			sdp->device->changed = 1;
 		}
 	}
+
+	if (req->sense_len)
+		memcpy(srp->sense_b, req->sense, SCSI_SENSE_BUFFERSIZE);
+
 	/* Rely on write phase to clean out srp status values, so no "else" */
 
 	/*
@@ -1342,8 +1345,7 @@ sg_rq_end_io(struct request *rq, int uptodate)
 	 * blk_rq_unmap_user() can be called from user context.
 	 */
 	srp->rq = NULL;
-	if (rq->cmd != rq->__cmd)
-		kfree(rq->cmd);
+	scsi_req_free_cmd(scsi_req(rq));
 	__blk_put_request(rq->q, rq);
 
 	write_lock_irqsave(&sfp->rq_list_lock, iflags);
@@ -1658,6 +1660,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 {
 	int res;
 	struct request *rq;
+	struct scsi_request *req;
 	Sg_fd *sfp = srp->parentfp;
 	sg_io_hdr_t *hp = &srp->header;
 	int dxfer_len = (int) hp->dxfer_len;
@@ -1695,22 +1698,23 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 	 * With scsi-mq disabled, blk_get_request() with GFP_KERNEL usually
 	 * does not sleep except under memory pressure.
 	 */
-	rq = blk_get_request(q, rw, GFP_KERNEL);
+	rq = blk_get_request(q, hp->dxfer_direction == SG_DXFER_TO_DEV ?
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL);
 	if (IS_ERR(rq)) {
 		kfree(long_cmdp);
 		return PTR_ERR(rq);
 	}
+	req = scsi_req(rq);
 
-	blk_rq_set_block_pc(rq);
+	scsi_req_init(rq);
 
 	if (hp->cmd_len > BLK_MAX_CDB)
-		rq->cmd = long_cmdp;
-	memcpy(rq->cmd, cmd, hp->cmd_len);
-	rq->cmd_len = hp->cmd_len;
+		req->cmd = long_cmdp;
+	memcpy(req->cmd, cmd, hp->cmd_len);
+	req->cmd_len = hp->cmd_len;
 
 	srp->rq = rq;
 	rq->end_io_data = srp;
-	rq->sense = srp->sense_b;
 	rq->retries = SG_DEFAULT_RETRIES;
 
 	if ((dxfer_len <= 0) || (dxfer_dir == SG_DXFER_NONE))
@@ -1753,6 +1757,10 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
 			return res;
 
 		iov_iter_truncate(&i, hp->dxfer_len);
+		if (!iov_iter_count(&i)) {
+			kfree(iov);
+			return -EINVAL;
+		}
 
 		res = blk_rq_map_user_iov(q, rq, md, &i, GFP_ATOMIC);
 		kfree(iov);
@@ -1786,8 +1794,7 @@ sg_finish_rem_req(Sg_request *srp)
 		ret = blk_rq_unmap_user(srp->bio);
 
 	if (srp->rq) {
-		if (srp->rq->cmd != srp->rq->__cmd)
-			kfree(srp->rq->cmd);
+		scsi_req_free_cmd(scsi_req(srp->rq));
 		blk_put_request(srp->rq);
 	}
 
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 8702d9cf8040..11c0dfb3dfa3 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -4499,7 +4499,7 @@ static int pqi_scsi_queue_command(struct Scsi_Host *shost,
 	if (pqi_is_logical_device(device)) {
 		raid_bypassed = false;
 		if (device->offload_enabled &&
-			scmd->request->cmd_type == REQ_TYPE_FS) {
+				!blk_rq_is_passthrough(scmd->request)) {
 			rc = pqi_raid_bypass_submit_scsi_cmd(ctrl_info, device,
 				scmd, queue_group);
 			if (rc == 0 ||
diff --git a/drivers/scsi/snic/snic.h b/drivers/scsi/snic/snic.h
index 8ed778d4dbb9..de0ab5fc8474 100644
--- a/drivers/scsi/snic/snic.h
+++ b/drivers/scsi/snic/snic.h
@@ -299,7 +299,6 @@ struct snic {
 
 	/* pci related */
 	struct pci_dev *pdev;
-	struct msix_entry msix_entry[SNIC_MSIX_INTR_MAX];
 	struct snic_msix_entry msix[SNIC_MSIX_INTR_MAX];
 
 	/* io related info */
diff --git a/drivers/scsi/snic/snic_isr.c b/drivers/scsi/snic/snic_isr.c
index f552003128c6..d859501e4ccd 100644
--- a/drivers/scsi/snic/snic_isr.c
+++ b/drivers/scsi/snic/snic_isr.c
@@ -93,7 +93,7 @@ snic_free_intr(struct snic *snic)
 	/* ONLY interrupt mode MSIX is supported */
 	for (i = 0; i < ARRAY_SIZE(snic->msix); i++) {
 		if (snic->msix[i].requested) {
-			free_irq(snic->msix_entry[i].vector,
+			free_irq(pci_irq_vector(snic->pdev, i),
 				 snic->msix[i].devid);
 		}
 	}
@@ -134,7 +134,7 @@ snic_request_intr(struct snic *snic)
 	snic->msix[SNIC_MSIX_ERR_NOTIFY].devid = snic;
 
 	for (i = 0; i < ARRAY_SIZE(snic->msix); i++) {
-		ret = request_irq(snic->msix_entry[i].vector,
+		ret = request_irq(pci_irq_vector(snic->pdev, i),
 				  snic->msix[i].isr,
 				  0,
 				  snic->msix[i].devname,
@@ -158,47 +158,37 @@ snic_set_intr_mode(struct snic *snic)
 {
 	unsigned int n = ARRAY_SIZE(snic->wq);
 	unsigned int m = SNIC_CQ_IO_CMPL_MAX;
-	unsigned int i;
+	unsigned int vecs = n + m + 1;
 
 	/*
 	 * We need n WQs, m CQs, and n+m+1 INTRs
 	 * (last INTR is used for WQ/CQ errors and notification area
 	 */
-
 	BUILD_BUG_ON((ARRAY_SIZE(snic->wq) + SNIC_CQ_IO_CMPL_MAX) >
 			ARRAY_SIZE(snic->intr));
-	SNIC_BUG_ON(ARRAY_SIZE(snic->msix_entry) < (n + m + 1));
-
-	for (i = 0; i < (n + m + 1); i++)
-		snic->msix_entry[i].entry = i;
-
-	if (snic->wq_count >= n && snic->cq_count >= (n + m)) {
-		if (!pci_enable_msix(snic->pdev,
-				     snic->msix_entry,
-				     (n + m + 1))) {
-			snic->wq_count = n;
-			snic->cq_count = n + m;
-			snic->intr_count = n + m + 1;
-			snic->err_intr_offset = SNIC_MSIX_ERR_NOTIFY;
-
-			SNIC_ISR_DBG(snic->shost,
-				     "Using MSI-X Interrupts\n");
-			svnic_dev_set_intr_mode(snic->vdev,
-						VNIC_DEV_INTR_MODE_MSIX);
-
-			return 0;
-		}
-	}
 
-	svnic_dev_set_intr_mode(snic->vdev, VNIC_DEV_INTR_MODE_UNKNOWN);
+	if (snic->wq_count < n || snic->cq_count < n + m)
+		goto fail;
 
+	if (pci_alloc_irq_vectors(snic->pdev, vecs, vecs, PCI_IRQ_MSIX) < 0)
+		goto fail;
+
+	snic->wq_count = n;
+	snic->cq_count = n + m;
+	snic->intr_count = vecs;
+	snic->err_intr_offset = SNIC_MSIX_ERR_NOTIFY;
+
+	SNIC_ISR_DBG(snic->shost, "Using MSI-X Interrupts\n");
+	svnic_dev_set_intr_mode(snic->vdev, VNIC_DEV_INTR_MODE_MSIX);
+	return 0;
+fail:
+	svnic_dev_set_intr_mode(snic->vdev, VNIC_DEV_INTR_MODE_UNKNOWN);
 	return -EINVAL;
 } /* end of snic_set_intr_mode */
 
 void
 snic_clear_intr_mode(struct snic *snic)
 {
-	pci_disable_msix(snic->pdev);
-
+	pci_free_irq_vectors(snic->pdev);
 	svnic_dev_set_intr_mode(snic->vdev, VNIC_DEV_INTR_MODE_INTX);
 }
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 94352e4df831..0b29b9329b1c 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -117,7 +117,7 @@ static unsigned int sr_check_events(struct cdrom_device_info *cdi,
 				    unsigned int clearing, int slot);
 static int sr_packet(struct cdrom_device_info *, struct packet_command *);
 
-static struct cdrom_device_ops sr_dops = {
+static const struct cdrom_device_ops sr_dops = {
 	.open			= sr_open,
 	.release	 	= sr_release,
 	.drive_status	 	= sr_drive_status,
@@ -437,14 +437,17 @@ static int sr_init_command(struct scsi_cmnd *SCpnt)
 		goto out;
 	}
 
-	if (rq_data_dir(rq) == WRITE) {
+	switch (req_op(rq)) {
+	case REQ_OP_WRITE:
 		if (!cd->writeable)
 			goto out;
 		SCpnt->cmnd[0] = WRITE_10;
 		cd->cdi.media_written = 1;
-	} else if (rq_data_dir(rq) == READ) {
+		break;
+	case REQ_OP_READ:
 		SCpnt->cmnd[0] = READ_10;
-	} else {
+		break;
+	default:
 		blk_dump_rq_flags(rq, "Unknown sr command");
 		goto out;
 	}
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 5f35b863e1a7..81212d4bd9bf 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -475,7 +475,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
 	ktime_t now;
 
 	now = ktime_get();
-	if (req->cmd[0] == WRITE_6) {
+	if (scsi_req(req)->cmd[0] == WRITE_6) {
 		now = ktime_sub(now, STp->stats->write_time);
 		atomic64_add(ktime_to_ns(now), &STp->stats->tot_write_time);
 		atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time);
@@ -489,7 +489,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
 		} else
 			atomic64_add(atomic_read(&STp->stats->last_write_size),
 				&STp->stats->write_byte_cnt);
-	} else if (req->cmd[0] == READ_6) {
+	} else if (scsi_req(req)->cmd[0] == READ_6) {
 		now = ktime_sub(now, STp->stats->read_time);
 		atomic64_add(ktime_to_ns(now), &STp->stats->tot_read_time);
 		atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time);
@@ -514,15 +514,18 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
 static void st_scsi_execute_end(struct request *req, int uptodate)
 {
 	struct st_request *SRpnt = req->end_io_data;
+	struct scsi_request *rq = scsi_req(req);
 	struct scsi_tape *STp = SRpnt->stp;
 	struct bio *tmp;
 
 	STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors;
-	STp->buffer->cmdstat.residual = req->resid_len;
+	STp->buffer->cmdstat.residual = rq->resid_len;
 
 	st_do_stats(STp, req);
 
 	tmp = SRpnt->bio;
+	if (rq->sense_len)
+		memcpy(SRpnt->sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
 	if (SRpnt->waiting)
 		complete(SRpnt->waiting);
 
@@ -535,17 +538,18 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
 			   int timeout, int retries)
 {
 	struct request *req;
+	struct scsi_request *rq;
 	struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data;
 	int err = 0;
-	int write = (data_direction == DMA_TO_DEVICE);
 	struct scsi_tape *STp = SRpnt->stp;
 
-	req = blk_get_request(SRpnt->stp->device->request_queue, write,
-			      GFP_KERNEL);
+	req = blk_get_request(SRpnt->stp->device->request_queue,
+			data_direction == DMA_TO_DEVICE ?
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, GFP_KERNEL);
 	if (IS_ERR(req))
 		return DRIVER_ERROR << 24;
-
-	blk_rq_set_block_pc(req);
+	rq = scsi_req(req);
+	scsi_req_init(req);
 	req->rq_flags |= RQF_QUIET;
 
 	mdata->null_mapped = 1;
@@ -571,11 +575,9 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
 	}
 
 	SRpnt->bio = req->bio;
-	req->cmd_len = COMMAND_SIZE(cmd[0]);
-	memset(req->cmd, 0, BLK_MAX_CDB);
-	memcpy(req->cmd, cmd, req->cmd_len);
-	req->sense = SRpnt->sense;
-	req->sense_len = 0;
+	rq->cmd_len = COMMAND_SIZE(cmd[0]);
+	memset(rq->cmd, 0, BLK_MAX_CDB);
+	memcpy(rq->cmd, cmd, rq->cmd_len);
 	req->timeout = timeout;
 	req->retries = retries;
 	req->end_io_data = SRpnt;
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 05526b71541b..585e54f6512c 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -136,6 +136,8 @@ struct hv_fc_wwn_packet {
 #define SRB_FLAGS_PORT_DRIVER_RESERVED		0x0F000000
 #define SRB_FLAGS_CLASS_DRIVER_RESERVED		0xF0000000
 
+#define SP_UNTAGGED			((unsigned char) ~0)
+#define SRB_SIMPLE_TAG_REQUEST		0x20
 
 /*
  * Platform neutral description of a scsi request -
@@ -375,6 +377,7 @@ enum storvsc_request_type {
 #define SRB_STATUS_SUCCESS	0x01
 #define SRB_STATUS_ABORTED	0x02
 #define SRB_STATUS_ERROR	0x04
+#define SRB_STATUS_DATA_OVERRUN	0x12
 
 #define SRB_STATUS(status) \
 	(status & ~(SRB_STATUS_AUTOSENSE_VALID | SRB_STATUS_QUEUE_FROZEN))
@@ -458,6 +461,15 @@ struct storvsc_device {
 	 * Max I/O, the device can support.
 	 */
 	u32   max_transfer_bytes;
+	/*
+	 * Number of sub-channels we will open.
+	 */
+	u16 num_sc;
+	struct vmbus_channel **stor_chns;
+	/*
+	 * Mask of CPUs bound to subchannels.
+	 */
+	struct cpumask alloced_cpus;
 	/* Used for vsc/vsp channel reset process */
 	struct storvsc_cmd_request init_request;
 	struct storvsc_cmd_request reset_request;
@@ -635,6 +647,11 @@ static void handle_sc_creation(struct vmbus_channel *new_sc)
 		   (void *)&props,
 		   sizeof(struct vmstorage_channel_properties),
 		   storvsc_on_channel_callback, new_sc);
+
+	if (new_sc->state == CHANNEL_OPENED_STATE) {
+		stor_device->stor_chns[new_sc->target_cpu] = new_sc;
+		cpumask_set_cpu(new_sc->target_cpu, &stor_device->alloced_cpus);
+	}
 }
 
 static void  handle_multichannel_storage(struct hv_device *device, int max_chns)
@@ -651,6 +668,7 @@ static void  handle_multichannel_storage(struct hv_device *device, int max_chns)
 	if (!stor_device)
 		return;
 
+	stor_device->num_sc = num_sc;
 	request = &stor_device->init_request;
 	vstor_packet = &request->vstor_packet;
 
@@ -838,6 +856,25 @@ static int storvsc_channel_init(struct hv_device *device, bool is_fc)
 	 * support multi-channel.
 	 */
 	max_chns = vstor_packet->storage_channel_properties.max_channel_cnt;
+
+	/*
+	 * Allocate state to manage the sub-channels.
+	 * We allocate an array based on the numbers of possible CPUs
+	 * (Hyper-V does not support cpu online/offline).
+	 * This Array will be sparseley populated with unique
+	 * channels - primary + sub-channels.
+	 * We will however populate all the slots to evenly distribute
+	 * the load.
+	 */
+	stor_device->stor_chns = kzalloc(sizeof(void *) * num_possible_cpus(),
+					 GFP_KERNEL);
+	if (stor_device->stor_chns == NULL)
+		return -ENOMEM;
+
+	stor_device->stor_chns[device->channel->target_cpu] = device->channel;
+	cpumask_set_cpu(device->channel->target_cpu,
+			&stor_device->alloced_cpus);
+
 	if (vmstor_proto_version >= VMSTOR_PROTO_VERSION_WIN8) {
 		if (vstor_packet->storage_channel_properties.flags &
 		    STORAGE_CHANNEL_SUPPORTS_MULTI_CHANNEL)
@@ -889,6 +926,13 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb,
 	switch (SRB_STATUS(vm_srb->srb_status)) {
 	case SRB_STATUS_ERROR:
 		/*
+		 * Let upper layer deal with error when
+		 * sense message is present.
+		 */
+
+		if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID)
+			break;
+		/*
 		 * If there is an error; offline the device since all
 		 * error recovery strategies would have already been
 		 * deployed on the host side. However, if the command
@@ -953,6 +997,7 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request,
 	struct scsi_cmnd *scmnd = cmd_request->cmd;
 	struct scsi_sense_hdr sense_hdr;
 	struct vmscsi_request *vm_srb;
+	u32 data_transfer_length;
 	struct Scsi_Host *host;
 	u32 payload_sz = cmd_request->payload_sz;
 	void *payload = cmd_request->payload;
@@ -960,6 +1005,7 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request,
 	host = stor_dev->host;
 
 	vm_srb = &cmd_request->vstor_packet.vm_srb;
+	data_transfer_length = vm_srb->data_transfer_length;
 
 	scmnd->result = vm_srb->scsi_status;
 
@@ -973,13 +1019,20 @@ static void storvsc_command_completion(struct storvsc_cmd_request *cmd_request,
 					     &sense_hdr);
 	}
 
-	if (vm_srb->srb_status != SRB_STATUS_SUCCESS)
+	if (vm_srb->srb_status != SRB_STATUS_SUCCESS) {
 		storvsc_handle_error(vm_srb, scmnd, host, sense_hdr.asc,
 					 sense_hdr.ascq);
+		/*
+		 * The Windows driver set data_transfer_length on
+		 * SRB_STATUS_DATA_OVERRUN. On other errors, this value
+		 * is untouched.  In these cases we set it to 0.
+		 */
+		if (vm_srb->srb_status != SRB_STATUS_DATA_OVERRUN)
+			data_transfer_length = 0;
+	}
 
 	scsi_set_resid(scmnd,
-		cmd_request->payload->range.len -
-		vm_srb->data_transfer_length);
+		cmd_request->payload->range.len - data_transfer_length);
 
 	scmnd->scsi_done(scmnd);
 
@@ -1198,17 +1251,64 @@ static int storvsc_dev_remove(struct hv_device *device)
 	/* Close the channel */
 	vmbus_close(device->channel);
 
+	kfree(stor_device->stor_chns);
 	kfree(stor_device);
 	return 0;
 }
 
+static struct vmbus_channel *get_og_chn(struct storvsc_device *stor_device,
+					u16 q_num)
+{
+	u16 slot = 0;
+	u16 hash_qnum;
+	struct cpumask alloced_mask;
+	int num_channels, tgt_cpu;
+
+	if (stor_device->num_sc == 0)
+		return stor_device->device->channel;
+
+	/*
+	 * Our channel array is sparsley populated and we
+	 * initiated I/O on a processor/hw-q that does not
+	 * currently have a designated channel. Fix this.
+	 * The strategy is simple:
+	 * I. Ensure NUMA locality
+	 * II. Distribute evenly (best effort)
+	 * III. Mapping is persistent.
+	 */
+
+	cpumask_and(&alloced_mask, &stor_device->alloced_cpus,
+		    cpumask_of_node(cpu_to_node(q_num)));
+
+	num_channels = cpumask_weight(&alloced_mask);
+	if (num_channels == 0)
+		return stor_device->device->channel;
+
+	hash_qnum = q_num;
+	while (hash_qnum >= num_channels)
+		hash_qnum -= num_channels;
+
+	for_each_cpu(tgt_cpu, &alloced_mask) {
+		if (slot == hash_qnum)
+			break;
+		slot++;
+	}
+
+	stor_device->stor_chns[q_num] = stor_device->stor_chns[tgt_cpu];
+
+	return stor_device->stor_chns[q_num];
+}
+
+
 static int storvsc_do_io(struct hv_device *device,
-			 struct storvsc_cmd_request *request)
+			 struct storvsc_cmd_request *request, u16 q_num)
 {
 	struct storvsc_device *stor_device;
 	struct vstor_packet *vstor_packet;
 	struct vmbus_channel *outgoing_channel;
 	int ret = 0;
+	struct cpumask alloced_mask;
+	int tgt_cpu;
 
 	vstor_packet = &request->vstor_packet;
 	stor_device = get_out_stor_device(device);
@@ -1222,7 +1322,26 @@ static int storvsc_do_io(struct hv_device *device,
 	 * Select an an appropriate channel to send the request out.
 	 */
 
-	outgoing_channel = vmbus_get_outgoing_channel(device->channel);
+	if (stor_device->stor_chns[q_num] != NULL) {
+		outgoing_channel = stor_device->stor_chns[q_num];
+		if (outgoing_channel->target_cpu == smp_processor_id()) {
+			/*
+			 * Ideally, we want to pick a different channel if
+			 * available on the same NUMA node.
+			 */
+			cpumask_and(&alloced_mask, &stor_device->alloced_cpus,
+				    cpumask_of_node(cpu_to_node(q_num)));
+			for_each_cpu(tgt_cpu, &alloced_mask) {
+				if (tgt_cpu != outgoing_channel->target_cpu) {
+					outgoing_channel =
+					stor_device->stor_chns[tgt_cpu];
+					break;
+				}
+			}
+		}
+	} else {
+		outgoing_channel = get_og_chn(stor_device, q_num);
+	}
 
 
 	vstor_packet->flags |= REQUEST_COMPLETION_FLAG;
@@ -1267,8 +1386,6 @@ static int storvsc_do_io(struct hv_device *device,
 static int storvsc_device_configure(struct scsi_device *sdevice)
 {
 
-	blk_queue_max_segment_size(sdevice->request_queue, PAGE_SIZE);
-
 	blk_queue_bounce_limit(sdevice->request_queue, BLK_BOUNCE_ANY);
 
 	blk_queue_rq_timeout(sdevice->request_queue, (storvsc_timeout * HZ));
@@ -1451,6 +1568,13 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 	vm_srb->win8_extension.srb_flags |=
 		SRB_FLAGS_DISABLE_SYNCH_TRANSFER;
 
+	if (scmnd->device->tagged_supported) {
+		vm_srb->win8_extension.srb_flags |=
+		(SRB_FLAGS_QUEUE_ACTION_ENABLE | SRB_FLAGS_NO_QUEUE_FREEZE);
+		vm_srb->win8_extension.queue_tag = SP_UNTAGGED;
+		vm_srb->win8_extension.queue_action = SRB_SIMPLE_TAG_REQUEST;
+	}
+
 	/* Build the SRB */
 	switch (scmnd->sc_data_direction) {
 	case DMA_TO_DEVICE:
@@ -1511,20 +1635,14 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd)
 				page_to_pfn(sg_page((cur_sgl)));
 			cur_sgl = sg_next(cur_sgl);
 		}
-
-	} else if (scsi_sglist(scmnd)) {
-		payload->range.len = length;
-		payload->range.offset =
-			virt_to_phys(scsi_sglist(scmnd)) & (PAGE_SIZE-1);
-		payload->range.pfn_array[0] =
-			virt_to_phys(scsi_sglist(scmnd)) >> PAGE_SHIFT;
 	}
 
 	cmd_request->payload = payload;
 	cmd_request->payload_sz = payload_sz;
 
 	/* Invokes the vsc to start an IO */
-	ret = storvsc_do_io(dev, cmd_request);
+	ret = storvsc_do_io(dev, cmd_request, get_cpu());
+	put_cpu();
 
 	if (ret == -EAGAIN) {
 		/* no more space */
@@ -1550,6 +1668,7 @@ static struct scsi_host_template scsi_driver = {
 	/* Make sure we dont get a sg segment crosses a page boundary */
 	.dma_boundary =		PAGE_SIZE-1,
 	.no_write_same =	1,
+	.track_queue_depth =	1,
 };
 
 enum {
@@ -1680,6 +1799,11 @@ static int storvsc_probe(struct hv_device *device,
 	 * from the host.
 	 */
 	host->sg_tablesize = (stor_device->max_transfer_bytes >> PAGE_SHIFT);
+	/*
+	 * Set the number of HW queues we are supporting.
+	 */
+	if (stor_device->num_sc != 0)
+		host->nr_hw_queues = stor_device->num_sc + 1;
 
 	/* Register the HBA and start the scsi bus scan */
 	ret = scsi_add_host(host, &device->device);
@@ -1716,6 +1840,7 @@ err_out2:
 	goto err_out0;
 
 err_out1:
+	kfree(stor_device->stor_chns);
 	kfree(stor_device);
 
 err_out0:
@@ -1774,11 +1899,6 @@ static int __init storvsc_drv_init(void)
 	fc_transport_template = fc_attach_transport(&fc_transport_functions);
 	if (!fc_transport_template)
 		return -ENODEV;
-
-	/*
-	 * Install Hyper-V specific timeout handler.
-	 */
-	fc_transport_template->eh_timed_out = storvsc_eh_timed_out;
 #endif
 
 	ret = vmbus_driver_register(&storvsc_drv);
diff --git a/drivers/scsi/sun3_scsi.c b/drivers/scsi/sun3_scsi.c
index 88db6992420e..e64b0c542f95 100644
--- a/drivers/scsi/sun3_scsi.c
+++ b/drivers/scsi/sun3_scsi.c
@@ -34,7 +34,6 @@
 #include <asm/dvma.h>
 
 #include <scsi/scsi_host.h>
-#include "sun3_scsi.h"
 
 /* minimum number of bytes to do dma on */
 #define DMA_MIN_SIZE                    129
@@ -56,11 +55,87 @@
 #define NCR5380_dma_send_setup          sun3scsi_dma_count
 #define NCR5380_dma_residual            sun3scsi_dma_residual
 
-#define NCR5380_acquire_dma_irq(instance)    (1)
-#define NCR5380_release_dma_irq(instance)
-
 #include "NCR5380.h"
 
+/* dma regs start at regbase + 8, directly after the NCR regs */
+struct sun3_dma_regs {
+	unsigned short dma_addr_hi; /* vme only */
+	unsigned short dma_addr_lo; /* vme only */
+	unsigned short dma_count_hi; /* vme only */
+	unsigned short dma_count_lo; /* vme only */
+	unsigned short udc_data; /* udc dma data reg (obio only) */
+	unsigned short udc_addr; /* uda dma addr reg (obio only) */
+	unsigned short fifo_data; /* fifo data reg,
+	                           * holds extra byte on odd dma reads
+	                           */
+	unsigned short fifo_count;
+	unsigned short csr; /* control/status reg */
+	unsigned short bpack_hi; /* vme only */
+	unsigned short bpack_lo; /* vme only */
+	unsigned short ivect; /* vme only */
+	unsigned short fifo_count_hi; /* vme only */
+};
+
+/* ucd chip specific regs - live in dvma space */
+struct sun3_udc_regs {
+	unsigned short rsel; /* select regs to load */
+	unsigned short addr_hi; /* high word of addr */
+	unsigned short addr_lo; /* low word */
+	unsigned short count; /* words to be xfer'd */
+	unsigned short mode_hi; /* high word of channel mode */
+	unsigned short mode_lo; /* low word of channel mode */
+};
+
+/* addresses of the udc registers */
+#define UDC_MODE 0x38
+#define UDC_CSR 0x2e /* command/status */
+#define UDC_CHN_HI 0x26 /* chain high word */
+#define UDC_CHN_LO 0x22 /* chain lo word */
+#define UDC_CURA_HI 0x1a /* cur reg A high */
+#define UDC_CURA_LO 0x0a /* cur reg A low */
+#define UDC_CURB_HI 0x12 /* cur reg B high */
+#define UDC_CURB_LO 0x02 /* cur reg B low */
+#define UDC_MODE_HI 0x56 /* mode reg high */
+#define UDC_MODE_LO 0x52 /* mode reg low */
+#define UDC_COUNT 0x32 /* words to xfer */
+
+/* some udc commands */
+#define UDC_RESET 0
+#define UDC_CHN_START 0xa0 /* start chain */
+#define UDC_INT_ENABLE 0x32 /* channel 1 int on */
+
+/* udc mode words */
+#define UDC_MODE_HIWORD 0x40
+#define UDC_MODE_LSEND 0xc2
+#define UDC_MODE_LRECV 0xd2
+
+/* udc reg selections */
+#define UDC_RSEL_SEND 0x282
+#define UDC_RSEL_RECV 0x182
+
+/* bits in csr reg */
+#define CSR_DMA_ACTIVE 0x8000
+#define CSR_DMA_CONFLICT 0x4000
+#define CSR_DMA_BUSERR 0x2000
+
+#define CSR_FIFO_EMPTY 0x400 /* fifo flushed? */
+#define CSR_SDB_INT 0x200 /* sbc interrupt pending */
+#define CSR_DMA_INT 0x100 /* dma interrupt pending */
+
+#define CSR_LEFT 0xc0
+#define CSR_LEFT_3 0xc0
+#define CSR_LEFT_2 0x80
+#define CSR_LEFT_1 0x40
+#define CSR_PACK_ENABLE 0x20
+
+#define CSR_DMA_ENABLE 0x10
+
+#define CSR_SEND 0x8 /* 1 = send  0 = recv */
+#define CSR_FIFO 0x2 /* reset fifo */
+#define CSR_INTR 0x4 /* interrupt enable */
+#define CSR_SCSI 0x1
+
+#define VME_DATA24 0x3d00
 
 extern int sun3_map_test(unsigned long, char *);
 
@@ -260,7 +335,7 @@ static int sun3scsi_dma_xfer_len(struct NCR5380_hostdata *hostdata,
 {
 	int wanted_len = cmd->SCp.this_residual;
 
-	if (wanted_len < DMA_MIN_SIZE || cmd->request->cmd_type != REQ_TYPE_FS)
+	if (wanted_len < DMA_MIN_SIZE || blk_rq_is_passthrough(cmd->request))
 		return 0;
 
 	return wanted_len;
diff --git a/drivers/scsi/sun3_scsi.h b/drivers/scsi/sun3_scsi.h
deleted file mode 100644
index d22745fae328..000000000000
--- a/drivers/scsi/sun3_scsi.h
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * Sun3 SCSI stuff by Erik Verbruggen (erik@bigmama.xtdnet.nl)
- *
- * Sun3 DMA additions by Sam Creasey (sammy@sammy.net)
- *
- * Adapted from mac_scsinew.h:
- */
-/*
- * Cumana Generic NCR5380 driver defines
- *
- * Copyright 1993, Drew Eckhardt
- *	Visionary Computing
- *	(Unix and Linux consulting and custom programming)
- *	drew@colorado.edu
- *      +1 (303) 440-4894
- */
-
-#ifndef SUN3_SCSI_H
-#define SUN3_SCSI_H
-
-/* additional registers - mainly DMA control regs */
-/* these start at regbase + 8 -- directly after the NCR regs */
-struct sun3_dma_regs {
-	unsigned short dma_addr_hi; /* vme only */
-	unsigned short dma_addr_lo; /* vme only */
-	unsigned short dma_count_hi; /* vme only */
-	unsigned short dma_count_lo; /* vme only */
-	unsigned short udc_data; /* udc dma data reg (obio only) */
-	unsigned short udc_addr; /* uda dma addr reg (obio only) */
-	unsigned short fifo_data; /* fifo data reg, holds extra byte on
-				     odd dma reads */
-	unsigned short fifo_count; 
-	unsigned short csr; /* control/status reg */
-	unsigned short bpack_hi; /* vme only */
-	unsigned short bpack_lo; /* vme only */
-	unsigned short ivect; /* vme only */
-	unsigned short fifo_count_hi; /* vme only */
-};
-
-/* ucd chip specific regs - live in dvma space */
-struct sun3_udc_regs {
-     unsigned short rsel; /* select regs to load */
-     unsigned short addr_hi; /* high word of addr */
-     unsigned short addr_lo; /* low word */
-     unsigned short count; /* words to be xfer'd */
-     unsigned short mode_hi; /* high word of channel mode */
-     unsigned short mode_lo; /* low word of channel mode */
-};
-
-/* addresses of the udc registers */
-#define UDC_MODE 0x38 
-#define UDC_CSR 0x2e /* command/status */
-#define UDC_CHN_HI 0x26 /* chain high word */
-#define UDC_CHN_LO 0x22 /* chain lo word */
-#define UDC_CURA_HI 0x1a /* cur reg A high */
-#define UDC_CURA_LO 0x0a /* cur reg A low */
-#define UDC_CURB_HI 0x12 /* cur reg B high */
-#define UDC_CURB_LO 0x02 /* cur reg B low */
-#define UDC_MODE_HI 0x56 /* mode reg high */
-#define UDC_MODE_LO 0x52 /* mode reg low */
-#define UDC_COUNT 0x32 /* words to xfer */
-
-/* some udc commands */
-#define UDC_RESET 0
-#define UDC_CHN_START 0xa0 /* start chain */
-#define UDC_INT_ENABLE 0x32 /* channel 1 int on */
-
-/* udc mode words */
-#define UDC_MODE_HIWORD 0x40
-#define UDC_MODE_LSEND 0xc2
-#define UDC_MODE_LRECV 0xd2
-
-/* udc reg selections */
-#define UDC_RSEL_SEND 0x282
-#define UDC_RSEL_RECV 0x182
-
-/* bits in csr reg */
-#define CSR_DMA_ACTIVE 0x8000
-#define CSR_DMA_CONFLICT 0x4000
-#define CSR_DMA_BUSERR 0x2000
-
-#define CSR_FIFO_EMPTY 0x400 /* fifo flushed? */
-#define CSR_SDB_INT 0x200 /* sbc interrupt pending */
-#define CSR_DMA_INT 0x100 /* dma interrupt pending */
-
-#define CSR_LEFT 0xc0
-#define CSR_LEFT_3 0xc0
-#define CSR_LEFT_2 0x80
-#define CSR_LEFT_1 0x40
-#define CSR_PACK_ENABLE 0x20
-
-#define CSR_DMA_ENABLE 0x10
-
-#define CSR_SEND 0x8 /* 1 = send  0 = recv */
-#define CSR_FIFO 0x2 /* reset fifo */
-#define CSR_INTR 0x4 /* interrupt enable */
-#define CSR_SCSI 0x1 
-
-#define VME_DATA24 0x3d00
-
-#endif /* SUN3_SCSI_H */
-
diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index abe617372661..ce5d023c1c91 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -1497,17 +1497,21 @@ static void ufs_qcom_print_hw_debug_reg_all(struct ufs_hba *hba,
 
 static void ufs_qcom_enable_test_bus(struct ufs_qcom_host *host)
 {
-	if (host->dbg_print_en & UFS_QCOM_DBG_PRINT_TEST_BUS_EN)
+	if (host->dbg_print_en & UFS_QCOM_DBG_PRINT_TEST_BUS_EN) {
+		ufshcd_rmwl(host->hba, UFS_REG_TEST_BUS_EN,
+				UFS_REG_TEST_BUS_EN, REG_UFS_CFG1);
 		ufshcd_rmwl(host->hba, TEST_BUS_EN, TEST_BUS_EN, REG_UFS_CFG1);
-	else
+	} else {
+		ufshcd_rmwl(host->hba, UFS_REG_TEST_BUS_EN, 0, REG_UFS_CFG1);
 		ufshcd_rmwl(host->hba, TEST_BUS_EN, 0, REG_UFS_CFG1);
+	}
 }
 
 static void ufs_qcom_get_default_testbus_cfg(struct ufs_qcom_host *host)
 {
 	/* provide a legal default configuration */
-	host->testbus.select_major = TSTBUS_UAWM;
-	host->testbus.select_minor = 1;
+	host->testbus.select_major = TSTBUS_UNIPRO;
+	host->testbus.select_minor = 37;
 }
 
 static bool ufs_qcom_testbus_cfg_is_ok(struct ufs_qcom_host *host)
@@ -1524,7 +1528,7 @@ static bool ufs_qcom_testbus_cfg_is_ok(struct ufs_qcom_host *host)
 	 * mappings of select_minor, since there is no harm in
 	 * configuring a non-existent select_minor
 	 */
-	if (host->testbus.select_minor > 0x1F) {
+	if (host->testbus.select_minor > 0xFF) {
 		dev_err(host->hba->dev,
 			"%s: 0x%05X is not a legal testbus option\n",
 			__func__, host->testbus.select_minor);
@@ -1593,7 +1597,8 @@ int ufs_qcom_testbus_config(struct ufs_qcom_host *host)
 		break;
 	case TSTBUS_UNIPRO:
 		reg = UFS_UNIPRO_CFG;
-		offset = 1;
+		offset = 20;
+		mask = 0xFFF;
 		break;
 	/*
 	 * No need for a default case, since
@@ -1612,6 +1617,11 @@ int ufs_qcom_testbus_config(struct ufs_qcom_host *host)
 		    (u32)host->testbus.select_minor << offset,
 		    reg);
 	ufs_qcom_enable_test_bus(host);
+	/*
+	 * Make sure the test bus configuration is
+	 * committed before returning.
+	 */
+	mb();
 	ufshcd_release(host->hba);
 	pm_runtime_put_sync(host->hba->dev);
 
@@ -1623,13 +1633,39 @@ static void ufs_qcom_testbus_read(struct ufs_hba *hba)
 	ufs_qcom_dump_regs(hba, UFS_TEST_BUS, 1, "UFS_TEST_BUS ");
 }
 
+static void ufs_qcom_print_unipro_testbus(struct ufs_hba *hba)
+{
+	struct ufs_qcom_host *host = ufshcd_get_variant(hba);
+	u32 *testbus = NULL;
+	int i, nminor = 256, testbus_len = nminor * sizeof(u32);
+
+	testbus = kmalloc(testbus_len, GFP_KERNEL);
+	if (!testbus)
+		return;
+
+	host->testbus.select_major = TSTBUS_UNIPRO;
+	for (i = 0; i < nminor; i++) {
+		host->testbus.select_minor = i;
+		ufs_qcom_testbus_config(host);
+		testbus[i] = ufshcd_readl(hba, UFS_TEST_BUS);
+	}
+	print_hex_dump(KERN_ERR, "UNIPRO_TEST_BUS ", DUMP_PREFIX_OFFSET,
+			16, 4, testbus, testbus_len, false);
+	kfree(testbus);
+}
+
 static void ufs_qcom_dump_dbg_regs(struct ufs_hba *hba)
 {
 	ufs_qcom_dump_regs(hba, REG_UFS_SYS1CLK_1US, 16,
 			"HCI Vendor Specific Registers ");
 
+	/* sleep a bit intermittently as we are dumping too much data */
 	ufs_qcom_print_hw_debug_reg_all(hba, NULL, ufs_qcom_dump_regs_wrapper);
+	usleep_range(1000, 1100);
 	ufs_qcom_testbus_read(hba);
+	usleep_range(1000, 1100);
+	ufs_qcom_print_unipro_testbus(hba);
+	usleep_range(1000, 1100);
 }
 
 /**
@@ -1692,6 +1728,7 @@ static const struct of_device_id ufs_qcom_of_match[] = {
 	{ .compatible = "qcom,ufshc"},
 	{},
 };
+MODULE_DEVICE_TABLE(of, ufs_qcom_of_match);
 
 static const struct dev_pm_ops ufs_qcom_pm_ops = {
 	.suspend	= ufshcd_pltfrm_suspend,
diff --git a/drivers/scsi/ufs/ufs-qcom.h b/drivers/scsi/ufs/ufs-qcom.h
index fe517cd7dac3..076f52813a4c 100644
--- a/drivers/scsi/ufs/ufs-qcom.h
+++ b/drivers/scsi/ufs/ufs-qcom.h
@@ -95,6 +95,7 @@ enum {
 #define QUNIPRO_SEL	UFS_BIT(0)
 #define TEST_BUS_EN		BIT(18)
 #define TEST_BUS_SEL		GENMASK(22, 19)
+#define UFS_REG_TEST_BUS_EN	BIT(30)
 
 /* bit definitions for REG_UFS_CFG2 register */
 #define UAWM_HW_CGC_EN		(1 << 0)
diff --git a/drivers/scsi/ufs/ufs.h b/drivers/scsi/ufs/ufs.h
index 8e6709a3fb6b..318e4a1f76c9 100644
--- a/drivers/scsi/ufs/ufs.h
+++ b/drivers/scsi/ufs/ufs.h
@@ -523,4 +523,16 @@ struct ufs_dev_info {
 	bool is_lu_power_on_wp;
 };
 
+#define MAX_MODEL_LEN 16
+/**
+ * ufs_dev_desc - ufs device details from the device descriptor
+ *
+ * @wmanufacturerid: card details
+ * @model: card model
+ */
+struct ufs_dev_desc {
+	u16 wmanufacturerid;
+	char model[MAX_MODEL_LEN + 1];
+};
+
 #endif /* End of Header */
diff --git a/drivers/scsi/ufs/ufs_quirks.h b/drivers/scsi/ufs/ufs_quirks.h
index 08b799d4efcc..71f73d1d1ad1 100644
--- a/drivers/scsi/ufs/ufs_quirks.h
+++ b/drivers/scsi/ufs/ufs_quirks.h
@@ -21,41 +21,28 @@
 #define UFS_ANY_VENDOR 0xFFFF
 #define UFS_ANY_MODEL  "ANY_MODEL"
 
-#define MAX_MODEL_LEN 16
-
 #define UFS_VENDOR_TOSHIBA     0x198
 #define UFS_VENDOR_SAMSUNG     0x1CE
 #define UFS_VENDOR_SKHYNIX     0x1AD
 
 /**
- * ufs_device_info - ufs device details
- * @wmanufacturerid: card details
- * @model: card model
- */
-struct ufs_device_info {
-	u16 wmanufacturerid;
-	char model[MAX_MODEL_LEN + 1];
-};
-
-/**
  * ufs_dev_fix - ufs device quirk info
  * @card: ufs card details
  * @quirk: device quirk
  */
 struct ufs_dev_fix {
-	struct ufs_device_info card;
+	struct ufs_dev_desc card;
 	unsigned int quirk;
 };
 
 #define END_FIX { { 0 }, 0 }
 
 /* add specific device quirk */
-#define UFS_FIX(_vendor, _model, _quirk) \
-		{					  \
-			.card.wmanufacturerid = (_vendor),\
-			.card.model = (_model),		  \
-			.quirk = (_quirk),		  \
-		}
+#define UFS_FIX(_vendor, _model, _quirk) { \
+	.card.wmanufacturerid = (_vendor),\
+	.card.model = (_model),		   \
+	.quirk = (_quirk),		   \
+}
 
 /*
  * If UFS device is having issue in processing LCC (Line Control
@@ -144,7 +131,4 @@ struct ufs_dev_fix {
  */
 #define UFS_DEVICE_QUIRK_HOST_PA_SAVECONFIGTIME	(1 << 8)
 
-struct ufs_hba;
-void ufs_advertise_fixup_device(struct ufs_hba *hba);
-
 #endif /* UFS_QUIRKS_H_ */
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 20e5e5fb048c..8b721f431dd0 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -45,6 +45,9 @@
 #include "ufs_quirks.h"
 #include "unipro.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/ufs.h>
+
 #define UFSHCD_REQ_SENSE_SIZE	18
 
 #define UFSHCD_ENABLE_INTRS	(UTP_TRANSFER_REQ_COMPL |\
@@ -94,6 +97,9 @@
 		_ret;                                                   \
 	})
 
+#define ufshcd_hex_dump(prefix_str, buf, len) \
+print_hex_dump(KERN_ERR, prefix_str, DUMP_PREFIX_OFFSET, 16, 4, buf, len, false)
+
 static u32 ufs_query_desc_max_size[] = {
 	QUERY_DESC_DEVICE_MAX_SIZE,
 	QUERY_DESC_CONFIGURAION_MAX_SIZE,
@@ -185,6 +191,22 @@ ufs_get_pm_lvl_to_link_pwr_state(enum ufs_pm_level lvl)
 	return ufs_pm_lvl_states[lvl].link_state;
 }
 
+static inline enum ufs_pm_level
+ufs_get_desired_pm_lvl_for_dev_link_state(enum ufs_dev_pwr_mode dev_state,
+					enum uic_link_state link_state)
+{
+	enum ufs_pm_level lvl;
+
+	for (lvl = UFS_PM_LVL_0; lvl < UFS_PM_LVL_MAX; lvl++) {
+		if ((ufs_pm_lvl_states[lvl].dev_state == dev_state) &&
+			(ufs_pm_lvl_states[lvl].link_state == link_state))
+			return lvl;
+	}
+
+	/* if no match found, return the level 0 */
+	return UFS_PM_LVL_0;
+}
+
 static struct ufs_dev_fix ufs_fixups[] = {
 	/* UFS cards deviations table */
 	UFS_FIX(UFS_VENDOR_SAMSUNG, UFS_ANY_MODEL,
@@ -212,6 +234,7 @@ static struct ufs_dev_fix ufs_fixups[] = {
 static void ufshcd_tmc_handler(struct ufs_hba *hba);
 static void ufshcd_async_scan(void *data, async_cookie_t cookie);
 static int ufshcd_reset_and_restore(struct ufs_hba *hba);
+static int ufshcd_eh_host_reset_handler(struct scsi_cmnd *cmd);
 static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag);
 static void ufshcd_hba_exit(struct ufs_hba *hba);
 static int ufshcd_probe_hba(struct ufs_hba *hba);
@@ -223,6 +246,10 @@ static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba);
 static int ufshcd_uic_hibern8_enter(struct ufs_hba *hba);
 static inline void ufshcd_add_delay_before_dme_cmd(struct ufs_hba *hba);
 static int ufshcd_host_reset_and_restore(struct ufs_hba *hba);
+static void ufshcd_resume_clkscaling(struct ufs_hba *hba);
+static void ufshcd_suspend_clkscaling(struct ufs_hba *hba);
+static void __ufshcd_suspend_clkscaling(struct ufs_hba *hba);
+static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up);
 static irqreturn_t ufshcd_intr(int irq, void *__hba);
 static int ufshcd_config_pwr_mode(struct ufs_hba *hba,
 		struct ufs_pa_layer_attr *desired_pwr_mode);
@@ -267,6 +294,214 @@ static inline void ufshcd_remove_non_printable(char *val)
 		*val = ' ';
 }
 
+static void ufshcd_add_command_trace(struct ufs_hba *hba,
+		unsigned int tag, const char *str)
+{
+	sector_t lba = -1;
+	u8 opcode = 0;
+	u32 intr, doorbell;
+	struct ufshcd_lrb *lrbp;
+	int transfer_len = -1;
+
+	if (!trace_ufshcd_command_enabled())
+		return;
+
+	lrbp = &hba->lrb[tag];
+
+	if (lrbp->cmd) { /* data phase exists */
+		opcode = (u8)(*lrbp->cmd->cmnd);
+		if ((opcode == READ_10) || (opcode == WRITE_10)) {
+			/*
+			 * Currently we only fully trace read(10) and write(10)
+			 * commands
+			 */
+			if (lrbp->cmd->request && lrbp->cmd->request->bio)
+				lba =
+				  lrbp->cmd->request->bio->bi_iter.bi_sector;
+			transfer_len = be32_to_cpu(
+				lrbp->ucd_req_ptr->sc.exp_data_transfer_len);
+		}
+	}
+
+	intr = ufshcd_readl(hba, REG_INTERRUPT_STATUS);
+	doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
+	trace_ufshcd_command(dev_name(hba->dev), str, tag,
+				doorbell, transfer_len, intr, lba, opcode);
+}
+
+static void ufshcd_print_clk_freqs(struct ufs_hba *hba)
+{
+	struct ufs_clk_info *clki;
+	struct list_head *head = &hba->clk_list_head;
+
+	if (!head || list_empty(head))
+		return;
+
+	list_for_each_entry(clki, head, list) {
+		if (!IS_ERR_OR_NULL(clki->clk) && clki->min_freq &&
+				clki->max_freq)
+			dev_err(hba->dev, "clk: %s, rate: %u\n",
+					clki->name, clki->curr_freq);
+	}
+}
+
+static void ufshcd_print_uic_err_hist(struct ufs_hba *hba,
+		struct ufs_uic_err_reg_hist *err_hist, char *err_name)
+{
+	int i;
+
+	for (i = 0; i < UIC_ERR_REG_HIST_LENGTH; i++) {
+		int p = (i + err_hist->pos - 1) % UIC_ERR_REG_HIST_LENGTH;
+
+		if (err_hist->reg[p] == 0)
+			continue;
+		dev_err(hba->dev, "%s[%d] = 0x%x at %lld us\n", err_name, i,
+			err_hist->reg[p], ktime_to_us(err_hist->tstamp[p]));
+	}
+}
+
+static void ufshcd_print_host_regs(struct ufs_hba *hba)
+{
+	/*
+	 * hex_dump reads its data without the readl macro. This might
+	 * cause inconsistency issues on some platform, as the printed
+	 * values may be from cache and not the most recent value.
+	 * To know whether you are looking at an un-cached version verify
+	 * that IORESOURCE_MEM flag is on when xxx_get_resource() is invoked
+	 * during platform/pci probe function.
+	 */
+	ufshcd_hex_dump("host regs: ", hba->mmio_base, UFSHCI_REG_SPACE_SIZE);
+	dev_err(hba->dev, "hba->ufs_version = 0x%x, hba->capabilities = 0x%x\n",
+		hba->ufs_version, hba->capabilities);
+	dev_err(hba->dev,
+		"hba->outstanding_reqs = 0x%x, hba->outstanding_tasks = 0x%x\n",
+		(u32)hba->outstanding_reqs, (u32)hba->outstanding_tasks);
+	dev_err(hba->dev,
+		"last_hibern8_exit_tstamp at %lld us, hibern8_exit_cnt = %d\n",
+		ktime_to_us(hba->ufs_stats.last_hibern8_exit_tstamp),
+		hba->ufs_stats.hibern8_exit_cnt);
+
+	ufshcd_print_uic_err_hist(hba, &hba->ufs_stats.pa_err, "pa_err");
+	ufshcd_print_uic_err_hist(hba, &hba->ufs_stats.dl_err, "dl_err");
+	ufshcd_print_uic_err_hist(hba, &hba->ufs_stats.nl_err, "nl_err");
+	ufshcd_print_uic_err_hist(hba, &hba->ufs_stats.tl_err, "tl_err");
+	ufshcd_print_uic_err_hist(hba, &hba->ufs_stats.dme_err, "dme_err");
+
+	ufshcd_print_clk_freqs(hba);
+
+	if (hba->vops && hba->vops->dbg_register_dump)
+		hba->vops->dbg_register_dump(hba);
+}
+
+static
+void ufshcd_print_trs(struct ufs_hba *hba, unsigned long bitmap, bool pr_prdt)
+{
+	struct ufshcd_lrb *lrbp;
+	int prdt_length;
+	int tag;
+
+	for_each_set_bit(tag, &bitmap, hba->nutrs) {
+		lrbp = &hba->lrb[tag];
+
+		dev_err(hba->dev, "UPIU[%d] - issue time %lld us\n",
+				tag, ktime_to_us(lrbp->issue_time_stamp));
+		dev_err(hba->dev,
+			"UPIU[%d] - Transfer Request Descriptor phys@0x%llx\n",
+			tag, (u64)lrbp->utrd_dma_addr);
+
+		ufshcd_hex_dump("UPIU TRD: ", lrbp->utr_descriptor_ptr,
+				sizeof(struct utp_transfer_req_desc));
+		dev_err(hba->dev, "UPIU[%d] - Request UPIU phys@0x%llx\n", tag,
+			(u64)lrbp->ucd_req_dma_addr);
+		ufshcd_hex_dump("UPIU REQ: ", lrbp->ucd_req_ptr,
+				sizeof(struct utp_upiu_req));
+		dev_err(hba->dev, "UPIU[%d] - Response UPIU phys@0x%llx\n", tag,
+			(u64)lrbp->ucd_rsp_dma_addr);
+		ufshcd_hex_dump("UPIU RSP: ", lrbp->ucd_rsp_ptr,
+				sizeof(struct utp_upiu_rsp));
+
+		prdt_length = le16_to_cpu(
+			lrbp->utr_descriptor_ptr->prd_table_length);
+		dev_err(hba->dev,
+			"UPIU[%d] - PRDT - %d entries  phys@0x%llx\n",
+			tag, prdt_length,
+			(u64)lrbp->ucd_prdt_dma_addr);
+
+		if (pr_prdt)
+			ufshcd_hex_dump("UPIU PRDT: ", lrbp->ucd_prdt_ptr,
+				sizeof(struct ufshcd_sg_entry) * prdt_length);
+	}
+}
+
+static void ufshcd_print_tmrs(struct ufs_hba *hba, unsigned long bitmap)
+{
+	struct utp_task_req_desc *tmrdp;
+	int tag;
+
+	for_each_set_bit(tag, &bitmap, hba->nutmrs) {
+		tmrdp = &hba->utmrdl_base_addr[tag];
+		dev_err(hba->dev, "TM[%d] - Task Management Header\n", tag);
+		ufshcd_hex_dump("TM TRD: ", &tmrdp->header,
+				sizeof(struct request_desc_header));
+		dev_err(hba->dev, "TM[%d] - Task Management Request UPIU\n",
+				tag);
+		ufshcd_hex_dump("TM REQ: ", tmrdp->task_req_upiu,
+				sizeof(struct utp_upiu_req));
+		dev_err(hba->dev, "TM[%d] - Task Management Response UPIU\n",
+				tag);
+		ufshcd_hex_dump("TM RSP: ", tmrdp->task_rsp_upiu,
+				sizeof(struct utp_task_req_desc));
+	}
+}
+
+static void ufshcd_print_host_state(struct ufs_hba *hba)
+{
+	dev_err(hba->dev, "UFS Host state=%d\n", hba->ufshcd_state);
+	dev_err(hba->dev, "lrb in use=0x%lx, outstanding reqs=0x%lx tasks=0x%lx\n",
+		hba->lrb_in_use, hba->outstanding_tasks, hba->outstanding_reqs);
+	dev_err(hba->dev, "saved_err=0x%x, saved_uic_err=0x%x\n",
+		hba->saved_err, hba->saved_uic_err);
+	dev_err(hba->dev, "Device power mode=%d, UIC link state=%d\n",
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
+	dev_err(hba->dev, "PM in progress=%d, sys. suspended=%d\n",
+		hba->pm_op_in_progress, hba->is_sys_suspended);
+	dev_err(hba->dev, "Auto BKOPS=%d, Host self-block=%d\n",
+		hba->auto_bkops_enabled, hba->host->host_self_blocked);
+	dev_err(hba->dev, "Clk gate=%d\n", hba->clk_gating.state);
+	dev_err(hba->dev, "error handling flags=0x%x, req. abort count=%d\n",
+		hba->eh_flags, hba->req_abort_count);
+	dev_err(hba->dev, "Host capabilities=0x%x, caps=0x%x\n",
+		hba->capabilities, hba->caps);
+	dev_err(hba->dev, "quirks=0x%x, dev. quirks=0x%x\n", hba->quirks,
+		hba->dev_quirks);
+}
+
+/**
+ * ufshcd_print_pwr_info - print power params as saved in hba
+ * power info
+ * @hba: per-adapter instance
+ */
+static void ufshcd_print_pwr_info(struct ufs_hba *hba)
+{
+	static const char * const names[] = {
+		"INVALID MODE",
+		"FAST MODE",
+		"SLOW_MODE",
+		"INVALID MODE",
+		"FASTAUTO_MODE",
+		"SLOWAUTO_MODE",
+		"INVALID MODE",
+	};
+
+	dev_err(hba->dev, "%s:[RX, TX]: gear=[%d, %d], lane[%d, %d], pwr[%s, %s], rate = %d\n",
+		 __func__,
+		 hba->pwr_info.gear_rx, hba->pwr_info.gear_tx,
+		 hba->pwr_info.lane_rx, hba->pwr_info.lane_tx,
+		 names[hba->pwr_info.pwr_rx],
+		 names[hba->pwr_info.pwr_tx],
+		 hba->pwr_info.hs_rate);
+}
+
 /*
  * ufshcd_wait_for_register - wait for register value to change
  * @hba - per-adapter interface
@@ -605,6 +840,28 @@ static inline int ufshcd_is_hba_active(struct ufs_hba *hba)
 	return (ufshcd_readl(hba, REG_CONTROLLER_ENABLE) & 0x1) ? 0 : 1;
 }
 
+static const char *ufschd_uic_link_state_to_string(
+			enum uic_link_state state)
+{
+	switch (state) {
+	case UIC_LINK_OFF_STATE:	return "OFF";
+	case UIC_LINK_ACTIVE_STATE:	return "ACTIVE";
+	case UIC_LINK_HIBERN8_STATE:	return "HIBERN8";
+	default:			return "UNKNOWN";
+	}
+}
+
+static const char *ufschd_ufs_dev_pwr_mode_to_string(
+			enum ufs_dev_pwr_mode state)
+{
+	switch (state) {
+	case UFS_ACTIVE_PWR_MODE:	return "ACTIVE";
+	case UFS_SLEEP_PWR_MODE:	return "SLEEP";
+	case UFS_POWERDOWN_PWR_MODE:	return "POWERDOWN";
+	default:			return "UNKNOWN";
+	}
+}
+
 u32 ufshcd_get_local_unipro_ver(struct ufs_hba *hba)
 {
 	/* HCI version 1.0 and 1.1 supports UniPro 1.41 */
@@ -633,20 +890,523 @@ static bool ufshcd_is_unipro_pa_params_tuning_req(struct ufs_hba *hba)
 		return false;
 }
 
+static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up)
+{
+	int ret = 0;
+	struct ufs_clk_info *clki;
+	struct list_head *head = &hba->clk_list_head;
+	ktime_t start = ktime_get();
+	bool clk_state_changed = false;
+
+	if (!head || list_empty(head))
+		goto out;
+
+	ret = ufshcd_vops_clk_scale_notify(hba, scale_up, PRE_CHANGE);
+	if (ret)
+		return ret;
+
+	list_for_each_entry(clki, head, list) {
+		if (!IS_ERR_OR_NULL(clki->clk)) {
+			if (scale_up && clki->max_freq) {
+				if (clki->curr_freq == clki->max_freq)
+					continue;
+
+				clk_state_changed = true;
+				ret = clk_set_rate(clki->clk, clki->max_freq);
+				if (ret) {
+					dev_err(hba->dev, "%s: %s clk set rate(%dHz) failed, %d\n",
+						__func__, clki->name,
+						clki->max_freq, ret);
+					break;
+				}
+				trace_ufshcd_clk_scaling(dev_name(hba->dev),
+						"scaled up", clki->name,
+						clki->curr_freq,
+						clki->max_freq);
+
+				clki->curr_freq = clki->max_freq;
+
+			} else if (!scale_up && clki->min_freq) {
+				if (clki->curr_freq == clki->min_freq)
+					continue;
+
+				clk_state_changed = true;
+				ret = clk_set_rate(clki->clk, clki->min_freq);
+				if (ret) {
+					dev_err(hba->dev, "%s: %s clk set rate(%dHz) failed, %d\n",
+						__func__, clki->name,
+						clki->min_freq, ret);
+					break;
+				}
+				trace_ufshcd_clk_scaling(dev_name(hba->dev),
+						"scaled down", clki->name,
+						clki->curr_freq,
+						clki->min_freq);
+				clki->curr_freq = clki->min_freq;
+			}
+		}
+		dev_dbg(hba->dev, "%s: clk: %s, rate: %lu\n", __func__,
+				clki->name, clk_get_rate(clki->clk));
+	}
+
+	ret = ufshcd_vops_clk_scale_notify(hba, scale_up, POST_CHANGE);
+
+out:
+	if (clk_state_changed)
+		trace_ufshcd_profile_clk_scaling(dev_name(hba->dev),
+			(scale_up ? "up" : "down"),
+			ktime_to_us(ktime_sub(ktime_get(), start)), ret);
+	return ret;
+}
+
+/**
+ * ufshcd_is_devfreq_scaling_required - check if scaling is required or not
+ * @hba: per adapter instance
+ * @scale_up: True if scaling up and false if scaling down
+ *
+ * Returns true if scaling is required, false otherwise.
+ */
+static bool ufshcd_is_devfreq_scaling_required(struct ufs_hba *hba,
+					       bool scale_up)
+{
+	struct ufs_clk_info *clki;
+	struct list_head *head = &hba->clk_list_head;
+
+	if (!head || list_empty(head))
+		return false;
+
+	list_for_each_entry(clki, head, list) {
+		if (!IS_ERR_OR_NULL(clki->clk)) {
+			if (scale_up && clki->max_freq) {
+				if (clki->curr_freq == clki->max_freq)
+					continue;
+				return true;
+			} else if (!scale_up && clki->min_freq) {
+				if (clki->curr_freq == clki->min_freq)
+					continue;
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
+static int ufshcd_wait_for_doorbell_clr(struct ufs_hba *hba,
+					u64 wait_timeout_us)
+{
+	unsigned long flags;
+	int ret = 0;
+	u32 tm_doorbell;
+	u32 tr_doorbell;
+	bool timeout = false, do_last_check = false;
+	ktime_t start;
+
+	ufshcd_hold(hba, false);
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	/*
+	 * Wait for all the outstanding tasks/transfer requests.
+	 * Verify by checking the doorbell registers are clear.
+	 */
+	start = ktime_get();
+	do {
+		if (hba->ufshcd_state != UFSHCD_STATE_OPERATIONAL) {
+			ret = -EBUSY;
+			goto out;
+		}
+
+		tm_doorbell = ufshcd_readl(hba, REG_UTP_TASK_REQ_DOOR_BELL);
+		tr_doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
+		if (!tm_doorbell && !tr_doorbell) {
+			timeout = false;
+			break;
+		} else if (do_last_check) {
+			break;
+		}
+
+		spin_unlock_irqrestore(hba->host->host_lock, flags);
+		schedule();
+		if (ktime_to_us(ktime_sub(ktime_get(), start)) >
+		    wait_timeout_us) {
+			timeout = true;
+			/*
+			 * We might have scheduled out for long time so make
+			 * sure to check if doorbells are cleared by this time
+			 * or not.
+			 */
+			do_last_check = true;
+		}
+		spin_lock_irqsave(hba->host->host_lock, flags);
+	} while (tm_doorbell || tr_doorbell);
+
+	if (timeout) {
+		dev_err(hba->dev,
+			"%s: timedout waiting for doorbell to clear (tm=0x%x, tr=0x%x)\n",
+			__func__, tm_doorbell, tr_doorbell);
+		ret = -EBUSY;
+	}
+out:
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	ufshcd_release(hba);
+	return ret;
+}
+
+/**
+ * ufshcd_scale_gear - scale up/down UFS gear
+ * @hba: per adapter instance
+ * @scale_up: True for scaling up gear and false for scaling down
+ *
+ * Returns 0 for success,
+ * Returns -EBUSY if scaling can't happen at this time
+ * Returns non-zero for any other errors
+ */
+static int ufshcd_scale_gear(struct ufs_hba *hba, bool scale_up)
+{
+	#define UFS_MIN_GEAR_TO_SCALE_DOWN	UFS_HS_G1
+	int ret = 0;
+	struct ufs_pa_layer_attr new_pwr_info;
+
+	if (scale_up) {
+		memcpy(&new_pwr_info, &hba->clk_scaling.saved_pwr_info.info,
+		       sizeof(struct ufs_pa_layer_attr));
+	} else {
+		memcpy(&new_pwr_info, &hba->pwr_info,
+		       sizeof(struct ufs_pa_layer_attr));
+
+		if (hba->pwr_info.gear_tx > UFS_MIN_GEAR_TO_SCALE_DOWN
+		    || hba->pwr_info.gear_rx > UFS_MIN_GEAR_TO_SCALE_DOWN) {
+			/* save the current power mode */
+			memcpy(&hba->clk_scaling.saved_pwr_info.info,
+				&hba->pwr_info,
+				sizeof(struct ufs_pa_layer_attr));
+
+			/* scale down gear */
+			new_pwr_info.gear_tx = UFS_MIN_GEAR_TO_SCALE_DOWN;
+			new_pwr_info.gear_rx = UFS_MIN_GEAR_TO_SCALE_DOWN;
+		}
+	}
+
+	/* check if the power mode needs to be changed or not? */
+	ret = ufshcd_change_power_mode(hba, &new_pwr_info);
+
+	if (ret)
+		dev_err(hba->dev, "%s: failed err %d, old gear: (tx %d rx %d), new gear: (tx %d rx %d)",
+			__func__, ret,
+			hba->pwr_info.gear_tx, hba->pwr_info.gear_rx,
+			new_pwr_info.gear_tx, new_pwr_info.gear_rx);
+
+	return ret;
+}
+
+static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba)
+{
+	#define DOORBELL_CLR_TOUT_US		(1000 * 1000) /* 1 sec */
+	int ret = 0;
+	/*
+	 * make sure that there are no outstanding requests when
+	 * clock scaling is in progress
+	 */
+	scsi_block_requests(hba->host);
+	down_write(&hba->clk_scaling_lock);
+	if (ufshcd_wait_for_doorbell_clr(hba, DOORBELL_CLR_TOUT_US)) {
+		ret = -EBUSY;
+		up_write(&hba->clk_scaling_lock);
+		scsi_unblock_requests(hba->host);
+	}
+
+	return ret;
+}
+
+static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba)
+{
+	up_write(&hba->clk_scaling_lock);
+	scsi_unblock_requests(hba->host);
+}
+
+/**
+ * ufshcd_devfreq_scale - scale up/down UFS clocks and gear
+ * @hba: per adapter instance
+ * @scale_up: True for scaling up and false for scalin down
+ *
+ * Returns 0 for success,
+ * Returns -EBUSY if scaling can't happen at this time
+ * Returns non-zero for any other errors
+ */
+static int ufshcd_devfreq_scale(struct ufs_hba *hba, bool scale_up)
+{
+	int ret = 0;
+
+	/* let's not get into low power until clock scaling is completed */
+	ufshcd_hold(hba, false);
+
+	ret = ufshcd_clock_scaling_prepare(hba);
+	if (ret)
+		return ret;
+
+	/* scale down the gear before scaling down clocks */
+	if (!scale_up) {
+		ret = ufshcd_scale_gear(hba, false);
+		if (ret)
+			goto out;
+	}
+
+	ret = ufshcd_scale_clks(hba, scale_up);
+	if (ret) {
+		if (!scale_up)
+			ufshcd_scale_gear(hba, true);
+		goto out;
+	}
+
+	/* scale up the gear after scaling up clocks */
+	if (scale_up) {
+		ret = ufshcd_scale_gear(hba, true);
+		if (ret) {
+			ufshcd_scale_clks(hba, false);
+			goto out;
+		}
+	}
+
+	ret = ufshcd_vops_clk_scale_notify(hba, scale_up, POST_CHANGE);
+
+out:
+	ufshcd_clock_scaling_unprepare(hba);
+	ufshcd_release(hba);
+	return ret;
+}
+
+static void ufshcd_clk_scaling_suspend_work(struct work_struct *work)
+{
+	struct ufs_hba *hba = container_of(work, struct ufs_hba,
+					   clk_scaling.suspend_work);
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(hba->host->host_lock, irq_flags);
+	if (hba->clk_scaling.active_reqs || hba->clk_scaling.is_suspended) {
+		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+		return;
+	}
+	hba->clk_scaling.is_suspended = true;
+	spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+
+	__ufshcd_suspend_clkscaling(hba);
+}
+
+static void ufshcd_clk_scaling_resume_work(struct work_struct *work)
+{
+	struct ufs_hba *hba = container_of(work, struct ufs_hba,
+					   clk_scaling.resume_work);
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(hba->host->host_lock, irq_flags);
+	if (!hba->clk_scaling.is_suspended) {
+		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+		return;
+	}
+	hba->clk_scaling.is_suspended = false;
+	spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+
+	devfreq_resume_device(hba->devfreq);
+}
+
+static int ufshcd_devfreq_target(struct device *dev,
+				unsigned long *freq, u32 flags)
+{
+	int ret = 0;
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	ktime_t start;
+	bool scale_up, sched_clk_scaling_suspend_work = false;
+	unsigned long irq_flags;
+
+	if (!ufshcd_is_clkscaling_supported(hba))
+		return -EINVAL;
+
+	if ((*freq > 0) && (*freq < UINT_MAX)) {
+		dev_err(hba->dev, "%s: invalid freq = %lu\n", __func__, *freq);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(hba->host->host_lock, irq_flags);
+	if (ufshcd_eh_in_progress(hba)) {
+		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+		return 0;
+	}
+
+	if (!hba->clk_scaling.active_reqs)
+		sched_clk_scaling_suspend_work = true;
+
+	scale_up = (*freq == UINT_MAX) ? true : false;
+	if (!ufshcd_is_devfreq_scaling_required(hba, scale_up)) {
+		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+		ret = 0;
+		goto out; /* no state change required */
+	}
+	spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
+
+	start = ktime_get();
+	ret = ufshcd_devfreq_scale(hba, scale_up);
+
+	trace_ufshcd_profile_clk_scaling(dev_name(hba->dev),
+		(scale_up ? "up" : "down"),
+		ktime_to_us(ktime_sub(ktime_get(), start)), ret);
+
+out:
+	if (sched_clk_scaling_suspend_work)
+		queue_work(hba->clk_scaling.workq,
+			   &hba->clk_scaling.suspend_work);
+
+	return ret;
+}
+
+
+static int ufshcd_devfreq_get_dev_status(struct device *dev,
+		struct devfreq_dev_status *stat)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	struct ufs_clk_scaling *scaling = &hba->clk_scaling;
+	unsigned long flags;
+
+	if (!ufshcd_is_clkscaling_supported(hba))
+		return -EINVAL;
+
+	memset(stat, 0, sizeof(*stat));
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (!scaling->window_start_t)
+		goto start_window;
+
+	if (scaling->is_busy_started)
+		scaling->tot_busy_t += ktime_to_us(ktime_sub(ktime_get(),
+					scaling->busy_start_t));
+
+	stat->total_time = jiffies_to_usecs((long)jiffies -
+				(long)scaling->window_start_t);
+	stat->busy_time = scaling->tot_busy_t;
+start_window:
+	scaling->window_start_t = jiffies;
+	scaling->tot_busy_t = 0;
+
+	if (hba->outstanding_reqs) {
+		scaling->busy_start_t = ktime_get();
+		scaling->is_busy_started = true;
+	} else {
+		scaling->busy_start_t = 0;
+		scaling->is_busy_started = false;
+	}
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	return 0;
+}
+
+static struct devfreq_dev_profile ufs_devfreq_profile = {
+	.polling_ms	= 100,
+	.target		= ufshcd_devfreq_target,
+	.get_dev_status	= ufshcd_devfreq_get_dev_status,
+};
+
+static void __ufshcd_suspend_clkscaling(struct ufs_hba *hba)
+{
+	unsigned long flags;
+
+	devfreq_suspend_device(hba->devfreq);
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	hba->clk_scaling.window_start_t = 0;
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+}
+
 static void ufshcd_suspend_clkscaling(struct ufs_hba *hba)
 {
-	if (ufshcd_is_clkscaling_enabled(hba)) {
-		devfreq_suspend_device(hba->devfreq);
-		hba->clk_scaling.window_start_t = 0;
+	unsigned long flags;
+	bool suspend = false;
+
+	if (!ufshcd_is_clkscaling_supported(hba))
+		return;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (!hba->clk_scaling.is_suspended) {
+		suspend = true;
+		hba->clk_scaling.is_suspended = true;
 	}
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	if (suspend)
+		__ufshcd_suspend_clkscaling(hba);
 }
 
 static void ufshcd_resume_clkscaling(struct ufs_hba *hba)
 {
-	if (ufshcd_is_clkscaling_enabled(hba))
+	unsigned long flags;
+	bool resume = false;
+
+	if (!ufshcd_is_clkscaling_supported(hba))
+		return;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (hba->clk_scaling.is_suspended) {
+		resume = true;
+		hba->clk_scaling.is_suspended = false;
+	}
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+
+	if (resume)
 		devfreq_resume_device(hba->devfreq);
 }
 
+static ssize_t ufshcd_clkscale_enable_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", hba->clk_scaling.is_allowed);
+}
+
+static ssize_t ufshcd_clkscale_enable_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	u32 value;
+	int err;
+
+	if (kstrtou32(buf, 0, &value))
+		return -EINVAL;
+
+	value = !!value;
+	if (value == hba->clk_scaling.is_allowed)
+		goto out;
+
+	pm_runtime_get_sync(hba->dev);
+	ufshcd_hold(hba, false);
+
+	cancel_work_sync(&hba->clk_scaling.suspend_work);
+	cancel_work_sync(&hba->clk_scaling.resume_work);
+
+	hba->clk_scaling.is_allowed = value;
+
+	if (value) {
+		ufshcd_resume_clkscaling(hba);
+	} else {
+		ufshcd_suspend_clkscaling(hba);
+		err = ufshcd_devfreq_scale(hba, true);
+		if (err)
+			dev_err(hba->dev, "%s: failed to scale clocks up %d\n",
+					__func__, err);
+	}
+
+	ufshcd_release(hba);
+	pm_runtime_put_sync(hba->dev);
+out:
+	return count;
+}
+
+static void ufshcd_clkscaling_init_sysfs(struct ufs_hba *hba)
+{
+	hba->clk_scaling.enable_attr.show = ufshcd_clkscale_enable_show;
+	hba->clk_scaling.enable_attr.store = ufshcd_clkscale_enable_store;
+	sysfs_attr_init(&hba->clk_scaling.enable_attr.attr);
+	hba->clk_scaling.enable_attr.attr.name = "clkscale_enable";
+	hba->clk_scaling.enable_attr.attr.mode = 0644;
+	if (device_create_file(hba->dev, &hba->clk_scaling.enable_attr))
+		dev_err(hba->dev, "Failed to create sysfs for clkscale_enable\n");
+}
+
 static void ufshcd_ungate_work(struct work_struct *work)
 {
 	int ret;
@@ -680,7 +1440,6 @@ static void ufshcd_ungate_work(struct work_struct *work)
 		hba->clk_gating.is_suspended = false;
 	}
 unblock_reqs:
-	ufshcd_resume_clkscaling(hba);
 	scsi_unblock_requests(hba->host);
 }
 
@@ -727,6 +1486,8 @@ start:
 	case REQ_CLKS_OFF:
 		if (cancel_delayed_work(&hba->clk_gating.gate_work)) {
 			hba->clk_gating.state = CLKS_ON;
+			trace_ufshcd_clk_gating(dev_name(hba->dev),
+						hba->clk_gating.state);
 			break;
 		}
 		/*
@@ -737,6 +1498,8 @@ start:
 	case CLKS_OFF:
 		scsi_block_requests(hba->host);
 		hba->clk_gating.state = REQ_CLKS_ON;
+		trace_ufshcd_clk_gating(dev_name(hba->dev),
+					hba->clk_gating.state);
 		schedule_work(&hba->clk_gating.ungate_work);
 		/*
 		 * fall through to check if we should wait for this
@@ -781,6 +1544,8 @@ static void ufshcd_gate_work(struct work_struct *work)
 	if (hba->clk_gating.is_suspended ||
 		(hba->clk_gating.state == REQ_CLKS_ON)) {
 		hba->clk_gating.state = CLKS_ON;
+		trace_ufshcd_clk_gating(dev_name(hba->dev),
+					hba->clk_gating.state);
 		goto rel_lock;
 	}
 
@@ -796,13 +1561,13 @@ static void ufshcd_gate_work(struct work_struct *work)
 	if (ufshcd_can_hibern8_during_gating(hba)) {
 		if (ufshcd_uic_hibern8_enter(hba)) {
 			hba->clk_gating.state = CLKS_ON;
+			trace_ufshcd_clk_gating(dev_name(hba->dev),
+						hba->clk_gating.state);
 			goto out;
 		}
 		ufshcd_set_link_hibern8(hba);
 	}
 
-	ufshcd_suspend_clkscaling(hba);
-
 	if (!ufshcd_is_link_active(hba))
 		ufshcd_setup_clocks(hba, false);
 	else
@@ -819,9 +1584,11 @@ static void ufshcd_gate_work(struct work_struct *work)
 	 * new requests arriving before the current cancel work is done.
 	 */
 	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (hba->clk_gating.state == REQ_CLKS_OFF)
+	if (hba->clk_gating.state == REQ_CLKS_OFF) {
 		hba->clk_gating.state = CLKS_OFF;
-
+		trace_ufshcd_clk_gating(dev_name(hba->dev),
+					hba->clk_gating.state);
+	}
 rel_lock:
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 out:
@@ -844,6 +1611,7 @@ static void __ufshcd_release(struct ufs_hba *hba)
 		return;
 
 	hba->clk_gating.state = REQ_CLKS_OFF;
+	trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state);
 	schedule_delayed_work(&hba->clk_gating.gate_work,
 			msecs_to_jiffies(hba->clk_gating.delay_ms));
 }
@@ -881,6 +1649,41 @@ static ssize_t ufshcd_clkgate_delay_store(struct device *dev,
 	return count;
 }
 
+static ssize_t ufshcd_clkgate_enable_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", hba->clk_gating.is_enabled);
+}
+
+static ssize_t ufshcd_clkgate_enable_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	unsigned long flags;
+	u32 value;
+
+	if (kstrtou32(buf, 0, &value))
+		return -EINVAL;
+
+	value = !!value;
+	if (value == hba->clk_gating.is_enabled)
+		goto out;
+
+	if (value) {
+		ufshcd_release(hba);
+	} else {
+		spin_lock_irqsave(hba->host->host_lock, flags);
+		hba->clk_gating.active_reqs++;
+		spin_unlock_irqrestore(hba->host->host_lock, flags);
+	}
+
+	hba->clk_gating.is_enabled = value;
+out:
+	return count;
+}
+
 static void ufshcd_init_clk_gating(struct ufs_hba *hba)
 {
 	if (!ufshcd_is_clkgating_allowed(hba))
@@ -890,13 +1693,23 @@ static void ufshcd_init_clk_gating(struct ufs_hba *hba)
 	INIT_DELAYED_WORK(&hba->clk_gating.gate_work, ufshcd_gate_work);
 	INIT_WORK(&hba->clk_gating.ungate_work, ufshcd_ungate_work);
 
+	hba->clk_gating.is_enabled = true;
+
 	hba->clk_gating.delay_attr.show = ufshcd_clkgate_delay_show;
 	hba->clk_gating.delay_attr.store = ufshcd_clkgate_delay_store;
 	sysfs_attr_init(&hba->clk_gating.delay_attr.attr);
 	hba->clk_gating.delay_attr.attr.name = "clkgate_delay_ms";
-	hba->clk_gating.delay_attr.attr.mode = S_IRUGO | S_IWUSR;
+	hba->clk_gating.delay_attr.attr.mode = 0644;
 	if (device_create_file(hba->dev, &hba->clk_gating.delay_attr))
 		dev_err(hba->dev, "Failed to create sysfs for clkgate_delay\n");
+
+	hba->clk_gating.enable_attr.show = ufshcd_clkgate_enable_show;
+	hba->clk_gating.enable_attr.store = ufshcd_clkgate_enable_store;
+	sysfs_attr_init(&hba->clk_gating.enable_attr.attr);
+	hba->clk_gating.enable_attr.attr.name = "clkgate_enable";
+	hba->clk_gating.enable_attr.attr.mode = 0644;
+	if (device_create_file(hba->dev, &hba->clk_gating.enable_attr))
+		dev_err(hba->dev, "Failed to create sysfs for clkgate_enable\n");
 }
 
 static void ufshcd_exit_clk_gating(struct ufs_hba *hba)
@@ -904,6 +1717,7 @@ static void ufshcd_exit_clk_gating(struct ufs_hba *hba)
 	if (!ufshcd_is_clkgating_allowed(hba))
 		return;
 	device_remove_file(hba->dev, &hba->clk_gating.delay_attr);
+	device_remove_file(hba->dev, &hba->clk_gating.enable_attr);
 	cancel_work_sync(&hba->clk_gating.ungate_work);
 	cancel_delayed_work_sync(&hba->clk_gating.gate_work);
 }
@@ -911,9 +1725,27 @@ static void ufshcd_exit_clk_gating(struct ufs_hba *hba)
 /* Must be called with host lock acquired */
 static void ufshcd_clk_scaling_start_busy(struct ufs_hba *hba)
 {
-	if (!ufshcd_is_clkscaling_enabled(hba))
+	bool queue_resume_work = false;
+
+	if (!ufshcd_is_clkscaling_supported(hba))
+		return;
+
+	if (!hba->clk_scaling.active_reqs++)
+		queue_resume_work = true;
+
+	if (!hba->clk_scaling.is_allowed || hba->pm_op_in_progress)
 		return;
 
+	if (queue_resume_work)
+		queue_work(hba->clk_scaling.workq,
+			   &hba->clk_scaling.resume_work);
+
+	if (!hba->clk_scaling.window_start_t) {
+		hba->clk_scaling.window_start_t = jiffies;
+		hba->clk_scaling.tot_busy_t = 0;
+		hba->clk_scaling.is_busy_started = false;
+	}
+
 	if (!hba->clk_scaling.is_busy_started) {
 		hba->clk_scaling.busy_start_t = ktime_get();
 		hba->clk_scaling.is_busy_started = true;
@@ -924,7 +1756,7 @@ static void ufshcd_clk_scaling_update_busy(struct ufs_hba *hba)
 {
 	struct ufs_clk_scaling *scaling = &hba->clk_scaling;
 
-	if (!ufshcd_is_clkscaling_enabled(hba))
+	if (!ufshcd_is_clkscaling_supported(hba))
 		return;
 
 	if (!hba->outstanding_reqs && scaling->is_busy_started) {
@@ -942,11 +1774,13 @@ static void ufshcd_clk_scaling_update_busy(struct ufs_hba *hba)
 static inline
 void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
 {
+	hba->lrb[task_tag].issue_time_stamp = ktime_get();
 	ufshcd_clk_scaling_start_busy(hba);
 	__set_bit(task_tag, &hba->outstanding_reqs);
 	ufshcd_writel(hba, 1 << task_tag, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	/* Make sure that doorbell is committed immediately */
 	wmb();
+	ufshcd_add_command_trace(hba, task_tag, "send");
 }
 
 /**
@@ -1484,6 +2318,9 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 		BUG();
 	}
 
+	if (!down_read_trylock(&hba->clk_scaling_lock))
+		return SCSI_MLQUEUE_HOST_BUSY;
+
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	switch (hba->ufshcd_state) {
 	case UFSHCD_STATE_OPERATIONAL:
@@ -1512,6 +2349,8 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	}
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
+	hba->req_abort_count = 0;
+
 	/* acquire the tag to make sure device cmds don't use it */
 	if (test_and_set_bit_lock(tag, &hba->lrb_in_use)) {
 		/*
@@ -1541,6 +2380,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 	lrbp->task_tag = tag;
 	lrbp->lun = ufshcd_scsi_to_upiu_lun(cmd->device->lun);
 	lrbp->intr_cmd = !ufshcd_is_intr_aggr_allowed(hba) ? true : false;
+	lrbp->req_abort_skip = false;
 
 	ufshcd_comp_scsi_upiu(hba, lrbp);
 
@@ -1560,6 +2400,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
 out_unlock:
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 out:
+	up_read(&hba->clk_scaling_lock);
 	return err;
 }
 
@@ -1622,6 +2463,7 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	int resp;
 	int err = 0;
 
+	hba->ufs_stats.last_hibern8_exit_tstamp = ktime_set(0, 0);
 	resp = ufshcd_get_req_rsp(lrbp->ucd_rsp_ptr);
 
 	switch (resp) {
@@ -1748,6 +2590,8 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 	struct completion wait;
 	unsigned long flags;
 
+	down_read(&hba->clk_scaling_lock);
+
 	/*
 	 * Get free slot, sleep if slots are unavailable.
 	 * Even though we use wait_event() which sleeps indefinitely,
@@ -1776,6 +2620,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba,
 out_put_tag:
 	ufshcd_put_dev_cmd_tag(hba, tag);
 	wake_up(&hba->dev_cmd.tag_wq);
+	up_read(&hba->clk_scaling_lock);
 	return err;
 }
 
@@ -2073,9 +2918,11 @@ out:
  * The buf_len parameter will contain, on return, the length parameter
  * received on the response.
  */
-int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
-			enum query_opcode opcode, enum desc_idn idn, u8 index,
-			u8 selector, u8 *desc_buf, int *buf_len)
+static int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
+					 enum query_opcode opcode,
+					 enum desc_idn idn, u8 index,
+					 u8 selector,
+					 u8 *desc_buf, int *buf_len)
 {
 	int err;
 	int retries;
@@ -2089,7 +2936,6 @@ int ufshcd_query_descriptor_retry(struct ufs_hba *hba,
 
 	return err;
 }
-EXPORT_SYMBOL(ufshcd_query_descriptor_retry);
 
 /**
  * ufshcd_read_desc_param - read the specified descriptor parameter
@@ -2207,11 +3053,10 @@ static inline int ufshcd_read_power_desc(struct ufs_hba *hba,
 	return err;
 }
 
-int ufshcd_read_device_desc(struct ufs_hba *hba, u8 *buf, u32 size)
+static int ufshcd_read_device_desc(struct ufs_hba *hba, u8 *buf, u32 size)
 {
 	return ufshcd_read_desc(hba, QUERY_DESC_IDN_DEVICE, 0, buf, size);
 }
-EXPORT_SYMBOL(ufshcd_read_device_desc);
 
 /**
  * ufshcd_read_string_desc - read string descriptor
@@ -2223,8 +3068,9 @@ EXPORT_SYMBOL(ufshcd_read_device_desc);
  *
  * Return 0 in case of success, non-zero otherwise
  */
-int ufshcd_read_string_desc(struct ufs_hba *hba, int desc_index, u8 *buf,
-				u32 size, bool ascii)
+#define ASCII_STD true
+static int ufshcd_read_string_desc(struct ufs_hba *hba, int desc_index,
+				   u8 *buf, u32 size, bool ascii)
 {
 	int err = 0;
 
@@ -2280,7 +3126,6 @@ int ufshcd_read_string_desc(struct ufs_hba *hba, int desc_index, u8 *buf,
 out:
 	return err;
 }
-EXPORT_SYMBOL(ufshcd_read_string_desc);
 
 /**
  * ufshcd_read_unit_desc_param - read the specified unit descriptor parameter
@@ -2453,12 +3298,19 @@ static void ufshcd_host_memory_configure(struct ufs_hba *hba)
 		}
 
 		hba->lrb[i].utr_descriptor_ptr = (utrdlp + i);
+		hba->lrb[i].utrd_dma_addr = hba->utrdl_dma_addr +
+				(i * sizeof(struct utp_transfer_req_desc));
 		hba->lrb[i].ucd_req_ptr =
 			(struct utp_upiu_req *)(cmd_descp + i);
+		hba->lrb[i].ucd_req_dma_addr = cmd_desc_element_addr;
 		hba->lrb[i].ucd_rsp_ptr =
 			(struct utp_upiu_rsp *)cmd_descp[i].response_upiu;
+		hba->lrb[i].ucd_rsp_dma_addr = cmd_desc_element_addr +
+				response_offset;
 		hba->lrb[i].ucd_prdt_ptr =
 			(struct ufshcd_sg_entry *)cmd_descp[i].prd_table;
+		hba->lrb[i].ucd_prdt_dma_addr = cmd_desc_element_addr +
+				prdt_offset;
 	}
 }
 
@@ -2482,7 +3334,7 @@ static int ufshcd_dme_link_startup(struct ufs_hba *hba)
 
 	ret = ufshcd_send_uic_cmd(hba, &uic_cmd);
 	if (ret)
-		dev_err(hba->dev,
+		dev_dbg(hba->dev,
 			"dme-link-startup: error code %d\n", ret);
 	return ret;
 }
@@ -2702,6 +3554,12 @@ static int ufshcd_uic_pwr_ctrl(struct ufs_hba *hba, struct uic_command *cmd)
 		ret = (status != PWR_OK) ? status : -1;
 	}
 out:
+	if (ret) {
+		ufshcd_print_host_state(hba);
+		ufshcd_print_pwr_info(hba);
+		ufshcd_print_host_regs(hba);
+	}
+
 	spin_lock_irqsave(hba->host->host_lock, flags);
 	hba->active_uic_cmd = NULL;
 	hba->uic_async_done = NULL;
@@ -2776,11 +3634,14 @@ static int __ufshcd_uic_hibern8_enter(struct ufs_hba *hba)
 {
 	int ret;
 	struct uic_command uic_cmd = {0};
+	ktime_t start = ktime_get();
 
 	ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_ENTER, PRE_CHANGE);
 
 	uic_cmd.command = UIC_CMD_DME_HIBER_ENTER;
 	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
+	trace_ufshcd_profile_hibern8(dev_name(hba->dev), "enter",
+			     ktime_to_us(ktime_sub(ktime_get(), start)), ret);
 
 	if (ret) {
 		dev_err(hba->dev, "%s: hibern8 enter failed. ret = %d\n",
@@ -2816,18 +3677,25 @@ static int ufshcd_uic_hibern8_exit(struct ufs_hba *hba)
 {
 	struct uic_command uic_cmd = {0};
 	int ret;
+	ktime_t start = ktime_get();
 
 	ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_EXIT, PRE_CHANGE);
 
 	uic_cmd.command = UIC_CMD_DME_HIBER_EXIT;
 	ret = ufshcd_uic_pwr_ctrl(hba, &uic_cmd);
+	trace_ufshcd_profile_hibern8(dev_name(hba->dev), "exit",
+			     ktime_to_us(ktime_sub(ktime_get(), start)), ret);
+
 	if (ret) {
 		dev_err(hba->dev, "%s: hibern8 exit failed. ret = %d\n",
 			__func__, ret);
 		ret = ufshcd_link_recovery(hba);
-	} else
+	} else {
 		ufshcd_vops_hibern8_notify(hba, UIC_CMD_DME_HIBER_EXIT,
 								POST_CHANGE);
+		hba->ufs_stats.last_hibern8_exit_tstamp = ktime_get();
+		hba->ufs_stats.hibern8_exit_cnt++;
+	}
 
 	return ret;
 }
@@ -2994,6 +3862,8 @@ static int ufshcd_config_pwr_mode(struct ufs_hba *hba,
 		memcpy(&final_params, desired_pwr_mode, sizeof(final_params));
 
 	ret = ufshcd_change_power_mode(hba, &final_params);
+	if (!ret)
+		ufshcd_print_pwr_info(hba);
 
 	return ret;
 }
@@ -3265,6 +4135,10 @@ link_startup:
 		goto link_startup;
 	}
 
+	/* Mark that link is up in PWM-G1, 1-lane, SLOW-AUTO mode */
+	ufshcd_init_pwr_info(hba);
+	ufshcd_print_pwr_info(hba);
+
 	if (hba->quirks & UFSHCD_QUIRK_BROKEN_LCC) {
 		ret = ufshcd_disable_device_tx_lcc(hba);
 		if (ret)
@@ -3278,8 +4152,12 @@ link_startup:
 
 	ret = ufshcd_make_hba_operational(hba);
 out:
-	if (ret)
+	if (ret) {
 		dev_err(hba->dev, "link startup failed %d\n", ret);
+		ufshcd_print_host_state(hba);
+		ufshcd_print_pwr_info(hba);
+		ufshcd_print_host_regs(hba);
+	}
 	return ret;
 }
 
@@ -3591,7 +4469,7 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	switch (ocs) {
 	case OCS_SUCCESS:
 		result = ufshcd_get_req_rsp(lrbp->ucd_rsp_ptr);
-
+		hba->ufs_stats.last_hibern8_exit_tstamp = ktime_set(0, 0);
 		switch (result) {
 		case UPIU_TRANSACTION_RESPONSE:
 			/*
@@ -3652,10 +4530,15 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
 	default:
 		result |= DID_ERROR << 16;
 		dev_err(hba->dev,
-		"OCS error from controller = %x\n", ocs);
+				"OCS error from controller = %x for tag %d\n",
+				ocs, lrbp->task_tag);
+		ufshcd_print_host_regs(hba);
+		ufshcd_print_host_state(hba);
 		break;
 	} /* end of switch */
 
+	if (host_byte(result) != DID_OK)
+		ufshcd_print_trs(hba, 1 << lrbp->task_tag, true);
 	return result;
 }
 
@@ -3695,6 +4578,7 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 		lrbp = &hba->lrb[index];
 		cmd = lrbp->cmd;
 		if (cmd) {
+			ufshcd_add_command_trace(hba, index, "complete");
 			result = ufshcd_transfer_rsp_status(hba, lrbp);
 			scsi_dma_unmap(cmd);
 			cmd->result = result;
@@ -3706,9 +4590,16 @@ static void __ufshcd_transfer_req_compl(struct ufs_hba *hba,
 			__ufshcd_release(hba);
 		} else if (lrbp->command_type == UTP_CMD_TYPE_DEV_MANAGE ||
 			lrbp->command_type == UTP_CMD_TYPE_UFS_STORAGE) {
-			if (hba->dev_cmd.complete)
+			if (hba->dev_cmd.complete) {
+				ufshcd_add_command_trace(hba, index,
+						"dev_complete");
 				complete(hba->dev_cmd.complete);
+			}
 		}
+		if (ufshcd_is_clkscaling_supported(hba))
+			hba->clk_scaling.active_reqs--;
+		if (ufshcd_is_clkscaling_supported(hba))
+			hba->clk_scaling.active_reqs--;
 	}
 
 	/* clear corresponding bits of completed commands */
@@ -3828,6 +4719,7 @@ static int ufshcd_enable_auto_bkops(struct ufs_hba *hba)
 	}
 
 	hba->auto_bkops_enabled = true;
+	trace_ufshcd_auto_bkops_state(dev_name(hba->dev), "Enabled");
 
 	/* No need of URGENT_BKOPS exception from the device */
 	err = ufshcd_disable_ee(hba, MASK_EE_URGENT_BKOPS);
@@ -3878,23 +4770,31 @@ static int ufshcd_disable_auto_bkops(struct ufs_hba *hba)
 	}
 
 	hba->auto_bkops_enabled = false;
+	trace_ufshcd_auto_bkops_state(dev_name(hba->dev), "Disabled");
 out:
 	return err;
 }
 
 /**
- * ufshcd_force_reset_auto_bkops - force enable of auto bkops
+ * ufshcd_force_reset_auto_bkops - force reset auto bkops state
  * @hba: per adapter instance
  *
  * After a device reset the device may toggle the BKOPS_EN flag
  * to default value. The s/w tracking variables should be updated
- * as well. Do this by forcing enable of auto bkops.
+ * as well. This function would change the auto-bkops state based on
+ * UFSHCD_CAP_KEEP_AUTO_BKOPS_ENABLED_EXCEPT_SUSPEND.
  */
-static void  ufshcd_force_reset_auto_bkops(struct ufs_hba *hba)
+static void ufshcd_force_reset_auto_bkops(struct ufs_hba *hba)
 {
-	hba->auto_bkops_enabled = false;
-	hba->ee_ctrl_mask |= MASK_EE_URGENT_BKOPS;
-	ufshcd_enable_auto_bkops(hba);
+	if (ufshcd_keep_autobkops_enabled_except_suspend(hba)) {
+		hba->auto_bkops_enabled = false;
+		hba->ee_ctrl_mask |= MASK_EE_URGENT_BKOPS;
+		ufshcd_enable_auto_bkops(hba);
+	} else {
+		hba->auto_bkops_enabled = true;
+		hba->ee_ctrl_mask &= ~MASK_EE_URGENT_BKOPS;
+		ufshcd_disable_auto_bkops(hba);
+	}
 }
 
 static inline int ufshcd_get_bkops_status(struct ufs_hba *hba, u32 *status)
@@ -4246,6 +5146,14 @@ out:
 	pm_runtime_put_sync(hba->dev);
 }
 
+static void ufshcd_update_uic_reg_hist(struct ufs_uic_err_reg_hist *reg_hist,
+		u32 reg)
+{
+	reg_hist->reg[reg_hist->pos] = reg;
+	reg_hist->tstamp[reg_hist->pos] = ktime_get();
+	reg_hist->pos = (reg_hist->pos + 1) % UIC_ERR_REG_HIST_LENGTH;
+}
+
 /**
  * ufshcd_update_uic_error - check and set fatal UIC error flags.
  * @hba: per-adapter instance
@@ -4258,15 +5166,20 @@ static void ufshcd_update_uic_error(struct ufs_hba *hba)
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_PHY_ADAPTER_LAYER);
 	/* Ignore LINERESET indication, as this is not an error */
 	if ((reg & UIC_PHY_ADAPTER_LAYER_ERROR) &&
-			(reg & UIC_PHY_ADAPTER_LAYER_LANE_ERR_MASK))
+			(reg & UIC_PHY_ADAPTER_LAYER_LANE_ERR_MASK)) {
 		/*
 		 * To know whether this error is fatal or not, DB timeout
 		 * must be checked but this error is handled separately.
 		 */
 		dev_dbg(hba->dev, "%s: UIC Lane error reported\n", __func__);
+		ufshcd_update_uic_reg_hist(&hba->ufs_stats.pa_err, reg);
+	}
 
 	/* PA_INIT_ERROR is fatal and needs UIC reset */
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_DATA_LINK_LAYER);
+	if (reg)
+		ufshcd_update_uic_reg_hist(&hba->ufs_stats.dl_err, reg);
+
 	if (reg & UIC_DATA_LINK_LAYER_ERROR_PA_INIT)
 		hba->uic_error |= UFSHCD_UIC_DL_PA_INIT_ERROR;
 	else if (hba->dev_quirks &
@@ -4280,16 +5193,22 @@ static void ufshcd_update_uic_error(struct ufs_hba *hba)
 
 	/* UIC NL/TL/DME errors needs software retry */
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_NETWORK_LAYER);
-	if (reg)
+	if (reg) {
+		ufshcd_update_uic_reg_hist(&hba->ufs_stats.nl_err, reg);
 		hba->uic_error |= UFSHCD_UIC_NL_ERROR;
+	}
 
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_TRANSPORT_LAYER);
-	if (reg)
+	if (reg) {
+		ufshcd_update_uic_reg_hist(&hba->ufs_stats.tl_err, reg);
 		hba->uic_error |= UFSHCD_UIC_TL_ERROR;
+	}
 
 	reg = ufshcd_readl(hba, REG_UIC_ERROR_CODE_DME);
-	if (reg)
+	if (reg) {
+		ufshcd_update_uic_reg_hist(&hba->ufs_stats.dme_err, reg);
 		hba->uic_error |= UFSHCD_UIC_DME_ERROR;
+	}
 
 	dev_dbg(hba->dev, "%s: UIC error flags = 0x%08x\n",
 			__func__, hba->uic_error);
@@ -4327,6 +5246,22 @@ static void ufshcd_check_errors(struct ufs_hba *hba)
 			scsi_block_requests(hba->host);
 
 			hba->ufshcd_state = UFSHCD_STATE_EH_SCHEDULED;
+
+			/* dump controller state before resetting */
+			if (hba->saved_err & (INT_FATAL_ERRORS | UIC_ERROR)) {
+				bool pr_prdt = !!(hba->saved_err &
+						SYSTEM_BUS_FATAL_ERROR);
+
+				dev_err(hba->dev, "%s: saved_err 0x%x saved_uic_err 0x%x\n",
+					__func__, hba->saved_err,
+					hba->saved_uic_err);
+
+				ufshcd_print_host_regs(hba);
+				ufshcd_print_pwr_info(hba);
+				ufshcd_print_tmrs(hba, hba->outstanding_tasks);
+				ufshcd_print_trs(hba, hba->outstanding_reqs,
+							pr_prdt);
+			}
 			schedule_work(&hba->eh_work);
 		}
 	}
@@ -4557,7 +5492,9 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd)
 	spin_lock_irqsave(host->host_lock, flags);
 	ufshcd_transfer_req_compl(hba);
 	spin_unlock_irqrestore(host->host_lock, flags);
+
 out:
+	hba->req_abort_count = 0;
 	if (!err) {
 		err = SUCCESS;
 	} else {
@@ -4567,6 +5504,17 @@ out:
 	return err;
 }
 
+static void ufshcd_set_req_abort_skip(struct ufs_hba *hba, unsigned long bitmap)
+{
+	struct ufshcd_lrb *lrbp;
+	int tag;
+
+	for_each_set_bit(tag, &bitmap, hba->nutrs) {
+		lrbp = &hba->lrb[tag];
+		lrbp->req_abort_skip = true;
+	}
+}
+
 /**
  * ufshcd_abort - abort a specific command
  * @cmd: SCSI command pointer
@@ -4594,6 +5542,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	host = cmd->device->host;
 	hba = shost_priv(host);
 	tag = cmd->request->tag;
+	lrbp = &hba->lrb[tag];
 	if (!ufshcd_valid_tag(hba, tag)) {
 		dev_err(hba->dev,
 			"%s: invalid command tag %d: cmd=0x%p, cmd->request=0x%p",
@@ -4601,6 +5550,16 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 		BUG();
 	}
 
+	/*
+	 * Task abort to the device W-LUN is illegal. When this command
+	 * will fail, due to spec violation, scsi err handling next step
+	 * will be to send LU reset which, again, is a spec violation.
+	 * To avoid these unnecessary/illegal step we skip to the last error
+	 * handling stage: reset and restore.
+	 */
+	if (lrbp->lun == UFS_UPIU_UFS_DEVICE_WLUN)
+		return ufshcd_eh_host_reset_handler(cmd);
+
 	ufshcd_hold(hba, false);
 	reg = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 	/* If command is already aborted/completed, return SUCCESS */
@@ -4617,18 +5576,48 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 		__func__, tag);
 	}
 
-	lrbp = &hba->lrb[tag];
+	/* Print Transfer Request of aborted task */
+	dev_err(hba->dev, "%s: Device abort task at tag %d\n", __func__, tag);
+
+	/*
+	 * Print detailed info about aborted request.
+	 * As more than one request might get aborted at the same time,
+	 * print full information only for the first aborted request in order
+	 * to reduce repeated printouts. For other aborted requests only print
+	 * basic details.
+	 */
+	scsi_print_command(hba->lrb[tag].cmd);
+	if (!hba->req_abort_count) {
+		ufshcd_print_host_regs(hba);
+		ufshcd_print_host_state(hba);
+		ufshcd_print_pwr_info(hba);
+		ufshcd_print_trs(hba, 1 << tag, true);
+	} else {
+		ufshcd_print_trs(hba, 1 << tag, false);
+	}
+	hba->req_abort_count++;
+
+	/* Skip task abort in case previous aborts failed and report failure */
+	if (lrbp->req_abort_skip) {
+		err = -EIO;
+		goto out;
+	}
+
 	for (poll_cnt = 100; poll_cnt; poll_cnt--) {
 		err = ufshcd_issue_tm_cmd(hba, lrbp->lun, lrbp->task_tag,
 				UFS_QUERY_TASK, &resp);
 		if (!err && resp == UPIU_TASK_MANAGEMENT_FUNC_SUCCEEDED) {
 			/* cmd pending in the device */
+			dev_err(hba->dev, "%s: cmd pending in the device. tag = %d\n",
+				__func__, tag);
 			break;
 		} else if (!err && resp == UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
 			/*
 			 * cmd not pending in the device, check if it is
 			 * in transition.
 			 */
+			dev_err(hba->dev, "%s: cmd at tag %d not pending in the device.\n",
+				__func__, tag);
 			reg = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
 			if (reg & (1 << tag)) {
 				/* sleep for max. 200us to stabilize */
@@ -4636,8 +5625,13 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 				continue;
 			}
 			/* command completed already */
+			dev_err(hba->dev, "%s: cmd at tag %d successfully cleared from DB.\n",
+				__func__, tag);
 			goto out;
 		} else {
+			dev_err(hba->dev,
+				"%s: no response from device. tag = %d, err %d\n",
+				__func__, tag, err);
 			if (!err)
 				err = resp; /* service response error */
 			goto out;
@@ -4652,14 +5646,20 @@ static int ufshcd_abort(struct scsi_cmnd *cmd)
 	err = ufshcd_issue_tm_cmd(hba, lrbp->lun, lrbp->task_tag,
 			UFS_ABORT_TASK, &resp);
 	if (err || resp != UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
-		if (!err)
+		if (!err) {
 			err = resp; /* service response error */
+			dev_err(hba->dev, "%s: issued. tag = %d, err %d\n",
+				__func__, tag, err);
+		}
 		goto out;
 	}
 
 	err = ufshcd_clear_cmd(hba, tag);
-	if (err)
+	if (err) {
+		dev_err(hba->dev, "%s: Failed clearing cmd at tag %d, err %d\n",
+			__func__, tag, err);
 		goto out;
+	}
 
 	scsi_dma_unmap(cmd);
 
@@ -4676,6 +5676,7 @@ out:
 		err = SUCCESS;
 	} else {
 		dev_err(hba->dev, "%s: failed with err %d\n", __func__, err);
+		ufshcd_set_req_abort_skip(hba, hba->outstanding_reqs);
 		err = FAILED;
 	}
 
@@ -4707,6 +5708,9 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
 	ufshcd_hba_stop(hba, false);
 	spin_unlock_irqrestore(hba->host->host_lock, flags);
 
+	/* scale up clocks to max frequency before full reinitialization */
+	ufshcd_scale_clks(hba, true);
+
 	err = ufshcd_hba_enable(hba);
 	if (err)
 		goto out;
@@ -4822,7 +5826,7 @@ static u32 ufshcd_get_max_icc_level(int sup_curr_uA, u32 start_scan, char *buff)
 	u16 unit;
 
 	for (i = start_scan; i >= 0; i--) {
-		data = be16_to_cpu(*((u16 *)(buff + 2*i)));
+		data = be16_to_cpup((__be16 *)&buff[2 * i]);
 		unit = (data & ATTR_ICC_LVL_UNIT_MASK) >>
 						ATTR_ICC_LVL_UNIT_OFFSET;
 		curr_uA = data & ATTR_ICC_LVL_VALUE_MASK;
@@ -5008,8 +6012,8 @@ out:
 	return ret;
 }
 
-static int ufs_get_device_info(struct ufs_hba *hba,
-				struct ufs_device_info *card_data)
+static int ufs_get_device_desc(struct ufs_hba *hba,
+			       struct ufs_dev_desc *dev_desc)
 {
 	int err;
 	u8 model_index;
@@ -5028,7 +6032,7 @@ static int ufs_get_device_info(struct ufs_hba *hba,
 	 * getting vendor (manufacturerID) and Bank Index in big endian
 	 * format
 	 */
-	card_data->wmanufacturerid = desc_buf[DEVICE_DESC_PARAM_MANF_ID] << 8 |
+	dev_desc->wmanufacturerid = desc_buf[DEVICE_DESC_PARAM_MANF_ID] << 8 |
 				     desc_buf[DEVICE_DESC_PARAM_MANF_ID + 1];
 
 	model_index = desc_buf[DEVICE_DESC_PARAM_PRDCT_NAME];
@@ -5042,36 +6046,26 @@ static int ufs_get_device_info(struct ufs_hba *hba,
 	}
 
 	str_desc_buf[QUERY_DESC_STRING_MAX_SIZE] = '\0';
-	strlcpy(card_data->model, (str_desc_buf + QUERY_DESC_HDR_SIZE),
+	strlcpy(dev_desc->model, (str_desc_buf + QUERY_DESC_HDR_SIZE),
 		min_t(u8, str_desc_buf[QUERY_DESC_LENGTH_OFFSET],
 		      MAX_MODEL_LEN));
 
 	/* Null terminate the model string */
-	card_data->model[MAX_MODEL_LEN] = '\0';
+	dev_desc->model[MAX_MODEL_LEN] = '\0';
 
 out:
 	return err;
 }
 
-void ufs_advertise_fixup_device(struct ufs_hba *hba)
+static void ufs_fixup_device_setup(struct ufs_hba *hba,
+				   struct ufs_dev_desc *dev_desc)
 {
-	int err;
 	struct ufs_dev_fix *f;
-	struct ufs_device_info card_data;
-
-	card_data.wmanufacturerid = 0;
-
-	err = ufs_get_device_info(hba, &card_data);
-	if (err) {
-		dev_err(hba->dev, "%s: Failed getting device info. err = %d\n",
-			__func__, err);
-		return;
-	}
 
 	for (f = ufs_fixups; f->quirk; f++) {
-		if (((f->card.wmanufacturerid == card_data.wmanufacturerid) ||
-		    (f->card.wmanufacturerid == UFS_ANY_VENDOR)) &&
-		    (STR_PRFX_EQUAL(f->card.model, card_data.model) ||
+		if ((f->card.wmanufacturerid == dev_desc->wmanufacturerid ||
+		     f->card.wmanufacturerid == UFS_ANY_VENDOR) &&
+		    (STR_PRFX_EQUAL(f->card.model, dev_desc->model) ||
 		     !strcmp(f->card.model, UFS_ANY_MODEL)))
 			hba->dev_quirks |= f->quirk;
 	}
@@ -5241,6 +6235,22 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
 	ufshcd_vops_apply_dev_quirks(hba);
 }
 
+static void ufshcd_clear_dbg_ufs_stats(struct ufs_hba *hba)
+{
+	int err_reg_hist_size = sizeof(struct ufs_uic_err_reg_hist);
+
+	hba->ufs_stats.hibern8_exit_cnt = 0;
+	hba->ufs_stats.last_hibern8_exit_tstamp = ktime_set(0, 0);
+
+	memset(&hba->ufs_stats.pa_err, 0, err_reg_hist_size);
+	memset(&hba->ufs_stats.dl_err, 0, err_reg_hist_size);
+	memset(&hba->ufs_stats.nl_err, 0, err_reg_hist_size);
+	memset(&hba->ufs_stats.tl_err, 0, err_reg_hist_size);
+	memset(&hba->ufs_stats.dme_err, 0, err_reg_hist_size);
+
+	hba->req_abort_count = 0;
+}
+
 /**
  * ufshcd_probe_hba - probe hba to detect device and initialize
  * @hba: per-adapter instance
@@ -5249,18 +6259,21 @@ static void ufshcd_tune_unipro_params(struct ufs_hba *hba)
  */
 static int ufshcd_probe_hba(struct ufs_hba *hba)
 {
+	struct ufs_dev_desc card = {0};
 	int ret;
+	ktime_t start = ktime_get();
 
 	ret = ufshcd_link_startup(hba);
 	if (ret)
 		goto out;
 
-	ufshcd_init_pwr_info(hba);
-
 	/* set the default level for urgent bkops */
 	hba->urgent_bkops_lvl = BKOPS_STATUS_PERF_IMPACT;
 	hba->is_urgent_bkops_lvl_checked = false;
 
+	/* Debug counters initialization */
+	ufshcd_clear_dbg_ufs_stats(hba);
+
 	/* UniPro link is active now */
 	ufshcd_set_link_active(hba);
 
@@ -5272,7 +6285,14 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	if (ret)
 		goto out;
 
-	ufs_advertise_fixup_device(hba);
+	ret = ufs_get_device_desc(hba, &card);
+	if (ret) {
+		dev_err(hba->dev, "%s: Failed getting device info. err = %d\n",
+			__func__, ret);
+		goto out;
+	}
+
+	ufs_fixup_device_setup(hba, &card);
 	ufshcd_tune_unipro_params(hba);
 
 	ret = ufshcd_set_vccq_rail_unused(hba,
@@ -5320,6 +6340,27 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 		if (ufshcd_scsi_add_wlus(hba))
 			goto out;
 
+		/* Initialize devfreq after UFS device is detected */
+		if (ufshcd_is_clkscaling_supported(hba)) {
+			memcpy(&hba->clk_scaling.saved_pwr_info.info,
+				&hba->pwr_info,
+				sizeof(struct ufs_pa_layer_attr));
+			hba->clk_scaling.saved_pwr_info.is_valid = true;
+			if (!hba->devfreq) {
+				hba->devfreq = devm_devfreq_add_device(hba->dev,
+							&ufs_devfreq_profile,
+							"simple_ondemand",
+							NULL);
+				if (IS_ERR(hba->devfreq)) {
+					ret = PTR_ERR(hba->devfreq);
+					dev_err(hba->dev, "Unable to register with devfreq %d\n",
+							ret);
+					goto out;
+				}
+			}
+			hba->clk_scaling.is_allowed = true;
+		}
+
 		scsi_scan_host(hba->host);
 		pm_runtime_put_sync(hba->dev);
 	}
@@ -5327,9 +6368,6 @@ static int ufshcd_probe_hba(struct ufs_hba *hba)
 	if (!hba->is_init_prefetch)
 		hba->is_init_prefetch = true;
 
-	/* Resume devfreq after UFS device is detected */
-	ufshcd_resume_clkscaling(hba);
-
 out:
 	/*
 	 * If we failed to initialize the device or the device is not
@@ -5340,6 +6378,9 @@ out:
 		ufshcd_hba_exit(hba);
 	}
 
+	trace_ufshcd_init(dev_name(hba->dev), ret,
+		ktime_to_us(ktime_sub(ktime_get(), start)),
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
 	return ret;
 }
 
@@ -5650,6 +6691,8 @@ static int __ufshcd_setup_clocks(struct ufs_hba *hba, bool on,
 	struct ufs_clk_info *clki;
 	struct list_head *head = &hba->clk_list_head;
 	unsigned long flags;
+	ktime_t start = ktime_get();
+	bool clk_state_changed = false;
 
 	if (!head || list_empty(head))
 		goto out;
@@ -5663,6 +6706,7 @@ static int __ufshcd_setup_clocks(struct ufs_hba *hba, bool on,
 			if (skip_ref_clk && !strcmp(clki->name, "ref_clk"))
 				continue;
 
+			clk_state_changed = on ^ clki->enabled;
 			if (on && !clki->enabled) {
 				ret = clk_prepare_enable(clki->clk);
 				if (ret) {
@@ -5689,11 +6733,18 @@ out:
 			if (!IS_ERR_OR_NULL(clki->clk) && clki->enabled)
 				clk_disable_unprepare(clki->clk);
 		}
-	} else if (on) {
+	} else if (!ret && on) {
 		spin_lock_irqsave(hba->host->host_lock, flags);
 		hba->clk_gating.state = CLKS_ON;
+		trace_ufshcd_clk_gating(dev_name(hba->dev),
+					hba->clk_gating.state);
 		spin_unlock_irqrestore(hba->host->host_lock, flags);
 	}
+
+	if (clk_state_changed)
+		trace_ufshcd_profile_clk_gating(dev_name(hba->dev),
+			(on ? "on" : "off"),
+			ktime_to_us(ktime_sub(ktime_get(), start)), ret);
 	return ret;
 }
 
@@ -5835,6 +6886,11 @@ static void ufshcd_hba_exit(struct ufs_hba *hba)
 		ufshcd_variant_hba_exit(hba);
 		ufshcd_setup_vreg(hba, false);
 		ufshcd_suspend_clkscaling(hba);
+		if (ufshcd_is_clkscaling_supported(hba)) {
+			if (hba->devfreq)
+				ufshcd_suspend_clkscaling(hba);
+			destroy_workqueue(hba->clk_scaling.workq);
+		}
 		ufshcd_setup_clocks(hba, false);
 		ufshcd_setup_hba_vreg(hba, false);
 		hba->is_powered = false;
@@ -6110,7 +7166,11 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 	ufshcd_hold(hba, false);
 	hba->clk_gating.is_suspended = true;
 
-	ufshcd_suspend_clkscaling(hba);
+	if (hba->clk_scaling.is_allowed) {
+		cancel_work_sync(&hba->clk_scaling.suspend_work);
+		cancel_work_sync(&hba->clk_scaling.resume_work);
+		ufshcd_suspend_clkscaling(hba);
+	}
 
 	if (req_dev_pwr_mode == UFS_ACTIVE_PWR_MODE &&
 			req_link_state == UIC_LINK_ACTIVE_STATE) {
@@ -6176,6 +7236,7 @@ disable_clks:
 		__ufshcd_setup_clocks(hba, false, true);
 
 	hba->clk_gating.state = CLKS_OFF;
+	trace_ufshcd_clk_gating(dev_name(hba->dev), hba->clk_gating.state);
 	/*
 	 * Disable the host irq as host controller as there won't be any
 	 * host controller transaction expected till resume.
@@ -6186,7 +7247,8 @@ disable_clks:
 	goto out;
 
 set_link_active:
-	ufshcd_resume_clkscaling(hba);
+	if (hba->clk_scaling.is_allowed)
+		ufshcd_resume_clkscaling(hba);
 	ufshcd_vreg_set_hpm(hba);
 	if (ufshcd_is_link_hibern8(hba) && !ufshcd_uic_hibern8_exit(hba))
 		ufshcd_set_link_active(hba);
@@ -6196,7 +7258,8 @@ set_dev_active:
 	if (!ufshcd_set_dev_pwr_mode(hba, UFS_ACTIVE_PWR_MODE))
 		ufshcd_disable_auto_bkops(hba);
 enable_gating:
-	ufshcd_resume_clkscaling(hba);
+	if (hba->clk_scaling.is_allowed)
+		ufshcd_resume_clkscaling(hba);
 	hba->clk_gating.is_suspended = false;
 	ufshcd_release(hba);
 out:
@@ -6268,14 +7331,19 @@ static int ufshcd_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
 			goto set_old_link_state;
 	}
 
-	/*
-	 * If BKOPs operations are urgently needed at this moment then
-	 * keep auto-bkops enabled or else disable it.
-	 */
-	ufshcd_urgent_bkops(hba);
+	if (ufshcd_keep_autobkops_enabled_except_suspend(hba))
+		ufshcd_enable_auto_bkops(hba);
+	else
+		/*
+		 * If BKOPs operations are urgently needed at this moment then
+		 * keep auto-bkops enabled or else disable it.
+		 */
+		ufshcd_urgent_bkops(hba);
+
 	hba->clk_gating.is_suspended = false;
 
-	ufshcd_resume_clkscaling(hba);
+	if (hba->clk_scaling.is_allowed)
+		ufshcd_resume_clkscaling(hba);
 
 	/* Schedule clock gating in case of no access to UFS device yet */
 	ufshcd_release(hba);
@@ -6289,7 +7357,8 @@ disable_vreg:
 	ufshcd_vreg_set_lpm(hba);
 disable_irq_and_vops_clks:
 	ufshcd_disable_irq(hba);
-	ufshcd_suspend_clkscaling(hba);
+	if (hba->clk_scaling.is_allowed)
+		ufshcd_suspend_clkscaling(hba);
 	ufshcd_setup_clocks(hba, false);
 out:
 	hba->pm_op_in_progress = 0;
@@ -6308,6 +7377,7 @@ out:
 int ufshcd_system_suspend(struct ufs_hba *hba)
 {
 	int ret = 0;
+	ktime_t start = ktime_get();
 
 	if (!hba || !hba->is_powered)
 		return 0;
@@ -6334,6 +7404,9 @@ int ufshcd_system_suspend(struct ufs_hba *hba)
 
 	ret = ufshcd_suspend(hba, UFS_SYSTEM_PM);
 out:
+	trace_ufshcd_system_suspend(dev_name(hba->dev), ret,
+		ktime_to_us(ktime_sub(ktime_get(), start)),
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
 	if (!ret)
 		hba->is_sys_suspended = true;
 	return ret;
@@ -6349,6 +7422,9 @@ EXPORT_SYMBOL(ufshcd_system_suspend);
 
 int ufshcd_system_resume(struct ufs_hba *hba)
 {
+	int ret = 0;
+	ktime_t start = ktime_get();
+
 	if (!hba)
 		return -EINVAL;
 
@@ -6357,9 +7433,14 @@ int ufshcd_system_resume(struct ufs_hba *hba)
 		 * Let the runtime resume take care of resuming
 		 * if runtime suspended.
 		 */
-		return 0;
-
-	return ufshcd_resume(hba, UFS_SYSTEM_PM);
+		goto out;
+	else
+		ret = ufshcd_resume(hba, UFS_SYSTEM_PM);
+out:
+	trace_ufshcd_system_resume(dev_name(hba->dev), ret,
+		ktime_to_us(ktime_sub(ktime_get(), start)),
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
+	return ret;
 }
 EXPORT_SYMBOL(ufshcd_system_resume);
 
@@ -6373,13 +7454,21 @@ EXPORT_SYMBOL(ufshcd_system_resume);
  */
 int ufshcd_runtime_suspend(struct ufs_hba *hba)
 {
+	int ret = 0;
+	ktime_t start = ktime_get();
+
 	if (!hba)
 		return -EINVAL;
 
 	if (!hba->is_powered)
-		return 0;
-
-	return ufshcd_suspend(hba, UFS_RUNTIME_PM);
+		goto out;
+	else
+		ret = ufshcd_suspend(hba, UFS_RUNTIME_PM);
+out:
+	trace_ufshcd_runtime_suspend(dev_name(hba->dev), ret,
+		ktime_to_us(ktime_sub(ktime_get(), start)),
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
+	return ret;
 }
 EXPORT_SYMBOL(ufshcd_runtime_suspend);
 
@@ -6406,13 +7495,21 @@ EXPORT_SYMBOL(ufshcd_runtime_suspend);
  */
 int ufshcd_runtime_resume(struct ufs_hba *hba)
 {
+	int ret = 0;
+	ktime_t start = ktime_get();
+
 	if (!hba)
 		return -EINVAL;
 
 	if (!hba->is_powered)
-		return 0;
-
-	return ufshcd_resume(hba, UFS_RUNTIME_PM);
+		goto out;
+	else
+		ret = ufshcd_resume(hba, UFS_RUNTIME_PM);
+out:
+	trace_ufshcd_runtime_resume(dev_name(hba->dev), ret,
+		ktime_to_us(ktime_sub(ktime_get(), start)),
+		hba->curr_dev_pwr_mode, hba->uic_link_state);
+	return ret;
 }
 EXPORT_SYMBOL(ufshcd_runtime_resume);
 
@@ -6422,6 +7519,127 @@ int ufshcd_runtime_idle(struct ufs_hba *hba)
 }
 EXPORT_SYMBOL(ufshcd_runtime_idle);
 
+static inline ssize_t ufshcd_pm_lvl_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t count,
+					   bool rpm)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	unsigned long flags, value;
+
+	if (kstrtoul(buf, 0, &value))
+		return -EINVAL;
+
+	if ((value < UFS_PM_LVL_0) || (value >= UFS_PM_LVL_MAX))
+		return -EINVAL;
+
+	spin_lock_irqsave(hba->host->host_lock, flags);
+	if (rpm)
+		hba->rpm_lvl = value;
+	else
+		hba->spm_lvl = value;
+	spin_unlock_irqrestore(hba->host->host_lock, flags);
+	return count;
+}
+
+static ssize_t ufshcd_rpm_lvl_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	int curr_len;
+	u8 lvl;
+
+	curr_len = snprintf(buf, PAGE_SIZE,
+			    "\nCurrent Runtime PM level [%d] => dev_state [%s] link_state [%s]\n",
+			    hba->rpm_lvl,
+			    ufschd_ufs_dev_pwr_mode_to_string(
+				ufs_pm_lvl_states[hba->rpm_lvl].dev_state),
+			    ufschd_uic_link_state_to_string(
+				ufs_pm_lvl_states[hba->rpm_lvl].link_state));
+
+	curr_len += snprintf((buf + curr_len), (PAGE_SIZE - curr_len),
+			     "\nAll available Runtime PM levels info:\n");
+	for (lvl = UFS_PM_LVL_0; lvl < UFS_PM_LVL_MAX; lvl++)
+		curr_len += snprintf((buf + curr_len), (PAGE_SIZE - curr_len),
+				     "\tRuntime PM level [%d] => dev_state [%s] link_state [%s]\n",
+				    lvl,
+				    ufschd_ufs_dev_pwr_mode_to_string(
+					ufs_pm_lvl_states[lvl].dev_state),
+				    ufschd_uic_link_state_to_string(
+					ufs_pm_lvl_states[lvl].link_state));
+
+	return curr_len;
+}
+
+static ssize_t ufshcd_rpm_lvl_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return ufshcd_pm_lvl_store(dev, attr, buf, count, true);
+}
+
+static void ufshcd_add_rpm_lvl_sysfs_nodes(struct ufs_hba *hba)
+{
+	hba->rpm_lvl_attr.show = ufshcd_rpm_lvl_show;
+	hba->rpm_lvl_attr.store = ufshcd_rpm_lvl_store;
+	sysfs_attr_init(&hba->rpm_lvl_attr.attr);
+	hba->rpm_lvl_attr.attr.name = "rpm_lvl";
+	hba->rpm_lvl_attr.attr.mode = 0644;
+	if (device_create_file(hba->dev, &hba->rpm_lvl_attr))
+		dev_err(hba->dev, "Failed to create sysfs for rpm_lvl\n");
+}
+
+static ssize_t ufshcd_spm_lvl_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct ufs_hba *hba = dev_get_drvdata(dev);
+	int curr_len;
+	u8 lvl;
+
+	curr_len = snprintf(buf, PAGE_SIZE,
+			    "\nCurrent System PM level [%d] => dev_state [%s] link_state [%s]\n",
+			    hba->spm_lvl,
+			    ufschd_ufs_dev_pwr_mode_to_string(
+				ufs_pm_lvl_states[hba->spm_lvl].dev_state),
+			    ufschd_uic_link_state_to_string(
+				ufs_pm_lvl_states[hba->spm_lvl].link_state));
+
+	curr_len += snprintf((buf + curr_len), (PAGE_SIZE - curr_len),
+			     "\nAll available System PM levels info:\n");
+	for (lvl = UFS_PM_LVL_0; lvl < UFS_PM_LVL_MAX; lvl++)
+		curr_len += snprintf((buf + curr_len), (PAGE_SIZE - curr_len),
+				     "\tSystem PM level [%d] => dev_state [%s] link_state [%s]\n",
+				    lvl,
+				    ufschd_ufs_dev_pwr_mode_to_string(
+					ufs_pm_lvl_states[lvl].dev_state),
+				    ufschd_uic_link_state_to_string(
+					ufs_pm_lvl_states[lvl].link_state));
+
+	return curr_len;
+}
+
+static ssize_t ufshcd_spm_lvl_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return ufshcd_pm_lvl_store(dev, attr, buf, count, false);
+}
+
+static void ufshcd_add_spm_lvl_sysfs_nodes(struct ufs_hba *hba)
+{
+	hba->spm_lvl_attr.show = ufshcd_spm_lvl_show;
+	hba->spm_lvl_attr.store = ufshcd_spm_lvl_store;
+	sysfs_attr_init(&hba->spm_lvl_attr.attr);
+	hba->spm_lvl_attr.attr.name = "spm_lvl";
+	hba->spm_lvl_attr.attr.mode = 0644;
+	if (device_create_file(hba->dev, &hba->spm_lvl_attr))
+		dev_err(hba->dev, "Failed to create sysfs for spm_lvl\n");
+}
+
+static inline void ufshcd_add_sysfs_nodes(struct ufs_hba *hba)
+{
+	ufshcd_add_rpm_lvl_sysfs_nodes(hba);
+	ufshcd_add_spm_lvl_sysfs_nodes(hba);
+}
+
 /**
  * ufshcd_shutdown - shutdown routine
  * @hba: per adapter instance
@@ -6465,6 +7683,8 @@ void ufshcd_remove(struct ufs_hba *hba)
 	ufshcd_hba_stop(hba, true);
 
 	ufshcd_exit_clk_gating(hba);
+	if (ufshcd_is_clkscaling_supported(hba))
+		device_remove_file(hba->dev, &hba->clk_scaling.enable_attr);
 	ufshcd_hba_exit(hba);
 }
 EXPORT_SYMBOL_GPL(ufshcd_remove);
@@ -6531,149 +7751,6 @@ out_error:
 }
 EXPORT_SYMBOL(ufshcd_alloc_host);
 
-static int ufshcd_scale_clks(struct ufs_hba *hba, bool scale_up)
-{
-	int ret = 0;
-	struct ufs_clk_info *clki;
-	struct list_head *head = &hba->clk_list_head;
-
-	if (!head || list_empty(head))
-		goto out;
-
-	ret = ufshcd_vops_clk_scale_notify(hba, scale_up, PRE_CHANGE);
-	if (ret)
-		return ret;
-
-	list_for_each_entry(clki, head, list) {
-		if (!IS_ERR_OR_NULL(clki->clk)) {
-			if (scale_up && clki->max_freq) {
-				if (clki->curr_freq == clki->max_freq)
-					continue;
-				ret = clk_set_rate(clki->clk, clki->max_freq);
-				if (ret) {
-					dev_err(hba->dev, "%s: %s clk set rate(%dHz) failed, %d\n",
-						__func__, clki->name,
-						clki->max_freq, ret);
-					break;
-				}
-				clki->curr_freq = clki->max_freq;
-
-			} else if (!scale_up && clki->min_freq) {
-				if (clki->curr_freq == clki->min_freq)
-					continue;
-				ret = clk_set_rate(clki->clk, clki->min_freq);
-				if (ret) {
-					dev_err(hba->dev, "%s: %s clk set rate(%dHz) failed, %d\n",
-						__func__, clki->name,
-						clki->min_freq, ret);
-					break;
-				}
-				clki->curr_freq = clki->min_freq;
-			}
-		}
-		dev_dbg(hba->dev, "%s: clk: %s, rate: %lu\n", __func__,
-				clki->name, clk_get_rate(clki->clk));
-	}
-
-	ret = ufshcd_vops_clk_scale_notify(hba, scale_up, POST_CHANGE);
-
-out:
-	return ret;
-}
-
-static int ufshcd_devfreq_target(struct device *dev,
-				unsigned long *freq, u32 flags)
-{
-	int err = 0;
-	struct ufs_hba *hba = dev_get_drvdata(dev);
-	bool release_clk_hold = false;
-	unsigned long irq_flags;
-
-	if (!ufshcd_is_clkscaling_enabled(hba))
-		return -EINVAL;
-
-	spin_lock_irqsave(hba->host->host_lock, irq_flags);
-	if (ufshcd_eh_in_progress(hba)) {
-		spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
-		return 0;
-	}
-
-	if (ufshcd_is_clkgating_allowed(hba) &&
-	    (hba->clk_gating.state != CLKS_ON)) {
-		if (cancel_delayed_work(&hba->clk_gating.gate_work)) {
-			/* hold the vote until the scaling work is completed */
-			hba->clk_gating.active_reqs++;
-			release_clk_hold = true;
-			hba->clk_gating.state = CLKS_ON;
-		} else {
-			/*
-			 * Clock gating work seems to be running in parallel
-			 * hence skip scaling work to avoid deadlock between
-			 * current scaling work and gating work.
-			 */
-			spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
-			return 0;
-		}
-	}
-	spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
-
-	if (*freq == UINT_MAX)
-		err = ufshcd_scale_clks(hba, true);
-	else if (*freq == 0)
-		err = ufshcd_scale_clks(hba, false);
-
-	spin_lock_irqsave(hba->host->host_lock, irq_flags);
-	if (release_clk_hold)
-		__ufshcd_release(hba);
-	spin_unlock_irqrestore(hba->host->host_lock, irq_flags);
-
-	return err;
-}
-
-static int ufshcd_devfreq_get_dev_status(struct device *dev,
-		struct devfreq_dev_status *stat)
-{
-	struct ufs_hba *hba = dev_get_drvdata(dev);
-	struct ufs_clk_scaling *scaling = &hba->clk_scaling;
-	unsigned long flags;
-
-	if (!ufshcd_is_clkscaling_enabled(hba))
-		return -EINVAL;
-
-	memset(stat, 0, sizeof(*stat));
-
-	spin_lock_irqsave(hba->host->host_lock, flags);
-	if (!scaling->window_start_t)
-		goto start_window;
-
-	if (scaling->is_busy_started)
-		scaling->tot_busy_t += ktime_to_us(ktime_sub(ktime_get(),
-					scaling->busy_start_t));
-
-	stat->total_time = jiffies_to_usecs((long)jiffies -
-				(long)scaling->window_start_t);
-	stat->busy_time = scaling->tot_busy_t;
-start_window:
-	scaling->window_start_t = jiffies;
-	scaling->tot_busy_t = 0;
-
-	if (hba->outstanding_reqs) {
-		scaling->busy_start_t = ktime_get();
-		scaling->is_busy_started = true;
-	} else {
-		scaling->busy_start_t = 0;
-		scaling->is_busy_started = false;
-	}
-	spin_unlock_irqrestore(hba->host->host_lock, flags);
-	return 0;
-}
-
-static struct devfreq_dev_profile ufs_devfreq_profile = {
-	.polling_ms	= 100,
-	.target		= ufshcd_devfreq_target,
-	.get_dev_status	= ufshcd_devfreq_get_dev_status,
-};
-
 /**
  * ufshcd_init - Driver initialization routine
  * @hba: per-adapter instance
@@ -6757,6 +7834,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	/* Initialize mutex for device management commands */
 	mutex_init(&hba->dev_cmd.lock);
 
+	init_rwsem(&hba->clk_scaling_lock);
+
 	/* Initialize device management tag acquire wait queue */
 	init_waitqueue_head(&hba->dev_cmd.tag_wq);
 
@@ -6795,22 +7874,38 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	err = ufshcd_hba_enable(hba);
 	if (err) {
 		dev_err(hba->dev, "Host controller enable failed\n");
+		ufshcd_print_host_regs(hba);
+		ufshcd_print_host_state(hba);
 		goto out_remove_scsi_host;
 	}
 
-	if (ufshcd_is_clkscaling_enabled(hba)) {
-		hba->devfreq = devm_devfreq_add_device(dev, &ufs_devfreq_profile,
-						   "simple_ondemand", NULL);
-		if (IS_ERR(hba->devfreq)) {
-			dev_err(hba->dev, "Unable to register with devfreq %ld\n",
-					PTR_ERR(hba->devfreq));
-			err = PTR_ERR(hba->devfreq);
-			goto out_remove_scsi_host;
-		}
-		/* Suspend devfreq until the UFS device is detected */
-		ufshcd_suspend_clkscaling(hba);
+	if (ufshcd_is_clkscaling_supported(hba)) {
+		char wq_name[sizeof("ufs_clkscaling_00")];
+
+		INIT_WORK(&hba->clk_scaling.suspend_work,
+			  ufshcd_clk_scaling_suspend_work);
+		INIT_WORK(&hba->clk_scaling.resume_work,
+			  ufshcd_clk_scaling_resume_work);
+
+		snprintf(wq_name, ARRAY_SIZE(wq_name), "ufs_clkscaling_%d",
+			 host->host_no);
+		hba->clk_scaling.workq = create_singlethread_workqueue(wq_name);
+
+		ufshcd_clkscaling_init_sysfs(hba);
 	}
 
+	/*
+	 * Set the default power management level for runtime and system PM.
+	 * Default power saving mode is to keep UFS link in Hibern8 state
+	 * and UFS device in sleep state.
+	 */
+	hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
+						UFS_SLEEP_PWR_MODE,
+						UIC_LINK_HIBERN8_STATE);
+	hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
+						UFS_SLEEP_PWR_MODE,
+						UIC_LINK_HIBERN8_STATE);
+
 	/* Hold auto suspend until async scan completes */
 	pm_runtime_get_sync(dev);
 
@@ -6823,6 +7918,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	ufshcd_set_ufs_dev_active(hba);
 
 	async_schedule(ufshcd_async_scan, hba);
+	ufshcd_add_sysfs_nodes(hba);
 
 	return 0;
 
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 08cd26ed2382..7630600217a2 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -45,6 +45,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/rwsem.h>
 #include <linux/workqueue.h>
 #include <linux/errno.h>
 #include <linux/types.h>
@@ -152,6 +153,10 @@ struct ufs_pm_lvl_states {
  * @ucd_req_ptr: UCD address of the command
  * @ucd_rsp_ptr: Response UPIU address for this command
  * @ucd_prdt_ptr: PRDT address of the command
+ * @utrd_dma_addr: UTRD dma address for debug
+ * @ucd_prdt_dma_addr: PRDT dma address for debug
+ * @ucd_rsp_dma_addr: UPIU response dma address for debug
+ * @ucd_req_dma_addr: UPIU request dma address for debug
  * @cmd: pointer to SCSI command
  * @sense_buffer: pointer to sense buffer address of the SCSI command
  * @sense_bufflen: Length of the sense buffer
@@ -160,6 +165,8 @@ struct ufs_pm_lvl_states {
  * @task_tag: Task tag of the command
  * @lun: LUN of the command
  * @intr_cmd: Interrupt command (doesn't participate in interrupt aggregation)
+ * @issue_time_stamp: time stamp for debug purposes
+ * @req_abort_skip: skip request abort task flag
  */
 struct ufshcd_lrb {
 	struct utp_transfer_req_desc *utr_descriptor_ptr;
@@ -167,6 +174,11 @@ struct ufshcd_lrb {
 	struct utp_upiu_rsp *ucd_rsp_ptr;
 	struct ufshcd_sg_entry *ucd_prdt_ptr;
 
+	dma_addr_t utrd_dma_addr;
+	dma_addr_t ucd_req_dma_addr;
+	dma_addr_t ucd_rsp_dma_addr;
+	dma_addr_t ucd_prdt_dma_addr;
+
 	struct scsi_cmnd *cmd;
 	u8 *sense_buffer;
 	unsigned int sense_bufflen;
@@ -176,6 +188,9 @@ struct ufshcd_lrb {
 	int task_tag;
 	u8 lun; /* UPIU LUN id field is only 8-bit wide */
 	bool intr_cmd;
+	ktime_t issue_time_stamp;
+
+	bool req_abort_skip;
 };
 
 /**
@@ -320,6 +335,8 @@ enum clk_gating_state {
  * @is_suspended: clk gating is suspended when set to 1 which can be used
  * during suspend/resume
  * @delay_attr: sysfs attribute to control delay_attr
+ * @enable_attr: sysfs attribute to enable/disable clock gating
+ * @is_enabled: Indicates the current status of clock gating
  * @active_reqs: number of requests that are pending and should be waited for
  * completion before gating clocks.
  */
@@ -330,14 +347,47 @@ struct ufs_clk_gating {
 	unsigned long delay_ms;
 	bool is_suspended;
 	struct device_attribute delay_attr;
+	struct device_attribute enable_attr;
+	bool is_enabled;
 	int active_reqs;
 };
 
+struct ufs_saved_pwr_info {
+	struct ufs_pa_layer_attr info;
+	bool is_valid;
+};
+
+/**
+ * struct ufs_clk_scaling - UFS clock scaling related data
+ * @active_reqs: number of requests that are pending. If this is zero when
+ * devfreq ->target() function is called then schedule "suspend_work" to
+ * suspend devfreq.
+ * @tot_busy_t: Total busy time in current polling window
+ * @window_start_t: Start time (in jiffies) of the current polling window
+ * @busy_start_t: Start time of current busy period
+ * @enable_attr: sysfs attribute to enable/disable clock scaling
+ * @saved_pwr_info: UFS power mode may also be changed during scaling and this
+ * one keeps track of previous power mode.
+ * @workq: workqueue to schedule devfreq suspend/resume work
+ * @suspend_work: worker to suspend devfreq
+ * @resume_work: worker to resume devfreq
+ * @is_allowed: tracks if scaling is currently allowed or not
+ * @is_busy_started: tracks if busy period has started or not
+ * @is_suspended: tracks if devfreq is suspended or not
+ */
 struct ufs_clk_scaling {
-	ktime_t  busy_start_t;
-	bool is_busy_started;
-	unsigned long  tot_busy_t;
+	int active_reqs;
+	unsigned long tot_busy_t;
 	unsigned long window_start_t;
+	ktime_t busy_start_t;
+	struct device_attribute enable_attr;
+	struct ufs_saved_pwr_info saved_pwr_info;
+	struct workqueue_struct *workq;
+	struct work_struct suspend_work;
+	struct work_struct resume_work;
+	bool is_allowed;
+	bool is_busy_started;
+	bool is_suspended;
 };
 
 /**
@@ -349,6 +399,41 @@ struct ufs_init_prefetch {
 	u32 icc_level;
 };
 
+#define UIC_ERR_REG_HIST_LENGTH 8
+/**
+ * struct ufs_uic_err_reg_hist - keeps history of uic errors
+ * @pos: index to indicate cyclic buffer position
+ * @reg: cyclic buffer for registers value
+ * @tstamp: cyclic buffer for time stamp
+ */
+struct ufs_uic_err_reg_hist {
+	int pos;
+	u32 reg[UIC_ERR_REG_HIST_LENGTH];
+	ktime_t tstamp[UIC_ERR_REG_HIST_LENGTH];
+};
+
+/**
+ * struct ufs_stats - keeps usage/err statistics
+ * @hibern8_exit_cnt: Counter to keep track of number of exits,
+ *		reset this after link-startup.
+ * @last_hibern8_exit_tstamp: Set time after the hibern8 exit.
+ *		Clear after the first successful command completion.
+ * @pa_err: tracks pa-uic errors
+ * @dl_err: tracks dl-uic errors
+ * @nl_err: tracks nl-uic errors
+ * @tl_err: tracks tl-uic errors
+ * @dme_err: tracks dme errors
+ */
+struct ufs_stats {
+	u32 hibern8_exit_cnt;
+	ktime_t last_hibern8_exit_tstamp;
+	struct ufs_uic_err_reg_hist pa_err;
+	struct ufs_uic_err_reg_hist dl_err;
+	struct ufs_uic_err_reg_hist nl_err;
+	struct ufs_uic_err_reg_hist tl_err;
+	struct ufs_uic_err_reg_hist dme_err;
+};
+
 /**
  * struct ufs_hba - per adapter private structure
  * @mmio_base: UFSHCI base register address
@@ -429,6 +514,8 @@ struct ufs_hba {
 	enum ufs_pm_level rpm_lvl;
 	/* Desired UFS power management level during system PM */
 	enum ufs_pm_level spm_lvl;
+	struct device_attribute rpm_lvl_attr;
+	struct device_attribute spm_lvl_attr;
 	int pm_op_in_progress;
 
 	struct ufshcd_lrb *lrb;
@@ -523,6 +610,7 @@ struct ufs_hba {
 	u32 uic_error;
 	u32 saved_err;
 	u32 saved_uic_err;
+	struct ufs_stats ufs_stats;
 
 	/* Device management request data */
 	struct ufs_dev_cmd dev_cmd;
@@ -536,6 +624,9 @@ struct ufs_hba {
 
 	bool wlun_dev_clr_ua;
 
+	/* Number of requests aborts */
+	int req_abort_count;
+
 	/* Number of lanes available (1 or 2) for Rx/Tx */
 	u32 lanes_per_direction;
 	struct ufs_pa_layer_attr pwr_info;
@@ -558,6 +649,14 @@ struct ufs_hba {
 	 * CAUTION: Enabling this might reduce overall UFS throughput.
 	 */
 #define UFSHCD_CAP_INTR_AGGR (1 << 4)
+	/*
+	 * This capability allows the device auto-bkops to be always enabled
+	 * except during suspend (both runtime and suspend).
+	 * Enabling this capability means that device will always be allowed
+	 * to do background operation when it's active but it might degrade
+	 * the performance of ongoing read/write operations.
+	 */
+#define UFSHCD_CAP_KEEP_AUTO_BKOPS_ENABLED_EXCEPT_SUSPEND (1 << 5)
 
 	struct devfreq *devfreq;
 	struct ufs_clk_scaling clk_scaling;
@@ -565,6 +664,8 @@ struct ufs_hba {
 
 	enum bkops_status urgent_bkops_lvl;
 	bool is_urgent_bkops_lvl_checked;
+
+	struct rw_semaphore clk_scaling_lock;
 };
 
 /* Returns true if clocks can be gated. Otherwise false */
@@ -576,7 +677,7 @@ static inline bool ufshcd_can_hibern8_during_gating(struct ufs_hba *hba)
 {
 	return hba->caps & UFSHCD_CAP_HIBERN8_WITH_CLK_GATING;
 }
-static inline int ufshcd_is_clkscaling_enabled(struct ufs_hba *hba)
+static inline int ufshcd_is_clkscaling_supported(struct ufs_hba *hba)
 {
 	return hba->caps & UFSHCD_CAP_CLK_SCALING;
 }
@@ -655,6 +756,11 @@ static inline void *ufshcd_get_variant(struct ufs_hba *hba)
 	BUG_ON(!hba);
 	return hba->priv;
 }
+static inline bool ufshcd_keep_autobkops_enabled_except_suspend(
+							struct ufs_hba *hba)
+{
+	return hba->caps & UFSHCD_CAP_KEEP_AUTO_BKOPS_ENABLED_EXCEPT_SUSPEND;
+}
 
 extern int ufshcd_runtime_suspend(struct ufs_hba *hba);
 extern int ufshcd_runtime_resume(struct ufs_hba *hba);
@@ -713,8 +819,6 @@ static inline int ufshcd_dme_peer_get(struct ufs_hba *hba,
 	return ufshcd_dme_get_attr(hba, attr_sel, mib_val, DME_PEER);
 }
 
-int ufshcd_read_device_desc(struct ufs_hba *hba, u8 *buf, u32 size);
-
 static inline bool ufshcd_is_hs_mode(struct ufs_pa_layer_attr *pwr_info)
 {
 	return (pwr_info->pwr_rx == FAST_MODE ||
@@ -723,11 +827,6 @@ static inline bool ufshcd_is_hs_mode(struct ufs_pa_layer_attr *pwr_info)
 		pwr_info->pwr_tx == FASTAUTO_MODE);
 }
 
-#define ASCII_STD true
-
-int ufshcd_read_string_desc(struct ufs_hba *hba, int desc_index, u8 *buf,
-				u32 size, bool ascii);
-
 /* Expose Query-Request API */
 int ufshcd_query_flag(struct ufs_hba *hba, enum query_opcode opcode,
 	enum flag_idn idn, bool *flag_res);
diff --git a/drivers/scsi/ufs/ufshci.h b/drivers/scsi/ufs/ufshci.h
index 8c5190e2e1c9..d14e9b965d1e 100644
--- a/drivers/scsi/ufs/ufshci.h
+++ b/drivers/scsi/ufs/ufshci.h
@@ -72,6 +72,9 @@ enum {
 	REG_UIC_COMMAND_ARG_1			= 0x94,
 	REG_UIC_COMMAND_ARG_2			= 0x98,
 	REG_UIC_COMMAND_ARG_3			= 0x9C,
+
+	UFSHCI_REG_SPACE_SIZE			= 0xA0,
+
 	REG_UFS_CCAP				= 0x100,
 	REG_UFS_CRYPTOCAP			= 0x104,
 
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index ec91bd07f00a..c680d7641311 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -534,7 +534,9 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
 {
 	struct Scsi_Host *shost = virtio_scsi_host(vscsi->vdev);
 	struct virtio_scsi_cmd *cmd = scsi_cmd_priv(sc);
+	unsigned long flags;
 	int req_size;
+	int ret;
 
 	BUG_ON(scsi_sg_count(sc) > shost->sg_tablesize);
 
@@ -562,8 +564,15 @@ static int virtscsi_queuecommand(struct virtio_scsi *vscsi,
 		req_size = sizeof(cmd->req.cmd);
 	}
 
-	if (virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd)) != 0)
+	ret = virtscsi_kick_cmd(req_vq, cmd, req_size, sizeof(cmd->resp.cmd));
+	if (ret == -EIO) {
+		cmd->resp.cmd.response = VIRTIO_SCSI_S_BAD_TARGET;
+		spin_lock_irqsave(&req_vq->vq_lock, flags);
+		virtscsi_complete_cmd(vscsi, cmd);
+		spin_unlock_irqrestore(&req_vq->vq_lock, flags);
+	} else if (ret != 0) {
 		return SCSI_MLQUEUE_HOST_BUSY;
+	}
 	return 0;
 }
 
diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c
index 15ca09cd16f3..ef474a748744 100644
--- a/drivers/scsi/vmw_pvscsi.c
+++ b/drivers/scsi/vmw_pvscsi.c
@@ -68,10 +68,7 @@ struct pvscsi_ctx {
 
 struct pvscsi_adapter {
 	char				*mmioBase;
-	unsigned int			irq;
 	u8				rev;
-	bool				use_msi;
-	bool				use_msix;
 	bool				use_msg;
 	bool				use_req_threshold;
 
@@ -1161,30 +1158,26 @@ static bool pvscsi_setup_req_threshold(struct pvscsi_adapter *adapter,
 static irqreturn_t pvscsi_isr(int irq, void *devp)
 {
 	struct pvscsi_adapter *adapter = devp;
-	int handled;
-
-	if (adapter->use_msi || adapter->use_msix)
-		handled = true;
-	else {
-		u32 val = pvscsi_read_intr_status(adapter);
-		handled = (val & PVSCSI_INTR_ALL_SUPPORTED) != 0;
-		if (handled)
-			pvscsi_write_intr_status(devp, val);
-	}
-
-	if (handled) {
-		unsigned long flags;
+	unsigned long flags;
 
-		spin_lock_irqsave(&adapter->hw_lock, flags);
+	spin_lock_irqsave(&adapter->hw_lock, flags);
+	pvscsi_process_completion_ring(adapter);
+	if (adapter->use_msg && pvscsi_msg_pending(adapter))
+		queue_work(adapter->workqueue, &adapter->work);
+	spin_unlock_irqrestore(&adapter->hw_lock, flags);
 
-		pvscsi_process_completion_ring(adapter);
-		if (adapter->use_msg && pvscsi_msg_pending(adapter))
-			queue_work(adapter->workqueue, &adapter->work);
+	return IRQ_HANDLED;
+}
 
-		spin_unlock_irqrestore(&adapter->hw_lock, flags);
-	}
+static irqreturn_t pvscsi_shared_isr(int irq, void *devp)
+{
+	struct pvscsi_adapter *adapter = devp;
+	u32 val = pvscsi_read_intr_status(adapter);
 
-	return IRQ_RETVAL(handled);
+	if (!(val & PVSCSI_INTR_ALL_SUPPORTED))
+		return IRQ_NONE;
+	pvscsi_write_intr_status(devp, val);
+	return pvscsi_isr(irq, devp);
 }
 
 static void pvscsi_free_sgls(const struct pvscsi_adapter *adapter)
@@ -1196,34 +1189,10 @@ static void pvscsi_free_sgls(const struct pvscsi_adapter *adapter)
 		free_pages((unsigned long)ctx->sgl, get_order(SGL_SIZE));
 }
 
-static int pvscsi_setup_msix(const struct pvscsi_adapter *adapter,
-			     unsigned int *irq)
-{
-	struct msix_entry entry = { 0, PVSCSI_VECTOR_COMPLETION };
-	int ret;
-
-	ret = pci_enable_msix_exact(adapter->dev, &entry, 1);
-	if (ret)
-		return ret;
-
-	*irq = entry.vector;
-
-	return 0;
-}
-
 static void pvscsi_shutdown_intr(struct pvscsi_adapter *adapter)
 {
-	if (adapter->irq) {
-		free_irq(adapter->irq, adapter);
-		adapter->irq = 0;
-	}
-	if (adapter->use_msi) {
-		pci_disable_msi(adapter->dev);
-		adapter->use_msi = 0;
-	} else if (adapter->use_msix) {
-		pci_disable_msix(adapter->dev);
-		adapter->use_msix = 0;
-	}
+	free_irq(pci_irq_vector(adapter->dev, 0), adapter);
+	pci_free_irq_vectors(adapter->dev);
 }
 
 static void pvscsi_release_resources(struct pvscsi_adapter *adapter)
@@ -1359,11 +1328,11 @@ exit:
 
 static int pvscsi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	unsigned int irq_flag = PCI_IRQ_MSIX | PCI_IRQ_MSI | PCI_IRQ_LEGACY;
 	struct pvscsi_adapter *adapter;
 	struct pvscsi_adapter adapter_temp;
 	struct Scsi_Host *host = NULL;
 	unsigned int i;
-	unsigned long flags = 0;
 	int error;
 	u32 max_id;
 
@@ -1512,30 +1481,33 @@ static int pvscsi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto out_reset_adapter;
 	}
 
-	if (!pvscsi_disable_msix &&
-	    pvscsi_setup_msix(adapter, &adapter->irq) == 0) {
-		printk(KERN_INFO "vmw_pvscsi: using MSI-X\n");
-		adapter->use_msix = 1;
-	} else if (!pvscsi_disable_msi && pci_enable_msi(pdev) == 0) {
-		printk(KERN_INFO "vmw_pvscsi: using MSI\n");
-		adapter->use_msi = 1;
-		adapter->irq = pdev->irq;
-	} else {
-		printk(KERN_INFO "vmw_pvscsi: using INTx\n");
-		adapter->irq = pdev->irq;
-		flags = IRQF_SHARED;
-	}
+	if (pvscsi_disable_msix)
+		irq_flag &= ~PCI_IRQ_MSIX;
+	if (pvscsi_disable_msi)
+		irq_flag &= ~PCI_IRQ_MSI;
+
+	error = pci_alloc_irq_vectors(adapter->dev, 1, 1, irq_flag);
+	if (error)
+		goto out_reset_adapter;
 
 	adapter->use_req_threshold = pvscsi_setup_req_threshold(adapter, true);
 	printk(KERN_DEBUG "vmw_pvscsi: driver-based request coalescing %sabled\n",
 	       adapter->use_req_threshold ? "en" : "dis");
 
-	error = request_irq(adapter->irq, pvscsi_isr, flags,
-			    "vmw_pvscsi", adapter);
+	if (adapter->dev->msix_enabled || adapter->dev->msi_enabled) {
+		printk(KERN_INFO "vmw_pvscsi: using MSI%s\n",
+			adapter->dev->msix_enabled ? "-X" : "");
+		error = request_irq(pci_irq_vector(pdev, 0), pvscsi_isr,
+				0, "vmw_pvscsi", adapter);
+	} else {
+		printk(KERN_INFO "vmw_pvscsi: using INTx\n");
+		error = request_irq(pci_irq_vector(pdev, 0), pvscsi_shared_isr,
+				IRQF_SHARED, "vmw_pvscsi", adapter);
+	}
+
 	if (error) {
 		printk(KERN_ERR
 		       "vmw_pvscsi: unable to request IRQ: %d\n", error);
-		adapter->irq = 0;
 		goto out_reset_adapter;
 	}
 
diff --git a/drivers/scsi/vmw_pvscsi.h b/drivers/scsi/vmw_pvscsi.h
index d41292ef85f2..75966d3f326e 100644
--- a/drivers/scsi/vmw_pvscsi.h
+++ b/drivers/scsi/vmw_pvscsi.h
@@ -423,11 +423,6 @@ struct PVSCSIConfigPageController {
 #define PVSCSI_MAX_INTRS        24
 
 /*
- * Enumeration of supported MSI-X vectors
- */
-#define PVSCSI_VECTOR_COMPLETION   0
-
-/*
  * Misc constants for the rings.
  */
 
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 2922a9908302..25ae7f2e44b5 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -162,7 +162,8 @@ config SPI_BCM63XX_HSSPI
 
 config SPI_BCM_QSPI
 	tristate "Broadcom BSPI and MSPI controller support"
-	depends on ARCH_BRCMSTB || ARCH_BCM || ARCH_BCM_IPROC || COMPILE_TEST
+	depends on ARCH_BRCMSTB || ARCH_BCM || ARCH_BCM_IPROC || \
+			BMIPS_GENERIC || COMPILE_TEST
 	default ARCH_BCM_IPROC
 	help
 	  Enables support for the Broadcom SPI flash and MSPI controller.
@@ -263,7 +264,7 @@ config SPI_EP93XX
 	  mode.
 
 config SPI_FALCON
-	tristate "Falcon SPI controller support"
+	bool "Falcon SPI controller support"
 	depends on SOC_FALCON
 	help
 	  The external bus unit (EBU) found on the FALC-ON SoC has SPI
@@ -416,6 +417,14 @@ config SPI_NUC900
 	help
 	  SPI driver for Nuvoton NUC900 series ARM SoCs
 
+config SPI_LANTIQ_SSC
+	tristate "Lantiq SSC SPI controller"
+	depends on LANTIQ || COMPILE_TEST
+	help
+	  This driver supports the Lantiq SSC SPI controller in master
+	  mode. This controller is found on Intel (former Lantiq) SoCs like
+	  the Danube, Falcon, xRX200, xRX300.
+
 config SPI_OC_TINY
 	tristate "OpenCores tiny SPI"
 	depends on GPIOLIB || COMPILE_TEST
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 7a6b64662c82..b375a7a89216 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -49,6 +49,7 @@ obj-$(CONFIG_SPI_FSL_SPI)		+= spi-fsl-spi.o
 obj-$(CONFIG_SPI_GPIO)			+= spi-gpio.o
 obj-$(CONFIG_SPI_IMG_SPFI)		+= spi-img-spfi.o
 obj-$(CONFIG_SPI_IMX)			+= spi-imx.o
+obj-$(CONFIG_SPI_LANTIQ_SSC)		+= spi-lantiq-ssc.o
 obj-$(CONFIG_SPI_JCORE)			+= spi-jcore.o
 obj-$(CONFIG_SPI_LM70_LLP)		+= spi-lm70llp.o
 obj-$(CONFIG_SPI_LP8841_RTC)		+= spi-lp8841-rtc.o
diff --git a/drivers/spi/spi-armada-3700.c b/drivers/spi/spi-armada-3700.c
index 0314c6b9e044..6c7d7a460689 100644
--- a/drivers/spi/spi-armada-3700.c
+++ b/drivers/spi/spi-armada-3700.c
@@ -170,12 +170,12 @@ static int a3700_spi_pin_mode_set(struct a3700_spi *a3700_spi,
 	val &= ~(A3700_SPI_DATA_PIN0 | A3700_SPI_DATA_PIN1);
 
 	switch (pin_mode) {
-	case 1:
+	case SPI_NBITS_SINGLE:
 		break;
-	case 2:
+	case SPI_NBITS_DUAL:
 		val |= A3700_SPI_DATA_PIN0;
 		break;
-	case 4:
+	case SPI_NBITS_QUAD:
 		val |= A3700_SPI_DATA_PIN1;
 		break;
 	default:
@@ -340,8 +340,7 @@ static irqreturn_t a3700_spi_interrupt(int irq, void *dev_id)
 	spireg_write(a3700_spi, A3700_SPI_INT_STAT_REG, cause);
 
 	/* Wake up the transfer */
-	if (a3700_spi->wait_mask & cause)
-		complete(&a3700_spi->done);
+	complete(&a3700_spi->done);
 
 	return IRQ_HANDLED;
 }
@@ -421,7 +420,7 @@ static void a3700_spi_fifo_thres_set(struct a3700_spi *a3700_spi,
 }
 
 static void a3700_spi_transfer_setup(struct spi_device *spi,
-				    struct spi_transfer *xfer)
+				     struct spi_transfer *xfer)
 {
 	struct a3700_spi *a3700_spi;
 	unsigned int byte_len;
@@ -562,6 +561,7 @@ static int a3700_spi_fifo_read(struct a3700_spi *a3700_spi)
 		val = spireg_read(a3700_spi, A3700_SPI_DATA_IN_REG);
 		if (a3700_spi->buf_len >= 4) {
 			u32 data = le32_to_cpu(val);
+
 			memcpy(a3700_spi->rx_buf, &data, 4);
 
 			a3700_spi->buf_len -= 4;
@@ -901,7 +901,6 @@ static int a3700_spi_remove(struct platform_device *pdev)
 	struct a3700_spi *spi = spi_master_get_devdata(master);
 
 	clk_unprepare(spi->clk);
-	spi_master_put(master);
 
 	return 0;
 }
@@ -909,7 +908,6 @@ static int a3700_spi_remove(struct platform_device *pdev)
 static struct platform_driver a3700_spi_driver = {
 	.driver = {
 		.name	= DRIVER_NAME,
-		.owner	= THIS_MODULE,
 		.of_match_table = of_match_ptr(a3700_spi_dt_ids),
 	},
 	.probe		= a3700_spi_probe,
diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index f369174fbd88..b89cee11f418 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -78,14 +78,16 @@ static void ath79_spi_chipselect(struct spi_device *spi, int is_active)
 		ath79_spi_wr(sp, AR71XX_SPI_REG_IOC, sp->ioc_base);
 	}
 
-	if (spi->chip_select) {
+	if (gpio_is_valid(spi->cs_gpio)) {
 		/* SPI is normally active-low */
-		gpio_set_value(spi->cs_gpio, cs_high);
+		gpio_set_value_cansleep(spi->cs_gpio, cs_high);
 	} else {
+		u32 cs_bit = AR71XX_SPI_IOC_CS(spi->chip_select);
+
 		if (cs_high)
-			sp->ioc_base |= AR71XX_SPI_IOC_CS0;
+			sp->ioc_base |= cs_bit;
 		else
-			sp->ioc_base &= ~AR71XX_SPI_IOC_CS0;
+			sp->ioc_base &= ~cs_bit;
 
 		ath79_spi_wr(sp, AR71XX_SPI_REG_IOC, sp->ioc_base);
 	}
@@ -118,11 +120,8 @@ static int ath79_spi_setup_cs(struct spi_device *spi)
 	struct ath79_spi *sp = ath79_spidev_to_sp(spi);
 	int status;
 
-	if (spi->chip_select && !gpio_is_valid(spi->cs_gpio))
-		return -EINVAL;
-
 	status = 0;
-	if (spi->chip_select) {
+	if (gpio_is_valid(spi->cs_gpio)) {
 		unsigned long flags;
 
 		flags = GPIOF_DIR_OUT;
@@ -134,10 +133,12 @@ static int ath79_spi_setup_cs(struct spi_device *spi)
 		status = gpio_request_one(spi->cs_gpio, flags,
 					  dev_name(&spi->dev));
 	} else {
+		u32 cs_bit = AR71XX_SPI_IOC_CS(spi->chip_select);
+
 		if (spi->mode & SPI_CS_HIGH)
-			sp->ioc_base &= ~AR71XX_SPI_IOC_CS0;
+			sp->ioc_base &= ~cs_bit;
 		else
-			sp->ioc_base |= AR71XX_SPI_IOC_CS0;
+			sp->ioc_base |= cs_bit;
 
 		ath79_spi_wr(sp, AR71XX_SPI_REG_IOC, sp->ioc_base);
 	}
@@ -147,7 +148,7 @@ static int ath79_spi_setup_cs(struct spi_device *spi)
 
 static void ath79_spi_cleanup_cs(struct spi_device *spi)
 {
-	if (spi->chip_select) {
+	if (gpio_is_valid(spi->cs_gpio)) {
 		gpio_free(spi->cs_gpio);
 	}
 }
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index 14f9dea3173f..b19722ba908c 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -89,7 +89,7 @@
 #define BSPI_BPP_MODE_SELECT_MASK		BIT(8)
 #define BSPI_BPP_ADDR_SELECT_MASK		BIT(16)
 
-#define BSPI_READ_LENGTH			256
+#define BSPI_READ_LENGTH			512
 
 /* MSPI register offsets */
 #define MSPI_SPCR0_LSB				0x000
@@ -192,9 +192,11 @@ struct bcm_qspi_dev_id {
 	void *dev;
 };
 
+
 struct qspi_trans {
 	struct spi_transfer *trans;
 	int byte;
+	bool mspi_last_trans;
 };
 
 struct bcm_qspi {
@@ -371,7 +373,7 @@ static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi, int width,
 			/* default mode, does not need flex_cmd */
 			flex_mode = 0;
 		else
-			command = SPINOR_OP_READ4_FAST;
+			command = SPINOR_OP_READ_FAST_4B;
 		break;
 	case SPI_NBITS_DUAL:
 		bpc = 0x00000001;
@@ -384,7 +386,7 @@ static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi, int width,
 		} else {
 			command = SPINOR_OP_READ_1_1_2;
 			if (spans_4byte)
-				command = SPINOR_OP_READ4_1_1_2;
+				command = SPINOR_OP_READ_1_1_2_4B;
 		}
 		break;
 	case SPI_NBITS_QUAD:
@@ -399,7 +401,7 @@ static int bcm_qspi_bspi_set_flex_mode(struct bcm_qspi *qspi, int width,
 		} else {
 			command = SPINOR_OP_READ_1_1_4;
 			if (spans_4byte)
-				command = SPINOR_OP_READ4_1_1_4;
+				command = SPINOR_OP_READ_1_1_4_4B;
 		}
 		break;
 	default:
@@ -616,6 +618,16 @@ static int bcm_qspi_setup(struct spi_device *spi)
 	return 0;
 }
 
+static bool bcm_qspi_mspi_transfer_is_last(struct bcm_qspi *qspi,
+					   struct qspi_trans *qt)
+{
+	if (qt->mspi_last_trans &&
+	    spi_transfer_is_last(qspi->master, qt->trans))
+		return true;
+	else
+		return false;
+}
+
 static int update_qspi_trans_byte_count(struct bcm_qspi *qspi,
 					struct qspi_trans *qt, int flags)
 {
@@ -629,7 +641,6 @@ static int update_qspi_trans_byte_count(struct bcm_qspi *qspi,
 
 	if (qt->byte >= qt->trans->len) {
 		/* we're at the end of the spi_transfer */
-
 		/* in TX mode, need to pause for a delay or CS change */
 		if (qt->trans->delay_usecs &&
 		    (flags & TRANS_STATUS_BREAK_DELAY))
@@ -641,7 +652,7 @@ static int update_qspi_trans_byte_count(struct bcm_qspi *qspi,
 			goto done;
 
 		dev_dbg(&qspi->pdev->dev, "advance msg exit\n");
-		if (spi_transfer_is_last(qspi->master, qt->trans))
+		if (bcm_qspi_mspi_transfer_is_last(qspi, qt))
 			ret = TRANS_STATUS_BREAK_EOM;
 		else
 			ret = TRANS_STATUS_BREAK_NO_BYTES;
@@ -813,7 +824,7 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
 				    struct spi_flash_read_message *msg)
 {
 	struct bcm_qspi *qspi = spi_master_get_devdata(spi->master);
-	u32 addr = 0, len, len_words;
+	u32 addr = 0, len, rdlen, len_words;
 	int ret = 0;
 	unsigned long timeo = msecs_to_jiffies(100);
 	struct bcm_qspi_soc_intc *soc_intc = qspi->soc_intc;
@@ -826,7 +837,7 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
 	bcm_qspi_write(qspi, MSPI, MSPI_WRITE_LOCK, 0);
 
 	/*
-	 * when using flex mode mode we need to send
+	 * when using flex mode we need to send
 	 * the upper address byte to bspi
 	 */
 	if (bcm_qspi_bspi_ver_three(qspi) == false) {
@@ -840,48 +851,127 @@ static int bcm_qspi_bspi_flash_read(struct spi_device *spi,
 	else
 		addr = msg->from & 0x00ffffff;
 
-	/* set BSPI RAF buffer max read length */
-	len = msg->len;
-	if (len > BSPI_READ_LENGTH)
-		len = BSPI_READ_LENGTH;
-
 	if (bcm_qspi_bspi_ver_three(qspi) == true)
 		addr = (addr + 0xc00000) & 0xffffff;
 
-	reinit_completion(&qspi->bspi_done);
-	bcm_qspi_enable_bspi(qspi);
-	len_words = (len + 3) >> 2;
-	qspi->bspi_rf_msg = msg;
-	qspi->bspi_rf_msg_status = 0;
+	/*
+	 * read into the entire buffer by breaking the reads
+	 * into RAF buffer read lengths
+	 */
+	len = msg->len;
 	qspi->bspi_rf_msg_idx = 0;
-	qspi->bspi_rf_msg_len = len;
-	dev_dbg(&qspi->pdev->dev, "bspi xfr addr 0x%x len 0x%x", addr, len);
 
-	bcm_qspi_write(qspi, BSPI, BSPI_RAF_START_ADDR, addr);
-	bcm_qspi_write(qspi, BSPI, BSPI_RAF_NUM_WORDS, len_words);
-	bcm_qspi_write(qspi, BSPI, BSPI_RAF_WATERMARK, 0);
+	do {
+		if (len > BSPI_READ_LENGTH)
+			rdlen = BSPI_READ_LENGTH;
+		else
+			rdlen = len;
+
+		reinit_completion(&qspi->bspi_done);
+		bcm_qspi_enable_bspi(qspi);
+		len_words = (rdlen + 3) >> 2;
+		qspi->bspi_rf_msg = msg;
+		qspi->bspi_rf_msg_status = 0;
+		qspi->bspi_rf_msg_len = rdlen;
+		dev_dbg(&qspi->pdev->dev,
+			"bspi xfr addr 0x%x len 0x%x", addr, rdlen);
+		bcm_qspi_write(qspi, BSPI, BSPI_RAF_START_ADDR, addr);
+		bcm_qspi_write(qspi, BSPI, BSPI_RAF_NUM_WORDS, len_words);
+		bcm_qspi_write(qspi, BSPI, BSPI_RAF_WATERMARK, 0);
+		if (qspi->soc_intc) {
+			/*
+			 * clear soc MSPI and BSPI interrupts and enable
+			 * BSPI interrupts.
+			 */
+			soc_intc->bcm_qspi_int_ack(soc_intc, MSPI_BSPI_DONE);
+			soc_intc->bcm_qspi_int_set(soc_intc, BSPI_DONE, true);
+		}
 
-	if (qspi->soc_intc) {
-		/*
-		 * clear soc MSPI and BSPI interrupts and enable
-		 * BSPI interrupts.
-		 */
-		soc_intc->bcm_qspi_int_ack(soc_intc, MSPI_BSPI_DONE);
-		soc_intc->bcm_qspi_int_set(soc_intc, BSPI_DONE, true);
+		/* Must flush previous writes before starting BSPI operation */
+		mb();
+		bcm_qspi_bspi_lr_start(qspi);
+		if (!wait_for_completion_timeout(&qspi->bspi_done, timeo)) {
+			dev_err(&qspi->pdev->dev, "timeout waiting for BSPI\n");
+			ret = -ETIMEDOUT;
+			break;
+		}
+
+		/* set msg return length */
+		msg->retlen += rdlen;
+		addr += rdlen;
+		len -= rdlen;
+	} while (len);
+
+	return ret;
+}
+
+static int bcm_qspi_transfer_one(struct spi_master *master,
+				 struct spi_device *spi,
+				 struct spi_transfer *trans)
+{
+	struct bcm_qspi *qspi = spi_master_get_devdata(master);
+	int slots;
+	unsigned long timeo = msecs_to_jiffies(100);
+
+	bcm_qspi_chip_select(qspi, spi->chip_select);
+	qspi->trans_pos.trans = trans;
+	qspi->trans_pos.byte = 0;
+
+	while (qspi->trans_pos.byte < trans->len) {
+		reinit_completion(&qspi->mspi_done);
+
+		slots = write_to_hw(qspi, spi);
+		if (!wait_for_completion_timeout(&qspi->mspi_done, timeo)) {
+			dev_err(&qspi->pdev->dev, "timeout waiting for MSPI\n");
+			return -ETIMEDOUT;
+		}
+
+		read_from_hw(qspi, slots);
 	}
 
-	/* Must flush previous writes before starting BSPI operation */
-	mb();
+	return 0;
+}
 
-	bcm_qspi_bspi_lr_start(qspi);
-	if (!wait_for_completion_timeout(&qspi->bspi_done, timeo)) {
-		dev_err(&qspi->pdev->dev, "timeout waiting for BSPI\n");
-		ret = -ETIMEDOUT;
-	} else {
-		/* set the return length for the caller */
-		msg->retlen = len;
+static int bcm_qspi_mspi_flash_read(struct spi_device *spi,
+				    struct spi_flash_read_message *msg)
+{
+	struct bcm_qspi *qspi = spi_master_get_devdata(spi->master);
+	struct spi_transfer t[2];
+	u8 cmd[6];
+	int ret;
+
+	memset(cmd, 0, sizeof(cmd));
+	memset(t, 0, sizeof(t));
+
+	/* tx */
+	/* opcode is in cmd[0] */
+	cmd[0] = msg->read_opcode;
+	cmd[1] = msg->from >> (msg->addr_width * 8 -  8);
+	cmd[2] = msg->from >> (msg->addr_width * 8 - 16);
+	cmd[3] = msg->from >> (msg->addr_width * 8 - 24);
+	cmd[4] = msg->from >> (msg->addr_width * 8 - 32);
+	t[0].tx_buf = cmd;
+	t[0].len = msg->addr_width + msg->dummy_bytes + 1;
+	t[0].bits_per_word = spi->bits_per_word;
+	t[0].tx_nbits = msg->opcode_nbits;
+	/* lets mspi know that this is not last transfer */
+	qspi->trans_pos.mspi_last_trans = false;
+	ret = bcm_qspi_transfer_one(spi->master, spi, &t[0]);
+
+	/* rx */
+	qspi->trans_pos.mspi_last_trans = true;
+	if (!ret) {
+		/* rx */
+		t[1].rx_buf = msg->buf;
+		t[1].len = msg->len;
+		t[1].rx_nbits =  msg->data_nbits;
+		t[1].bits_per_word = spi->bits_per_word;
+		ret = bcm_qspi_transfer_one(spi->master, spi, &t[1]);
 	}
 
+	if (!ret)
+		msg->retlen = msg->len;
+
 	return ret;
 }
 
@@ -918,8 +1008,7 @@ static int bcm_qspi_flash_read(struct spi_device *spi,
 		mspi_read = true;
 
 	if (mspi_read)
-		/* this will make the m25p80 read to fallback to mspi read */
-		return -EAGAIN;
+		return bcm_qspi_mspi_flash_read(spi, msg);
 
 	io_width = msg->data_nbits ? msg->data_nbits : SPI_NBITS_SINGLE;
 	addrlen = msg->addr_width;
@@ -931,33 +1020,6 @@ static int bcm_qspi_flash_read(struct spi_device *spi,
 	return ret;
 }
 
-static int bcm_qspi_transfer_one(struct spi_master *master,
-				 struct spi_device *spi,
-				 struct spi_transfer *trans)
-{
-	struct bcm_qspi *qspi = spi_master_get_devdata(master);
-	int slots;
-	unsigned long timeo = msecs_to_jiffies(100);
-
-	bcm_qspi_chip_select(qspi, spi->chip_select);
-	qspi->trans_pos.trans = trans;
-	qspi->trans_pos.byte = 0;
-
-	while (qspi->trans_pos.byte < trans->len) {
-		reinit_completion(&qspi->mspi_done);
-
-		slots = write_to_hw(qspi, spi);
-		if (!wait_for_completion_timeout(&qspi->mspi_done, timeo)) {
-			dev_err(&qspi->pdev->dev, "timeout waiting for MSPI\n");
-			return -ETIMEDOUT;
-		}
-
-		read_from_hw(qspi, slots);
-	}
-
-	return 0;
-}
-
 static void bcm_qspi_cleanup(struct spi_device *spi)
 {
 	struct bcm_qspi_parms *xp = spi_get_ctldata(spi);
@@ -1187,6 +1249,7 @@ int bcm_qspi_probe(struct platform_device *pdev,
 	qspi->pdev = pdev;
 	qspi->trans_pos.trans = NULL;
 	qspi->trans_pos.byte = 0;
+	qspi->trans_pos.mspi_last_trans = true;
 	qspi->master = master;
 
 	master->bus_num = -1;
@@ -1345,7 +1408,6 @@ int bcm_qspi_remove(struct platform_device *pdev)
 {
 	struct bcm_qspi *qspi = platform_get_drvdata(pdev);
 
-	platform_set_drvdata(pdev, NULL);
 	bcm_qspi_hw_uninit(qspi);
 	clk_disable_unprepare(qspi->clk);
 	kfree(qspi->dev_ids);
diff --git a/drivers/spi/spi-bcm53xx.c b/drivers/spi/spi-bcm53xx.c
index afb51699dbb5..6e409eabe1c9 100644
--- a/drivers/spi/spi-bcm53xx.c
+++ b/drivers/spi/spi-bcm53xx.c
@@ -1,3 +1,11 @@
+/*
+ * Copyright (C) 2014-2016 Rafał Miłecki <rafal@milecki.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
 #define pr_fmt(fmt)		KBUILD_MODNAME ": " fmt
 
 #include <linux/kernel.h>
@@ -275,10 +283,6 @@ static int bcm53xxspi_flash_read(struct spi_device *spi,
  * BCMA
  **************************************************/
 
-static struct spi_board_info bcm53xx_info = {
-	.modalias	= "bcm53xxspiflash",
-};
-
 static const struct bcma_device_id bcm53xxspi_bcma_tbl[] = {
 	BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_NS_QSPI, BCMA_ANY_REV, BCMA_ANY_CLASS),
 	{},
@@ -311,6 +315,7 @@ static int bcm53xxspi_bcma_probe(struct bcma_device *core)
 	b53spi->bspi = true;
 	bcm53xxspi_disable_bspi(b53spi);
 
+	master->dev.of_node = dev->of_node;
 	master->transfer_one = bcm53xxspi_transfer_one;
 	if (b53spi->mmio_base)
 		master->spi_flash_read = bcm53xxspi_flash_read;
@@ -324,9 +329,6 @@ static int bcm53xxspi_bcma_probe(struct bcma_device *core)
 		return err;
 	}
 
-	/* Broadcom SoCs (at least with the CC rev 42) use SPI for flash only */
-	spi_new_device(master, &bcm53xx_info);
-
 	return 0;
 }
 
@@ -361,4 +363,4 @@ module_exit(bcm53xxspi_module_exit);
 
 MODULE_DESCRIPTION("Broadcom BCM53xx SPI Controller driver");
 MODULE_AUTHOR("Rafał Miłecki <zajec5@gmail.com>");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index 054012f87567..b217c22ff72f 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -107,9 +107,9 @@ static const struct file_operations dw_spi_regs_ops = {
 
 static int dw_spi_debugfs_init(struct dw_spi *dws)
 {
-	char name[128];
+	char name[32];
 
-	snprintf(name, 128, "dw_spi-%s", dev_name(&dws->master->dev));
+	snprintf(name, 32, "dw_spi%d", dws->master->bus_num);
 	dws->debugfs = debugfs_create_dir(name, NULL);
 	if (!dws->debugfs)
 		return -ENOMEM;
@@ -486,9 +486,9 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	dws->type = SSI_MOTO_SPI;
 	dws->dma_inited = 0;
 	dws->dma_addr = (dma_addr_t)(dws->paddr + DW_SPI_DR);
-	snprintf(dws->name, sizeof(dws->name), "dw_spi%d", dws->bus_num);
 
-	ret = request_irq(dws->irq, dw_spi_irq, IRQF_SHARED, dws->name, master);
+	ret = request_irq(dws->irq, dw_spi_irq, IRQF_SHARED, dev_name(dev),
+			  master);
 	if (ret < 0) {
 		dev_err(dev, "can not get IRQ\n");
 		goto err_free_master;
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index c21ca02f8ec5..da5eab62df34 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -101,7 +101,6 @@ struct dw_spi_dma_ops {
 struct dw_spi {
 	struct spi_master	*master;
 	enum dw_ssi_type	type;
-	char			name[16];
 
 	void __iomem		*regs;
 	unsigned long		paddr;
diff --git a/drivers/spi/spi-ep93xx.c b/drivers/spi/spi-ep93xx.c
index 17a6387e20b5..b5d766064b7b 100644
--- a/drivers/spi/spi-ep93xx.c
+++ b/drivers/spi/spi-ep93xx.c
@@ -28,6 +28,7 @@
 #include <linux/platform_device.h>
 #include <linux/sched.h>
 #include <linux/scatterlist.h>
+#include <linux/gpio.h>
 #include <linux/spi/spi.h>
 
 #include <linux/platform_data/dma-ep93xx.h>
@@ -107,16 +108,6 @@ struct ep93xx_spi {
 	void				*zeropage;
 };
 
-/**
- * struct ep93xx_spi_chip - SPI device hardware settings
- * @spi: back pointer to the SPI device
- * @ops: private chip operations
- */
-struct ep93xx_spi_chip {
-	const struct spi_device		*spi;
-	struct ep93xx_spi_chip_ops	*ops;
-};
-
 /* converts bits per word to CR0.DSS value */
 #define bits_per_word_to_dss(bpw)	((bpw) - 1)
 
@@ -229,104 +220,36 @@ static int ep93xx_spi_calc_divisors(const struct ep93xx_spi *espi,
 	return -EINVAL;
 }
 
-static void ep93xx_spi_cs_control(struct spi_device *spi, bool control)
-{
-	struct ep93xx_spi_chip *chip = spi_get_ctldata(spi);
-	int value = (spi->mode & SPI_CS_HIGH) ? control : !control;
-
-	if (chip->ops && chip->ops->cs_control)
-		chip->ops->cs_control(spi, value);
-}
-
-/**
- * ep93xx_spi_setup() - setup an SPI device
- * @spi: SPI device to setup
- *
- * This function sets up SPI device mode, speed etc. Can be called multiple
- * times for a single device. Returns %0 in case of success, negative error in
- * case of failure. When this function returns success, the device is
- * deselected.
- */
-static int ep93xx_spi_setup(struct spi_device *spi)
+static void ep93xx_spi_cs_control(struct spi_device *spi, bool enable)
 {
-	struct ep93xx_spi *espi = spi_master_get_devdata(spi->master);
-	struct ep93xx_spi_chip *chip;
+	if (spi->mode & SPI_CS_HIGH)
+		enable = !enable;
 
-	chip = spi_get_ctldata(spi);
-	if (!chip) {
-		dev_dbg(&espi->pdev->dev, "initial setup for %s\n",
-			spi->modalias);
-
-		chip = kzalloc(sizeof(*chip), GFP_KERNEL);
-		if (!chip)
-			return -ENOMEM;
-
-		chip->spi = spi;
-		chip->ops = spi->controller_data;
-
-		if (chip->ops && chip->ops->setup) {
-			int ret = chip->ops->setup(spi);
-
-			if (ret) {
-				kfree(chip);
-				return ret;
-			}
-		}
-
-		spi_set_ctldata(spi, chip);
-	}
-
-	ep93xx_spi_cs_control(spi, false);
-	return 0;
+	if (gpio_is_valid(spi->cs_gpio))
+		gpio_set_value(spi->cs_gpio, !enable);
 }
 
-/**
- * ep93xx_spi_cleanup() - cleans up master controller specific state
- * @spi: SPI device to cleanup
- *
- * This function releases master controller specific state for given @spi
- * device.
- */
-static void ep93xx_spi_cleanup(struct spi_device *spi)
-{
-	struct ep93xx_spi_chip *chip;
-
-	chip = spi_get_ctldata(spi);
-	if (chip) {
-		if (chip->ops && chip->ops->cleanup)
-			chip->ops->cleanup(spi);
-		spi_set_ctldata(spi, NULL);
-		kfree(chip);
-	}
-}
-
-/**
- * ep93xx_spi_chip_setup() - configures hardware according to given @chip
- * @espi: ep93xx SPI controller struct
- * @chip: chip specific settings
- * @speed_hz: transfer speed
- * @bits_per_word: transfer bits_per_word
- */
 static int ep93xx_spi_chip_setup(const struct ep93xx_spi *espi,
-				 const struct ep93xx_spi_chip *chip,
-				 u32 speed_hz, u8 bits_per_word)
+				 struct spi_device *spi,
+				 struct spi_transfer *xfer)
 {
-	u8 dss = bits_per_word_to_dss(bits_per_word);
+	u8 dss = bits_per_word_to_dss(xfer->bits_per_word);
 	u8 div_cpsr = 0;
 	u8 div_scr = 0;
 	u16 cr0;
 	int err;
 
-	err = ep93xx_spi_calc_divisors(espi, speed_hz, &div_cpsr, &div_scr);
+	err = ep93xx_spi_calc_divisors(espi, xfer->speed_hz,
+				       &div_cpsr, &div_scr);
 	if (err)
 		return err;
 
 	cr0 = div_scr << SSPCR0_SCR_SHIFT;
-	cr0 |= (chip->spi->mode & (SPI_CPHA|SPI_CPOL)) << SSPCR0_MODE_SHIFT;
+	cr0 |= (spi->mode & (SPI_CPHA | SPI_CPOL)) << SSPCR0_MODE_SHIFT;
 	cr0 |= dss;
 
 	dev_dbg(&espi->pdev->dev, "setup: mode %d, cpsr %d, scr %d, dss %d\n",
-		chip->spi->mode, div_cpsr, div_scr, dss);
+		spi->mode, div_cpsr, div_scr, dss);
 	dev_dbg(&espi->pdev->dev, "setup: cr0 %#x\n", cr0);
 
 	ep93xx_spi_write_u8(espi, SSPCPSR, div_cpsr);
@@ -603,12 +526,11 @@ static void ep93xx_spi_process_transfer(struct ep93xx_spi *espi,
 					struct spi_message *msg,
 					struct spi_transfer *t)
 {
-	struct ep93xx_spi_chip *chip = spi_get_ctldata(msg->spi);
 	int err;
 
 	msg->state = t;
 
-	err = ep93xx_spi_chip_setup(espi, chip, t->speed_hz, t->bits_per_word);
+	err = ep93xx_spi_chip_setup(espi, msg->spi, t);
 	if (err) {
 		dev_err(&espi->pdev->dev,
 			"failed to setup chip for transfer\n");
@@ -863,8 +785,13 @@ static int ep93xx_spi_probe(struct platform_device *pdev)
 	struct resource *res;
 	int irq;
 	int error;
+	int i;
 
 	info = dev_get_platdata(&pdev->dev);
+	if (!info) {
+		dev_err(&pdev->dev, "missing platform data\n");
+		return -EINVAL;
+	}
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
@@ -882,14 +809,36 @@ static int ep93xx_spi_probe(struct platform_device *pdev)
 	if (!master)
 		return -ENOMEM;
 
-	master->setup = ep93xx_spi_setup;
 	master->transfer_one_message = ep93xx_spi_transfer_one_message;
-	master->cleanup = ep93xx_spi_cleanup;
 	master->bus_num = pdev->id;
-	master->num_chipselect = info->num_chipselect;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
 
+	master->num_chipselect = info->num_chipselect;
+	master->cs_gpios = devm_kzalloc(&master->dev,
+					sizeof(int) * master->num_chipselect,
+					GFP_KERNEL);
+	if (!master->cs_gpios) {
+		error = -ENOMEM;
+		goto fail_release_master;
+	}
+
+	for (i = 0; i < master->num_chipselect; i++) {
+		master->cs_gpios[i] = info->chipselect[i];
+
+		if (!gpio_is_valid(master->cs_gpios[i]))
+			continue;
+
+		error = devm_gpio_request_one(&pdev->dev, master->cs_gpios[i],
+					      GPIOF_OUT_INIT_HIGH,
+					      "ep93xx-spi");
+		if (error) {
+			dev_err(&pdev->dev, "could not request cs gpio %d\n",
+				master->cs_gpios[i]);
+			goto fail_release_master;
+		}
+	}
+
 	platform_set_drvdata(pdev, master);
 
 	espi = spi_master_get_devdata(master);
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 52551f6d0c7d..cb3c73007ca1 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -366,7 +366,7 @@ static int fsl_lpspi_transfer_one_msg(struct spi_master *master,
 	struct spi_transfer *xfer;
 	bool is_first_xfer = true;
 	u32 temp;
-	int ret;
+	int ret = 0;
 
 	msg->status = 0;
 	msg->actual_length = 0;
@@ -512,9 +512,9 @@ static int fsl_lpspi_remove(struct platform_device *pdev)
 
 static struct platform_driver fsl_lpspi_driver = {
 	.driver = {
-		   .name = DRIVER_NAME,
-		   .of_match_table = fsl_lpspi_dt_ids,
-		   },
+		.name = DRIVER_NAME,
+		.of_match_table = fsl_lpspi_dt_ids,
+	},
 	.probe = fsl_lpspi_probe,
 	.remove = fsl_lpspi_remove,
 };
diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c
index 8b290d9d7935..0fc3452652ae 100644
--- a/drivers/spi/spi-fsl-spi.c
+++ b/drivers/spi/spi-fsl-spi.c
@@ -267,10 +267,9 @@ static int fsl_spi_setup_transfer(struct spi_device *spi,
 	if ((mpc8xxx_spi->spibrg / hz) > 64) {
 		cs->hw_mode |= SPMODE_DIV16;
 		pm = (mpc8xxx_spi->spibrg - 1) / (hz * 64) + 1;
-
-		WARN_ONCE(pm > 16, "%s: Requested speed is too low: %d Hz. "
-			  "Will use %d Hz instead.\n", dev_name(&spi->dev),
-			  hz, mpc8xxx_spi->spibrg / 1024);
+		WARN_ONCE(pm > 16,
+			  "%s: Requested speed is too low: %d Hz. Will use %d Hz instead.\n",
+			  dev_name(&spi->dev), hz, mpc8xxx_spi->spibrg / 1024);
 		if (pm > 16)
 			pm = 16;
 	} else {
@@ -727,12 +726,13 @@ static int of_fsl_spi_get_chipselects(struct device *dev)
 		return 0;
 	}
 
-	pinfo->gpios = kmalloc(ngpios * sizeof(*pinfo->gpios), GFP_KERNEL);
+	pinfo->gpios = kmalloc_array(ngpios, sizeof(*pinfo->gpios),
+				     GFP_KERNEL);
 	if (!pinfo->gpios)
 		return -ENOMEM;
 	memset(pinfo->gpios, -1, ngpios * sizeof(*pinfo->gpios));
 
-	pinfo->alow_flags = kzalloc(ngpios * sizeof(*pinfo->alow_flags),
+	pinfo->alow_flags = kcalloc(ngpios, sizeof(*pinfo->alow_flags),
 				    GFP_KERNEL);
 	if (!pinfo->alow_flags) {
 		ret = -ENOMEM;
@@ -762,8 +762,9 @@ static int of_fsl_spi_get_chipselects(struct device *dev)
 		ret = gpio_direction_output(pinfo->gpios[i],
 					    pinfo->alow_flags[i]);
 		if (ret) {
-			dev_err(dev, "can't set output direction for gpio "
-				"#%d: %d\n", i, ret);
+			dev_err(dev,
+				"can't set output direction for gpio #%d: %d\n",
+				i, ret);
 			goto err_loop;
 		}
 	}
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 32ced64a5bb9..9a7c62f471dc 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -211,7 +211,7 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 			 struct spi_transfer *transfer)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
-	unsigned int bpw;
+	unsigned int bpw, i;
 
 	if (!master->dma_rx)
 		return false;
@@ -228,12 +228,16 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 	if (bpw != 1 && bpw != 2 && bpw != 4)
 		return false;
 
-	if (transfer->len < spi_imx->wml * bpw)
-		return false;
+	for (i = spi_imx_get_fifosize(spi_imx) / 2; i > 0; i--) {
+		if (!(transfer->len % (i * bpw)))
+			break;
+	}
 
-	if (transfer->len % (spi_imx->wml * bpw))
+	if (i == 0)
 		return false;
 
+	spi_imx->wml = i;
+
 	return true;
 }
 
@@ -837,10 +841,6 @@ static int spi_imx_dma_configure(struct spi_master *master,
 	struct dma_slave_config rx = {}, tx = {};
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
 
-	if (bytes_per_word == spi_imx->bytes_per_word)
-		/* Same as last time */
-		return 0;
-
 	switch (bytes_per_word) {
 	case 4:
 		buswidth = DMA_SLAVE_BUSWIDTH_4_BYTES;
diff --git a/drivers/spi/spi-lantiq-ssc.c b/drivers/spi/spi-lantiq-ssc.c
new file mode 100644
index 000000000000..8a626f7fccea
--- /dev/null
+++ b/drivers/spi/spi-lantiq-ssc.c
@@ -0,0 +1,983 @@
+/*
+ * Copyright (C) 2011-2015 Daniel Schwierzeck <daniel.schwierzeck@gmail.com>
+ * Copyright (C) 2016 Hauke Mehrtens <hauke@hauke-m.de>
+ *
+ * This program is free software; you can distribute it and/or modify it
+ * under the terms of the GNU General Public License (Version 2) as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/spinlock.h>
+#include <linux/err.h>
+#include <linux/gpio.h>
+#include <linux/pm_runtime.h>
+#include <linux/spi/spi.h>
+
+#ifdef CONFIG_LANTIQ
+#include <lantiq_soc.h>
+#endif
+
+#define SPI_RX_IRQ_NAME		"spi_rx"
+#define SPI_TX_IRQ_NAME		"spi_tx"
+#define SPI_ERR_IRQ_NAME	"spi_err"
+#define SPI_FRM_IRQ_NAME	"spi_frm"
+
+#define SPI_CLC			0x00
+#define SPI_PISEL		0x04
+#define SPI_ID			0x08
+#define SPI_CON			0x10
+#define SPI_STAT		0x14
+#define SPI_WHBSTATE		0x18
+#define SPI_TB			0x20
+#define SPI_RB			0x24
+#define SPI_RXFCON		0x30
+#define SPI_TXFCON		0x34
+#define SPI_FSTAT		0x38
+#define SPI_BRT			0x40
+#define SPI_BRSTAT		0x44
+#define SPI_SFCON		0x60
+#define SPI_SFSTAT		0x64
+#define SPI_GPOCON		0x70
+#define SPI_GPOSTAT		0x74
+#define SPI_FPGO		0x78
+#define SPI_RXREQ		0x80
+#define SPI_RXCNT		0x84
+#define SPI_DMACON		0xec
+#define SPI_IRNEN		0xf4
+#define SPI_IRNICR		0xf8
+#define SPI_IRNCR		0xfc
+
+#define SPI_CLC_SMC_S		16	/* Clock divider for sleep mode */
+#define SPI_CLC_SMC_M		(0xFF << SPI_CLC_SMC_S)
+#define SPI_CLC_RMC_S		8	/* Clock divider for normal run mode */
+#define SPI_CLC_RMC_M		(0xFF << SPI_CLC_RMC_S)
+#define SPI_CLC_DISS		BIT(1)	/* Disable status bit */
+#define SPI_CLC_DISR		BIT(0)	/* Disable request bit */
+
+#define SPI_ID_TXFS_S		24	/* Implemented TX FIFO size */
+#define SPI_ID_TXFS_M		(0x3F << SPI_ID_TXFS_S)
+#define SPI_ID_RXFS_S		16	/* Implemented RX FIFO size */
+#define SPI_ID_RXFS_M		(0x3F << SPI_ID_RXFS_S)
+#define SPI_ID_MOD_S		8	/* Module ID */
+#define SPI_ID_MOD_M		(0xff << SPI_ID_MOD_S)
+#define SPI_ID_CFG_S		5	/* DMA interface support */
+#define SPI_ID_CFG_M		(1 << SPI_ID_CFG_S)
+#define SPI_ID_REV_M		0x1F	/* Hardware revision number */
+
+#define SPI_CON_BM_S		16	/* Data width selection */
+#define SPI_CON_BM_M		(0x1F << SPI_CON_BM_S)
+#define SPI_CON_EM		BIT(24)	/* Echo mode */
+#define SPI_CON_IDLE		BIT(23)	/* Idle bit value */
+#define SPI_CON_ENBV		BIT(22)	/* Enable byte valid control */
+#define SPI_CON_RUEN		BIT(12)	/* Receive underflow error enable */
+#define SPI_CON_TUEN		BIT(11)	/* Transmit underflow error enable */
+#define SPI_CON_AEN		BIT(10)	/* Abort error enable */
+#define SPI_CON_REN		BIT(9)	/* Receive overflow error enable */
+#define SPI_CON_TEN		BIT(8)	/* Transmit overflow error enable */
+#define SPI_CON_LB		BIT(7)	/* Loopback control */
+#define SPI_CON_PO		BIT(6)	/* Clock polarity control */
+#define SPI_CON_PH		BIT(5)	/* Clock phase control */
+#define SPI_CON_HB		BIT(4)	/* Heading control */
+#define SPI_CON_RXOFF		BIT(1)	/* Switch receiver off */
+#define SPI_CON_TXOFF		BIT(0)	/* Switch transmitter off */
+
+#define SPI_STAT_RXBV_S		28
+#define SPI_STAT_RXBV_M		(0x7 << SPI_STAT_RXBV_S)
+#define SPI_STAT_BSY		BIT(13)	/* Busy flag */
+#define SPI_STAT_RUE		BIT(12)	/* Receive underflow error flag */
+#define SPI_STAT_TUE		BIT(11)	/* Transmit underflow error flag */
+#define SPI_STAT_AE		BIT(10)	/* Abort error flag */
+#define SPI_STAT_RE		BIT(9)	/* Receive error flag */
+#define SPI_STAT_TE		BIT(8)	/* Transmit error flag */
+#define SPI_STAT_ME		BIT(7)	/* Mode error flag */
+#define SPI_STAT_MS		BIT(1)	/* Master/slave select bit */
+#define SPI_STAT_EN		BIT(0)	/* Enable bit */
+#define SPI_STAT_ERRORS		(SPI_STAT_ME | SPI_STAT_TE | SPI_STAT_RE | \
+				 SPI_STAT_AE | SPI_STAT_TUE | SPI_STAT_RUE)
+
+#define SPI_WHBSTATE_SETTUE	BIT(15)	/* Set transmit underflow error flag */
+#define SPI_WHBSTATE_SETAE	BIT(14)	/* Set abort error flag */
+#define SPI_WHBSTATE_SETRE	BIT(13)	/* Set receive error flag */
+#define SPI_WHBSTATE_SETTE	BIT(12)	/* Set transmit error flag */
+#define SPI_WHBSTATE_CLRTUE	BIT(11)	/* Clear transmit underflow error flag */
+#define SPI_WHBSTATE_CLRAE	BIT(10)	/* Clear abort error flag */
+#define SPI_WHBSTATE_CLRRE	BIT(9)	/* Clear receive error flag */
+#define SPI_WHBSTATE_CLRTE	BIT(8)	/* Clear transmit error flag */
+#define SPI_WHBSTATE_SETME	BIT(7)	/* Set mode error flag */
+#define SPI_WHBSTATE_CLRME	BIT(6)	/* Clear mode error flag */
+#define SPI_WHBSTATE_SETRUE	BIT(5)	/* Set receive underflow error flag */
+#define SPI_WHBSTATE_CLRRUE	BIT(4)	/* Clear receive underflow error flag */
+#define SPI_WHBSTATE_SETMS	BIT(3)	/* Set master select bit */
+#define SPI_WHBSTATE_CLRMS	BIT(2)	/* Clear master select bit */
+#define SPI_WHBSTATE_SETEN	BIT(1)	/* Set enable bit (operational mode) */
+#define SPI_WHBSTATE_CLREN	BIT(0)	/* Clear enable bit (config mode */
+#define SPI_WHBSTATE_CLR_ERRORS	(SPI_WHBSTATE_CLRRUE | SPI_WHBSTATE_CLRME | \
+				 SPI_WHBSTATE_CLRTE | SPI_WHBSTATE_CLRRE | \
+				 SPI_WHBSTATE_CLRAE | SPI_WHBSTATE_CLRTUE)
+
+#define SPI_RXFCON_RXFITL_S	8	/* FIFO interrupt trigger level */
+#define SPI_RXFCON_RXFITL_M	(0x3F << SPI_RXFCON_RXFITL_S)
+#define SPI_RXFCON_RXFLU	BIT(1)	/* FIFO flush */
+#define SPI_RXFCON_RXFEN	BIT(0)	/* FIFO enable */
+
+#define SPI_TXFCON_TXFITL_S	8	/* FIFO interrupt trigger level */
+#define SPI_TXFCON_TXFITL_M	(0x3F << SPI_TXFCON_TXFITL_S)
+#define SPI_TXFCON_TXFLU	BIT(1)	/* FIFO flush */
+#define SPI_TXFCON_TXFEN	BIT(0)	/* FIFO enable */
+
+#define SPI_FSTAT_RXFFL_S	0
+#define SPI_FSTAT_RXFFL_M	(0x3f << SPI_FSTAT_RXFFL_S)
+#define SPI_FSTAT_TXFFL_S	8
+#define SPI_FSTAT_TXFFL_M	(0x3f << SPI_FSTAT_TXFFL_S)
+
+#define SPI_GPOCON_ISCSBN_S	8
+#define SPI_GPOCON_INVOUTN_S	0
+
+#define SPI_FGPO_SETOUTN_S	8
+#define SPI_FGPO_CLROUTN_S	0
+
+#define SPI_RXREQ_RXCNT_M	0xFFFF	/* Receive count value */
+#define SPI_RXCNT_TODO_M	0xFFFF	/* Recevie to-do value */
+
+#define SPI_IRNEN_TFI		BIT(4)	/* TX finished interrupt */
+#define SPI_IRNEN_F		BIT(3)	/* Frame end interrupt request */
+#define SPI_IRNEN_E		BIT(2)	/* Error end interrupt request */
+#define SPI_IRNEN_T_XWAY	BIT(1)	/* Transmit end interrupt request */
+#define SPI_IRNEN_R_XWAY	BIT(0)	/* Receive end interrupt request */
+#define SPI_IRNEN_R_XRX		BIT(1)	/* Transmit end interrupt request */
+#define SPI_IRNEN_T_XRX		BIT(0)	/* Receive end interrupt request */
+#define SPI_IRNEN_ALL		0x1F
+
+struct lantiq_ssc_hwcfg {
+	unsigned int irnen_r;
+	unsigned int irnen_t;
+};
+
+struct lantiq_ssc_spi {
+	struct spi_master		*master;
+	struct device			*dev;
+	void __iomem			*regbase;
+	struct clk			*spi_clk;
+	struct clk			*fpi_clk;
+	const struct lantiq_ssc_hwcfg	*hwcfg;
+
+	spinlock_t			lock;
+	struct workqueue_struct		*wq;
+	struct work_struct		work;
+
+	const u8			*tx;
+	u8				*rx;
+	unsigned int			tx_todo;
+	unsigned int			rx_todo;
+	unsigned int			bits_per_word;
+	unsigned int			speed_hz;
+	unsigned int			tx_fifo_size;
+	unsigned int			rx_fifo_size;
+	unsigned int			base_cs;
+};
+
+static u32 lantiq_ssc_readl(const struct lantiq_ssc_spi *spi, u32 reg)
+{
+	return __raw_readl(spi->regbase + reg);
+}
+
+static void lantiq_ssc_writel(const struct lantiq_ssc_spi *spi, u32 val,
+			      u32 reg)
+{
+	__raw_writel(val, spi->regbase + reg);
+}
+
+static void lantiq_ssc_maskl(const struct lantiq_ssc_spi *spi, u32 clr,
+			     u32 set, u32 reg)
+{
+	u32 val = __raw_readl(spi->regbase + reg);
+
+	val &= ~clr;
+	val |= set;
+	__raw_writel(val, spi->regbase + reg);
+}
+
+static unsigned int tx_fifo_level(const struct lantiq_ssc_spi *spi)
+{
+	u32 fstat = lantiq_ssc_readl(spi, SPI_FSTAT);
+
+	return (fstat & SPI_FSTAT_TXFFL_M) >> SPI_FSTAT_TXFFL_S;
+}
+
+static unsigned int rx_fifo_level(const struct lantiq_ssc_spi *spi)
+{
+	u32 fstat = lantiq_ssc_readl(spi, SPI_FSTAT);
+
+	return fstat & SPI_FSTAT_RXFFL_M;
+}
+
+static unsigned int tx_fifo_free(const struct lantiq_ssc_spi *spi)
+{
+	return spi->tx_fifo_size - tx_fifo_level(spi);
+}
+
+static void rx_fifo_reset(const struct lantiq_ssc_spi *spi)
+{
+	u32 val = spi->rx_fifo_size << SPI_RXFCON_RXFITL_S;
+
+	val |= SPI_RXFCON_RXFEN | SPI_RXFCON_RXFLU;
+	lantiq_ssc_writel(spi, val, SPI_RXFCON);
+}
+
+static void tx_fifo_reset(const struct lantiq_ssc_spi *spi)
+{
+	u32 val = 1 << SPI_TXFCON_TXFITL_S;
+
+	val |= SPI_TXFCON_TXFEN | SPI_TXFCON_TXFLU;
+	lantiq_ssc_writel(spi, val, SPI_TXFCON);
+}
+
+static void rx_fifo_flush(const struct lantiq_ssc_spi *spi)
+{
+	lantiq_ssc_maskl(spi, 0, SPI_RXFCON_RXFLU, SPI_RXFCON);
+}
+
+static void tx_fifo_flush(const struct lantiq_ssc_spi *spi)
+{
+	lantiq_ssc_maskl(spi, 0, SPI_TXFCON_TXFLU, SPI_TXFCON);
+}
+
+static void hw_enter_config_mode(const struct lantiq_ssc_spi *spi)
+{
+	lantiq_ssc_writel(spi, SPI_WHBSTATE_CLREN, SPI_WHBSTATE);
+}
+
+static void hw_enter_active_mode(const struct lantiq_ssc_spi *spi)
+{
+	lantiq_ssc_writel(spi, SPI_WHBSTATE_SETEN, SPI_WHBSTATE);
+}
+
+static void hw_setup_speed_hz(const struct lantiq_ssc_spi *spi,
+			      unsigned int max_speed_hz)
+{
+	u32 spi_clk, brt;
+
+	/*
+	 * SPI module clock is derived from FPI bus clock dependent on
+	 * divider value in CLC.RMS which is always set to 1.
+	 *
+	 *                 f_SPI
+	 * baudrate = --------------
+	 *             2 * (BR + 1)
+	 */
+	spi_clk = clk_get_rate(spi->fpi_clk) / 2;
+
+	if (max_speed_hz > spi_clk)
+		brt = 0;
+	else
+		brt = spi_clk / max_speed_hz - 1;
+
+	if (brt > 0xFFFF)
+		brt = 0xFFFF;
+
+	dev_dbg(spi->dev, "spi_clk %u, max_speed_hz %u, brt %u\n",
+		spi_clk, max_speed_hz, brt);
+
+	lantiq_ssc_writel(spi, brt, SPI_BRT);
+}
+
+static void hw_setup_bits_per_word(const struct lantiq_ssc_spi *spi,
+				   unsigned int bits_per_word)
+{
+	u32 bm;
+
+	/* CON.BM value = bits_per_word - 1 */
+	bm = (bits_per_word - 1) << SPI_CON_BM_S;
+
+	lantiq_ssc_maskl(spi, SPI_CON_BM_M, bm, SPI_CON);
+}
+
+static void hw_setup_clock_mode(const struct lantiq_ssc_spi *spi,
+				unsigned int mode)
+{
+	u32 con_set = 0, con_clr = 0;
+
+	/*
+	 * SPI mode mapping in CON register:
+	 * Mode CPOL CPHA CON.PO CON.PH
+	 *  0    0    0      0      1
+	 *  1    0    1      0      0
+	 *  2    1    0      1      1
+	 *  3    1    1      1      0
+	 */
+	if (mode & SPI_CPHA)
+		con_clr |= SPI_CON_PH;
+	else
+		con_set |= SPI_CON_PH;
+
+	if (mode & SPI_CPOL)
+		con_set |= SPI_CON_PO | SPI_CON_IDLE;
+	else
+		con_clr |= SPI_CON_PO | SPI_CON_IDLE;
+
+	/* Set heading control */
+	if (mode & SPI_LSB_FIRST)
+		con_clr |= SPI_CON_HB;
+	else
+		con_set |= SPI_CON_HB;
+
+	/* Set loopback mode */
+	if (mode & SPI_LOOP)
+		con_set |= SPI_CON_LB;
+	else
+		con_clr |= SPI_CON_LB;
+
+	lantiq_ssc_maskl(spi, con_clr, con_set, SPI_CON);
+}
+
+static void lantiq_ssc_hw_init(const struct lantiq_ssc_spi *spi)
+{
+	const struct lantiq_ssc_hwcfg *hwcfg = spi->hwcfg;
+
+	/*
+	 * Set clock divider for run mode to 1 to
+	 * run at same frequency as FPI bus
+	 */
+	lantiq_ssc_writel(spi, 1 << SPI_CLC_RMC_S, SPI_CLC);
+
+	/* Put controller into config mode */
+	hw_enter_config_mode(spi);
+
+	/* Clear error flags */
+	lantiq_ssc_maskl(spi, 0, SPI_WHBSTATE_CLR_ERRORS, SPI_WHBSTATE);
+
+	/* Enable error checking, disable TX/RX */
+	lantiq_ssc_writel(spi, SPI_CON_RUEN | SPI_CON_AEN | SPI_CON_TEN |
+		SPI_CON_REN | SPI_CON_TXOFF | SPI_CON_RXOFF, SPI_CON);
+
+	/* Setup default SPI mode */
+	hw_setup_bits_per_word(spi, spi->bits_per_word);
+	hw_setup_clock_mode(spi, SPI_MODE_0);
+
+	/* Enable master mode and clear error flags */
+	lantiq_ssc_writel(spi, SPI_WHBSTATE_SETMS | SPI_WHBSTATE_CLR_ERRORS,
+			       SPI_WHBSTATE);
+
+	/* Reset GPIO/CS registers */
+	lantiq_ssc_writel(spi, 0, SPI_GPOCON);
+	lantiq_ssc_writel(spi, 0xFF00, SPI_FPGO);
+
+	/* Enable and flush FIFOs */
+	rx_fifo_reset(spi);
+	tx_fifo_reset(spi);
+
+	/* Enable interrupts */
+	lantiq_ssc_writel(spi, hwcfg->irnen_t | hwcfg->irnen_r | SPI_IRNEN_E,
+			  SPI_IRNEN);
+}
+
+static int lantiq_ssc_setup(struct spi_device *spidev)
+{
+	struct spi_master *master = spidev->master;
+	struct lantiq_ssc_spi *spi = spi_master_get_devdata(master);
+	unsigned int cs = spidev->chip_select;
+	u32 gpocon;
+
+	/* GPIOs are used for CS */
+	if (gpio_is_valid(spidev->cs_gpio))
+		return 0;
+
+	dev_dbg(spi->dev, "using internal chipselect %u\n", cs);
+
+	if (cs < spi->base_cs) {
+		dev_err(spi->dev,
+			"chipselect %i too small (min %i)\n", cs, spi->base_cs);
+		return -EINVAL;
+	}
+
+	/* set GPO pin to CS mode */
+	gpocon = 1 << ((cs - spi->base_cs) + SPI_GPOCON_ISCSBN_S);
+
+	/* invert GPO pin */
+	if (spidev->mode & SPI_CS_HIGH)
+		gpocon |= 1 << (cs - spi->base_cs);
+
+	lantiq_ssc_maskl(spi, 0, gpocon, SPI_GPOCON);
+
+	return 0;
+}
+
+static int lantiq_ssc_prepare_message(struct spi_master *master,
+				      struct spi_message *message)
+{
+	struct lantiq_ssc_spi *spi = spi_master_get_devdata(master);
+
+	hw_enter_config_mode(spi);
+	hw_setup_clock_mode(spi, message->spi->mode);
+	hw_enter_active_mode(spi);
+
+	return 0;
+}
+
+static void hw_setup_transfer(struct lantiq_ssc_spi *spi,
+			      struct spi_device *spidev, struct spi_transfer *t)
+{
+	unsigned int speed_hz = t->speed_hz;
+	unsigned int bits_per_word = t->bits_per_word;
+	u32 con;
+
+	if (bits_per_word != spi->bits_per_word ||
+		speed_hz != spi->speed_hz) {
+		hw_enter_config_mode(spi);
+		hw_setup_speed_hz(spi, speed_hz);
+		hw_setup_bits_per_word(spi, bits_per_word);
+		hw_enter_active_mode(spi);
+
+		spi->speed_hz = speed_hz;
+		spi->bits_per_word = bits_per_word;
+	}
+
+	/* Configure transmitter and receiver */
+	con = lantiq_ssc_readl(spi, SPI_CON);
+	if (t->tx_buf)
+		con &= ~SPI_CON_TXOFF;
+	else
+		con |= SPI_CON_TXOFF;
+
+	if (t->rx_buf)
+		con &= ~SPI_CON_RXOFF;
+	else
+		con |= SPI_CON_RXOFF;
+
+	lantiq_ssc_writel(spi, con, SPI_CON);
+}
+
+static int lantiq_ssc_unprepare_message(struct spi_master *master,
+					struct spi_message *message)
+{
+	struct lantiq_ssc_spi *spi = spi_master_get_devdata(master);
+
+	flush_workqueue(spi->wq);
+
+	/* Disable transmitter and receiver while idle */
+	lantiq_ssc_maskl(spi, 0, SPI_CON_TXOFF | SPI_CON_RXOFF, SPI_CON);
+
+	return 0;
+}
+
+static void tx_fifo_write(struct lantiq_ssc_spi *spi)
+{
+	const u8 *tx8;
+	const u16 *tx16;
+	const u32 *tx32;
+	u32 data;
+	unsigned int tx_free = tx_fifo_free(spi);
+
+	while (spi->tx_todo && tx_free) {
+		switch (spi->bits_per_word) {
+		case 2 ... 8:
+			tx8 = spi->tx;
+			data = *tx8;
+			spi->tx_todo--;
+			spi->tx++;
+			break;
+		case 16:
+			tx16 = (u16 *) spi->tx;
+			data = *tx16;
+			spi->tx_todo -= 2;
+			spi->tx += 2;
+			break;
+		case 32:
+			tx32 = (u32 *) spi->tx;
+			data = *tx32;
+			spi->tx_todo -= 4;
+			spi->tx += 4;
+			break;
+		default:
+			WARN_ON(1);
+			data = 0;
+			break;
+		}
+
+		lantiq_ssc_writel(spi, data, SPI_TB);
+		tx_free--;
+	}
+}
+
+static void rx_fifo_read_full_duplex(struct lantiq_ssc_spi *spi)
+{
+	u8 *rx8;
+	u16 *rx16;
+	u32 *rx32;
+	u32 data;
+	unsigned int rx_fill = rx_fifo_level(spi);
+
+	while (rx_fill) {
+		data = lantiq_ssc_readl(spi, SPI_RB);
+
+		switch (spi->bits_per_word) {
+		case 2 ... 8:
+			rx8 = spi->rx;
+			*rx8 = data;
+			spi->rx_todo--;
+			spi->rx++;
+			break;
+		case 16:
+			rx16 = (u16 *) spi->rx;
+			*rx16 = data;
+			spi->rx_todo -= 2;
+			spi->rx += 2;
+			break;
+		case 32:
+			rx32 = (u32 *) spi->rx;
+			*rx32 = data;
+			spi->rx_todo -= 4;
+			spi->rx += 4;
+			break;
+		default:
+			WARN_ON(1);
+			break;
+		}
+
+		rx_fill--;
+	}
+}
+
+static void rx_fifo_read_half_duplex(struct lantiq_ssc_spi *spi)
+{
+	u32 data, *rx32;
+	u8 *rx8;
+	unsigned int rxbv, shift;
+	unsigned int rx_fill = rx_fifo_level(spi);
+
+	/*
+	 * In RX-only mode the bits per word value is ignored by HW. A value
+	 * of 32 is used instead. Thus all 4 bytes per FIFO must be read.
+	 * If remaining RX bytes are less than 4, the FIFO must be read
+	 * differently. The amount of received and valid bytes is indicated
+	 * by STAT.RXBV register value.
+	 */
+	while (rx_fill) {
+		if (spi->rx_todo < 4)  {
+			rxbv = (lantiq_ssc_readl(spi, SPI_STAT) &
+				SPI_STAT_RXBV_M) >> SPI_STAT_RXBV_S;
+			data = lantiq_ssc_readl(spi, SPI_RB);
+
+			shift = (rxbv - 1) * 8;
+			rx8 = spi->rx;
+
+			while (rxbv) {
+				*rx8++ = (data >> shift) & 0xFF;
+				rxbv--;
+				shift -= 8;
+				spi->rx_todo--;
+				spi->rx++;
+			}
+		} else {
+			data = lantiq_ssc_readl(spi, SPI_RB);
+			rx32 = (u32 *) spi->rx;
+
+			*rx32++ = data;
+			spi->rx_todo -= 4;
+			spi->rx += 4;
+		}
+		rx_fill--;
+	}
+}
+
+static void rx_request(struct lantiq_ssc_spi *spi)
+{
+	unsigned int rxreq, rxreq_max;
+
+	/*
+	 * To avoid receive overflows at high clocks it is better to request
+	 * only the amount of bytes that fits into all FIFOs. This value
+	 * depends on the FIFO size implemented in hardware.
+	 */
+	rxreq = spi->rx_todo;
+	rxreq_max = spi->rx_fifo_size * 4;
+	if (rxreq > rxreq_max)
+		rxreq = rxreq_max;
+
+	lantiq_ssc_writel(spi, rxreq, SPI_RXREQ);
+}
+
+static irqreturn_t lantiq_ssc_xmit_interrupt(int irq, void *data)
+{
+	struct lantiq_ssc_spi *spi = data;
+
+	if (spi->tx) {
+		if (spi->rx && spi->rx_todo)
+			rx_fifo_read_full_duplex(spi);
+
+		if (spi->tx_todo)
+			tx_fifo_write(spi);
+		else if (!tx_fifo_level(spi))
+			goto completed;
+	} else if (spi->rx) {
+		if (spi->rx_todo) {
+			rx_fifo_read_half_duplex(spi);
+
+			if (spi->rx_todo)
+				rx_request(spi);
+			else
+				goto completed;
+		} else {
+			goto completed;
+		}
+	}
+
+	return IRQ_HANDLED;
+
+completed:
+	queue_work(spi->wq, &spi->work);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t lantiq_ssc_err_interrupt(int irq, void *data)
+{
+	struct lantiq_ssc_spi *spi = data;
+	u32 stat = lantiq_ssc_readl(spi, SPI_STAT);
+
+	if (!(stat & SPI_STAT_ERRORS))
+		return IRQ_NONE;
+
+	if (stat & SPI_STAT_RUE)
+		dev_err(spi->dev, "receive underflow error\n");
+	if (stat & SPI_STAT_TUE)
+		dev_err(spi->dev, "transmit underflow error\n");
+	if (stat & SPI_STAT_AE)
+		dev_err(spi->dev, "abort error\n");
+	if (stat & SPI_STAT_RE)
+		dev_err(spi->dev, "receive overflow error\n");
+	if (stat & SPI_STAT_TE)
+		dev_err(spi->dev, "transmit overflow error\n");
+	if (stat & SPI_STAT_ME)
+		dev_err(spi->dev, "mode error\n");
+
+	/* Clear error flags */
+	lantiq_ssc_maskl(spi, 0, SPI_WHBSTATE_CLR_ERRORS, SPI_WHBSTATE);
+
+	/* set bad status so it can be retried */
+	if (spi->master->cur_msg)
+		spi->master->cur_msg->status = -EIO;
+	queue_work(spi->wq, &spi->work);
+
+	return IRQ_HANDLED;
+}
+
+static int transfer_start(struct lantiq_ssc_spi *spi, struct spi_device *spidev,
+			  struct spi_transfer *t)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&spi->lock, flags);
+
+	spi->tx = t->tx_buf;
+	spi->rx = t->rx_buf;
+
+	if (t->tx_buf) {
+		spi->tx_todo = t->len;
+
+		/* initially fill TX FIFO */
+		tx_fifo_write(spi);
+	}
+
+	if (spi->rx) {
+		spi->rx_todo = t->len;
+
+		/* start shift clock in RX-only mode */
+		if (!spi->tx)
+			rx_request(spi);
+	}
+
+	spin_unlock_irqrestore(&spi->lock, flags);
+
+	return t->len;
+}
+
+/*
+ * The driver only gets an interrupt when the FIFO is empty, but there
+ * is an additional shift register from which the data is written to
+ * the wire. We get the last interrupt when the controller starts to
+ * write the last word to the wire, not when it is finished. Do busy
+ * waiting till it finishes.
+ */
+static void lantiq_ssc_bussy_work(struct work_struct *work)
+{
+	struct lantiq_ssc_spi *spi;
+	unsigned long long timeout = 8LL * 1000LL;
+	unsigned long end;
+
+	spi = container_of(work, typeof(*spi), work);
+
+	do_div(timeout, spi->speed_hz);
+	timeout += timeout + 100; /* some tolerance */
+
+	end = jiffies + msecs_to_jiffies(timeout);
+	do {
+		u32 stat = lantiq_ssc_readl(spi, SPI_STAT);
+
+		if (!(stat & SPI_STAT_BSY)) {
+			spi_finalize_current_transfer(spi->master);
+			return;
+		}
+
+		cond_resched();
+	} while (!time_after_eq(jiffies, end));
+
+	if (spi->master->cur_msg)
+		spi->master->cur_msg->status = -EIO;
+	spi_finalize_current_transfer(spi->master);
+}
+
+static void lantiq_ssc_handle_err(struct spi_master *master,
+				  struct spi_message *message)
+{
+	struct lantiq_ssc_spi *spi = spi_master_get_devdata(master);
+
+	/* flush FIFOs on timeout */
+	rx_fifo_flush(spi);
+	tx_fifo_flush(spi);
+}
+
+static void lantiq_ssc_set_cs(struct spi_device *spidev, bool enable)
+{
+	struct lantiq_ssc_spi *spi = spi_master_get_devdata(spidev->master);
+	unsigned int cs = spidev->chip_select;
+	u32 fgpo;
+
+	if (!!(spidev->mode & SPI_CS_HIGH) == enable)
+		fgpo = (1 << (cs - spi->base_cs));
+	else
+		fgpo = (1 << (cs - spi->base_cs + SPI_FGPO_SETOUTN_S));
+
+	lantiq_ssc_writel(spi, fgpo, SPI_FPGO);
+}
+
+static int lantiq_ssc_transfer_one(struct spi_master *master,
+				   struct spi_device *spidev,
+				   struct spi_transfer *t)
+{
+	struct lantiq_ssc_spi *spi = spi_master_get_devdata(master);
+
+	hw_setup_transfer(spi, spidev, t);
+
+	return transfer_start(spi, spidev, t);
+}
+
+static const struct lantiq_ssc_hwcfg lantiq_ssc_xway = {
+	.irnen_r = SPI_IRNEN_R_XWAY,
+	.irnen_t = SPI_IRNEN_T_XWAY,
+};
+
+static const struct lantiq_ssc_hwcfg lantiq_ssc_xrx = {
+	.irnen_r = SPI_IRNEN_R_XRX,
+	.irnen_t = SPI_IRNEN_T_XRX,
+};
+
+static const struct of_device_id lantiq_ssc_match[] = {
+	{ .compatible = "lantiq,ase-spi", .data = &lantiq_ssc_xway, },
+	{ .compatible = "lantiq,falcon-spi", .data = &lantiq_ssc_xrx, },
+	{ .compatible = "lantiq,xrx100-spi", .data = &lantiq_ssc_xrx, },
+	{},
+};
+MODULE_DEVICE_TABLE(of, lantiq_ssc_match);
+
+static int lantiq_ssc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct spi_master *master;
+	struct resource *res;
+	struct lantiq_ssc_spi *spi;
+	const struct lantiq_ssc_hwcfg *hwcfg;
+	const struct of_device_id *match;
+	int err, rx_irq, tx_irq, err_irq;
+	u32 id, supports_dma, revision;
+	unsigned int num_cs;
+
+	match = of_match_device(lantiq_ssc_match, dev);
+	if (!match) {
+		dev_err(dev, "no device match\n");
+		return -EINVAL;
+	}
+	hwcfg = match->data;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(dev, "failed to get resources\n");
+		return -ENXIO;
+	}
+
+	rx_irq = platform_get_irq_byname(pdev, SPI_RX_IRQ_NAME);
+	if (rx_irq < 0) {
+		dev_err(dev, "failed to get %s\n", SPI_RX_IRQ_NAME);
+		return -ENXIO;
+	}
+
+	tx_irq = platform_get_irq_byname(pdev, SPI_TX_IRQ_NAME);
+	if (tx_irq < 0) {
+		dev_err(dev, "failed to get %s\n", SPI_TX_IRQ_NAME);
+		return -ENXIO;
+	}
+
+	err_irq = platform_get_irq_byname(pdev, SPI_ERR_IRQ_NAME);
+	if (err_irq < 0) {
+		dev_err(dev, "failed to get %s\n", SPI_ERR_IRQ_NAME);
+		return -ENXIO;
+	}
+
+	master = spi_alloc_master(dev, sizeof(struct lantiq_ssc_spi));
+	if (!master)
+		return -ENOMEM;
+
+	spi = spi_master_get_devdata(master);
+	spi->master = master;
+	spi->dev = dev;
+	spi->hwcfg = hwcfg;
+	platform_set_drvdata(pdev, spi);
+
+	spi->regbase = devm_ioremap_resource(dev, res);
+	if (IS_ERR(spi->regbase)) {
+		err = PTR_ERR(spi->regbase);
+		goto err_master_put;
+	}
+
+	err = devm_request_irq(dev, rx_irq, lantiq_ssc_xmit_interrupt,
+			       0, SPI_RX_IRQ_NAME, spi);
+	if (err)
+		goto err_master_put;
+
+	err = devm_request_irq(dev, tx_irq, lantiq_ssc_xmit_interrupt,
+			       0, SPI_TX_IRQ_NAME, spi);
+	if (err)
+		goto err_master_put;
+
+	err = devm_request_irq(dev, err_irq, lantiq_ssc_err_interrupt,
+			       0, SPI_ERR_IRQ_NAME, spi);
+	if (err)
+		goto err_master_put;
+
+	spi->spi_clk = devm_clk_get(dev, "gate");
+	if (IS_ERR(spi->spi_clk)) {
+		err = PTR_ERR(spi->spi_clk);
+		goto err_master_put;
+	}
+	err = clk_prepare_enable(spi->spi_clk);
+	if (err)
+		goto err_master_put;
+
+	/*
+	 * Use the old clk_get_fpi() function on Lantiq platform, till it
+	 * supports common clk.
+	 */
+#if defined(CONFIG_LANTIQ) && !defined(CONFIG_COMMON_CLK)
+	spi->fpi_clk = clk_get_fpi();
+#else
+	spi->fpi_clk = clk_get(dev, "freq");
+#endif
+	if (IS_ERR(spi->fpi_clk)) {
+		err = PTR_ERR(spi->fpi_clk);
+		goto err_clk_disable;
+	}
+
+	num_cs = 8;
+	of_property_read_u32(pdev->dev.of_node, "num-cs", &num_cs);
+
+	spi->base_cs = 1;
+	of_property_read_u32(pdev->dev.of_node, "base-cs", &spi->base_cs);
+
+	spin_lock_init(&spi->lock);
+	spi->bits_per_word = 8;
+	spi->speed_hz = 0;
+
+	master->dev.of_node = pdev->dev.of_node;
+	master->num_chipselect = num_cs;
+	master->setup = lantiq_ssc_setup;
+	master->set_cs = lantiq_ssc_set_cs;
+	master->handle_err = lantiq_ssc_handle_err;
+	master->prepare_message = lantiq_ssc_prepare_message;
+	master->unprepare_message = lantiq_ssc_unprepare_message;
+	master->transfer_one = lantiq_ssc_transfer_one;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST | SPI_CS_HIGH |
+				SPI_LOOP;
+	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(2, 8) |
+				     SPI_BPW_MASK(16) | SPI_BPW_MASK(32);
+
+	spi->wq = alloc_ordered_workqueue(dev_name(dev), 0);
+	if (!spi->wq) {
+		err = -ENOMEM;
+		goto err_clk_put;
+	}
+	INIT_WORK(&spi->work, lantiq_ssc_bussy_work);
+
+	id = lantiq_ssc_readl(spi, SPI_ID);
+	spi->tx_fifo_size = (id & SPI_ID_TXFS_M) >> SPI_ID_TXFS_S;
+	spi->rx_fifo_size = (id & SPI_ID_RXFS_M) >> SPI_ID_RXFS_S;
+	supports_dma = (id & SPI_ID_CFG_M) >> SPI_ID_CFG_S;
+	revision = id & SPI_ID_REV_M;
+
+	lantiq_ssc_hw_init(spi);
+
+	dev_info(dev,
+		"Lantiq SSC SPI controller (Rev %i, TXFS %u, RXFS %u, DMA %u)\n",
+		revision, spi->tx_fifo_size, spi->rx_fifo_size, supports_dma);
+
+	err = devm_spi_register_master(dev, master);
+	if (err) {
+		dev_err(dev, "failed to register spi_master\n");
+		goto err_wq_destroy;
+	}
+
+	return 0;
+
+err_wq_destroy:
+	destroy_workqueue(spi->wq);
+err_clk_put:
+	clk_put(spi->fpi_clk);
+err_clk_disable:
+	clk_disable_unprepare(spi->spi_clk);
+err_master_put:
+	spi_master_put(master);
+
+	return err;
+}
+
+static int lantiq_ssc_remove(struct platform_device *pdev)
+{
+	struct lantiq_ssc_spi *spi = platform_get_drvdata(pdev);
+
+	lantiq_ssc_writel(spi, 0, SPI_IRNEN);
+	lantiq_ssc_writel(spi, 0, SPI_CLC);
+	rx_fifo_flush(spi);
+	tx_fifo_flush(spi);
+	hw_enter_config_mode(spi);
+
+	destroy_workqueue(spi->wq);
+	clk_disable_unprepare(spi->spi_clk);
+	clk_put(spi->fpi_clk);
+
+	return 0;
+}
+
+static struct platform_driver lantiq_ssc_driver = {
+	.probe = lantiq_ssc_probe,
+	.remove = lantiq_ssc_remove,
+	.driver = {
+		.name = "spi-lantiq-ssc",
+		.owner = THIS_MODULE,
+		.of_match_table = lantiq_ssc_match,
+	},
+};
+module_platform_driver(lantiq_ssc_driver);
+
+MODULE_DESCRIPTION("Lantiq SSC SPI controller driver");
+MODULE_AUTHOR("Daniel Schwierzeck <daniel.schwierzeck@gmail.com>");
+MODULE_AUTHOR("Hauke Mehrtens <hauke@hauke-m.de>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:spi-lantiq-ssc");
diff --git a/drivers/spi/spi-mpc52xx.c b/drivers/spi/spi-mpc52xx.c
index c36002110c30..e8b59ce4dc3a 100644
--- a/drivers/spi/spi-mpc52xx.c
+++ b/drivers/spi/spi-mpc52xx.c
@@ -437,8 +437,9 @@ static int mpc52xx_spi_probe(struct platform_device *op)
 	ms->gpio_cs_count = of_gpio_count(op->dev.of_node);
 	if (ms->gpio_cs_count > 0) {
 		master->num_chipselect = ms->gpio_cs_count;
-		ms->gpio_cs = kmalloc(ms->gpio_cs_count * sizeof(unsigned int),
-				GFP_KERNEL);
+		ms->gpio_cs = kmalloc_array(ms->gpio_cs_count,
+					    sizeof(*ms->gpio_cs),
+					    GFP_KERNEL);
 		if (!ms->gpio_cs) {
 			rc = -ENOMEM;
 			goto err_alloc_gpio;
@@ -448,8 +449,7 @@ static int mpc52xx_spi_probe(struct platform_device *op)
 			gpio_cs = of_get_gpio(op->dev.of_node, i);
 			if (gpio_cs < 0) {
 				dev_err(&op->dev,
-					"could not parse the gpio field "
-					"in oftree\n");
+					"could not parse the gpio field in oftree\n");
 				rc = -ENODEV;
 				goto err_gpio;
 			}
@@ -457,8 +457,8 @@ static int mpc52xx_spi_probe(struct platform_device *op)
 			rc = gpio_request(gpio_cs, dev_name(&op->dev));
 			if (rc) {
 				dev_err(&op->dev,
-					"can't request spi cs gpio #%d "
-					"on gpio line %d\n", i, gpio_cs);
+					"can't request spi cs gpio #%d on gpio line %d\n",
+					i, gpio_cs);
 				goto err_gpio;
 			}
 
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 899d7a8f0889..278867a31950 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -73,7 +73,7 @@
 #define MTK_SPI_IDLE 0
 #define MTK_SPI_PAUSED 1
 
-#define MTK_SPI_MAX_FIFO_SIZE 32
+#define MTK_SPI_MAX_FIFO_SIZE 32U
 #define MTK_SPI_PACKET_SIZE 1024
 
 struct mtk_spi_compatible {
@@ -333,7 +333,7 @@ static int mtk_spi_fifo_transfer(struct spi_master *master,
 	struct mtk_spi *mdata = spi_master_get_devdata(master);
 
 	mdata->cur_transfer = xfer;
-	mdata->xfer_len = xfer->len;
+	mdata->xfer_len = min(MTK_SPI_MAX_FIFO_SIZE, xfer->len);
 	mtk_spi_prepare_transfer(master, xfer);
 	mtk_spi_setup_packet(master);
 
@@ -410,7 +410,10 @@ static bool mtk_spi_can_dma(struct spi_master *master,
 			    struct spi_device *spi,
 			    struct spi_transfer *xfer)
 {
-	return xfer->len > MTK_SPI_MAX_FIFO_SIZE;
+	/* Buffers for DMA transactions must be 4-byte aligned */
+	return (xfer->len > MTK_SPI_MAX_FIFO_SIZE &&
+		(unsigned long)xfer->tx_buf % 4 == 0 &&
+		(unsigned long)xfer->rx_buf % 4 == 0);
 }
 
 static int mtk_spi_setup(struct spi_device *spi)
@@ -451,7 +454,33 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id)
 					&reg_val, remainder);
 			}
 		}
-		spi_finalize_current_transfer(master);
+
+		trans->len -= mdata->xfer_len;
+		if (!trans->len) {
+			spi_finalize_current_transfer(master);
+			return IRQ_HANDLED;
+		}
+
+		if (trans->tx_buf)
+			trans->tx_buf += mdata->xfer_len;
+		if (trans->rx_buf)
+			trans->rx_buf += mdata->xfer_len;
+
+		mdata->xfer_len = min(MTK_SPI_MAX_FIFO_SIZE, trans->len);
+		mtk_spi_setup_packet(master);
+
+		cnt = trans->len / 4;
+		iowrite32_rep(mdata->base + SPI_TX_DATA_REG, trans->tx_buf, cnt);
+
+		remainder = trans->len % 4;
+		if (remainder > 0) {
+			reg_val = 0;
+			memcpy(&reg_val, trans->tx_buf + (cnt * 4), remainder);
+			writel(reg_val, mdata->base + SPI_TX_DATA_REG);
+		}
+
+		mtk_spi_enable_transfer(master);
+
 		return IRQ_HANDLED;
 	}
 
diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c
index dd3d0a218d8b..967d94844b30 100644
--- a/drivers/spi/spi-ppc4xx.c
+++ b/drivers/spi/spi-ppc4xx.c
@@ -411,7 +411,7 @@ static int spi_ppc4xx_of_probe(struct platform_device *op)
 	if (num_gpios > 0) {
 		int i;
 
-		hw->gpios = kzalloc(sizeof(int) * num_gpios, GFP_KERNEL);
+		hw->gpios = kcalloc(num_gpios, sizeof(*hw->gpios), GFP_KERNEL);
 		if (!hw->gpios) {
 			ret = -ENOMEM;
 			goto free_master;
@@ -428,8 +428,9 @@ static int spi_ppc4xx_of_probe(struct platform_device *op)
 				/* Real CS - set the initial state. */
 				ret = gpio_request(gpio, np->name);
 				if (ret < 0) {
-					dev_err(dev, "can't request gpio "
-							"#%d: %d\n", i, ret);
+					dev_err(dev,
+						"can't request gpio #%d: %d\n",
+						i, ret);
 					goto free_gpios;
 				}
 
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index 58d2d48e16a5..869f188b02eb 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -41,6 +41,13 @@ struct pxa_spi_info {
 static struct dw_dma_slave byt_tx_param = { .dst_id = 0 };
 static struct dw_dma_slave byt_rx_param = { .src_id = 1 };
 
+static struct dw_dma_slave mrfld3_tx_param = { .dst_id = 15 };
+static struct dw_dma_slave mrfld3_rx_param = { .src_id = 14 };
+static struct dw_dma_slave mrfld5_tx_param = { .dst_id = 13 };
+static struct dw_dma_slave mrfld5_rx_param = { .src_id = 12 };
+static struct dw_dma_slave mrfld6_tx_param = { .dst_id = 11 };
+static struct dw_dma_slave mrfld6_rx_param = { .src_id = 10 };
+
 static struct dw_dma_slave bsw0_tx_param = { .dst_id = 0 };
 static struct dw_dma_slave bsw0_rx_param = { .src_id = 1 };
 static struct dw_dma_slave bsw1_tx_param = { .dst_id = 6 };
@@ -93,22 +100,39 @@ static int lpss_spi_setup(struct pci_dev *dev, struct pxa_spi_info *c)
 
 static int mrfld_spi_setup(struct pci_dev *dev, struct pxa_spi_info *c)
 {
+	struct pci_dev *dma_dev = pci_get_slot(dev->bus, PCI_DEVFN(21, 0));
+	struct dw_dma_slave *tx, *rx;
+
 	switch (PCI_FUNC(dev->devfn)) {
 	case 0:
 		c->port_id = 3;
 		c->num_chipselect = 1;
+		c->tx_param = &mrfld3_tx_param;
+		c->rx_param = &mrfld3_rx_param;
 		break;
 	case 1:
 		c->port_id = 5;
 		c->num_chipselect = 4;
+		c->tx_param = &mrfld5_tx_param;
+		c->rx_param = &mrfld5_rx_param;
 		break;
 	case 2:
 		c->port_id = 6;
 		c->num_chipselect = 1;
+		c->tx_param = &mrfld6_tx_param;
+		c->rx_param = &mrfld6_rx_param;
 		break;
 	default:
 		return -ENODEV;
 	}
+
+	tx = c->tx_param;
+	tx->dma_dev = &dma_dev->dev;
+
+	rx = c->rx_param;
+	rx->dma_dev = &dma_dev->dev;
+
+	c->dma_filter = lpss_dma_filter;
 	return 0;
 }
 
@@ -203,10 +227,16 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
 	ssp = &spi_pdata.ssp;
 	ssp->phys_base = pci_resource_start(dev, 0);
 	ssp->mmio_base = pcim_iomap_table(dev)[0];
-	ssp->irq = dev->irq;
 	ssp->port_id = (c->port_id >= 0) ? c->port_id : dev->devfn;
 	ssp->type = c->type;
 
+	pci_set_master(dev);
+
+	ret = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_ALL_TYPES);
+	if (ret < 0)
+		return ret;
+	ssp->irq = pci_irq_vector(dev, 0);
+
 	snprintf(buf, sizeof(buf), "pxa2xx-spi.%d", ssp->port_id);
 	ssp->clk = clk_register_fixed_rate(&dev->dev, buf , NULL, 0,
 					   c->max_clk_rate);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index d6239fa718be..47b65d7c4072 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -732,6 +732,20 @@ static irqreturn_t interrupt_transfer(struct driver_data *drv_data)
 	return IRQ_HANDLED;
 }
 
+static void handle_bad_msg(struct driver_data *drv_data)
+{
+	pxa2xx_spi_write(drv_data, SSCR0,
+			 pxa2xx_spi_read(drv_data, SSCR0) & ~SSCR0_SSE);
+	pxa2xx_spi_write(drv_data, SSCR1,
+			 pxa2xx_spi_read(drv_data, SSCR1) & ~drv_data->int_cr1);
+	if (!pxa25x_ssp_comp(drv_data))
+		pxa2xx_spi_write(drv_data, SSTO, 0);
+	write_SSSR_CS(drv_data, drv_data->clear_sr);
+
+	dev_err(&drv_data->pdev->dev,
+		"bad message state in interrupt handler\n");
+}
+
 static irqreturn_t ssp_int(int irq, void *dev_id)
 {
 	struct driver_data *drv_data = dev_id;
@@ -771,21 +785,11 @@ static irqreturn_t ssp_int(int irq, void *dev_id)
 	if (!(status & mask))
 		return IRQ_NONE;
 
-	if (!drv_data->master->cur_msg) {
-
-		pxa2xx_spi_write(drv_data, SSCR0,
-				 pxa2xx_spi_read(drv_data, SSCR0)
-				 & ~SSCR0_SSE);
-		pxa2xx_spi_write(drv_data, SSCR1,
-				 pxa2xx_spi_read(drv_data, SSCR1)
-				 & ~drv_data->int_cr1);
-		if (!pxa25x_ssp_comp(drv_data))
-			pxa2xx_spi_write(drv_data, SSTO, 0);
-		write_SSSR_CS(drv_data, drv_data->clear_sr);
-
-		dev_err(&drv_data->pdev->dev,
-			"bad message state in interrupt handler\n");
+	pxa2xx_spi_write(drv_data, SSCR1, sccr1_reg & ~drv_data->int_cr1);
+	pxa2xx_spi_write(drv_data, SSCR1, sccr1_reg);
 
+	if (!drv_data->master->cur_msg) {
+		handle_bad_msg(drv_data);
 		/* Never fail */
 		return IRQ_HANDLED;
 	}
@@ -1458,6 +1462,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	{ PCI_VDEVICE(INTEL, 0x1ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x1ac4), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x1ac6), LPSS_BXT_SSP },
+	/* GLK */
+	{ PCI_VDEVICE(INTEL, 0x31c2), LPSS_BXT_SSP },
+	{ PCI_VDEVICE(INTEL, 0x31c4), LPSS_BXT_SSP },
+	{ PCI_VDEVICE(INTEL, 0x31c6), LPSS_BXT_SSP },
 	/* APL */
 	{ PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP },
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 0f89c2169c24..acf31f36b898 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -17,6 +17,7 @@
 #include <linux/dmaengine.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
 #include <linux/pm_runtime.h>
@@ -843,6 +844,8 @@ static int rockchip_spi_suspend(struct device *dev)
 		clk_disable_unprepare(rs->apb_pclk);
 	}
 
+	pinctrl_pm_select_sleep_state(dev);
+
 	return ret;
 }
 
@@ -852,6 +855,8 @@ static int rockchip_spi_resume(struct device *dev)
 	struct spi_master *master = dev_get_drvdata(dev);
 	struct rockchip_spi *rs = spi_master_get_devdata(master);
 
+	pinctrl_pm_select_default_state(dev);
+
 	if (!pm_runtime_suspended(dev)) {
 		ret = clk_prepare_enable(rs->apb_pclk);
 		if (ret < 0)
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 9daf50031737..2a10b3f94ff7 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -808,7 +808,7 @@ static int qspi_transfer_out(struct rspi_data *rspi, struct spi_transfer *xfer)
 			for (i = 0; i < len; i++)
 				rspi_write_data(rspi, *tx++);
 		} else {
-			ret = rspi_pio_transfer(rspi, tx, NULL, n);
+			ret = rspi_pio_transfer(rspi, tx, NULL, len);
 			if (ret < 0)
 				return ret;
 		}
@@ -845,10 +845,9 @@ static int qspi_transfer_in(struct rspi_data *rspi, struct spi_transfer *xfer)
 			for (i = 0; i < len; i++)
 				*rx++ = rspi_read_data(rspi);
 		} else {
-			ret = rspi_pio_transfer(rspi, NULL, rx, n);
+			ret = rspi_pio_transfer(rspi, NULL, rx, len);
 			if (ret < 0)
 				return ret;
-			*rx++ = ret;
 		}
 		n -= len;
 	}
@@ -1227,10 +1226,8 @@ static int rspi_probe(struct platform_device *pdev)
 	const struct spi_ops *ops;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(struct rspi_data));
-	if (master == NULL) {
-		dev_err(&pdev->dev, "spi_alloc_master error.\n");
+	if (master == NULL)
 		return -ENOMEM;
-	}
 
 	of_id = of_match_device(rspi_of_match, &pdev->dev);
 	if (of_id) {
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 28dfdce4beae..b392cca8fa4f 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -341,43 +341,16 @@ static void s3c64xx_spi_set_cs(struct spi_device *spi, bool enable)
 static int s3c64xx_spi_prepare_transfer(struct spi_master *spi)
 {
 	struct s3c64xx_spi_driver_data *sdd = spi_master_get_devdata(spi);
-	struct device *dev = &sdd->pdev->dev;
 
 	if (is_polling(sdd))
 		return 0;
 
-	/* Acquire DMA channels */
-	sdd->rx_dma.ch = dma_request_slave_channel(dev, "rx");
-	if (!sdd->rx_dma.ch) {
-		dev_err(dev, "Failed to get RX DMA channel\n");
-		return -EBUSY;
-	}
 	spi->dma_rx = sdd->rx_dma.ch;
-
-	sdd->tx_dma.ch = dma_request_slave_channel(dev, "tx");
-	if (!sdd->tx_dma.ch) {
-		dev_err(dev, "Failed to get TX DMA channel\n");
-		dma_release_channel(sdd->rx_dma.ch);
-		return -EBUSY;
-	}
 	spi->dma_tx = sdd->tx_dma.ch;
 
 	return 0;
 }
 
-static int s3c64xx_spi_unprepare_transfer(struct spi_master *spi)
-{
-	struct s3c64xx_spi_driver_data *sdd = spi_master_get_devdata(spi);
-
-	/* Free DMA channels */
-	if (!is_polling(sdd)) {
-		dma_release_channel(sdd->rx_dma.ch);
-		dma_release_channel(sdd->tx_dma.ch);
-	}
-
-	return 0;
-}
-
 static bool s3c64xx_spi_can_dma(struct spi_master *master,
 				struct spi_device *spi,
 				struct spi_transfer *xfer)
@@ -996,7 +969,7 @@ static struct s3c64xx_spi_info *s3c64xx_spi_parse_dt(struct device *dev)
 		sci->num_cs = temp;
 	}
 
-	sci->no_cs = of_property_read_bool(dev->of_node, "broken-cs");
+	sci->no_cs = of_property_read_bool(dev->of_node, "no-cs-readback");
 
 	return sci;
 }
@@ -1094,7 +1067,6 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
 	master->prepare_transfer_hardware = s3c64xx_spi_prepare_transfer;
 	master->prepare_message = s3c64xx_spi_prepare_message;
 	master->transfer_one = s3c64xx_spi_transfer_one;
-	master->unprepare_transfer_hardware = s3c64xx_spi_unprepare_transfer;
 	master->num_chipselect = sci->num_cs;
 	master->dma_alignment = 8;
 	master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) |
@@ -1161,6 +1133,24 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (!is_polling(sdd)) {
+		/* Acquire DMA channels */
+		sdd->rx_dma.ch = dma_request_slave_channel_reason(&pdev->dev,
+								  "rx");
+		if (IS_ERR(sdd->rx_dma.ch)) {
+			dev_err(&pdev->dev, "Failed to get RX DMA channel\n");
+			ret = PTR_ERR(sdd->rx_dma.ch);
+			goto err_disable_io_clk;
+		}
+		sdd->tx_dma.ch = dma_request_slave_channel_reason(&pdev->dev,
+								  "tx");
+		if (IS_ERR(sdd->tx_dma.ch)) {
+			dev_err(&pdev->dev, "Failed to get TX DMA channel\n");
+			ret = PTR_ERR(sdd->tx_dma.ch);
+			goto err_release_rx_dma;
+		}
+	}
+
 	pm_runtime_set_autosuspend_delay(&pdev->dev, AUTOSUSPEND_TIMEOUT);
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_set_active(&pdev->dev);
@@ -1206,6 +1196,12 @@ err_pm_put:
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
 
+	if (!is_polling(sdd))
+		dma_release_channel(sdd->tx_dma.ch);
+err_release_rx_dma:
+	if (!is_polling(sdd))
+		dma_release_channel(sdd->rx_dma.ch);
+err_disable_io_clk:
 	clk_disable_unprepare(sdd->ioclk);
 err_disable_src_clk:
 	clk_disable_unprepare(sdd->src_clk);
@@ -1226,6 +1222,11 @@ static int s3c64xx_spi_remove(struct platform_device *pdev)
 
 	writel(0, sdd->regs + S3C64XX_SPI_INT_EN);
 
+	if (!is_polling(sdd)) {
+		dma_release_channel(sdd->rx_dma.ch);
+		dma_release_channel(sdd->tx_dma.ch);
+	}
+
 	clk_disable_unprepare(sdd->ioclk);
 
 	clk_disable_unprepare(sdd->src_clk);
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 1f00eeb0b5a3..2ce15ca97782 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -1164,10 +1164,8 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	int ret;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(struct sh_msiof_spi_priv));
-	if (master == NULL) {
-		dev_err(&pdev->dev, "failed to allocate spi master\n");
+	if (master == NULL)
 		return -ENOMEM;
-	}
 
 	p = spi_master_get_devdata(master);
 
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index ec6fb09e2e17..ad76a44fee6f 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -652,7 +652,8 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 		if (r == NULL) {
 			dev_err(&pdev->dev, "missing platform data\n");
-			return -ENODEV;
+			ret = -ENODEV;
+			goto free_master;
 		}
 	}
 
@@ -669,7 +670,8 @@ static int ti_qspi_probe(struct platform_device *pdev)
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		dev_err(&pdev->dev, "no irq resource?\n");
-		return irq;
+		ret = irq;
+		goto free_master;
 	}
 
 	mutex_init(&qspi->list_lock);
@@ -685,15 +687,17 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		qspi->ctrl_base =
 		syscon_regmap_lookup_by_phandle(np,
 						"syscon-chipselects");
-		if (IS_ERR(qspi->ctrl_base))
-			return PTR_ERR(qspi->ctrl_base);
+		if (IS_ERR(qspi->ctrl_base)) {
+			ret = PTR_ERR(qspi->ctrl_base);
+			goto free_master;
+		}
 		ret = of_property_read_u32_index(np,
 						 "syscon-chipselects",
 						 1, &qspi->ctrl_reg);
 		if (ret) {
 			dev_err(&pdev->dev,
 				"couldn't get ctrl_mod reg index\n");
-			return ret;
+			goto free_master;
 		}
 	}
 
@@ -714,9 +718,10 @@ static int ti_qspi_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_MEMCPY, mask);
 
 	qspi->rx_chan = dma_request_chan_by_mask(&mask);
-	if (!qspi->rx_chan) {
+	if (IS_ERR(qspi->rx_chan)) {
 		dev_err(qspi->dev,
 			"No Rx DMA available, trying mmap mode\n");
+		qspi->rx_chan = NULL;
 		ret = 0;
 		goto no_dma;
 	}
@@ -742,6 +747,7 @@ no_dma:
 	if (!ret)
 		return 0;
 
+	pm_runtime_disable(&pdev->dev);
 free_master:
 	spi_master_put(master);
 	return ret;
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index fcb991034c3d..97d137591b18 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -591,7 +591,6 @@ static void pch_spi_set_tx(struct pch_spi_data *data, int *bpw)
 
 	if (!data->pkt_rx_buff) {
 		/* flush queue and set status of all transfers to -ENOMEM */
-		dev_err(&data->master->dev, "%s :kzalloc failed\n", __func__);
 		list_for_each_entry_safe(pmsg, tmp, data->queue.next, queue) {
 			pmsg->status = -ENOMEM;
 
@@ -622,8 +621,9 @@ static void pch_spi_set_tx(struct pch_spi_data *data, int *bpw)
 	if (n_writes > PCH_MAX_FIFO_DEPTH)
 		n_writes = PCH_MAX_FIFO_DEPTH;
 
-	dev_dbg(&data->master->dev, "\n%s:Pulling down SSN low - writing "
-		"0x2 to SSNXCR\n", __func__);
+	dev_dbg(&data->master->dev,
+		"\n%s:Pulling down SSN low - writing 0x2 to SSNXCR\n",
+		__func__);
 	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_LOW);
 
 	for (j = 0; j < n_writes; j++)
@@ -915,7 +915,6 @@ static void pch_spi_release_dma(struct pch_spi_data *data)
 		dma_release_channel(dma->chan_rx);
 		dma->chan_rx = NULL;
 	}
-	return;
 }
 
 static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
@@ -1008,7 +1007,7 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 	spin_unlock_irqrestore(&data->lock, flags);
 
 	/* RX */
-	dma->sg_rx_p = kzalloc(sizeof(struct scatterlist)*num, GFP_ATOMIC);
+	dma->sg_rx_p = kcalloc(num, sizeof(*dma->sg_rx_p), GFP_ATOMIC);
 	sg_init_table(dma->sg_rx_p, num); /* Initialize SG table */
 	/* offset, length setting */
 	sg = dma->sg_rx_p;
@@ -1068,7 +1067,7 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 		head = 0;
 	}
 
-	dma->sg_tx_p = kzalloc(sizeof(struct scatterlist)*num, GFP_ATOMIC);
+	dma->sg_tx_p = kcalloc(num, sizeof(*dma->sg_tx_p), GFP_ATOMIC);
 	sg_init_table(dma->sg_tx_p, num); /* Initialize SG table */
 	/* offset, length setting */
 	sg = dma->sg_tx_p;
@@ -1181,14 +1180,16 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 			data->cur_trans =
 				list_entry(data->current_msg->transfers.next,
 					   struct spi_transfer, transfer_list);
-			dev_dbg(&data->master->dev, "%s "
-				":Getting 1st transfer message\n", __func__);
+			dev_dbg(&data->master->dev,
+				"%s :Getting 1st transfer message\n",
+				__func__);
 		} else {
 			data->cur_trans =
 				list_entry(data->cur_trans->transfer_list.next,
 					   struct spi_transfer, transfer_list);
-			dev_dbg(&data->master->dev, "%s "
-				":Getting next transfer message\n", __func__);
+			dev_dbg(&data->master->dev,
+				"%s :Getting next transfer message\n",
+				__func__);
 		}
 		spin_unlock(&data->lock);
 
@@ -1233,9 +1234,8 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 
 		/* check for delay */
 		if (data->cur_trans->delay_usecs) {
-			dev_dbg(&data->master->dev, "%s:"
-				"delay in usec=%d\n", __func__,
-				data->cur_trans->delay_usecs);
+			dev_dbg(&data->master->dev, "%s:delay in usec=%d\n",
+				__func__, data->cur_trans->delay_usecs);
 			udelay(data->cur_trans->delay_usecs);
 		}
 
@@ -1292,7 +1292,6 @@ static void pch_free_dma_buf(struct pch_spi_board_data *board_dat,
 	if (dma->rx_buf_dma)
 		dma_free_coherent(&board_dat->pdev->dev, PCH_BUF_SIZE,
 				  dma->rx_buf_virt, dma->rx_buf_dma);
-	return;
 }
 
 static void pch_alloc_dma_buf(struct pch_spi_board_data *board_dat,
@@ -1541,11 +1540,11 @@ static int pch_spi_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	int i;
 	struct pch_pd_dev_save *pd_dev_save;
 
-	pd_dev_save = kzalloc(sizeof(struct pch_pd_dev_save), GFP_KERNEL);
+	pd_dev_save = kzalloc(sizeof(*pd_dev_save), GFP_KERNEL);
 	if (!pd_dev_save)
 		return -ENOMEM;
 
-	board_dat = kzalloc(sizeof(struct pch_spi_board_data), GFP_KERNEL);
+	board_dat = kzalloc(sizeof(*board_dat), GFP_KERNEL);
 	if (!board_dat) {
 		retval = -ENOMEM;
 		goto err_no_mem;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 656dd3e3220c..44222ef9471e 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -621,8 +621,10 @@ void spi_unregister_device(struct spi_device *spi)
 	if (!spi)
 		return;
 
-	if (spi->dev.of_node)
+	if (spi->dev.of_node) {
 		of_node_clear_flag(spi->dev.of_node, OF_POPULATED);
+		of_node_put(spi->dev.of_node);
+	}
 	if (ACPI_COMPANION(&spi->dev))
 		acpi_device_clear_enumerated(ACPI_COMPANION(&spi->dev));
 	device_unregister(&spi->dev);
@@ -672,7 +674,7 @@ int spi_register_board_info(struct spi_board_info const *info, unsigned n)
 	if (!n)
 		return -EINVAL;
 
-	bi = kzalloc(n * sizeof(*bi), GFP_KERNEL);
+	bi = kcalloc(n, sizeof(*bi), GFP_KERNEL);
 	if (!bi)
 		return -ENOMEM;
 
@@ -805,12 +807,12 @@ static int __spi_map_msg(struct spi_master *master, struct spi_message *msg)
 	if (master->dma_tx)
 		tx_dev = master->dma_tx->device->dev;
 	else
-		tx_dev = &master->dev;
+		tx_dev = master->dev.parent;
 
 	if (master->dma_rx)
 		rx_dev = master->dma_rx->device->dev;
 	else
-		rx_dev = &master->dev;
+		rx_dev = master->dev.parent;
 
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		if (!master->can_dma(master, msg->spi, xfer))
@@ -852,12 +854,12 @@ static int __spi_unmap_msg(struct spi_master *master, struct spi_message *msg)
 	if (master->dma_tx)
 		tx_dev = master->dma_tx->device->dev;
 	else
-		tx_dev = &master->dev;
+		tx_dev = master->dev.parent;
 
 	if (master->dma_rx)
 		rx_dev = master->dma_rx->device->dev;
 	else
-		rx_dev = &master->dev;
+		rx_dev = master->dev.parent;
 
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		if (!master->can_dma(master, msg->spi, xfer))
@@ -1502,37 +1504,18 @@ err_init_queue:
 /*-------------------------------------------------------------------------*/
 
 #if defined(CONFIG_OF)
-static struct spi_device *
-of_register_spi_device(struct spi_master *master, struct device_node *nc)
+static int of_spi_parse_dt(struct spi_master *master, struct spi_device *spi,
+			   struct device_node *nc)
 {
-	struct spi_device *spi;
-	int rc;
 	u32 value;
-
-	/* Alloc an spi_device */
-	spi = spi_alloc_device(master);
-	if (!spi) {
-		dev_err(&master->dev, "spi_device alloc error for %s\n",
-			nc->full_name);
-		rc = -ENOMEM;
-		goto err_out;
-	}
-
-	/* Select device driver */
-	rc = of_modalias_node(nc, spi->modalias,
-				sizeof(spi->modalias));
-	if (rc < 0) {
-		dev_err(&master->dev, "cannot find modalias for %s\n",
-			nc->full_name);
-		goto err_out;
-	}
+	int rc;
 
 	/* Device address */
 	rc = of_property_read_u32(nc, "reg", &value);
 	if (rc) {
 		dev_err(&master->dev, "%s has no valid 'reg' property (%d)\n",
 			nc->full_name, rc);
-		goto err_out;
+		return rc;
 	}
 	spi->chip_select = value;
 
@@ -1590,10 +1573,41 @@ of_register_spi_device(struct spi_master *master, struct device_node *nc)
 	if (rc) {
 		dev_err(&master->dev, "%s has no valid 'spi-max-frequency' property (%d)\n",
 			nc->full_name, rc);
-		goto err_out;
+		return rc;
 	}
 	spi->max_speed_hz = value;
 
+	return 0;
+}
+
+static struct spi_device *
+of_register_spi_device(struct spi_master *master, struct device_node *nc)
+{
+	struct spi_device *spi;
+	int rc;
+
+	/* Alloc an spi_device */
+	spi = spi_alloc_device(master);
+	if (!spi) {
+		dev_err(&master->dev, "spi_device alloc error for %s\n",
+			nc->full_name);
+		rc = -ENOMEM;
+		goto err_out;
+	}
+
+	/* Select device driver */
+	rc = of_modalias_node(nc, spi->modalias,
+				sizeof(spi->modalias));
+	if (rc < 0) {
+		dev_err(&master->dev, "cannot find modalias for %s\n",
+			nc->full_name);
+		goto err_out;
+	}
+
+	rc = of_spi_parse_dt(master, spi, nc);
+	if (rc)
+		goto err_out;
+
 	/* Store a pointer to the node in the device structure */
 	of_node_get(nc);
 	spi->dev.of_node = nc;
@@ -1603,11 +1617,13 @@ of_register_spi_device(struct spi_master *master, struct device_node *nc)
 	if (rc) {
 		dev_err(&master->dev, "spi_device register error %s\n",
 			nc->full_name);
-		goto err_out;
+		goto err_of_node_put;
 	}
 
 	return spi;
 
+err_of_node_put:
+	of_node_put(nc);
 err_out:
 	spi_dev_put(spi);
 	return ERR_PTR(rc);
@@ -1722,13 +1738,15 @@ static acpi_status acpi_register_spi_device(struct spi_master *master,
 		return AE_OK;
 	}
 
+	acpi_set_modalias(adev, acpi_device_hid(adev), spi->modalias,
+			  sizeof(spi->modalias));
+
 	if (spi->irq < 0)
 		spi->irq = acpi_dev_gpio_irq_get(adev, 0);
 
 	acpi_device_set_enumerated(adev);
 
 	adev->power.flags.ignore_parent = true;
-	strlcpy(spi->modalias, acpi_device_hid(adev), sizeof(spi->modalias));
 	if (spi_add_device(spi)) {
 		adev->power.flags.ignore_parent = false;
 		dev_err(&master->dev, "failed to add SPI device %s from ACPI\n",
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index b653451843c8..937c2d5d7ec3 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -1300,7 +1300,7 @@ static int ion_debug_heap_show(struct seq_file *s, void *unused)
 			seq_printf(s, "%16s %16u %16zu %d %d\n",
 				   buffer->task_comm, buffer->pid,
 				   buffer->size, buffer->kmap_cnt,
-				   atomic_read(&buffer->ref.refcount));
+				   kref_read(&buffer->ref));
 			total_orphaned_size += buffer->size;
 		}
 	}
diff --git a/drivers/staging/comedi/comedi_buf.c b/drivers/staging/comedi/comedi_buf.c
index c7d7682b1412..1e1df89b5018 100644
--- a/drivers/staging/comedi/comedi_buf.c
+++ b/drivers/staging/comedi/comedi_buf.c
@@ -188,7 +188,7 @@ bool comedi_buf_is_mmapped(struct comedi_subdevice *s)
 {
 	struct comedi_buf_map *bm = s->async->buf_map;
 
-	return bm && (atomic_read(&bm->refcount.refcount) > 1);
+	return bm && (kref_read(&bm->refcount) > 1);
 }
 
 int comedi_buf_alloc(struct comedi_device *dev, struct comedi_subdevice *s,
diff --git a/drivers/staging/greybus/timesync_platform.c b/drivers/staging/greybus/timesync_platform.c
index 113f3d6c4b3a..27f75b17679b 100644
--- a/drivers/staging/greybus/timesync_platform.c
+++ b/drivers/staging/greybus/timesync_platform.c
@@ -45,12 +45,18 @@ u32 gb_timesync_platform_get_clock_rate(void)
 
 int gb_timesync_platform_lock_bus(struct gb_timesync_svc *pdata)
 {
+	if (!arche_platform_change_state_cb)
+		return 0;
+
 	return arche_platform_change_state_cb(ARCHE_PLATFORM_STATE_TIME_SYNC,
 					      pdata);
 }
 
 void gb_timesync_platform_unlock_bus(void)
 {
+	if (!arche_platform_change_state_cb)
+		return;
+
 	arche_platform_change_state_cb(ARCHE_PLATFORM_STATE_ACTIVE, NULL);
 }
 
diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c
index 39a72e3f0c18..7035356e56b3 100644
--- a/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c
+++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c
@@ -107,7 +107,7 @@ void __noreturn lbug_with_loc(struct libcfs_debug_msg_data *msgdata)
 		libcfs_debug_dumplog();
 	if (libcfs_panic_on_lbug)
 		panic("LBUG");
-	set_task_state(current, TASK_UNINTERRUPTIBLE);
+	set_current_state(TASK_UNINTERRUPTIBLE);
 	while (1)
 		schedule();
 }
diff --git a/drivers/staging/lustre/lustre/llite/llite_mmap.c b/drivers/staging/lustre/lustre/llite/llite_mmap.c
index ee01f20d8b11..9afa6bec3e6f 100644
--- a/drivers/staging/lustre/lustre/llite/llite_mmap.c
+++ b/drivers/staging/lustre/lustre/llite/llite_mmap.c
@@ -390,15 +390,13 @@ static int ll_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		result = VM_FAULT_LOCKED;
 		break;
 	case -ENODATA:
+	case -EAGAIN:
 	case -EFAULT:
 		result = VM_FAULT_NOPAGE;
 		break;
 	case -ENOMEM:
 		result = VM_FAULT_OOM;
 		break;
-	case -EAGAIN:
-		result = VM_FAULT_RETRY;
-		break;
 	default:
 		result = VM_FAULT_SIGBUS;
 		break;
diff --git a/drivers/target/Kconfig b/drivers/target/Kconfig
index 257361280510..e2bc99980f75 100644
--- a/drivers/target/Kconfig
+++ b/drivers/target/Kconfig
@@ -4,6 +4,7 @@ menuconfig TARGET_CORE
 	depends on SCSI && BLOCK
 	select CONFIGFS_FS
 	select CRC_T10DIF
+	select BLK_SCSI_REQUEST # only for scsi_command_size_tbl..
 	default n
 	help
 	Say Y or M here to enable the TCM Storage Engine and ConfigFS enabled
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 1ebd13ef7bd3..26929c44d703 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -352,7 +352,15 @@ int core_enable_device_list_for_node(
 			kfree(new);
 			return -EINVAL;
 		}
-		BUG_ON(orig->se_lun_acl != NULL);
+		if (orig->se_lun_acl != NULL) {
+			pr_warn_ratelimited("Detected existing explicit"
+				" se_lun_acl->se_lun_group reference for %s"
+				" mapped_lun: %llu, failing\n",
+				 nacl->initiatorname, mapped_lun);
+			mutex_unlock(&nacl->lun_entry_mutex);
+			kfree(new);
+			return -EINVAL;
+		}
 
 		rcu_assign_pointer(new->se_lun, lun);
 		rcu_assign_pointer(new->se_lun_acl, lun_acl);
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index d761025144f9..e18051185846 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -788,7 +788,7 @@ static struct t10_pr_registration *__core_scsi3_alloc_registration(
 			 * __core_scsi3_add_registration()
 			 */
 			dest_lun = rcu_dereference_check(deve_tmp->se_lun,
-				atomic_read(&deve_tmp->pr_kref.refcount) != 0);
+				kref_read(&deve_tmp->pr_kref) != 0);
 
 			pr_reg_atp = __core_scsi3_do_alloc_registration(dev,
 						nacl_tmp, dest_lun, deve_tmp,
@@ -1463,7 +1463,7 @@ static int core_scsi3_lunacl_depend_item(struct se_dev_entry *se_deve)
 	 * For nacl->dynamic_node_acl=1
 	 */
 	lun_acl = rcu_dereference_check(se_deve->se_lun_acl,
-				atomic_read(&se_deve->pr_kref.refcount) != 0);
+				kref_read(&se_deve->pr_kref) != 0);
 	if (!lun_acl)
 		return 0;
 
@@ -1478,7 +1478,7 @@ static void core_scsi3_lunacl_undepend_item(struct se_dev_entry *se_deve)
 	 * For nacl->dynamic_node_acl=1
 	 */
 	lun_acl = rcu_dereference_check(se_deve->se_lun_acl,
-				atomic_read(&se_deve->pr_kref.refcount) != 0);
+				kref_read(&se_deve->pr_kref) != 0);
 	if (!lun_acl) {
 		kref_put(&se_deve->pr_kref, target_pr_kref_release);
 		return;
@@ -1759,7 +1759,7 @@ core_scsi3_decode_spec_i_port(
 		 * 2nd loop which will never fail.
 		 */
 		dest_lun = rcu_dereference_check(dest_se_deve->se_lun,
-				atomic_read(&dest_se_deve->pr_kref.refcount) != 0);
+				kref_read(&dest_se_deve->pr_kref) != 0);
 
 		dest_pr_reg = __core_scsi3_alloc_registration(cmd->se_dev,
 					dest_node_acl, dest_lun, dest_se_deve,
@@ -3466,7 +3466,7 @@ after_iport_check:
 					iport_ptr);
 	if (!dest_pr_reg) {
 		struct se_lun *dest_lun = rcu_dereference_check(dest_se_deve->se_lun,
-				atomic_read(&dest_se_deve->pr_kref.refcount) != 0);
+				kref_read(&dest_se_deve->pr_kref) != 0);
 
 		spin_unlock(&dev->dev_reservation_lock);
 		if (core_scsi3_alloc_registration(cmd->se_dev, dest_node_acl,
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 04d7aa7390d0..a8f8e53f2f57 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -1005,7 +1005,8 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 		scsi_command_size(cmd->t_task_cdb));
 
 	req = blk_get_request(pdv->pdv_sd->request_queue,
-			(cmd->data_direction == DMA_TO_DEVICE),
+			cmd->data_direction == DMA_TO_DEVICE ?
+			REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
 			GFP_KERNEL);
 	if (IS_ERR(req)) {
 		pr_err("PSCSI: blk_get_request() failed\n");
@@ -1013,7 +1014,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 		goto fail;
 	}
 
-	blk_rq_set_block_pc(req);
+	scsi_req_init(req);
 
 	if (sgl) {
 		ret = pscsi_map_sg(cmd, sgl, sgl_nents, req);
@@ -1023,10 +1024,8 @@ pscsi_execute_cmd(struct se_cmd *cmd)
 
 	req->end_io = pscsi_req_done;
 	req->end_io_data = cmd;
-	req->cmd_len = scsi_command_size(pt->pscsi_cdb);
-	req->cmd = &pt->pscsi_cdb[0];
-	req->sense = &pt->pscsi_sense[0];
-	req->sense_len = 0;
+	scsi_req(req)->cmd_len = scsi_command_size(pt->pscsi_cdb);
+	scsi_req(req)->cmd = &pt->pscsi_cdb[0];
 	if (pdv->pdv_sd->type == TYPE_DISK)
 		req->timeout = PS_TIMEOUT_DISK;
 	else
@@ -1075,7 +1074,7 @@ static void pscsi_req_done(struct request *req, int uptodate)
 	struct pscsi_plugin_task *pt = cmd->priv;
 
 	pt->pscsi_result = req->errors;
-	pt->pscsi_resid = req->resid_len;
+	pt->pscsi_resid = scsi_req(req)->resid_len;
 
 	cmd->scsi_status = status_byte(pt->pscsi_result) << 1;
 	if (cmd->scsi_status) {
@@ -1096,6 +1095,7 @@ static void pscsi_req_done(struct request *req, int uptodate)
 		break;
 	}
 
+	memcpy(pt->pscsi_sense, scsi_req(req)->sense, TRANSPORT_SENSE_BUFFER);
 	__blk_put_request(req->q, req);
 	kfree(pt);
 }
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index 4879e70e2eef..df7b6e95c019 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -451,6 +451,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
 					     int *post_ret)
 {
 	struct se_device *dev = cmd->se_dev;
+	sense_reason_t ret = TCM_NO_SENSE;
 
 	/*
 	 * Only set SCF_COMPARE_AND_WRITE_POST to force a response fall-through
@@ -458,9 +459,12 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
 	 * sent to the backend driver.
 	 */
 	spin_lock_irq(&cmd->t_state_lock);
-	if ((cmd->transport_state & CMD_T_SENT) && !cmd->scsi_status) {
+	if (cmd->transport_state & CMD_T_SENT) {
 		cmd->se_cmd_flags |= SCF_COMPARE_AND_WRITE_POST;
 		*post_ret = 1;
+
+		if (cmd->scsi_status == SAM_STAT_CHECK_CONDITION)
+			ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 	}
 	spin_unlock_irq(&cmd->t_state_lock);
 
@@ -470,7 +474,7 @@ static sense_reason_t compare_and_write_post(struct se_cmd *cmd, bool success,
 	 */
 	up(&dev->caw_sem);
 
-	return TCM_NO_SENSE;
+	return ret;
 }
 
 static sense_reason_t compare_and_write_callback(struct se_cmd *cmd, bool success,
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 1cadc9eefa21..437591bc7c08 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -457,8 +457,20 @@ static void target_complete_nacl(struct kref *kref)
 {
 	struct se_node_acl *nacl = container_of(kref,
 				struct se_node_acl, acl_kref);
+	struct se_portal_group *se_tpg = nacl->se_tpg;
 
-	complete(&nacl->acl_free_comp);
+	if (!nacl->dynamic_stop) {
+		complete(&nacl->acl_free_comp);
+		return;
+	}
+
+	mutex_lock(&se_tpg->acl_node_mutex);
+	list_del(&nacl->acl_list);
+	mutex_unlock(&se_tpg->acl_node_mutex);
+
+	core_tpg_wait_for_nacl_pr_ref(nacl);
+	core_free_device_list_for_node(nacl, se_tpg);
+	kfree(nacl);
 }
 
 void target_put_nacl(struct se_node_acl *nacl)
@@ -499,12 +511,39 @@ EXPORT_SYMBOL(transport_deregister_session_configfs);
 void transport_free_session(struct se_session *se_sess)
 {
 	struct se_node_acl *se_nacl = se_sess->se_node_acl;
+
 	/*
 	 * Drop the se_node_acl->nacl_kref obtained from within
 	 * core_tpg_get_initiator_node_acl().
 	 */
 	if (se_nacl) {
+		struct se_portal_group *se_tpg = se_nacl->se_tpg;
+		const struct target_core_fabric_ops *se_tfo = se_tpg->se_tpg_tfo;
+		unsigned long flags;
+
 		se_sess->se_node_acl = NULL;
+
+		/*
+		 * Also determine if we need to drop the extra ->cmd_kref if
+		 * it had been previously dynamically generated, and
+		 * the endpoint is not caching dynamic ACLs.
+		 */
+		mutex_lock(&se_tpg->acl_node_mutex);
+		if (se_nacl->dynamic_node_acl &&
+		    !se_tfo->tpg_check_demo_mode_cache(se_tpg)) {
+			spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags);
+			if (list_empty(&se_nacl->acl_sess_list))
+				se_nacl->dynamic_stop = true;
+			spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags);
+
+			if (se_nacl->dynamic_stop)
+				list_del(&se_nacl->acl_list);
+		}
+		mutex_unlock(&se_tpg->acl_node_mutex);
+
+		if (se_nacl->dynamic_stop)
+			target_put_nacl(se_nacl);
+
 		target_put_nacl(se_nacl);
 	}
 	if (se_sess->sess_cmd_map) {
@@ -518,16 +557,12 @@ EXPORT_SYMBOL(transport_free_session);
 void transport_deregister_session(struct se_session *se_sess)
 {
 	struct se_portal_group *se_tpg = se_sess->se_tpg;
-	const struct target_core_fabric_ops *se_tfo;
-	struct se_node_acl *se_nacl;
 	unsigned long flags;
-	bool drop_nacl = false;
 
 	if (!se_tpg) {
 		transport_free_session(se_sess);
 		return;
 	}
-	se_tfo = se_tpg->se_tpg_tfo;
 
 	spin_lock_irqsave(&se_tpg->session_lock, flags);
 	list_del(&se_sess->sess_list);
@@ -535,33 +570,15 @@ void transport_deregister_session(struct se_session *se_sess)
 	se_sess->fabric_sess_ptr = NULL;
 	spin_unlock_irqrestore(&se_tpg->session_lock, flags);
 
-	/*
-	 * Determine if we need to do extra work for this initiator node's
-	 * struct se_node_acl if it had been previously dynamically generated.
-	 */
-	se_nacl = se_sess->se_node_acl;
-
-	mutex_lock(&se_tpg->acl_node_mutex);
-	if (se_nacl && se_nacl->dynamic_node_acl) {
-		if (!se_tfo->tpg_check_demo_mode_cache(se_tpg)) {
-			list_del(&se_nacl->acl_list);
-			drop_nacl = true;
-		}
-	}
-	mutex_unlock(&se_tpg->acl_node_mutex);
-
-	if (drop_nacl) {
-		core_tpg_wait_for_nacl_pr_ref(se_nacl);
-		core_free_device_list_for_node(se_nacl, se_tpg);
-		se_sess->se_node_acl = NULL;
-		kfree(se_nacl);
-	}
 	pr_debug("TARGET_CORE[%s]: Deregistered fabric_sess\n",
 		se_tpg->se_tpg_tfo->get_fabric_name());
 	/*
 	 * If last kref is dropping now for an explicit NodeACL, awake sleeping
 	 * ->acl_free_comp caller to wakeup configfs se_node_acl->acl_group
 	 * removal context from within transport_free_session() code.
+	 *
+	 * For dynamic ACL, target_put_nacl() uses target_complete_nacl()
+	 * to release all remaining generate_node_acl=1 created ACL resources.
 	 */
 
 	transport_free_session(se_sess);
@@ -3110,7 +3127,6 @@ static void target_tmr_work(struct work_struct *work)
 		spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 		goto check_stop;
 	}
-	cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
 	cmd->se_tfo->queue_tm_rsp(cmd);
@@ -3123,11 +3139,25 @@ int transport_generic_handle_tmr(
 	struct se_cmd *cmd)
 {
 	unsigned long flags;
+	bool aborted = false;
 
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	cmd->transport_state |= CMD_T_ACTIVE;
+	if (cmd->transport_state & CMD_T_ABORTED) {
+		aborted = true;
+	} else {
+		cmd->t_state = TRANSPORT_ISTATE_PROCESSING;
+		cmd->transport_state |= CMD_T_ACTIVE;
+	}
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
+	if (aborted) {
+		pr_warn_ratelimited("handle_tmr caught CMD_T_ABORTED TMR %d"
+			"ref_tag: %llu tag: %llu\n", cmd->se_tmr_req->function,
+			cmd->se_tmr_req->ref_task_tag, cmd->tag);
+		transport_cmd_check_stop_to_fabric(cmd);
+		return 0;
+	}
+
 	INIT_WORK(&cmd->work, target_tmr_work);
 	queue_work(cmd->se_dev->tmr_wq, &cmd->work);
 	return 0;
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index d828b3b5000b..cac5a20a4de0 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -864,7 +864,7 @@ out:
 			" CHECK_CONDITION -> sending response\n", rc);
 		ec_cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
 	}
-	target_complete_cmd(ec_cmd, SAM_STAT_CHECK_CONDITION);
+	target_complete_cmd(ec_cmd, ec_cmd->scsi_status);
 }
 
 sense_reason_t target_do_xcopy(struct se_cmd *se_cmd)
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index fd5c3de79470..c91979c1463d 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -454,7 +454,7 @@ static void ft_sess_free(struct kref *kref)
 
 void ft_sess_put(struct ft_sess *sess)
 {
-	int sess_held = atomic_read(&sess->kref.refcount);
+	int sess_held = kref_read(&sess->kref);
 
 	BUG_ON(!sess_held);
 	kref_put(&sess->kref, ft_sess_free);
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 9ce0e9eef923..85fdbf762fa0 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -297,8 +297,6 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 	if (!power_table)
 		return -ENOMEM;
 
-	rcu_read_lock();
-
 	for (freq = 0, i = 0;
 	     opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
 	     freq++, i++) {
@@ -306,13 +304,13 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		u64 power;
 
 		if (i >= num_opps) {
-			rcu_read_unlock();
 			ret = -EAGAIN;
 			goto free_power_table;
 		}
 
 		freq_mhz = freq / 1000000;
 		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
+		dev_pm_opp_put(opp);
 
 		/*
 		 * Do the multiplication with MHz and millivolt so as
@@ -328,8 +326,6 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		power_table[i].power = power;
 	}
 
-	rcu_read_unlock();
-
 	if (i != num_opps) {
 		ret = PTR_ERR(opp);
 		goto free_power_table;
@@ -433,13 +429,10 @@ static int get_static_power(struct cpufreq_cooling_device *cpufreq_device,
 		return 0;
 	}
 
-	rcu_read_lock();
-
 	opp = dev_pm_opp_find_freq_exact(cpufreq_device->cpu_dev, freq_hz,
 					 true);
 	voltage = dev_pm_opp_get_voltage(opp);
-
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	if (voltage == 0) {
 		dev_warn_ratelimited(cpufreq_device->cpu_dev,
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index 5a737fd5f1aa..ba7a5cd994dc 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -113,15 +113,15 @@ static int partition_enable_opps(struct devfreq_cooling_device *dfc,
 		unsigned int freq = dfc->freq_table[i];
 		bool want_enable = i >= cdev_state ? true : false;
 
-		rcu_read_lock();
 		opp = dev_pm_opp_find_freq_exact(dev, freq, !want_enable);
-		rcu_read_unlock();
 
 		if (PTR_ERR(opp) == -ERANGE)
 			continue;
 		else if (IS_ERR(opp))
 			return PTR_ERR(opp);
 
+		dev_pm_opp_put(opp);
+
 		if (want_enable)
 			ret = dev_pm_opp_enable(dev, freq);
 		else
@@ -221,15 +221,12 @@ get_static_power(struct devfreq_cooling_device *dfc, unsigned long freq)
 	if (!dfc->power_ops->get_static_power)
 		return 0;
 
-	rcu_read_lock();
-
 	opp = dev_pm_opp_find_freq_exact(dev, freq, true);
 	if (IS_ERR(opp) && (PTR_ERR(opp) == -ERANGE))
 		opp = dev_pm_opp_find_freq_exact(dev, freq, false);
 
 	voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
-
-	rcu_read_unlock();
+	dev_pm_opp_put(opp);
 
 	if (voltage == 0) {
 		dev_warn_ratelimited(dev,
@@ -412,18 +409,14 @@ static int devfreq_cooling_gen_tables(struct devfreq_cooling_device *dfc)
 		unsigned long power_dyn, voltage;
 		struct dev_pm_opp *opp;
 
-		rcu_read_lock();
-
 		opp = dev_pm_opp_find_freq_floor(dev, &freq);
 		if (IS_ERR(opp)) {
-			rcu_read_unlock();
 			ret = PTR_ERR(opp);
 			goto free_tables;
 		}
 
 		voltage = dev_pm_opp_get_voltage(opp) / 1000; /* mV */
-
-		rcu_read_unlock();
+		dev_pm_opp_put(opp);
 
 		if (dfc->power_ops) {
 			power_dyn = get_dynamic_power(dfc, freq, voltage);
diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index c4a508a124dc..541af5946203 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -59,6 +59,14 @@ static LIST_HEAD(thermal_hwmon_list);
 static DEFINE_MUTEX(thermal_hwmon_list_lock);
 
 static ssize_t
+name_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct thermal_hwmon_device *hwmon = dev_get_drvdata(dev);
+	return sprintf(buf, "%s\n", hwmon->type);
+}
+static DEVICE_ATTR_RO(name);
+
+static ssize_t
 temp_input_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	int temperature;
@@ -157,12 +165,15 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 
 	INIT_LIST_HEAD(&hwmon->tz_list);
 	strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
-	hwmon->device = hwmon_device_register_with_info(NULL, hwmon->type,
-							hwmon, NULL, NULL);
+	hwmon->device = hwmon_device_register(NULL);
 	if (IS_ERR(hwmon->device)) {
 		result = PTR_ERR(hwmon->device);
 		goto free_mem;
 	}
+	dev_set_drvdata(hwmon->device, hwmon);
+	result = device_create_file(hwmon->device, &dev_attr_name);
+	if (result)
+		goto free_mem;
 
  register_sys_interface:
 	temp = kzalloc(sizeof(*temp), GFP_KERNEL);
@@ -211,8 +222,10 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
  free_temp_mem:
 	kfree(temp);
  unregister_name:
-	if (new_hwmon_device)
+	if (new_hwmon_device) {
+		device_remove_file(hwmon->device, &dev_attr_name);
 		hwmon_device_unregister(hwmon->device);
+	}
  free_mem:
 	if (new_hwmon_device)
 		kfree(hwmon);
@@ -254,6 +267,7 @@ void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz)
 	list_del(&hwmon->node);
 	mutex_unlock(&thermal_hwmon_list_lock);
 
+	device_remove_file(hwmon->device, &dev_attr_name);
 	hwmon_device_unregister(hwmon->device);
 	kfree(hwmon);
 }
diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c
index 1bf8ed13f827..9229de43e19d 100644
--- a/drivers/tty/tty_ldsem.c
+++ b/drivers/tty/tty_ldsem.c
@@ -200,7 +200,6 @@ static struct ld_semaphore __sched *
 down_read_failed(struct ld_semaphore *sem, long count, long timeout)
 {
 	struct ldsem_waiter waiter;
-	struct task_struct *tsk = current;
 	long adjust = -LDSEM_ACTIVE_BIAS + LDSEM_WAIT_BIAS;
 
 	/* set up my own style of waitqueue */
@@ -221,8 +220,8 @@ down_read_failed(struct ld_semaphore *sem, long count, long timeout)
 	list_add_tail(&waiter.list, &sem->read_wait);
 	sem->wait_readers++;
 
-	waiter.task = tsk;
-	get_task_struct(tsk);
+	waiter.task = current;
+	get_task_struct(current);
 
 	/* if there are no active locks, wake the new lock owner(s) */
 	if ((count & LDSEM_ACTIVE_MASK) == 0)
@@ -232,7 +231,7 @@ down_read_failed(struct ld_semaphore *sem, long count, long timeout)
 
 	/* wait to be given the lock */
 	for (;;) {
-		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE);
 
 		if (!waiter.task)
 			break;
@@ -241,7 +240,7 @@ down_read_failed(struct ld_semaphore *sem, long count, long timeout)
 		timeout = schedule_timeout(timeout);
 	}
 
-	__set_task_state(tsk, TASK_RUNNING);
+	__set_current_state(TASK_RUNNING);
 
 	if (!timeout) {
 		/* lock timed out but check if this task was just
@@ -268,7 +267,6 @@ static struct ld_semaphore __sched *
 down_write_failed(struct ld_semaphore *sem, long count, long timeout)
 {
 	struct ldsem_waiter waiter;
-	struct task_struct *tsk = current;
 	long adjust = -LDSEM_ACTIVE_BIAS;
 	int locked = 0;
 
@@ -289,16 +287,16 @@ down_write_failed(struct ld_semaphore *sem, long count, long timeout)
 
 	list_add_tail(&waiter.list, &sem->write_wait);
 
-	waiter.task = tsk;
+	waiter.task = current;
 
-	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	set_current_state(TASK_UNINTERRUPTIBLE);
 	for (;;) {
 		if (!timeout)
 			break;
 		raw_spin_unlock_irq(&sem->wait_lock);
 		timeout = schedule_timeout(timeout);
 		raw_spin_lock_irq(&sem->wait_lock);
-		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE);
 		locked = writer_trylock(sem);
 		if (locked)
 			break;
@@ -309,7 +307,7 @@ down_write_failed(struct ld_semaphore *sem, long count, long timeout)
 	list_del(&waiter.list);
 	raw_spin_unlock_irq(&sem->wait_lock);
 
-	__set_task_state(tsk, TASK_RUNNING);
+	__set_current_state(TASK_RUNNING);
 
 	/* lock wait may have timed out */
 	if (!locked)
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index d2e50a27140c..24f9f98968a5 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -37,6 +37,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* CBM - Flash disk */
 	{ USB_DEVICE(0x0204, 0x6025), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* WORLDE easy key (easykey.25) MIDI controller  */
+	{ USB_DEVICE(0x0218, 0x0401), .driver_info =
+			USB_QUIRK_CONFIG_INTF_STRINGS },
+
 	/* HP 5300/5370C scanner */
 	{ USB_DEVICE(0x03f0, 0x0701), .driver_info =
 			USB_QUIRK_STRING_FETCH_255 },
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 5490fc51638e..e6a17455adac 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -2269,6 +2269,8 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type,
 		if (len < sizeof(*d) || h->interface >= ffs->interfaces_count)
 			return -EINVAL;
 		length = le32_to_cpu(d->dwSize);
+		if (len < length)
+			return -EINVAL;
 		type = le32_to_cpu(d->dwPropertyDataType);
 		if (type < USB_EXT_PROP_UNICODE ||
 		    type > USB_EXT_PROP_UNICODE_MULTI) {
@@ -2277,6 +2279,11 @@ static int __ffs_data_do_os_desc(enum ffs_os_desc_type type,
 			return -EINVAL;
 		}
 		pnl = le16_to_cpu(d->wPropertyNameLength);
+		if (length < 14 + pnl) {
+			pr_vdebug("invalid os descriptor length: %d pnl:%d (descriptor %d)\n",
+				  length, pnl, type);
+			return -EINVAL;
+		}
 		pdl = le32_to_cpu(*(u32 *)((u8 *)data + 10 + pnl));
 		if (length != 14 + pnl + pdl) {
 			pr_vdebug("invalid os descriptor length: %d pnl:%d pdl:%d (descriptor %d)\n",
@@ -2363,6 +2370,9 @@ static int __ffs_data_got_descs(struct ffs_data *ffs,
 		}
 	}
 	if (flags & (1 << i)) {
+		if (len < 4) {
+			goto error;
+		}
 		os_descs_count = get_unaligned_le32(data);
 		data += 4;
 		len -= 4;
@@ -2435,7 +2445,8 @@ static int __ffs_data_got_strings(struct ffs_data *ffs,
 
 	ENTER();
 
-	if (unlikely(get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC ||
+	if (unlikely(len < 16 ||
+		     get_unaligned_le32(data) != FUNCTIONFS_STRINGS_MAGIC ||
 		     get_unaligned_le32(data + 4) != len))
 		goto error;
 	str_count  = get_unaligned_le32(data + 8);
@@ -3687,7 +3698,7 @@ static void ffs_closed(struct ffs_data *ffs)
 		goto done;
 
 	if (opts->no_configfs || !opts->func_inst.group.cg_item.ci_parent
-	    || !atomic_read(&opts->func_inst.group.cg_item.ci_kref.refcount))
+	    || !kref_read(&opts->func_inst.group.cg_item.ci_kref))
 		goto done;
 
 	ci = opts->func_inst.group.cg_item.ci_parent->ci_parent;
diff --git a/drivers/usb/mon/mon_main.c b/drivers/usb/mon/mon_main.c
index 33ff49c4cea4..46847340b819 100644
--- a/drivers/usb/mon/mon_main.c
+++ b/drivers/usb/mon/mon_main.c
@@ -409,7 +409,7 @@ static void __exit mon_exit(void)
 			printk(KERN_ERR TAG
 			    ": Outstanding opens (%d) on usb%d, leaking...\n",
 			    mbus->nreaders, mbus->u_bus->busnum);
-			atomic_set(&mbus->ref.refcount, 2);	/* Force leak */
+			kref_get(&mbus->ref); /* Force leak */
 		}
 
 		mon_dissolve(mbus, mbus->u_bus);
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index fca288bbc800..772f15821242 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -594,11 +594,11 @@ static irqreturn_t musb_stage0_irq(struct musb *musb, u8 int_usb,
 						| MUSB_PORT_STAT_RESUME;
 				musb->rh_timer = jiffies
 					+ msecs_to_jiffies(USB_RESUME_TIMEOUT);
-				musb->need_finish_resume = 1;
-
 				musb->xceiv->otg->state = OTG_STATE_A_HOST;
 				musb->is_active = 1;
 				musb_host_resume_root_hub(musb);
+				schedule_delayed_work(&musb->finish_resume_work,
+					msecs_to_jiffies(USB_RESUME_TIMEOUT));
 				break;
 			case OTG_STATE_B_WAIT_ACON:
 				musb->xceiv->otg->state = OTG_STATE_B_PERIPHERAL;
@@ -1925,6 +1925,14 @@ static void musb_pm_runtime_check_session(struct musb *musb)
 static void musb_irq_work(struct work_struct *data)
 {
 	struct musb *musb = container_of(data, struct musb, irq_work.work);
+	int error;
+
+	error = pm_runtime_get_sync(musb->controller);
+	if (error < 0) {
+		dev_err(musb->controller, "Could not enable: %i\n", error);
+
+		return;
+	}
 
 	musb_pm_runtime_check_session(musb);
 
@@ -1932,6 +1940,9 @@ static void musb_irq_work(struct work_struct *data)
 		musb->xceiv_old_state = musb->xceiv->otg->state;
 		sysfs_notify(&musb->controller->kobj, NULL, "mode");
 	}
+
+	pm_runtime_mark_last_busy(musb->controller);
+	pm_runtime_put_autosuspend(musb->controller);
 }
 
 static void musb_recover_from_babble(struct musb *musb)
@@ -2710,11 +2721,6 @@ static int musb_resume(struct device *dev)
 	mask = MUSB_DEVCTL_BDEVICE | MUSB_DEVCTL_FSDEV | MUSB_DEVCTL_LSDEV;
 	if ((devctl & mask) != (musb->context.devctl & mask))
 		musb->port1_status = 0;
-	if (musb->need_finish_resume) {
-		musb->need_finish_resume = 0;
-		schedule_delayed_work(&musb->finish_resume_work,
-				      msecs_to_jiffies(USB_RESUME_TIMEOUT));
-	}
 
 	/*
 	 * The USB HUB code expects the device to be in RPM_ACTIVE once it came
@@ -2766,12 +2772,6 @@ static int musb_runtime_resume(struct device *dev)
 
 	musb_restore_context(musb);
 
-	if (musb->need_finish_resume) {
-		musb->need_finish_resume = 0;
-		schedule_delayed_work(&musb->finish_resume_work,
-				msecs_to_jiffies(USB_RESUME_TIMEOUT));
-	}
-
 	spin_lock_irqsave(&musb->lock, flags);
 	error = musb_run_resume_work(musb);
 	if (error)
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index ade902ea1221..ce5a18c98c6d 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -410,7 +410,6 @@ struct musb {
 
 	/* is_suspended means USB B_PERIPHERAL suspend */
 	unsigned		is_suspended:1;
-	unsigned		need_finish_resume :1;
 
 	/* may_wakeup means remote wakeup is enabled */
 	unsigned		may_wakeup:1;
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 7ce31a4c7e7f..42cc72e54c05 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -2007,6 +2007,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_6802, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD300, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x421d, 0xff, 0xff, 0xff) }, /* HP lt2523 (Novatel E371) */
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 46fca6b75846..1db4b61bdf7b 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -49,6 +49,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) },
 	{ USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) },
 	{ USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) },
+	{ USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID2) },
 	{ USB_DEVICE(ATEN_VENDOR_ID2, ATEN_PRODUCT_ID) },
 	{ USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID) },
 	{ USB_DEVICE(ELCOM_VENDOR_ID, ELCOM_PRODUCT_ID_UCSGT) },
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index e3b7af8adfb7..09d9be88209e 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -27,6 +27,7 @@
 #define ATEN_VENDOR_ID		0x0557
 #define ATEN_VENDOR_ID2		0x0547
 #define ATEN_PRODUCT_ID		0x2008
+#define ATEN_PRODUCT_ID2	0x2118
 
 #define IODATA_VENDOR_ID	0x04bb
 #define IODATA_PRODUCT_ID	0x0a03
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 1bc6089b9008..696458db7e3c 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -124,6 +124,7 @@ static const struct usb_device_id id_table[] = {
 	{USB_DEVICE(0x1410, 0xa021)},	/* Novatel Gobi 3000 Composite */
 	{USB_DEVICE(0x413c, 0x8193)},	/* Dell Gobi 3000 QDL */
 	{USB_DEVICE(0x413c, 0x8194)},	/* Dell Gobi 3000 Composite */
+	{USB_DEVICE(0x413c, 0x81a6)},	/* Dell DW5570 QDL (MC8805) */
 	{USB_DEVICE(0x1199, 0x68a4)},	/* Sierra Wireless QDL */
 	{USB_DEVICE(0x1199, 0x68a5)},	/* Sierra Wireless Modem */
 	{USB_DEVICE(0x1199, 0x68a8)},	/* Sierra Wireless QDL */
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index c8823578a1b2..59b3f62a2d64 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -1123,12 +1123,11 @@ static long tce_iommu_ioctl(void *iommu_data,
 		mutex_lock(&container->lock);
 
 		ret = tce_iommu_create_default_window(container);
-		if (ret)
-			return ret;
-
-		ret = tce_iommu_create_window(container, create.page_shift,
-				create.window_size, create.levels,
-				&create.start_addr);
+		if (!ret)
+			ret = tce_iommu_create_window(container,
+					create.page_shift,
+					create.window_size, create.levels,
+					&create.start_addr);
 
 		mutex_unlock(&container->lock);
 
@@ -1246,6 +1245,8 @@ static void tce_iommu_release_ownership_ddw(struct tce_container *container,
 static long tce_iommu_take_ownership_ddw(struct tce_container *container,
 		struct iommu_table_group *table_group)
 {
+	long i, ret = 0;
+
 	if (!table_group->ops->create_table || !table_group->ops->set_window ||
 			!table_group->ops->release_ownership) {
 		WARN_ON_ONCE(1);
@@ -1254,7 +1255,27 @@ static long tce_iommu_take_ownership_ddw(struct tce_container *container,
 
 	table_group->ops->take_ownership(table_group);
 
+	/* Set all windows to the new group */
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
+		struct iommu_table *tbl = container->tables[i];
+
+		if (!tbl)
+			continue;
+
+		ret = table_group->ops->set_window(table_group, i, tbl);
+		if (ret)
+			goto release_exit;
+	}
+
 	return 0;
+
+release_exit:
+	for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
+		table_group->ops->unset_window(table_group, i);
+
+	table_group->ops->release_ownership(table_group);
+
+	return ret;
 }
 
 static int tce_iommu_attach_group(void *iommu_data,
@@ -1270,6 +1291,10 @@ static int tce_iommu_attach_group(void *iommu_data,
 	/* pr_debug("tce_vfio: Attaching group #%u to iommu %p\n",
 			iommu_group_id(iommu_group), iommu_group); */
 	table_group = iommu_group_get_iommudata(iommu_group);
+	if (!table_group) {
+		ret = -ENODEV;
+		goto unlock_exit;
+	}
 
 	if (tce_groups_attached(container) && (!table_group->ops ||
 			!table_group->ops->take_ownership ||
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index b3cc33fa6d26..bd6f293c4ebd 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -38,6 +38,8 @@
 #include <linux/workqueue.h>
 #include <linux/mdev.h>
 #include <linux/notifier.h>
+#include <linux/dma-iommu.h>
+#include <linux/irqdomain.h>
 
 #define DRIVER_VERSION  "0.2"
 #define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
@@ -1179,6 +1181,28 @@ static struct vfio_group *find_iommu_group(struct vfio_domain *domain,
 	return NULL;
 }
 
+static bool vfio_iommu_has_resv_msi(struct iommu_group *group,
+				    phys_addr_t *base)
+{
+	struct list_head group_resv_regions;
+	struct iommu_resv_region *region, *next;
+	bool ret = false;
+
+	INIT_LIST_HEAD(&group_resv_regions);
+	iommu_get_group_resv_regions(group, &group_resv_regions);
+	list_for_each_entry(region, &group_resv_regions, list) {
+		if (region->type & IOMMU_RESV_MSI) {
+			*base = region->start;
+			ret = true;
+			goto out;
+		}
+	}
+out:
+	list_for_each_entry_safe(region, next, &group_resv_regions, list)
+		kfree(region);
+	return ret;
+}
+
 static int vfio_iommu_type1_attach_group(void *iommu_data,
 					 struct iommu_group *iommu_group)
 {
@@ -1187,6 +1211,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	struct vfio_domain *domain, *d;
 	struct bus_type *bus = NULL, *mdev_bus;
 	int ret;
+	bool resv_msi, msi_remap;
+	phys_addr_t resv_msi_base;
 
 	mutex_lock(&iommu->lock);
 
@@ -1256,11 +1282,15 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	if (ret)
 		goto out_domain;
 
+	resv_msi = vfio_iommu_has_resv_msi(iommu_group, &resv_msi_base);
+
 	INIT_LIST_HEAD(&domain->group_list);
 	list_add(&group->next, &domain->group_list);
 
-	if (!allow_unsafe_interrupts &&
-	    !iommu_capable(bus, IOMMU_CAP_INTR_REMAP)) {
+	msi_remap = resv_msi ? irq_domain_check_msi_remap() :
+				iommu_capable(bus, IOMMU_CAP_INTR_REMAP);
+
+	if (!allow_unsafe_interrupts && !msi_remap) {
 		pr_warn("%s: No interrupt remapping support.  Use the module param \"allow_unsafe_interrupts\" to enable VFIO IOMMU support on this platform\n",
 		       __func__);
 		ret = -EPERM;
@@ -1302,6 +1332,12 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	if (ret)
 		goto out_detach;
 
+	if (resv_msi) {
+		ret = iommu_get_msi_cookie(domain->domain, resv_msi_base);
+		if (ret)
+			goto out_detach;
+	}
+
 	list_add(&domain->next, &iommu->domain_list);
 
 	mutex_unlock(&iommu->lock);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index d6432603880c..8f99fe08de02 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -130,14 +130,14 @@ static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx,
 
 static void vhost_init_is_le(struct vhost_virtqueue *vq)
 {
-	if (vhost_has_feature(vq, VIRTIO_F_VERSION_1))
-		vq->is_le = true;
+	vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1)
+		|| virtio_legacy_is_little_endian();
 }
 #endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */
 
 static void vhost_reset_is_le(struct vhost_virtqueue *vq)
 {
-	vq->is_le = virtio_legacy_is_little_endian();
+	vhost_init_is_le(vq);
 }
 
 struct vhost_flush_struct {
@@ -1714,10 +1714,8 @@ int vhost_vq_init_access(struct vhost_virtqueue *vq)
 	int r;
 	bool is_le = vq->is_le;
 
-	if (!vq->private_data) {
-		vhost_reset_is_le(vq);
+	if (!vq->private_data)
 		return 0;
-	}
 
 	vhost_init_is_le(vq);
 
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index bbbf588540ed..ce5e63d2c66a 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -373,6 +373,7 @@ static void vhost_vsock_handle_rx_kick(struct vhost_work *work)
 
 static int vhost_vsock_start(struct vhost_vsock *vsock)
 {
+	struct vhost_virtqueue *vq;
 	size_t i;
 	int ret;
 
@@ -383,19 +384,20 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 		goto err;
 
 	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
-		struct vhost_virtqueue *vq = &vsock->vqs[i];
+		vq = &vsock->vqs[i];
 
 		mutex_lock(&vq->mutex);
 
 		if (!vhost_vq_access_ok(vq)) {
 			ret = -EFAULT;
-			mutex_unlock(&vq->mutex);
 			goto err_vq;
 		}
 
 		if (!vq->private_data) {
 			vq->private_data = vsock;
-			vhost_vq_init_access(vq);
+			ret = vhost_vq_init_access(vq);
+			if (ret)
+				goto err_vq;
 		}
 
 		mutex_unlock(&vq->mutex);
@@ -405,8 +407,11 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 	return 0;
 
 err_vq:
+	vq->private_data = NULL;
+	mutex_unlock(&vq->mutex);
+
 	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
-		struct vhost_virtqueue *vq = &vsock->vqs[i];
+		vq = &vsock->vqs[i];
 
 		mutex_lock(&vq->mutex);
 		vq->private_data = NULL;
diff --git a/drivers/video/fbdev/core/fbcmap.c b/drivers/video/fbdev/core/fbcmap.c
index f89245b8ba8e..68a113594808 100644
--- a/drivers/video/fbdev/core/fbcmap.c
+++ b/drivers/video/fbdev/core/fbcmap.c
@@ -163,17 +163,18 @@ void fb_dealloc_cmap(struct fb_cmap *cmap)
 
 int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to)
 {
-	int tooff = 0, fromoff = 0;
-	int size;
+	unsigned int tooff = 0, fromoff = 0;
+	size_t size;
 
 	if (to->start > from->start)
 		fromoff = to->start - from->start;
 	else
 		tooff = from->start - to->start;
-	size = to->len - tooff;
-	if (size > (int) (from->len - fromoff))
-		size = from->len - fromoff;
-	if (size <= 0)
+	if (fromoff >= from->len || tooff >= to->len)
+		return -EINVAL;
+
+	size = min_t(size_t, to->len - tooff, from->len - fromoff);
+	if (size == 0)
 		return -EINVAL;
 	size *= sizeof(u16);
 
@@ -187,17 +188,18 @@ int fb_copy_cmap(const struct fb_cmap *from, struct fb_cmap *to)
 
 int fb_cmap_to_user(const struct fb_cmap *from, struct fb_cmap_user *to)
 {
-	int tooff = 0, fromoff = 0;
-	int size;
+	unsigned int tooff = 0, fromoff = 0;
+	size_t size;
 
 	if (to->start > from->start)
 		fromoff = to->start - from->start;
 	else
 		tooff = from->start - to->start;
-	size = to->len - tooff;
-	if (size > (int) (from->len - fromoff))
-		size = from->len - fromoff;
-	if (size <= 0)
+	if (fromoff >= from->len || tooff >= to->len)
+		return -EINVAL;
+
+	size = min_t(size_t, to->len - tooff, from->len - fromoff);
+	if (size == 0)
 		return -EINVAL;
 	size *= sizeof(u16);
 
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index d47a2fcef818..c71fde5fe835 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -59,6 +59,7 @@
 #define pr_fmt(fmt) "virtio-mmio: " fmt
 
 #include <linux/acpi.h>
+#include <linux/dma-mapping.h>
 #include <linux/highmem.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -498,6 +499,7 @@ static int virtio_mmio_probe(struct platform_device *pdev)
 	struct virtio_mmio_device *vm_dev;
 	struct resource *mem;
 	unsigned long magic;
+	int rc;
 
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!mem)
@@ -547,9 +549,25 @@ static int virtio_mmio_probe(struct platform_device *pdev)
 	}
 	vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID);
 
-	if (vm_dev->version == 1)
+	if (vm_dev->version == 1) {
 		writel(PAGE_SIZE, vm_dev->base + VIRTIO_MMIO_GUEST_PAGE_SIZE);
 
+		rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
+		/*
+		 * In the legacy case, ensure our coherently-allocated virtio
+		 * ring will be at an address expressable as a 32-bit PFN.
+		 */
+		if (!rc)
+			dma_set_coherent_mask(&pdev->dev,
+					      DMA_BIT_MASK(32 + PAGE_SHIFT));
+	} else {
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	}
+	if (rc)
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+	if (rc)
+		dev_warn(&pdev->dev, "Failed to enable 64-bit or 32-bit DMA.  Trying to continue, but this might not work.\n");
+
 	platform_set_drvdata(pdev, vm_dev);
 
 	return register_virtio_device(&vm_dev->vdev);
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index f905d6eeb048..f8afc6dcc29f 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -414,9 +414,9 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	if (map == SWIOTLB_MAP_ERROR)
 		return DMA_ERROR_CODE;
 
+	dev_addr = xen_phys_to_bus(map);
 	xen_dma_map_page(dev, pfn_to_page(map >> PAGE_SHIFT),
 					dev_addr, map & ~PAGE_MASK, size, dir, attrs);
-	dev_addr = xen_phys_to_bus(map);
 
 	/*
 	 * Ensure that the address returned is DMA'ble
@@ -575,13 +575,14 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 				sg_dma_len(sgl) = 0;
 				return 0;
 			}
+			dev_addr = xen_phys_to_bus(map);
 			xen_dma_map_page(hwdev, pfn_to_page(map >> PAGE_SHIFT),
 						dev_addr,
 						map & ~PAGE_MASK,
 						sg->length,
 						dir,
 						attrs);
-			sg->dma_address = xen_phys_to_bus(map);
+			sg->dma_address = dev_addr;
 		} else {
 			/* we are not interested in the dma_addr returned by
 			 * xen_dma_map_page, only in the potential cache flushes executed
diff --git a/fs/Kconfig b/fs/Kconfig
index c2a377cdda2b..83eab52fb3f6 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -38,6 +38,7 @@ config FS_DAX
 	bool "Direct Access (DAX) support"
 	depends on MMU
 	depends on !(ARM || MIPS || SPARC)
+	select FS_IOMAP
 	help
 	  Direct Access (DAX) can be used on memory-backed block devices.
 	  If the block device supports DAX and the filesystem supports DAX,
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 422370293cfd..e7bf01373bc4 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1428,17 +1428,18 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
 		 * group-wide total, not its individual thread total.
 		 */
 		thread_group_cputime(p, &cputime);
-		cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
-		cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(cputime.utime);
+		prstatus->pr_stime = ns_to_timeval(cputime.stime);
 	} else {
-		cputime_t utime, stime;
+		u64 utime, stime;
 
 		task_cputime(p, &utime, &stime);
-		cputime_to_timeval(utime, &prstatus->pr_utime);
-		cputime_to_timeval(stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(utime);
+		prstatus->pr_stime = ns_to_timeval(stime);
 	}
-	cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
-	cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
+
+	prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
+	prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);
 }
 
 static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index d2e36f82c35d..ffca4bbc3d63 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -1349,17 +1349,17 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
 		 * group-wide total, not its individual thread total.
 		 */
 		thread_group_cputime(p, &cputime);
-		cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
-		cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(cputime.utime);
+		prstatus->pr_stime = ns_to_timeval(cputime.stime);
 	} else {
-		cputime_t utime, stime;
+		u64 utime, stime;
 
 		task_cputime(p, &utime, &stime);
-		cputime_to_timeval(utime, &prstatus->pr_utime);
-		cputime_to_timeval(stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(utime);
+		prstatus->pr_stime = ns_to_timeval(stime);
 	}
-	cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
-	cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
+	prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
+	prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);
 
 	prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap;
 	prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 5db5d1340d69..73031ec54a7b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -331,7 +331,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	struct blk_plug plug;
 	struct blkdev_dio *dio;
 	struct bio *bio;
-	bool is_read = (iov_iter_rw(iter) == READ);
+	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
 	loff_t pos = iocb->ki_pos;
 	blk_qc_t qc = BLK_QC_T_NONE;
 	int ret;
@@ -344,7 +344,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	bio_get(bio); /* extra ref for the completion handler */
 
 	dio = container_of(bio, struct blkdev_dio, bio);
-	dio->is_sync = is_sync_kiocb(iocb);
+	dio->is_sync = is_sync = is_sync_kiocb(iocb);
 	if (dio->is_sync)
 		dio->waiter = current;
 	else
@@ -398,7 +398,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	}
 	blk_finish_plug(&plug);
 
-	if (!dio->is_sync)
+	if (!is_sync)
 		return -EIOCBQUEUED;
 
 	for (;;) {
@@ -884,6 +884,8 @@ static void bdev_evict_inode(struct inode *inode)
 	spin_lock(&bdev_lock);
 	list_del_init(&bdev->bd_list);
 	spin_unlock(&bdev_lock);
+	if (bdev->bd_bdi != &noop_backing_dev_info)
+		bdi_put(bdev->bd_bdi);
 }
 
 static const struct super_operations bdev_sops = {
@@ -954,6 +956,21 @@ static int bdev_set(struct inode *inode, void *data)
 
 static LIST_HEAD(all_bdevs);
 
+/*
+ * If there is a bdev inode for this device, unhash it so that it gets evicted
+ * as soon as last inode reference is dropped.
+ */
+void bdev_unhash_inode(dev_t dev)
+{
+	struct inode *inode;
+
+	inode = ilookup5(blockdev_superblock, hash(dev), bdev_test, &dev);
+	if (inode) {
+		remove_inode_hash(inode);
+		iput(inode);
+	}
+}
+
 struct block_device *bdget(dev_t dev)
 {
 	struct block_device *bdev;
@@ -971,6 +988,7 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
+		bdev->bd_bdi = &noop_backing_dev_info;
 		bdev->bd_block_size = (1 << inode->i_blkbits);
 		bdev->bd_part_count = 0;
 		bdev->bd_invalidated = 0;
@@ -1527,6 +1545,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
+		if (bdev->bd_bdi == &noop_backing_dev_info)
+			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
 
 		if (!partno) {
 			ret = -ENXIO;
@@ -1622,6 +1642,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
 	bdev->bd_queue = NULL;
+	bdi_put(bdev->bd_bdi);
+	bdev->bd_bdi = &noop_backing_dev_info;
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 7f390849343b..c4444d6f439f 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -1024,6 +1024,7 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 	unsigned long buf_offset;
 	unsigned long current_buf_start;
 	unsigned long start_byte;
+	unsigned long prev_start_byte;
 	unsigned long working_bytes = total_out - buf_start;
 	unsigned long bytes;
 	char *kaddr;
@@ -1071,26 +1072,34 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 		if (!bio->bi_iter.bi_size)
 			return 0;
 		bvec = bio_iter_iovec(bio, bio->bi_iter);
-
+		prev_start_byte = start_byte;
 		start_byte = page_offset(bvec.bv_page) - disk_start;
 
 		/*
-		 * make sure our new page is covered by this
-		 * working buffer
+		 * We need to make sure we're only adjusting
+		 * our offset into compression working buffer when
+		 * we're switching pages.  Otherwise we can incorrectly
+		 * keep copying when we were actually done.
 		 */
-		if (total_out <= start_byte)
-			return 1;
+		if (start_byte != prev_start_byte) {
+			/*
+			 * make sure our new page is covered by this
+			 * working buffer
+			 */
+			if (total_out <= start_byte)
+				return 1;
 
-		/*
-		 * the next page in the biovec might not be adjacent
-		 * to the last page, but it might still be found
-		 * inside this working buffer. bump our offset pointer
-		 */
-		if (total_out > start_byte &&
-		    current_buf_start < start_byte) {
-			buf_offset = start_byte - buf_start;
-			working_bytes = total_out - start_byte;
-			current_buf_start = buf_start + buf_offset;
+			/*
+			 * the next page in the biovec might not be adjacent
+			 * to the last page, but it might still be found
+			 * inside this working buffer. bump our offset pointer
+			 */
+			if (total_out > start_byte &&
+			    current_buf_start < start_byte) {
+				buf_offset = start_byte - buf_start;
+				working_bytes = total_out - start_byte;
+				current_buf_start = buf_start + buf_offset;
+			}
 		}
 	}
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 18004169552c..37a31b12bb0c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1800,7 +1800,7 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 	list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) {
 		if (!device->bdev)
 			continue;
-		bdi = blk_get_backing_dev_info(device->bdev);
+		bdi = device->bdev->bd_bdi;
 		if (bdi_congested(bdi, bdi_bits)) {
 			ret = 1;
 			break;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4e024260ad71..1e861a063721 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3835,10 +3835,7 @@ cache_acl:
 		break;
 	case S_IFDIR:
 		inode->i_fop = &btrfs_dir_file_operations;
-		if (root == fs_info->tree_root)
-			inode->i_op = &btrfs_dir_ro_inode_operations;
-		else
-			inode->i_op = &btrfs_dir_inode_operations;
+		inode->i_op = &btrfs_dir_inode_operations;
 		break;
 	case S_IFLNK:
 		inode->i_op = &btrfs_symlink_inode_operations;
@@ -4505,8 +4502,19 @@ search_again:
 		if (found_type > min_type) {
 			del_item = 1;
 		} else {
-			if (item_end < new_size)
+			if (item_end < new_size) {
+				/*
+				 * With NO_HOLES mode, for the following mapping
+				 *
+				 * [0-4k][hole][8k-12k]
+				 *
+				 * if truncating isize down to 6k, it ends up
+				 * isize being 8k.
+				 */
+				if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
+					last_size = new_size;
 				break;
+			}
 			if (found_key.offset >= new_size)
 				del_item = 1;
 			else
@@ -5710,6 +5718,7 @@ static struct inode *new_simple_dir(struct super_block *s,
 
 	inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID;
 	inode->i_op = &btrfs_dir_ro_inode_operations;
+	inode->i_opflags &= ~IOP_XATTR;
 	inode->i_fop = &simple_dir_operations;
 	inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
 	inode->i_mtime = current_time(inode);
@@ -7215,7 +7224,6 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
 	struct extent_map *em = NULL;
 	int ret;
 
-	down_read(&BTRFS_I(inode)->dio_sem);
 	if (type != BTRFS_ORDERED_NOCOW) {
 		em = create_pinned_em(inode, start, len, orig_start,
 				      block_start, block_len, orig_block_len,
@@ -7234,7 +7242,6 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
 		em = ERR_PTR(ret);
 	}
  out:
-	up_read(&BTRFS_I(inode)->dio_sem);
 
 	return em;
 }
@@ -8692,6 +8699,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		dio_data.unsubmitted_oe_range_start = (u64)offset;
 		dio_data.unsubmitted_oe_range_end = (u64)offset;
 		current->journal_info = &dio_data;
+		down_read(&BTRFS_I(inode)->dio_sem);
 	} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 				     &BTRFS_I(inode)->runtime_flags)) {
 		inode_dio_end(inode);
@@ -8704,6 +8712,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 				   iter, btrfs_get_blocks_direct, NULL,
 				   btrfs_submit_direct, flags);
 	if (iov_iter_rw(iter) == WRITE) {
+		up_read(&BTRFS_I(inode)->dio_sem);
 		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED) {
 			if (dio_data.reserve)
@@ -9212,6 +9221,7 @@ static int btrfs_truncate(struct inode *inode)
 			break;
 		}
 
+		btrfs_block_rsv_release(fs_info, rsv, -1);
 		ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv,
 					      rsv, min_size, 0);
 		BUG_ON(ret);	/* shouldn't happen */
@@ -10579,8 +10589,6 @@ static const struct inode_operations btrfs_dir_inode_operations = {
 static const struct inode_operations btrfs_dir_ro_inode_operations = {
 	.lookup		= btrfs_lookup,
 	.permission	= btrfs_permission,
-	.get_acl	= btrfs_get_acl,
-	.set_acl	= btrfs_set_acl,
 	.update_time	= btrfs_update_time,
 };
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 33f967d30b2a..21e51b0ba188 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5653,6 +5653,10 @@ long btrfs_ioctl(struct file *file, unsigned int
 #ifdef CONFIG_COMPAT
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
+	/*
+	 * These all access 32-bit values anyway so no further
+	 * handling is necessary.
+	 */
 	switch (cmd) {
 	case FS_IOC32_GETFLAGS:
 		cmd = FS_IOC_GETFLAGS;
@@ -5663,8 +5667,6 @@ long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case FS_IOC32_GETVERSION:
 		cmd = FS_IOC_GETVERSION;
 		break;
-	default:
-		return -ENOIOCTLCMD;
 	}
 
 	return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 3c3c69c0eee4..b2e70073a10d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -366,7 +366,7 @@ static noinline void run_scheduled_bios(struct btrfs_device *device)
 	 */
 	blk_start_plug(&plug);
 
-	bdi = blk_get_backing_dev_info(device->bdev);
+	bdi = device->bdev->bd_bdi;
 	limit = btrfs_async_submit_limit(fs_info);
 	limit = limit * 2 / 3;
 
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index e7b478b49985..034f00f21390 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -9,8 +9,6 @@ config CIFS
 	select CRYPTO_ARC4
 	select CRYPTO_ECB
 	select CRYPTO_DES
-	select CRYPTO_SHA256
-	select CRYPTO_CMAC
 	help
 	  This is the client VFS module for the Common Internet File System
 	  (CIFS) protocol which is the successor to the Server Message Block
@@ -169,11 +167,15 @@ config CIFS_NFSD_EXPORT
 
 config CIFS_SMB2
 	bool "SMB2 and SMB3 network file system support"
-	depends on CIFS && INET
-	select NLS
+	depends on CIFS
 	select KEYS
 	select FSCACHE
 	select DNS_RESOLVER
+	select CRYPTO_AES
+	select CRYPTO_SHA256
+	select CRYPTO_CMAC
+	select CRYPTO_AEAD2
+	select CRYPTO_CCM
 
 	help
 	  This enables support for the Server Message Block version 2
@@ -194,7 +196,7 @@ config CIFS_SMB2
 
 config CIFS_SMB311
 	bool "SMB3.1.1 network file system support (Experimental)"
-	depends on CIFS_SMB2 && INET
+	depends on CIFS_SMB2
 
 	help
 	  This enables experimental support for the newest, SMB3.1.1, dialect.
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 66bd7fa9b7a6..058ac9b36f04 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -34,6 +34,7 @@
 #include <linux/random.h>
 #include <linux/highmem.h>
 #include <crypto/skcipher.h>
+#include <crypto/aead.h>
 
 static int
 cifs_crypto_shash_md5_allocate(struct TCP_Server_Info *server)
@@ -75,24 +76,20 @@ int __cifs_calc_signature(struct smb_rqst *rqst,
 	struct kvec *iov = rqst->rq_iov;
 	int n_vec = rqst->rq_nvec;
 
-	for (i = 0; i < n_vec; i++) {
+	if (n_vec < 2 || iov[0].iov_len != 4)
+		return -EIO;
+
+	for (i = 1; i < n_vec; i++) {
 		if (iov[i].iov_len == 0)
 			continue;
 		if (iov[i].iov_base == NULL) {
 			cifs_dbg(VFS, "null iovec entry\n");
 			return -EIO;
 		}
-		/* The first entry includes a length field (which does not get
-		   signed that occupies the first 4 bytes before the header */
-		if (i == 0) {
-			if (iov[0].iov_len <= 8) /* cmd field at offset 9 */
-				break; /* nothing to sign or corrupt header */
-			rc = crypto_shash_update(shash,
-				iov[i].iov_base + 4, iov[i].iov_len - 4);
-		} else {
-			rc = crypto_shash_update(shash,
-				iov[i].iov_base, iov[i].iov_len);
-		}
+		if (i == 1 && iov[1].iov_len <= 4)
+			break; /* nothing to sign or corrupt header */
+		rc = crypto_shash_update(shash,
+					 iov[i].iov_base, iov[i].iov_len);
 		if (rc) {
 			cifs_dbg(VFS, "%s: Could not update with payload\n",
 				 __func__);
@@ -168,6 +165,10 @@ int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server,
 	char smb_signature[20];
 	struct smb_hdr *cifs_pdu = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
 
+	if (rqst->rq_iov[0].iov_len != 4 ||
+	    rqst->rq_iov[0].iov_base + 4 != rqst->rq_iov[1].iov_base)
+		return -EIO;
+
 	if ((cifs_pdu == NULL) || (server == NULL))
 		return -EINVAL;
 
@@ -209,12 +210,14 @@ int cifs_sign_smbv(struct kvec *iov, int n_vec, struct TCP_Server_Info *server,
 int cifs_sign_smb(struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server,
 		  __u32 *pexpected_response_sequence_number)
 {
-	struct kvec iov;
+	struct kvec iov[2];
 
-	iov.iov_base = cifs_pdu;
-	iov.iov_len = be32_to_cpu(cifs_pdu->smb_buf_length) + 4;
+	iov[0].iov_base = cifs_pdu;
+	iov[0].iov_len = 4;
+	iov[1].iov_base = (char *)cifs_pdu + 4;
+	iov[1].iov_len = be32_to_cpu(cifs_pdu->smb_buf_length);
 
-	return cifs_sign_smbv(&iov, 1, server,
+	return cifs_sign_smbv(iov, 2, server,
 			      pexpected_response_sequence_number);
 }
 
@@ -227,6 +230,10 @@ int cifs_verify_signature(struct smb_rqst *rqst,
 	char what_we_think_sig_should_be[20];
 	struct smb_hdr *cifs_pdu = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
 
+	if (rqst->rq_iov[0].iov_len != 4 ||
+	    rqst->rq_iov[0].iov_base + 4 != rqst->rq_iov[1].iov_base)
+		return -EIO;
+
 	if (cifs_pdu == NULL || server == NULL)
 		return -EINVAL;
 
@@ -868,7 +875,7 @@ out:
 }
 
 void
-cifs_crypto_shash_release(struct TCP_Server_Info *server)
+cifs_crypto_secmech_release(struct TCP_Server_Info *server)
 {
 	if (server->secmech.cmacaes) {
 		crypto_free_shash(server->secmech.cmacaes);
@@ -890,6 +897,16 @@ cifs_crypto_shash_release(struct TCP_Server_Info *server)
 		server->secmech.hmacmd5 = NULL;
 	}
 
+	if (server->secmech.ccmaesencrypt) {
+		crypto_free_aead(server->secmech.ccmaesencrypt);
+		server->secmech.ccmaesencrypt = NULL;
+	}
+
+	if (server->secmech.ccmaesdecrypt) {
+		crypto_free_aead(server->secmech.ccmaesdecrypt);
+		server->secmech.ccmaesdecrypt = NULL;
+	}
+
 	kfree(server->secmech.sdesccmacaes);
 	server->secmech.sdesccmacaes = NULL;
 	kfree(server->secmech.sdeschmacsha256);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 70f4e65fced2..15e1db8738ae 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -1365,5 +1365,19 @@ MODULE_DESCRIPTION
     ("VFS to access servers complying with the SNIA CIFS Specification "
      "e.g. Samba and Windows");
 MODULE_VERSION(CIFS_VERSION);
+MODULE_SOFTDEP("pre: arc4");
+MODULE_SOFTDEP("pre: des");
+MODULE_SOFTDEP("pre: ecb");
+MODULE_SOFTDEP("pre: hmac");
+MODULE_SOFTDEP("pre: md4");
+MODULE_SOFTDEP("pre: md5");
+MODULE_SOFTDEP("pre: nls");
+#ifdef CONFIG_CIFS_SMB2
+MODULE_SOFTDEP("pre: aes");
+MODULE_SOFTDEP("pre: cmac");
+MODULE_SOFTDEP("pre: sha256");
+MODULE_SOFTDEP("pre: aead2");
+MODULE_SOFTDEP("pre: ccm");
+#endif /* CONFIG_CIFS_SMB2 */
 module_init(init_cifs)
 module_exit(exit_cifs)
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 7ea8a3393936..1a90bb3e2986 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -136,6 +136,8 @@ struct cifs_secmech {
 	struct sdesc *sdescmd5; /* ctxt to generate cifs/smb signature */
 	struct sdesc *sdeschmacsha256;  /* ctxt to generate smb2 signature */
 	struct sdesc *sdesccmacaes;  /* ctxt to generate smb3 signature */
+	struct crypto_aead *ccmaesencrypt; /* smb3 encryption aead */
+	struct crypto_aead *ccmaesdecrypt; /* smb3 decryption aead */
 };
 
 /* per smb session structure/fields */
@@ -208,7 +210,7 @@ struct cifsInodeInfo;
 struct cifs_open_parms;
 
 struct smb_version_operations {
-	int (*send_cancel)(struct TCP_Server_Info *, void *,
+	int (*send_cancel)(struct TCP_Server_Info *, struct smb_rqst *,
 			   struct mid_q_entry *);
 	bool (*compare_fids)(struct cifsFileInfo *, struct cifsFileInfo *);
 	/* setup request: allocate mid, sign message */
@@ -433,6 +435,14 @@ struct smb_version_operations {
 	bool (*dir_needs_close)(struct cifsFileInfo *);
 	long (*fallocate)(struct file *, struct cifs_tcon *, int, loff_t,
 			  loff_t);
+	/* init transform request - used for encryption for now */
+	int (*init_transform_rq)(struct TCP_Server_Info *, struct smb_rqst *,
+				 struct smb_rqst *);
+	/* free transform request */
+	void (*free_transform_rq)(struct smb_rqst *);
+	int (*is_transform_hdr)(void *buf);
+	int (*receive_transform)(struct TCP_Server_Info *,
+				 struct mid_q_entry **);
 };
 
 struct smb_version_values {
@@ -1119,7 +1129,10 @@ struct cifs_readdata {
 	int (*read_into_pages)(struct TCP_Server_Info *server,
 				struct cifs_readdata *rdata,
 				unsigned int len);
-	struct kvec			iov;
+	int (*copy_into_pages)(struct TCP_Server_Info *server,
+				struct cifs_readdata *rdata,
+				struct iov_iter *iter);
+	struct kvec			iov[2];
 	unsigned int			pagesz;
 	unsigned int			tailsz;
 	unsigned int			credits;
@@ -1302,6 +1315,13 @@ typedef int (mid_receive_t)(struct TCP_Server_Info *server,
  */
 typedef void (mid_callback_t)(struct mid_q_entry *mid);
 
+/*
+ * This is the protopyte for mid handle function. This is called once the mid
+ * has been recognized after decryption of the message.
+ */
+typedef int (mid_handle_t)(struct TCP_Server_Info *server,
+			    struct mid_q_entry *mid);
+
 /* one of these for every pending CIFS request to the server */
 struct mid_q_entry {
 	struct list_head qhead;	/* mids waiting on reply from this server */
@@ -1316,6 +1336,7 @@ struct mid_q_entry {
 #endif
 	mid_receive_t *receive; /* call receive callback */
 	mid_callback_t *callback; /* call completion callback */
+	mid_handle_t *handle; /* call handle mid callback */
 	void *callback_data;	  /* general purpose pointer for callback */
 	void *resp_buf;		/* pointer to received SMB header */
 	int mid_state;	/* wish this were enum but can not pass to wait_event */
@@ -1323,6 +1344,7 @@ struct mid_q_entry {
 	bool large_buf:1;	/* if valid response, is pointer to large buf */
 	bool multiRsp:1;	/* multiple trans2 responses for one request  */
 	bool multiEnd:1;	/* both received */
+	bool decrypted:1;	/* decrypted entry */
 };
 
 /*	Make code in transport.c a little cleaner by moving
@@ -1475,7 +1497,9 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
 #define   CIFS_OBREAK_OP   0x0100    /* oplock break request */
 #define   CIFS_NEG_OP      0x0200    /* negotiate request */
 #define   CIFS_OP_MASK     0x0380    /* mask request type */
+
 #define   CIFS_HAS_CREDITS 0x0400    /* already has credits */
+#define   CIFS_TRANSFORM_REQ 0x0800    /* transform request before sending */
 
 /* Security Flags: indicate type of session setup needed */
 #define   CIFSSEC_MAY_SIGN	0x00001
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index c7b3c841e660..406d2c10ba78 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -75,10 +75,16 @@ extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer,
 extern void DeleteMidQEntry(struct mid_q_entry *midEntry);
 extern void cifs_delete_mid(struct mid_q_entry *mid);
 extern void cifs_wake_up_task(struct mid_q_entry *mid);
+extern int cifs_handle_standard(struct TCP_Server_Info *server,
+				struct mid_q_entry *mid);
+extern int cifs_discard_remaining_data(struct TCP_Server_Info *server);
 extern int cifs_call_async(struct TCP_Server_Info *server,
 			struct smb_rqst *rqst,
 			mid_receive_t *receive, mid_callback_t *callback,
-			void *cbdata, const int flags);
+			mid_handle_t *handle, void *cbdata, const int flags);
+extern int cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
+			  struct smb_rqst *rqst, int *resp_buf_type,
+			  const int flags, struct kvec *resp_iov);
 extern int SendReceive(const unsigned int /* xid */ , struct cifs_ses *,
 			struct smb_hdr * /* input */ ,
 			struct smb_hdr * /* out */ ,
@@ -96,7 +102,8 @@ extern int cifs_wait_mtu_credits(struct TCP_Server_Info *server,
 				 unsigned int *credits);
 extern int SendReceive2(const unsigned int /* xid */ , struct cifs_ses *,
 			struct kvec *, int /* nvec to send */,
-			int * /* type of buf returned */ , const int flags);
+			int * /* type of buf returned */, const int flags,
+			struct kvec * /* resp vec */);
 extern int SendReceiveBlockingLock(const unsigned int xid,
 			struct cifs_tcon *ptcon,
 			struct smb_hdr *in_buf ,
@@ -441,7 +448,7 @@ extern int SMBNTencrypt(unsigned char *, unsigned char *, unsigned char *,
 			const struct nls_table *);
 extern int setup_ntlm_response(struct cifs_ses *, const struct nls_table *);
 extern int setup_ntlmv2_rsp(struct cifs_ses *, const struct nls_table *);
-extern void cifs_crypto_shash_release(struct TCP_Server_Info *);
+extern void cifs_crypto_secmech_release(struct TCP_Server_Info *server);
 extern int calc_seckey(struct cifs_ses *);
 extern int generate_smb30signingkey(struct cifs_ses *);
 extern int generate_smb311signingkey(struct cifs_ses *);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index b47261858e6d..f5099fb8a22f 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -673,6 +673,7 @@ CIFSSMBTDis(const unsigned int xid, struct cifs_tcon *tcon)
 		return rc;
 
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *)smb_buffer, 0);
+	cifs_small_buf_release(smb_buffer);
 	if (rc)
 		cifs_dbg(FYI, "Tree disconnect failed %d\n", rc);
 
@@ -707,9 +708,9 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
 {
 	ECHO_REQ *smb;
 	int rc = 0;
-	struct kvec iov;
-	struct smb_rqst rqst = { .rq_iov = &iov,
-				 .rq_nvec = 1 };
+	struct kvec iov[2];
+	struct smb_rqst rqst = { .rq_iov = iov,
+				 .rq_nvec = 2 };
 
 	cifs_dbg(FYI, "In echo request\n");
 
@@ -724,10 +725,13 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
 	put_bcc(1, &smb->hdr);
 	smb->Data[0] = 'a';
 	inc_rfc1001_len(smb, 3);
-	iov.iov_base = smb;
-	iov.iov_len = be32_to_cpu(smb->hdr.smb_buf_length) + 4;
 
-	rc = cifs_call_async(server, &rqst, NULL, cifs_echo_callback,
+	iov[0].iov_len = 4;
+	iov[0].iov_base = smb;
+	iov[1].iov_len = get_rfc1002_length(smb);
+	iov[1].iov_base = (char *)smb + 4;
+
+	rc = cifs_call_async(server, &rqst, NULL, cifs_echo_callback, NULL,
 			     server, CIFS_ASYNC_OP | CIFS_ECHO_OP);
 	if (rc)
 		cifs_dbg(FYI, "Echo request failed: %d\n", rc);
@@ -772,6 +776,7 @@ CIFSSMBLogoff(const unsigned int xid, struct cifs_ses *ses)
 
 	pSMB->AndXCommand = 0xFF;
 	rc = SendReceiveNoRsp(xid, ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 session_already_dead:
 	mutex_unlock(&ses->session_mutex);
 
@@ -1394,8 +1399,8 @@ openRetry:
  * Discard any remaining data in the current SMB. To do this, we borrow the
  * current bigbuf.
  */
-static int
-discard_remaining_data(struct TCP_Server_Info *server)
+int
+cifs_discard_remaining_data(struct TCP_Server_Info *server)
 {
 	unsigned int rfclen = get_rfc1002_length(server->smallbuf);
 	int remaining = rfclen + 4 - server->total_read;
@@ -1421,7 +1426,7 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	int length;
 	struct cifs_readdata *rdata = mid->callback_data;
 
-	length = discard_remaining_data(server);
+	length = cifs_discard_remaining_data(server);
 	dequeue_mid(mid, rdata->result);
 	return length;
 }
@@ -1454,7 +1459,7 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 
 	if (server->ops->is_status_pending &&
 	    server->ops->is_status_pending(buf, server, 0)) {
-		discard_remaining_data(server);
+		cifs_discard_remaining_data(server);
 		return -1;
 	}
 
@@ -1507,10 +1512,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	}
 
 	/* set up first iov for signature check */
-	rdata->iov.iov_base = buf;
-	rdata->iov.iov_len = server->total_read;
-	cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n",
-		 rdata->iov.iov_base, rdata->iov.iov_len);
+	rdata->iov[0].iov_base = buf;
+	rdata->iov[0].iov_len = 4;
+	rdata->iov[1].iov_base = buf + 4;
+	rdata->iov[1].iov_len = server->total_read - 4;
+	cifs_dbg(FYI, "0: iov_base=%p iov_len=%u\n",
+		 rdata->iov[0].iov_base, server->total_read);
 
 	/* how much data is in the response? */
 	data_len = server->ops->read_data_length(buf);
@@ -1543,8 +1550,8 @@ cifs_readv_callback(struct mid_q_entry *mid)
 	struct cifs_readdata *rdata = mid->callback_data;
 	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
-	struct smb_rqst rqst = { .rq_iov = &rdata->iov,
-				 .rq_nvec = 1,
+	struct smb_rqst rqst = { .rq_iov = rdata->iov,
+				 .rq_nvec = 2,
 				 .rq_pages = rdata->pages,
 				 .rq_npages = rdata->nr_pages,
 				 .rq_pagesz = rdata->pagesz,
@@ -1599,8 +1606,8 @@ cifs_async_readv(struct cifs_readdata *rdata)
 	READ_REQ *smb = NULL;
 	int wct;
 	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
-	struct smb_rqst rqst = { .rq_iov = &rdata->iov,
-				 .rq_nvec = 1 };
+	struct smb_rqst rqst = { .rq_iov = rdata->iov,
+				 .rq_nvec = 2 };
 
 	cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n",
 		 __func__, rdata->offset, rdata->bytes);
@@ -1640,12 +1647,14 @@ cifs_async_readv(struct cifs_readdata *rdata)
 	}
 
 	/* 4 for RFC1001 length + 1 for BCC */
-	rdata->iov.iov_base = smb;
-	rdata->iov.iov_len = be32_to_cpu(smb->hdr.smb_buf_length) + 4;
+	rdata->iov[0].iov_base = smb;
+	rdata->iov[0].iov_len = 4;
+	rdata->iov[1].iov_base = (char *)smb + 4;
+	rdata->iov[1].iov_len = get_rfc1002_length(smb);
 
 	kref_get(&rdata->refcount);
 	rc = cifs_call_async(tcon->ses->server, &rqst, cifs_readv_receive,
-			     cifs_readv_callback, rdata, 0);
+			     cifs_readv_callback, NULL, rdata, 0);
 
 	if (rc == 0)
 		cifs_stats_inc(&tcon->stats.cifs_stats.num_reads);
@@ -1667,6 +1676,7 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms,
 	int wct;
 	int resp_buf_type = 0;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 	__u32 pid = io_parms->pid;
 	__u16 netfid = io_parms->netfid;
 	__u64 offset = io_parms->offset;
@@ -1716,10 +1726,11 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms,
 
 	iov[0].iov_base = (char *)pSMB;
 	iov[0].iov_len = be32_to_cpu(pSMB->hdr.smb_buf_length) + 4;
-	rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovecs */,
-			 &resp_buf_type, CIFS_LOG_ERROR);
+	rc = SendReceive2(xid, tcon->ses, iov, 1, &resp_buf_type,
+			  CIFS_LOG_ERROR, &rsp_iov);
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_reads);
-	pSMBr = (READ_RSP *)iov[0].iov_base;
+	pSMBr = (READ_RSP *)rsp_iov.iov_base;
 	if (rc) {
 		cifs_dbg(VFS, "Send error in read = %d\n", rc);
 	} else {
@@ -1747,12 +1758,11 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms,
 		}
 	}
 
-/*	cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */
 	if (*buf) {
-		free_rsp_buf(resp_buf_type, iov[0].iov_base);
+		free_rsp_buf(resp_buf_type, rsp_iov.iov_base);
 	} else if (resp_buf_type != CIFS_NO_BUFFER) {
 		/* return buffer to caller to free */
-		*buf = iov[0].iov_base;
+		*buf = rsp_iov.iov_base;
 		if (resp_buf_type == CIFS_SMALL_BUFFER)
 			*pbuf_type = CIFS_SMALL_BUFFER;
 		else if (resp_buf_type == CIFS_LARGE_BUFFER)
@@ -2093,7 +2103,7 @@ cifs_async_writev(struct cifs_writedata *wdata,
 	WRITE_REQ *smb = NULL;
 	int wct;
 	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
-	struct kvec iov;
+	struct kvec iov[2];
 	struct smb_rqst rqst = { };
 
 	if (tcon->ses->capabilities & CAP_LARGE_FILES) {
@@ -2126,11 +2136,13 @@ cifs_async_writev(struct cifs_writedata *wdata,
 	    cpu_to_le16(offsetof(struct smb_com_write_req, Data) - 4);
 
 	/* 4 for RFC1001 length + 1 for BCC */
-	iov.iov_len = be32_to_cpu(smb->hdr.smb_buf_length) + 4 + 1;
-	iov.iov_base = smb;
+	iov[0].iov_len = 4;
+	iov[0].iov_base = smb;
+	iov[1].iov_len = get_rfc1002_length(smb) + 1;
+	iov[1].iov_base = (char *)smb + 4;
 
-	rqst.rq_iov = &iov;
-	rqst.rq_nvec = 1;
+	rqst.rq_iov = iov;
+	rqst.rq_nvec = 2;
 	rqst.rq_pages = wdata->pages;
 	rqst.rq_npages = wdata->nr_pages;
 	rqst.rq_pagesz = wdata->pagesz;
@@ -2151,12 +2163,12 @@ cifs_async_writev(struct cifs_writedata *wdata,
 				(struct smb_com_writex_req *)smb;
 		inc_rfc1001_len(&smbw->hdr, wdata->bytes + 5);
 		put_bcc(wdata->bytes + 5, &smbw->hdr);
-		iov.iov_len += 4; /* pad bigger by four bytes */
+		iov[1].iov_len += 4; /* pad bigger by four bytes */
 	}
 
 	kref_get(&wdata->refcount);
 	rc = cifs_call_async(tcon->ses->server, &rqst, NULL,
-				cifs_writev_callback, wdata, 0);
+				cifs_writev_callback, NULL, wdata, 0);
 
 	if (rc == 0)
 		cifs_stats_inc(&tcon->stats.cifs_stats.num_writes);
@@ -2182,6 +2194,7 @@ CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms,
 	__u64 offset = io_parms->offset;
 	struct cifs_tcon *tcon = io_parms->tcon;
 	unsigned int count = io_parms->length;
+	struct kvec rsp_iov;
 
 	*nbytes = 0;
 
@@ -2240,8 +2253,9 @@ CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms,
 	else /* wct == 12 pad bigger by four bytes */
 		iov[0].iov_len = smb_hdr_len + 8;
 
-
-	rc = SendReceive2(xid, tcon->ses, iov, n_vec + 1, &resp_buf_type, 0);
+	rc = SendReceive2(xid, tcon->ses, iov, n_vec + 1, &resp_buf_type, 0,
+			  &rsp_iov);
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_writes);
 	if (rc) {
 		cifs_dbg(FYI, "Send error Write2 = %d\n", rc);
@@ -2249,7 +2263,7 @@ CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms,
 		/* presumably this can not happen, but best to be safe */
 		rc = -EIO;
 	} else {
-		WRITE_RSP *pSMBr = (WRITE_RSP *)iov[0].iov_base;
+		WRITE_RSP *pSMBr = (WRITE_RSP *)rsp_iov.iov_base;
 		*nbytes = le16_to_cpu(pSMBr->CountHigh);
 		*nbytes = (*nbytes) << 16;
 		*nbytes += le16_to_cpu(pSMBr->Count);
@@ -2263,8 +2277,7 @@ CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms,
 			*nbytes &= 0xFFFF;
 	}
 
-/*	cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */
-	free_rsp_buf(resp_buf_type, iov[0].iov_base);
+	free_rsp_buf(resp_buf_type, rsp_iov.iov_base);
 
 	/* Note: On -EAGAIN error only caller can retry on handle based calls
 		since file handle passed in no longer valid */
@@ -2279,6 +2292,7 @@ int cifs_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	LOCK_REQ *pSMB = NULL;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int resp_buf_type;
 	__u16 count;
 
@@ -2307,7 +2321,9 @@ int cifs_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	iov[1].iov_len = (num_unlock + num_lock) * sizeof(LOCKING_ANDX_RANGE);
 
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_locks);
-	rc = SendReceive2(xid, tcon->ses, iov, 2, &resp_buf_type, CIFS_NO_RESP);
+	rc = SendReceive2(xid, tcon->ses, iov, 2, &resp_buf_type, CIFS_NO_RESP,
+			  &rsp_iov);
+	cifs_small_buf_release(pSMB);
 	if (rc)
 		cifs_dbg(FYI, "Send error in cifs_lockv = %d\n", rc);
 
@@ -2368,14 +2384,12 @@ CIFSSMBLock(const unsigned int xid, struct cifs_tcon *tcon,
 	inc_rfc1001_len(pSMB, count);
 	pSMB->ByteCount = cpu_to_le16(count);
 
-	if (waitFlag) {
+	if (waitFlag)
 		rc = SendReceiveBlockingLock(xid, tcon, (struct smb_hdr *) pSMB,
 			(struct smb_hdr *) pSMB, &bytes_returned);
-		cifs_small_buf_release(pSMB);
-	} else {
+	else
 		rc = SendReceiveNoRsp(xid, tcon->ses, (char *)pSMB, flags);
-		/* SMB buffer freed by function above */
-	}
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_locks);
 	if (rc)
 		cifs_dbg(FYI, "Send error in Lock = %d\n", rc);
@@ -2401,6 +2415,7 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 	int resp_buf_type = 0;
 	__u16 params, param_offset, offset, byte_count, count;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 
 	cifs_dbg(FYI, "Posix Lock\n");
 
@@ -2462,11 +2477,10 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 		iov[0].iov_base = (char *)pSMB;
 		iov[0].iov_len = be32_to_cpu(pSMB->hdr.smb_buf_length) + 4;
 		rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovecs */,
-				&resp_buf_type, timeout);
-		pSMB = NULL; /* request buf already freed by SendReceive2. Do
-				not try to free it twice below on exit */
-		pSMBr = (struct smb_com_transaction2_sfi_rsp *)iov[0].iov_base;
+				&resp_buf_type, timeout, &rsp_iov);
+		pSMBr = (struct smb_com_transaction2_sfi_rsp *)rsp_iov.iov_base;
 	}
+	cifs_small_buf_release(pSMB);
 
 	if (rc) {
 		cifs_dbg(FYI, "Send error in Posix Lock = %d\n", rc);
@@ -2506,10 +2520,7 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 	}
 
 plk_err_exit:
-	if (pSMB)
-		cifs_small_buf_release(pSMB);
-
-	free_rsp_buf(resp_buf_type, iov[0].iov_base);
+	free_rsp_buf(resp_buf_type, rsp_iov.iov_base);
 
 	/* Note: On -EAGAIN error only caller can retry on handle based calls
 	   since file handle passed in no longer valid */
@@ -2536,6 +2547,7 @@ CIFSSMBClose(const unsigned int xid, struct cifs_tcon *tcon, int smb_file_id)
 	pSMB->LastWriteTime = 0xFFFFFFFF;
 	pSMB->ByteCount = 0;
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_closes);
 	if (rc) {
 		if (rc != -EINTR) {
@@ -2565,6 +2577,7 @@ CIFSSMBFlush(const unsigned int xid, struct cifs_tcon *tcon, int smb_file_id)
 	pSMB->FileID = (__u16) smb_file_id;
 	pSMB->ByteCount = 0;
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_flushes);
 	if (rc)
 		cifs_dbg(VFS, "Send error in Flush = %d\n", rc);
@@ -3820,6 +3833,7 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid,
 	int buf_type = 0;
 	QUERY_SEC_DESC_REQ *pSMB;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 
 	cifs_dbg(FYI, "GetCifsACL\n");
 
@@ -3843,7 +3857,8 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid,
 	iov[0].iov_len = be32_to_cpu(pSMB->hdr.smb_buf_length) + 4;
 
 	rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovec */, &buf_type,
-			 0);
+			  0, &rsp_iov);
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_acl_get);
 	if (rc) {
 		cifs_dbg(FYI, "Send error in QuerySecDesc = %d\n", rc);
@@ -3855,11 +3870,11 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid,
 		char *pdata;
 
 /* validate_nttransact */
-		rc = validate_ntransact(iov[0].iov_base, (char **)&parm,
+		rc = validate_ntransact(rsp_iov.iov_base, (char **)&parm,
 					&pdata, &parm_len, pbuflen);
 		if (rc)
 			goto qsec_out;
-		pSMBr = (struct smb_com_ntransact_rsp *)iov[0].iov_base;
+		pSMBr = (struct smb_com_ntransact_rsp *)rsp_iov.iov_base;
 
 		cifs_dbg(FYI, "smb %p parm %p data %p\n",
 			 pSMBr, parm, *acl_inf);
@@ -3896,8 +3911,7 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid,
 		}
 	}
 qsec_out:
-	free_rsp_buf(buf_type, iov[0].iov_base);
-/*	cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */
+	free_rsp_buf(buf_type, rsp_iov.iov_base);
 	return rc;
 }
 
@@ -4666,6 +4680,7 @@ CIFSFindClose(const unsigned int xid, struct cifs_tcon *tcon,
 	pSMB->FileID = searchHandle;
 	pSMB->ByteCount = 0;
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	if (rc)
 		cifs_dbg(VFS, "Send error in FindClose = %d\n", rc);
 
@@ -5687,6 +5702,7 @@ CIFSSMBSetFileSize(const unsigned int xid, struct cifs_tcon *tcon,
 	inc_rfc1001_len(pSMB, byte_count);
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	if (rc) {
 		cifs_dbg(FYI, "Send error in SetFileInfo (SetFileSize) = %d\n",
 			 rc);
@@ -5758,6 +5774,7 @@ CIFSSMBSetFileInfo(const unsigned int xid, struct cifs_tcon *tcon,
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 	memcpy(data_offset, data, sizeof(FILE_BASIC_INFO));
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	if (rc)
 		cifs_dbg(FYI, "Send error in Set Time (SetFileInfo) = %d\n",
 			 rc);
@@ -5818,6 +5835,7 @@ CIFSSMBSetFileDisposition(const unsigned int xid, struct cifs_tcon *tcon,
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 	*data_offset = delete_file ? 1 : 0;
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	if (rc)
 		cifs_dbg(FYI, "Send error in SetFileDisposition = %d\n", rc);
 
@@ -6057,6 +6075,7 @@ CIFSSMBUnixSetFileInfo(const unsigned int xid, struct cifs_tcon *tcon,
 	cifs_fill_unix_set_info((FILE_UNIX_BASIC_INFO *)data_offset, args);
 
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	if (rc)
 		cifs_dbg(FYI, "Send error in Set Time (SetFileInfo) = %d\n",
 			 rc);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 35ae49ed1f76..777ad9f4fc3c 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -787,6 +787,15 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 
 	dump_smb(buf, server->total_read);
 
+	return cifs_handle_standard(server, mid);
+}
+
+int
+cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+{
+	char *buf = server->large_buf ? server->bigbuf : server->smallbuf;
+	int length;
+
 	/*
 	 * We know that we received enough to get to the MID as we
 	 * checked the pdu_length earlier. Now check to see
@@ -872,12 +881,19 @@ cifs_demultiplex_thread(void *p)
 			continue;
 		server->total_read += length;
 
-		mid_entry = server->ops->find_mid(server, buf);
+		if (server->ops->is_transform_hdr &&
+		    server->ops->receive_transform &&
+		    server->ops->is_transform_hdr(buf)) {
+			length = server->ops->receive_transform(server,
+								&mid_entry);
+		} else {
+			mid_entry = server->ops->find_mid(server, buf);
 
-		if (!mid_entry || !mid_entry->receive)
-			length = standard_receive3(server, mid_entry);
-		else
-			length = mid_entry->receive(server, mid_entry);
+			if (!mid_entry || !mid_entry->receive)
+				length = standard_receive3(server, mid_entry);
+			else
+				length = mid_entry->receive(server, mid_entry);
+		}
 
 		if (length < 0)
 			continue;
@@ -2154,7 +2170,7 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 	server->tcpStatus = CifsExiting;
 	spin_unlock(&GlobalMid_Lock);
 
-	cifs_crypto_shash_release(server);
+	cifs_crypto_secmech_release(server);
 	cifs_fscache_release_client_cookie(server);
 
 	kfree(server->session_key.response);
@@ -2273,7 +2289,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 	return tcp_ses;
 
 out_err_crypto_release:
-	cifs_crypto_shash_release(tcp_ses);
+	cifs_crypto_secmech_release(tcp_ses);
 
 	put_net(cifs_net_ns(tcp_ses));
 
@@ -2614,12 +2630,18 @@ get_ses_fail:
 	return ERR_PTR(rc);
 }
 
-static int match_tcon(struct cifs_tcon *tcon, const char *unc)
+static int match_tcon(struct cifs_tcon *tcon, struct smb_vol *volume_info)
 {
 	if (tcon->tidStatus == CifsExiting)
 		return 0;
-	if (strncmp(tcon->treeName, unc, MAX_TREE_SIZE))
+	if (strncmp(tcon->treeName, volume_info->UNC, MAX_TREE_SIZE))
 		return 0;
+	if (tcon->seal != volume_info->seal)
+		return 0;
+#ifdef CONFIG_CIFS_SMB2
+	if (tcon->snapshot_time != volume_info->snapshot_time)
+		return 0;
+#endif /* CONFIG_CIFS_SMB2 */
 	return 1;
 }
 
@@ -2632,14 +2654,8 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each(tmp, &ses->tcon_list) {
 		tcon = list_entry(tmp, struct cifs_tcon, tcon_list);
-		if (!match_tcon(tcon, volume_info->UNC))
-			continue;
-
-#ifdef CONFIG_CIFS_SMB2
-		if (tcon->snapshot_time != volume_info->snapshot_time)
+		if (!match_tcon(tcon, volume_info))
 			continue;
-#endif /* CONFIG_CIFS_SMB2 */
-
 		++tcon->tc_count;
 		spin_unlock(&cifs_tcp_ses_lock);
 		return tcon;
@@ -2685,8 +2701,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		cifs_dbg(FYI, "Found match on UNC path\n");
 		/* existing tcon already has a reference */
 		cifs_put_smb_ses(ses);
-		if (tcon->seal != volume_info->seal)
-			cifs_dbg(VFS, "transport encryption setting conflicts with existing tid\n");
 		return tcon;
 	}
 
@@ -2742,7 +2756,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		tcon->Flags &= ~SMB_SHARE_IS_IN_DFS;
 		cifs_dbg(FYI, "DFS disabled (%d)\n", tcon->Flags);
 	}
-	tcon->seal = volume_info->seal;
 	tcon->use_persistent = false;
 	/* check if SMB2 or later, CIFS does not support persistent handles */
 	if (volume_info->persistent) {
@@ -2779,6 +2792,24 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		tcon->use_resilient = true;
 	}
 
+	if (volume_info->seal) {
+		if (ses->server->vals->protocol_id == 0) {
+			cifs_dbg(VFS,
+				 "SMB3 or later required for encryption\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+#ifdef CONFIG_CIFS_SMB2
+		} else if (tcon->ses->server->capabilities &
+					SMB2_GLOBAL_CAP_ENCRYPTION)
+			tcon->seal = true;
+		else {
+			cifs_dbg(VFS, "Encryption is not supported on share\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+#endif /* CONFIG_CIFS_SMB2 */
+		}
+	}
+
 	/*
 	 * We can have only one retry value for a connection to a share so for
 	 * resources mounted more than once to the same server share the last
@@ -2910,7 +2941,7 @@ cifs_match_super(struct super_block *sb, void *data)
 
 	if (!match_server(tcp_srv, volume_info) ||
 	    !match_session(ses, volume_info) ||
-	    !match_tcon(tcon, volume_info->UNC) ||
+	    !match_tcon(tcon, volume_info) ||
 	    !match_prepath(sb, mnt_data)) {
 		rc = 0;
 		goto out;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 18a1e1d6671f..98dc842e7245 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2884,7 +2884,15 @@ cifs_readdata_to_iov(struct cifs_readdata *rdata, struct iov_iter *iter)
 	for (i = 0; i < rdata->nr_pages; i++) {
 		struct page *page = rdata->pages[i];
 		size_t copy = min_t(size_t, remaining, PAGE_SIZE);
-		size_t written = copy_page_to_iter(page, 0, copy, iter);
+		size_t written;
+
+		if (unlikely(iter->type & ITER_PIPE)) {
+			void *addr = kmap_atomic(page);
+
+			written = copy_to_iter(addr, copy, iter);
+			kunmap_atomic(addr);
+		} else
+			written = copy_page_to_iter(page, 0, copy, iter);
 		remaining -= written;
 		if (written < copy && iov_iter_count(iter) > 0)
 			break;
@@ -2903,8 +2911,9 @@ cifs_uncached_readv_complete(struct work_struct *work)
 }
 
 static int
-cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
-			struct cifs_readdata *rdata, unsigned int len)
+uncached_fill_pages(struct TCP_Server_Info *server,
+		    struct cifs_readdata *rdata, struct iov_iter *iter,
+		    unsigned int len)
 {
 	int result = 0;
 	unsigned int i;
@@ -2933,7 +2942,10 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
 			rdata->tailsz = len;
 			len = 0;
 		}
-		result = cifs_read_page_from_socket(server, page, n);
+		if (iter)
+			result = copy_page_from_iter(page, 0, n, iter);
+		else
+			result = cifs_read_page_from_socket(server, page, n);
 		if (result < 0)
 			break;
 
@@ -2945,6 +2957,21 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
 }
 
 static int
+cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
+			      struct cifs_readdata *rdata, unsigned int len)
+{
+	return uncached_fill_pages(server, rdata, NULL, len);
+}
+
+static int
+cifs_uncached_copy_into_pages(struct TCP_Server_Info *server,
+			      struct cifs_readdata *rdata,
+			      struct iov_iter *iter)
+{
+	return uncached_fill_pages(server, rdata, iter, iter->count);
+}
+
+static int
 cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		     struct cifs_sb_info *cifs_sb, struct list_head *rdata_list)
 {
@@ -2991,6 +3018,7 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		rdata->pid = pid;
 		rdata->pagesz = PAGE_SIZE;
 		rdata->read_into_pages = cifs_uncached_read_into_pages;
+		rdata->copy_into_pages = cifs_uncached_copy_into_pages;
 		rdata->credits = credits;
 
 		if (!rdata->cfile->invalidHandle ||
@@ -3341,8 +3369,9 @@ cifs_readv_complete(struct work_struct *work)
 }
 
 static int
-cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
-			struct cifs_readdata *rdata, unsigned int len)
+readpages_fill_pages(struct TCP_Server_Info *server,
+		     struct cifs_readdata *rdata, struct iov_iter *iter,
+		     unsigned int len)
 {
 	int result = 0;
 	unsigned int i;
@@ -3396,7 +3425,10 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
 			continue;
 		}
 
-		result = cifs_read_page_from_socket(server, page, n);
+		if (iter)
+			result = copy_page_from_iter(page, 0, n, iter);
+		else
+			result = cifs_read_page_from_socket(server, page, n);
 		if (result < 0)
 			break;
 
@@ -3408,6 +3440,21 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
 }
 
 static int
+cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
+			       struct cifs_readdata *rdata, unsigned int len)
+{
+	return readpages_fill_pages(server, rdata, NULL, len);
+}
+
+static int
+cifs_readpages_copy_into_pages(struct TCP_Server_Info *server,
+			       struct cifs_readdata *rdata,
+			       struct iov_iter *iter)
+{
+	return readpages_fill_pages(server, rdata, iter, iter->count);
+}
+
+static int
 readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 		    unsigned int rsize, struct list_head *tmplist,
 		    unsigned int *nr_pages, loff_t *offset, unsigned int *bytes)
@@ -3561,6 +3608,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		rdata->pid = pid;
 		rdata->pagesz = PAGE_SIZE;
 		rdata->read_into_pages = cifs_readpages_read_into_pages;
+		rdata->copy_into_pages = cifs_readpages_copy_into_pages;
 		rdata->credits = credits;
 
 		list_for_each_entry_safe(page, tpage, &tmplist, lru) {
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 8f6a2a5863b9..a27fc8791551 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -285,6 +285,7 @@ initiate_cifs_search(const unsigned int xid, struct file *file)
 			rc = -ENOMEM;
 			goto error_exit;
 		}
+		spin_lock_init(&cifsFile->file_info_lock);
 		file->private_data = cifsFile;
 		cifsFile->tlink = cifs_get_tlink(tlink);
 		tcon = tlink_tcon(tlink);
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 538d9b55699a..dcbcc927399a 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -344,13 +344,12 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
 	/* BB is NTLMV2 session security format easier to use here? */
 	flags = NTLMSSP_NEGOTIATE_56 |	NTLMSSP_REQUEST_TARGET |
 		NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
-		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC;
-	if (ses->server->sign) {
+		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC |
+		NTLMSSP_NEGOTIATE_SEAL;
+	if (ses->server->sign)
 		flags |= NTLMSSP_NEGOTIATE_SIGN;
-		if (!ses->server->session_estab ||
-				ses->ntlmssp->sesskey_per_smbsess)
-			flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
-	}
+	if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess)
+		flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
 
 	sec_blob->NegotiateFlags = cpu_to_le32(flags);
 
@@ -407,13 +406,12 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer,
 	flags = NTLMSSP_NEGOTIATE_56 |
 		NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO |
 		NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
-		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC;
-	if (ses->server->sign) {
+		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC |
+		NTLMSSP_NEGOTIATE_SEAL;
+	if (ses->server->sign)
 		flags |= NTLMSSP_NEGOTIATE_SIGN;
-		if (!ses->server->session_estab ||
-				ses->ntlmssp->sesskey_per_smbsess)
-			flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
-	}
+	if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess)
+		flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
 
 	tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE);
 	sec_blob->NegotiateFlags = cpu_to_le32(flags);
@@ -652,6 +650,7 @@ sess_sendreceive(struct sess_data *sess_data)
 	int rc;
 	struct smb_hdr *smb_buf = (struct smb_hdr *) sess_data->iov[0].iov_base;
 	__u16 count;
+	struct kvec rsp_iov = { NULL, 0 };
 
 	count = sess_data->iov[1].iov_len + sess_data->iov[2].iov_len;
 	smb_buf->smb_buf_length =
@@ -661,7 +660,9 @@ sess_sendreceive(struct sess_data *sess_data)
 	rc = SendReceive2(sess_data->xid, sess_data->ses,
 			  sess_data->iov, 3 /* num_iovecs */,
 			  &sess_data->buf0_type,
-			  CIFS_LOG_ERROR);
+			  CIFS_LOG_ERROR, &rsp_iov);
+	cifs_small_buf_release(sess_data->iov[0].iov_base);
+	memcpy(&sess_data->iov[0], &rsp_iov, sizeof(struct kvec));
 
 	return rc;
 }
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index fc537c29044e..67a987e4d026 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -36,11 +36,11 @@
  * SMB_COM_NT_CANCEL request and then sends it.
  */
 static int
-send_nt_cancel(struct TCP_Server_Info *server, void *buf,
+send_nt_cancel(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 	       struct mid_q_entry *mid)
 {
 	int rc = 0;
-	struct smb_hdr *in_buf = (struct smb_hdr *)buf;
+	struct smb_hdr *in_buf = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
 
 	/* -4 for RFC1001 length and +2 for BCC field */
 	in_buf->smb_buf_length = cpu_to_be32(sizeof(struct smb_hdr) - 4  + 2);
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index 0ffa18094335..401a5d856636 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -61,4 +61,9 @@
 /* Maximum buffer size value we can send with 1 credit */
 #define SMB2_MAX_BUFFER_SIZE 65536
 
+static inline struct smb2_sync_hdr *get_sync_hdr(void *buf)
+{
+	return &(((struct smb2_hdr *)buf)->sync_hdr);
+}
+
 #endif	/* _SMB2_GLOB_H */
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 8257a5a97cc0..3030a9dfb0dd 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -26,6 +26,7 @@
 #include "smb2pdu.h"
 #include "smb2proto.h"
 #include "smb2status.h"
+#include "smb2glob.h"
 
 struct status_to_posix_error {
 	__le32 smb2_status;
@@ -2449,10 +2450,10 @@ smb2_print_status(__le32 status)
 int
 map_smb2_to_linux_error(char *buf, bool log_err)
 {
-	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
 	unsigned int i;
 	int rc = -EIO;
-	__le32 smb2err = hdr->Status;
+	__le32 smb2err = shdr->Status;
 
 	if (smb2err == 0)
 		return 0;
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 3d383489b9cf..fd516ea8b8f8 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -28,31 +28,32 @@
 #include "cifs_debug.h"
 #include "cifs_unicode.h"
 #include "smb2status.h"
+#include "smb2glob.h"
 
 static int
-check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid)
+check_smb2_hdr(struct smb2_sync_hdr *shdr, __u64 mid)
 {
-	__u64 wire_mid = le64_to_cpu(hdr->MessageId);
+	__u64 wire_mid = le64_to_cpu(shdr->MessageId);
 
 	/*
 	 * Make sure that this really is an SMB, that it is a response,
 	 * and that the message ids match.
 	 */
-	if ((hdr->ProtocolId == SMB2_PROTO_NUMBER) &&
+	if ((shdr->ProtocolId == SMB2_PROTO_NUMBER) &&
 	    (mid == wire_mid)) {
-		if (hdr->Flags & SMB2_FLAGS_SERVER_TO_REDIR)
+		if (shdr->Flags & SMB2_FLAGS_SERVER_TO_REDIR)
 			return 0;
 		else {
 			/* only one valid case where server sends us request */
-			if (hdr->Command == SMB2_OPLOCK_BREAK)
+			if (shdr->Command == SMB2_OPLOCK_BREAK)
 				return 0;
 			else
 				cifs_dbg(VFS, "Received Request not response\n");
 		}
 	} else { /* bad signature or mid */
-		if (hdr->ProtocolId != SMB2_PROTO_NUMBER)
+		if (shdr->ProtocolId != SMB2_PROTO_NUMBER)
 			cifs_dbg(VFS, "Bad protocol string signature header %x\n",
-				 le32_to_cpu(hdr->ProtocolId));
+				 le32_to_cpu(shdr->ProtocolId));
 		if (mid != wire_mid)
 			cifs_dbg(VFS, "Mids do not match: %llu and %llu\n",
 				 mid, wire_mid);
@@ -95,8 +96,9 @@ static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 int
 smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 {
-	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
-	struct smb2_pdu *pdu = (struct smb2_pdu *)hdr;
+	struct smb2_pdu *pdu = (struct smb2_pdu *)buf;
+	struct smb2_hdr *hdr = &pdu->hdr;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
 	__u64 mid;
 	__u32 len = get_rfc1002_length(buf);
 	__u32 clc_len;  /* calculated length */
@@ -111,7 +113,7 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 	 * ie Validate the wct via smb2_struct_sizes table above
 	 */
 
-	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
+	if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
 		struct smb2_transform_hdr *thdr =
 			(struct smb2_transform_hdr *)buf;
 		struct cifs_ses *ses = NULL;
@@ -133,10 +135,10 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 		}
 	}
 
-
-	mid = le64_to_cpu(hdr->MessageId);
+	mid = le64_to_cpu(shdr->MessageId);
 	if (length < sizeof(struct smb2_pdu)) {
-		if ((length >= sizeof(struct smb2_hdr)) && (hdr->Status != 0)) {
+		if ((length >= sizeof(struct smb2_hdr))
+		    && (shdr->Status != 0)) {
 			pdu->StructureSize2 = 0;
 			/*
 			 * As with SMB/CIFS, on some error cases servers may
@@ -154,29 +156,30 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 		return 1;
 	}
 
-	if (check_smb2_hdr(hdr, mid))
+	if (check_smb2_hdr(shdr, mid))
 		return 1;
 
-	if (hdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) {
+	if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) {
 		cifs_dbg(VFS, "Illegal structure size %u\n",
-			 le16_to_cpu(hdr->StructureSize));
+			 le16_to_cpu(shdr->StructureSize));
 		return 1;
 	}
 
-	command = le16_to_cpu(hdr->Command);
+	command = le16_to_cpu(shdr->Command);
 	if (command >= NUMBER_OF_SMB2_COMMANDS) {
 		cifs_dbg(VFS, "Illegal SMB2 command %d\n", command);
 		return 1;
 	}
 
 	if (smb2_rsp_struct_sizes[command] != pdu->StructureSize2) {
-		if (command != SMB2_OPLOCK_BREAK_HE && (hdr->Status == 0 ||
+		if (command != SMB2_OPLOCK_BREAK_HE && (shdr->Status == 0 ||
 		    pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2)) {
 			/* error packets have 9 byte structure size */
 			cifs_dbg(VFS, "Illegal response size %u for command %d\n",
 				 le16_to_cpu(pdu->StructureSize2), command);
 			return 1;
-		} else if (command == SMB2_OPLOCK_BREAK_HE && (hdr->Status == 0)
+		} else if (command == SMB2_OPLOCK_BREAK_HE
+			   && (shdr->Status == 0)
 			   && (le16_to_cpu(pdu->StructureSize2) != 44)
 			   && (le16_to_cpu(pdu->StructureSize2) != 36)) {
 			/* special case for SMB2.1 lease break message */
@@ -199,7 +202,7 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 			 clc_len, 4 + len, mid);
 		/* create failed on symlink */
 		if (command == SMB2_CREATE_HE &&
-		    hdr->Status == STATUS_STOPPED_ON_SYMLINK)
+		    shdr->Status == STATUS_STOPPED_ON_SYMLINK)
 			return 0;
 		/* Windows 7 server returns 24 bytes more */
 		if (clc_len + 20 == len && command == SMB2_OPLOCK_BREAK_HE)
@@ -261,11 +264,12 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = {
 char *
 smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
 {
+	struct smb2_sync_hdr *shdr = get_sync_hdr(hdr);
 	*off = 0;
 	*len = 0;
 
 	/* error responses do not have data area */
-	if (hdr->Status && hdr->Status != STATUS_MORE_PROCESSING_REQUIRED &&
+	if (shdr->Status && shdr->Status != STATUS_MORE_PROCESSING_REQUIRED &&
 	    (((struct smb2_err_rsp *)hdr)->StructureSize) ==
 						SMB2_ERROR_STRUCTURE_SIZE2)
 		return NULL;
@@ -275,7 +279,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
 	 * of the data buffer offset and data buffer length for the particular
 	 * command.
 	 */
-	switch (hdr->Command) {
+	switch (shdr->Command) {
 	case SMB2_NEGOTIATE:
 		*off = le16_to_cpu(
 		    ((struct smb2_negotiate_rsp *)hdr)->SecurityBufferOffset);
@@ -346,7 +350,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
 
 	/* return pointer to beginning of data area, ie offset from SMB start */
 	if ((*off != 0) && (*len != 0))
-		return (char *)(&hdr->ProtocolId) + *off;
+		return (char *)shdr + *off;
 	else
 		return NULL;
 }
@@ -358,12 +362,13 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
 unsigned int
 smb2_calc_size(void *buf)
 {
-	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
-	struct smb2_pdu *pdu = (struct smb2_pdu *)hdr;
+	struct smb2_pdu *pdu = (struct smb2_pdu *)buf;
+	struct smb2_hdr *hdr = &pdu->hdr;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(hdr);
 	int offset; /* the offset from the beginning of SMB to data area */
 	int data_length; /* the length of the variable length data area */
 	/* Structure Size has already been checked to make sure it is 64 */
-	int len = 4 + le16_to_cpu(pdu->hdr.StructureSize);
+	int len = 4 + le16_to_cpu(shdr->StructureSize);
 
 	/*
 	 * StructureSize2, ie length of fixed parameter area has already
@@ -371,7 +376,7 @@ smb2_calc_size(void *buf)
 	 */
 	len += le16_to_cpu(pdu->StructureSize2);
 
-	if (has_smb2_data_area[le16_to_cpu(hdr->Command)] == false)
+	if (has_smb2_data_area[le16_to_cpu(shdr->Command)] == false)
 		goto calc_size_exit;
 
 	smb2_get_data_area_len(&offset, &data_length, hdr);
@@ -582,7 +587,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 
 	cifs_dbg(FYI, "Checking for oplock break\n");
 
-	if (rsp->hdr.Command != SMB2_OPLOCK_BREAK)
+	if (rsp->hdr.sync_hdr.Command != SMB2_OPLOCK_BREAK)
 		return false;
 
 	if (rsp->StructureSize !=
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 5d456ebb3813..a44b4dbe4aae 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -20,6 +20,8 @@
 #include <linux/pagemap.h>
 #include <linux/vfs.h>
 #include <linux/falloc.h>
+#include <linux/scatterlist.h>
+#include <crypto/aead.h>
 #include "cifsglob.h"
 #include "smb2pdu.h"
 #include "smb2proto.h"
@@ -119,7 +121,9 @@ smb2_get_credits_field(struct TCP_Server_Info *server, const int optype)
 static unsigned int
 smb2_get_credits(struct mid_q_entry *mid)
 {
-	return le16_to_cpu(((struct smb2_hdr *)mid->resp_buf)->CreditRequest);
+	struct smb2_sync_hdr *shdr = get_sync_hdr(mid->resp_buf);
+
+	return le16_to_cpu(shdr->CreditRequest);
 }
 
 static int
@@ -184,10 +188,10 @@ static struct mid_q_entry *
 smb2_find_mid(struct TCP_Server_Info *server, char *buf)
 {
 	struct mid_q_entry *mid;
-	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
-	__u64 wire_mid = le64_to_cpu(hdr->MessageId);
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	__u64 wire_mid = le64_to_cpu(shdr->MessageId);
 
-	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
+	if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
 		cifs_dbg(VFS, "encrypted frame parsing not supported yet");
 		return NULL;
 	}
@@ -196,7 +200,7 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf)
 	list_for_each_entry(mid, &server->pending_mid_q, qhead) {
 		if ((mid->mid == wire_mid) &&
 		    (mid->mid_state == MID_REQUEST_SUBMITTED) &&
-		    (mid->command == hdr->Command)) {
+		    (mid->command == shdr->Command)) {
 			spin_unlock(&GlobalMid_Lock);
 			return mid;
 		}
@@ -209,12 +213,12 @@ static void
 smb2_dump_detail(void *buf)
 {
 #ifdef CONFIG_CIFS_DEBUG2
-	struct smb2_hdr *smb = (struct smb2_hdr *)buf;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
 
 	cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Mid: %llu Pid: %d\n",
-		 smb->Command, smb->Status, smb->Flags, smb->MessageId,
-		 smb->ProcessId);
-	cifs_dbg(VFS, "smb buf %p len %u\n", smb, smb2_calc_size(smb));
+		 shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId,
+		 shdr->ProcessId);
+	cifs_dbg(VFS, "smb buf %p len %u\n", buf, smb2_calc_size(buf));
 #endif
 }
 
@@ -1002,14 +1006,14 @@ smb2_close_dir(const unsigned int xid, struct cifs_tcon *tcon,
 static bool
 smb2_is_status_pending(char *buf, struct TCP_Server_Info *server, int length)
 {
-	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
 
-	if (hdr->Status != STATUS_PENDING)
+	if (shdr->Status != STATUS_PENDING)
 		return false;
 
 	if (!length) {
 		spin_lock(&server->req_lock);
-		server->credits += le16_to_cpu(hdr->CreditRequest);
+		server->credits += le16_to_cpu(shdr->CreditRequest);
 		spin_unlock(&server->req_lock);
 		wake_up(&server->request_q);
 	}
@@ -1545,6 +1549,633 @@ smb2_dir_needs_close(struct cifsFileInfo *cfile)
 	return !cfile->invalidHandle;
 }
 
+static void
+fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, struct smb_rqst *old_rq)
+{
+	struct smb2_sync_hdr *shdr =
+			(struct smb2_sync_hdr *)old_rq->rq_iov[1].iov_base;
+	unsigned int orig_len = get_rfc1002_length(old_rq->rq_iov[0].iov_base);
+
+	memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr));
+	tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM;
+	tr_hdr->OriginalMessageSize = cpu_to_le32(orig_len);
+	tr_hdr->Flags = cpu_to_le16(0x01);
+	get_random_bytes(&tr_hdr->Nonce, SMB3_AES128CMM_NONCE);
+	memcpy(&tr_hdr->SessionId, &shdr->SessionId, 8);
+	inc_rfc1001_len(tr_hdr, sizeof(struct smb2_transform_hdr) - 4);
+	inc_rfc1001_len(tr_hdr, orig_len);
+}
+
+static struct scatterlist *
+init_sg(struct smb_rqst *rqst, u8 *sign)
+{
+	unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages + 1;
+	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24;
+	struct scatterlist *sg;
+	unsigned int i;
+	unsigned int j;
+
+	sg = kmalloc_array(sg_len, sizeof(struct scatterlist), GFP_KERNEL);
+	if (!sg)
+		return NULL;
+
+	sg_init_table(sg, sg_len);
+	sg_set_buf(&sg[0], rqst->rq_iov[0].iov_base + 24, assoc_data_len);
+	for (i = 1; i < rqst->rq_nvec; i++)
+		sg_set_buf(&sg[i], rqst->rq_iov[i].iov_base,
+						rqst->rq_iov[i].iov_len);
+	for (j = 0; i < sg_len - 1; i++, j++) {
+		unsigned int len = (j < rqst->rq_npages - 1) ? rqst->rq_pagesz
+							: rqst->rq_tailsz;
+		sg_set_page(&sg[i], rqst->rq_pages[j], len, 0);
+	}
+	sg_set_buf(&sg[sg_len - 1], sign, SMB2_SIGNATURE_SIZE);
+	return sg;
+}
+
+struct cifs_crypt_result {
+	int err;
+	struct completion completion;
+};
+
+static void cifs_crypt_complete(struct crypto_async_request *req, int err)
+{
+	struct cifs_crypt_result *res = req->data;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	res->err = err;
+	complete(&res->completion);
+}
+
+/*
+ * Encrypt or decrypt @rqst message. @rqst has the following format:
+ * iov[0] - transform header (associate data),
+ * iov[1-N] and pages - data to encrypt.
+ * On success return encrypted data in iov[1-N] and pages, leave iov[0]
+ * untouched.
+ */
+static int
+crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
+{
+	struct smb2_transform_hdr *tr_hdr =
+			(struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base;
+	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24;
+	struct cifs_ses *ses;
+	int rc = 0;
+	struct scatterlist *sg;
+	u8 sign[SMB2_SIGNATURE_SIZE] = {};
+	struct aead_request *req;
+	char *iv;
+	unsigned int iv_len;
+	struct cifs_crypt_result result = {0, };
+	struct crypto_aead *tfm;
+	unsigned int crypt_len = le32_to_cpu(tr_hdr->OriginalMessageSize);
+
+	init_completion(&result.completion);
+
+	ses = smb2_find_smb_ses(server, tr_hdr->SessionId);
+	if (!ses) {
+		cifs_dbg(VFS, "%s: Could not find session\n", __func__);
+		return 0;
+	}
+
+	rc = smb3_crypto_aead_allocate(server);
+	if (rc) {
+		cifs_dbg(VFS, "%s: crypto alloc failed\n", __func__);
+		return rc;
+	}
+
+	tfm = enc ? server->secmech.ccmaesencrypt :
+						server->secmech.ccmaesdecrypt;
+	rc = crypto_aead_setkey(tfm, enc ? ses->smb3encryptionkey :
+				ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE);
+	if (rc) {
+		cifs_dbg(VFS, "%s: Failed to set aead key %d\n", __func__, rc);
+		return rc;
+	}
+
+	rc = crypto_aead_setauthsize(tfm, SMB2_SIGNATURE_SIZE);
+	if (rc) {
+		cifs_dbg(VFS, "%s: Failed to set authsize %d\n", __func__, rc);
+		return rc;
+	}
+
+	req = aead_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		cifs_dbg(VFS, "%s: Failed to alloc aead request", __func__);
+		return -ENOMEM;
+	}
+
+	if (!enc) {
+		memcpy(sign, &tr_hdr->Signature, SMB2_SIGNATURE_SIZE);
+		crypt_len += SMB2_SIGNATURE_SIZE;
+	}
+
+	sg = init_sg(rqst, sign);
+	if (!sg) {
+		cifs_dbg(VFS, "%s: Failed to init sg %d", __func__, rc);
+		goto free_req;
+	}
+
+	iv_len = crypto_aead_ivsize(tfm);
+	iv = kzalloc(iv_len, GFP_KERNEL);
+	if (!iv) {
+		cifs_dbg(VFS, "%s: Failed to alloc IV", __func__);
+		goto free_sg;
+	}
+	iv[0] = 3;
+	memcpy(iv + 1, (char *)tr_hdr->Nonce, SMB3_AES128CMM_NONCE);
+
+	aead_request_set_crypt(req, sg, sg, crypt_len, iv);
+	aead_request_set_ad(req, assoc_data_len);
+
+	aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				  cifs_crypt_complete, &result);
+
+	rc = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req);
+
+	if (rc == -EINPROGRESS || rc == -EBUSY) {
+		wait_for_completion(&result.completion);
+		rc = result.err;
+	}
+
+	if (!rc && enc)
+		memcpy(&tr_hdr->Signature, sign, SMB2_SIGNATURE_SIZE);
+
+	kfree(iv);
+free_sg:
+	kfree(sg);
+free_req:
+	kfree(req);
+	return rc;
+}
+
+static int
+smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
+		       struct smb_rqst *old_rq)
+{
+	struct kvec *iov;
+	struct page **pages;
+	struct smb2_transform_hdr *tr_hdr;
+	unsigned int npages = old_rq->rq_npages;
+	int i;
+	int rc = -ENOMEM;
+
+	pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		return rc;
+
+	new_rq->rq_pages = pages;
+	new_rq->rq_npages = old_rq->rq_npages;
+	new_rq->rq_pagesz = old_rq->rq_pagesz;
+	new_rq->rq_tailsz = old_rq->rq_tailsz;
+
+	for (i = 0; i < npages; i++) {
+		pages[i] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
+		if (!pages[i])
+			goto err_free_pages;
+	}
+
+	iov = kmalloc_array(old_rq->rq_nvec, sizeof(struct kvec), GFP_KERNEL);
+	if (!iov)
+		goto err_free_pages;
+
+	/* copy all iovs from the old except the 1st one (rfc1002 length) */
+	memcpy(&iov[1], &old_rq->rq_iov[1],
+				sizeof(struct kvec) * (old_rq->rq_nvec - 1));
+	new_rq->rq_iov = iov;
+	new_rq->rq_nvec = old_rq->rq_nvec;
+
+	tr_hdr = kmalloc(sizeof(struct smb2_transform_hdr), GFP_KERNEL);
+	if (!tr_hdr)
+		goto err_free_iov;
+
+	/* fill the 1st iov with a transform header */
+	fill_transform_hdr(tr_hdr, old_rq);
+	new_rq->rq_iov[0].iov_base = tr_hdr;
+	new_rq->rq_iov[0].iov_len = sizeof(struct smb2_transform_hdr);
+
+	/* copy pages form the old */
+	for (i = 0; i < npages; i++) {
+		char *dst = kmap(new_rq->rq_pages[i]);
+		char *src = kmap(old_rq->rq_pages[i]);
+		unsigned int len = (i < npages - 1) ? new_rq->rq_pagesz :
+							new_rq->rq_tailsz;
+		memcpy(dst, src, len);
+		kunmap(new_rq->rq_pages[i]);
+		kunmap(old_rq->rq_pages[i]);
+	}
+
+	rc = crypt_message(server, new_rq, 1);
+	cifs_dbg(FYI, "encrypt message returned %d", rc);
+	if (rc)
+		goto err_free_tr_hdr;
+
+	return rc;
+
+err_free_tr_hdr:
+	kfree(tr_hdr);
+err_free_iov:
+	kfree(iov);
+err_free_pages:
+	for (i = i - 1; i >= 0; i--)
+		put_page(pages[i]);
+	kfree(pages);
+	return rc;
+}
+
+static void
+smb3_free_transform_rq(struct smb_rqst *rqst)
+{
+	int i = rqst->rq_npages - 1;
+
+	for (; i >= 0; i--)
+		put_page(rqst->rq_pages[i]);
+	kfree(rqst->rq_pages);
+	/* free transform header */
+	kfree(rqst->rq_iov[0].iov_base);
+	kfree(rqst->rq_iov);
+}
+
+static int
+smb3_is_transform_hdr(void *buf)
+{
+	struct smb2_transform_hdr *trhdr = buf;
+
+	return trhdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM;
+}
+
+static int
+decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
+		 unsigned int buf_data_size, struct page **pages,
+		 unsigned int npages, unsigned int page_data_size)
+{
+	struct kvec iov[2];
+	struct smb_rqst rqst = {NULL};
+	struct smb2_hdr *hdr;
+	int rc;
+
+	iov[0].iov_base = buf;
+	iov[0].iov_len = sizeof(struct smb2_transform_hdr);
+	iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr);
+	iov[1].iov_len = buf_data_size;
+
+	rqst.rq_iov = iov;
+	rqst.rq_nvec = 2;
+	rqst.rq_pages = pages;
+	rqst.rq_npages = npages;
+	rqst.rq_pagesz = PAGE_SIZE;
+	rqst.rq_tailsz = (page_data_size % PAGE_SIZE) ? : PAGE_SIZE;
+
+	rc = crypt_message(server, &rqst, 0);
+	cifs_dbg(FYI, "decrypt message returned %d\n", rc);
+
+	if (rc)
+		return rc;
+
+	memmove(buf + 4, iov[1].iov_base, buf_data_size);
+	hdr = (struct smb2_hdr *)buf;
+	hdr->smb2_buf_length = cpu_to_be32(buf_data_size + page_data_size);
+	server->total_read = buf_data_size + page_data_size + 4;
+
+	return rc;
+}
+
+static int
+read_data_into_pages(struct TCP_Server_Info *server, struct page **pages,
+		     unsigned int npages, unsigned int len)
+{
+	int i;
+	int length;
+
+	for (i = 0; i < npages; i++) {
+		struct page *page = pages[i];
+		size_t n;
+
+		n = len;
+		if (len >= PAGE_SIZE) {
+			/* enough data to fill the page */
+			n = PAGE_SIZE;
+			len -= n;
+		} else {
+			zero_user(page, len, PAGE_SIZE - len);
+			len = 0;
+		}
+		length = cifs_read_page_from_socket(server, page, n);
+		if (length < 0)
+			return length;
+		server->total_read += length;
+	}
+
+	return 0;
+}
+
+static int
+init_read_bvec(struct page **pages, unsigned int npages, unsigned int data_size,
+	       unsigned int cur_off, struct bio_vec **page_vec)
+{
+	struct bio_vec *bvec;
+	int i;
+
+	bvec = kcalloc(npages, sizeof(struct bio_vec), GFP_KERNEL);
+	if (!bvec)
+		return -ENOMEM;
+
+	for (i = 0; i < npages; i++) {
+		bvec[i].bv_page = pages[i];
+		bvec[i].bv_offset = (i == 0) ? cur_off : 0;
+		bvec[i].bv_len = min_t(unsigned int, PAGE_SIZE, data_size);
+		data_size -= bvec[i].bv_len;
+	}
+
+	if (data_size != 0) {
+		cifs_dbg(VFS, "%s: something went wrong\n", __func__);
+		kfree(bvec);
+		return -EIO;
+	}
+
+	*page_vec = bvec;
+	return 0;
+}
+
+static int
+handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
+		 char *buf, unsigned int buf_len, struct page **pages,
+		 unsigned int npages, unsigned int page_data_size)
+{
+	unsigned int data_offset;
+	unsigned int data_len;
+	unsigned int cur_off;
+	unsigned int cur_page_idx;
+	unsigned int pad_len;
+	struct cifs_readdata *rdata = mid->callback_data;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	struct bio_vec *bvec = NULL;
+	struct iov_iter iter;
+	struct kvec iov;
+	int length;
+
+	if (shdr->Command != SMB2_READ) {
+		cifs_dbg(VFS, "only big read responses are supported\n");
+		return -ENOTSUPP;
+	}
+
+	if (server->ops->is_status_pending &&
+			server->ops->is_status_pending(buf, server, 0))
+		return -1;
+
+	rdata->result = server->ops->map_error(buf, false);
+	if (rdata->result != 0) {
+		cifs_dbg(FYI, "%s: server returned error %d\n",
+			 __func__, rdata->result);
+		dequeue_mid(mid, rdata->result);
+		return 0;
+	}
+
+	data_offset = server->ops->read_data_offset(buf) + 4;
+	data_len = server->ops->read_data_length(buf);
+
+	if (data_offset < server->vals->read_rsp_size) {
+		/*
+		 * win2k8 sometimes sends an offset of 0 when the read
+		 * is beyond the EOF. Treat it as if the data starts just after
+		 * the header.
+		 */
+		cifs_dbg(FYI, "%s: data offset (%u) inside read response header\n",
+			 __func__, data_offset);
+		data_offset = server->vals->read_rsp_size;
+	} else if (data_offset > MAX_CIFS_SMALL_BUFFER_SIZE) {
+		/* data_offset is beyond the end of smallbuf */
+		cifs_dbg(FYI, "%s: data offset (%u) beyond end of smallbuf\n",
+			 __func__, data_offset);
+		rdata->result = -EIO;
+		dequeue_mid(mid, rdata->result);
+		return 0;
+	}
+
+	pad_len = data_offset - server->vals->read_rsp_size;
+
+	if (buf_len <= data_offset) {
+		/* read response payload is in pages */
+		cur_page_idx = pad_len / PAGE_SIZE;
+		cur_off = pad_len % PAGE_SIZE;
+
+		if (cur_page_idx != 0) {
+			/* data offset is beyond the 1st page of response */
+			cifs_dbg(FYI, "%s: data offset (%u) beyond 1st page of response\n",
+				 __func__, data_offset);
+			rdata->result = -EIO;
+			dequeue_mid(mid, rdata->result);
+			return 0;
+		}
+
+		if (data_len > page_data_size - pad_len) {
+			/* data_len is corrupt -- discard frame */
+			rdata->result = -EIO;
+			dequeue_mid(mid, rdata->result);
+			return 0;
+		}
+
+		rdata->result = init_read_bvec(pages, npages, page_data_size,
+					       cur_off, &bvec);
+		if (rdata->result != 0) {
+			dequeue_mid(mid, rdata->result);
+			return 0;
+		}
+
+		iov_iter_bvec(&iter, WRITE | ITER_BVEC, bvec, npages, data_len);
+	} else if (buf_len >= data_offset + data_len) {
+		/* read response payload is in buf */
+		WARN_ONCE(npages > 0, "read data can be either in buf or in pages");
+		iov.iov_base = buf + data_offset;
+		iov.iov_len = data_len;
+		iov_iter_kvec(&iter, WRITE | ITER_KVEC, &iov, 1, data_len);
+	} else {
+		/* read response payload cannot be in both buf and pages */
+		WARN_ONCE(1, "buf can not contain only a part of read data");
+		rdata->result = -EIO;
+		dequeue_mid(mid, rdata->result);
+		return 0;
+	}
+
+	/* set up first iov for signature check */
+	rdata->iov[0].iov_base = buf;
+	rdata->iov[0].iov_len = 4;
+	rdata->iov[1].iov_base = buf + 4;
+	rdata->iov[1].iov_len = server->vals->read_rsp_size - 4;
+	cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n",
+		 rdata->iov[0].iov_base, server->vals->read_rsp_size);
+
+	length = rdata->copy_into_pages(server, rdata, &iter);
+
+	kfree(bvec);
+
+	if (length < 0)
+		return length;
+
+	dequeue_mid(mid, false);
+	return length;
+}
+
+static int
+receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid)
+{
+	char *buf = server->smallbuf;
+	struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf;
+	unsigned int npages;
+	struct page **pages;
+	unsigned int len;
+	unsigned int buflen = get_rfc1002_length(buf) + 4;
+	int rc;
+	int i = 0;
+
+	len = min_t(unsigned int, buflen, server->vals->read_rsp_size - 4 +
+		sizeof(struct smb2_transform_hdr)) - HEADER_SIZE(server) + 1;
+
+	rc = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1, len);
+	if (rc < 0)
+		return rc;
+	server->total_read += rc;
+
+	len = le32_to_cpu(tr_hdr->OriginalMessageSize) + 4 -
+						server->vals->read_rsp_size;
+	npages = DIV_ROUND_UP(len, PAGE_SIZE);
+
+	pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
+	if (!pages) {
+		rc = -ENOMEM;
+		goto discard_data;
+	}
+
+	for (; i < npages; i++) {
+		pages[i] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
+		if (!pages[i]) {
+			rc = -ENOMEM;
+			goto discard_data;
+		}
+	}
+
+	/* read read data into pages */
+	rc = read_data_into_pages(server, pages, npages, len);
+	if (rc)
+		goto free_pages;
+
+	rc = cifs_discard_remaining_data(server);
+	if (rc)
+		goto free_pages;
+
+	rc = decrypt_raw_data(server, buf, server->vals->read_rsp_size - 4,
+			      pages, npages, len);
+	if (rc)
+		goto free_pages;
+
+	*mid = smb2_find_mid(server, buf);
+	if (*mid == NULL)
+		cifs_dbg(FYI, "mid not found\n");
+	else {
+		cifs_dbg(FYI, "mid found\n");
+		(*mid)->decrypted = true;
+		rc = handle_read_data(server, *mid, buf,
+				      server->vals->read_rsp_size,
+				      pages, npages, len);
+	}
+
+free_pages:
+	for (i = i - 1; i >= 0; i--)
+		put_page(pages[i]);
+	kfree(pages);
+	return rc;
+discard_data:
+	cifs_discard_remaining_data(server);
+	goto free_pages;
+}
+
+static int
+receive_encrypted_standard(struct TCP_Server_Info *server,
+			   struct mid_q_entry **mid)
+{
+	int length;
+	char *buf = server->smallbuf;
+	unsigned int pdu_length = get_rfc1002_length(buf);
+	unsigned int buf_size;
+	struct mid_q_entry *mid_entry;
+
+	/* switch to large buffer if too big for a small one */
+	if (pdu_length + 4 > MAX_CIFS_SMALL_BUFFER_SIZE) {
+		server->large_buf = true;
+		memcpy(server->bigbuf, buf, server->total_read);
+		buf = server->bigbuf;
+	}
+
+	/* now read the rest */
+	length = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1,
+				pdu_length - HEADER_SIZE(server) + 1 + 4);
+	if (length < 0)
+		return length;
+	server->total_read += length;
+
+	buf_size = pdu_length + 4 - sizeof(struct smb2_transform_hdr);
+	length = decrypt_raw_data(server, buf, buf_size, NULL, 0, 0);
+	if (length)
+		return length;
+
+	mid_entry = smb2_find_mid(server, buf);
+	if (mid_entry == NULL)
+		cifs_dbg(FYI, "mid not found\n");
+	else {
+		cifs_dbg(FYI, "mid found\n");
+		mid_entry->decrypted = true;
+	}
+
+	*mid = mid_entry;
+
+	if (mid_entry && mid_entry->handle)
+		return mid_entry->handle(server, mid_entry);
+
+	return cifs_handle_standard(server, mid_entry);
+}
+
+static int
+smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
+{
+	char *buf = server->smallbuf;
+	unsigned int pdu_length = get_rfc1002_length(buf);
+	struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf;
+	unsigned int orig_len = le32_to_cpu(tr_hdr->OriginalMessageSize);
+
+	if (pdu_length + 4 < sizeof(struct smb2_transform_hdr) +
+						sizeof(struct smb2_sync_hdr)) {
+		cifs_dbg(VFS, "Transform message is too small (%u)\n",
+			 pdu_length);
+		cifs_reconnect(server);
+		wake_up(&server->response_q);
+		return -ECONNABORTED;
+	}
+
+	if (pdu_length + 4 < orig_len + sizeof(struct smb2_transform_hdr)) {
+		cifs_dbg(VFS, "Transform message is broken\n");
+		cifs_reconnect(server);
+		wake_up(&server->response_q);
+		return -ECONNABORTED;
+	}
+
+	if (pdu_length + 4 > CIFSMaxBufSize + MAX_HEADER_SIZE(server))
+		return receive_encrypted_read(server, mid);
+
+	return receive_encrypted_standard(server, mid);
+}
+
+int
+smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+{
+	char *buf = server->large_buf ? server->bigbuf : server->smallbuf;
+
+	return handle_read_data(server, mid, buf, get_rfc1002_length(buf) + 4,
+				NULL, 0, 0);
+}
+
 struct smb_version_operations smb20_operations = {
 	.compare_fids = smb2_compare_fids,
 	.setup_request = smb2_setup_request,
@@ -1791,6 +2422,10 @@ struct smb_version_operations smb30_operations = {
 	.dir_needs_close = smb2_dir_needs_close,
 	.fallocate = smb3_fallocate,
 	.enum_snapshots = smb3_enum_snapshots,
+	.init_transform_rq = smb3_init_transform_rq,
+	.free_transform_rq = smb3_free_transform_rq,
+	.is_transform_hdr = smb3_is_transform_hdr,
+	.receive_transform = smb3_receive_transform,
 };
 
 #ifdef CONFIG_CIFS_SMB311
@@ -1879,6 +2514,10 @@ struct smb_version_operations smb311_operations = {
 	.dir_needs_close = smb2_dir_needs_close,
 	.fallocate = smb3_fallocate,
 	.enum_snapshots = smb3_enum_snapshots,
+	.init_transform_rq = smb3_init_transform_rq,
+	.free_transform_rq = smb3_free_transform_rq,
+	.is_transform_hdr = smb3_is_transform_hdr,
+	.receive_transform = smb3_receive_transform,
 };
 #endif /* CIFS_SMB311 */
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 87457227812c..ad83b3db2840 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -77,45 +77,42 @@ static const int smb2_req_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 	/* SMB2_OPLOCK_BREAK */ 24 /* BB this is 36 for LEASE_BREAK variant */
 };
 
+static int encryption_required(const struct cifs_tcon *tcon)
+{
+	if (!tcon)
+		return 0;
+	if ((tcon->ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) ||
+	    (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA))
+		return 1;
+	if (tcon->seal &&
+	    (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
+		return 1;
+	return 0;
+}
 
 static void
-smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ ,
+smb2_hdr_assemble(struct smb2_sync_hdr *shdr, __le16 smb2_cmd,
 		  const struct cifs_tcon *tcon)
 {
-	struct smb2_pdu *pdu = (struct smb2_pdu *)hdr;
-	char *temp = (char *)hdr;
-	/* lookup word count ie StructureSize from table */
-	__u16 parmsize = smb2_req_struct_sizes[le16_to_cpu(smb2_cmd)];
-
-	/*
-	 * smaller than SMALL_BUFFER_SIZE but bigger than fixed area of
-	 * largest operations (Create)
-	 */
-	memset(temp, 0, 256);
-
-	/* Note this is only network field converted to big endian */
-	hdr->smb2_buf_length = cpu_to_be32(parmsize + sizeof(struct smb2_hdr)
-			- 4 /*  RFC 1001 length field itself not counted */);
-
-	hdr->ProtocolId = SMB2_PROTO_NUMBER;
-	hdr->StructureSize = cpu_to_le16(64);
-	hdr->Command = smb2_cmd;
+	shdr->ProtocolId = SMB2_PROTO_NUMBER;
+	shdr->StructureSize = cpu_to_le16(64);
+	shdr->Command = smb2_cmd;
 	if (tcon && tcon->ses && tcon->ses->server) {
 		struct TCP_Server_Info *server = tcon->ses->server;
 
 		spin_lock(&server->req_lock);
 		/* Request up to 2 credits but don't go over the limit. */
 		if (server->credits >= server->max_credits)
-			hdr->CreditRequest = cpu_to_le16(0);
+			shdr->CreditRequest = cpu_to_le16(0);
 		else
-			hdr->CreditRequest = cpu_to_le16(
+			shdr->CreditRequest = cpu_to_le16(
 				min_t(int, server->max_credits -
 						server->credits, 2));
 		spin_unlock(&server->req_lock);
 	} else {
-		hdr->CreditRequest = cpu_to_le16(2);
+		shdr->CreditRequest = cpu_to_le16(2);
 	}
-	hdr->ProcessId = cpu_to_le32((__u16)current->tgid);
+	shdr->ProcessId = cpu_to_le32((__u16)current->tgid);
 
 	if (!tcon)
 		goto out;
@@ -124,13 +121,13 @@ smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ ,
 	/* See sections 2.2.4 and 3.2.4.1.5 of MS-SMB2 */
 	if ((tcon->ses) && (tcon->ses->server) &&
 	    (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
-		hdr->CreditCharge = cpu_to_le16(1);
+		shdr->CreditCharge = cpu_to_le16(1);
 	/* else CreditCharge MBZ */
 
-	hdr->TreeId = tcon->tid;
+	shdr->TreeId = tcon->tid;
 	/* Uid is not converted */
 	if (tcon->ses)
-		hdr->SessionId = tcon->ses->Suid;
+		shdr->SessionId = tcon->ses->Suid;
 
 	/*
 	 * If we would set SMB2_FLAGS_DFS_OPERATIONS on open we also would have
@@ -143,12 +140,12 @@ smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ ,
 	 * but it is safer to net set it for now.
 	 */
 /*	if (tcon->share_flags & SHI1005_FLAGS_DFS)
-		hdr->Flags |= SMB2_FLAGS_DFS_OPERATIONS; */
+		shdr->Flags |= SMB2_FLAGS_DFS_OPERATIONS; */
 
-	if (tcon->ses && tcon->ses->server && tcon->ses->server->sign)
-		hdr->Flags |= SMB2_FLAGS_SIGNED;
+	if (tcon->ses && tcon->ses->server && tcon->ses->server->sign &&
+	    !encryption_required(tcon))
+		shdr->Flags |= SMB2_FLAGS_SIGNED;
 out:
-	pdu->StructureSize2 = cpu_to_le16(parmsize);
 	return;
 }
 
@@ -289,16 +286,74 @@ out:
 	return rc;
 }
 
+static void
+fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon, void *buf,
+	       unsigned int *total_len)
+{
+	struct smb2_sync_pdu *spdu = (struct smb2_sync_pdu *)buf;
+	/* lookup word count ie StructureSize from table */
+	__u16 parmsize = smb2_req_struct_sizes[le16_to_cpu(smb2_command)];
+
+	/*
+	 * smaller than SMALL_BUFFER_SIZE but bigger than fixed area of
+	 * largest operations (Create)
+	 */
+	memset(buf, 0, 256);
+
+	smb2_hdr_assemble(&spdu->sync_hdr, smb2_command, tcon);
+	spdu->StructureSize2 = cpu_to_le16(parmsize);
+
+	*total_len = parmsize + sizeof(struct smb2_sync_hdr);
+}
+
+/* init request without RFC1001 length at the beginning */
+static int
+smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
+		    void **request_buf, unsigned int *total_len)
+{
+	int rc;
+	struct smb2_sync_hdr *shdr;
+
+	rc = smb2_reconnect(smb2_command, tcon);
+	if (rc)
+		return rc;
+
+	/* BB eventually switch this to SMB2 specific small buf size */
+	*request_buf = cifs_small_buf_get();
+	if (*request_buf == NULL) {
+		/* BB should we add a retry in here if not a writepage? */
+		return -ENOMEM;
+	}
+
+	shdr = (struct smb2_sync_hdr *)(*request_buf);
+
+	fill_small_buf(smb2_command, tcon, shdr, total_len);
+
+	if (tcon != NULL) {
+#ifdef CONFIG_CIFS_STATS2
+		uint16_t com_code = le16_to_cpu(smb2_command);
+
+		cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_sent[com_code]);
+#endif
+		cifs_stats_inc(&tcon->num_smbs_sent);
+	}
+
+	return rc;
+}
+
 /*
  * Allocate and return pointer to an SMB request hdr, and set basic
  * SMB information in the SMB header. If the return code is zero, this
- * function must have filled in request_buf pointer.
+ * function must have filled in request_buf pointer. The returned buffer
+ * has RFC1001 length at the beginning.
  */
 static int
 small_smb2_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		void **request_buf)
 {
-	int rc = 0;
+	int rc;
+	unsigned int total_len;
+	struct smb2_pdu *pdu;
 
 	rc = smb2_reconnect(smb2_command, tcon);
 	if (rc)
@@ -311,7 +366,12 @@ small_smb2_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		return -ENOMEM;
 	}
 
-	smb2_hdr_assemble((struct smb2_hdr *) *request_buf, smb2_command, tcon);
+	pdu = (struct smb2_pdu *)(*request_buf);
+
+	fill_small_buf(smb2_command, tcon, get_sync_hdr(pdu), &total_len);
+
+	/* Note this is only network field converted to big endian */
+	pdu->hdr.smb2_buf_length = cpu_to_be32(total_len);
 
 	if (tcon != NULL) {
 #ifdef CONFIG_CIFS_STATS2
@@ -376,7 +436,6 @@ static void assemble_neg_contexts(struct smb2_negotiate_req *req)
 }
 #endif /* SMB311 */
 
-
 /*
  *
  *	SMB2 Worker functions follow:
@@ -398,6 +457,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	struct smb2_negotiate_req *req;
 	struct smb2_negotiate_rsp *rsp;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype;
 	struct TCP_Server_Info *server = ses->server;
@@ -416,7 +476,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	if (rc)
 		return rc;
 
-	req->hdr.SessionId = 0;
+	req->hdr.sync_hdr.SessionId = 0;
 
 	req->Dialects[0] = cpu_to_le16(ses->server->vals->protocol_id);
 
@@ -446,9 +506,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	/* 4 for rfc1002 length field */
 	iov[0].iov_len = get_rfc1002_length(req) + 4;
 
-	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, flags);
-
-	rsp = (struct smb2_negotiate_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_negotiate_rsp *)rsp_iov.iov_base;
 	/*
 	 * No tcon so can't do
 	 * cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]);
@@ -627,14 +687,15 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data)
 	if (rc)
 		return rc;
 
-	req->hdr.SessionId = 0; /* First session, not a reauthenticate */
+	/* First session, not a reauthenticate */
+	req->hdr.sync_hdr.SessionId = 0;
 
 	/* if reconnect, we need to send previous sess id, otherwise it is 0 */
 	req->PreviousSessionId = sess_data->previous_session;
 
 	req->Flags = 0; /* MBZ */
 	/* to enable echos and oplocks */
-	req->hdr.CreditRequest = cpu_to_le16(3);
+	req->hdr.sync_hdr.CreditRequest = cpu_to_le16(3);
 
 	/* only one of SMB2 signing flags may be set in SMB2 request */
 	if (server->sign)
@@ -671,6 +732,7 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data)
 {
 	int rc;
 	struct smb2_sess_setup_req *req = sess_data->iov[0].iov_base;
+	struct kvec rsp_iov = { NULL, 0 };
 
 	/* Testing shows that buffer offset must be at location of Buffer[0] */
 	req->SecurityBufferOffset =
@@ -685,7 +747,9 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data)
 	rc = SendReceive2(sess_data->xid, sess_data->ses,
 				sess_data->iov, 2,
 				&sess_data->buf0_type,
-				CIFS_LOG_ERROR | CIFS_NEG_OP);
+				CIFS_LOG_ERROR | CIFS_NEG_OP, &rsp_iov);
+	cifs_small_buf_release(sess_data->iov[0].iov_base);
+	memcpy(&sess_data->iov[0], &rsp_iov, sizeof(struct kvec));
 
 	return rc;
 }
@@ -697,15 +761,13 @@ SMB2_sess_establish_session(struct SMB2_sess_data *sess_data)
 	struct cifs_ses *ses = sess_data->ses;
 
 	mutex_lock(&ses->server->srv_mutex);
-	if (ses->server->sign && ses->server->ops->generate_signingkey) {
+	if (ses->server->ops->generate_signingkey) {
 		rc = ses->server->ops->generate_signingkey(ses);
-		kfree(ses->auth_key.response);
-		ses->auth_key.response = NULL;
 		if (rc) {
 			cifs_dbg(FYI,
 				"SMB3 session key generation failed\n");
 			mutex_unlock(&ses->server->srv_mutex);
-			goto keygen_exit;
+			return rc;
 		}
 	}
 	if (!ses->server->session_estab) {
@@ -719,12 +781,6 @@ SMB2_sess_establish_session(struct SMB2_sess_data *sess_data)
 	ses->status = CifsGood;
 	ses->need_reconnect = false;
 	spin_unlock(&GlobalMid_Lock);
-
-keygen_exit:
-	if (!ses->server->sign) {
-		kfree(ses->auth_key.response);
-		ses->auth_key.response = NULL;
-	}
 	return rc;
 }
 
@@ -781,11 +837,9 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
 		goto out_put_spnego_key;
 
 	rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
-	ses->Suid = rsp->hdr.SessionId;
+	ses->Suid = rsp->hdr.sync_hdr.SessionId;
 
 	ses->session_flags = le16_to_cpu(rsp->SessionFlags);
-	if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
-		cifs_dbg(VFS, "SMB3 encryption not supported yet\n");
 
 	rc = SMB2_sess_establish_session(sess_data);
 out_put_spnego_key:
@@ -859,7 +913,7 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
 
 	/* If true, rc here is expected and not an error */
 	if (sess_data->buf0_type != CIFS_NO_BUFFER &&
-		rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
+		rsp->hdr.sync_hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
 		rc = 0;
 
 	if (rc)
@@ -880,10 +934,8 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
 	cifs_dbg(FYI, "rawntlmssp session setup challenge phase\n");
 
 
-	ses->Suid = rsp->hdr.SessionId;
+	ses->Suid = rsp->hdr.sync_hdr.SessionId;
 	ses->session_flags = le16_to_cpu(rsp->SessionFlags);
-	if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
-		cifs_dbg(VFS, "SMB3 encryption not supported yet\n");
 
 out:
 	kfree(ntlmssp_blob);
@@ -916,7 +968,7 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
 		goto out;
 
 	req = (struct smb2_sess_setup_req *) sess_data->iov[0].iov_base;
-	req->hdr.SessionId = ses->Suid;
+	req->hdr.sync_hdr.SessionId = ses->Suid;
 
 	rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses,
 					sess_data->nls_cp);
@@ -940,10 +992,8 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
 
 	rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
 
-	ses->Suid = rsp->hdr.SessionId;
+	ses->Suid = rsp->hdr.sync_hdr.SessionId;
 	ses->session_flags = le16_to_cpu(rsp->SessionFlags);
-	if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
-		cifs_dbg(VFS, "SMB3 encryption not supported yet\n");
 
 	rc = SMB2_sess_establish_session(sess_data);
 out:
@@ -1018,6 +1068,7 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses)
 	struct smb2_logoff_req *req; /* response is also trivial struct */
 	int rc = 0;
 	struct TCP_Server_Info *server;
+	int flags = 0;
 
 	cifs_dbg(FYI, "disconnect session %p\n", ses);
 
@@ -1035,11 +1086,15 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses)
 		return rc;
 
 	 /* since no tcon, smb2_init can not do this, so do here */
-	req->hdr.SessionId = ses->Suid;
-	if (server->sign)
-		req->hdr.Flags |= SMB2_FLAGS_SIGNED;
+	req->hdr.sync_hdr.SessionId = ses->Suid;
+
+	if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
+		flags |= CIFS_TRANSFORM_REQ;
+	else if (server->sign)
+		req->hdr.sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
 
-	rc = SendReceiveNoRsp(xid, ses, (char *) &req->hdr, 0);
+	rc = SendReceiveNoRsp(xid, ses, (char *) req, flags);
+	cifs_small_buf_release(req);
 	/*
 	 * No tcon so can't do
 	 * cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]);
@@ -1071,11 +1126,13 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	struct smb2_tree_connect_req *req;
 	struct smb2_tree_connect_rsp *rsp = NULL;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype;
 	int unc_path_len;
 	struct TCP_Server_Info *server;
 	__le16 *unc_path = NULL;
+	int flags = 0;
 
 	cifs_dbg(FYI, "TCON\n");
 
@@ -1087,12 +1144,6 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	if (tcon && tcon->bad_network_name)
 		return -ENOENT;
 
-	if ((tcon && tcon->seal) &&
-	    ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) {
-		cifs_dbg(VFS, "encryption requested but no server support");
-		return -EOPNOTSUPP;
-	}
-
 	unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL);
 	if (unc_path == NULL)
 		return -ENOMEM;
@@ -1111,11 +1162,15 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	}
 
 	if (tcon == NULL) {
+		if ((ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA))
+			flags |= CIFS_TRANSFORM_REQ;
+
 		/* since no tcon, smb2_init can not do this, so do here */
-		req->hdr.SessionId = ses->Suid;
+		req->hdr.sync_hdr.SessionId = ses->Suid;
 		/* if (ses->server->sec_mode & SECMODE_SIGN_REQUIRED)
 			req->hdr.Flags |= SMB2_FLAGS_SIGNED; */
-	}
+	} else if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
 
 	iov[0].iov_base = (char *)req;
 	/* 4 for rfc1002 length field and 1 for pad */
@@ -1130,8 +1185,9 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 
 	inc_rfc1001_len(req, unc_path_len - 1 /* pad */);
 
-	rc = SendReceive2(xid, ses, iov, 2, &resp_buftype, 0);
-	rsp = (struct smb2_tree_connect_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
 		if (tcon) {
@@ -1142,7 +1198,7 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	}
 
 	if (tcon == NULL) {
-		ses->ipc_tid = rsp->hdr.TreeId;
+		ses->ipc_tid = rsp->hdr.sync_hdr.TreeId;
 		goto tcon_exit;
 	}
 
@@ -1165,15 +1221,18 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	tcon->maximal_access = le32_to_cpu(rsp->MaximalAccess);
 	tcon->tidStatus = CifsGood;
 	tcon->need_reconnect = false;
-	tcon->tid = rsp->hdr.TreeId;
+	tcon->tid = rsp->hdr.sync_hdr.TreeId;
 	strlcpy(tcon->treeName, tree, sizeof(tcon->treeName));
 
 	if ((rsp->Capabilities & SMB2_SHARE_CAP_DFS) &&
 	    ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0))
 		cifs_dbg(VFS, "DFS capability contradicts DFS flag\n");
+
+	if (tcon->seal &&
+	    !(tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
+		cifs_dbg(VFS, "Encryption is requested but not supported\n");
+
 	init_copy_chunk_defaults(tcon);
-	if (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA)
-		cifs_dbg(VFS, "Encrypted shares not supported");
 	if (tcon->ses->server->ops->validate_negotiate)
 		rc = tcon->ses->server->ops->validate_negotiate(xid, tcon);
 tcon_exit:
@@ -1182,7 +1241,7 @@ tcon_exit:
 	return rc;
 
 tcon_error_exit:
-	if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) {
+	if (rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
 		cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
 		if (tcon)
 			tcon->bad_network_name = true;
@@ -1197,6 +1256,7 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 	int rc = 0;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
+	int flags = 0;
 
 	cifs_dbg(FYI, "Tree Disconnect\n");
 
@@ -1212,7 +1272,11 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 	if (rc)
 		return rc;
 
-	rc = SendReceiveNoRsp(xid, ses, (char *)&req->hdr, 0);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	rc = SendReceiveNoRsp(xid, ses, (char *)req, flags);
+	cifs_small_buf_release(req);
 	if (rc)
 		cifs_stats_fail_inc(tcon, SMB2_TREE_DISCONNECT_HE);
 
@@ -1474,14 +1538,16 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	struct cifs_tcon *tcon = oparms->tcon;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[4];
+	struct kvec rsp_iov;
 	int resp_buftype;
 	int uni_path_len;
 	__le16 *copy_path = NULL;
 	int copy_size;
 	int rc = 0;
-	unsigned int num_iovecs = 2;
+	unsigned int n_iov = 2;
 	__u32 file_attributes = 0;
 	char *dhc_buf = NULL, *lc_buf = NULL;
+	int flags = 0;
 
 	cifs_dbg(FYI, "create/open\n");
 
@@ -1494,6 +1560,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	if (oparms->create_options & CREATE_OPTION_READONLY)
 		file_attributes |= ATTR_READONLY;
 	if (oparms->create_options & CREATE_OPTION_SPECIAL)
@@ -1544,25 +1613,25 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	    *oplock == SMB2_OPLOCK_LEVEL_NONE)
 		req->RequestedOplockLevel = *oplock;
 	else {
-		rc = add_lease_context(server, iov, &num_iovecs, oplock);
+		rc = add_lease_context(server, iov, &n_iov, oplock);
 		if (rc) {
 			cifs_small_buf_release(req);
 			kfree(copy_path);
 			return rc;
 		}
-		lc_buf = iov[num_iovecs-1].iov_base;
+		lc_buf = iov[n_iov-1].iov_base;
 	}
 
 	if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) {
 		/* need to set Next field of lease context if we request it */
 		if (server->capabilities & SMB2_GLOBAL_CAP_LEASING) {
 			struct create_context *ccontext =
-			    (struct create_context *)iov[num_iovecs-1].iov_base;
+			    (struct create_context *)iov[n_iov-1].iov_base;
 			ccontext->Next =
 				cpu_to_le32(server->vals->create_lease_size);
 		}
 
-		rc = add_durable_context(iov, &num_iovecs, oparms,
+		rc = add_durable_context(iov, &n_iov, oparms,
 					tcon->use_persistent);
 		if (rc) {
 			cifs_small_buf_release(req);
@@ -1570,11 +1639,12 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 			kfree(lc_buf);
 			return rc;
 		}
-		dhc_buf = iov[num_iovecs-1].iov_base;
+		dhc_buf = iov[n_iov-1].iov_base;
 	}
 
-	rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0);
-	rsp = (struct smb2_create_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, n_iov, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
 		cifs_stats_fail_inc(tcon, SMB2_CREATE_HE);
@@ -1618,12 +1688,15 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 {
 	struct smb2_ioctl_req *req;
 	struct smb2_ioctl_rsp *rsp;
+	struct smb2_sync_hdr *shdr;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int resp_buftype;
-	int num_iovecs;
+	int n_iov;
 	int rc = 0;
+	int flags = 0;
 
 	cifs_dbg(FYI, "SMB2 IOCTL\n");
 
@@ -1648,6 +1721,9 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	req->CtlCode = cpu_to_le32(opcode);
 	req->PersistentFileId = persistent_fid;
 	req->VolatileFileId = volatile_fid;
@@ -1659,9 +1735,9 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		       cpu_to_le32(offsetof(struct smb2_ioctl_req, Buffer) - 4);
 		iov[1].iov_base = in_data;
 		iov[1].iov_len = indatalen;
-		num_iovecs = 2;
+		n_iov = 2;
 	} else
-		num_iovecs = 1;
+		n_iov = 1;
 
 	req->OutputOffset = 0;
 	req->OutputCount = 0; /* MBZ */
@@ -1698,8 +1774,9 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		iov[0].iov_len = get_rfc1002_length(req) + 4;
 
 
-	rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0);
-	rsp = (struct smb2_ioctl_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, n_iov, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_ioctl_rsp *)rsp_iov.iov_base;
 
 	if ((rc != 0) && (rc != -EINVAL)) {
 		cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
@@ -1742,9 +1819,8 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		goto ioctl_exit;
 	}
 
-	memcpy(*out_data,
-	       (char *)&rsp->hdr.ProtocolId + le32_to_cpu(rsp->OutputOffset),
-	       *plen);
+	shdr = get_sync_hdr(rsp);
+	memcpy(*out_data, (char *)shdr + le32_to_cpu(rsp->OutputOffset), *plen);
 ioctl_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -1784,8 +1860,10 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 	int resp_buftype;
 	int rc = 0;
+	int flags = 0;
 
 	cifs_dbg(FYI, "Close\n");
 
@@ -1798,6 +1876,9 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	req->PersistentFileId = persistent_fid;
 	req->VolatileFileId = volatile_fid;
 
@@ -1805,8 +1886,9 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	/* 4 for rfc1002 length field */
 	iov[0].iov_len = get_rfc1002_length(req) + 4;
 
-	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, 0);
-	rsp = (struct smb2_close_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_close_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
 		cifs_stats_fail_inc(tcon, SMB2_CLOSE_HE);
@@ -1885,10 +1967,12 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	struct smb2_query_info_req *req;
 	struct smb2_query_info_rsp *rsp = NULL;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
+	int flags = 0;
 
 	cifs_dbg(FYI, "Query Info\n");
 
@@ -1901,6 +1985,9 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	req->InfoType = SMB2_O_INFO_FILE;
 	req->FileInfoClass = info_class;
 	req->PersistentFileId = persistent_fid;
@@ -1914,8 +2001,9 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	/* 4 for rfc1002 length field */
 	iov[0].iov_len = get_rfc1002_length(req) + 4;
 
-	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, 0);
-	rsp = (struct smb2_query_info_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
@@ -1963,11 +2051,11 @@ static void
 smb2_echo_callback(struct mid_q_entry *mid)
 {
 	struct TCP_Server_Info *server = mid->callback_data;
-	struct smb2_echo_rsp *smb2 = (struct smb2_echo_rsp *)mid->resp_buf;
+	struct smb2_echo_rsp *rsp = (struct smb2_echo_rsp *)mid->resp_buf;
 	unsigned int credits_received = 1;
 
 	if (mid->mid_state == MID_RESPONSE_RECEIVED)
-		credits_received = le16_to_cpu(smb2->hdr.CreditRequest);
+		credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest);
 
 	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
@@ -2029,9 +2117,9 @@ SMB2_echo(struct TCP_Server_Info *server)
 {
 	struct smb2_echo_req *req;
 	int rc = 0;
-	struct kvec iov;
-	struct smb_rqst rqst = { .rq_iov = &iov,
-				 .rq_nvec = 1 };
+	struct kvec iov[2];
+	struct smb_rqst rqst = { .rq_iov = iov,
+				 .rq_nvec = 2 };
 
 	cifs_dbg(FYI, "In echo request\n");
 
@@ -2045,14 +2133,16 @@ SMB2_echo(struct TCP_Server_Info *server)
 	if (rc)
 		return rc;
 
-	req->hdr.CreditRequest = cpu_to_le16(1);
+	req->hdr.sync_hdr.CreditRequest = cpu_to_le16(1);
 
-	iov.iov_base = (char *)req;
 	/* 4 for rfc1002 length field */
-	iov.iov_len = get_rfc1002_length(req) + 4;
+	iov[0].iov_len = 4;
+	iov[0].iov_base = (char *)req;
+	iov[1].iov_len = get_rfc1002_length(req);
+	iov[1].iov_base = (char *)req + 4;
 
-	rc = cifs_call_async(server, &rqst, NULL, smb2_echo_callback, server,
-			     CIFS_ECHO_OP);
+	rc = cifs_call_async(server, &rqst, NULL, smb2_echo_callback, NULL,
+			     server, CIFS_ECHO_OP);
 	if (rc)
 		cifs_dbg(FYI, "Echo request failed: %d\n", rc);
 
@@ -2068,8 +2158,10 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 	int resp_buftype;
 	int rc = 0;
+	int flags = 0;
 
 	cifs_dbg(FYI, "Flush\n");
 
@@ -2082,6 +2174,9 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	req->PersistentFileId = persistent_fid;
 	req->VolatileFileId = volatile_fid;
 
@@ -2089,12 +2184,13 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	/* 4 for rfc1002 length field */
 	iov[0].iov_len = get_rfc1002_length(req) + 4;
 
-	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, 0);
+	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
 
 	if (rc != 0)
 		cifs_stats_fail_inc(tcon, SMB2_FLUSH_HE);
 
-	free_rsp_buf(resp_buftype, iov[0].iov_base);
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	return rc;
 }
 
@@ -2103,19 +2199,23 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
  * have the end_of_chain boolean set to true.
  */
 static int
-smb2_new_read_req(struct kvec *iov, struct cifs_io_parms *io_parms,
-		  unsigned int remaining_bytes, int request_type)
+smb2_new_read_req(void **buf, unsigned int *total_len,
+		  struct cifs_io_parms *io_parms, unsigned int remaining_bytes,
+		  int request_type)
 {
 	int rc = -EACCES;
-	struct smb2_read_req *req = NULL;
+	struct smb2_read_plain_req *req = NULL;
+	struct smb2_sync_hdr *shdr;
 
-	rc = small_smb2_init(SMB2_READ, io_parms->tcon, (void **) &req);
+	rc = smb2_plain_req_init(SMB2_READ, io_parms->tcon, (void **) &req,
+				 total_len);
 	if (rc)
 		return rc;
 	if (io_parms->tcon->ses->server == NULL)
 		return -ECONNABORTED;
 
-	req->hdr.ProcessId = cpu_to_le32(io_parms->pid);
+	shdr = &req->sync_hdr;
+	shdr->ProcessId = cpu_to_le32(io_parms->pid);
 
 	req->PersistentFileId = io_parms->persistent_fid;
 	req->VolatileFileId = io_parms->volatile_fid;
@@ -2128,19 +2228,19 @@ smb2_new_read_req(struct kvec *iov, struct cifs_io_parms *io_parms,
 
 	if (request_type & CHAINED_REQUEST) {
 		if (!(request_type & END_OF_CHAIN)) {
-			/* 4 for rfc1002 length field */
-			req->hdr.NextCommand =
-				cpu_to_le32(get_rfc1002_length(req) + 4);
+			/* next 8-byte aligned request */
+			*total_len = DIV_ROUND_UP(*total_len, 8) * 8;
+			shdr->NextCommand = cpu_to_le32(*total_len);
 		} else /* END_OF_CHAIN */
-			req->hdr.NextCommand = 0;
+			shdr->NextCommand = 0;
 		if (request_type & RELATED_REQUEST) {
-			req->hdr.Flags |= SMB2_FLAGS_RELATED_OPERATIONS;
+			shdr->Flags |= SMB2_FLAGS_RELATED_OPERATIONS;
 			/*
 			 * Related requests use info from previous read request
 			 * in chain.
 			 */
-			req->hdr.SessionId = 0xFFFFFFFF;
-			req->hdr.TreeId = 0xFFFFFFFF;
+			shdr->SessionId = 0xFFFFFFFF;
+			shdr->TreeId = 0xFFFFFFFF;
 			req->PersistentFileId = 0xFFFFFFFF;
 			req->VolatileFileId = 0xFFFFFFFF;
 		}
@@ -2150,9 +2250,7 @@ smb2_new_read_req(struct kvec *iov, struct cifs_io_parms *io_parms,
 	else
 		req->RemainingBytes = 0;
 
-	iov[0].iov_base = (char *)req;
-	/* 4 for rfc1002 length field */
-	iov[0].iov_len = get_rfc1002_length(req) + 4;
+	*buf = req;
 	return rc;
 }
 
@@ -2162,10 +2260,11 @@ smb2_readv_callback(struct mid_q_entry *mid)
 	struct cifs_readdata *rdata = mid->callback_data;
 	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
-	struct smb2_hdr *buf = (struct smb2_hdr *)rdata->iov.iov_base;
+	struct smb2_sync_hdr *shdr =
+				(struct smb2_sync_hdr *)rdata->iov[1].iov_base;
 	unsigned int credits_received = 1;
-	struct smb_rqst rqst = { .rq_iov = &rdata->iov,
-				 .rq_nvec = 1,
+	struct smb_rqst rqst = { .rq_iov = rdata->iov,
+				 .rq_nvec = 2,
 				 .rq_pages = rdata->pages,
 				 .rq_npages = rdata->nr_pages,
 				 .rq_pagesz = rdata->pagesz,
@@ -2177,9 +2276,9 @@ smb2_readv_callback(struct mid_q_entry *mid)
 
 	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
-		credits_received = le16_to_cpu(buf->CreditRequest);
+		credits_received = le16_to_cpu(shdr->CreditRequest);
 		/* result already set, check signature */
-		if (server->sign) {
+		if (server->sign && !mid->decrypted) {
 			int rc;
 
 			rc = smb2_verify_signature(&rqst, server);
@@ -2216,16 +2315,19 @@ smb2_readv_callback(struct mid_q_entry *mid)
 	add_credits(server, credits_received, 0);
 }
 
-/* smb2_async_readv - send an async write, and set up mid to handle result */
+/* smb2_async_readv - send an async read, and set up mid to handle result */
 int
 smb2_async_readv(struct cifs_readdata *rdata)
 {
 	int rc, flags = 0;
-	struct smb2_hdr *buf;
+	char *buf;
+	struct smb2_sync_hdr *shdr;
 	struct cifs_io_parms io_parms;
-	struct smb_rqst rqst = { .rq_iov = &rdata->iov,
-				 .rq_nvec = 1 };
+	struct smb_rqst rqst = { .rq_iov = rdata->iov,
+				 .rq_nvec = 2 };
 	struct TCP_Server_Info *server;
+	unsigned int total_len;
+	__be32 req_len;
 
 	cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n",
 		 __func__, rdata->offset, rdata->bytes);
@@ -2239,7 +2341,7 @@ smb2_async_readv(struct cifs_readdata *rdata)
 
 	server = io_parms.tcon->ses->server;
 
-	rc = smb2_new_read_req(&rdata->iov, &io_parms, 0, 0);
+	rc = smb2_new_read_req((void **) &buf, &total_len, &io_parms, 0, 0);
 	if (rc) {
 		if (rc == -EAGAIN && rdata->credits) {
 			/* credits was reset by reconnect */
@@ -2252,26 +2354,34 @@ smb2_async_readv(struct cifs_readdata *rdata)
 		return rc;
 	}
 
-	buf = (struct smb2_hdr *)rdata->iov.iov_base;
-	/* 4 for rfc1002 length field */
-	rdata->iov.iov_len = get_rfc1002_length(rdata->iov.iov_base) + 4;
+	if (encryption_required(io_parms.tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req_len = cpu_to_be32(total_len);
+
+	rdata->iov[0].iov_base = &req_len;
+	rdata->iov[0].iov_len = sizeof(__be32);
+	rdata->iov[1].iov_base = buf;
+	rdata->iov[1].iov_len = total_len;
+
+	shdr = (struct smb2_sync_hdr *)buf;
 
 	if (rdata->credits) {
-		buf->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
+		shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
 						SMB2_MAX_BUFFER_SIZE));
-		buf->CreditRequest = buf->CreditCharge;
+		shdr->CreditRequest = shdr->CreditCharge;
 		spin_lock(&server->req_lock);
 		server->credits += rdata->credits -
-						le16_to_cpu(buf->CreditCharge);
+						le16_to_cpu(shdr->CreditCharge);
 		spin_unlock(&server->req_lock);
 		wake_up(&server->request_q);
-		flags = CIFS_HAS_CREDITS;
+		flags |= CIFS_HAS_CREDITS;
 	}
 
 	kref_get(&rdata->refcount);
 	rc = cifs_call_async(io_parms.tcon->ses->server, &rqst,
 			     cifs_readv_receive, smb2_readv_callback,
-			     rdata, flags);
+			     smb3_handle_read_data, rdata, flags);
 	if (rc) {
 		kref_put(&rdata->refcount, cifs_readdata_release);
 		cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE);
@@ -2286,21 +2396,41 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 	  unsigned int *nbytes, char **buf, int *buf_type)
 {
 	int resp_buftype, rc = -EACCES;
+	struct smb2_read_plain_req *req = NULL;
 	struct smb2_read_rsp *rsp = NULL;
-	struct kvec iov[1];
+	struct smb2_sync_hdr *shdr;
+	struct kvec iov[2];
+	struct kvec rsp_iov;
+	unsigned int total_len;
+	__be32 req_len;
+	struct smb_rqst rqst = { .rq_iov = iov,
+				 .rq_nvec = 2 };
+	int flags = CIFS_LOG_ERROR;
+	struct cifs_ses *ses = io_parms->tcon->ses;
 
 	*nbytes = 0;
-	rc = smb2_new_read_req(iov, io_parms, 0, 0);
+	rc = smb2_new_read_req((void **)&req, &total_len, io_parms, 0, 0);
 	if (rc)
 		return rc;
 
-	rc = SendReceive2(xid, io_parms->tcon->ses, iov, 1,
-			  &resp_buftype, CIFS_LOG_ERROR);
+	if (encryption_required(io_parms->tcon))
+		flags |= CIFS_TRANSFORM_REQ;
 
-	rsp = (struct smb2_read_rsp *)iov[0].iov_base;
+	req_len = cpu_to_be32(total_len);
 
-	if (rsp->hdr.Status == STATUS_END_OF_FILE) {
-		free_rsp_buf(resp_buftype, iov[0].iov_base);
+	iov[0].iov_base = &req_len;
+	iov[0].iov_len = sizeof(__be32);
+	iov[1].iov_base = req;
+	iov[1].iov_len = total_len;
+
+	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+
+	rsp = (struct smb2_read_rsp *)rsp_iov.iov_base;
+	shdr = get_sync_hdr(rsp);
+
+	if (shdr->Status == STATUS_END_OF_FILE) {
+		free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 		return 0;
 	}
 
@@ -2319,11 +2449,10 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 	}
 
 	if (*buf) {
-		memcpy(*buf, (char *)&rsp->hdr.ProtocolId + rsp->DataOffset,
-		       *nbytes);
-		free_rsp_buf(resp_buftype, iov[0].iov_base);
+		memcpy(*buf, (char *)shdr + rsp->DataOffset, *nbytes);
+		free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	} else if (resp_buftype != CIFS_NO_BUFFER) {
-		*buf = iov[0].iov_base;
+		*buf = rsp_iov.iov_base;
 		if (resp_buftype == CIFS_SMALL_BUFFER)
 			*buf_type = CIFS_SMALL_BUFFER;
 		else if (resp_buftype == CIFS_LARGE_BUFFER)
@@ -2348,7 +2477,7 @@ smb2_writev_callback(struct mid_q_entry *mid)
 
 	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
-		credits_received = le16_to_cpu(rsp->hdr.CreditRequest);
+		credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest);
 		wdata->result = smb2_check_receive(mid, tcon->ses->server, 0);
 		if (wdata->result != 0)
 			break;
@@ -2394,10 +2523,11 @@ smb2_async_writev(struct cifs_writedata *wdata,
 {
 	int rc = -EACCES, flags = 0;
 	struct smb2_write_req *req = NULL;
+	struct smb2_sync_hdr *shdr;
 	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
-	struct kvec iov;
-	struct smb_rqst rqst;
+	struct kvec iov[2];
+	struct smb_rqst rqst = { };
 
 	rc = small_smb2_init(SMB2_WRITE, tcon, (void **) &req);
 	if (rc) {
@@ -2412,7 +2542,11 @@ smb2_async_writev(struct cifs_writedata *wdata,
 		goto async_writev_out;
 	}
 
-	req->hdr.ProcessId = cpu_to_le32(wdata->cfile->pid);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	shdr = get_sync_hdr(req);
+	shdr->ProcessId = cpu_to_le32(wdata->cfile->pid);
 
 	req->PersistentFileId = wdata->cfile->fid.persistent_fid;
 	req->VolatileFileId = wdata->cfile->fid.volatile_fid;
@@ -2426,11 +2560,13 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	req->RemainingBytes = 0;
 
 	/* 4 for rfc1002 length field and 1 for Buffer */
-	iov.iov_len = get_rfc1002_length(req) + 4 - 1;
-	iov.iov_base = req;
+	iov[0].iov_len = 4;
+	iov[0].iov_base = req;
+	iov[1].iov_len = get_rfc1002_length(req) - 1;
+	iov[1].iov_base = (char *)req + 4;
 
-	rqst.rq_iov = &iov;
-	rqst.rq_nvec = 1;
+	rqst.rq_iov = iov;
+	rqst.rq_nvec = 2;
 	rqst.rq_pages = wdata->pages;
 	rqst.rq_npages = wdata->nr_pages;
 	rqst.rq_pagesz = wdata->pagesz;
@@ -2444,20 +2580,20 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	inc_rfc1001_len(&req->hdr, wdata->bytes - 1 /* Buffer */);
 
 	if (wdata->credits) {
-		req->hdr.CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes,
+		shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes,
 						    SMB2_MAX_BUFFER_SIZE));
-		req->hdr.CreditRequest = req->hdr.CreditCharge;
+		shdr->CreditRequest = shdr->CreditCharge;
 		spin_lock(&server->req_lock);
 		server->credits += wdata->credits -
-					le16_to_cpu(req->hdr.CreditCharge);
+						le16_to_cpu(shdr->CreditCharge);
 		spin_unlock(&server->req_lock);
 		wake_up(&server->request_q);
-		flags = CIFS_HAS_CREDITS;
+		flags |= CIFS_HAS_CREDITS;
 	}
 
 	kref_get(&wdata->refcount);
-	rc = cifs_call_async(server, &rqst, NULL, smb2_writev_callback, wdata,
-			     flags);
+	rc = cifs_call_async(server, &rqst, NULL, smb2_writev_callback, NULL,
+			     wdata, flags);
 
 	if (rc) {
 		kref_put(&wdata->refcount, release);
@@ -2483,6 +2619,9 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	struct smb2_write_req *req = NULL;
 	struct smb2_write_rsp *rsp = NULL;
 	int resp_buftype;
+	struct kvec rsp_iov;
+	int flags = 0;
+
 	*nbytes = 0;
 
 	if (n_vec < 1)
@@ -2495,7 +2634,10 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	if (io_parms->tcon->ses->server == NULL)
 		return -ECONNABORTED;
 
-	req->hdr.ProcessId = cpu_to_le32(io_parms->pid);
+	if (encryption_required(io_parms->tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req->hdr.sync_hdr.ProcessId = cpu_to_le32(io_parms->pid);
 
 	req->PersistentFileId = io_parms->persistent_fid;
 	req->VolatileFileId = io_parms->volatile_fid;
@@ -2517,8 +2659,9 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	inc_rfc1001_len(req, io_parms->length - 1 /* Buffer */);
 
 	rc = SendReceive2(xid, io_parms->tcon->ses, iov, n_vec + 1,
-			  &resp_buftype, 0);
-	rsp = (struct smb2_write_rsp *)iov[0].iov_base;
+			  &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_write_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
 		cifs_stats_fail_inc(io_parms->tcon, SMB2_WRITE_HE);
@@ -2581,6 +2724,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	struct smb2_query_directory_req *req;
 	struct smb2_query_directory_rsp *rsp = NULL;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int rc = 0;
 	int len;
 	int resp_buftype = CIFS_NO_BUFFER;
@@ -2591,6 +2735,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	char *end_of_smb;
 	unsigned int output_size = CIFSMaxBufSize;
 	size_t info_buf_size;
+	int flags = 0;
 
 	if (ses && (ses->server))
 		server = ses->server;
@@ -2601,6 +2746,9 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	switch (srch_inf->info_level) {
 	case SMB_FIND_FILE_DIRECTORY_INFO:
 		req->FileInformationClass = FILE_DIRECTORY_INFORMATION;
@@ -2645,11 +2793,13 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 
 	inc_rfc1001_len(req, len - 1 /* Buffer */);
 
-	rc = SendReceive2(xid, ses, iov, 2, &resp_buftype, 0);
-	rsp = (struct smb2_query_directory_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_query_directory_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
-		if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) {
+		if (rc == -ENODATA &&
+		    rsp->hdr.sync_hdr.Status == STATUS_NO_MORE_FILES) {
 			srch_inf->endOfSearch = true;
 			rc = 0;
 		}
@@ -2705,11 +2855,13 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 	struct smb2_set_info_req *req;
 	struct smb2_set_info_rsp *rsp = NULL;
 	struct kvec *iov;
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype;
 	unsigned int i;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
+	int flags = 0;
 
 	if (ses && (ses->server))
 		server = ses->server;
@@ -2729,7 +2881,10 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 		return rc;
 	}
 
-	req->hdr.ProcessId = cpu_to_le32(pid);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req->hdr.sync_hdr.ProcessId = cpu_to_le32(pid);
 
 	req->InfoType = SMB2_O_INFO_FILE;
 	req->FileInfoClass = info_class;
@@ -2756,8 +2911,9 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 		iov[i].iov_len = size[i];
 	}
 
-	rc = SendReceive2(xid, ses, iov, num, &resp_buftype, 0);
-	rsp = (struct smb2_set_info_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, num, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0)
 		cifs_stats_fail_inc(tcon, SMB2_SET_INFO_HE);
@@ -2885,20 +3041,23 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	int rc;
 	struct smb2_oplock_break *req = NULL;
+	int flags = CIFS_OBREAK_OP;
 
 	cifs_dbg(FYI, "SMB2_oplock_break\n");
 	rc = small_smb2_init(SMB2_OPLOCK_BREAK, tcon, (void **) &req);
-
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	req->VolatileFid = volatile_fid;
 	req->PersistentFid = persistent_fid;
 	req->OplockLevel = oplock_level;
-	req->hdr.CreditRequest = cpu_to_le16(1);
+	req->hdr.sync_hdr.CreditRequest = cpu_to_le16(1);
 
-	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) req, CIFS_OBREAK_OP);
-	/* SMB2 buffer freed by function above */
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) req, flags);
+	cifs_small_buf_release(req);
 
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE);
@@ -2958,10 +3117,12 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct smb2_query_info_rsp *rsp = NULL;
 	struct kvec iov;
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype;
 	struct cifs_ses *ses = tcon->ses;
 	struct smb2_fs_full_size_info *info = NULL;
+	int flags = 0;
 
 	rc = build_qfs_info_req(&iov, tcon, FS_FULL_SIZE_INFORMATION,
 				sizeof(struct smb2_fs_full_size_info),
@@ -2969,12 +3130,16 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	rc = SendReceive2(xid, ses, &iov, 1, &resp_buftype, 0);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	rc = SendReceive2(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(iov.iov_base);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto qfsinf_exit;
 	}
-	rsp = (struct smb2_query_info_rsp *)iov.iov_base;
+	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
 
 	info = (struct smb2_fs_full_size_info *)(4 /* RFC1001 len */ +
 		le16_to_cpu(rsp->OutputBufferOffset) + (char *)&rsp->hdr);
@@ -2985,7 +3150,7 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 		copy_fs_info_to_kstatfs(info, fsdata);
 
 qfsinf_exit:
-	free_rsp_buf(resp_buftype, iov.iov_base);
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	return rc;
 }
 
@@ -2995,10 +3160,12 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct smb2_query_info_rsp *rsp = NULL;
 	struct kvec iov;
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype, max_len, min_len;
 	struct cifs_ses *ses = tcon->ses;
 	unsigned int rsp_len, offset;
+	int flags = 0;
 
 	if (level == FS_DEVICE_INFORMATION) {
 		max_len = sizeof(FILE_SYSTEM_DEVICE_INFO);
@@ -3019,12 +3186,16 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	rc = SendReceive2(xid, ses, &iov, 1, &resp_buftype, 0);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	rc = SendReceive2(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(iov.iov_base);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto qfsattr_exit;
 	}
-	rsp = (struct smb2_query_info_rsp *)iov.iov_base;
+	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
 
 	rsp_len = le32_to_cpu(rsp->OutputBufferLength);
 	offset = le16_to_cpu(rsp->OutputBufferOffset);
@@ -3048,7 +3219,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	}
 
 qfsattr_exit:
-	free_rsp_buf(resp_buftype, iov.iov_base);
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	return rc;
 }
 
@@ -3060,8 +3231,10 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	struct smb2_lock_req *req = NULL;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int resp_buf_type;
 	unsigned int count;
+	int flags = CIFS_NO_RESP;
 
 	cifs_dbg(FYI, "smb2_lockv num lock %d\n", num_lock);
 
@@ -3069,7 +3242,10 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	req->hdr.ProcessId = cpu_to_le32(pid);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req->hdr.sync_hdr.ProcessId = cpu_to_le32(pid);
 	req->LockCount = cpu_to_le16(num_lock);
 
 	req->PersistentFileId = persist_fid;
@@ -3085,7 +3261,9 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	iov[1].iov_len = count;
 
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_locks);
-	rc = SendReceive2(xid, tcon->ses, iov, 2, &resp_buf_type, CIFS_NO_RESP);
+	rc = SendReceive2(xid, tcon->ses, iov, 2, &resp_buf_type, flags,
+			  &rsp_iov);
+	cifs_small_buf_release(req);
 	if (rc) {
 		cifs_dbg(FYI, "Send error in smb2_lockv = %d\n", rc);
 		cifs_stats_fail_inc(tcon, SMB2_LOCK_HE);
@@ -3117,22 +3295,25 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	int rc;
 	struct smb2_lease_ack *req = NULL;
+	int flags = CIFS_OBREAK_OP;
 
 	cifs_dbg(FYI, "SMB2_lease_break\n");
 	rc = small_smb2_init(SMB2_OPLOCK_BREAK, tcon, (void **) &req);
-
 	if (rc)
 		return rc;
 
-	req->hdr.CreditRequest = cpu_to_le16(1);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req->hdr.sync_hdr.CreditRequest = cpu_to_le16(1);
 	req->StructureSize = cpu_to_le16(36);
 	inc_rfc1001_len(req, 12);
 
 	memcpy(req->LeaseKey, lease_key, 16);
 	req->LeaseState = lease_state;
 
-	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) req, CIFS_OBREAK_OP);
-	/* SMB2 buffer freed by function above */
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) req, flags);
+	cifs_small_buf_release(req);
 
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE);
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index dc0d141f33e2..c03b252501a1 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -101,10 +101,7 @@
 
 #define SMB2_HEADER_STRUCTURE_SIZE cpu_to_le16(64)
 
-struct smb2_hdr {
-	__be32 smb2_buf_length;	/* big endian on wire */
-				/* length is only two or three bytes - with
-				 one or two byte type preceding it that MBZ */
+struct smb2_sync_hdr {
 	__le32 ProtocolId;	/* 0xFE 'S' 'M' 'B' */
 	__le16 StructureSize;	/* 64 */
 	__le16 CreditCharge;	/* MBZ */
@@ -120,16 +117,31 @@ struct smb2_hdr {
 	__u8   Signature[16];
 } __packed;
 
+struct smb2_sync_pdu {
+	struct smb2_sync_hdr sync_hdr;
+	__le16 StructureSize2; /* size of wct area (varies, request specific) */
+} __packed;
+
+struct smb2_hdr {
+	__be32 smb2_buf_length;	/* big endian on wire */
+				/* length is only two or three bytes - with */
+				/* one or two byte type preceding it that MBZ */
+	struct smb2_sync_hdr sync_hdr;
+} __packed;
+
 struct smb2_pdu {
 	struct smb2_hdr hdr;
 	__le16 StructureSize2; /* size of wct area (varies, request specific) */
 } __packed;
 
+#define SMB3_AES128CMM_NONCE 11
+#define SMB3_AES128GCM_NONCE 12
+
 struct smb2_transform_hdr {
 	__be32 smb2_buf_length;	/* big endian on wire */
 				/* length is only two or three bytes - with
 				 one or two byte type preceding it that MBZ */
-	__u8   ProtocolId[4];	/* 0xFD 'S' 'M' 'B' */
+	__le32 ProtocolId;	/* 0xFD 'S' 'M' 'B' */
 	__u8   Signature[16];
 	__u8   Nonce[16];
 	__le32 OriginalMessageSize;
@@ -814,8 +826,9 @@ struct smb2_flush_rsp {
 #define SMB2_CHANNEL_RDMA_V1		0x00000001 /* SMB3 or later */
 #define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000001 /* SMB3.02 or later */
 
-struct smb2_read_req {
-	struct smb2_hdr hdr;
+/* SMB2 read request without RFC1001 length at the beginning */
+struct smb2_read_plain_req {
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 49 */
 	__u8   Padding; /* offset from start of SMB2 header to place read */
 	__u8   Flags; /* MBZ unless SMB3.02 or later */
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index f2d511a6971b..85fc7a789334 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -56,6 +56,10 @@ extern void smb2_echo_request(struct work_struct *work);
 extern __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode);
 extern bool smb2_is_valid_oplock_break(char *buffer,
 				       struct TCP_Server_Info *srv);
+extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
+					  __u64 ses_id);
+extern int smb3_handle_read_data(struct TCP_Server_Info *server,
+				 struct mid_q_entry *mid);
 
 extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst,
 				   struct smb2_file_all_info *src);
@@ -97,6 +101,7 @@ extern int smb2_unlock_range(struct cifsFileInfo *cfile,
 			     struct file_lock *flock, const unsigned int xid);
 extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile);
 extern void smb2_reconnect_server(struct work_struct *work);
+extern int smb3_crypto_aead_allocate(struct TCP_Server_Info *server);
 
 /*
  * SMB2 Worker functions - most of protocol specific implementation details
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index bc9a7b634643..7c3bb1bd7eed 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -31,6 +31,7 @@
 #include <asm/processor.h>
 #include <linux/mempool.h>
 #include <linux/highmem.h>
+#include <crypto/aead.h>
 #include "smb2pdu.h"
 #include "cifsglob.h"
 #include "cifsproto.h"
@@ -114,14 +115,14 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server)
 	return 0;
 }
 
-static struct cifs_ses *
-smb2_find_smb_ses(struct smb2_hdr *smb2hdr, struct TCP_Server_Info *server)
+struct cifs_ses *
+smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
 {
 	struct cifs_ses *ses;
 
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
-		if (ses->Suid != smb2hdr->SessionId)
+		if (ses->Suid != ses_id)
 			continue;
 		spin_unlock(&cifs_tcp_ses_lock);
 		return ses;
@@ -131,7 +132,6 @@ smb2_find_smb_ses(struct smb2_hdr *smb2hdr, struct TCP_Server_Info *server)
 	return NULL;
 }
 
-
 int
 smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 {
@@ -139,17 +139,17 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	unsigned char smb2_signature[SMB2_HMACSHA256_SIZE];
 	unsigned char *sigptr = smb2_signature;
 	struct kvec *iov = rqst->rq_iov;
-	struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[1].iov_base;
 	struct cifs_ses *ses;
 
-	ses = smb2_find_smb_ses(smb2_pdu, server);
+	ses = smb2_find_smb_ses(server, shdr->SessionId);
 	if (!ses) {
 		cifs_dbg(VFS, "%s: Could not find session\n", __func__);
 		return 0;
 	}
 
 	memset(smb2_signature, 0x0, SMB2_HMACSHA256_SIZE);
-	memset(smb2_pdu->Signature, 0x0, SMB2_SIGNATURE_SIZE);
+	memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE);
 
 	rc = smb2_crypto_shash_allocate(server);
 	if (rc) {
@@ -174,7 +174,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 		&server->secmech.sdeschmacsha256->shash);
 
 	if (!rc)
-		memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE);
+		memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE);
 
 	return rc;
 }
@@ -356,17 +356,17 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	unsigned char smb3_signature[SMB2_CMACAES_SIZE];
 	unsigned char *sigptr = smb3_signature;
 	struct kvec *iov = rqst->rq_iov;
-	struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[1].iov_base;
 	struct cifs_ses *ses;
 
-	ses = smb2_find_smb_ses(smb2_pdu, server);
+	ses = smb2_find_smb_ses(server, shdr->SessionId);
 	if (!ses) {
 		cifs_dbg(VFS, "%s: Could not find session\n", __func__);
 		return 0;
 	}
 
 	memset(smb3_signature, 0x0, SMB2_CMACAES_SIZE);
-	memset(smb2_pdu->Signature, 0x0, SMB2_SIGNATURE_SIZE);
+	memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE);
 
 	rc = crypto_shash_setkey(server->secmech.cmacaes,
 		ses->smb3signingkey, SMB2_CMACAES_SIZE);
@@ -391,7 +391,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 				   &server->secmech.sdesccmacaes->shash);
 
 	if (!rc)
-		memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE);
+		memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE);
 
 	return rc;
 }
@@ -401,14 +401,15 @@ static int
 smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 {
 	int rc = 0;
-	struct smb2_hdr *smb2_pdu = rqst->rq_iov[0].iov_base;
+	struct smb2_sync_hdr *shdr =
+			(struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
 
-	if (!(smb2_pdu->Flags & SMB2_FLAGS_SIGNED) ||
+	if (!(shdr->Flags & SMB2_FLAGS_SIGNED) ||
 	    server->tcpStatus == CifsNeedNegotiate)
 		return rc;
 
 	if (!server->session_estab) {
-		strncpy(smb2_pdu->Signature, "BSRSPYL", 8);
+		strncpy(shdr->Signature, "BSRSPYL", 8);
 		return rc;
 	}
 
@@ -422,11 +423,12 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 {
 	unsigned int rc;
 	char server_response_sig[16];
-	struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
+	struct smb2_sync_hdr *shdr =
+			(struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
 
-	if ((smb2_pdu->Command == SMB2_NEGOTIATE) ||
-	    (smb2_pdu->Command == SMB2_SESSION_SETUP) ||
-	    (smb2_pdu->Command == SMB2_OPLOCK_BREAK) ||
+	if ((shdr->Command == SMB2_NEGOTIATE) ||
+	    (shdr->Command == SMB2_SESSION_SETUP) ||
+	    (shdr->Command == SMB2_OPLOCK_BREAK) ||
 	    (!server->session_estab))
 		return 0;
 
@@ -436,17 +438,17 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	 */
 
 	/* Do not need to verify session setups with signature "BSRSPYL " */
-	if (memcmp(smb2_pdu->Signature, "BSRSPYL ", 8) == 0)
+	if (memcmp(shdr->Signature, "BSRSPYL ", 8) == 0)
 		cifs_dbg(FYI, "dummy signature received for smb command 0x%x\n",
-			 smb2_pdu->Command);
+			 shdr->Command);
 
 	/*
 	 * Save off the origiginal signature so we can modify the smb and check
 	 * our calculated signature against what the server sent.
 	 */
-	memcpy(server_response_sig, smb2_pdu->Signature, SMB2_SIGNATURE_SIZE);
+	memcpy(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE);
 
-	memset(smb2_pdu->Signature, 0, SMB2_SIGNATURE_SIZE);
+	memset(shdr->Signature, 0, SMB2_SIGNATURE_SIZE);
 
 	mutex_lock(&server->srv_mutex);
 	rc = server->ops->calc_signature(rqst, server);
@@ -455,8 +457,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	if (rc)
 		return rc;
 
-	if (memcmp(server_response_sig, smb2_pdu->Signature,
-		   SMB2_SIGNATURE_SIZE))
+	if (memcmp(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE))
 		return -EACCES;
 	else
 		return 0;
@@ -467,18 +468,19 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
  * and when srv_mutex is held.
  */
 static inline void
-smb2_seq_num_into_buf(struct TCP_Server_Info *server, struct smb2_hdr *hdr)
+smb2_seq_num_into_buf(struct TCP_Server_Info *server,
+		      struct smb2_sync_hdr *shdr)
 {
-	unsigned int i, num = le16_to_cpu(hdr->CreditCharge);
+	unsigned int i, num = le16_to_cpu(shdr->CreditCharge);
 
-	hdr->MessageId = get_next_mid64(server);
+	shdr->MessageId = get_next_mid64(server);
 	/* skip message numbers according to CreditCharge field */
 	for (i = 1; i < num; i++)
 		get_next_mid(server);
 }
 
 static struct mid_q_entry *
-smb2_mid_entry_alloc(const struct smb2_hdr *smb_buffer,
+smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr,
 		     struct TCP_Server_Info *server)
 {
 	struct mid_q_entry *temp;
@@ -493,9 +495,9 @@ smb2_mid_entry_alloc(const struct smb2_hdr *smb_buffer,
 		return temp;
 	else {
 		memset(temp, 0, sizeof(struct mid_q_entry));
-		temp->mid = le64_to_cpu(smb_buffer->MessageId);
+		temp->mid = le64_to_cpu(shdr->MessageId);
 		temp->pid = current->pid;
-		temp->command = smb_buffer->Command;	/* Always LE */
+		temp->command = shdr->Command; /* Always LE */
 		temp->when_alloc = jiffies;
 		temp->server = server;
 
@@ -513,7 +515,7 @@ smb2_mid_entry_alloc(const struct smb2_hdr *smb_buffer,
 }
 
 static int
-smb2_get_mid_entry(struct cifs_ses *ses, struct smb2_hdr *buf,
+smb2_get_mid_entry(struct cifs_ses *ses, struct smb2_sync_hdr *shdr,
 		   struct mid_q_entry **mid)
 {
 	if (ses->server->tcpStatus == CifsExiting)
@@ -525,19 +527,19 @@ smb2_get_mid_entry(struct cifs_ses *ses, struct smb2_hdr *buf,
 	}
 
 	if (ses->status == CifsNew) {
-		if ((buf->Command != SMB2_SESSION_SETUP) &&
-		    (buf->Command != SMB2_NEGOTIATE))
+		if ((shdr->Command != SMB2_SESSION_SETUP) &&
+		    (shdr->Command != SMB2_NEGOTIATE))
 			return -EAGAIN;
 		/* else ok - we are setting up session */
 	}
 
 	if (ses->status == CifsExiting) {
-		if (buf->Command != SMB2_LOGOFF)
+		if (shdr->Command != SMB2_LOGOFF)
 			return -EAGAIN;
 		/* else ok - we are shutting down the session */
 	}
 
-	*mid = smb2_mid_entry_alloc(buf, ses->server);
+	*mid = smb2_mid_entry_alloc(shdr, ses->server);
 	if (*mid == NULL)
 		return -ENOMEM;
 	spin_lock(&GlobalMid_Lock);
@@ -551,16 +553,18 @@ smb2_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
 		   bool log_error)
 {
 	unsigned int len = get_rfc1002_length(mid->resp_buf);
-	struct kvec iov;
-	struct smb_rqst rqst = { .rq_iov = &iov,
-				 .rq_nvec = 1 };
+	struct kvec iov[2];
+	struct smb_rqst rqst = { .rq_iov = iov,
+				 .rq_nvec = 2 };
 
-	iov.iov_base = (char *)mid->resp_buf;
-	iov.iov_len = get_rfc1002_length(mid->resp_buf) + 4;
+	iov[0].iov_base = (char *)mid->resp_buf;
+	iov[0].iov_len = 4;
+	iov[1].iov_base = (char *)mid->resp_buf + 4;
+	iov[1].iov_len = len;
 
 	dump_smb(mid->resp_buf, min_t(u32, 80, len));
 	/* convert the length into a more usable form */
-	if (len > 24 && server->sign) {
+	if (len > 24 && server->sign && !mid->decrypted) {
 		int rc;
 
 		rc = smb2_verify_signature(&rqst, server);
@@ -576,12 +580,13 @@ struct mid_q_entry *
 smb2_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
 {
 	int rc;
-	struct smb2_hdr *hdr = (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
+	struct smb2_sync_hdr *shdr =
+			(struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
 	struct mid_q_entry *mid;
 
-	smb2_seq_num_into_buf(ses->server, hdr);
+	smb2_seq_num_into_buf(ses->server, shdr);
 
-	rc = smb2_get_mid_entry(ses, hdr, &mid);
+	rc = smb2_get_mid_entry(ses, shdr, &mid);
 	if (rc)
 		return ERR_PTR(rc);
 	rc = smb2_sign_rqst(rqst, ses->server);
@@ -596,12 +601,13 @@ struct mid_q_entry *
 smb2_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 {
 	int rc;
-	struct smb2_hdr *hdr = (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
+	struct smb2_sync_hdr *shdr =
+			(struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
 	struct mid_q_entry *mid;
 
-	smb2_seq_num_into_buf(server, hdr);
+	smb2_seq_num_into_buf(server, shdr);
 
-	mid = smb2_mid_entry_alloc(hdr, server);
+	mid = smb2_mid_entry_alloc(shdr, server);
 	if (mid == NULL)
 		return ERR_PTR(-ENOMEM);
 
@@ -613,3 +619,33 @@ smb2_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 
 	return mid;
 }
+
+int
+smb3_crypto_aead_allocate(struct TCP_Server_Info *server)
+{
+	struct crypto_aead *tfm;
+
+	if (!server->secmech.ccmaesencrypt) {
+		tfm = crypto_alloc_aead("ccm(aes)", 0, 0);
+		if (IS_ERR(tfm)) {
+			cifs_dbg(VFS, "%s: Failed to alloc encrypt aead\n",
+				 __func__);
+			return PTR_ERR(tfm);
+		}
+		server->secmech.ccmaesencrypt = tfm;
+	}
+
+	if (!server->secmech.ccmaesdecrypt) {
+		tfm = crypto_alloc_aead("ccm(aes)", 0, 0);
+		if (IS_ERR(tfm)) {
+			crypto_free_aead(server->secmech.ccmaesencrypt);
+			server->secmech.ccmaesencrypt = NULL;
+			cifs_dbg(VFS, "%s: Failed to alloc decrypt aead\n",
+				 __func__);
+			return PTR_ERR(tfm);
+		}
+		server->secmech.ccmaesdecrypt = tfm;
+	}
+
+	return 0;
+}
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index fbb84c08e3cd..526f0533cb4e 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -221,7 +221,7 @@ rqst_len(struct smb_rqst *rqst)
 }
 
 static int
-smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
+__smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 {
 	int rc;
 	struct kvec *iov = rqst->rq_iov;
@@ -245,8 +245,12 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 		return -EIO;
 	}
 
+	if (n_vec < 2)
+		return -EIO;
+
 	cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length);
 	dump_smb(iov[0].iov_base, iov[0].iov_len);
+	dump_smb(iov[1].iov_base, iov[1].iov_len);
 
 	/* cork the socket */
 	kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
@@ -309,24 +313,43 @@ uncork:
 }
 
 static int
-smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
+smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst, int flags)
 {
-	struct smb_rqst rqst = { .rq_iov = iov,
-				 .rq_nvec = n_vec };
+	struct smb_rqst cur_rqst;
+	int rc;
+
+	if (!(flags & CIFS_TRANSFORM_REQ))
+		return __smb_send_rqst(server, rqst);
+
+	if (!server->ops->init_transform_rq ||
+	    !server->ops->free_transform_rq) {
+		cifs_dbg(VFS, "Encryption requested but transform callbacks are missed\n");
+		return -EIO;
+	}
+
+	rc = server->ops->init_transform_rq(server, &cur_rqst, rqst);
+	if (rc)
+		return rc;
 
-	return smb_send_rqst(server, &rqst);
+	rc = __smb_send_rqst(server, &cur_rqst);
+	server->ops->free_transform_rq(&cur_rqst);
+	return rc;
 }
 
 int
 smb_send(struct TCP_Server_Info *server, struct smb_hdr *smb_buffer,
 	 unsigned int smb_buf_length)
 {
-	struct kvec iov;
+	struct kvec iov[2];
+	struct smb_rqst rqst = { .rq_iov = iov,
+				 .rq_nvec = 2 };
 
-	iov.iov_base = smb_buffer;
-	iov.iov_len = smb_buf_length + 4;
+	iov[0].iov_base = smb_buffer;
+	iov[0].iov_len = 4;
+	iov[1].iov_base = (char *)smb_buffer + 4;
+	iov[1].iov_len = smb_buf_length;
 
-	return smb_sendv(server, &iov, 1);
+	return __smb_send_rqst(server, &rqst);
 }
 
 static int
@@ -454,6 +477,10 @@ cifs_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 	struct smb_hdr *hdr = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
 	struct mid_q_entry *mid;
 
+	if (rqst->rq_iov[0].iov_len != 4 ||
+	    rqst->rq_iov[0].iov_base + 4 != rqst->rq_iov[1].iov_base)
+		return ERR_PTR(-EIO);
+
 	/* enable signing if server requires it */
 	if (server->sign)
 		hdr->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
@@ -478,7 +505,7 @@ cifs_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 int
 cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 		mid_receive_t *receive, mid_callback_t *callback,
-		void *cbdata, const int flags)
+		mid_handle_t *handle, void *cbdata, const int flags)
 {
 	int rc, timeout, optype;
 	struct mid_q_entry *mid;
@@ -505,6 +532,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 	mid->receive = receive;
 	mid->callback = callback;
 	mid->callback_data = cbdata;
+	mid->handle = handle;
 	mid->mid_state = MID_REQUEST_SUBMITTED;
 
 	/* put it on the pending_mid_q */
@@ -514,7 +542,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 
 
 	cifs_in_send_inc(server);
-	rc = smb_send_rqst(server, rqst);
+	rc = smb_send_rqst(server, rqst, flags);
 	cifs_in_send_dec(server);
 	cifs_save_when_sent(mid);
 
@@ -547,12 +575,13 @@ SendReceiveNoRsp(const unsigned int xid, struct cifs_ses *ses,
 {
 	int rc;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 	int resp_buf_type;
 
 	iov[0].iov_base = in_buf;
 	iov[0].iov_len = get_rfc1002_length(in_buf) + 4;
 	flags |= CIFS_NO_RESP;
-	rc = SendReceive2(xid, ses, iov, 1, &resp_buf_type, flags);
+	rc = SendReceive2(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov);
 	cifs_dbg(NOISY, "SendRcvNoRsp flags %d rc %d\n", flags, rc);
 
 	return rc;
@@ -595,10 +624,11 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
 }
 
 static inline int
-send_cancel(struct TCP_Server_Info *server, void *buf, struct mid_q_entry *mid)
+send_cancel(struct TCP_Server_Info *server, struct smb_rqst *rqst,
+	    struct mid_q_entry *mid)
 {
 	return server->ops->send_cancel ?
-				server->ops->send_cancel(server, buf, mid) : 0;
+				server->ops->send_cancel(server, rqst, mid) : 0;
 }
 
 int
@@ -611,13 +641,15 @@ cifs_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
 
 	/* convert the length into a more usable form */
 	if (server->sign) {
-		struct kvec iov;
+		struct kvec iov[2];
 		int rc = 0;
-		struct smb_rqst rqst = { .rq_iov = &iov,
-					 .rq_nvec = 1 };
+		struct smb_rqst rqst = { .rq_iov = iov,
+					 .rq_nvec = 2 };
 
-		iov.iov_base = mid->resp_buf;
-		iov.iov_len = len;
+		iov[0].iov_base = mid->resp_buf;
+		iov[0].iov_len = 4;
+		iov[1].iov_base = (char *)mid->resp_buf + 4;
+		iov[1].iov_len = len - 4;
 		/* FIXME: add code to kill session */
 		rc = cifs_verify_signature(&rqst, server,
 					   mid->sequence_number);
@@ -637,6 +669,10 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
 	struct smb_hdr *hdr = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
 	struct mid_q_entry *mid;
 
+	if (rqst->rq_iov[0].iov_len != 4 ||
+	    rqst->rq_iov[0].iov_base + 4 != rqst->rq_iov[1].iov_base)
+		return ERR_PTR(-EIO);
+
 	rc = allocate_mid(ses, hdr, &mid);
 	if (rc)
 		return ERR_PTR(rc);
@@ -649,17 +685,15 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
 }
 
 int
-SendReceive2(const unsigned int xid, struct cifs_ses *ses,
-	     struct kvec *iov, int n_vec, int *resp_buf_type /* ret */,
-	     const int flags)
+cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
+	       struct smb_rqst *rqst, int *resp_buf_type, const int flags,
+	       struct kvec *resp_iov)
 {
 	int rc = 0;
 	int timeout, optype;
 	struct mid_q_entry *midQ;
-	char *buf = iov[0].iov_base;
 	unsigned int credits = 1;
-	struct smb_rqst rqst = { .rq_iov = iov,
-				 .rq_nvec = n_vec };
+	char *buf;
 
 	timeout = flags & CIFS_TIMEOUT_MASK;
 	optype = flags & CIFS_OP_MASK;
@@ -667,15 +701,12 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	*resp_buf_type = CIFS_NO_BUFFER;  /* no response buf yet */
 
 	if ((ses == NULL) || (ses->server == NULL)) {
-		cifs_small_buf_release(buf);
 		cifs_dbg(VFS, "Null session\n");
 		return -EIO;
 	}
 
-	if (ses->server->tcpStatus == CifsExiting) {
-		cifs_small_buf_release(buf);
+	if (ses->server->tcpStatus == CifsExiting)
 		return -ENOENT;
-	}
 
 	/*
 	 * Ensure that we do not send more than 50 overlapping requests
@@ -684,10 +715,8 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	 */
 
 	rc = wait_for_free_request(ses->server, timeout, optype);
-	if (rc) {
-		cifs_small_buf_release(buf);
+	if (rc)
 		return rc;
-	}
 
 	/*
 	 * Make sure that we sign in the same order that we send on this socket
@@ -697,10 +726,9 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 
 	mutex_lock(&ses->server->srv_mutex);
 
-	midQ = ses->server->ops->setup_request(ses, &rqst);
+	midQ = ses->server->ops->setup_request(ses, rqst);
 	if (IS_ERR(midQ)) {
 		mutex_unlock(&ses->server->srv_mutex);
-		cifs_small_buf_release(buf);
 		/* Update # of requests on wire to server */
 		add_credits(ses->server, 1, optype);
 		return PTR_ERR(midQ);
@@ -708,7 +736,7 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 
 	midQ->mid_state = MID_REQUEST_SUBMITTED;
 	cifs_in_send_inc(ses->server);
-	rc = smb_sendv(ses->server, iov, n_vec);
+	rc = smb_send_rqst(ses->server, rqst, flags);
 	cifs_in_send_dec(ses->server);
 	cifs_save_when_sent(midQ);
 
@@ -716,32 +744,25 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 		ses->server->sequence_number -= 2;
 	mutex_unlock(&ses->server->srv_mutex);
 
-	if (rc < 0) {
-		cifs_small_buf_release(buf);
+	if (rc < 0)
 		goto out;
-	}
 
-	if (timeout == CIFS_ASYNC_OP) {
-		cifs_small_buf_release(buf);
+	if (timeout == CIFS_ASYNC_OP)
 		goto out;
-	}
 
 	rc = wait_for_response(ses->server, midQ);
 	if (rc != 0) {
-		send_cancel(ses->server, buf, midQ);
+		send_cancel(ses->server, rqst, midQ);
 		spin_lock(&GlobalMid_Lock);
 		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
 			midQ->callback = DeleteMidQEntry;
 			spin_unlock(&GlobalMid_Lock);
-			cifs_small_buf_release(buf);
 			add_credits(ses->server, 1, optype);
 			return rc;
 		}
 		spin_unlock(&GlobalMid_Lock);
 	}
 
-	cifs_small_buf_release(buf);
-
 	rc = cifs_sync_mid_result(midQ, ses->server);
 	if (rc != 0) {
 		add_credits(ses->server, 1, optype);
@@ -755,8 +776,8 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	}
 
 	buf = (char *)midQ->resp_buf;
-	iov[0].iov_base = buf;
-	iov[0].iov_len = get_rfc1002_length(buf) + 4;
+	resp_iov->iov_base = buf;
+	resp_iov->iov_len = get_rfc1002_length(buf) + 4;
 	if (midQ->large_buf)
 		*resp_buf_type = CIFS_LARGE_BUFFER;
 	else
@@ -778,12 +799,45 @@ out:
 }
 
 int
+SendReceive2(const unsigned int xid, struct cifs_ses *ses,
+	     struct kvec *iov, int n_vec, int *resp_buf_type /* ret */,
+	     const int flags, struct kvec *resp_iov)
+{
+	struct smb_rqst rqst;
+	struct kvec *new_iov;
+	int rc;
+
+	new_iov = kmalloc(sizeof(struct kvec) * (n_vec + 1), GFP_KERNEL);
+	if (!new_iov)
+		return -ENOMEM;
+
+	/* 1st iov is a RFC1001 length followed by the rest of the packet */
+	memcpy(new_iov + 1, iov, (sizeof(struct kvec) * n_vec));
+
+	new_iov[0].iov_base = new_iov[1].iov_base;
+	new_iov[0].iov_len = 4;
+	new_iov[1].iov_base += 4;
+	new_iov[1].iov_len -= 4;
+
+	memset(&rqst, 0, sizeof(struct smb_rqst));
+	rqst.rq_iov = new_iov;
+	rqst.rq_nvec = n_vec + 1;
+
+	rc = cifs_send_recv(xid, ses, &rqst, resp_buf_type, flags, resp_iov);
+	kfree(new_iov);
+	return rc;
+}
+
+int
 SendReceive(const unsigned int xid, struct cifs_ses *ses,
 	    struct smb_hdr *in_buf, struct smb_hdr *out_buf,
 	    int *pbytes_returned, const int timeout)
 {
 	int rc = 0;
 	struct mid_q_entry *midQ;
+	unsigned int len = be32_to_cpu(in_buf->smb_buf_length);
+	struct kvec iov = { .iov_base = in_buf, .iov_len = len };
+	struct smb_rqst rqst = { .rq_iov = &iov, .rq_nvec = 1 };
 
 	if (ses == NULL) {
 		cifs_dbg(VFS, "Null smb session\n");
@@ -801,10 +855,9 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
 	   to the same server. We may make this configurable later or
 	   use ses->maxReq */
 
-	if (be32_to_cpu(in_buf->smb_buf_length) > CIFSMaxBufSize +
-			MAX_CIFS_HDR_SIZE - 4) {
+	if (len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
 		cifs_dbg(VFS, "Illegal length, greater than maximum frame, %d\n",
-			 be32_to_cpu(in_buf->smb_buf_length));
+			 len);
 		return -EIO;
 	}
 
@@ -835,7 +888,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
 	midQ->mid_state = MID_REQUEST_SUBMITTED;
 
 	cifs_in_send_inc(ses->server);
-	rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
+	rc = smb_send(ses->server, in_buf, len);
 	cifs_in_send_dec(ses->server);
 	cifs_save_when_sent(midQ);
 
@@ -852,7 +905,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
 
 	rc = wait_for_response(ses->server, midQ);
 	if (rc != 0) {
-		send_cancel(ses->server, in_buf, midQ);
+		send_cancel(ses->server, &rqst, midQ);
 		spin_lock(&GlobalMid_Lock);
 		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
 			/* no longer considered to be "in-flight" */
@@ -921,6 +974,9 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 	int rstart = 0;
 	struct mid_q_entry *midQ;
 	struct cifs_ses *ses;
+	unsigned int len = be32_to_cpu(in_buf->smb_buf_length);
+	struct kvec iov = { .iov_base = in_buf, .iov_len = len };
+	struct smb_rqst rqst = { .rq_iov = &iov, .rq_nvec = 1 };
 
 	if (tcon == NULL || tcon->ses == NULL) {
 		cifs_dbg(VFS, "Null smb session\n");
@@ -940,10 +996,9 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 	   to the same server. We may make this configurable later or
 	   use ses->maxReq */
 
-	if (be32_to_cpu(in_buf->smb_buf_length) > CIFSMaxBufSize +
-			MAX_CIFS_HDR_SIZE - 4) {
+	if (len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
 		cifs_dbg(VFS, "Illegal length, greater than maximum frame, %d\n",
-			 be32_to_cpu(in_buf->smb_buf_length));
+			 len);
 		return -EIO;
 	}
 
@@ -972,7 +1027,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 
 	midQ->mid_state = MID_REQUEST_SUBMITTED;
 	cifs_in_send_inc(ses->server);
-	rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
+	rc = smb_send(ses->server, in_buf, len);
 	cifs_in_send_dec(ses->server);
 	cifs_save_when_sent(midQ);
 
@@ -1001,7 +1056,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 		if (in_buf->Command == SMB_COM_TRANSACTION2) {
 			/* POSIX lock. We send a NT_CANCEL SMB to cause the
 			   blocking lock to return. */
-			rc = send_cancel(ses->server, in_buf, midQ);
+			rc = send_cancel(ses->server, &rqst, midQ);
 			if (rc) {
 				cifs_delete_mid(midQ);
 				return rc;
@@ -1022,7 +1077,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 
 		rc = wait_for_response(ses->server, midQ);
 		if (rc) {
-			send_cancel(ses->server, in_buf, midQ);
+			send_cancel(ses->server, &rqst, midQ);
 			spin_lock(&GlobalMid_Lock);
 			if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
 				/* no longer considered to be "in-flight" */
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index 4d24d17bcfc1..504b3c3539dc 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -51,22 +51,8 @@
 #define elf_prstatus	compat_elf_prstatus
 #define elf_prpsinfo	compat_elf_prpsinfo
 
-/*
- * Compat version of cputime_to_compat_timeval, perhaps this
- * should be an inline in <linux/compat.h>.
- */
-static void cputime_to_compat_timeval(const cputime_t cputime,
-				      struct compat_timeval *value)
-{
-	struct timeval tv;
-	cputime_to_timeval(cputime, &tv);
-	value->tv_sec = tv.tv_sec;
-	value->tv_usec = tv.tv_usec;
-}
-
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
 
 /*
  * To use this file, asm/elf.h must define compat_elf_check_arch.
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
index f514978f6688..08b46e6e3995 100644
--- a/fs/crypto/Kconfig
+++ b/fs/crypto/Kconfig
@@ -1,6 +1,5 @@
 config FS_ENCRYPTION
 	tristate "FS Encryption (Per-file encryption)"
-	depends on BLOCK
 	select CRYPTO
 	select CRYPTO_AES
 	select CRYPTO_CBC
diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile
index f17684c48739..9f6607f17b53 100644
--- a/fs/crypto/Makefile
+++ b/fs/crypto/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_FS_ENCRYPTION)	+= fscrypto.o
 
 fscrypto-y := crypto.o fname.o policy.o keyinfo.o
+fscrypto-$(CONFIG_BLOCK) += bio.o
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
new file mode 100644
index 000000000000..a409a84f1bca
--- /dev/null
+++ b/fs/crypto/bio.c
@@ -0,0 +1,145 @@
+/*
+ * This contains encryption functions for per-file encryption.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ *	Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ *	Ildar Muslukhov, 2014
+ * Add fscrypt_pullback_bio_page()
+ *	Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/namei.h>
+#include "fscrypt_private.h"
+
+/*
+ * Call fscrypt_decrypt_page on every single page, reusing the encryption
+ * context.
+ */
+static void completion_pages(struct work_struct *work)
+{
+	struct fscrypt_ctx *ctx =
+		container_of(work, struct fscrypt_ctx, r.work);
+	struct bio *bio = ctx->r.bio;
+	struct bio_vec *bv;
+	int i;
+
+	bio_for_each_segment_all(bv, bio, i) {
+		struct page *page = bv->bv_page;
+		int ret = fscrypt_decrypt_page(page->mapping->host, page,
+				PAGE_SIZE, 0, page->index);
+
+		if (ret) {
+			WARN_ON_ONCE(1);
+			SetPageError(page);
+		} else {
+			SetPageUptodate(page);
+		}
+		unlock_page(page);
+	}
+	fscrypt_release_ctx(ctx);
+	bio_put(bio);
+}
+
+void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
+{
+	INIT_WORK(&ctx->r.work, completion_pages);
+	ctx->r.bio = bio;
+	queue_work(fscrypt_read_workqueue, &ctx->r.work);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
+
+void fscrypt_pullback_bio_page(struct page **page, bool restore)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *bounce_page;
+
+	/* The bounce data pages are unmapped. */
+	if ((*page)->mapping)
+		return;
+
+	/* The bounce data page is unmapped. */
+	bounce_page = *page;
+	ctx = (struct fscrypt_ctx *)page_private(bounce_page);
+
+	/* restore control page */
+	*page = ctx->w.control_page;
+
+	if (restore)
+		fscrypt_restore_control_page(bounce_page);
+}
+EXPORT_SYMBOL(fscrypt_pullback_bio_page);
+
+int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
+				sector_t pblk, unsigned int len)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	struct bio *bio;
+	int ret, err = 0;
+
+	BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
+
+	ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	ciphertext_page = fscrypt_alloc_bounce_page(ctx, GFP_NOWAIT);
+	if (IS_ERR(ciphertext_page)) {
+		err = PTR_ERR(ciphertext_page);
+		goto errout;
+	}
+
+	while (len--) {
+		err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk,
+					     ZERO_PAGE(0), ciphertext_page,
+					     PAGE_SIZE, 0, GFP_NOFS);
+		if (err)
+			goto errout;
+
+		bio = bio_alloc(GFP_NOWAIT, 1);
+		if (!bio) {
+			err = -ENOMEM;
+			goto errout;
+		}
+		bio->bi_bdev = inode->i_sb->s_bdev;
+		bio->bi_iter.bi_sector =
+			pblk << (inode->i_sb->s_blocksize_bits - 9);
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		ret = bio_add_page(bio, ciphertext_page,
+					inode->i_sb->s_blocksize, 0);
+		if (ret != inode->i_sb->s_blocksize) {
+			/* should never happen! */
+			WARN_ON(1);
+			bio_put(bio);
+			err = -EIO;
+			goto errout;
+		}
+		err = submit_bio_wait(bio);
+		if ((err == 0) && bio->bi_error)
+			err = -EIO;
+		bio_put(bio);
+		if (err)
+			goto errout;
+		lblk++;
+		pblk++;
+	}
+	err = 0;
+errout:
+	fscrypt_release_ctx(ctx);
+	return err;
+}
+EXPORT_SYMBOL(fscrypt_zeroout_range);
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index ac8e4f6a3773..02a7a9286449 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -24,7 +24,6 @@
 #include <linux/module.h>
 #include <linux/scatterlist.h>
 #include <linux/ratelimit.h>
-#include <linux/bio.h>
 #include <linux/dcache.h>
 #include <linux/namei.h>
 #include "fscrypt_private.h"
@@ -44,7 +43,7 @@ static mempool_t *fscrypt_bounce_page_pool = NULL;
 static LIST_HEAD(fscrypt_free_ctxs);
 static DEFINE_SPINLOCK(fscrypt_ctx_lock);
 
-static struct workqueue_struct *fscrypt_read_workqueue;
+struct workqueue_struct *fscrypt_read_workqueue;
 static DEFINE_MUTEX(fscrypt_init_mutex);
 
 static struct kmem_cache *fscrypt_ctx_cachep;
@@ -141,16 +140,10 @@ static void page_crypt_complete(struct crypto_async_request *req, int res)
 	complete(&ecr->completion);
 }
 
-typedef enum {
-	FS_DECRYPT = 0,
-	FS_ENCRYPT,
-} fscrypt_direction_t;
-
-static int do_page_crypto(const struct inode *inode,
-			fscrypt_direction_t rw, u64 lblk_num,
-			struct page *src_page, struct page *dest_page,
-			unsigned int len, unsigned int offs,
-			gfp_t gfp_flags)
+int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
+			   u64 lblk_num, struct page *src_page,
+			   struct page *dest_page, unsigned int len,
+			   unsigned int offs, gfp_t gfp_flags)
 {
 	struct {
 		__le64 index;
@@ -205,7 +198,8 @@ static int do_page_crypto(const struct inode *inode,
 	return 0;
 }
 
-static struct page *alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags)
+struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
+				       gfp_t gfp_flags)
 {
 	ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool, gfp_flags);
 	if (ctx->w.bounce_page == NULL)
@@ -260,9 +254,9 @@ struct page *fscrypt_encrypt_page(const struct inode *inode,
 
 	if (inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES) {
 		/* with inplace-encryption we just encrypt the page */
-		err = do_page_crypto(inode, FS_ENCRYPT, lblk_num,
-					page, ciphertext_page,
-					len, offs, gfp_flags);
+		err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num, page,
+					     ciphertext_page, len, offs,
+					     gfp_flags);
 		if (err)
 			return ERR_PTR(err);
 
@@ -276,14 +270,14 @@ struct page *fscrypt_encrypt_page(const struct inode *inode,
 		return (struct page *)ctx;
 
 	/* The encryption operation will require a bounce page. */
-	ciphertext_page = alloc_bounce_page(ctx, gfp_flags);
+	ciphertext_page = fscrypt_alloc_bounce_page(ctx, gfp_flags);
 	if (IS_ERR(ciphertext_page))
 		goto errout;
 
 	ctx->w.control_page = page;
-	err = do_page_crypto(inode, FS_ENCRYPT, lblk_num,
-					page, ciphertext_page,
-					len, offs, gfp_flags);
+	err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num,
+				     page, ciphertext_page, len, offs,
+				     gfp_flags);
 	if (err) {
 		ciphertext_page = ERR_PTR(err);
 		goto errout;
@@ -320,72 +314,11 @@ int fscrypt_decrypt_page(const struct inode *inode, struct page *page,
 	if (!(inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES))
 		BUG_ON(!PageLocked(page));
 
-	return do_page_crypto(inode, FS_DECRYPT, lblk_num, page, page, len,
-			offs, GFP_NOFS);
+	return fscrypt_do_page_crypto(inode, FS_DECRYPT, lblk_num, page, page,
+				      len, offs, GFP_NOFS);
 }
 EXPORT_SYMBOL(fscrypt_decrypt_page);
 
-int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
-				sector_t pblk, unsigned int len)
-{
-	struct fscrypt_ctx *ctx;
-	struct page *ciphertext_page = NULL;
-	struct bio *bio;
-	int ret, err = 0;
-
-	BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
-
-	ctx = fscrypt_get_ctx(inode, GFP_NOFS);
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-
-	ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT);
-	if (IS_ERR(ciphertext_page)) {
-		err = PTR_ERR(ciphertext_page);
-		goto errout;
-	}
-
-	while (len--) {
-		err = do_page_crypto(inode, FS_ENCRYPT, lblk,
-					ZERO_PAGE(0), ciphertext_page,
-					PAGE_SIZE, 0, GFP_NOFS);
-		if (err)
-			goto errout;
-
-		bio = bio_alloc(GFP_NOWAIT, 1);
-		if (!bio) {
-			err = -ENOMEM;
-			goto errout;
-		}
-		bio->bi_bdev = inode->i_sb->s_bdev;
-		bio->bi_iter.bi_sector =
-			pblk << (inode->i_sb->s_blocksize_bits - 9);
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-		ret = bio_add_page(bio, ciphertext_page,
-					inode->i_sb->s_blocksize, 0);
-		if (ret != inode->i_sb->s_blocksize) {
-			/* should never happen! */
-			WARN_ON(1);
-			bio_put(bio);
-			err = -EIO;
-			goto errout;
-		}
-		err = submit_bio_wait(bio);
-		if ((err == 0) && bio->bi_error)
-			err = -EIO;
-		bio_put(bio);
-		if (err)
-			goto errout;
-		lblk++;
-		pblk++;
-	}
-	err = 0;
-errout:
-	fscrypt_release_ctx(ctx);
-	return err;
-}
-EXPORT_SYMBOL(fscrypt_zeroout_range);
-
 /*
  * Validate dentries for encrypted directories to make sure we aren't
  * potentially caching stale data after a key has been added or
@@ -442,64 +375,6 @@ const struct dentry_operations fscrypt_d_ops = {
 };
 EXPORT_SYMBOL(fscrypt_d_ops);
 
-/*
- * Call fscrypt_decrypt_page on every single page, reusing the encryption
- * context.
- */
-static void completion_pages(struct work_struct *work)
-{
-	struct fscrypt_ctx *ctx =
-		container_of(work, struct fscrypt_ctx, r.work);
-	struct bio *bio = ctx->r.bio;
-	struct bio_vec *bv;
-	int i;
-
-	bio_for_each_segment_all(bv, bio, i) {
-		struct page *page = bv->bv_page;
-		int ret = fscrypt_decrypt_page(page->mapping->host, page,
-				PAGE_SIZE, 0, page->index);
-
-		if (ret) {
-			WARN_ON_ONCE(1);
-			SetPageError(page);
-		} else {
-			SetPageUptodate(page);
-		}
-		unlock_page(page);
-	}
-	fscrypt_release_ctx(ctx);
-	bio_put(bio);
-}
-
-void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
-{
-	INIT_WORK(&ctx->r.work, completion_pages);
-	ctx->r.bio = bio;
-	queue_work(fscrypt_read_workqueue, &ctx->r.work);
-}
-EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
-
-void fscrypt_pullback_bio_page(struct page **page, bool restore)
-{
-	struct fscrypt_ctx *ctx;
-	struct page *bounce_page;
-
-	/* The bounce data pages are unmapped. */
-	if ((*page)->mapping)
-		return;
-
-	/* The bounce data page is unmapped. */
-	bounce_page = *page;
-	ctx = (struct fscrypt_ctx *)page_private(bounce_page);
-
-	/* restore control page */
-	*page = ctx->w.control_page;
-
-	if (restore)
-		fscrypt_restore_control_page(bounce_page);
-}
-EXPORT_SYMBOL(fscrypt_pullback_bio_page);
-
 void fscrypt_restore_control_page(struct page *page)
 {
 	struct fscrypt_ctx *ctx;
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 56ad9d195f18..13052b85c393 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -332,7 +332,7 @@ int fscrypt_fname_usr_to_disk(struct inode *inode,
 	 * in a directory. Consequently, a user space name cannot be mapped to
 	 * a disk-space name
 	 */
-	return -EACCES;
+	return -ENOKEY;
 }
 EXPORT_SYMBOL(fscrypt_fname_usr_to_disk);
 
@@ -367,7 +367,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 		return 0;
 	}
 	if (!lookup)
-		return -EACCES;
+		return -ENOKEY;
 
 	/*
 	 * We don't have the key and we are doing a lookup; decode the
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index aeab032d7d35..fdbb8af32eaf 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -11,7 +11,7 @@
 #ifndef _FSCRYPT_PRIVATE_H
 #define _FSCRYPT_PRIVATE_H
 
-#include <linux/fscrypto.h>
+#include <linux/fscrypt_supp.h>
 
 #define FS_FNAME_CRYPTO_DIGEST_SIZE	32
 
@@ -71,6 +71,11 @@ struct fscrypt_info {
 	u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE];
 };
 
+typedef enum {
+	FS_DECRYPT = 0,
+	FS_ENCRYPT,
+} fscrypt_direction_t;
+
 #define FS_CTX_REQUIRES_FREE_ENCRYPT_FL		0x00000001
 #define FS_CTX_HAS_BOUNCE_BUFFER_FL		0x00000002
 
@@ -81,11 +86,20 @@ struct fscrypt_completion_result {
 
 #define DECLARE_FS_COMPLETION_RESULT(ecr) \
 	struct fscrypt_completion_result ecr = { \
-		COMPLETION_INITIALIZER((ecr).completion), 0 }
+		COMPLETION_INITIALIZER_ONSTACK((ecr).completion), 0 }
 
 
 /* crypto.c */
-int fscrypt_initialize(unsigned int cop_flags);
+extern int fscrypt_initialize(unsigned int cop_flags);
+extern struct workqueue_struct *fscrypt_read_workqueue;
+extern int fscrypt_do_page_crypto(const struct inode *inode,
+				  fscrypt_direction_t rw, u64 lblk_num,
+				  struct page *src_page,
+				  struct page *dest_page,
+				  unsigned int len, unsigned int offs,
+				  gfp_t gfp_flags);
+extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
+					      gfp_t gfp_flags);
 
 /* keyinfo.c */
 extern int fscrypt_get_crypt_info(struct inode *);
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 95cd4c3b06c3..02eb6b9e4438 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -77,26 +77,22 @@ out:
 
 static int validate_user_key(struct fscrypt_info *crypt_info,
 			struct fscrypt_context *ctx, u8 *raw_key,
-			u8 *prefix, int prefix_size)
+			const char *prefix)
 {
-	u8 *full_key_descriptor;
+	char *description;
 	struct key *keyring_key;
 	struct fscrypt_key *master_key;
 	const struct user_key_payload *ukp;
-	int full_key_len = prefix_size + (FS_KEY_DESCRIPTOR_SIZE * 2) + 1;
 	int res;
 
-	full_key_descriptor = kmalloc(full_key_len, GFP_NOFS);
-	if (!full_key_descriptor)
+	description = kasprintf(GFP_NOFS, "%s%*phN", prefix,
+				FS_KEY_DESCRIPTOR_SIZE,
+				ctx->master_key_descriptor);
+	if (!description)
 		return -ENOMEM;
 
-	memcpy(full_key_descriptor, prefix, prefix_size);
-	sprintf(full_key_descriptor + prefix_size,
-			"%*phN", FS_KEY_DESCRIPTOR_SIZE,
-			ctx->master_key_descriptor);
-	full_key_descriptor[full_key_len - 1] = '\0';
-	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
-	kfree(full_key_descriptor);
+	keyring_key = request_key(&key_type_logon, description, NULL);
+	kfree(description);
 	if (IS_ERR(keyring_key))
 		return PTR_ERR(keyring_key);
 
@@ -206,12 +202,15 @@ retry:
 
 	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
 	if (res < 0) {
-		if (!fscrypt_dummy_context_enabled(inode))
+		if (!fscrypt_dummy_context_enabled(inode) ||
+		    inode->i_sb->s_cop->is_encrypted(inode))
 			return res;
+		/* Fake up a context for an unencrypted directory */
+		memset(&ctx, 0, sizeof(ctx));
 		ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
 		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
 		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
-		ctx.flags = 0;
+		memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
 	} else if (res != sizeof(ctx)) {
 		return -EINVAL;
 	}
@@ -247,21 +246,10 @@ retry:
 	if (!raw_key)
 		goto out;
 
-	if (fscrypt_dummy_context_enabled(inode)) {
-		memset(raw_key, 0x42, keysize/2);
-		memset(raw_key+keysize/2, 0x24, keysize - (keysize/2));
-		goto got_key;
-	}
-
-	res = validate_user_key(crypt_info, &ctx, raw_key,
-			FS_KEY_DESC_PREFIX, FS_KEY_DESC_PREFIX_SIZE);
+	res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX);
 	if (res && inode->i_sb->s_cop->key_prefix) {
-		u8 *prefix = NULL;
-		int prefix_size, res2;
-
-		prefix_size = inode->i_sb->s_cop->key_prefix(inode, &prefix);
-		res2 = validate_user_key(crypt_info, &ctx, raw_key,
-							prefix, prefix_size);
+		int res2 = validate_user_key(crypt_info, &ctx, raw_key,
+					     inode->i_sb->s_cop->key_prefix);
 		if (res2) {
 			if (res2 == -ENOKEY)
 				res = -ENOKEY;
@@ -270,7 +258,6 @@ retry:
 	} else if (res) {
 		goto out;
 	}
-got_key:
 	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
 	if (!ctfm || IS_ERR(ctfm)) {
 		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index d6cd7ea4851d..14b76da71269 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -13,37 +13,20 @@
 #include <linux/mount.h>
 #include "fscrypt_private.h"
 
-static int inode_has_encryption_context(struct inode *inode)
-{
-	if (!inode->i_sb->s_cop->get_context)
-		return 0;
-	return (inode->i_sb->s_cop->get_context(inode, NULL, 0L) > 0);
-}
-
 /*
- * check whether the policy is consistent with the encryption context
- * for the inode
+ * check whether an encryption policy is consistent with an encryption context
  */
-static int is_encryption_context_consistent_with_policy(struct inode *inode,
+static bool is_encryption_context_consistent_with_policy(
+				const struct fscrypt_context *ctx,
 				const struct fscrypt_policy *policy)
 {
-	struct fscrypt_context ctx;
-	int res;
-
-	if (!inode->i_sb->s_cop->get_context)
-		return 0;
-
-	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
-	if (res != sizeof(ctx))
-		return 0;
-
-	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
-			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
-			(ctx.flags == policy->flags) &&
-			(ctx.contents_encryption_mode ==
-			 policy->contents_encryption_mode) &&
-			(ctx.filenames_encryption_mode ==
-			 policy->filenames_encryption_mode));
+	return memcmp(ctx->master_key_descriptor, policy->master_key_descriptor,
+		      FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(ctx->flags == policy->flags) &&
+		(ctx->contents_encryption_mode ==
+		 policy->contents_encryption_mode) &&
+		(ctx->filenames_encryption_mode ==
+		 policy->filenames_encryption_mode);
 }
 
 static int create_encryption_context_from_policy(struct inode *inode,
@@ -66,20 +49,12 @@ static int create_encryption_context_from_policy(struct inode *inode,
 					FS_KEY_DESCRIPTOR_SIZE);
 
 	if (!fscrypt_valid_contents_enc_mode(
-				policy->contents_encryption_mode)) {
-		printk(KERN_WARNING
-		       "%s: Invalid contents encryption mode %d\n", __func__,
-			policy->contents_encryption_mode);
+				policy->contents_encryption_mode))
 		return -EINVAL;
-	}
 
 	if (!fscrypt_valid_filenames_enc_mode(
-				policy->filenames_encryption_mode)) {
-		printk(KERN_WARNING
-			"%s: Invalid filenames encryption mode %d\n", __func__,
-			policy->filenames_encryption_mode);
+				policy->filenames_encryption_mode))
 		return -EINVAL;
-	}
 
 	if (policy->flags & ~FS_POLICY_FLAGS_VALID)
 		return -EINVAL;
@@ -98,6 +73,7 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
 	struct fscrypt_policy policy;
 	struct inode *inode = file_inode(filp);
 	int ret;
+	struct fscrypt_context ctx;
 
 	if (copy_from_user(&policy, arg, sizeof(policy)))
 		return -EFAULT;
@@ -114,9 +90,10 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
 
 	inode_lock(inode);
 
-	if (!inode_has_encryption_context(inode)) {
+	ret = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (ret == -ENODATA) {
 		if (!S_ISDIR(inode->i_mode))
-			ret = -EINVAL;
+			ret = -ENOTDIR;
 		else if (!inode->i_sb->s_cop->empty_dir)
 			ret = -EOPNOTSUPP;
 		else if (!inode->i_sb->s_cop->empty_dir(inode))
@@ -124,12 +101,14 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
 		else
 			ret = create_encryption_context_from_policy(inode,
 								    &policy);
-	} else if (!is_encryption_context_consistent_with_policy(inode,
-								 &policy)) {
-		printk(KERN_WARNING
-		       "%s: Policy inconsistent with encryption context\n",
-		       __func__);
-		ret = -EINVAL;
+	} else if (ret == sizeof(ctx) &&
+		   is_encryption_context_consistent_with_policy(&ctx,
+								&policy)) {
+		/* The file already uses the same encryption policy. */
+		ret = 0;
+	} else if (ret >= 0 || ret == -ERANGE) {
+		/* The file already uses a different encryption policy. */
+		ret = -EEXIST;
 	}
 
 	inode_unlock(inode);
@@ -151,8 +130,10 @@ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
 		return -ENODATA;
 
 	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res < 0 && res != -ERANGE)
+		return res;
 	if (res != sizeof(ctx))
-		return -ENODATA;
+		return -EINVAL;
 	if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
 		return -EINVAL;
 
@@ -217,9 +198,9 @@ EXPORT_SYMBOL(fscrypt_has_permitted_context);
  * @parent: Parent inode from which the context is inherited.
  * @child:  Child inode that inherits the context from @parent.
  * @fs_data:  private data given by FS.
- * @preload:  preload child i_crypt_info
+ * @preload:  preload child i_crypt_info if true
  *
- * Return: Zero on success, non-zero otherwise
+ * Return: 0 on success, -errno on failure
  */
 int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 						void *fs_data, bool preload)
@@ -240,19 +221,11 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 		return -ENOKEY;
 
 	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
-	if (fscrypt_dummy_context_enabled(parent)) {
-		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
-		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
-		ctx.flags = 0;
-		memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
-		res = 0;
-	} else {
-		ctx.contents_encryption_mode = ci->ci_data_mode;
-		ctx.filenames_encryption_mode = ci->ci_filename_mode;
-		ctx.flags = ci->ci_flags;
-		memcpy(ctx.master_key_descriptor, ci->ci_master_key,
-				FS_KEY_DESCRIPTOR_SIZE);
-	}
+	ctx.contents_encryption_mode = ci->ci_data_mode;
+	ctx.filenames_encryption_mode = ci->ci_filename_mode;
+	ctx.flags = ci->ci_flags;
+	memcpy(ctx.master_key_descriptor, ci->ci_master_key,
+	       FS_KEY_DESCRIPTOR_SIZE);
 	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
 	res = parent->i_sb->s_cop->set_context(child, &ctx,
 						sizeof(ctx), fs_data);
diff --git a/fs/dax.c b/fs/dax.c
index ddcddfeaa03b..e9cf8b4cd234 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -990,7 +990,6 @@ int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(__dax_zero_page_range);
 
-#ifdef CONFIG_FS_IOMAP
 static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
 {
 	return iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9);
@@ -1032,6 +1031,11 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		struct blk_dax_ctl dax = { 0 };
 		ssize_t map_len;
 
+		if (fatal_signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+
 		dax.sector = dax_iomap_sector(iomap, pos);
 		dax.size = (length + offset + PAGE_SIZE - 1) & PAGE_MASK;
 		map_len = dax_map_atomic(iomap->bdev, &dax);
@@ -1082,8 +1086,12 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 	loff_t pos = iocb->ki_pos, ret = 0, done = 0;
 	unsigned flags = 0;
 
-	if (iov_iter_rw(iter) == WRITE)
+	if (iov_iter_rw(iter) == WRITE) {
+		lockdep_assert_held_exclusive(&inode->i_rwsem);
 		flags |= IOMAP_WRITE;
+	} else {
+		lockdep_assert_held(&inode->i_rwsem);
+	}
 
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
@@ -1428,4 +1436,3 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 }
 EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
 #endif /* CONFIG_FS_DAX_PMD */
-#endif /* CONFIG_FS_IOMAP */
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index f17fcf89e18e..7fb1732a3630 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -248,6 +248,42 @@ static struct file_system_type debug_fs_type = {
 };
 MODULE_ALIAS_FS("debugfs");
 
+/**
+ * debugfs_lookup() - look up an existing debugfs file
+ * @name: a pointer to a string containing the name of the file to look up.
+ * @parent: a pointer to the parent dentry of the file.
+ *
+ * This function will return a pointer to a dentry if it succeeds.  If the file
+ * doesn't exist or an error occurs, %NULL will be returned.  The returned
+ * dentry must be passed to dput() when it is no longer needed.
+ *
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
+ * returned.
+ */
+struct dentry *debugfs_lookup(const char *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+
+	if (IS_ERR(parent))
+		return NULL;
+
+	if (!parent)
+		parent = debugfs_mount->mnt_root;
+
+	inode_lock(d_inode(parent));
+	dentry = lookup_one_len(name, parent, strlen(name));
+	inode_unlock(d_inode(parent));
+
+	if (IS_ERR(dentry))
+		return NULL;
+	if (!d_really_is_positive(dentry)) {
+		dput(dentry);
+		return NULL;
+	}
+	return dentry;
+}
+EXPORT_SYMBOL_GPL(debugfs_lookup);
+
 static struct dentry *start_creating(const char *name, struct dentry *parent)
 {
 	struct dentry *dentry;
diff --git a/fs/exofs/sys.c b/fs/exofs/sys.c
index 5e6a2c0a1f0b..1f7d5e46cdda 100644
--- a/fs/exofs/sys.c
+++ b/fs/exofs/sys.c
@@ -122,7 +122,7 @@ void exofs_sysfs_dbg_print(void)
 	list_for_each_entry_safe(k_name, k_tmp, &exofs_kset->list, entry) {
 		printk(KERN_INFO "%s: name %s ref %d\n",
 			__func__, kobject_name(k_name),
-			(int)atomic_read(&k_name->kref.refcount));
+			(int)kref_read(&k_name->kref));
 	}
 #endif
 }
diff --git a/fs/ext2/Kconfig b/fs/ext2/Kconfig
index 36bea5adcaba..c634874e12d9 100644
--- a/fs/ext2/Kconfig
+++ b/fs/ext2/Kconfig
@@ -1,6 +1,5 @@
 config EXT2_FS
 	tristate "Second extended fs support"
-	select FS_IOMAP if FS_DAX
 	help
 	  Ext2 is a standard Linux file system for hard disks.
 
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 7b90691e98c4..e38039fd96ff 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -37,7 +37,6 @@ config EXT4_FS
 	select CRC16
 	select CRYPTO
 	select CRYPTO_CRC32C
-	select FS_IOMAP if FS_DAX
 	help
 	  This is the next generation of the ext3 filesystem.
 
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 2163c1e69f2a..01d52b98f9a7 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -32,7 +32,11 @@
 #include <linux/percpu_counter.h>
 #include <linux/ratelimit.h>
 #include <crypto/hash.h>
-#include <linux/fscrypto.h>
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+#include <linux/fscrypt_supp.h>
+#else
+#include <linux/fscrypt_notsupp.h>
+#endif
 #include <linux/falloc.h>
 #include <linux/percpu-rwsem.h>
 #ifdef __KERNEL__
@@ -679,6 +683,16 @@ struct fsxattr {
 #define EXT4_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
 #define EXT4_IOC_FSSETXATTR		FS_IOC_FSSETXATTR
 
+#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
+
+/*
+ * Flags for going down operation
+ */
+#define EXT4_GOING_FLAGS_DEFAULT		0x0	/* going down */
+#define EXT4_GOING_FLAGS_LOGFLUSH		0x1	/* flush log but not data */
+#define EXT4_GOING_FLAGS_NOLOGFLUSH		0x2	/* don't flush log nor data */
+
+
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
  * ioctl commands in 32 bit emulation
@@ -1343,11 +1357,6 @@ struct ext4_super_block {
 /* Number of quota types we support */
 #define EXT4_MAXQUOTAS 3
 
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-#define EXT4_KEY_DESC_PREFIX "ext4:"
-#define EXT4_KEY_DESC_PREFIX_SIZE 5
-#endif
-
 /*
  * fourth extended-fs super-block data in memory
  */
@@ -1404,8 +1413,7 @@ struct ext4_sb_info {
 	struct journal_s *s_journal;
 	struct list_head s_orphan;
 	struct mutex s_orphan_lock;
-	unsigned long s_resize_flags;		/* Flags indicating if there
-						   is a resizer */
+	unsigned long s_ext4_flags;		/* Ext4 superblock flags */
 	unsigned long s_commit_interval;
 	u32 s_max_batch_time;
 	u32 s_min_batch_time;
@@ -1517,12 +1525,6 @@ struct ext4_sb_info {
 
 	/* Barrier between changing inodes' journal flags and writepages ops. */
 	struct percpu_rw_semaphore s_journal_flag_rwsem;
-
-	/* Encryption support */
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	u8 key_prefix[EXT4_KEY_DESC_PREFIX_SIZE];
-	u8 key_prefix_size;
-#endif
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1845,6 +1847,18 @@ static inline bool ext4_has_incompat_features(struct super_block *sb)
 }
 
 /*
+ * Superblock flags
+ */
+#define EXT4_FLAGS_RESIZING	0
+#define EXT4_FLAGS_SHUTDOWN	1
+
+static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
+{
+	return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+}
+
+
+/*
  * Default values for user and/or group using reserved blocks
  */
 #define	EXT4_DEF_RESUID		0
@@ -2320,28 +2334,6 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
 }
 static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
 
-#define fscrypt_set_d_op(i)
-#define fscrypt_get_ctx			fscrypt_notsupp_get_ctx
-#define fscrypt_release_ctx		fscrypt_notsupp_release_ctx
-#define fscrypt_encrypt_page		fscrypt_notsupp_encrypt_page
-#define fscrypt_decrypt_page		fscrypt_notsupp_decrypt_page
-#define fscrypt_decrypt_bio_pages	fscrypt_notsupp_decrypt_bio_pages
-#define fscrypt_pullback_bio_page	fscrypt_notsupp_pullback_bio_page
-#define fscrypt_restore_control_page	fscrypt_notsupp_restore_control_page
-#define fscrypt_zeroout_range		fscrypt_notsupp_zeroout_range
-#define fscrypt_ioctl_set_policy	fscrypt_notsupp_ioctl_set_policy
-#define fscrypt_ioctl_get_policy	fscrypt_notsupp_ioctl_get_policy
-#define fscrypt_has_permitted_context	fscrypt_notsupp_has_permitted_context
-#define fscrypt_inherit_context		fscrypt_notsupp_inherit_context
-#define fscrypt_get_encryption_info	fscrypt_notsupp_get_encryption_info
-#define fscrypt_put_encryption_info	fscrypt_notsupp_put_encryption_info
-#define fscrypt_setup_filename		fscrypt_notsupp_setup_filename
-#define fscrypt_free_filename		fscrypt_notsupp_free_filename
-#define fscrypt_fname_encrypted_size	fscrypt_notsupp_fname_encrypted_size
-#define fscrypt_fname_alloc_buffer	fscrypt_notsupp_fname_alloc_buffer
-#define fscrypt_fname_free_buffer	fscrypt_notsupp_fname_free_buffer
-#define fscrypt_fname_disk_to_usr	fscrypt_notsupp_fname_disk_to_usr
-#define fscrypt_fname_usr_to_disk	fscrypt_notsupp_fname_usr_to_disk
 #endif
 
 /* dir.c */
@@ -3034,7 +3026,7 @@ extern int ext4_inline_data_fiemap(struct inode *inode,
 extern int ext4_try_to_evict_inline_data(handle_t *handle,
 					 struct inode *inode,
 					 int needed);
-extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline);
+extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
 
 extern int ext4_convert_inline_data(struct inode *inode);
 
@@ -3228,7 +3220,6 @@ static inline void ext4_inode_resume_unlocked_dio(struct inode *inode)
 					    EXT4_WQ_HASH_SZ])
 extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
 
-#define EXT4_RESIZING	0
 extern int ext4_resize_begin(struct super_block *sb);
 extern void ext4_resize_end(struct super_block *sb);
 
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index e770c1ee4613..dd106b1d5d89 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -43,6 +43,10 @@ static int ext4_journal_check_start(struct super_block *sb)
 	journal_t *journal;
 
 	might_sleep();
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return -EIO;
+
 	if (sb->s_flags & MS_RDONLY)
 		return -EROFS;
 	WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
@@ -161,6 +165,13 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
 	might_sleep();
 
 	if (ext4_handle_valid(handle)) {
+		struct super_block *sb;
+
+		sb = handle->h_transaction->t_journal->j_private;
+		if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) {
+			jbd2_journal_abort_handle(handle);
+			return -EIO;
+		}
 		err = jbd2_journal_get_write_access(handle, bh);
 		if (err)
 			ext4_journal_abort_handle(where, line, __func__, bh,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 3e295d3350a9..2a97dff87b96 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5334,7 +5334,8 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	ext4_lblk_t stop, *iterator, ex_start, ex_end;
 
 	/* Let path point to the last extent */
-	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+				EXT4_EX_NOCACHE);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 
@@ -5343,15 +5344,15 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	if (!extent)
 		goto out;
 
-	stop = le32_to_cpu(extent->ee_block) +
-			ext4_ext_get_actual_len(extent);
+	stop = le32_to_cpu(extent->ee_block);
 
        /*
 	 * In case of left shift, Don't start shifting extents until we make
 	 * sure the hole is big enough to accommodate the shift.
 	*/
 	if (SHIFT == SHIFT_LEFT) {
-		path = ext4_find_extent(inode, start - 1, &path, 0);
+		path = ext4_find_extent(inode, start - 1, &path,
+					EXT4_EX_NOCACHE);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5383,9 +5384,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	else
 		iterator = &stop;
 
-	/* Its safe to start updating extents */
-	while (start < stop) {
-		path = ext4_find_extent(inode, *iterator, &path, 0);
+	/*
+	 * Its safe to start updating extents.  Start and stop are unsigned, so
+	 * in case of right shift if extent with 0 block is reached, iterator
+	 * becomes NULL to indicate the end of the loop.
+	 */
+	while (iterator && start <= stop) {
+		path = ext4_find_extent(inode, *iterator, &path,
+					EXT4_EX_NOCACHE);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5412,8 +5418,11 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 					ext4_ext_get_actual_len(extent);
 		} else {
 			extent = EXT_FIRST_EXTENT(path[depth].p_hdr);
-			*iterator =  le32_to_cpu(extent->ee_block) > 0 ?
-				le32_to_cpu(extent->ee_block) - 1 : 0;
+			if (le32_to_cpu(extent->ee_block) > 0)
+				*iterator = le32_to_cpu(extent->ee_block) - 1;
+			else
+				/* Beginning is reached, end of the loop */
+				iterator = NULL;
 			/* Update path extent in case we need to stop */
 			while (le32_to_cpu(extent->ee_block) < start)
 				extent++;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d663d3d7c81c..87e11dfe3cde 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -57,6 +57,9 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
+		return -EIO;
+
 	if (!iov_iter_count(to))
 		return 0; /* skip atime */
 
@@ -175,7 +178,6 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
-	bool overwrite = false;
 
 	inode_lock(inode);
 	ret = ext4_write_checks(iocb, from);
@@ -188,16 +190,9 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret)
 		goto out;
 
-	if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
-		overwrite = true;
-		downgrade_write(&inode->i_rwsem);
-	}
 	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
 out:
-	if (!overwrite)
-		inode_unlock(inode);
-	else
-		inode_unlock_shared(inode);
+	inode_unlock(inode);
 	if (ret > 0)
 		ret = generic_write_sync(iocb, ret);
 	return ret;
@@ -213,6 +208,9 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	int overwrite = 0;
 	ssize_t ret;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 #ifdef CONFIG_FS_DAX
 	if (IS_DAX(inode))
 		return ext4_dax_write_iter(iocb, from);
@@ -348,6 +346,9 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_mapping->host;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (ext4_encrypted_inode(inode)) {
 		int err = fscrypt_get_encryption_info(inode);
 		if (err)
@@ -375,6 +376,9 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	char buf[64], *cp;
 	int ret;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
 		     !(sb->s_flags & MS_RDONLY))) {
 		sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 88effb1053c7..9d549608fd30 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -100,6 +100,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	tid_t commit_tid;
 	bool needs_barrier = false;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	J_ASSERT(ext4_journal_current_handle() == NULL);
 
 	trace_ext4_sync_file_enter(file, datasync);
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index e026aa941fd5..38b8a96eb97c 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -10,7 +10,8 @@
  */
 
 #include <linux/fs.h>
-#include <linux/cryptohash.h>
+#include <linux/compiler.h>
+#include <linux/bitops.h>
 #include "ext4.h"
 
 #define DELTA 0x9E3779B9
@@ -32,6 +33,74 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 	buf[1] += b1;
 }
 
+/* F, G and H are basic MD4 functions: selection, majority, parity */
+#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
+#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
+#define H(x, y, z) ((x) ^ (y) ^ (z))
+
+/*
+ * The generic round function.  The application is so specific that
+ * we don't bother protecting all the arguments with parens, as is generally
+ * good macro practice, in favor of extra legibility.
+ * Rotation is separate from addition to prevent recomputation
+ */
+#define ROUND(f, a, b, c, d, x, s)	\
+	(a += f(b, c, d) + x, a = rol32(a, s))
+#define K1 0
+#define K2 013240474631UL
+#define K3 015666365641UL
+
+/*
+ * Basic cut-down MD4 transform.  Returns only 32 bits of result.
+ */
+static __u32 half_md4_transform(__u32 buf[4], __u32 const in[8])
+{
+	__u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3];
+
+	/* Round 1 */
+	ROUND(F, a, b, c, d, in[0] + K1,  3);
+	ROUND(F, d, a, b, c, in[1] + K1,  7);
+	ROUND(F, c, d, a, b, in[2] + K1, 11);
+	ROUND(F, b, c, d, a, in[3] + K1, 19);
+	ROUND(F, a, b, c, d, in[4] + K1,  3);
+	ROUND(F, d, a, b, c, in[5] + K1,  7);
+	ROUND(F, c, d, a, b, in[6] + K1, 11);
+	ROUND(F, b, c, d, a, in[7] + K1, 19);
+
+	/* Round 2 */
+	ROUND(G, a, b, c, d, in[1] + K2,  3);
+	ROUND(G, d, a, b, c, in[3] + K2,  5);
+	ROUND(G, c, d, a, b, in[5] + K2,  9);
+	ROUND(G, b, c, d, a, in[7] + K2, 13);
+	ROUND(G, a, b, c, d, in[0] + K2,  3);
+	ROUND(G, d, a, b, c, in[2] + K2,  5);
+	ROUND(G, c, d, a, b, in[4] + K2,  9);
+	ROUND(G, b, c, d, a, in[6] + K2, 13);
+
+	/* Round 3 */
+	ROUND(H, a, b, c, d, in[3] + K3,  3);
+	ROUND(H, d, a, b, c, in[7] + K3,  9);
+	ROUND(H, c, d, a, b, in[2] + K3, 11);
+	ROUND(H, b, c, d, a, in[6] + K3, 15);
+	ROUND(H, a, b, c, d, in[1] + K3,  3);
+	ROUND(H, d, a, b, c, in[5] + K3,  9);
+	ROUND(H, c, d, a, b, in[0] + K3, 11);
+	ROUND(H, b, c, d, a, in[4] + K3, 15);
+
+	buf[0] += a;
+	buf[1] += b;
+	buf[2] += c;
+	buf[3] += d;
+
+	return buf[1]; /* "most hashed" word */
+}
+#undef ROUND
+#undef K1
+#undef K2
+#undef K3
+#undef F
+#undef G
+#undef H
 
 /* The old legacy hash */
 static __u32 dx_hack_hash_unsigned(const char *name, int len)
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index e57e8d90ea54..b14bae2598bc 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -764,6 +764,9 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	if (!dir || !dir->i_nlink)
 		return ERR_PTR(-EPERM);
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+		return ERR_PTR(-EIO);
+
 	if ((ext4_encrypted_inode(dir) ||
 	     DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) &&
 	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
@@ -771,7 +774,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 		if (err)
 			return ERR_PTR(err);
 		if (!fscrypt_has_encryption_key(dir))
-			return ERR_PTR(-EPERM);
+			return ERR_PTR(-ENOKEY);
 		if (!handle)
 			nblocks += EXT4_DATA_TRANS_BLOCKS(dir->i_sb);
 		encrypt = 1;
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 437df6a1a841..30a9f210d1e3 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -215,6 +215,9 @@ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
 	struct ext4_inode *raw_inode;
 	int cp_len = 0;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return;
+
 	BUG_ON(!EXT4_I(inode)->i_inline_off);
 	BUG_ON(pos + len > EXT4_I(inode)->i_inline_size);
 
@@ -381,7 +384,7 @@ out:
 static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
 				    unsigned int len)
 {
-	int ret, size;
+	int ret, size, no_expand;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 
 	if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
@@ -391,15 +394,14 @@ static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
 	if (size < len)
 		return -ENOSPC;
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 
 	if (ei->i_inline_off)
 		ret = ext4_update_inline_data(handle, inode, len);
 	else
 		ret = ext4_create_inline_data(handle, inode, len);
 
-	up_write(&EXT4_I(inode)->xattr_sem);
-
+	ext4_write_unlock_xattr(inode, &no_expand);
 	return ret;
 }
 
@@ -533,7 +535,7 @@ static int ext4_convert_inline_data_to_extent(struct address_space *mapping,
 					      struct inode *inode,
 					      unsigned flags)
 {
-	int ret, needed_blocks;
+	int ret, needed_blocks, no_expand;
 	handle_t *handle = NULL;
 	int retries = 0, sem_held = 0;
 	struct page *page = NULL;
@@ -573,7 +575,7 @@ retry:
 		goto out;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	sem_held = 1;
 	/* If some one has already done this for us, just exit. */
 	if (!ext4_has_inline_data(inode)) {
@@ -610,7 +612,7 @@ retry:
 		put_page(page);
 		page = NULL;
 		ext4_orphan_add(handle, inode);
-		up_write(&EXT4_I(inode)->xattr_sem);
+		ext4_write_unlock_xattr(inode, &no_expand);
 		sem_held = 0;
 		ext4_journal_stop(handle);
 		handle = NULL;
@@ -636,7 +638,7 @@ out:
 		put_page(page);
 	}
 	if (sem_held)
-		up_write(&EXT4_I(inode)->xattr_sem);
+		ext4_write_unlock_xattr(inode, &no_expand);
 	if (handle)
 		ext4_journal_stop(handle);
 	brelse(iloc.bh);
@@ -729,7 +731,7 @@ convert:
 int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 			       unsigned copied, struct page *page)
 {
-	int ret;
+	int ret, no_expand;
 	void *kaddr;
 	struct ext4_iloc iloc;
 
@@ -747,7 +749,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 		goto out;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	BUG_ON(!ext4_has_inline_data(inode));
 
 	kaddr = kmap_atomic(page);
@@ -757,7 +759,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 	/* clear page dirty so that writepages wouldn't work for us. */
 	ClearPageDirty(page);
 
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	brelse(iloc.bh);
 out:
 	return copied;
@@ -768,7 +770,7 @@ ext4_journalled_write_inline_data(struct inode *inode,
 				  unsigned len,
 				  struct page *page)
 {
-	int ret;
+	int ret, no_expand;
 	void *kaddr;
 	struct ext4_iloc iloc;
 
@@ -778,11 +780,11 @@ ext4_journalled_write_inline_data(struct inode *inode,
 		return NULL;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	kaddr = kmap_atomic(page);
 	ext4_write_inline_data(inode, &iloc, kaddr, 0, len);
 	kunmap_atomic(kaddr);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 
 	return iloc.bh;
 }
@@ -944,8 +946,15 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 				  struct page *page)
 {
 	int i_size_changed = 0;
+	int ret;
 
-	copied = ext4_write_inline_data_end(inode, pos, len, copied, page);
+	ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
+	if (ret < 0) {
+		unlock_page(page);
+		put_page(page);
+		return ret;
+	}
+	copied = ret;
 
 	/*
 	 * No need to use i_size_read() here, the i_size
@@ -1043,7 +1052,6 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
 	dir->i_mtime = dir->i_ctime = current_time(dir);
 	ext4_update_dx_flag(dir);
 	dir->i_version++;
-	ext4_mark_inode_dirty(handle, dir);
 	return 1;
 }
 
@@ -1259,7 +1267,7 @@ out:
 int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 			      struct inode *dir, struct inode *inode)
 {
-	int ret, inline_size;
+	int ret, inline_size, no_expand;
 	void *inline_start;
 	struct ext4_iloc iloc;
 
@@ -1267,7 +1275,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 	if (ret)
 		return ret;
 
-	down_write(&EXT4_I(dir)->xattr_sem);
+	ext4_write_lock_xattr(dir, &no_expand);
 	if (!ext4_has_inline_data(dir))
 		goto out;
 
@@ -1312,8 +1320,8 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 	ret = ext4_convert_inline_data_nolock(handle, dir, &iloc);
 
 out:
+	ext4_write_unlock_xattr(dir, &no_expand);
 	ext4_mark_inode_dirty(handle, dir);
-	up_write(&EXT4_I(dir)->xattr_sem);
 	brelse(iloc.bh);
 	return ret;
 }
@@ -1673,7 +1681,7 @@ int ext4_delete_inline_entry(handle_t *handle,
 			     struct buffer_head *bh,
 			     int *has_inline_data)
 {
-	int err, inline_size;
+	int err, inline_size, no_expand;
 	struct ext4_iloc iloc;
 	void *inline_start;
 
@@ -1681,7 +1689,7 @@ int ext4_delete_inline_entry(handle_t *handle,
 	if (err)
 		return err;
 
-	down_write(&EXT4_I(dir)->xattr_sem);
+	ext4_write_lock_xattr(dir, &no_expand);
 	if (!ext4_has_inline_data(dir)) {
 		*has_inline_data = 0;
 		goto out;
@@ -1709,13 +1717,11 @@ int ext4_delete_inline_entry(handle_t *handle,
 	if (err)
 		goto out;
 
-	err = ext4_mark_inode_dirty(handle, dir);
-	if (unlikely(err))
-		goto out;
-
 	ext4_show_inline_dir(dir, iloc.bh, inline_start, inline_size);
 out:
-	up_write(&EXT4_I(dir)->xattr_sem);
+	ext4_write_unlock_xattr(dir, &no_expand);
+	if (likely(err == 0))
+		err = ext4_mark_inode_dirty(handle, dir);
 	brelse(iloc.bh);
 	if (err != -ENOENT)
 		ext4_std_error(dir->i_sb, err);
@@ -1814,11 +1820,11 @@ out:
 
 int ext4_destroy_inline_data(handle_t *handle, struct inode *inode)
 {
-	int ret;
+	int ret, no_expand;
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	ret = ext4_destroy_inline_data_nolock(handle, inode);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 
 	return ret;
 }
@@ -1900,10 +1906,10 @@ out:
 	return error;
 }
 
-void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
+int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 {
 	handle_t *handle;
-	int inline_size, value_len, needed_blocks;
+	int inline_size, value_len, needed_blocks, no_expand, err = 0;
 	size_t i_size;
 	void *value = NULL;
 	struct ext4_xattr_ibody_find is = {
@@ -1918,19 +1924,19 @@ void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 	needed_blocks = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks);
 	if (IS_ERR(handle))
-		return;
+		return PTR_ERR(handle);
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	if (!ext4_has_inline_data(inode)) {
 		*has_inline = 0;
 		ext4_journal_stop(handle);
-		return;
+		return 0;
 	}
 
-	if (ext4_orphan_add(handle, inode))
+	if ((err = ext4_orphan_add(handle, inode)) != 0)
 		goto out;
 
-	if (ext4_get_inode_loc(inode, &is.iloc))
+	if ((err = ext4_get_inode_loc(inode, &is.iloc)) != 0)
 		goto out;
 
 	down_write(&EXT4_I(inode)->i_data_sem);
@@ -1941,24 +1947,29 @@ void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 	if (i_size < inline_size) {
 		/* Clear the content in the xattr space. */
 		if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) {
-			if (ext4_xattr_ibody_find(inode, &i, &is))
+			if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0)
 				goto out_error;
 
 			BUG_ON(is.s.not_found);
 
 			value_len = le32_to_cpu(is.s.here->e_value_size);
 			value = kmalloc(value_len, GFP_NOFS);
-			if (!value)
+			if (!value) {
+				err = -ENOMEM;
 				goto out_error;
+			}
 
-			if (ext4_xattr_ibody_get(inode, i.name_index, i.name,
-						value, value_len))
+			err = ext4_xattr_ibody_get(inode, i.name_index,
+						   i.name, value, value_len);
+			if (err <= 0)
 				goto out_error;
 
 			i.value = value;
 			i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ?
 					i_size - EXT4_MIN_INLINE_DATA_SIZE : 0;
-			if (ext4_xattr_ibody_inline_set(handle, inode, &i, &is))
+			err = ext4_xattr_ibody_inline_set(handle, inode,
+							  &i, &is);
+			if (err)
 				goto out_error;
 		}
 
@@ -1978,23 +1989,24 @@ out_error:
 	up_write(&EXT4_I(inode)->i_data_sem);
 out:
 	brelse(is.iloc.bh);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	kfree(value);
 	if (inode->i_nlink)
 		ext4_orphan_del(handle, inode);
 
-	inode->i_mtime = inode->i_ctime = current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
-	if (IS_SYNC(inode))
-		ext4_handle_sync(handle);
-
+	if (err == 0) {
+		inode->i_mtime = inode->i_ctime = current_time(inode);
+		err = ext4_mark_inode_dirty(handle, inode);
+		if (IS_SYNC(inode))
+			ext4_handle_sync(handle);
+	}
 	ext4_journal_stop(handle);
-	return;
+	return err;
 }
 
 int ext4_convert_inline_data(struct inode *inode)
 {
-	int error, needed_blocks;
+	int error, needed_blocks, no_expand;
 	handle_t *handle;
 	struct ext4_iloc iloc;
 
@@ -2016,15 +2028,10 @@ int ext4_convert_inline_data(struct inode *inode)
 		goto out_free;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
-	if (!ext4_has_inline_data(inode)) {
-		up_write(&EXT4_I(inode)->xattr_sem);
-		goto out;
-	}
-
-	error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
-	up_write(&EXT4_I(inode)->xattr_sem);
-out:
+	ext4_write_lock_xattr(inode, &no_expand);
+	if (ext4_has_inline_data(inode))
+		error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	ext4_journal_stop(handle);
 out_free:
 	brelse(iloc.bh);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 88d57af1b516..f622d4a577e3 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1189,6 +1189,9 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	pgoff_t index;
 	unsigned from, to;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	trace_ext4_write_begin(inode, pos, len, flags);
 	/*
 	 * Reserve one block more for addition to orphan list in case
@@ -1330,8 +1333,11 @@ static int ext4_write_end(struct file *file,
 	if (ext4_has_inline_data(inode)) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
-		if (ret < 0)
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
 			goto errout;
+		}
 		copied = ret;
 	} else
 		copied = block_write_end(file, mapping, pos,
@@ -1385,7 +1391,9 @@ errout:
  * set the buffer to be dirty, since in data=journalled mode we need
  * to call ext4_handle_dirty_metadata() instead.
  */
-static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
+static void ext4_journalled_zero_new_buffers(handle_t *handle,
+					    struct page *page,
+					    unsigned from, unsigned to)
 {
 	unsigned int block_start = 0, block_end;
 	struct buffer_head *head, *bh;
@@ -1402,7 +1410,7 @@ static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
 					size = min(to, block_end) - start;
 
 					zero_user(page, start, size);
-					set_buffer_uptodate(bh);
+					write_end_fn(handle, bh);
 				}
 				clear_buffer_new(bh);
 			}
@@ -1431,18 +1439,25 @@ static int ext4_journalled_write_end(struct file *file,
 
 	BUG_ON(!ext4_handle_valid(handle));
 
-	if (ext4_has_inline_data(inode))
-		copied = ext4_write_inline_data_end(inode, pos, len,
-						    copied, page);
-	else {
-		if (copied < len) {
-			if (!PageUptodate(page))
-				copied = 0;
-			zero_new_buffers(page, from+copied, to);
+	if (ext4_has_inline_data(inode)) {
+		ret = ext4_write_inline_data_end(inode, pos, len,
+						 copied, page);
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
+			goto errout;
 		}
-
+		copied = ret;
+	} else if (unlikely(copied < len) && !PageUptodate(page)) {
+		copied = 0;
+		ext4_journalled_zero_new_buffers(handle, page, from, to);
+	} else {
+		if (unlikely(copied < len))
+			ext4_journalled_zero_new_buffers(handle, page,
+							 from + copied, to);
 		ret = ext4_walk_page_buffers(handle, page_buffers(page), from,
-					     to, &partial, write_end_fn);
+					     from + copied, &partial,
+					     write_end_fn);
 		if (!partial)
 			SetPageUptodate(page);
 	}
@@ -1468,6 +1483,7 @@ static int ext4_journalled_write_end(struct file *file,
 		 */
 		ext4_orphan_add(handle, inode);
 
+errout:
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
@@ -2034,6 +2050,12 @@ static int ext4_writepage(struct page *page,
 	struct ext4_io_submit io_submit;
 	bool keep_towrite = false;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
+		ext4_invalidatepage(page, 0, PAGE_SIZE);
+		unlock_page(page);
+		return -EIO;
+	}
+
 	trace_ext4_writepage(page);
 	size = i_size_read(inode);
 	if (page->index == size >> PAGE_SHIFT)
@@ -2409,7 +2431,8 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 		if (err < 0) {
 			struct super_block *sb = inode->i_sb;
 
-			if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+			if (ext4_forced_shutdown(EXT4_SB(sb)) ||
+			    EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
 				goto invalidate_dirty_pages;
 			/*
 			 * Let the uper layers retry transient errors.
@@ -2464,8 +2487,8 @@ update_disksize:
 			disksize = i_size;
 		if (disksize > EXT4_I(inode)->i_disksize)
 			EXT4_I(inode)->i_disksize = disksize;
-		err2 = ext4_mark_inode_dirty(handle, inode);
 		up_write(&EXT4_I(inode)->i_data_sem);
+		err2 = ext4_mark_inode_dirty(handle, inode);
 		if (err2)
 			ext4_error(inode->i_sb,
 				   "Failed to mark inode %lu dirty",
@@ -2631,6 +2654,9 @@ static int ext4_writepages(struct address_space *mapping,
 	struct blk_plug plug;
 	bool give_up_on_write = false;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	percpu_down_read(&sbi->s_journal_flag_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
@@ -2667,7 +2693,8 @@ static int ext4_writepages(struct address_space *mapping,
 	 * *never* be called, so if that ever happens, we would want
 	 * the stack trace.
 	 */
-	if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
+		     sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
 		ret = -EROFS;
 		goto out_writepages;
 	}
@@ -2892,6 +2919,9 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	handle_t *handle;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	index = pos >> PAGE_SHIFT;
 
 	if (ext4_nonda_switch(inode->i_sb) ||
@@ -3914,6 +3944,10 @@ static int ext4_block_truncate_page(handle_t *handle,
 	unsigned blocksize;
 	struct inode *inode = mapping->host;
 
+	/* If we are processing an encrypted inode during orphan list handling */
+	if (ext4_encrypted_inode(inode) && !fscrypt_has_encryption_key(inode))
+		return 0;
+
 	blocksize = inode->i_sb->s_blocksize;
 	length = blocksize - (offset & (blocksize - 1));
 
@@ -4222,7 +4256,9 @@ int ext4_truncate(struct inode *inode)
 	if (ext4_has_inline_data(inode)) {
 		int has_inline = 1;
 
-		ext4_inline_data_truncate(inode, &has_inline);
+		err = ext4_inline_data_truncate(inode, &has_inline);
+		if (err)
+			return err;
 		if (has_inline)
 			return 0;
 	}
@@ -5197,6 +5233,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	int orphan = 0;
 	const unsigned int ia_valid = attr->ia_valid;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	error = setattr_prepare(dentry, attr);
 	if (error)
 		return error;
@@ -5483,6 +5522,9 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 {
 	int err = 0;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
 
@@ -5506,6 +5548,9 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 {
 	int err;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	err = ext4_get_inode_loc(inode, iloc);
 	if (!err) {
 		BUFFER_TRACE(iloc->bh, "get_write_access");
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index d534399cf607..a4273ddb9922 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -16,6 +16,7 @@
 #include <linux/quotaops.h>
 #include <linux/uuid.h>
 #include <linux/uaccess.h>
+#include <linux/delay.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 
@@ -442,6 +443,52 @@ static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
 	return iflags;
 }
 
+int ext4_shutdown(struct super_block *sb, unsigned long arg)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	__u32 flags;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (get_user(flags, (__u32 __user *)arg))
+		return -EFAULT;
+
+	if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH)
+		return -EINVAL;
+
+	if (ext4_forced_shutdown(sbi))
+		return 0;
+
+	ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags);
+
+	switch (flags) {
+	case EXT4_GOING_FLAGS_DEFAULT:
+		freeze_bdev(sb->s_bdev);
+		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+		thaw_bdev(sb->s_bdev, sb);
+		break;
+	case EXT4_GOING_FLAGS_LOGFLUSH:
+		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+		if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
+			(void) ext4_force_commit(sb);
+			jbd2_journal_abort(sbi->s_journal, 0);
+		}
+		break;
+	case EXT4_GOING_FLAGS_NOLOGFLUSH:
+		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+		if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
+			msleep(100);
+			jbd2_journal_abort(sbi->s_journal, 0);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	clear_opt(sb, DISCARD);
+	return 0;
+}
+
 long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -893,6 +940,8 @@ resizefs_out:
 
 		return 0;
 	}
+	case EXT4_IOC_SHUTDOWN:
+		return ext4_shutdown(sb, arg);
 	default:
 		return -ENOTTY;
 	}
@@ -959,6 +1008,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case EXT4_IOC_SET_ENCRYPTION_POLICY:
 	case EXT4_IOC_GET_ENCRYPTION_PWSALT:
 	case EXT4_IOC_GET_ENCRYPTION_POLICY:
+	case EXT4_IOC_SHUTDOWN:
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 7ae43c59bc79..10c62de642c6 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1556,7 +1556,17 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block,
 		ex->fe_len += 1 << order;
 	}
 
-	BUG_ON(ex->fe_start + ex->fe_len > (1 << (e4b->bd_blkbits + 3)));
+	if (ex->fe_start + ex->fe_len > (1 << (e4b->bd_blkbits + 3))) {
+		/* Should never happen! (but apparently sometimes does?!?) */
+		WARN_ON(1);
+		ext4_error(e4b->bd_sb, "corruption or bug in mb_find_extent "
+			   "block=%d, order=%d needed=%d ex=%u/%d/%d@%u",
+			   block, order, needed, ex->fe_group, ex->fe_start,
+			   ex->fe_len, ex->fe_logical);
+		ex->fe_len = 0;
+		ex->fe_start = 0;
+		ex->fe_group = 0;
+	}
 	return ex->fe_len;
 }
 
@@ -2136,8 +2146,10 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 	 * We search using buddy data only if the order of the request
 	 * is greater than equal to the sbi_s_mb_order2_reqs
 	 * You can tune it via /sys/fs/ext4/<partition>/mb_order2_req
+	 * We also support searching for power-of-two requests only for
+	 * requests upto maximum buddy size we have constructed.
 	 */
-	if (i >= sbi->s_mb_order2_reqs) {
+	if (i >= sbi->s_mb_order2_reqs && i <= sb->s_blocksize_bits + 2) {
 		/*
 		 * This should tell if fe_len is exactly power of 2
 		 */
@@ -2207,7 +2219,7 @@ repeat:
 			}
 
 			ac->ac_groups_scanned++;
-			if (cr == 0 && ac->ac_2order < sb->s_blocksize_bits+2)
+			if (cr == 0)
 				ext4_mb_simple_scan_group(ac, &e4b);
 			else if (cr == 1 && sbi->s_stripe &&
 					!(ac->ac_g_ex.fe_len % sbi->s_stripe))
@@ -3123,6 +3135,13 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	if (ar->pright && start + size - 1 >= ar->lright)
 		size -= start + size - ar->lright;
 
+	/*
+	 * Trim allocation request for filesystems with artificially small
+	 * groups.
+	 */
+	if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb))
+		size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb);
+
 	end = start + size;
 
 	/* check we don't cross already preallocated blocks */
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index eadba919f26b..6ad612c576fc 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1378,6 +1378,8 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 		return NULL;
 
 	retval = ext4_fname_setup_filename(dir, d_name, 1, &fname);
+	if (retval == -ENOENT)
+		return NULL;
 	if (retval)
 		return ERR_PTR(retval);
 
@@ -1616,13 +1618,15 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 		    !fscrypt_has_permitted_context(dir, inode)) {
 			int nokey = ext4_encrypted_inode(inode) &&
 				!fscrypt_has_encryption_key(inode);
-			iput(inode);
-			if (nokey)
+			if (nokey) {
+				iput(inode);
 				return ERR_PTR(-ENOKEY);
+			}
 			ext4_warning(inode->i_sb,
 				     "Inconsistent encryption contexts: %lu/%lu",
 				     (unsigned long) dir->i_ino,
 				     (unsigned long) inode->i_ino);
+			iput(inode);
 			return ERR_PTR(-EPERM);
 		}
 	}
@@ -2935,6 +2939,9 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 	struct ext4_dir_entry_2 *de;
 	handle_t *handle = NULL;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+		return -EIO;
+
 	/* Initialize quotas before so that eventual writes go in
 	 * separate transaction */
 	retval = dquot_initialize(dir);
@@ -3008,6 +3015,9 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	struct ext4_dir_entry_2 *de;
 	handle_t *handle = NULL;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+		return -EIO;
+
 	trace_ext4_unlink_enter(dir, dentry);
 	/* Initialize quotas before so that eventual writes go
 	 * in separate transaction */
@@ -3078,6 +3088,9 @@ static int ext4_symlink(struct inode *dir,
 	struct fscrypt_str disk_link;
 	struct fscrypt_symlink_data *sd = NULL;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+		return -EIO;
+
 	disk_link.len = len + 1;
 	disk_link.name = (char *) symname;
 
@@ -3088,7 +3101,7 @@ static int ext4_symlink(struct inode *dir,
 		if (err)
 			return err;
 		if (!fscrypt_has_encryption_key(dir))
-			return -EPERM;
+			return -ENOKEY;
 		disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
 				 sizeof(struct fscrypt_symlink_data));
 		sd = kzalloc(disk_link.len, GFP_KERNEL);
@@ -3525,6 +3538,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 			EXT4_I(old_dentry->d_inode)->i_projid)))
 		return -EXDEV;
 
+	if ((ext4_encrypted_inode(old_dir) &&
+	     !fscrypt_has_encryption_key(old_dir)) ||
+	    (ext4_encrypted_inode(new_dir) &&
+	     !fscrypt_has_encryption_key(new_dir)))
+		return -ENOKEY;
+
 	retval = dquot_initialize(old.dir);
 	if (retval)
 		return retval;
@@ -3725,6 +3744,12 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int retval;
 	struct timespec ctime;
 
+	if ((ext4_encrypted_inode(old_dir) &&
+	     !fscrypt_has_encryption_key(old_dir)) ||
+	    (ext4_encrypted_inode(new_dir) &&
+	     !fscrypt_has_encryption_key(new_dir)))
+		return -ENOKEY;
+
 	if ((ext4_encrypted_inode(old_dir) ||
 	     ext4_encrypted_inode(new_dir)) &&
 	    (old_dir != new_dir) &&
@@ -3858,6 +3883,9 @@ static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry,
 			struct inode *new_dir, struct dentry *new_dentry,
 			unsigned int flags)
 {
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(old_dir->i_sb))))
+		return -EIO;
+
 	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
 		return -EINVAL;
 
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index d83b0f3c5fe9..208241b06662 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -24,7 +24,6 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/backing-dev.h>
-#include <linux/fscrypto.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -158,7 +157,7 @@ static int ext4_end_io(ext4_io_end_t *io)
 
 	io->handle = NULL;	/* Following call will use up the handle */
 	ret = ext4_convert_unwritten_extents(handle, inode, offset, size);
-	if (ret < 0) {
+	if (ret < 0 && !ext4_forced_shutdown(EXT4_SB(inode->i_sb))) {
 		ext4_msg(inode->i_sb, KERN_EMERG,
 			 "failed to convert unwritten extents to written "
 			 "extents -- potential data loss!  "
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index cf681004b196..c3ed9021b781 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -45,7 +45,8 @@ int ext4_resize_begin(struct super_block *sb)
 		return -EPERM;
 	}
 
-	if (test_and_set_bit_lock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags))
+	if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING,
+				  &EXT4_SB(sb)->s_ext4_flags))
 		ret = -EBUSY;
 
 	return ret;
@@ -53,7 +54,7 @@ int ext4_resize_begin(struct super_block *sb)
 
 void ext4_resize_end(struct super_block *sb)
 {
-	clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
+	clear_bit_unlock(EXT4_FLAGS_RESIZING, &EXT4_SB(sb)->s_ext4_flags);
 	smp_mb__after_atomic();
 }
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 66845a08a87a..2e03a0a88d92 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -438,6 +438,9 @@ void __ext4_error(struct super_block *sb, const char *function,
 	struct va_format vaf;
 	va_list args;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return;
+
 	if (ext4_error_ratelimit(sb)) {
 		va_start(args, fmt);
 		vaf.fmt = fmt;
@@ -459,6 +462,9 @@ void __ext4_error_inode(struct inode *inode, const char *function,
 	struct va_format vaf;
 	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return;
+
 	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
 	es->s_last_error_block = cpu_to_le64(block);
 	if (ext4_error_ratelimit(inode->i_sb)) {
@@ -491,6 +497,9 @@ void __ext4_error_file(struct file *file, const char *function,
 	struct inode *inode = file_inode(file);
 	char pathname[80], *path;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return;
+
 	es = EXT4_SB(inode->i_sb)->s_es;
 	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
 	if (ext4_error_ratelimit(inode->i_sb)) {
@@ -567,6 +576,9 @@ void __ext4_std_error(struct super_block *sb, const char *function,
 	char nbuf[16];
 	const char *errstr;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return;
+
 	/* Special case: if the error is EROFS, and we're not already
 	 * inside a transaction, then there's really no point in logging
 	 * an error. */
@@ -600,6 +612,9 @@ void __ext4_abort(struct super_block *sb, const char *function,
 	struct va_format vaf;
 	va_list args;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return;
+
 	save_error_info(sb, function, line);
 	va_start(args, fmt);
 	vaf.fmt = fmt;
@@ -695,6 +710,9 @@ __acquires(bitlock)
 	va_list args;
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return;
+
 	es->s_last_error_ino = cpu_to_le32(ino);
 	es->s_last_error_block = cpu_to_le64(block);
 	__save_error_info(sb, function, line);
@@ -825,6 +843,7 @@ static void ext4_put_super(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
+	int aborted = 0;
 	int i, err;
 
 	ext4_unregister_li_request(sb);
@@ -834,9 +853,10 @@ static void ext4_put_super(struct super_block *sb)
 	destroy_workqueue(sbi->rsv_conversion_wq);
 
 	if (sbi->s_journal) {
+		aborted = is_journal_aborted(sbi->s_journal);
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
-		if (err < 0)
+		if ((err < 0) && !aborted)
 			ext4_abort(sb, "Couldn't clean up the journal");
 	}
 
@@ -847,7 +867,7 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
 
-	if (!(sb->s_flags & MS_RDONLY)) {
+	if (!(sb->s_flags & MS_RDONLY) && !aborted) {
 		ext4_clear_feature_journal_needs_recovery(sb);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
 	}
@@ -1100,12 +1120,6 @@ static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
 				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
 }
 
-static int ext4_key_prefix(struct inode *inode, u8 **key)
-{
-	*key = EXT4_SB(inode->i_sb)->key_prefix;
-	return EXT4_SB(inode->i_sb)->key_prefix_size;
-}
-
 static int ext4_prepare_context(struct inode *inode)
 {
 	return ext4_convert_inline_data(inode);
@@ -1179,9 +1193,9 @@ static unsigned ext4_max_namelen(struct inode *inode)
 		EXT4_NAME_LEN;
 }
 
-static struct fscrypt_operations ext4_cryptops = {
+static const struct fscrypt_operations ext4_cryptops = {
+	.key_prefix		= "ext4:",
 	.get_context		= ext4_get_context,
-	.key_prefix		= ext4_key_prefix,
 	.prepare_context	= ext4_prepare_context,
 	.set_context		= ext4_set_context,
 	.dummy_context		= ext4_dummy_context,
@@ -1190,7 +1204,7 @@ static struct fscrypt_operations ext4_cryptops = {
 	.max_namelen		= ext4_max_namelen,
 };
 #else
-static struct fscrypt_operations ext4_cryptops = {
+static const struct fscrypt_operations ext4_cryptops = {
 	.is_encrypted		= ext4_encrypted_inode,
 };
 #endif
@@ -1290,7 +1304,7 @@ enum {
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
 	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
-	Opt_lazytime, Opt_nolazytime,
+	Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
 	Opt_dioread_nolock, Opt_dioread_lock,
@@ -1358,6 +1372,7 @@ static const match_table_t tokens = {
 	{Opt_delalloc, "delalloc"},
 	{Opt_lazytime, "lazytime"},
 	{Opt_nolazytime, "nolazytime"},
+	{Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"},
 	{Opt_nodelalloc, "nodelalloc"},
 	{Opt_removed, "mblk_io_submit"},
 	{Opt_removed, "nomblk_io_submit"},
@@ -1563,6 +1578,7 @@ static const struct mount_opts {
 #endif
 	{Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET},
 	{Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET},
+	{Opt_debug_want_extra_isize, 0, MOPT_GTE0},
 	{Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q},
 	{Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA,
 							MOPT_SET | MOPT_Q},
@@ -1676,6 +1692,8 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		if (arg == 0)
 			arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
 		sbi->s_commit_interval = HZ * arg;
+	} else if (token == Opt_debug_want_extra_isize) {
+		sbi->s_want_extra_isize = arg;
 	} else if (token == Opt_max_batch_time) {
 		sbi->s_max_batch_time = arg;
 	} else if (token == Opt_min_batch_time) {
@@ -2619,9 +2637,9 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
 
 	if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
 		ret = sbi->s_stripe;
-	else if (stripe_width <= sbi->s_blocks_per_group)
+	else if (stripe_width && stripe_width <= sbi->s_blocks_per_group)
 		ret = stripe_width;
-	else if (stride <= sbi->s_blocks_per_group)
+	else if (stride && stride <= sbi->s_blocks_per_group)
 		ret = stride;
 	else
 		ret = 0;
@@ -3842,7 +3860,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
 		   EXT4_DESC_PER_BLOCK(sb);
 	if (ext4_has_feature_meta_bg(sb)) {
-		if (le32_to_cpu(es->s_first_meta_bg) >= db_count) {
+		if (le32_to_cpu(es->s_first_meta_bg) > db_count) {
 			ext4_msg(sb, KERN_WARNING,
 				 "first meta block group too large: %u "
 				 "(group descriptor block count %u)",
@@ -3925,7 +3943,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 * root first: it may be modified in the journal!
 	 */
 	if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) {
-		if (ext4_load_journal(sb, es, journal_devnum))
+		err = ext4_load_journal(sb, es, journal_devnum);
+		if (err)
 			goto failed_mount3a;
 	} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
 		   ext4_has_feature_journal_needs_recovery(sb)) {
@@ -4087,7 +4106,8 @@ no_journal:
 		sb->s_flags |= MS_RDONLY;
 
 	/* determine the minimum size of new large inodes, if present */
-	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
+	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
+	    sbi->s_want_extra_isize == 0) {
 		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
 						     EXT4_GOOD_OLD_INODE_SIZE;
 		if (ext4_has_feature_extra_isize(sb)) {
@@ -4218,11 +4238,6 @@ no_journal:
 	ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
 
 	kfree(orig_data);
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	memcpy(sbi->key_prefix, EXT4_KEY_DESC_PREFIX,
-				EXT4_KEY_DESC_PREFIX_SIZE);
-	sbi->key_prefix_size = EXT4_KEY_DESC_PREFIX_SIZE;
-#endif
 	return 0;
 
 cantfind_ext4:
@@ -4720,6 +4735,9 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 	bool needs_barrier = false;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return 0;
+
 	trace_ext4_sync_fs(sb, wait);
 	flush_workqueue(sbi->rsv_conversion_wq);
 	/*
@@ -4803,7 +4821,7 @@ out:
  */
 static int ext4_unfreeze(struct super_block *sb)
 {
-	if (sb->s_flags & MS_RDONLY)
+	if ((sb->s_flags & MS_RDONLY) || ext4_forced_shutdown(EXT4_SB(sb)))
 		return 0;
 
 	if (EXT4_SB(sb)->s_journal) {
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 5a94fa52b74f..67636acf7624 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -411,6 +411,9 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name,
 {
 	int error;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (strlen(name) > 255)
 		return -ERANGE;
 
@@ -1188,16 +1191,14 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 	struct ext4_xattr_block_find bs = {
 		.s = { .not_found = -ENODATA, },
 	};
-	unsigned long no_expand;
+	int no_expand;
 	int error;
 
 	if (!name)
 		return -EINVAL;
 	if (strlen(name) > 255)
 		return -ERANGE;
-	down_write(&EXT4_I(inode)->xattr_sem);
-	no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
-	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_write_lock_xattr(inode, &no_expand);
 
 	error = ext4_reserve_inode_write(handle, inode, &is.iloc);
 	if (error)
@@ -1264,7 +1265,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		ext4_xattr_update_super_block(handle, inode->i_sb);
 		inode->i_ctime = current_time(inode);
 		if (!value)
-			ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+			no_expand = 0;
 		error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
 		/*
 		 * The bh is consumed by ext4_mark_iloc_dirty, even with
@@ -1278,9 +1279,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 cleanup:
 	brelse(is.iloc.bh);
 	brelse(bs.bh);
-	if (no_expand == 0)
-		ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	return error;
 }
 
@@ -1497,12 +1496,11 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 	int error = 0, tried_min_extra_isize = 0;
 	int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
 	int isize_diff;	/* How much do we need to grow i_extra_isize */
+	int no_expand;
+
+	if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
+		return 0;
 
-	down_write(&EXT4_I(inode)->xattr_sem);
-	/*
-	 * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
-	 */
-	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
 retry:
 	isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
 	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
@@ -1584,17 +1582,16 @@ shift:
 	EXT4_I(inode)->i_extra_isize = new_extra_isize;
 	brelse(bh);
 out:
-	ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	return 0;
 
 cleanup:
 	brelse(bh);
 	/*
-	 * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
-	 * size expansion failed.
+	 * Inode size expansion failed; don't try again
 	 */
-	up_write(&EXT4_I(inode)->xattr_sem);
+	no_expand = 1;
+	ext4_write_unlock_xattr(inode, &no_expand);
 	return error;
 }
 
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index a92e783fa057..099c8b670ef5 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -102,6 +102,38 @@ extern const struct xattr_handler ext4_xattr_security_handler;
 
 #define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c"
 
+/*
+ * The EXT4_STATE_NO_EXPAND is overloaded and used for two purposes.
+ * The first is to signal that there the inline xattrs and data are
+ * taking up so much space that we might as well not keep trying to
+ * expand it.  The second is that xattr_sem is taken for writing, so
+ * we shouldn't try to recurse into the inode expansion.  For this
+ * second case, we need to make sure that we take save and restore the
+ * NO_EXPAND state flag appropriately.
+ */
+static inline void ext4_write_lock_xattr(struct inode *inode, int *save)
+{
+	down_write(&EXT4_I(inode)->xattr_sem);
+	*save = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+}
+
+static inline int ext4_write_trylock_xattr(struct inode *inode, int *save)
+{
+	if (down_write_trylock(&EXT4_I(inode)->xattr_sem) == 0)
+		return 0;
+	*save = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	return 1;
+}
+
+static inline void ext4_write_unlock_xattr(struct inode *inode, int *save)
+{
+	if (*save == 0)
+		ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	up_write(&EXT4_I(inode)->xattr_sem);
+}
+
 extern ssize_t ext4_listxattr(struct dentry *, char *, size_t);
 
 extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 827c5daef4fc..18607fc5240d 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -268,7 +268,10 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 
 	err = fscrypt_setup_filename(dir, child, 1, &fname);
 	if (err) {
-		*res_page = ERR_PTR(err);
+		if (err == -ENOENT)
+			*res_page = NULL;
+		else
+			*res_page = ERR_PTR(err);
 		return NULL;
 	}
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2da8c3aa0ce5..069fc7277d8d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -22,7 +22,11 @@
 #include <linux/vmalloc.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
-#include <linux/fscrypto.h>
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+#include <linux/fscrypt_supp.h>
+#else
+#include <linux/fscrypt_notsupp.h>
+#endif
 #include <crypto/hash.h>
 
 #ifdef CONFIG_F2FS_CHECK_FS
@@ -760,10 +764,6 @@ enum {
 	MAX_TIME,
 };
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-#define F2FS_KEY_DESC_PREFIX "f2fs:"
-#define F2FS_KEY_DESC_PREFIX_SIZE 5
-#endif
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
 	struct proc_dir_entry *s_proc;		/* proc entry */
@@ -771,11 +771,6 @@ struct f2fs_sb_info {
 	int valid_super_block;			/* valid super block no */
 	unsigned long s_flag;				/* flags for sbi */
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	u8 key_prefix[F2FS_KEY_DESC_PREFIX_SIZE];
-	u8 key_prefix_size;
-#endif
-
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int blocks_per_blkz;		/* F2FS blocks per zone */
 	unsigned int log_blocks_per_blkz;	/* log2 F2FS blocks per zone */
@@ -2510,28 +2505,4 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
 #endif
 }
 
-#ifndef CONFIG_F2FS_FS_ENCRYPTION
-#define fscrypt_set_d_op(i)
-#define fscrypt_get_ctx			fscrypt_notsupp_get_ctx
-#define fscrypt_release_ctx		fscrypt_notsupp_release_ctx
-#define fscrypt_encrypt_page		fscrypt_notsupp_encrypt_page
-#define fscrypt_decrypt_page		fscrypt_notsupp_decrypt_page
-#define fscrypt_decrypt_bio_pages	fscrypt_notsupp_decrypt_bio_pages
-#define fscrypt_pullback_bio_page	fscrypt_notsupp_pullback_bio_page
-#define fscrypt_restore_control_page	fscrypt_notsupp_restore_control_page
-#define fscrypt_zeroout_range		fscrypt_notsupp_zeroout_range
-#define fscrypt_ioctl_set_policy	fscrypt_notsupp_ioctl_set_policy
-#define fscrypt_ioctl_get_policy	fscrypt_notsupp_ioctl_get_policy
-#define fscrypt_has_permitted_context	fscrypt_notsupp_has_permitted_context
-#define fscrypt_inherit_context		fscrypt_notsupp_inherit_context
-#define fscrypt_get_encryption_info	fscrypt_notsupp_get_encryption_info
-#define fscrypt_put_encryption_info	fscrypt_notsupp_put_encryption_info
-#define fscrypt_setup_filename		fscrypt_notsupp_setup_filename
-#define fscrypt_free_filename		fscrypt_notsupp_free_filename
-#define fscrypt_fname_encrypted_size	fscrypt_notsupp_fname_encrypted_size
-#define fscrypt_fname_alloc_buffer	fscrypt_notsupp_fname_alloc_buffer
-#define fscrypt_fname_free_buffer	fscrypt_notsupp_fname_free_buffer
-#define fscrypt_fname_disk_to_usr	fscrypt_notsupp_fname_disk_to_usr
-#define fscrypt_fname_usr_to_disk	fscrypt_notsupp_fname_usr_to_disk
-#endif
 #endif
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 56c19b0610a8..11cabcadb1a3 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -403,7 +403,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 			return err;
 
 		if (!fscrypt_has_encryption_key(dir))
-			return -EPERM;
+			return -ENOKEY;
 
 		disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
 				sizeof(struct fscrypt_symlink_data));
@@ -447,7 +447,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 			goto err_out;
 
 		if (!fscrypt_has_encryption_key(inode)) {
-			err = -EPERM;
+			err = -ENOKEY;
 			goto err_out;
 		}
 
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 46fd30d8af77..a831303bb777 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1156,12 +1156,6 @@ static int f2fs_get_context(struct inode *inode, void *ctx, size_t len)
 				ctx, len, NULL);
 }
 
-static int f2fs_key_prefix(struct inode *inode, u8 **key)
-{
-	*key = F2FS_I_SB(inode)->key_prefix;
-	return F2FS_I_SB(inode)->key_prefix_size;
-}
-
 static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
 							void *fs_data)
 {
@@ -1176,16 +1170,16 @@ static unsigned f2fs_max_namelen(struct inode *inode)
 			inode->i_sb->s_blocksize : F2FS_NAME_LEN;
 }
 
-static struct fscrypt_operations f2fs_cryptops = {
+static const struct fscrypt_operations f2fs_cryptops = {
+	.key_prefix	= "f2fs:",
 	.get_context	= f2fs_get_context,
-	.key_prefix	= f2fs_key_prefix,
 	.set_context	= f2fs_set_context,
 	.is_encrypted	= f2fs_encrypted_inode,
 	.empty_dir	= f2fs_empty_dir,
 	.max_namelen	= f2fs_max_namelen,
 };
 #else
-static struct fscrypt_operations f2fs_cryptops = {
+static const struct fscrypt_operations f2fs_cryptops = {
 	.is_encrypted	= f2fs_encrypted_inode,
 };
 #endif
@@ -1518,12 +1512,6 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	mutex_init(&sbi->wio_mutex[NODE]);
 	mutex_init(&sbi->wio_mutex[DATA]);
 	spin_lock_init(&sbi->cp_lock);
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	memcpy(sbi->key_prefix, F2FS_KEY_DESC_PREFIX,
-				F2FS_KEY_DESC_PREFIX_SIZE);
-	sbi->key_prefix_size = F2FS_KEY_DESC_PREFIX_SIZE;
-#endif
 }
 
 static int init_percpu_info(struct f2fs_sb_info *sbi)
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 4304072161aa..40d61077bead 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -542,6 +542,7 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
 		hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) {
 			if (invalidate)
 				set_bit(FSCACHE_OBJECT_RETIRED, &object->flags);
+			clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
 			fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL);
 		}
 	} else {
@@ -560,6 +561,10 @@ void __fscache_disable_cookie(struct fscache_cookie *cookie, bool invalidate)
 		wait_on_atomic_t(&cookie->n_active, fscache_wait_atomic_t,
 				 TASK_UNINTERRUPTIBLE);
 
+	/* Make sure any pending writes are cancelled. */
+	if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
+		fscache_invalidate_writes(cookie);
+
 	/* Reset the cookie state if it wasn't relinquished */
 	if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) {
 		atomic_inc(&cookie->n_active);
diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c
index 9b28649df3a1..a8aa00be4444 100644
--- a/fs/fscache/netfs.c
+++ b/fs/fscache/netfs.c
@@ -48,6 +48,7 @@ int __fscache_register_netfs(struct fscache_netfs *netfs)
 	cookie->flags		= 1 << FSCACHE_COOKIE_ENABLED;
 
 	spin_lock_init(&cookie->lock);
+	spin_lock_init(&cookie->stores_lock);
 	INIT_HLIST_HEAD(&cookie->backing_objects);
 
 	/* check the netfs type is not already present */
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 9e792e30f4db..7a182c87f378 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -30,6 +30,7 @@ static const struct fscache_state *fscache_look_up_object(struct fscache_object
 static const struct fscache_state *fscache_object_available(struct fscache_object *, int);
 static const struct fscache_state *fscache_parent_ready(struct fscache_object *, int);
 static const struct fscache_state *fscache_update_object(struct fscache_object *, int);
+static const struct fscache_state *fscache_object_dead(struct fscache_object *, int);
 
 #define __STATE_NAME(n) fscache_osm_##n
 #define STATE(n) (&__STATE_NAME(n))
@@ -91,7 +92,7 @@ static WORK_STATE(LOOKUP_FAILURE,	"LCFL", fscache_lookup_failure);
 static WORK_STATE(KILL_OBJECT,		"KILL", fscache_kill_object);
 static WORK_STATE(KILL_DEPENDENTS,	"KDEP", fscache_kill_dependents);
 static WORK_STATE(DROP_OBJECT,		"DROP", fscache_drop_object);
-static WORK_STATE(OBJECT_DEAD,		"DEAD", (void*)2UL);
+static WORK_STATE(OBJECT_DEAD,		"DEAD", fscache_object_dead);
 
 static WAIT_STATE(WAIT_FOR_INIT,	"?INI",
 		  TRANSIT_TO(INIT_OBJECT,	1 << FSCACHE_OBJECT_EV_NEW_CHILD));
@@ -229,6 +230,10 @@ execute_work_state:
 	event = -1;
 	if (new_state == NO_TRANSIT) {
 		_debug("{OBJ%x} %s notrans", object->debug_id, state->name);
+		if (unlikely(state == STATE(OBJECT_DEAD))) {
+			_leave(" [dead]");
+			return;
+		}
 		fscache_enqueue_object(object);
 		event_mask = object->oob_event_mask;
 		goto unmask_events;
@@ -239,7 +244,7 @@ execute_work_state:
 	object->state = state = new_state;
 
 	if (state->work) {
-		if (unlikely(state->work == ((void *)2UL))) {
+		if (unlikely(state == STATE(OBJECT_DEAD))) {
 			_leave(" [dead]");
 			return;
 		}
@@ -645,6 +650,12 @@ static const struct fscache_state *fscache_kill_object(struct fscache_object *ob
 	fscache_mark_object_dead(object);
 	object->oob_event_mask = 0;
 
+	if (test_bit(FSCACHE_OBJECT_RETIRED, &object->flags)) {
+		/* Reject any new read/write ops and abort any that are pending. */
+		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+		fscache_cancel_all_ops(object);
+	}
+
 	if (list_empty(&object->dependents) &&
 	    object->n_ops == 0 &&
 	    object->n_children == 0)
@@ -1077,3 +1088,20 @@ void fscache_object_mark_killed(struct fscache_object *object,
 	}
 }
 EXPORT_SYMBOL(fscache_object_mark_killed);
+
+/*
+ * The object is dead.  We can get here if an object gets queued by an event
+ * that would lead to its death (such as EV_KILL) when the dispatcher is
+ * already running (and so can be requeued) but hasn't yet cleared the event
+ * mask.
+ */
+static const struct fscache_state *fscache_object_dead(struct fscache_object *object,
+						       int event)
+{
+	if (!test_and_set_bit(FSCACHE_OBJECT_RUN_AFTER_DEAD,
+			      &object->flags))
+		return NO_TRANSIT;
+
+	WARN(true, "FS-Cache object redispatched after death");
+	return NO_TRANSIT;
+}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 4e06a27ed7f8..f11792672977 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -399,6 +399,10 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)
 static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
 {
 	spin_lock(&fiq->waitq.lock);
+	if (test_bit(FR_FINISHED, &req->flags)) {
+		spin_unlock(&fiq->waitq.lock);
+		return;
+	}
 	if (list_empty(&req->intr_entry)) {
 		list_add_tail(&req->intr_entry, &fiq->interrupts);
 		wake_up_locked(&fiq->waitq);
@@ -1372,6 +1376,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 		 * code can Oops if the buffer persists after module unload.
 		 */
 		bufs[page_nr].ops = &nosteal_pipe_buf_ops;
+		bufs[page_nr].flags = 0;
 		ret = add_to_pipe(pipe, &bufs[page_nr++]);
 		if (unlikely(ret < 0))
 			break;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 91307940c8ac..052f8d3c41cb 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -256,7 +256,7 @@ struct fuse_io_priv {
 
 #define FUSE_IO_PRIV_SYNC(f) \
 {					\
-	.refcnt = { ATOMIC_INIT(1) },	\
+	.refcnt = KREF_INIT(1),		\
 	.async = 0,			\
 	.file = f,			\
 }
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 6b039d7ce160..ed7a2e252ad8 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -143,8 +143,8 @@ static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
 /* This is the same as calling block_write_full_page, but it also
  * writes pages outside of i_size
  */
-int gfs2_write_full_page(struct page *page, get_block_t *get_block,
-			 struct writeback_control *wbc)
+static int gfs2_write_full_page(struct page *page, get_block_t *get_block,
+				struct writeback_control *wbc)
 {
 	struct inode * const inode = page->mapping->host;
 	loff_t i_size = i_size_read(inode);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index fc5da4cbe88c..01b97c012c6e 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -720,6 +720,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrp_list rlist;
+	struct gfs2_trans *tr;
 	u64 bn, bstart;
 	u32 blen, btotal;
 	__be64 *p;
@@ -728,6 +729,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	unsigned int revokes = 0;
 	int x;
 	int error;
+	int jblocks_rqsted;
 
 	error = gfs2_rindex_update(sdp);
 	if (error)
@@ -791,12 +793,17 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */
 		gfs2_rs_deltree(&ip->i_res);
 
-	error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE +
-				 RES_INDIRECT + RES_STATFS + RES_QUOTA,
-				 revokes);
+restart:
+	jblocks_rqsted = rg_blocks + RES_DINODE +
+		RES_INDIRECT + RES_STATFS + RES_QUOTA +
+		gfs2_struct2blk(sdp, revokes, sizeof(u64));
+	if (jblocks_rqsted > atomic_read(&sdp->sd_log_thresh2))
+		jblocks_rqsted = atomic_read(&sdp->sd_log_thresh2);
+	error = gfs2_trans_begin(sdp, jblocks_rqsted, revokes);
 	if (error)
 		goto out_rg_gunlock;
 
+	tr = current->journal_info;
 	down_write(&ip->i_rw_mutex);
 
 	gfs2_trans_add_meta(ip->i_gl, dibh);
@@ -810,6 +817,16 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 		if (!*p)
 			continue;
 
+		/* check for max reasonable journal transaction blocks */
+		if (tr->tr_num_buf_new + RES_STATFS +
+		    RES_QUOTA >= atomic_read(&sdp->sd_log_thresh2)) {
+			if (rg_blocks >= tr->tr_num_buf_new)
+				rg_blocks -= tr->tr_num_buf_new;
+			else
+				rg_blocks = 0;
+			break;
+		}
+
 		bn = be64_to_cpu(*p);
 
 		if (bstart + blen == bn)
@@ -827,6 +844,9 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 		*p = 0;
 		gfs2_add_inode_blocks(&ip->i_inode, -1);
 	}
+	if (p == bottom)
+		rg_blocks = 0;
+
 	if (bstart) {
 		__gfs2_free_blocks(ip, bstart, blen, metadata);
 		btotal += blen;
@@ -844,6 +864,9 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 
 	gfs2_trans_end(sdp);
 
+	if (rg_blocks)
+		goto restart;
+
 out_rg_gunlock:
 	gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs);
 out_rlist:
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 94f50cac91c6..a2d45db32cd5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1802,16 +1802,18 @@ void gfs2_glock_exit(void)
 
 static void gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
 {
-	do {
-		gi->gl = rhashtable_walk_next(&gi->hti);
+	while ((gi->gl = rhashtable_walk_next(&gi->hti))) {
 		if (IS_ERR(gi->gl)) {
 			if (PTR_ERR(gi->gl) == -EAGAIN)
 				continue;
 			gi->gl = NULL;
+			return;
 		}
-	/* Skip entries for other sb and dead entries */
-	} while ((gi->gl) && ((gi->sdp != gi->gl->gl_name.ln_sbd) ||
-			      __lockref_is_dead(&gi->gl->gl_lockref)));
+		/* Skip entries for other sb and dead entries */
+		if (gi->sdp == gi->gl->gl_name.ln_sbd &&
+		    !__lockref_is_dead(&gi->gl->gl_lockref))
+			return;
+	}
 }
 
 static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index a6a3389a07fc..c45084ac642d 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -470,15 +470,19 @@ struct gfs2_quota_data {
 	struct rcu_head qd_rcu;
 };
 
+enum {
+	TR_TOUCHED = 1,
+	TR_ATTACHED = 2,
+	TR_ALLOCED = 3,
+};
+
 struct gfs2_trans {
 	unsigned long tr_ip;
 
 	unsigned int tr_blocks;
 	unsigned int tr_revokes;
 	unsigned int tr_reserved;
-	unsigned int tr_touched:1;
-	unsigned int tr_attached:1;
-	unsigned int tr_alloced:1;
+	unsigned long tr_flags;
 
 	unsigned int tr_num_buf_new;
 	unsigned int tr_num_databuf_new;
@@ -794,6 +798,7 @@ struct gfs2_sbd {
 	atomic_t sd_log_thresh1;
 	atomic_t sd_log_thresh2;
 	atomic_t sd_log_blks_free;
+	atomic_t sd_log_blks_needed;
 	wait_queue_head_t sd_log_waitq;
 	wait_queue_head_t sd_logd_waitq;
 
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 27c00a16def0..f865b96374df 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -349,6 +349,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
 	if (gfs2_assert_warn(sdp, blks) ||
 	    gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
 		return -EINVAL;
+	atomic_add(blks, &sdp->sd_log_blks_needed);
 retry:
 	free_blocks = atomic_read(&sdp->sd_log_blks_free);
 	if (unlikely(free_blocks <= wanted)) {
@@ -370,6 +371,7 @@ retry:
 			wake_up(&sdp->sd_reserving_log_wait);
 		goto retry;
 	}
+	atomic_sub(blks, &sdp->sd_log_blks_needed);
 	trace_gfs2_log_blocks(sdp, -blks);
 
 	/*
@@ -797,7 +799,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 
 static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
 {
-	WARN_ON_ONCE(old->tr_attached != 1);
+	WARN_ON_ONCE(!test_bit(TR_ATTACHED, &old->tr_flags));
 
 	old->tr_num_buf_new	+= new->tr_num_buf_new;
 	old->tr_num_databuf_new	+= new->tr_num_databuf_new;
@@ -821,9 +823,9 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	if (sdp->sd_log_tr) {
 		gfs2_merge_trans(sdp->sd_log_tr, tr);
 	} else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
-		gfs2_assert_withdraw(sdp, tr->tr_alloced);
+		gfs2_assert_withdraw(sdp, test_bit(TR_ALLOCED, &tr->tr_flags));
 		sdp->sd_log_tr = tr;
-		tr->tr_attached = 1;
+		set_bit(TR_ATTACHED, &tr->tr_flags);
 	}
 
 	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
@@ -891,13 +893,16 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 
 static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
 {
-	return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1));
+	return (atomic_read(&sdp->sd_log_pinned) +
+		atomic_read(&sdp->sd_log_blks_needed) >=
+		atomic_read(&sdp->sd_log_thresh1));
 }
 
 static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
 {
 	unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);
-	return used_blocks >= atomic_read(&sdp->sd_log_thresh2);
+	return used_blocks + atomic_read(&sdp->sd_log_blks_needed) >=
+		atomic_read(&sdp->sd_log_thresh2);
 }
 
 /**
@@ -913,12 +918,15 @@ int gfs2_logd(void *data)
 	struct gfs2_sbd *sdp = data;
 	unsigned long t = 1;
 	DEFINE_WAIT(wait);
+	bool did_flush;
 
 	while (!kthread_should_stop()) {
 
+		did_flush = false;
 		if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
 			gfs2_ail1_empty(sdp);
 			gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+			did_flush = true;
 		}
 
 		if (gfs2_ail_flush_reqd(sdp)) {
@@ -926,9 +934,10 @@ int gfs2_logd(void *data)
 			gfs2_ail1_wait(sdp);
 			gfs2_ail1_empty(sdp);
 			gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+			did_flush = true;
 		}
 
-		if (!gfs2_ail_flush_reqd(sdp))
+		if (!gfs2_ail_flush_reqd(sdp) || did_flush)
 			wake_up(&sdp->sd_log_waitq);
 
 		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 49db8ef13fdf..663ffc135ef3 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -292,7 +292,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	wait_on_buffer(bh);
 	if (unlikely(!buffer_uptodate(bh))) {
 		struct gfs2_trans *tr = current->journal_info;
-		if (tr && tr->tr_touched)
+		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
 			gfs2_io_error_bh(sdp, bh);
 		brelse(bh);
 		*bhp = NULL;
@@ -319,7 +319,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
 
 	if (!buffer_uptodate(bh)) {
 		struct gfs2_trans *tr = current->journal_info;
-		if (tr && tr->tr_touched)
+		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
 			gfs2_io_error_bh(sdp, bh);
 		return -EIO;
 	}
@@ -345,7 +345,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, int meta)
 			tr->tr_num_buf_rm++;
 		else
 			tr->tr_num_databuf_rm++;
-		tr->tr_touched = 1;
+		set_bit(TR_TOUCHED, &tr->tr_flags);
 		was_pinned = 1;
 		brelse(bh);
 	}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index a34308df927f..b108e7ba81af 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -683,6 +683,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 		goto fail_jindex;
 	}
 
+	atomic_set(&sdp->sd_log_blks_needed, 0);
 	if (sdp->sd_args.ar_spectator) {
 		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
 		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
@@ -1226,7 +1227,7 @@ static int set_gfs2_super(struct super_block *s, void *data)
 	 * We set the bdi here to the queue backing, file systems can
 	 * overwrite this in ->fill_super()
 	 */
-	s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
+	s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info;
 	return 0;
 }
 
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 0c1bde395062..affef3c066e0 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -48,7 +48,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	tr->tr_blocks = blocks;
 	tr->tr_revokes = revokes;
 	tr->tr_reserved = 1;
-	tr->tr_alloced = 1;
+	set_bit(TR_ALLOCED, &tr->tr_flags);
 	if (blocks)
 		tr->tr_reserved += 6 + blocks;
 	if (revokes)
@@ -78,7 +78,8 @@ static void gfs2_print_trans(const struct gfs2_trans *tr)
 {
 	pr_warn("Transaction created at: %pSR\n", (void *)tr->tr_ip);
 	pr_warn("blocks=%u revokes=%u reserved=%u touched=%u\n",
-		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched);
+		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved,
+		test_bit(TR_TOUCHED, &tr->tr_flags));
 	pr_warn("Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
 		tr->tr_num_buf_new, tr->tr_num_buf_rm,
 		tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
@@ -89,12 +90,12 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
 {
 	struct gfs2_trans *tr = current->journal_info;
 	s64 nbuf;
-	int alloced = tr->tr_alloced;
+	int alloced = test_bit(TR_ALLOCED, &tr->tr_flags);
 
 	BUG_ON(!tr);
 	current->journal_info = NULL;
 
-	if (!tr->tr_touched) {
+	if (!test_bit(TR_TOUCHED, &tr->tr_flags)) {
 		gfs2_log_release(sdp, tr->tr_reserved);
 		if (alloced) {
 			kfree(tr);
@@ -112,8 +113,8 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
 		gfs2_print_trans(tr);
 
 	gfs2_log_commit(sdp, tr);
-	if (alloced && !tr->tr_attached)
-			kfree(tr);
+	if (alloced && !test_bit(TR_ATTACHED, &tr->tr_flags))
+		kfree(tr);
 	up_read(&sdp->sd_log_flush_lock);
 
 	if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
@@ -169,6 +170,10 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 	}
 
 	lock_buffer(bh);
+	if (buffer_pinned(bh)) {
+		set_bit(TR_TOUCHED, &tr->tr_flags);
+		goto out;
+	}
 	gfs2_log_lock(sdp);
 	bd = bh->b_private;
 	if (bd == NULL) {
@@ -182,7 +187,7 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 		gfs2_log_lock(sdp);
 	}
 	gfs2_assert(sdp, bd->bd_gl == gl);
-	tr->tr_touched = 1;
+	set_bit(TR_TOUCHED, &tr->tr_flags);
 	if (list_empty(&bd->bd_list)) {
 		set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
 		set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
@@ -191,45 +196,24 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 		list_add_tail(&bd->bd_list, &tr->tr_databuf);
 	}
 	gfs2_log_unlock(sdp);
+out:
 	unlock_buffer(bh);
 }
 
-static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
-{
-	struct gfs2_meta_header *mh;
-	struct gfs2_trans *tr;
-	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
-
-	tr = current->journal_info;
-	tr->tr_touched = 1;
-	if (!list_empty(&bd->bd_list))
-		return;
-	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
-	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
-	mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
-	if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
-		pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n",
-		       (unsigned long long)bd->bd_bh->b_blocknr);
-		BUG();
-	}
-	if (unlikely(state == SFS_FROZEN)) {
-		printk(KERN_INFO "GFS2:adding buf while frozen\n");
-		gfs2_assert_withdraw(sdp, 0);
-	}
-	gfs2_pin(sdp, bd->bd_bh);
-	mh->__pad0 = cpu_to_be64(0);
-	mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
-	list_add(&bd->bd_list, &tr->tr_buf);
-	tr->tr_num_buf_new++;
-}
-
 void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
 {
 
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_bufdata *bd;
+	struct gfs2_meta_header *mh;
+	struct gfs2_trans *tr = current->journal_info;
+	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
 
 	lock_buffer(bh);
+	if (buffer_pinned(bh)) {
+		set_bit(TR_TOUCHED, &tr->tr_flags);
+		goto out;
+	}
 	gfs2_log_lock(sdp);
 	bd = bh->b_private;
 	if (bd == NULL) {
@@ -245,8 +229,29 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
 		gfs2_log_lock(sdp);
 	}
 	gfs2_assert(sdp, bd->bd_gl == gl);
-	meta_lo_add(sdp, bd);
+	set_bit(TR_TOUCHED, &tr->tr_flags);
+	if (!list_empty(&bd->bd_list))
+		goto out_unlock;
+	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
+	mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
+	if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
+		pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n",
+		       (unsigned long long)bd->bd_bh->b_blocknr);
+		BUG();
+	}
+	if (unlikely(state == SFS_FROZEN)) {
+		printk(KERN_INFO "GFS2:adding buf while frozen\n");
+		gfs2_assert_withdraw(sdp, 0);
+	}
+	gfs2_pin(sdp, bd->bd_bh);
+	mh->__pad0 = cpu_to_be64(0);
+	mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+	list_add(&bd->bd_list, &tr->tr_buf);
+	tr->tr_num_buf_new++;
+out_unlock:
 	gfs2_log_unlock(sdp);
+out:
 	unlock_buffer(bh);
 }
 
@@ -256,7 +261,7 @@ void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 
 	BUG_ON(!list_empty(&bd->bd_list));
 	gfs2_add_revoke(sdp, bd);
-	tr->tr_touched = 1;
+	set_bit(TR_TOUCHED, &tr->tr_flags);
 	tr->tr_num_revoke++;
 }
 
diff --git a/fs/iomap.c b/fs/iomap.c
index 354a123f170e..a51cb4c07d4d 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -114,6 +114,9 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 
 	BUG_ON(pos + len > iomap->offset + iomap->length);
 
+	if (fatal_signal_pending(current))
+		return -EINTR;
+
 	page = grab_cache_page_write_begin(inode->i_mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8c514367ba5a..b6b194ec1b4f 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -393,7 +393,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	/* Do we need to erase the effects of a prior jbd2_journal_flush? */
 	if (journal->j_flags & JBD2_FLUSHED) {
 		jbd_debug(3, "super block updated\n");
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		/*
 		 * We hold j_checkpoint_mutex so tail cannot change under us.
 		 * We don't need any special data guarantees for writing sb
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a097048ed1a3..a1a359bfcc9c 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -276,11 +276,11 @@ loop:
 	goto loop;
 
 end_loop:
-	write_unlock(&journal->j_state_lock);
 	del_timer_sync(&journal->j_commit_timer);
 	journal->j_task = NULL;
 	wake_up(&journal->j_wait_done_commit);
 	jbd_debug(1, "Journal thread exiting.\n");
+	write_unlock(&journal->j_state_lock);
 	return 0;
 }
 
@@ -944,7 +944,7 @@ out:
  */
 void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 {
-	mutex_lock(&journal->j_checkpoint_mutex);
+	mutex_lock_io(&journal->j_checkpoint_mutex);
 	if (tid_gt(tid, journal->j_tail_sequence))
 		__jbd2_update_log_tail(journal, tid, block);
 	mutex_unlock(&journal->j_checkpoint_mutex);
@@ -1304,7 +1304,7 @@ static int journal_reset(journal_t *journal)
 		journal->j_flags |= JBD2_FLUSHED;
 	} else {
 		/* Lock here to make assertions happy... */
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		/*
 		 * Update log tail information. We use REQ_FUA since new
 		 * transaction will start reusing journal space and so we
@@ -1691,7 +1691,7 @@ int jbd2_journal_destroy(journal_t *journal)
 	spin_lock(&journal->j_list_lock);
 	while (journal->j_checkpoint_transactions != NULL) {
 		spin_unlock(&journal->j_list_lock);
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		err = jbd2_log_do_checkpoint(journal);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 		/*
@@ -1713,7 +1713,7 @@ int jbd2_journal_destroy(journal_t *journal)
 
 	if (journal->j_sb_buffer) {
 		if (!is_journal_aborted(journal)) {
-			mutex_lock(&journal->j_checkpoint_mutex);
+			mutex_lock_io(&journal->j_checkpoint_mutex);
 
 			write_lock(&journal->j_state_lock);
 			journal->j_tail_sequence =
@@ -1955,7 +1955,7 @@ int jbd2_journal_flush(journal_t *journal)
 	spin_lock(&journal->j_list_lock);
 	while (!err && journal->j_checkpoint_transactions != NULL) {
 		spin_unlock(&journal->j_list_lock);
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		err = jbd2_log_do_checkpoint(journal);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 		spin_lock(&journal->j_list_lock);
@@ -1965,7 +1965,7 @@ int jbd2_journal_flush(journal_t *journal)
 	if (is_journal_aborted(journal))
 		return -EIO;
 
-	mutex_lock(&journal->j_checkpoint_mutex);
+	mutex_lock_io(&journal->j_checkpoint_mutex);
 	if (!err) {
 		err = jbd2_cleanup_journal_tail(journal);
 		if (err < 0) {
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index e1652665bd93..5e659ee08d6a 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1863,7 +1863,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
 
 	__blist_del_buffer(list, jh);
 	jh->b_jlist = BJ_None;
-	if (test_clear_buffer_jbddirty(bh))
+	if (transaction && is_journal_aborted(transaction->t_journal))
+		clear_buffer_jbddirty(bh);
+	else if (test_clear_buffer_jbddirty(bh))
 		mark_buffer_dirty(bh);	/* Expose it to the VM */
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ecc151697fd4..0a0eaecf9676 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2700,7 +2700,8 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata,
 		sattr->ia_valid |= ATTR_MTIME;
 
 	/* Except MODE, it seems harmless of setting twice. */
-	if ((attrset[1] & FATTR4_WORD1_MODE))
+	if (opendata->o_arg.createmode != NFS4_CREATE_EXCLUSIVE &&
+		attrset[1] & FATTR4_WORD1_MODE)
 		sattr->ia_valid &= ~ATTR_MODE;
 
 	if (attrset[2] & FATTR4_WORD2_SECURITY_LABEL)
@@ -8490,6 +8491,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 		goto out;
 	}
 
+	nfs4_sequence_free_slot(&lgp->res.seq_res);
 	err = nfs4_handle_exception(server, nfs4err, exception);
 	if (!status) {
 		if (exception->retry)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 90e6193ce6be..daeb94e3acd4 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1091,6 +1091,7 @@ static void nfs_increment_seqid(int status, struct nfs_seqid *seqid)
 		case -NFS4ERR_BADXDR:
 		case -NFS4ERR_RESOURCE:
 		case -NFS4ERR_NOFILEHANDLE:
+		case -NFS4ERR_MOVED:
 			/* Non-seqid mutating errors */
 			return;
 	};
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 59554f3adf29..dd042498ce7c 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1200,10 +1200,10 @@ _pnfs_return_layout(struct inode *ino)
 
 	send = pnfs_prepare_layoutreturn(lo, &stateid, NULL);
 	spin_unlock(&ino->i_lock);
-	pnfs_free_lseg_list(&tmp_list);
 	if (send)
 		status = pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true);
 out_put_layout_hdr:
+	pnfs_free_lseg_list(&tmp_list);
 	pnfs_put_layout_hdr(lo);
 out:
 	dprintk("<-- %s status: %d\n", __func__, status);
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 47febcf99185..20b1c17320d5 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -104,6 +104,7 @@ config NFSD_SCSILAYOUT
 	depends on NFSD_V4 && BLOCK
 	select NFSD_PNFS
 	select EXPORTFS_BLOCK_OPS
+	select BLK_SCSI_REQUEST
 	help
 	  This option enables support for the exporting pNFS SCSI layouts
 	  in the kernel's NFS server. The pNFS SCSI layout enables NFS
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 0780ff864539..a06115e31612 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -10,6 +10,7 @@
 #include <linux/nfsd/debug.h>
 #include <scsi/scsi_proto.h>
 #include <scsi/scsi_common.h>
+#include <scsi/scsi_request.h>
 
 #include "blocklayoutxdr.h"
 #include "pnfs.h"
@@ -213,6 +214,7 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev,
 {
 	struct request_queue *q = bdev->bd_disk->queue;
 	struct request *rq;
+	struct scsi_request *req;
 	size_t bufflen = 252, len, id_len;
 	u8 *buf, *d, type, assoc;
 	int error;
@@ -221,23 +223,24 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev,
 	if (!buf)
 		return -ENOMEM;
 
-	rq = blk_get_request(q, READ, GFP_KERNEL);
+	rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
 	if (IS_ERR(rq)) {
 		error = -ENOMEM;
 		goto out_free_buf;
 	}
-	blk_rq_set_block_pc(rq);
+	req = scsi_req(rq);
+	scsi_req_init(rq);
 
 	error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL);
 	if (error)
 		goto out_put_request;
 
-	rq->cmd[0] = INQUIRY;
-	rq->cmd[1] = 1;
-	rq->cmd[2] = 0x83;
-	rq->cmd[3] = bufflen >> 8;
-	rq->cmd[4] = bufflen & 0xff;
-	rq->cmd_len = COMMAND_SIZE(INQUIRY);
+	req->cmd[0] = INQUIRY;
+	req->cmd[1] = 1;
+	req->cmd[2] = 0x83;
+	req->cmd[3] = bufflen >> 8;
+	req->cmd[4] = bufflen & 0xff;
+	req->cmd_len = COMMAND_SIZE(INQUIRY);
 
 	error = blk_execute_rq(rq->q, NULL, rq, 1);
 	if (error) {
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 596205d939a1..1fc07a9c70e9 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -223,10 +223,11 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
 	struct nfs4_layout_stateid *ls;
 	struct nfs4_stid *stp;
 
-	stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache);
+	stp = nfs4_alloc_stid(cstate->clp, nfs4_layout_stateid_cache,
+					nfsd4_free_layout_stateid);
 	if (!stp)
 		return NULL;
-	stp->sc_free = nfsd4_free_layout_stateid;
+
 	get_nfs4_file(fp);
 	stp->sc_file = fp;
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4b4beaaa4eaa..a0dee8ae9f97 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -633,8 +633,8 @@ out:
 	return co;
 }
 
-struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
-					 struct kmem_cache *slab)
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
+				  void (*sc_free)(struct nfs4_stid *))
 {
 	struct nfs4_stid *stid;
 	int new_id;
@@ -650,6 +650,8 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
 	idr_preload_end();
 	if (new_id < 0)
 		goto out_free;
+
+	stid->sc_free = sc_free;
 	stid->sc_client = cl;
 	stid->sc_stateid.si_opaque.so_id = new_id;
 	stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
@@ -675,15 +677,12 @@ out_free:
 static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp)
 {
 	struct nfs4_stid *stid;
-	struct nfs4_ol_stateid *stp;
 
-	stid = nfs4_alloc_stid(clp, stateid_slab);
+	stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid);
 	if (!stid)
 		return NULL;
 
-	stp = openlockstateid(stid);
-	stp->st_stid.sc_free = nfs4_free_ol_stateid;
-	return stp;
+	return openlockstateid(stid);
 }
 
 static void nfs4_free_deleg(struct nfs4_stid *stid)
@@ -781,11 +780,10 @@ alloc_init_deleg(struct nfs4_client *clp, struct svc_fh *current_fh,
 		goto out_dec;
 	if (delegation_blocked(&current_fh->fh_handle))
 		goto out_dec;
-	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
+	dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg));
 	if (dp == NULL)
 		goto out_dec;
 
-	dp->dl_stid.sc_free = nfs4_free_deleg;
 	/*
 	 * delegation seqid's are never incremented.  The 4.1 special
 	 * meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -5580,7 +5578,6 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
 	stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner);
 	get_nfs4_file(fp);
 	stp->st_stid.sc_file = fp;
-	stp->st_stid.sc_free = nfs4_free_lock_stateid;
 	stp->st_access_bmap = 0;
 	stp->st_deny_bmap = open_stp->st_deny_bmap;
 	stp->st_openstp = open_stp;
@@ -5623,7 +5620,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi,
 	lst = find_lock_stateid(lo, fi);
 	if (lst == NULL) {
 		spin_unlock(&clp->cl_lock);
-		ns = nfs4_alloc_stid(clp, stateid_slab);
+		ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid);
 		if (ns == NULL)
 			return NULL;
 
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index c9399366f9df..4516e8b7d776 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -603,8 +603,8 @@ extern __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp,
 __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
 		     stateid_t *stateid, unsigned char typemask,
 		     struct nfs4_stid **s, struct nfsd_net *nn);
-struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
-		struct kmem_cache *slab);
+struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab,
+				  void (*sc_free)(struct nfs4_stid *));
 void nfs4_unhash_stid(struct nfs4_stid *s);
 void nfs4_put_stid(struct nfs4_stid *s);
 void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid);
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 12eeae62a2b1..e1872f36147f 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1068,7 +1068,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_time_gran = 1;
 	sb->s_max_links = NILFS_LINK_MAX;
 
-	sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info;
+	sb->s_bdi = bdev_get_queue(sb->s_bdev)->backing_dev_info;
 
 	err = load_nilfs(nilfs, sb);
 	if (err)
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index bbc175d4213d..a4c46221755e 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -31,7 +31,6 @@ static bool should_merge(struct fsnotify_event *old_fsn,
 static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 {
 	struct fsnotify_event *test_event;
-	bool do_merge = false;
 
 	pr_debug("%s: list=%p event=%p\n", __func__, list, event);
 
@@ -47,16 +46,12 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 
 	list_for_each_entry_reverse(test_event, list, list) {
 		if (should_merge(test_event, event)) {
-			do_merge = true;
-			break;
+			test_event->mask |= event->mask;
+			return 1;
 		}
 	}
 
-	if (!do_merge)
-		return 0;
-
-	test_event->mask |= event->mask;
-	return 1;
+	return 0;
 }
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 27d1242c8383..564c504d6efd 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -349,7 +349,7 @@ static void sc_show_sock_container(struct seq_file *seq,
 		   "  func key:        0x%08x\n"
 		   "  func type:       %u\n",
 		   sc,
-		   atomic_read(&sc->sc_kref.refcount),
+		   kref_read(&sc->sc_kref),
 		   &saddr, inet ? ntohs(sport) : 0,
 		   &daddr, inet ? ntohs(dport) : 0,
 		   sc->sc_node->nd_name,
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index d4b5c81f0445..ec000575e863 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -97,7 +97,7 @@
 	typeof(sc) __sc = (sc);						\
 	mlog(ML_SOCKET, "[sc %p refs %d sock %p node %u page %p "	\
 	     "pg_off %zu] " fmt, __sc,					\
-	     atomic_read(&__sc->sc_kref.refcount), __sc->sc_sock,	\
+	     kref_read(&__sc->sc_kref), __sc->sc_sock,	\
 	    __sc->sc_node->nd_num, __sc->sc_page, __sc->sc_page_off ,	\
 	    ##args);							\
 } while (0)
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index e7b760deefae..9b984cae4c4e 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -81,7 +81,7 @@ static void __dlm_print_lock(struct dlm_lock *lock)
 	       lock->ml.type, lock->ml.convert_type, lock->ml.node,
 	       dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
 	       dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
-	       atomic_read(&lock->lock_refs.refcount),
+	       kref_read(&lock->lock_refs),
 	       (list_empty(&lock->ast_list) ? 'y' : 'n'),
 	       (lock->ast_pending ? 'y' : 'n'),
 	       (list_empty(&lock->bast_list) ? 'y' : 'n'),
@@ -106,7 +106,7 @@ void __dlm_print_one_lock_resource(struct dlm_lock_resource *res)
 	printk("lockres: %s, owner=%u, state=%u\n",
 	       buf, res->owner, res->state);
 	printk("  last used: %lu, refcnt: %u, on purge list: %s\n",
-	       res->last_used, atomic_read(&res->refs.refcount),
+	       res->last_used, kref_read(&res->refs),
 	       list_empty(&res->purge) ? "no" : "yes");
 	printk("  on dirty list: %s, on reco list: %s, "
 	       "migrating pending: %s\n",
@@ -298,7 +298,7 @@ static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len)
 			mle_type, mle->master, mle->new_master,
 			!list_empty(&mle->hb_events),
 			!!mle->inuse,
-			atomic_read(&mle->mle_refs.refcount));
+			kref_read(&mle->mle_refs));
 
 	out += snprintf(buf + out, len - out, "Maybe=");
 	out += stringify_nodemap(mle->maybe_map, O2NM_MAX_NODES,
@@ -494,7 +494,7 @@ static int dump_lock(struct dlm_lock *lock, int list_type, char *buf, int len)
 		       lock->ast_pending, lock->bast_pending,
 		       lock->convert_pending, lock->lock_pending,
 		       lock->cancel_pending, lock->unlock_pending,
-		       atomic_read(&lock->lock_refs.refcount));
+		       kref_read(&lock->lock_refs));
 	spin_unlock(&lock->spinlock);
 
 	return out;
@@ -521,7 +521,7 @@ static int dump_lockres(struct dlm_lock_resource *res, char *buf, int len)
 			!list_empty(&res->recovering),
 			res->inflight_locks, res->migration_pending,
 			atomic_read(&res->asts_reserved),
-			atomic_read(&res->refs.refcount));
+			kref_read(&res->refs));
 
 	/* refmap */
 	out += snprintf(buf + out, len - out, "RMAP:");
@@ -777,7 +777,7 @@ static int debug_state_print(struct dlm_ctxt *dlm, char *buf, int len)
 	/* Purge Count: xxx  Refs: xxx */
 	out += snprintf(buf + out, len - out,
 			"Purge Count: %d  Refs: %d\n", dlm->purge_count,
-			atomic_read(&dlm->dlm_refs.refcount));
+			kref_read(&dlm->dlm_refs));
 
 	/* Dead Node: xxx */
 	out += snprintf(buf + out, len - out,
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 733e4e79c8e2..32fd261ae13d 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -2072,7 +2072,7 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	INIT_LIST_HEAD(&dlm->dlm_eviction_callbacks);
 
 	mlog(0, "context init: refcount %u\n",
-		  atomic_read(&dlm->dlm_refs.refcount));
+		  kref_read(&dlm->dlm_refs));
 
 leave:
 	if (ret < 0 && dlm) {
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index a464c8088170..7025d8c27999 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -233,7 +233,7 @@ static void __dlm_put_mle(struct dlm_master_list_entry *mle)
 
 	assert_spin_locked(&dlm->spinlock);
 	assert_spin_locked(&dlm->master_lock);
-	if (!atomic_read(&mle->mle_refs.refcount)) {
+	if (!kref_read(&mle->mle_refs)) {
 		/* this may or may not crash, but who cares.
 		 * it's a BUG. */
 		mlog(ML_ERROR, "bad mle: %p\n", mle);
@@ -1124,9 +1124,9 @@ recheck:
 		unsigned long timeo = msecs_to_jiffies(DLM_MASTERY_TIMEOUT_MS);
 
 		/*
-		if (atomic_read(&mle->mle_refs.refcount) < 2)
+		if (kref_read(&mle->mle_refs) < 2)
 			mlog(ML_ERROR, "mle (%p) refs=%d, name=%.*s\n", mle,
-			atomic_read(&mle->mle_refs.refcount),
+			kref_read(&mle->mle_refs),
 			res->lockname.len, res->lockname.name);
 		*/
 		atomic_set(&mle->woken, 0);
@@ -1979,7 +1979,7 @@ ok:
 		 * on this mle. */
 		spin_lock(&dlm->master_lock);
 
-		rr = atomic_read(&mle->mle_refs.refcount);
+		rr = kref_read(&mle->mle_refs);
 		if (mle->inuse > 0) {
 			if (extra_ref && rr < 3)
 				err = 1;
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 1082b2c3014b..63d701cd1e2e 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -251,7 +251,7 @@ leave:
 		mlog(0, "lock %u:%llu should be gone now! refs=%d\n",
 		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
 		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
-		     atomic_read(&lock->lock_refs.refcount)-1);
+		     kref_read(&lock->lock_refs)-1);
 		dlm_lock_put(lock);
 	}
 	if (actions & DLM_UNLOCK_CALL_AST)
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 51a4213afa2e..fe12b519d09b 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -401,8 +401,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	unsigned long long start_time;
 	unsigned long cmin_flt = 0, cmaj_flt = 0;
 	unsigned long  min_flt = 0,  maj_flt = 0;
-	cputime_t cutime, cstime, utime, stime;
-	cputime_t cgtime, gtime;
+	u64 cutime, cstime, utime, stime;
+	u64 cgtime, gtime;
 	unsigned long rsslim = 0;
 	char tcomm[sizeof(task->comm)];
 	unsigned long flags;
@@ -497,10 +497,10 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	seq_put_decimal_ull(m, " ", cmin_flt);
 	seq_put_decimal_ull(m, " ", maj_flt);
 	seq_put_decimal_ull(m, " ", cmaj_flt);
-	seq_put_decimal_ull(m, " ", cputime_to_clock_t(utime));
-	seq_put_decimal_ull(m, " ", cputime_to_clock_t(stime));
-	seq_put_decimal_ll(m, " ", cputime_to_clock_t(cutime));
-	seq_put_decimal_ll(m, " ", cputime_to_clock_t(cstime));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(utime));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(stime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cutime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cstime));
 	seq_put_decimal_ll(m, " ", priority);
 	seq_put_decimal_ll(m, " ", nice);
 	seq_put_decimal_ll(m, " ", num_threads);
@@ -542,8 +542,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	seq_put_decimal_ull(m, " ", task->rt_priority);
 	seq_put_decimal_ull(m, " ", task->policy);
 	seq_put_decimal_ull(m, " ", delayacct_blkio_ticks(task));
-	seq_put_decimal_ull(m, " ", cputime_to_clock_t(gtime));
-	seq_put_decimal_ll(m, " ", cputime_to_clock_t(cgtime));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(gtime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cgtime));
 
 	if (mm && permitted) {
 		seq_put_decimal_ull(m, " ", mm->start_data);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 8e7e61b28f31..b1f7d30e96c2 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2179,7 +2179,7 @@ static const struct file_operations proc_map_files_operations = {
 	.llseek		= generic_file_llseek,
 };
 
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS)
 struct timers_private {
 	struct pid *pid;
 	struct task_struct *task;
@@ -2936,7 +2936,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
 	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS)
 	REG("timers",	  S_IRUGO, proc_timers_operations),
 #endif
 	REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations),
@@ -3179,6 +3179,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 	     iter.tgid += 1, iter = next_tgid(ns, iter)) {
 		char name[PROC_NUMBUF];
 		int len;
+
+		cond_resched();
 		if (!has_pid_permissions(ns, iter.task, 2))
 			continue;
 
diff --git a/fs/proc/page.c b/fs/proc/page.c
index a2066e6dee90..2726536489b1 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -173,7 +173,8 @@ u64 stable_page_flags(struct page *page)
 	u |= kpf_copy_bit(k, KPF_ACTIVE,	PG_active);
 	u |= kpf_copy_bit(k, KPF_RECLAIM,	PG_reclaim);
 
-	u |= kpf_copy_bit(k, KPF_SWAPCACHE,	PG_swapcache);
+	if (PageSwapCache(page))
+		u |= 1 << KPF_SWAPCACHE;
 	u |= kpf_copy_bit(k, KPF_SWAPBACKED,	PG_swapbacked);
 
 	u |= kpf_copy_bit(k, KPF_UNEVICTABLE,	PG_unevictable);
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index d700c42b3572..e47c3e8c4dfe 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -21,9 +21,9 @@
 
 #ifdef arch_idle_time
 
-static cputime64_t get_idle_time(int cpu)
+static u64 get_idle_time(int cpu)
 {
-	cputime64_t idle;
+	u64 idle;
 
 	idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
 	if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
@@ -31,9 +31,9 @@ static cputime64_t get_idle_time(int cpu)
 	return idle;
 }
 
-static cputime64_t get_iowait_time(int cpu)
+static u64 get_iowait_time(int cpu)
 {
-	cputime64_t iowait;
+	u64 iowait;
 
 	iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
 	if (cpu_online(cpu) && nr_iowait_cpu(cpu))
@@ -45,32 +45,32 @@ static cputime64_t get_iowait_time(int cpu)
 
 static u64 get_idle_time(int cpu)
 {
-	u64 idle, idle_time = -1ULL;
+	u64 idle, idle_usecs = -1ULL;
 
 	if (cpu_online(cpu))
-		idle_time = get_cpu_idle_time_us(cpu, NULL);
+		idle_usecs = get_cpu_idle_time_us(cpu, NULL);
 
-	if (idle_time == -1ULL)
+	if (idle_usecs == -1ULL)
 		/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
 		idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
 	else
-		idle = usecs_to_cputime64(idle_time);
+		idle = idle_usecs * NSEC_PER_USEC;
 
 	return idle;
 }
 
 static u64 get_iowait_time(int cpu)
 {
-	u64 iowait, iowait_time = -1ULL;
+	u64 iowait, iowait_usecs = -1ULL;
 
 	if (cpu_online(cpu))
-		iowait_time = get_cpu_iowait_time_us(cpu, NULL);
+		iowait_usecs = get_cpu_iowait_time_us(cpu, NULL);
 
-	if (iowait_time == -1ULL)
+	if (iowait_usecs == -1ULL)
 		/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
 		iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
 	else
-		iowait = usecs_to_cputime64(iowait_time);
+		iowait = iowait_usecs * NSEC_PER_USEC;
 
 	return iowait;
 }
@@ -115,16 +115,16 @@ static int show_stat(struct seq_file *p, void *v)
 	}
 	sum += arch_irq_stat();
 
-	seq_put_decimal_ull(p, "cpu  ", cputime64_to_clock_t(user));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice));
+	seq_put_decimal_ull(p, "cpu  ", nsec_to_clock_t(user));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
 	seq_putc(p, '\n');
 
 	for_each_online_cpu(i) {
@@ -140,16 +140,16 @@ static int show_stat(struct seq_file *p, void *v)
 		guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
 		guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
 		seq_printf(p, "cpu%d", i);
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(user));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
 		seq_putc(p, '\n');
 	}
 	seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 33de567c25af..7981c4ffe787 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -5,23 +5,20 @@
 #include <linux/seq_file.h>
 #include <linux/time.h>
 #include <linux/kernel_stat.h>
-#include <linux/cputime.h>
 
 static int uptime_proc_show(struct seq_file *m, void *v)
 {
 	struct timespec uptime;
 	struct timespec idle;
-	u64 idletime;
 	u64 nsec;
 	u32 rem;
 	int i;
 
-	idletime = 0;
+	nsec = 0;
 	for_each_possible_cpu(i)
-		idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
+		nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
 
 	get_monotonic_boottime(&uptime);
-	nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC;
 	idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
 	idle.tv_nsec = rem;
 	seq_printf(m, "%lu.%02lu %lu.%02lu\n",
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 27c059e1760a..1d887efaaf71 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -280,7 +280,7 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 					   1, id, type, PSTORE_TYPE_PMSG, 0);
 
 	/* ftrace is last since it may want to dynamically allocate memory. */
-	if (!prz_ok(prz)) {
+	if (!prz_ok(prz) && cxt->fprzs) {
 		if (!(cxt->flags & RAMOOPS_FLAG_FTRACE_PER_CPU)) {
 			prz = ramoops_get_next_prz(cxt->fprzs,
 					&cxt->ftrace_read_cnt, 1, id, type,
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index d0f8a38dfafa..0186fe6d39f3 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -74,6 +74,7 @@
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/uaccess.h>
+#include <linux/major.h>
 #include "internal.h"
 
 static struct kmem_cache *romfs_inode_cachep;
@@ -416,7 +417,22 @@ static void romfs_destroy_inode(struct inode *inode)
 static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
-	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+	u64 id = 0;
+
+	/* When calling huge_encode_dev(),
+	 * use sb->s_bdev->bd_dev when,
+	 *   - CONFIG_ROMFS_ON_BLOCK defined
+	 * use sb->s_dev when,
+	 *   - CONFIG_ROMFS_ON_BLOCK undefined and
+	 *   - CONFIG_ROMFS_ON_MTD defined
+	 * leave id as 0 when,
+	 *   - CONFIG_ROMFS_ON_BLOCK undefined and
+	 *   - CONFIG_ROMFS_ON_MTD undefined
+	 */
+	if (sb->s_bdev)
+		id = huge_encode_dev(sb->s_bdev->bd_dev);
+	else if (sb->s_dev)
+		id = huge_encode_dev(sb->s_dev);
 
 	buf->f_type = ROMFS_MAGIC;
 	buf->f_namelen = ROMFS_MAXFN;
@@ -489,6 +505,11 @@ static int romfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_flags |= MS_RDONLY | MS_NOATIME;
 	sb->s_op = &romfs_super_ops;
 
+#ifdef CONFIG_ROMFS_ON_MTD
+	/* Use same dev ID from the underlying mtdblock device */
+	if (sb->s_mtd)
+		sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index);
+#endif
 	/* read the image superblock and check it */
 	rsb = kmalloc(512, GFP_KERNEL);
 	if (!rsb)
diff --git a/fs/splice.c b/fs/splice.c
index 873d83104e79..4ef78aa8ef61 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -204,6 +204,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 		buf->len = spd->partial[page_nr].len;
 		buf->private = spd->partial[page_nr].private;
 		buf->ops = spd->ops;
+		buf->flags = 0;
 
 		pipe->nrbufs++;
 		page_nr++;
diff --git a/fs/super.c b/fs/super.c
index 1709ed029a2c..ea662b0e5e78 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1047,7 +1047,7 @@ static int set_bdev_super(struct super_block *s, void *data)
 	 * We set the bdi here to the queue backing, file systems can
 	 * overwrite this in ->fill_super()
 	 */
-	s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
+	s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info;
 	return 0;
 }
 
diff --git a/fs/timerfd.c b/fs/timerfd.c
index c173cc196175..384fa759a563 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -40,6 +40,7 @@ struct timerfd_ctx {
 	short unsigned settime_flags;	/* to show in fdinfo */
 	struct rcu_head rcu;
 	struct list_head clist;
+	spinlock_t cancel_lock;
 	bool might_cancel;
 };
 
@@ -112,7 +113,7 @@ void timerfd_clock_was_set(void)
 	rcu_read_unlock();
 }
 
-static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+static void __timerfd_remove_cancel(struct timerfd_ctx *ctx)
 {
 	if (ctx->might_cancel) {
 		ctx->might_cancel = false;
@@ -122,6 +123,13 @@ static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
 	}
 }
 
+static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+{
+	spin_lock(&ctx->cancel_lock);
+	__timerfd_remove_cancel(ctx);
+	spin_unlock(&ctx->cancel_lock);
+}
+
 static bool timerfd_canceled(struct timerfd_ctx *ctx)
 {
 	if (!ctx->might_cancel || ctx->moffs != KTIME_MAX)
@@ -132,6 +140,7 @@ static bool timerfd_canceled(struct timerfd_ctx *ctx)
 
 static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
 {
+	spin_lock(&ctx->cancel_lock);
 	if ((ctx->clockid == CLOCK_REALTIME ||
 	     ctx->clockid == CLOCK_REALTIME_ALARM) &&
 	    (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) {
@@ -141,9 +150,10 @@ static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
 			list_add_rcu(&ctx->clist, &cancel_list);
 			spin_unlock(&cancel_lock);
 		}
-	} else if (ctx->might_cancel) {
-		timerfd_remove_cancel(ctx);
+	} else {
+		__timerfd_remove_cancel(ctx);
 	}
+	spin_unlock(&ctx->cancel_lock);
 }
 
 static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
@@ -400,6 +410,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 		return -ENOMEM;
 
 	init_waitqueue_head(&ctx->wqh);
+	spin_lock_init(&ctx->cancel_lock);
 	ctx->clockid = clockid;
 
 	if (isalarm(ctx))
diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c
index 3402720f2b28..382ed428cfd2 100644
--- a/fs/ubifs/crypto.c
+++ b/fs/ubifs/crypto.c
@@ -26,15 +26,6 @@ static unsigned int ubifs_crypt_max_namelen(struct inode *inode)
 		return UBIFS_MAX_NLEN;
 }
 
-static int ubifs_key_prefix(struct inode *inode, u8 **key)
-{
-	static char prefix[] = "ubifs:";
-
-	*key = prefix;
-
-	return sizeof(prefix) - 1;
-}
-
 int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn,
 		  unsigned int in_len, unsigned int *out_len, int block)
 {
@@ -86,12 +77,12 @@ int ubifs_decrypt(const struct inode *inode, struct ubifs_data_node *dn,
 	return 0;
 }
 
-struct fscrypt_operations ubifs_crypt_operations = {
+const struct fscrypt_operations ubifs_crypt_operations = {
 	.flags			= FS_CFLG_OWN_PAGES,
+	.key_prefix		= "ubifs:",
 	.get_context		= ubifs_crypt_get_context,
 	.set_context		= ubifs_crypt_set_context,
 	.is_encrypted		= __ubifs_crypt_is_encrypted,
 	.empty_dir		= ubifs_crypt_empty_dir,
 	.max_namelen		= ubifs_crypt_max_namelen,
-	.key_prefix		= ubifs_key_prefix,
 };
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index e08aa04fc835..b73811bd7676 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2000,7 +2000,7 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi)
 }
 
 #ifndef CONFIG_UBIFS_FS_ENCRYPTION
-struct fscrypt_operations ubifs_crypt_operations = {
+const struct fscrypt_operations ubifs_crypt_operations = {
 	.is_encrypted		= __ubifs_crypt_is_encrypted,
 };
 #endif
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index ca72382ce6cc..f0c86f076535 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -38,7 +38,11 @@
 #include <linux/backing-dev.h>
 #include <linux/security.h>
 #include <linux/xattr.h>
-#include <linux/fscrypto.h>
+#ifdef CONFIG_UBIFS_FS_ENCRYPTION
+#include <linux/fscrypt_supp.h>
+#else
+#include <linux/fscrypt_notsupp.h>
+#endif
 #include <linux/random.h>
 #include "ubifs-media.h"
 
@@ -1797,28 +1801,6 @@ int ubifs_decompress(const struct ubifs_info *c, const void *buf, int len,
 #include "key.h"
 
 #ifndef CONFIG_UBIFS_FS_ENCRYPTION
-#define fscrypt_set_d_op(i)
-#define fscrypt_get_ctx                 fscrypt_notsupp_get_ctx
-#define fscrypt_release_ctx             fscrypt_notsupp_release_ctx
-#define fscrypt_encrypt_page            fscrypt_notsupp_encrypt_page
-#define fscrypt_decrypt_page            fscrypt_notsupp_decrypt_page
-#define fscrypt_decrypt_bio_pages       fscrypt_notsupp_decrypt_bio_pages
-#define fscrypt_pullback_bio_page       fscrypt_notsupp_pullback_bio_page
-#define fscrypt_restore_control_page    fscrypt_notsupp_restore_control_page
-#define fscrypt_zeroout_range           fscrypt_notsupp_zeroout_range
-#define fscrypt_ioctl_set_policy	fscrypt_notsupp_ioctl_set_policy
-#define fscrypt_ioctl_get_policy	fscrypt_notsupp_ioctl_get_policy
-#define fscrypt_has_permitted_context   fscrypt_notsupp_has_permitted_context
-#define fscrypt_inherit_context         fscrypt_notsupp_inherit_context
-#define fscrypt_get_encryption_info     fscrypt_notsupp_get_encryption_info
-#define fscrypt_put_encryption_info     fscrypt_notsupp_put_encryption_info
-#define fscrypt_setup_filename          fscrypt_notsupp_setup_filename
-#define fscrypt_free_filename           fscrypt_notsupp_free_filename
-#define fscrypt_fname_encrypted_size    fscrypt_notsupp_fname_encrypted_size
-#define fscrypt_fname_alloc_buffer      fscrypt_notsupp_fname_alloc_buffer
-#define fscrypt_fname_free_buffer       fscrypt_notsupp_fname_free_buffer
-#define fscrypt_fname_disk_to_usr       fscrypt_notsupp_fname_disk_to_usr
-#define fscrypt_fname_usr_to_disk       fscrypt_notsupp_fname_usr_to_disk
 static inline int ubifs_encrypt(const struct inode *inode,
 				struct ubifs_data_node *dn,
 				unsigned int in_len, unsigned int *out_len,
@@ -1842,7 +1824,7 @@ int ubifs_decrypt(const struct inode *inode, struct ubifs_data_node *dn,
 		  unsigned int *out_len, int block);
 #endif
 
-extern struct fscrypt_operations ubifs_crypt_operations;
+extern const struct fscrypt_operations ubifs_crypt_operations;
 
 static inline bool __ubifs_crypt_is_encrypted(struct inode *inode)
 {
diff --git a/fs/udf/ecma_167.h b/fs/udf/ecma_167.h
index 4792b771aa80..9f24bd1a9f44 100644
--- a/fs/udf/ecma_167.h
+++ b/fs/udf/ecma_167.h
@@ -41,7 +41,7 @@
 struct charspec {
 	uint8_t		charSetType;
 	uint8_t		charSetInfo[63];
-} __attribute__ ((packed));
+} __packed;
 
 /* Character Set Type (ECMA 167r3 1/7.2.1.1) */
 #define CHARSPEC_TYPE_CS0		0x00	/* (1/7.2.2) */
@@ -68,7 +68,7 @@ struct timestamp {
 	uint8_t		centiseconds;
 	uint8_t		hundredsOfMicroseconds;
 	uint8_t		microseconds;
-} __attribute__ ((packed));
+} __packed;
 
 /* Type and Time Zone (ECMA 167r3 1/7.3.1) */
 #define TIMESTAMP_TYPE_MASK		0xF000
@@ -82,7 +82,7 @@ struct regid {
 	uint8_t		flags;
 	uint8_t		ident[23];
 	uint8_t		identSuffix[8];
-} __attribute__ ((packed));
+} __packed;
 
 /* Flags (ECMA 167r3 1/7.4.1) */
 #define ENTITYID_FLAGS_DIRTY		0x00
@@ -95,7 +95,7 @@ struct volStructDesc {
 	uint8_t		stdIdent[VSD_STD_ID_LEN];
 	uint8_t		structVersion;
 	uint8_t		structData[2041];
-} __attribute__ ((packed));
+} __packed;
 
 /* Standard Identifier (EMCA 167r2 2/9.1.2) */
 #define VSD_STD_ID_NSR02		"NSR02"	/* (3/9.1) */
@@ -114,7 +114,7 @@ struct beginningExtendedAreaDesc {
 	uint8_t		stdIdent[VSD_STD_ID_LEN];
 	uint8_t		structVersion;
 	uint8_t		structData[2041];
-} __attribute__ ((packed));
+} __packed;
 
 /* Terminating Extended Area Descriptor (ECMA 167r3 2/9.3) */
 struct terminatingExtendedAreaDesc {
@@ -122,7 +122,7 @@ struct terminatingExtendedAreaDesc {
 	uint8_t		stdIdent[VSD_STD_ID_LEN];
 	uint8_t		structVersion;
 	uint8_t		structData[2041];
-} __attribute__ ((packed));
+} __packed;
 
 /* Boot Descriptor (ECMA 167r3 2/9.4) */
 struct bootDesc {
@@ -140,7 +140,7 @@ struct bootDesc {
 	__le16			flags;
 	uint8_t			reserved2[32];
 	uint8_t			bootUse[1906];
-} __attribute__ ((packed));
+} __packed;
 
 /* Flags (ECMA 167r3 2/9.4.12) */
 #define BOOT_FLAGS_ERASE		0x01
@@ -149,7 +149,7 @@ struct bootDesc {
 struct extent_ad {
 	__le32		extLength;
 	__le32		extLocation;
-} __attribute__ ((packed));
+} __packed;
 
 struct kernel_extent_ad {
 	uint32_t	extLength;
@@ -166,7 +166,7 @@ struct tag {
 	__le16		descCRC;
 	__le16		descCRCLength;
 	__le32		tagLocation;
-} __attribute__ ((packed));
+} __packed;
 
 /* Tag Identifier (ECMA 167r3 3/7.2.1) */
 #define TAG_IDENT_PVD			0x0001
@@ -186,7 +186,7 @@ struct NSRDesc {
 	uint8_t		structVersion;
 	uint8_t		reserved;
 	uint8_t		structData[2040];
-} __attribute__ ((packed));
+} __packed;
 
 /* Primary Volume Descriptor (ECMA 167r3 3/10.1) */
 struct primaryVolDesc {
@@ -212,7 +212,7 @@ struct primaryVolDesc {
 	__le32			predecessorVolDescSeqLocation;
 	__le16			flags;
 	uint8_t			reserved[22];
-} __attribute__ ((packed));
+} __packed;
 
 /* Flags (ECMA 167r3 3/10.1.21) */
 #define PVD_FLAGS_VSID_COMMON		0x0001
@@ -223,7 +223,7 @@ struct anchorVolDescPtr {
 	struct extent_ad	mainVolDescSeqExt;
 	struct extent_ad	reserveVolDescSeqExt;
 	uint8_t	 		reserved[480];
-} __attribute__ ((packed));
+} __packed;
 
 /* Volume Descriptor Pointer (ECMA 167r3 3/10.3) */
 struct volDescPtr {
@@ -231,7 +231,7 @@ struct volDescPtr {
 	__le32			volDescSeqNum;
 	struct extent_ad	nextVolDescSeqExt;
 	uint8_t			reserved[484];
-} __attribute__ ((packed));
+} __packed;
 
 /* Implementation Use Volume Descriptor (ECMA 167r3 3/10.4) */
 struct impUseVolDesc {
@@ -239,7 +239,7 @@ struct impUseVolDesc {
 	__le32		volDescSeqNum;
 	struct regid	impIdent;
 	uint8_t		impUse[460];
-} __attribute__ ((packed));
+} __packed;
 
 /* Partition Descriptor (ECMA 167r3 3/10.5) */
 struct partitionDesc {
@@ -255,7 +255,7 @@ struct partitionDesc {
 	struct regid impIdent;
 	uint8_t impUse[128];
 	uint8_t reserved[156];
-} __attribute__ ((packed));
+} __packed;
 
 /* Partition Flags (ECMA 167r3 3/10.5.3) */
 #define PD_PARTITION_FLAGS_ALLOC	0x0001
@@ -291,14 +291,14 @@ struct logicalVolDesc {
 	uint8_t			impUse[128];
 	struct extent_ad	integritySeqExt;
 	uint8_t			partitionMaps[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Generic Partition Map (ECMA 167r3 3/10.7.1) */
 struct genericPartitionMap {
 	uint8_t		partitionMapType;
 	uint8_t		partitionMapLength;
 	uint8_t		partitionMapping[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Partition Map Type (ECMA 167r3 3/10.7.1.1) */
 #define GP_PARTITION_MAP_TYPE_UNDEF	0x00
@@ -311,14 +311,14 @@ struct genericPartitionMap1 {
 	uint8_t		partitionMapLength;
 	__le16		volSeqNum;
 	__le16		partitionNum;
-} __attribute__ ((packed));
+} __packed;
 
 /* Type 2 Partition Map (ECMA 167r3 3/10.7.3) */
 struct genericPartitionMap2 {
 	uint8_t		partitionMapType;
 	uint8_t		partitionMapLength;
 	uint8_t		partitionIdent[62];
-} __attribute__ ((packed));
+} __packed;
 
 /* Unallocated Space Descriptor (ECMA 167r3 3/10.8) */
 struct unallocSpaceDesc {
@@ -326,13 +326,13 @@ struct unallocSpaceDesc {
 	__le32			volDescSeqNum;
 	__le32			numAllocDescs;
 	struct extent_ad	allocDescs[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Terminating Descriptor (ECMA 167r3 3/10.9) */
 struct terminatingDesc {
 	struct tag	descTag;
 	uint8_t		reserved[496];
-} __attribute__ ((packed));
+} __packed;
 
 /* Logical Volume Integrity Descriptor (ECMA 167r3 3/10.10) */
 struct logicalVolIntegrityDesc {
@@ -346,7 +346,7 @@ struct logicalVolIntegrityDesc {
 	__le32			freeSpaceTable[0];
 	__le32			sizeTable[0];
 	uint8_t			impUse[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Integrity Type (ECMA 167r3 3/10.10.3) */
 #define LVID_INTEGRITY_TYPE_OPEN	0x00000000
@@ -356,7 +356,7 @@ struct logicalVolIntegrityDesc {
 struct lb_addr {
 	__le32		logicalBlockNum;
 	__le16	 	partitionReferenceNum;
-} __attribute__ ((packed));
+} __packed;
 
 /* ... and its in-core analog */
 struct kernel_lb_addr {
@@ -368,14 +368,14 @@ struct kernel_lb_addr {
 struct short_ad {
         __le32		extLength;
         __le32		extPosition;
-} __attribute__ ((packed));
+} __packed;
 
 /* Long Allocation Descriptor (ECMA 167r3 4/14.14.2) */
 struct long_ad {
 	__le32		extLength;
 	struct lb_addr	extLocation;
 	uint8_t		impUse[6];
-} __attribute__ ((packed));
+} __packed;
 
 struct kernel_long_ad {
 	uint32_t		extLength;
@@ -389,7 +389,7 @@ struct ext_ad {
 	__le32		recordedLength;
 	__le32		informationLength;
 	struct lb_addr	extLocation;
-} __attribute__ ((packed));
+} __packed;
 
 struct kernel_ext_ad {
 	uint32_t		extLength;
@@ -434,7 +434,7 @@ struct fileSetDesc {
 	struct long_ad		nextExt;
 	struct long_ad		streamDirectoryICB;
 	uint8_t			reserved[32];
-} __attribute__ ((packed));
+} __packed;
 
 /* Partition Header Descriptor (ECMA 167r3 4/14.3) */
 struct partitionHeaderDesc {
@@ -444,7 +444,7 @@ struct partitionHeaderDesc {
 	struct short_ad	freedSpaceTable;
 	struct short_ad	freedSpaceBitmap;
 	uint8_t		reserved[88];
-} __attribute__ ((packed));
+} __packed;
 
 /* File Identifier Descriptor (ECMA 167r3 4/14.4) */
 struct fileIdentDesc {
@@ -457,7 +457,7 @@ struct fileIdentDesc {
 	uint8_t		impUse[0];
 	uint8_t		fileIdent[0];
 	uint8_t		padding[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* File Characteristics (ECMA 167r3 4/14.4.3) */
 #define FID_FILE_CHAR_HIDDEN		0x01
@@ -471,7 +471,7 @@ struct allocExtDesc {
 	struct tag	descTag;
 	__le32		previousAllocExtLocation;
 	__le32		lengthAllocDescs;
-} __attribute__ ((packed));
+} __packed;
 
 /* ICB Tag (ECMA 167r3 4/14.6) */
 struct icbtag {
@@ -483,7 +483,7 @@ struct icbtag {
 	uint8_t		fileType;
 	struct lb_addr	parentICBLocation;
 	__le16		flags;
-} __attribute__ ((packed));
+} __packed;
 
 /* Strategy Type (ECMA 167r3 4/14.6.2) */
 #define ICBTAG_STRATEGY_TYPE_UNDEF	0x0000
@@ -531,13 +531,13 @@ struct indirectEntry {
 	struct tag	descTag;
 	struct icbtag	icbTag;
 	struct long_ad	indirectICB;
-} __attribute__ ((packed));
+} __packed;
 
 /* Terminal Entry (ECMA 167r3 4/14.8) */
 struct terminalEntry {
 	struct tag	descTag;
 	struct icbtag	icbTag;
-} __attribute__ ((packed));
+} __packed;
 
 /* File Entry (ECMA 167r3 4/14.9) */
 struct fileEntry {
@@ -563,7 +563,7 @@ struct fileEntry {
 	__le32			lengthAllocDescs;
 	uint8_t			extendedAttr[0];
 	uint8_t			allocDescs[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Permissions (ECMA 167r3 4/14.9.5) */
 #define FE_PERM_O_EXEC			0x00000001U
@@ -607,7 +607,7 @@ struct extendedAttrHeaderDesc {
 	struct tag	descTag;
 	__le32		impAttrLocation;
 	__le32		appAttrLocation;
-} __attribute__ ((packed));
+} __packed;
 
 /* Generic Format (ECMA 167r3 4/14.10.2) */
 struct genericFormat {
@@ -616,7 +616,7 @@ struct genericFormat {
 	uint8_t		reserved[3];
 	__le32		attrLength;
 	uint8_t		attrData[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Character Set Information (ECMA 167r3 4/14.10.3) */
 struct charSetInfo {
@@ -627,7 +627,7 @@ struct charSetInfo {
 	__le32		escapeSeqLength;
 	uint8_t		charSetType;
 	uint8_t		escapeSeq[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Alternate Permissions (ECMA 167r3 4/14.10.4) */
 struct altPerms {
@@ -638,7 +638,7 @@ struct altPerms {
 	__le16		ownerIdent;
 	__le16		groupIdent;
 	__le16		permission;
-} __attribute__ ((packed));
+} __packed;
 
 /* File Times Extended Attribute (ECMA 167r3 4/14.10.5) */
 struct fileTimesExtAttr {
@@ -649,7 +649,7 @@ struct fileTimesExtAttr {
 	__le32		dataLength;
 	__le32		fileTimeExistence;
 	uint8_t		fileTimes;
-} __attribute__ ((packed));
+} __packed;
 
 /* FileTimeExistence (ECMA 167r3 4/14.10.5.6) */
 #define FTE_CREATION			0x00000001
@@ -666,7 +666,7 @@ struct infoTimesExtAttr {
 	__le32		dataLength;
 	__le32		infoTimeExistence;
 	uint8_t		infoTimes[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Device Specification (ECMA 167r3 4/14.10.7) */
 struct deviceSpec {
@@ -678,7 +678,7 @@ struct deviceSpec {
 	__le32		majorDeviceIdent;
 	__le32		minorDeviceIdent;
 	uint8_t		impUse[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Implementation Use Extended Attr (ECMA 167r3 4/14.10.8) */
 struct impUseExtAttr {
@@ -689,7 +689,7 @@ struct impUseExtAttr {
 	__le32		impUseLength;
 	struct regid	impIdent;
 	uint8_t		impUse[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Application Use Extended Attribute (ECMA 167r3 4/14.10.9) */
 struct appUseExtAttr {
@@ -700,7 +700,7 @@ struct appUseExtAttr {
 	__le32		appUseLength;
 	struct regid	appIdent;
 	uint8_t		appUse[0];
-} __attribute__ ((packed));
+} __packed;
 
 #define EXTATTR_CHAR_SET		1
 #define EXTATTR_ALT_PERMS		3
@@ -716,7 +716,7 @@ struct unallocSpaceEntry {
 	struct icbtag	icbTag;
 	__le32		lengthAllocDescs;
 	uint8_t		allocDescs[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Space Bitmap Descriptor (ECMA 167r3 4/14.12) */
 struct spaceBitmapDesc {
@@ -724,7 +724,7 @@ struct spaceBitmapDesc {
 	__le32		numOfBits;
 	__le32		numOfBytes;
 	uint8_t		bitmap[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Partition Integrity Entry (ECMA 167r3 4/14.13) */
 struct partitionIntegrityEntry {
@@ -735,7 +735,7 @@ struct partitionIntegrityEntry {
 	uint8_t			reserved[175];
 	struct regid		impIdent;
 	uint8_t			impUse[256];
-} __attribute__ ((packed));
+} __packed;
 
 /* Short Allocation Descriptor (ECMA 167r3 4/14.14.1) */
 
@@ -753,7 +753,7 @@ struct partitionIntegrityEntry {
 struct logicalVolHeaderDesc {
 	__le64		uniqueID;
 	uint8_t		reserved[24];
-} __attribute__ ((packed));
+} __packed;
 
 /* Path Component (ECMA 167r3 4/14.16.1) */
 struct pathComponent {
@@ -761,7 +761,7 @@ struct pathComponent {
 	uint8_t		lengthComponentIdent;
 	__le16		componentFileVersionNum;
 	dstring		componentIdent[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* File Entry (ECMA 167r3 4/14.17) */
 struct extendedFileEntry {
@@ -791,6 +791,6 @@ struct extendedFileEntry {
 	__le32			lengthAllocDescs;
 	uint8_t			extendedAttr[0];
 	uint8_t			allocDescs[0];
-} __attribute__ ((packed));
+} __packed;
 
 #endif /* _ECMA_167_H */
diff --git a/fs/udf/file.c b/fs/udf/file.c
index dbcb3a4a0cb9..e04cc0cdca9d 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -176,54 +176,46 @@ long udf_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	long old_block, new_block;
-	int result = -EINVAL;
+	int result;
 
 	if (inode_permission(inode, MAY_READ) != 0) {
 		udf_debug("no permission to access inode %lu\n", inode->i_ino);
-		result = -EPERM;
-		goto out;
+		return -EPERM;
 	}
 
-	if (!arg) {
+	if (!arg && ((cmd == UDF_GETVOLIDENT) || (cmd == UDF_GETEASIZE) ||
+		     (cmd == UDF_RELOCATE_BLOCKS) || (cmd == UDF_GETEABLOCK))) {
 		udf_debug("invalid argument to udf_ioctl\n");
-		result = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	switch (cmd) {
 	case UDF_GETVOLIDENT:
 		if (copy_to_user((char __user *)arg,
 				 UDF_SB(inode->i_sb)->s_volume_ident, 32))
-			result = -EFAULT;
-		else
-			result = 0;
-		goto out;
+			return -EFAULT;
+		return 0;
 	case UDF_RELOCATE_BLOCKS:
-		if (!capable(CAP_SYS_ADMIN)) {
-			result = -EPERM;
-			goto out;
-		}
-		if (get_user(old_block, (long __user *)arg)) {
-			result = -EFAULT;
-			goto out;
-		}
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		if (get_user(old_block, (long __user *)arg))
+			return -EFAULT;
 		result = udf_relocate_blocks(inode->i_sb,
 						old_block, &new_block);
 		if (result == 0)
 			result = put_user(new_block, (long __user *)arg);
-		goto out;
+		return result;
 	case UDF_GETEASIZE:
-		result = put_user(UDF_I(inode)->i_lenEAttr, (int __user *)arg);
-		goto out;
+		return put_user(UDF_I(inode)->i_lenEAttr, (int __user *)arg);
 	case UDF_GETEABLOCK:
-		result = copy_to_user((char __user *)arg,
-				      UDF_I(inode)->i_ext.i_data,
-				      UDF_I(inode)->i_lenEAttr) ? -EFAULT : 0;
-		goto out;
+		return copy_to_user((char __user *)arg,
+				    UDF_I(inode)->i_ext.i_data,
+				    UDF_I(inode)->i_lenEAttr) ? -EFAULT : 0;
+	default:
+		return -ENOIOCTLCMD;
 	}
 
-out:
-	return result;
+	return 0;
 }
 
 static int udf_release_file(struct inode *inode, struct file *filp)
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 0f3db71753aa..8ec6b3df0bc7 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -43,10 +43,6 @@
 #include "udf_i.h"
 #include "udf_sb.h"
 
-MODULE_AUTHOR("Ben Fennema");
-MODULE_DESCRIPTION("Universal Disk Format Filesystem");
-MODULE_LICENSE("GPL");
-
 #define EXTENT_MERGE_SIZE 5
 
 static umode_t udf_convert_permissions(struct fileEntry *);
@@ -57,14 +53,12 @@ static sector_t inode_getblk(struct inode *, sector_t, int *, int *);
 static int8_t udf_insert_aext(struct inode *, struct extent_position,
 			      struct kernel_lb_addr, uint32_t);
 static void udf_split_extents(struct inode *, int *, int, int,
-			      struct kernel_long_ad[EXTENT_MERGE_SIZE], int *);
+			      struct kernel_long_ad *, int *);
 static void udf_prealloc_extents(struct inode *, int, int,
-				 struct kernel_long_ad[EXTENT_MERGE_SIZE], int *);
-static void udf_merge_extents(struct inode *,
-			      struct kernel_long_ad[EXTENT_MERGE_SIZE], int *);
-static void udf_update_extents(struct inode *,
-			       struct kernel_long_ad[EXTENT_MERGE_SIZE], int, int,
-			       struct extent_position *);
+				 struct kernel_long_ad *, int *);
+static void udf_merge_extents(struct inode *, struct kernel_long_ad *, int *);
+static void udf_update_extents(struct inode *, struct kernel_long_ad *, int,
+			       int, struct extent_position *);
 static int udf_get_block(struct inode *, sector_t, struct buffer_head *, int);
 
 static void __udf_clear_extent_cache(struct inode *inode)
@@ -111,7 +105,7 @@ static int udf_read_extent_cache(struct inode *inode, loff_t bcount,
 
 /* Add extent to extent cache */
 static void udf_update_extent_cache(struct inode *inode, loff_t estart,
-				    struct extent_position *pos, int next_epos)
+				    struct extent_position *pos)
 {
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
@@ -120,19 +114,16 @@ static void udf_update_extent_cache(struct inode *inode, loff_t estart,
 	__udf_clear_extent_cache(inode);
 	if (pos->bh)
 		get_bh(pos->bh);
-	memcpy(&iinfo->cached_extent.epos, pos,
-	       sizeof(struct extent_position));
+	memcpy(&iinfo->cached_extent.epos, pos, sizeof(struct extent_position));
 	iinfo->cached_extent.lstart = estart;
-	if (next_epos)
-		switch (iinfo->i_alloc_type) {
-		case ICBTAG_FLAG_AD_SHORT:
-			iinfo->cached_extent.epos.offset -=
-			sizeof(struct short_ad);
-			break;
-		case ICBTAG_FLAG_AD_LONG:
-			iinfo->cached_extent.epos.offset -=
-			sizeof(struct long_ad);
-		}
+	switch (iinfo->i_alloc_type) {
+	case ICBTAG_FLAG_AD_SHORT:
+		iinfo->cached_extent.epos.offset -= sizeof(struct short_ad);
+		break;
+	case ICBTAG_FLAG_AD_LONG:
+		iinfo->cached_extent.epos.offset -= sizeof(struct long_ad);
+		break;
+	}
 	spin_unlock(&iinfo->i_extent_cache_lock);
 }
 
@@ -747,11 +738,8 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 				 ~(inode->i_sb->s_blocksize - 1));
 			udf_write_aext(inode, &cur_epos, &eloc, elen, 1);
 		}
-		brelse(prev_epos.bh);
-		brelse(cur_epos.bh);
-		brelse(next_epos.bh);
 		newblock = udf_get_lb_pblock(inode->i_sb, &eloc, offset);
-		return newblock;
+		goto out_free;
 	}
 
 	/* Are we beyond EOF? */
@@ -774,11 +762,9 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 		/* Create extents for the hole between EOF and offset */
 		ret = udf_do_extend_file(inode, &prev_epos, laarr, offset);
 		if (ret < 0) {
-			brelse(prev_epos.bh);
-			brelse(cur_epos.bh);
-			brelse(next_epos.bh);
 			*err = ret;
-			return 0;
+			newblock = 0;
+			goto out_free;
 		}
 		c = 0;
 		offset = 0;
@@ -841,11 +827,9 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 				iinfo->i_location.partitionReferenceNum,
 				goal, err);
 		if (!newblocknum) {
-			brelse(prev_epos.bh);
-			brelse(cur_epos.bh);
-			brelse(next_epos.bh);
 			*err = -ENOSPC;
-			return 0;
+			newblock = 0;
+			goto out_free;
 		}
 		if (isBeyondEOF)
 			iinfo->i_lenExtents += inode->i_sb->s_blocksize;
@@ -857,14 +841,12 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 	 * block */
 	udf_split_extents(inode, &c, offset, newblocknum, laarr, &endnum);
 
-#ifdef UDF_PREALLOCATE
 	/* We preallocate blocks only for regular files. It also makes sense
 	 * for directories but there's a problem when to drop the
 	 * preallocation. We might use some delayed work for that but I feel
 	 * it's overengineering for a filesystem like UDF. */
 	if (S_ISREG(inode->i_mode))
 		udf_prealloc_extents(inode, c, lastblock, laarr, &endnum);
-#endif
 
 	/* merge any continuous blocks in laarr */
 	udf_merge_extents(inode, laarr, &endnum);
@@ -874,15 +856,11 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 	 * the new number of extents is less than the old number */
 	udf_update_extents(inode, laarr, startnum, endnum, &prev_epos);
 
-	brelse(prev_epos.bh);
-	brelse(cur_epos.bh);
-	brelse(next_epos.bh);
-
 	newblock = udf_get_pblock(inode->i_sb, newblocknum,
 				iinfo->i_location.partitionReferenceNum, 0);
 	if (!newblock) {
 		*err = -EIO;
-		return 0;
+		goto out_free;
 	}
 	*new = 1;
 	iinfo->i_next_alloc_block = block;
@@ -893,13 +871,15 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 		udf_sync_inode(inode);
 	else
 		mark_inode_dirty(inode);
-
+out_free:
+	brelse(prev_epos.bh);
+	brelse(cur_epos.bh);
+	brelse(next_epos.bh);
 	return newblock;
 }
 
 static void udf_split_extents(struct inode *inode, int *c, int offset,
-			      int newblocknum,
-			      struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+			      int newblocknum, struct kernel_long_ad *laarr,
 			      int *endnum)
 {
 	unsigned long blocksize = inode->i_sb->s_blocksize;
@@ -963,7 +943,7 @@ static void udf_split_extents(struct inode *inode, int *c, int offset,
 }
 
 static void udf_prealloc_extents(struct inode *inode, int c, int lastblock,
-				 struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+				 struct kernel_long_ad *laarr,
 				 int *endnum)
 {
 	int start, length = 0, currlength = 0, i;
@@ -1058,8 +1038,7 @@ static void udf_prealloc_extents(struct inode *inode, int c, int lastblock,
 	}
 }
 
-static void udf_merge_extents(struct inode *inode,
-			      struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr,
 			      int *endnum)
 {
 	int i;
@@ -1158,8 +1137,7 @@ static void udf_merge_extents(struct inode *inode,
 	}
 }
 
-static void udf_update_extents(struct inode *inode,
-			       struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr,
 			       int startnum, int endnum,
 			       struct extent_position *epos)
 {
@@ -1299,6 +1277,12 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode)
 	int ret = -EIO;
 
 reread:
+	if (iloc->partitionReferenceNum >= sbi->s_partitions) {
+		udf_debug("partition reference: %d > logical volume partitions: %d\n",
+			  iloc->partitionReferenceNum, sbi->s_partitions);
+		return -EIO;
+	}
+
 	if (iloc->logicalBlockNum >=
 	    sbi->s_partmaps[iloc->partitionReferenceNum].s_partition_len) {
 		udf_debug("block=%d, partition=%d out of range\n",
@@ -1549,7 +1533,7 @@ reread:
 		break;
 	case ICBTAG_FILE_TYPE_SYMLINK:
 		inode->i_data.a_ops = &udf_symlink_aops;
-		inode->i_op = &page_symlink_inode_operations;
+		inode->i_op = &udf_symlink_inode_operations;
 		inode_nohighmem(inode);
 		inode->i_mode = S_IFLNK | S_IRWXUGO;
 		break;
@@ -1627,6 +1611,14 @@ static int udf_sync_inode(struct inode *inode)
 	return udf_update_inode(inode, 1);
 }
 
+static void udf_adjust_time(struct udf_inode_info *iinfo, struct timespec time)
+{
+	if (iinfo->i_crtime.tv_sec > time.tv_sec ||
+	    (iinfo->i_crtime.tv_sec == time.tv_sec &&
+	     iinfo->i_crtime.tv_nsec > time.tv_nsec))
+		iinfo->i_crtime = time;
+}
+
 static int udf_update_inode(struct inode *inode, int do_sync)
 {
 	struct buffer_head *bh = NULL;
@@ -1753,20 +1745,9 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 		efe->objectSize = cpu_to_le64(inode->i_size);
 		efe->logicalBlocksRecorded = cpu_to_le64(lb_recorded);
 
-		if (iinfo->i_crtime.tv_sec > inode->i_atime.tv_sec ||
-		    (iinfo->i_crtime.tv_sec == inode->i_atime.tv_sec &&
-		     iinfo->i_crtime.tv_nsec > inode->i_atime.tv_nsec))
-			iinfo->i_crtime = inode->i_atime;
-
-		if (iinfo->i_crtime.tv_sec > inode->i_mtime.tv_sec ||
-		    (iinfo->i_crtime.tv_sec == inode->i_mtime.tv_sec &&
-		     iinfo->i_crtime.tv_nsec > inode->i_mtime.tv_nsec))
-			iinfo->i_crtime = inode->i_mtime;
-
-		if (iinfo->i_crtime.tv_sec > inode->i_ctime.tv_sec ||
-		    (iinfo->i_crtime.tv_sec == inode->i_ctime.tv_sec &&
-		     iinfo->i_crtime.tv_nsec > inode->i_ctime.tv_nsec))
-			iinfo->i_crtime = inode->i_ctime;
+		udf_adjust_time(iinfo, inode->i_atime);
+		udf_adjust_time(iinfo, inode->i_mtime);
+		udf_adjust_time(iinfo, inode->i_ctime);
 
 		udf_time_to_disk_stamp(&efe->accessTime, inode->i_atime);
 		udf_time_to_disk_stamp(&efe->modificationTime, inode->i_mtime);
@@ -2286,8 +2267,7 @@ int8_t inode_bmap(struct inode *inode, sector_t block,
 		  uint32_t *elen, sector_t *offset)
 {
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
-	loff_t lbcount = 0, bcount =
-	    (loff_t) block << blocksize_bits;
+	loff_t lbcount = 0, bcount = (loff_t) block << blocksize_bits;
 	int8_t etype;
 	struct udf_inode_info *iinfo;
 
@@ -2308,7 +2288,7 @@ int8_t inode_bmap(struct inode *inode, sector_t block,
 		lbcount += *elen;
 	} while (lbcount <= bcount);
 	/* update extent cache */
-	udf_update_extent_cache(inode, lbcount - *elen, pos, 1);
+	udf_update_extent_cache(inode, lbcount - *elen, pos);
 	*offset = (bcount + *elen - lbcount) >> blocksize_bits;
 
 	return etype;
diff --git a/fs/udf/lowlevel.c b/fs/udf/lowlevel.c
index 6ad5a453af97..5c7ec121990d 100644
--- a/fs/udf/lowlevel.c
+++ b/fs/udf/lowlevel.c
@@ -58,7 +58,7 @@ unsigned long udf_get_last_block(struct super_block *sb)
 	 */
 	if (ioctl_by_bdev(bdev, CDROM_LAST_WRITTEN, (unsigned long) &lblock) ||
 	    lblock == 0)
-		lblock = bdev->bd_inode->i_size >> sb->s_blocksize_bits;
+		lblock = i_size_read(bdev->bd_inode) >> sb->s_blocksize_bits;
 
 	if (lblock)
 		return lblock - 1;
diff --git a/fs/udf/misc.c b/fs/udf/misc.c
index 71d1c25f360d..3949c4bec3a3 100644
--- a/fs/udf/misc.c
+++ b/fs/udf/misc.c
@@ -141,8 +141,6 @@ struct genericFormat *udf_add_extendedattr(struct inode *inode, uint32_t size,
 		iinfo->i_lenEAttr += size;
 		return (struct genericFormat *)&ea[offset];
 	}
-	if (loc & 0x02)
-		;
 
 	return NULL;
 }
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 2d65e280748b..babf48d0e553 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -931,7 +931,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 	}
 
 	inode->i_data.a_ops = &udf_symlink_aops;
-	inode->i_op = &page_symlink_inode_operations;
+	inode->i_op = &udf_symlink_inode_operations;
 	inode_nohighmem(inode);
 
 	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
diff --git a/fs/udf/osta_udf.h b/fs/udf/osta_udf.h
index fbff74654df2..a4da59e38b7f 100644
--- a/fs/udf/osta_udf.h
+++ b/fs/udf/osta_udf.h
@@ -70,17 +70,17 @@ struct UDFIdentSuffix {
 	uint8_t		OSClass;
 	uint8_t		OSIdentifier;
 	uint8_t		reserved[4];
-} __attribute__ ((packed));
+} __packed;
 
 struct impIdentSuffix {
 	uint8_t		OSClass;
 	uint8_t		OSIdentifier;
 	uint8_t		reserved[6];
-} __attribute__ ((packed));
+} __packed;
 
 struct appIdentSuffix {
 	uint8_t		impUse[8];
-} __attribute__ ((packed));
+} __packed;
 
 /* Logical Volume Integrity Descriptor (UDF 2.50 2.2.6) */
 /* Implementation Use (UDF 2.50 2.2.6.4) */
@@ -92,7 +92,7 @@ struct logicalVolIntegrityDescImpUse {
 	__le16		minUDFWriteRev;
 	__le16		maxUDFWriteRev;
 	uint8_t		impUse[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Implementation Use Volume Descriptor (UDF 2.50 2.2.7) */
 /* Implementation Use (UDF 2.50 2.2.7.2) */
@@ -104,7 +104,7 @@ struct impUseVolDescImpUse {
 	dstring		LVInfo3[36];
 	struct regid	impIdent;
 	uint8_t		impUse[128];
-} __attribute__ ((packed));
+} __packed;
 
 struct udfPartitionMap2 {
 	uint8_t		partitionMapType;
@@ -113,7 +113,7 @@ struct udfPartitionMap2 {
 	struct regid	partIdent;
 	__le16		volSeqNum;
 	__le16		partitionNum;
-} __attribute__ ((packed));
+} __packed;
 
 /* Virtual Partition Map (UDF 2.50 2.2.8) */
 struct virtualPartitionMap {
@@ -124,7 +124,7 @@ struct virtualPartitionMap {
 	__le16		volSeqNum;
 	__le16		partitionNum;
 	uint8_t		reserved2[24];
-} __attribute__ ((packed));
+} __packed;
 
 /* Sparable Partition Map (UDF 2.50 2.2.9) */
 struct sparablePartitionMap {
@@ -139,7 +139,7 @@ struct sparablePartitionMap {
 	uint8_t reserved2[1];
 	__le32 sizeSparingTable;
 	__le32 locSparingTable[4];
-} __attribute__ ((packed));
+} __packed;
 
 /* Metadata Partition Map (UDF 2.4.0 2.2.10) */
 struct metadataPartitionMap {
@@ -156,14 +156,14 @@ struct metadataPartitionMap {
 	__le16		alignUnitSize;
 	uint8_t		flags;
 	uint8_t		reserved2[5];
-} __attribute__ ((packed));
+} __packed;
 
 /* Virtual Allocation Table (UDF 1.5 2.2.10) */
 struct virtualAllocationTable15 {
 	__le32		VirtualSector[0];
 	struct regid	vatIdent;
 	__le32		previousVATICBLoc;
-} __attribute__ ((packed));
+} __packed;
 
 #define ICBTAG_FILE_TYPE_VAT15		0x00U
 
@@ -181,7 +181,7 @@ struct virtualAllocationTable20 {
 	__le16		reserved;
 	uint8_t		impUse[0];
 	__le32		vatEntry[0];
-} __attribute__ ((packed));
+} __packed;
 
 #define ICBTAG_FILE_TYPE_VAT20		0xF8U
 
@@ -189,7 +189,7 @@ struct virtualAllocationTable20 {
 struct sparingEntry {
 	__le32		origLocation;
 	__le32		mappedLocation;
-} __attribute__ ((packed));
+} __packed;
 
 struct sparingTable {
 	struct tag	descTag;
@@ -199,7 +199,7 @@ struct sparingTable {
 	__le32		sequenceNum;
 	struct sparingEntry
 			mapEntry[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Metadata File (and Metadata Mirror File) (UDF 2.50 2.2.13.1) */
 #define ICBTAG_FILE_TYPE_MAIN		0xFA
@@ -210,7 +210,7 @@ struct sparingTable {
 struct allocDescImpUse {
 	__le16		flags;
 	uint8_t		impUse[4];
-} __attribute__ ((packed));
+} __packed;
 
 #define AD_IU_EXT_ERASED		0x0001
 
@@ -222,7 +222,7 @@ struct allocDescImpUse {
 struct freeEaSpace {
 	__le16		headerChecksum;
 	uint8_t		freeEASpace[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* DVD Copyright Management Information (UDF 2.50 3.3.4.5.1.2) */
 struct DVDCopyrightImpUse {
@@ -230,14 +230,14 @@ struct DVDCopyrightImpUse {
 	uint8_t		CGMSInfo;
 	uint8_t		dataType;
 	uint8_t		protectionSystemInfo[4];
-} __attribute__ ((packed));
+} __packed;
 
 /* Application Use Extended Attribute (UDF 2.50 3.3.4.6) */
 /* FreeAppEASpace (UDF 2.50 3.3.4.6.1) */
 struct freeAppEASpace {
 	__le16		headerChecksum;
 	uint8_t		freeEASpace[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* UDF Defined System Stream (UDF 2.50 3.3.7) */
 #define UDF_ID_UNIQUE_ID		"*UDF Unique ID Mapping Data"
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 4942549e7dc8..14b4bc1f6801 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -264,9 +264,6 @@ static void __exit exit_udf_fs(void)
 	destroy_inodecache();
 }
 
-module_init(init_udf_fs)
-module_exit(exit_udf_fs)
-
 static int udf_sb_alloc_partition_maps(struct super_block *sb, u32 count)
 {
 	struct udf_sb_info *sbi = UDF_SB(sb);
@@ -1216,7 +1213,8 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index)
 	struct udf_inode_info *vati;
 	uint32_t pos;
 	struct virtualAllocationTable20 *vat20;
-	sector_t blocks = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits;
+	sector_t blocks = i_size_read(sb->s_bdev->bd_inode) >>
+			  sb->s_blocksize_bits;
 
 	udf_find_vat_block(sb, p_index, type1_index, sbi->s_last_block);
 	if (!sbi->s_vat_inode &&
@@ -1806,7 +1804,7 @@ static int udf_check_anchor_block(struct super_block *sb, sector_t block,
 
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) &&
 	    udf_fixed_to_variable(block) >=
-	    sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits)
+	    i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits)
 		return -EAGAIN;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
@@ -1868,7 +1866,7 @@ static int udf_scan_anchors(struct super_block *sb, sector_t *lastblock,
 		last[last_count++] = *lastblock - 152;
 
 	for (i = 0; i < last_count; i++) {
-		if (last[i] >= sb->s_bdev->bd_inode->i_size >>
+		if (last[i] >= i_size_read(sb->s_bdev->bd_inode) >>
 				sb->s_blocksize_bits)
 			continue;
 		ret = udf_check_anchor_block(sb, last[i], fileset);
@@ -1957,7 +1955,7 @@ static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt,
 		if (!nsr_off) {
 			if (!silent)
 				udf_warn(sb, "No VRS found\n");
-			return 0;
+			return -EINVAL;
 		}
 		if (nsr_off == -1)
 			udf_debug("Failed to read sector at offset %d. "
@@ -1986,6 +1984,7 @@ static void udf_open_lvid(struct super_block *sb)
 	struct buffer_head *bh = sbi->s_lvid_bh;
 	struct logicalVolIntegrityDesc *lvid;
 	struct logicalVolIntegrityDescImpUse *lvidiu;
+	struct timespec ts;
 
 	if (!bh)
 		return;
@@ -1997,8 +1996,8 @@ static void udf_open_lvid(struct super_block *sb)
 	mutex_lock(&sbi->s_alloc_mutex);
 	lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX;
 	lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX;
-	udf_time_to_disk_stamp(&lvid->recordingDateAndTime,
-				CURRENT_TIME);
+	ktime_get_real_ts(&ts);
+	udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts);
 	lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_OPEN);
 
 	lvid->descTag.descCRC = cpu_to_le16(
@@ -2019,6 +2018,7 @@ static void udf_close_lvid(struct super_block *sb)
 	struct buffer_head *bh = sbi->s_lvid_bh;
 	struct logicalVolIntegrityDesc *lvid;
 	struct logicalVolIntegrityDescImpUse *lvidiu;
+	struct timespec ts;
 
 	if (!bh)
 		return;
@@ -2030,7 +2030,8 @@ static void udf_close_lvid(struct super_block *sb)
 	mutex_lock(&sbi->s_alloc_mutex);
 	lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX;
 	lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX;
-	udf_time_to_disk_stamp(&lvid->recordingDateAndTime, CURRENT_TIME);
+	ktime_get_real_ts(&ts);
+	udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts);
 	if (UDF_MAX_WRITE_VERSION > le16_to_cpu(lvidiu->maxUDFWriteRev))
 		lvidiu->maxUDFWriteRev = cpu_to_le16(UDF_MAX_WRITE_VERSION);
 	if (sbi->s_udfrev > le16_to_cpu(lvidiu->minUDFReadRev))
@@ -2158,15 +2159,25 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 		ret = udf_load_vrs(sb, &uopt, silent, &fileset);
 	} else {
 		uopt.blocksize = bdev_logical_block_size(sb->s_bdev);
-		ret = udf_load_vrs(sb, &uopt, silent, &fileset);
-		if (ret == -EAGAIN && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) {
-			if (!silent)
-				pr_notice("Rescanning with blocksize %d\n",
-					  UDF_DEFAULT_BLOCKSIZE);
-			brelse(sbi->s_lvid_bh);
-			sbi->s_lvid_bh = NULL;
-			uopt.blocksize = UDF_DEFAULT_BLOCKSIZE;
+		while (uopt.blocksize <= 4096) {
 			ret = udf_load_vrs(sb, &uopt, silent, &fileset);
+			if (ret < 0) {
+				if (!silent && ret != -EACCES) {
+					pr_notice("Scanning with blocksize %d failed\n",
+						  uopt.blocksize);
+				}
+				brelse(sbi->s_lvid_bh);
+				sbi->s_lvid_bh = NULL;
+				/*
+				 * EACCES is special - we want to propagate to
+				 * upper layers that we cannot handle RW mount.
+				 */
+				if (ret == -EACCES)
+					break;
+			} else
+				break;
+
+			uopt.blocksize <<= 1;
 		}
 	}
 	if (ret < 0) {
@@ -2497,3 +2508,9 @@ static unsigned int udf_count_free(struct super_block *sb)
 
 	return accum;
 }
+
+MODULE_AUTHOR("Ben Fennema");
+MODULE_DESCRIPTION("Universal Disk Format Filesystem");
+MODULE_LICENSE("GPL");
+module_init(init_udf_fs)
+module_exit(exit_udf_fs)
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index 8d619773056b..f7dfef53f739 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -152,9 +152,39 @@ out_unmap:
 	return err;
 }
 
+static int udf_symlink_getattr(struct vfsmount *mnt, struct dentry *dentry,
+			       struct kstat *stat)
+{
+	struct inode *inode = d_backing_inode(dentry);
+	struct page *page;
+
+	generic_fillattr(inode, stat);
+	page = read_mapping_page(inode->i_mapping, 0, NULL);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+	/*
+	 * UDF uses non-trivial encoding of symlinks so i_size does not match
+	 * number of characters reported by readlink(2) which apparently some
+	 * applications expect. Also POSIX says that "The value returned in the
+	 * st_size field shall be the length of the contents of the symbolic
+	 * link, and shall not count a trailing null if one is present." So
+	 * let's report the length of string returned by readlink(2) for
+	 * st_size.
+	 */
+	stat->size = strlen(page_address(page));
+	put_page(page);
+
+	return 0;
+}
+
 /*
  * symlinks can't do much...
  */
 const struct address_space_operations udf_symlink_aops = {
 	.readpage		= udf_symlink_filler,
 };
+
+const struct inode_operations udf_symlink_inode_operations = {
+	.get_link	= page_get_link,
+	.getattr	= udf_symlink_getattr,
+};
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 263829ef1873..63b034984378 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -15,7 +15,6 @@
 #include "udfend.h"
 #include "udf_i.h"
 
-#define UDF_PREALLOCATE
 #define UDF_DEFAULT_PREALLOC_BLOCKS	8
 
 extern __printf(3, 4) void _udf_err(struct super_block *sb,
@@ -85,6 +84,7 @@ extern const struct inode_operations udf_dir_inode_operations;
 extern const struct file_operations udf_dir_operations;
 extern const struct inode_operations udf_file_inode_operations;
 extern const struct file_operations udf_file_operations;
+extern const struct inode_operations udf_symlink_inode_operations;
 extern const struct address_space_operations udf_aops;
 extern const struct address_space_operations udf_adinicb_aops;
 extern const struct address_space_operations udf_symlink_aops;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index d96e2f30084b..43953e03c356 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -63,6 +63,7 @@ struct userfaultfd_wait_queue {
 	struct uffd_msg msg;
 	wait_queue_t wq;
 	struct userfaultfd_ctx *ctx;
+	bool waken;
 };
 
 struct userfaultfd_wake_range {
@@ -86,6 +87,12 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
 	if (len && (start > uwq->msg.arg.pagefault.address ||
 		    start + len <= uwq->msg.arg.pagefault.address))
 		goto out;
+	WRITE_ONCE(uwq->waken, true);
+	/*
+	 * The implicit smp_mb__before_spinlock in try_to_wake_up()
+	 * renders uwq->waken visible to other CPUs before the task is
+	 * waken.
+	 */
 	ret = wake_up_state(wq->private, mode);
 	if (ret)
 		/*
@@ -264,6 +271,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	struct userfaultfd_wait_queue uwq;
 	int ret;
 	bool must_wait, return_to_userland;
+	long blocking_state;
 
 	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
@@ -334,10 +342,13 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	uwq.wq.private = current;
 	uwq.msg = userfault_msg(vmf->address, vmf->flags, reason);
 	uwq.ctx = ctx;
+	uwq.waken = false;
 
 	return_to_userland =
 		(vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
 		(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
+	blocking_state = return_to_userland ? TASK_INTERRUPTIBLE :
+			 TASK_KILLABLE;
 
 	spin_lock(&ctx->fault_pending_wqh.lock);
 	/*
@@ -350,8 +361,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	 * following the spin_unlock to happen before the list_add in
 	 * __add_wait_queue.
 	 */
-	set_current_state(return_to_userland ? TASK_INTERRUPTIBLE :
-			  TASK_KILLABLE);
+	set_current_state(blocking_state);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
 	must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
@@ -364,6 +374,29 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 		wake_up_poll(&ctx->fd_wqh, POLLIN);
 		schedule();
 		ret |= VM_FAULT_MAJOR;
+
+		/*
+		 * False wakeups can orginate even from rwsem before
+		 * up_read() however userfaults will wait either for a
+		 * targeted wakeup on the specific uwq waitqueue from
+		 * wake_userfault() or for signals or for uffd
+		 * release.
+		 */
+		while (!READ_ONCE(uwq.waken)) {
+			/*
+			 * This needs the full smp_store_mb()
+			 * guarantee as the state write must be
+			 * visible to other CPUs before reading
+			 * uwq.waken from other CPUs.
+			 */
+			set_current_state(blocking_state);
+			if (READ_ONCE(uwq.waken) ||
+			    READ_ONCE(ctx->released) ||
+			    (return_to_userland ? signal_pending(current) :
+			     fatal_signal_pending(current)))
+				break;
+			schedule();
+		}
 	}
 
 	__set_current_state(TASK_RUNNING);
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index d346d42c54d1..33db69be4832 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -39,6 +39,7 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_btree.h"
 #include "xfs_refcount_btree.h"
+#include "xfs_ialloc_btree.h"
 
 /*
  * Per-AG Block Reservations
@@ -200,22 +201,30 @@ __xfs_ag_resv_init(
 	struct xfs_mount		*mp = pag->pag_mount;
 	struct xfs_ag_resv		*resv;
 	int				error;
+	xfs_extlen_t			reserved;
 
-	resv = xfs_perag_resv(pag, type);
 	if (used > ask)
 		ask = used;
-	resv->ar_asked = ask;
-	resv->ar_reserved = resv->ar_orig_reserved = ask - used;
-	mp->m_ag_max_usable -= ask;
+	reserved = ask - used;
 
-	trace_xfs_ag_resv_init(pag, type, ask);
-
-	error = xfs_mod_fdblocks(mp, -(int64_t)resv->ar_reserved, true);
-	if (error)
+	error = xfs_mod_fdblocks(mp, -(int64_t)reserved, true);
+	if (error) {
 		trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
 				error, _RET_IP_);
+		xfs_warn(mp,
+"Per-AG reservation for AG %u failed.  Filesystem may run out of space.",
+				pag->pag_agno);
+		return error;
+	}
 
-	return error;
+	mp->m_ag_max_usable -= ask;
+
+	resv = xfs_perag_resv(pag, type);
+	resv->ar_asked = ask;
+	resv->ar_reserved = resv->ar_orig_reserved = reserved;
+
+	trace_xfs_ag_resv_init(pag, type, ask);
+	return 0;
 }
 
 /* Create a per-AG block reservation. */
@@ -223,6 +232,8 @@ int
 xfs_ag_resv_init(
 	struct xfs_perag		*pag)
 {
+	struct xfs_mount		*mp = pag->pag_mount;
+	xfs_agnumber_t			agno = pag->pag_agno;
 	xfs_extlen_t			ask;
 	xfs_extlen_t			used;
 	int				error = 0;
@@ -231,23 +242,45 @@ xfs_ag_resv_init(
 	if (pag->pag_meta_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_refcountbt_calc_reserves(pag->pag_mount,
-				pag->pag_agno, &ask, &used);
+		error = xfs_refcountbt_calc_reserves(mp, agno, &ask, &used);
 		if (error)
 			goto out;
 
-		error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
-				ask, used);
+		error = xfs_finobt_calc_reserves(mp, agno, &ask, &used);
 		if (error)
 			goto out;
+
+		error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
+				ask, used);
+		if (error) {
+			/*
+			 * Because we didn't have per-AG reservations when the
+			 * finobt feature was added we might not be able to
+			 * reserve all needed blocks.  Warn and fall back to the
+			 * old and potentially buggy code in that case, but
+			 * ensure we do have the reservation for the refcountbt.
+			 */
+			ask = used = 0;
+
+			mp->m_inotbt_nores = true;
+
+			error = xfs_refcountbt_calc_reserves(mp, agno, &ask,
+					&used);
+			if (error)
+				goto out;
+
+			error = __xfs_ag_resv_init(pag, XFS_AG_RESV_METADATA,
+					ask, used);
+			if (error)
+				goto out;
+		}
 	}
 
 	/* Create the AGFL metadata reservation */
 	if (pag->pag_agfl_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_rmapbt_calc_reserves(pag->pag_mount, pag->pag_agno,
-				&ask, &used);
+		error = xfs_rmapbt_calc_reserves(mp, agno, &ask, &used);
 		if (error)
 			goto out;
 
@@ -256,9 +289,16 @@ xfs_ag_resv_init(
 			goto out;
 	}
 
+#ifdef DEBUG
+	/* need to read in the AGF for the ASSERT below to work */
+	error = xfs_alloc_pagf_init(pag->pag_mount, NULL, pag->pag_agno, 0);
+	if (error)
+		return error;
+
 	ASSERT(xfs_perag_resv(pag, XFS_AG_RESV_METADATA)->ar_reserved +
 	       xfs_perag_resv(pag, XFS_AG_RESV_AGFL)->ar_reserved <=
 	       pag->pagf_freeblks + pag->pagf_flcount);
+#endif
 out:
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index af1ecb19121e..6622d46ddec3 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -131,9 +131,6 @@ xfs_attr_get(
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
 		return -EIO;
 
-	if (!xfs_inode_hasattr(ip))
-		return -ENOATTR;
-
 	error = xfs_attr_args_init(&args, ip, name, flags);
 	if (error)
 		return error;
@@ -392,9 +389,6 @@ xfs_attr_remove(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	if (!xfs_inode_hasattr(dp))
-		return -ENOATTR;
-
 	error = xfs_attr_args_init(&args, dp, name, flags);
 	if (error)
 		return error;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 44773c9eb957..bfc00de5c6f1 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3629,7 +3629,7 @@ xfs_bmap_btalloc(
 		align = xfs_get_cowextsz_hint(ap->ip);
 	else if (xfs_alloc_is_userdata(ap->datatype))
 		align = xfs_get_extsz_hint(ap->ip);
-	if (unlikely(align)) {
+	if (align) {
 		error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev,
 						align, 0, ap->eof, 0, ap->conv,
 						&ap->offset, &ap->length);
@@ -3701,7 +3701,7 @@ xfs_bmap_btalloc(
 		args.minlen = ap->minlen;
 	}
 	/* apply extent size hints if obtained earlier */
-	if (unlikely(align)) {
+	if (align) {
 		args.prod = align;
 		if ((args.mod = (xfs_extlen_t)do_mod(ap->offset, args.prod)))
 			args.mod = (xfs_extlen_t)(args.prod - args.mod);
@@ -4514,8 +4514,6 @@ xfs_bmapi_write(
 	int			n;		/* current extent index */
 	xfs_fileoff_t		obno;		/* old block number (offset) */
 	int			whichfork;	/* data or attr fork */
-	char			inhole;		/* current location is hole in file */
-	char			wasdelay;	/* old extent was delayed */
 
 #ifdef DEBUG
 	xfs_fileoff_t		orig_bno;	/* original block number value */
@@ -4603,22 +4601,44 @@ xfs_bmapi_write(
 	bma.firstblock = firstblock;
 
 	while (bno < end && n < *nmap) {
-		inhole = eof || bma.got.br_startoff > bno;
-		wasdelay = !inhole && isnullstartblock(bma.got.br_startblock);
+		bool			need_alloc = false, wasdelay = false;
 
-		/*
-		 * Make sure we only reflink into a hole.
-		 */
-		if (flags & XFS_BMAPI_REMAP)
-			ASSERT(inhole);
-		if (flags & XFS_BMAPI_COWFORK)
-			ASSERT(!inhole);
+		/* in hole or beyoned EOF? */
+		if (eof || bma.got.br_startoff > bno) {
+			if (flags & XFS_BMAPI_DELALLOC) {
+				/*
+				 * For the COW fork we can reasonably get a
+				 * request for converting an extent that races
+				 * with other threads already having converted
+				 * part of it, as there converting COW to
+				 * regular blocks is not protected using the
+				 * IOLOCK.
+				 */
+				ASSERT(flags & XFS_BMAPI_COWFORK);
+				if (!(flags & XFS_BMAPI_COWFORK)) {
+					error = -EIO;
+					goto error0;
+				}
+
+				if (eof || bno >= end)
+					break;
+			} else {
+				need_alloc = true;
+			}
+		} else {
+			/*
+			 * Make sure we only reflink into a hole.
+			 */
+			ASSERT(!(flags & XFS_BMAPI_REMAP));
+			if (isnullstartblock(bma.got.br_startblock))
+				wasdelay = true;
+		}
 
 		/*
 		 * First, deal with the hole before the allocated space
 		 * that we found, if any.
 		 */
-		if (inhole || wasdelay) {
+		if (need_alloc || wasdelay) {
 			bma.eof = eof;
 			bma.conv = !!(flags & XFS_BMAPI_CONVERT);
 			bma.wasdel = wasdelay;
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index cecd094404cc..cdef87db5262 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -110,6 +110,9 @@ struct xfs_extent_free_item
 /* Map something in the CoW fork. */
 #define XFS_BMAPI_COWFORK	0x200
 
+/* Only convert delalloc space, don't allocate entirely new extents */
+#define XFS_BMAPI_DELALLOC	0x400
+
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \
@@ -120,7 +123,8 @@ struct xfs_extent_free_item
 	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
 	{ XFS_BMAPI_ZERO,	"ZERO" }, \
 	{ XFS_BMAPI_REMAP,	"REMAP" }, \
-	{ XFS_BMAPI_COWFORK,	"COWFORK" }
+	{ XFS_BMAPI_COWFORK,	"COWFORK" }, \
+	{ XFS_BMAPI_DELALLOC,	"DELALLOC" }
 
 
 static inline int xfs_bmapi_aflag(int w)
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 0fd086d03d41..7c471881c9a6 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -82,11 +82,12 @@ xfs_finobt_set_root(
 }
 
 STATIC int
-xfs_inobt_alloc_block(
+__xfs_inobt_alloc_block(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_ptr	*start,
 	union xfs_btree_ptr	*new,
-	int			*stat)
+	int			*stat,
+	enum xfs_ag_resv_type	resv)
 {
 	xfs_alloc_arg_t		args;		/* block allocation args */
 	int			error;		/* error return value */
@@ -103,6 +104,7 @@ xfs_inobt_alloc_block(
 	args.maxlen = 1;
 	args.prod = 1;
 	args.type = XFS_ALLOCTYPE_NEAR_BNO;
+	args.resv = resv;
 
 	error = xfs_alloc_vextent(&args);
 	if (error) {
@@ -123,6 +125,27 @@ xfs_inobt_alloc_block(
 }
 
 STATIC int
+xfs_inobt_alloc_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*start,
+	union xfs_btree_ptr	*new,
+	int			*stat)
+{
+	return __xfs_inobt_alloc_block(cur, start, new, stat, XFS_AG_RESV_NONE);
+}
+
+STATIC int
+xfs_finobt_alloc_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*start,
+	union xfs_btree_ptr	*new,
+	int			*stat)
+{
+	return __xfs_inobt_alloc_block(cur, start, new, stat,
+			XFS_AG_RESV_METADATA);
+}
+
+STATIC int
 xfs_inobt_free_block(
 	struct xfs_btree_cur	*cur,
 	struct xfs_buf		*bp)
@@ -328,7 +351,7 @@ static const struct xfs_btree_ops xfs_finobt_ops = {
 
 	.dup_cursor		= xfs_inobt_dup_cursor,
 	.set_root		= xfs_finobt_set_root,
-	.alloc_block		= xfs_inobt_alloc_block,
+	.alloc_block		= xfs_finobt_alloc_block,
 	.free_block		= xfs_inobt_free_block,
 	.get_minrecs		= xfs_inobt_get_minrecs,
 	.get_maxrecs		= xfs_inobt_get_maxrecs,
@@ -480,3 +503,64 @@ xfs_inobt_rec_check_count(
 	return 0;
 }
 #endif	/* DEBUG */
+
+static xfs_extlen_t
+xfs_inobt_max_size(
+	struct xfs_mount	*mp)
+{
+	/* Bail out if we're uninitialized, which can happen in mkfs. */
+	if (mp->m_inobt_mxr[0] == 0)
+		return 0;
+
+	return xfs_btree_calc_size(mp, mp->m_inobt_mnr,
+		(uint64_t)mp->m_sb.sb_agblocks * mp->m_sb.sb_inopblock /
+				XFS_INODES_PER_CHUNK);
+}
+
+static int
+xfs_inobt_count_blocks(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_btnum_t		btnum,
+	xfs_extlen_t		*tree_blocks)
+{
+	struct xfs_buf		*agbp;
+	struct xfs_btree_cur	*cur;
+	int			error;
+
+	error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
+	if (error)
+		return error;
+
+	cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, btnum);
+	error = xfs_btree_count_blocks(cur, tree_blocks);
+	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_buf_relse(agbp);
+
+	return error;
+}
+
+/*
+ * Figure out how many blocks to reserve and how many are used by this btree.
+ */
+int
+xfs_finobt_calc_reserves(
+	struct xfs_mount	*mp,
+	xfs_agnumber_t		agno,
+	xfs_extlen_t		*ask,
+	xfs_extlen_t		*used)
+{
+	xfs_extlen_t		tree_len = 0;
+	int			error;
+
+	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
+		return 0;
+
+	error = xfs_inobt_count_blocks(mp, agno, XFS_BTNUM_FINO, &tree_len);
+	if (error)
+		return error;
+
+	*ask += xfs_inobt_max_size(mp);
+	*used += tree_len;
+	return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index bd88453217ce..aa81e2e63f3f 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -72,4 +72,7 @@ int xfs_inobt_rec_check_count(struct xfs_mount *,
 #define xfs_inobt_rec_check_count(mp, rec)	0
 #endif	/* DEBUG */
 
+int xfs_finobt_calc_reserves(struct xfs_mount *mp, xfs_agnumber_t agno,
+		xfs_extlen_t *ask, xfs_extlen_t *used);
+
 #endif	/* __XFS_IALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 2580262e4ea0..584ec896a533 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -242,7 +242,7 @@ xfs_mount_validate_sb(
 	    sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG			||
 	    sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG			||
 	    sbp->sb_blocksize != (1 << sbp->sb_blocklog)		||
-	    sbp->sb_dirblklog > XFS_MAX_BLOCKSIZE_LOG			||
+	    sbp->sb_dirblklog + sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG ||
 	    sbp->sb_inodesize < XFS_DINODE_MIN_SIZE			||
 	    sbp->sb_inodesize > XFS_DINODE_MAX_SIZE			||
 	    sbp->sb_inodelog < XFS_DINODE_MIN_LOG			||
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index b9abce524c33..c1417919ab0a 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -528,7 +528,6 @@ xfs_getbmap(
 	xfs_bmbt_irec_t		*map;		/* buffer for user's data */
 	xfs_mount_t		*mp;		/* file system mount point */
 	int			nex;		/* # of user extents can do */
-	int			nexleft;	/* # of user extents left */
 	int			subnex;		/* # of bmapi's can do */
 	int			nmap;		/* number of map entries */
 	struct getbmapx		*out;		/* output structure */
@@ -686,10 +685,8 @@ xfs_getbmap(
 		goto out_free_map;
 	}
 
-	nexleft = nex;
-
 	do {
-		nmap = (nexleft > subnex) ? subnex : nexleft;
+		nmap = (nex> subnex) ? subnex : nex;
 		error = xfs_bmapi_read(ip, XFS_BB_TO_FSBT(mp, bmv->bmv_offset),
 				       XFS_BB_TO_FSB(mp, bmv->bmv_length),
 				       map, &nmap, bmapi_flags);
@@ -697,8 +694,8 @@ xfs_getbmap(
 			goto out_free_map;
 		ASSERT(nmap <= subnex);
 
-		for (i = 0; i < nmap && nexleft && bmv->bmv_length &&
-				cur_ext < bmv->bmv_count; i++) {
+		for (i = 0; i < nmap && bmv->bmv_length &&
+				cur_ext < bmv->bmv_count - 1; i++) {
 			out[cur_ext].bmv_oflags = 0;
 			if (map[i].br_state == XFS_EXT_UNWRITTEN)
 				out[cur_ext].bmv_oflags |= BMV_OF_PREALLOC;
@@ -760,16 +757,27 @@ xfs_getbmap(
 				continue;
 			}
 
+			/*
+			 * In order to report shared extents accurately,
+			 * we report each distinct shared/unshared part
+			 * of a single bmbt record using multiple bmap
+			 * extents.  To make that happen, we iterate the
+			 * same map array item multiple times, each
+			 * time trimming out the subextent that we just
+			 * reported.
+			 *
+			 * Because of this, we must check the out array
+			 * index (cur_ext) directly against bmv_count-1
+			 * to avoid overflows.
+			 */
 			if (inject_map.br_startblock != NULLFSBLOCK) {
 				map[i] = inject_map;
 				i--;
-			} else
-				nexleft--;
+			}
 			bmv->bmv_entries++;
 			cur_ext++;
 		}
-	} while (nmap && nexleft && bmv->bmv_length &&
-		 cur_ext < bmv->bmv_count);
+	} while (nmap && bmv->bmv_length && cur_ext < bmv->bmv_count - 1);
 
  out_free_map:
 	kmem_free(map);
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 7f0a01f7b592..8c7d01b75922 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -422,6 +422,7 @@ retry:
 out_free_pages:
 	for (i = 0; i < bp->b_page_count; i++)
 		__free_page(bp->b_pages[i]);
+	bp->b_flags &= ~_XBF_PAGES;
 	return error;
 }
 
@@ -757,7 +758,7 @@ xfs_buf_readahead_map(
 	int			nmaps,
 	const struct xfs_buf_ops *ops)
 {
-	if (bdi_read_congested(target->bt_bdi))
+	if (bdi_read_congested(target->bt_bdev->bd_bdi))
 		return;
 
 	xfs_buf_read_map(target, map, nmaps,
@@ -1790,7 +1791,6 @@ xfs_alloc_buftarg(
 	btp->bt_mount = mp;
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
-	btp->bt_bdi = blk_get_backing_dev_info(bdev);
 
 	if (xfs_setsize_buftarg_early(btp, bdev))
 		goto error;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 8a9d3a9599f0..3c867e5a63e1 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -109,7 +109,6 @@ typedef unsigned int xfs_buf_flags_t;
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
 	struct block_device	*bt_bdev;
-	struct backing_dev_info	*bt_bdi;
 	struct xfs_mount	*bt_mount;
 	unsigned int		bt_meta_sectorsize;
 	size_t			bt_meta_sectormask;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b9557795eb74..de32f0fe47c8 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1792,22 +1792,23 @@ xfs_inactive_ifree(
 	int			error;
 
 	/*
-	 * The ifree transaction might need to allocate blocks for record
-	 * insertion to the finobt. We don't want to fail here at ENOSPC, so
-	 * allow ifree to dip into the reserved block pool if necessary.
-	 *
-	 * Freeing large sets of inodes generally means freeing inode chunks,
-	 * directory and file data blocks, so this should be relatively safe.
-	 * Only under severe circumstances should it be possible to free enough
-	 * inodes to exhaust the reserve block pool via finobt expansion while
-	 * at the same time not creating free space in the filesystem.
+	 * We try to use a per-AG reservation for any block needed by the finobt
+	 * tree, but as the finobt feature predates the per-AG reservation
+	 * support a degraded file system might not have enough space for the
+	 * reservation at mount time.  In that case try to dip into the reserved
+	 * pool and pray.
 	 *
 	 * Send a warning if the reservation does happen to fail, as the inode
 	 * now remains allocated and sits on the unlinked list until the fs is
 	 * repaired.
 	 */
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
-			XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+	if (unlikely(mp->m_inotbt_nores)) {
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
+				XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE,
+				&tp);
+	} else {
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree, 0, 0, 0, &tp);
+	}
 	if (error) {
 		if (error == -ENOSPC) {
 			xfs_warn_ratelimited(mp,
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 0d147428971e..1aa3abd67b36 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -681,7 +681,7 @@ xfs_iomap_write_allocate(
 	xfs_trans_t	*tp;
 	int		nimaps;
 	int		error = 0;
-	int		flags = 0;
+	int		flags = XFS_BMAPI_DELALLOC;
 	int		nres;
 
 	if (whichfork == XFS_COW_FORK)
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 84f785218907..7f351f706b7a 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -140,6 +140,7 @@ typedef struct xfs_mount {
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_dmevmask;	/* DMI events for this FS */
 	__uint64_t		m_flags;	/* global mount flags */
+	bool			m_inotbt_nores; /* no per-AG finobt resv. */
 	int			m_ialloc_inos;	/* inodes in inode allocation */
 	int			m_ialloc_blks;	/* blocks in inode allocation */
 	int			m_ialloc_min_blks;/* min blocks in sparse inode
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 45e50ea90769..b669b123287b 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1177,7 +1177,8 @@ xfs_qm_dqusage_adjust(
 	 * the case in all other instances. It's OK that we do this because
 	 * quotacheck is done only at mount time.
 	 */
-	error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_EXCL, &ip);
+	error = xfs_iget(mp, NULL, ino, XFS_IGET_DONTCACHE, XFS_ILOCK_EXCL,
+			 &ip);
 	if (error) {
 		*res = BULKSTAT_RV_NOTHING;
 		return error;
diff --git a/include/acpi/acbuffer.h b/include/acpi/acbuffer.h
index cd20d5586f4b..c77b91ff1149 100644
--- a/include/acpi/acbuffer.h
+++ b/include/acpi/acbuffer.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h
index d25da936750e..07740072da55 100644
--- a/include/acpi/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h
index 2c396344a7a2..ad54610ea6cd 100644
--- a/include/acpi/acexcep.h
+++ b/include/acpi/acexcep.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -91,7 +91,6 @@ struct acpi_exception_info {
 #define ACPI_SUCCESS(a)                 (!(a))
 #define ACPI_FAILURE(a)                 (a)
 
-#define ACPI_SKIP(a)                    (a == AE_CTRL_SKIP)
 #define AE_OK                           (acpi_status) 0x0000
 
 /*
@@ -211,11 +210,10 @@ struct acpi_exception_info {
 #define AE_CTRL_TRANSFER                EXCEP_CTL (0x0008)
 #define AE_CTRL_BREAK                   EXCEP_CTL (0x0009)
 #define AE_CTRL_CONTINUE                EXCEP_CTL (0x000A)
-#define AE_CTRL_SKIP                    EXCEP_CTL (0x000B)
-#define AE_CTRL_PARSE_CONTINUE          EXCEP_CTL (0x000C)
-#define AE_CTRL_PARSE_PENDING           EXCEP_CTL (0x000D)
+#define AE_CTRL_PARSE_CONTINUE          EXCEP_CTL (0x000B)
+#define AE_CTRL_PARSE_PENDING           EXCEP_CTL (0x000C)
 
-#define AE_CODE_CTRL_MAX                0x000D
+#define AE_CODE_CTRL_MAX                0x000C
 
 /* Exception strings for acpi_format_exception */
 
@@ -378,7 +376,6 @@ static const struct acpi_exception_info acpi_gbl_exception_names_ctrl[] = {
 	EXCEP_TXT("AE_CTRL_TRANSFER", "Transfer control to called method"),
 	EXCEP_TXT("AE_CTRL_BREAK", "A Break has been executed"),
 	EXCEP_TXT("AE_CTRL_CONTINUE", "A Continue has been executed"),
-	EXCEP_TXT("AE_CTRL_SKIP", "Not currently used"),
 	EXCEP_TXT("AE_CTRL_PARSE_CONTINUE", "Used to skip over bad opcodes"),
 	EXCEP_TXT("AE_CTRL_PARSE_PENDING", "Used to implement AML While loops")
 };
diff --git a/include/acpi/acnames.h b/include/acpi/acnames.h
index be779db708bd..b421584033a5 100644
--- a/include/acpi/acnames.h
+++ b/include/acpi/acnames.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h
index 48eb4dd99bb1..c2e664e74075 100644
--- a/include/acpi/acoutput.h
+++ b/include/acpi/acoutput.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acpi.h b/include/acpi/acpi.h
index 82803ae9713f..ca036620703c 100644
--- a/include/acpi/acpi.h
+++ b/include/acpi/acpi.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 4242c31ffaee..ef0ae8aaa567 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -522,6 +522,8 @@ void acpi_bus_trim(struct acpi_device *start);
 acpi_status acpi_bus_get_ejd(acpi_handle handle, acpi_handle * ejd);
 int acpi_match_device_ids(struct acpi_device *device,
 			  const struct acpi_device_id *ids);
+void acpi_set_modalias(struct acpi_device *adev, const char *default_id,
+		       char *modalias, size_t len);
 int acpi_create_dir(struct acpi_device *);
 void acpi_remove_dir(struct acpi_device *);
 
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index f3414c83abb1..c66eb8ffa454 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -7,7 +7,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -333,6 +333,10 @@ u64 acpi_os_get_timer(void);
 acpi_status acpi_os_signal(u32 function, void *info);
 #endif
 
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_enter_sleep
+acpi_status acpi_os_enter_sleep(u8 sleep_state, u32 rega_value, u32 regb_value);
+#endif
+
 /*
  * Debug print routines
  */
@@ -355,12 +359,12 @@ void acpi_os_redirect_output(void *destination);
 acpi_status acpi_os_get_line(char *buffer, u32 buffer_length, u32 *bytes_read);
 #endif
 
-#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_initialize_command_signals
-acpi_status acpi_os_initialize_command_signals(void);
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_initialize_debugger
+acpi_status acpi_os_initialize_debugger(void);
 #endif
 
-#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_terminate_command_signals
-void acpi_os_terminate_command_signals(void);
+#ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_terminate_debugger
+void acpi_os_terminate_debugger(void);
 #endif
 
 #ifndef ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_wait_command_ready
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index f5e10dd8e86b..3795386ea706 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -46,7 +46,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20160930
+#define ACPI_CA_VERSION                 0x20170119
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
diff --git a/include/acpi/acrestyp.h b/include/acpi/acrestyp.h
index 16c189283ea0..f0f7403d2000 100644
--- a/include/acpi/acrestyp.h
+++ b/include/acpi/acrestyp.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index da5708caf8a1..d92543f3bbfd 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h
index 796d6baae3a3..b4ce55c008b0 100644
--- a/include/acpi/actbl1.h
+++ b/include/acpi/actbl1.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h
index c93dbadfc71d..7aee9fb3bd1f 100644
--- a/include/acpi/actbl2.h
+++ b/include/acpi/actbl2.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/actbl3.h b/include/acpi/actbl3.h
index ebc1f4f9fe66..94414b255a38 100644
--- a/include/acpi/actbl3.h
+++ b/include/acpi/actbl3.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 1d798abae710..d549e31c6d18 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/acuuid.h b/include/acpi/acuuid.h
index 0f269e088f7a..699a1999afe8 100644
--- a/include/acpi/acuuid.h
+++ b/include/acpi/acuuid.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/platform/acenv.h b/include/acpi/platform/acenv.h
index 34cce729109c..09994b063243 100644
--- a/include/acpi/platform/acenv.h
+++ b/include/acpi/platform/acenv.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -75,7 +75,8 @@
 	(defined ACPI_NAMES_APP)    || \
 	(defined ACPI_SRC_APP)      || \
 	(defined ACPI_XTRACT_APP)   || \
-	(defined ACPI_EXAMPLE_APP)
+	(defined ACPI_EXAMPLE_APP)  || \
+	(defined ACPI_EFI_HELLO)
 #define ACPI_APPLICATION
 #define ACPI_SINGLE_THREADED
 #define USE_NATIVE_ALLOCATE_ZEROED
@@ -177,7 +178,7 @@
 #include "acmsvc.h"
 
 #elif defined(__INTEL_COMPILER)
-#include "acintel.h"
+#include <acpi/platform/acintel.h>
 
 #endif
 
@@ -357,7 +358,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <ctype.h>
-#ifdef ACPI_APPLICATION
+#if defined (ACPI_APPLICATION) || defined(ACPI_LIBRARY)
 #include <stdio.h>
 #include <fcntl.h>
 #include <errno.h>
diff --git a/include/acpi/platform/acenvex.h b/include/acpi/platform/acenvex.h
index b3171b9d6974..127c848a1ba7 100644
--- a/include/acpi/platform/acenvex.h
+++ b/include/acpi/platform/acenvex.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h
index 8f66aaabadf7..e877a35ee977 100644
--- a/include/acpi/platform/acgcc.h
+++ b/include/acpi/platform/acgcc.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/platform/acgccex.h b/include/acpi/platform/acgccex.h
index 46ead2caada4..4f701b288cec 100644
--- a/include/acpi/platform/acgccex.h
+++ b/include/acpi/platform/acgccex.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/include/acpi/platform/acintel.h b/include/acpi/platform/acintel.h
new file mode 100644
index 000000000000..17bd3b7b4e5a
--- /dev/null
+++ b/include/acpi/platform/acintel.h
@@ -0,0 +1,87 @@
+/******************************************************************************
+ *
+ * Name: acintel.h - VC specific defines, etc.
+ *
+ *****************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2017, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ *    substantially similar to the "NO WARRANTY" disclaimer below
+ *    ("Disclaimer") and any redistribution must be conditioned upon
+ *    including a substantially similar Disclaimer requirement for further
+ *    binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ *    of any contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#ifndef __ACINTEL_H__
+#define __ACINTEL_H__
+
+/*
+ * Use compiler specific <stdarg.h> is a good practice for even when
+ * -nostdinc is specified (i.e., ACPI_USE_STANDARD_HEADERS undefined.
+ */
+#include <stdarg.h>
+
+/* Configuration specific to Intel 64-bit C compiler */
+
+#define COMPILER_DEPENDENT_INT64    __int64
+#define COMPILER_DEPENDENT_UINT64   unsigned __int64
+#define ACPI_INLINE                 __inline
+
+/*
+ * Calling conventions:
+ *
+ * ACPI_SYSTEM_XFACE        - Interfaces to host OS (handlers, threads)
+ * ACPI_EXTERNAL_XFACE      - External ACPI interfaces
+ * ACPI_INTERNAL_XFACE      - Internal ACPI interfaces
+ * ACPI_INTERNAL_VAR_XFACE  - Internal variable-parameter list interfaces
+ */
+#define ACPI_SYSTEM_XFACE
+#define ACPI_EXTERNAL_XFACE
+#define ACPI_INTERNAL_XFACE
+#define ACPI_INTERNAL_VAR_XFACE
+
+/* remark 981 - operands evaluated in no particular order */
+#pragma warning(disable:981)
+
+/* warn C4100: unreferenced formal parameter */
+#pragma warning(disable:4100)
+
+/* warn C4127: conditional expression is constant */
+#pragma warning(disable:4127)
+
+/* warn C4706: assignment within conditional expression */
+#pragma warning(disable:4706)
+
+/* warn C4214: bit field types other than int */
+#pragma warning(disable:4214)
+
+#endif				/* __ACINTEL_H__ */
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index e861a24f06f2..a39e3f67616f 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -156,8 +156,8 @@
  */
 #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_readable
 #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_writable
-#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_initialize_command_signals
-#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_terminate_command_signals
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_initialize_debugger
+#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_terminate_debugger
 
 /*
  * OSL interfaces used by utilities
@@ -201,7 +201,8 @@
 #define ACPI_CAST_PTHREAD_T(pthread) ((acpi_thread_id) (pthread))
 
 #if defined(__ia64__)    || defined(__x86_64__) ||\
-	defined(__aarch64__) || defined(__PPC64__)
+	defined(__aarch64__) || defined(__PPC64__) ||\
+	defined(__s390x__)
 #define ACPI_MACHINE_WIDTH          64
 #define COMPILER_DEPENDENT_INT64    long
 #define COMPILER_DEPENDENT_UINT64   unsigned long
diff --git a/include/acpi/platform/aclinuxex.h b/include/acpi/platform/aclinuxex.h
index 7dbb1141f546..efdff527f8fc 100644
--- a/include/acpi/platform/aclinuxex.h
+++ b/include/acpi/platform/aclinuxex.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -129,12 +129,12 @@ static inline u8 acpi_os_readable(void *pointer, acpi_size length)
 	return TRUE;
 }
 
-static inline acpi_status acpi_os_initialize_command_signals(void)
+static inline acpi_status acpi_os_initialize_debugger(void)
 {
 	return AE_OK;
 }
 
-static inline void acpi_os_terminate_command_signals(void)
+static inline void acpi_os_terminate_debugger(void)
 {
 	return;
 }
diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h
deleted file mode 100644
index 51969436b8b8..000000000000
--- a/include/asm-generic/cputime.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef _ASM_GENERIC_CPUTIME_H
-#define _ASM_GENERIC_CPUTIME_H
-
-#include <linux/time.h>
-#include <linux/jiffies.h>
-
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-# include <asm-generic/cputime_jiffies.h>
-#endif
-
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-# include <asm-generic/cputime_nsecs.h>
-#endif
-
-#endif
diff --git a/include/asm-generic/cputime_jiffies.h b/include/asm-generic/cputime_jiffies.h
deleted file mode 100644
index 6bb8cd45f53b..000000000000
--- a/include/asm-generic/cputime_jiffies.h
+++ /dev/null
@@ -1,75 +0,0 @@
-#ifndef _ASM_GENERIC_CPUTIME_JIFFIES_H
-#define _ASM_GENERIC_CPUTIME_JIFFIES_H
-
-typedef unsigned long __nocast cputime_t;
-
-#define cmpxchg_cputime(ptr, old, new) cmpxchg(ptr, old, new)
-
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-#define cputime_to_jiffies(__ct)	(__force unsigned long)(__ct)
-#define jiffies_to_cputime(__hz)	(__force cputime_t)(__hz)
-
-typedef u64 __nocast cputime64_t;
-
-#define cputime64_to_jiffies64(__ct)	(__force u64)(__ct)
-#define jiffies64_to_cputime64(__jif)	(__force cputime64_t)(__jif)
-
-
-/*
- * Convert nanoseconds <-> cputime
- */
-#define cputime_to_nsecs(__ct)		\
-	jiffies_to_nsecs(cputime_to_jiffies(__ct))
-#define nsecs_to_cputime64(__nsec)	\
-	jiffies64_to_cputime64(nsecs_to_jiffies64(__nsec))
-#define nsecs_to_cputime(__nsec)	\
-	jiffies_to_cputime(nsecs_to_jiffies(__nsec))
-
-
-/*
- * Convert cputime to microseconds and back.
- */
-#define cputime_to_usecs(__ct)		\
-	jiffies_to_usecs(cputime_to_jiffies(__ct))
-#define usecs_to_cputime(__usec)	\
-	jiffies_to_cputime(usecs_to_jiffies(__usec))
-#define usecs_to_cputime64(__usec)	\
-	jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000))
-
-/*
- * Convert cputime to seconds and back.
- */
-#define cputime_to_secs(jif)		(cputime_to_jiffies(jif) / HZ)
-#define secs_to_cputime(sec)		jiffies_to_cputime((sec) * HZ)
-
-/*
- * Convert cputime to timespec and back.
- */
-#define timespec_to_cputime(__val)	\
-	jiffies_to_cputime(timespec_to_jiffies(__val))
-#define cputime_to_timespec(__ct,__val)	\
-	jiffies_to_timespec(cputime_to_jiffies(__ct),__val)
-
-/*
- * Convert cputime to timeval and back.
- */
-#define timeval_to_cputime(__val)	\
-	jiffies_to_cputime(timeval_to_jiffies(__val))
-#define cputime_to_timeval(__ct,__val)	\
-	jiffies_to_timeval(cputime_to_jiffies(__ct),__val)
-
-/*
- * Convert cputime to clock and back.
- */
-#define cputime_to_clock_t(__ct)	\
-	jiffies_to_clock_t(cputime_to_jiffies(__ct))
-#define clock_t_to_cputime(__x)		\
-	jiffies_to_cputime(clock_t_to_jiffies(__x))
-
-/*
- * Convert cputime64 to clock.
- */
-#define cputime64_to_clock_t(__ct)	\
-	jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct))
-
-#endif
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
deleted file mode 100644
index 4e3b18e559b1..000000000000
--- a/include/asm-generic/cputime_nsecs.h
+++ /dev/null
@@ -1,121 +0,0 @@
-/*
- * Definitions for measuring cputime in nsecs resolution.
- *
- * Based on <arch/ia64/include/asm/cputime.h>
- *
- * Copyright (C) 2007 FUJITSU LIMITED
- * Copyright (C) 2007 Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- */
-
-#ifndef _ASM_GENERIC_CPUTIME_NSECS_H
-#define _ASM_GENERIC_CPUTIME_NSECS_H
-
-#include <linux/math64.h>
-
-typedef u64 __nocast cputime_t;
-typedef u64 __nocast cputime64_t;
-
-#define cmpxchg_cputime(ptr, old, new) cmpxchg64(ptr, old, new)
-
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-
-#define cputime_div(__ct, divisor)  div_u64((__force u64)__ct, divisor)
-#define cputime_div_rem(__ct, divisor, remainder) \
-	div_u64_rem((__force u64)__ct, divisor, remainder);
-
-/*
- * Convert cputime <-> jiffies (HZ)
- */
-#define cputime_to_jiffies(__ct)	\
-	cputime_div(__ct, NSEC_PER_SEC / HZ)
-#define jiffies_to_cputime(__jif)	\
-	(__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ))
-#define cputime64_to_jiffies64(__ct)	\
-	cputime_div(__ct, NSEC_PER_SEC / HZ)
-#define jiffies64_to_cputime64(__jif)	\
-	(__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ))
-
-
-/*
- * Convert cputime <-> nanoseconds
- */
-#define cputime_to_nsecs(__ct)		\
-	(__force u64)(__ct)
-#define nsecs_to_cputime(__nsecs)	\
-	(__force cputime_t)(__nsecs)
-#define nsecs_to_cputime64(__nsecs)	\
-	(__force cputime64_t)(__nsecs)
-
-
-/*
- * Convert cputime <-> microseconds
- */
-#define cputime_to_usecs(__ct)		\
-	cputime_div(__ct, NSEC_PER_USEC)
-#define usecs_to_cputime(__usecs)	\
-	(__force cputime_t)((__usecs) * NSEC_PER_USEC)
-#define usecs_to_cputime64(__usecs)	\
-	(__force cputime64_t)((__usecs) * NSEC_PER_USEC)
-
-/*
- * Convert cputime <-> seconds
- */
-#define cputime_to_secs(__ct)		\
-	cputime_div(__ct, NSEC_PER_SEC)
-#define secs_to_cputime(__secs)		\
-	(__force cputime_t)((__secs) * NSEC_PER_SEC)
-
-/*
- * Convert cputime <-> timespec (nsec)
- */
-static inline cputime_t timespec_to_cputime(const struct timespec *val)
-{
-	u64 ret = (u64)val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
-	return (__force cputime_t) ret;
-}
-static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
-{
-	u32 rem;
-
-	val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem);
-	val->tv_nsec = rem;
-}
-
-/*
- * Convert cputime <-> timeval (msec)
- */
-static inline cputime_t timeval_to_cputime(const struct timeval *val)
-{
-	u64 ret = (u64)val->tv_sec * NSEC_PER_SEC +
-			val->tv_usec * NSEC_PER_USEC;
-	return (__force cputime_t) ret;
-}
-static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
-{
-	u32 rem;
-
-	val->tv_sec = cputime_div_rem(ct, NSEC_PER_SEC, &rem);
-	val->tv_usec = rem / NSEC_PER_USEC;
-}
-
-/*
- * Convert cputime <-> clock (USER_HZ)
- */
-#define cputime_to_clock_t(__ct)	\
-	cputime_div(__ct, (NSEC_PER_SEC / USER_HZ))
-#define clock_t_to_cputime(__x)		\
-	(__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ))
-
-/*
- * Convert cputime64 to clock.
- */
-#define cputime64_to_clock_t(__ct)	\
-	cputime_to_clock_t((__force cputime_t)__ct)
-
-#endif
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
index 63554e9f6e0c..719db1968d81 100644
--- a/include/asm-generic/export.h
+++ b/include/asm-generic/export.h
@@ -9,18 +9,15 @@
 #ifndef KSYM_ALIGN
 #define KSYM_ALIGN 8
 #endif
-#ifndef KCRC_ALIGN
-#define KCRC_ALIGN 8
-#endif
 #else
 #define __put .long
 #ifndef KSYM_ALIGN
 #define KSYM_ALIGN 4
 #endif
+#endif
 #ifndef KCRC_ALIGN
 #define KCRC_ALIGN 4
 #endif
-#endif
 
 #ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX
 #define KSYM(name) _##name
@@ -52,7 +49,11 @@ KSYM(__kstrtab_\name):
 	.section ___kcrctab\sec+\name,"a"
 	.balign KCRC_ALIGN
 KSYM(__kcrctab_\name):
-	__put KSYM(__crc_\name)
+#if defined(CONFIG_MODULE_REL_CRCS)
+	.long KSYM(__crc_\name) - .
+#else
+	.long KSYM(__crc_\name)
+#endif
 	.weak KSYM(__crc_\name)
 	.previous
 #endif
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
index 5be122e3d326..6c6a2141f271 100644
--- a/include/asm-generic/rwsem.h
+++ b/include/asm-generic/rwsem.h
@@ -33,7 +33,7 @@
  */
 static inline void __down_read(struct rw_semaphore *sem)
 {
-	if (unlikely(atomic_long_inc_return_acquire((atomic_long_t *)&sem->count) <= 0))
+	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0))
 		rwsem_down_read_failed(sem);
 }
 
@@ -58,7 +58,7 @@ static inline void __down_write(struct rw_semaphore *sem)
 	long tmp;
 
 	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
-				     (atomic_long_t *)&sem->count);
+					     &sem->count);
 	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
 		rwsem_down_write_failed(sem);
 }
@@ -68,7 +68,7 @@ static inline int __down_write_killable(struct rw_semaphore *sem)
 	long tmp;
 
 	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
-				     (atomic_long_t *)&sem->count);
+					     &sem->count);
 	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
 		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
 			return -EINTR;
@@ -91,7 +91,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 {
 	long tmp;
 
-	tmp = atomic_long_dec_return_release((atomic_long_t *)&sem->count);
+	tmp = atomic_long_dec_return_release(&sem->count);
 	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
 		rwsem_wake(sem);
 }
@@ -102,7 +102,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 static inline void __up_write(struct rw_semaphore *sem)
 {
 	if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS,
-				 (atomic_long_t *)&sem->count) < 0))
+						    &sem->count) < 0))
 		rwsem_wake(sem);
 }
 
@@ -120,8 +120,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 	 * read-locked region is ok to be re-ordered into the
 	 * write side. As such, rely on RELEASE semantics.
 	 */
-	tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS,
-				     (atomic_long_t *)&sem->count);
+	tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count);
 	if (tmp < 0)
 		rwsem_downgrade_wake(sem);
 }
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 192016e2b518..9c4ee144b5f6 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -517,6 +517,7 @@ struct drm_device {
 	struct drm_minor *control;		/**< Control node */
 	struct drm_minor *primary;		/**< Primary node */
 	struct drm_minor *render;		/**< Render node */
+	bool registered;
 
 	/* currently active master for this device. Protected by master_mutex */
 	struct drm_master *master;
diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h
index d6d241f63b9f..56814e8ae7ea 100644
--- a/include/drm/drm_atomic.h
+++ b/include/drm/drm_atomic.h
@@ -144,7 +144,7 @@ struct __drm_crtcs_state {
 	struct drm_crtc *ptr;
 	struct drm_crtc_state *state;
 	struct drm_crtc_commit *commit;
-	s64 __user *out_fence_ptr;
+	s32 __user *out_fence_ptr;
 };
 
 struct __drm_connnectors_state {
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index a9b95246e26e..045a97cbeba2 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -381,6 +381,8 @@ struct drm_connector_funcs {
 	 * core drm connector interfaces. Everything added from this callback
 	 * should be unregistered in the early_unregister callback.
 	 *
+	 * This is called while holding drm_connector->mutex.
+	 *
 	 * Returns:
 	 *
 	 * 0 on success, or a negative error code on failure.
@@ -395,6 +397,8 @@ struct drm_connector_funcs {
 	 * late_register(). It is called from drm_connector_unregister(),
 	 * early in the driver unload sequence to disable userspace access
 	 * before data structures are torndown.
+	 *
+	 * This is called while holding drm_connector->mutex.
 	 */
 	void (*early_unregister)(struct drm_connector *connector);
 
@@ -559,7 +563,6 @@ struct drm_cmdline_mode {
  * @interlace_allowed: can this connector handle interlaced modes?
  * @doublescan_allowed: can this connector handle doublescan?
  * @stereo_allowed: can this connector handle stereo modes?
- * @registered: is this connector exposed (registered) with userspace?
  * @modes: modes available on this connector (from fill_modes() + user)
  * @status: one of the drm_connector_status enums (connected, not, or unknown)
  * @probed_modes: list of modes derived directly from the display
@@ -608,6 +611,13 @@ struct drm_connector {
 	char *name;
 
 	/**
+	 * @mutex: Lock for general connector state, but currently only protects
+	 * @registered. Most of the connector state is still protected by the
+	 * mutex in &drm_mode_config.
+	 */
+	struct mutex mutex;
+
+	/**
 	 * @index: Compacted connector index, which matches the position inside
 	 * the mode_config.list for drivers not supporting hot-add/removing. Can
 	 * be used as an array index. It is invariant over the lifetime of the
@@ -620,6 +630,10 @@ struct drm_connector {
 	bool interlace_allowed;
 	bool doublescan_allowed;
 	bool stereo_allowed;
+	/**
+	 * @registered: Is this connector exposed (registered) with userspace?
+	 * Protected by @mutex.
+	 */
 	bool registered;
 	struct list_head modes; /* list of modes on this connector */
 
diff --git a/include/drm/drm_framebuffer.h b/include/drm/drm_framebuffer.h
index 1ddfa2928802..a232e7f0c869 100644
--- a/include/drm/drm_framebuffer.h
+++ b/include/drm/drm_framebuffer.h
@@ -247,7 +247,7 @@ static inline void drm_framebuffer_unreference(struct drm_framebuffer *fb)
  */
 static inline uint32_t drm_framebuffer_read_refcount(struct drm_framebuffer *fb)
 {
-	return atomic_read(&fb->base.refcount.refcount);
+	return kref_read(&fb->base.refcount);
 }
 
 /**
diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index bf9991b20611..137432386310 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -488,7 +488,7 @@ struct drm_mode_config {
 	/**
 	 * @prop_out_fence_ptr: Sync File fd pointer representing the
 	 * outgoing fences for a CRTC. Userspace should provide a pointer to a
-	 * value of type s64, and then cast that pointer to u64.
+	 * value of type s32, and then cast that pointer to u64.
 	 */
 	struct drm_property *prop_out_fence_ptr;
 	/**
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index 652e45be97c8..9a465314572c 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -332,19 +332,6 @@ extern int ttm_bo_validate(struct ttm_buffer_object *bo,
  */
 extern void ttm_bo_unref(struct ttm_buffer_object **bo);
 
-
-/**
- * ttm_bo_list_ref_sub
- *
- * @bo: The buffer object.
- * @count: The number of references with which to decrease @bo::list_kref;
- * @never_free: The refcount should not reach zero with this operation.
- *
- * Release @count lru list references to this buffer object.
- */
-extern void ttm_bo_list_ref_sub(struct ttm_buffer_object *bo, int count,
-				bool never_free);
-
 /**
  * ttm_bo_add_to_lru
  *
@@ -367,7 +354,7 @@ extern void ttm_bo_add_to_lru(struct ttm_buffer_object *bo);
  * and is usually called just immediately after the bo has been reserved to
  * avoid recursive reservation from lru lists.
  */
-extern int ttm_bo_del_from_lru(struct ttm_buffer_object *bo);
+extern void ttm_bo_del_from_lru(struct ttm_buffer_object *bo);
 
 /**
  * ttm_bo_move_to_lru_tail
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index cdbdb40eb5bd..feecf33a1212 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -878,7 +878,7 @@ static inline int ttm_bo_reserve(struct ttm_buffer_object *bo,
 {
 	int ret;
 
-	WARN_ON(!atomic_read(&bo->kref.refcount));
+	WARN_ON(!kref_read(&bo->kref));
 
 	ret = __ttm_bo_reserve(bo, interruptible, no_wait, ticket);
 	if (likely(ret == 0))
@@ -903,7 +903,7 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo,
 {
 	int ret = 0;
 
-	WARN_ON(!atomic_read(&bo->kref.refcount));
+	WARN_ON(!kref_read(&bo->kref));
 
 	if (interruptible)
 		ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
diff --git a/include/dt-bindings/thermal/lm90.h b/include/dt-bindings/thermal/lm90.h
new file mode 100644
index 000000000000..8c2e3095f704
--- /dev/null
+++ b/include/dt-bindings/thermal/lm90.h
@@ -0,0 +1,12 @@
+/*
+ * This header provides constants for the LM90 thermal bindings.
+ */
+
+#ifndef _DT_BINDINGS_THERMAL_LM90_H_
+#define _DT_BINDINGS_THERMAL_LM90_H_
+
+#define LM90_LOCAL_TEMPERATURE 0
+#define LM90_REMOTE_TEMPERATURE 1
+#define LM90_REMOTE2_TEMPERATURE 2
+
+#endif
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 5b36974ed60a..673acda012af 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -291,7 +291,8 @@ bool acpi_processor_validate_proc_id(int proc_id);
 
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 /* Arch dependent functions for cpu hotplug support */
-int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, int *pcpu);
+int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id,
+		 int *pcpu);
 int acpi_unmap_cpu(int cpu);
 int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid);
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
@@ -1153,4 +1154,14 @@ int parse_spcr(bool earlycon);
 static inline int parse_spcr(bool earlycon) { return 0; }
 #endif
 
+#if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI)
+int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res);
+#else
+static inline
+int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res)
+{
+	return -EINVAL;
+}
+#endif
+
 #endif	/*_LINUX_ACPI_H*/
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index e850e76acaaf..ad955817916d 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -10,6 +10,7 @@
 #include <linux/flex_proportions.h>
 #include <linux/timer.h>
 #include <linux/workqueue.h>
+#include <linux/kref.h>
 
 struct page;
 struct device;
@@ -144,6 +145,7 @@ struct backing_dev_info {
 
 	char *name;
 
+	struct kref refcnt;	/* Reference counter for the structure */
 	unsigned int capabilities; /* Device capabilities */
 	unsigned int min_ratio;
 	unsigned int max_ratio, max_prop_frac;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 43b93a947e61..c52a48cb9a66 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -18,7 +18,14 @@
 #include <linux/slab.h>
 
 int __must_check bdi_init(struct backing_dev_info *bdi);
-void bdi_exit(struct backing_dev_info *bdi);
+
+static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi)
+{
+	kref_get(&bdi->refcnt);
+	return bdi;
+}
+
+void bdi_put(struct backing_dev_info *bdi);
 
 __printf(3, 4)
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -29,6 +36,7 @@ void bdi_unregister(struct backing_dev_info *bdi);
 
 int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
 void bdi_destroy(struct backing_dev_info *bdi);
+struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id);
 
 void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
 			bool range_cyclic, enum wb_reason reason);
@@ -183,7 +191,7 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
 	sb = inode->i_sb;
 #ifdef CONFIG_BLOCK
 	if (sb_is_blkdev_sb(sb))
-		return blk_get_backing_dev_info(I_BDEV(inode));
+		return I_BDEV(inode)->bd_bdi;
 #endif
 	return sb->s_bdi;
 }
diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h
index b20e3d56253f..2f1c690a3e66 100644
--- a/include/linux/bcma/bcma_driver_chipcommon.h
+++ b/include/linux/bcma/bcma_driver_chipcommon.h
@@ -593,9 +593,6 @@ struct bcma_sflash {
 	u32 blocksize;
 	u16 numblocks;
 	u32 size;
-
-	struct mtd_info *mtd;
-	void *priv;
 };
 #endif
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 4a2ab5d99ff7..8e4df3d6c8cd 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -22,6 +22,7 @@ struct blk_mq_hw_ctx {
 
 	unsigned long		flags;		/* BLK_MQ_F_* flags */
 
+	void			*sched_data;
 	struct request_queue	*queue;
 	struct blk_flush_queue	*fq;
 
@@ -35,6 +36,7 @@ struct blk_mq_hw_ctx {
 	atomic_t		wait_index;
 
 	struct blk_mq_tags	*tags;
+	struct blk_mq_tags	*sched_tags;
 
 	struct srcu_struct	queue_rq_srcu;
 
@@ -60,7 +62,7 @@ struct blk_mq_hw_ctx {
 
 struct blk_mq_tag_set {
 	unsigned int		*mq_map;
-	struct blk_mq_ops	*ops;
+	const struct blk_mq_ops	*ops;
 	unsigned int		nr_hw_queues;
 	unsigned int		queue_depth;	/* max hw supported */
 	unsigned int		reserved_tags;
@@ -151,11 +153,13 @@ enum {
 	BLK_MQ_F_SG_MERGE	= 1 << 2,
 	BLK_MQ_F_DEFER_ISSUE	= 1 << 4,
 	BLK_MQ_F_BLOCKING	= 1 << 5,
+	BLK_MQ_F_NO_SCHED	= 1 << 6,
 	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
 	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
 
 	BLK_MQ_S_STOPPED	= 0,
 	BLK_MQ_S_TAG_ACTIVE	= 1,
+	BLK_MQ_S_SCHED_RESTART	= 2,
 
 	BLK_MQ_MAX_DEPTH	= 10240,
 
@@ -179,14 +183,13 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
 
 void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
 
-void blk_mq_insert_request(struct request *, bool, bool, bool);
 void blk_mq_free_request(struct request *rq);
-void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *, struct request *rq);
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *);
 
 enum {
 	BLK_MQ_REQ_NOWAIT	= (1 << 0), /* return when out of requests */
 	BLK_MQ_REQ_RESERVED	= (1 << 1), /* allocate from reserved pool */
+	BLK_MQ_REQ_INTERNAL	= (1 << 2), /* allocate internal/sched tag */
 };
 
 struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 519ea2c9df61..d703acb55d0f 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -162,6 +162,13 @@ enum req_opf {
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= 8,
 
+	/* SCSI passthrough using struct scsi_request */
+	REQ_OP_SCSI_IN		= 32,
+	REQ_OP_SCSI_OUT		= 33,
+	/* Driver private requests */
+	REQ_OP_DRV_IN		= 34,
+	REQ_OP_DRV_OUT		= 35,
+
 	REQ_OP_LAST,
 };
 
@@ -221,6 +228,15 @@ static inline bool op_is_write(unsigned int op)
 }
 
 /*
+ * Check if the bio or request is one that needs special treatment in the
+ * flush state machine.
+ */
+static inline bool op_is_flush(unsigned int op)
+{
+	return op & (REQ_FUA | REQ_PREFLUSH);
+}
+
+/*
  * Reads are always treated as synchronous, as are requests with the FUA or
  * PREFLUSH flag.  Other operations may be marked as synchronous using the
  * REQ_SYNC flag.
@@ -232,22 +248,29 @@ static inline bool op_is_sync(unsigned int op)
 }
 
 typedef unsigned int blk_qc_t;
-#define BLK_QC_T_NONE	-1U
-#define BLK_QC_T_SHIFT	16
+#define BLK_QC_T_NONE		-1U
+#define BLK_QC_T_SHIFT		16
+#define BLK_QC_T_INTERNAL	(1U << 31)
 
 static inline bool blk_qc_t_valid(blk_qc_t cookie)
 {
 	return cookie != BLK_QC_T_NONE;
 }
 
-static inline blk_qc_t blk_tag_to_qc_t(unsigned int tag, unsigned int queue_num)
+static inline blk_qc_t blk_tag_to_qc_t(unsigned int tag, unsigned int queue_num,
+				       bool internal)
 {
-	return tag | (queue_num << BLK_QC_T_SHIFT);
+	blk_qc_t ret = tag | (queue_num << BLK_QC_T_SHIFT);
+
+	if (internal)
+		ret |= BLK_QC_T_INTERNAL;
+
+	return ret;
 }
 
 static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie)
 {
-	return cookie >> BLK_QC_T_SHIFT;
+	return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT;
 }
 
 static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
@@ -255,6 +278,11 @@ static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie)
 	return cookie & ((1u << BLK_QC_T_SHIFT) - 1);
 }
 
+static inline bool blk_qc_t_is_internal(blk_qc_t cookie)
+{
+	return (cookie & BLK_QC_T_INTERNAL) != 0;
+}
+
 struct blk_issue_stat {
 	u64 time;
 };
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1ca8e8fd1078..aecca0e7d9ca 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -71,15 +71,6 @@ struct request_list {
 };
 
 /*
- * request command types
- */
-enum rq_cmd_type_bits {
-	REQ_TYPE_FS		= 1,	/* fs request */
-	REQ_TYPE_BLOCK_PC,		/* scsi command */
-	REQ_TYPE_DRV_PRIV,		/* driver defined types from here */
-};
-
-/*
  * request flags */
 typedef __u32 __bitwise req_flags_t;
 
@@ -128,8 +119,6 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_NOMERGE_FLAGS \
 	(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
 
-#define BLK_MAX_CDB	16
-
 /*
  * Try to put the fields that are referenced together in the same cacheline.
  *
@@ -147,13 +136,16 @@ struct request {
 	struct blk_mq_ctx *mq_ctx;
 
 	int cpu;
-	unsigned cmd_type;
 	unsigned int cmd_flags;		/* op and common flags */
 	req_flags_t rq_flags;
+
+	int internal_tag;
+
 	unsigned long atomic_flags;
 
 	/* the following two fields are internal, NEVER access directly */
 	unsigned int __data_len;	/* total data len */
+	int tag;
 	sector_t __sector;		/* sector cursor */
 
 	struct bio *bio;
@@ -222,20 +214,9 @@ struct request {
 
 	void *special;		/* opaque pointer available for LLD use */
 
-	int tag;
 	int errors;
 
-	/*
-	 * when request is used as a packet command carrier
-	 */
-	unsigned char __cmd[BLK_MAX_CDB];
-	unsigned char *cmd;
-	unsigned short cmd_len;
-
 	unsigned int extra_len;	/* length of alignment and padding */
-	unsigned int sense_len;
-	unsigned int resid_len;	/* residual count */
-	void *sense;
 
 	unsigned long deadline;
 	struct list_head timeout_list;
@@ -252,6 +233,21 @@ struct request {
 	struct request *next_rq;
 };
 
+static inline bool blk_rq_is_scsi(struct request *rq)
+{
+	return req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT;
+}
+
+static inline bool blk_rq_is_private(struct request *rq)
+{
+	return req_op(rq) == REQ_OP_DRV_IN || req_op(rq) == REQ_OP_DRV_OUT;
+}
+
+static inline bool blk_rq_is_passthrough(struct request *rq)
+{
+	return blk_rq_is_scsi(rq) || blk_rq_is_private(rq);
+}
+
 static inline unsigned short req_get_ioprio(struct request *req)
 {
 	return req->ioprio;
@@ -271,6 +267,8 @@ typedef void (softirq_done_fn)(struct request *);
 typedef int (dma_drain_needed_fn)(struct request *);
 typedef int (lld_busy_fn) (struct request_queue *q);
 typedef int (bsg_job_fn) (struct bsg_job *);
+typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t);
+typedef void (exit_rq_fn)(struct request_queue *, struct request *);
 
 enum blk_eh_timer_return {
 	BLK_EH_NOT_HANDLED,
@@ -333,6 +331,7 @@ struct queue_limits {
 	unsigned short		logical_block_size;
 	unsigned short		max_segments;
 	unsigned short		max_integrity_segments;
+	unsigned short		max_discard_segments;
 
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
@@ -406,8 +405,10 @@ struct request_queue {
 	rq_timed_out_fn		*rq_timed_out_fn;
 	dma_drain_needed_fn	*dma_drain_needed;
 	lld_busy_fn		*lld_busy_fn;
+	init_rq_fn		*init_rq_fn;
+	exit_rq_fn		*exit_rq_fn;
 
-	struct blk_mq_ops	*mq_ops;
+	const struct blk_mq_ops	*mq_ops;
 
 	unsigned int		*mq_map;
 
@@ -432,7 +433,8 @@ struct request_queue {
 	 */
 	struct delayed_work	delay_work;
 
-	struct backing_dev_info	backing_dev_info;
+	struct backing_dev_info	*backing_dev_info;
+	struct disk_devt	*disk_devt;
 
 	/*
 	 * The queue owner gets to use this for whatever they like.
@@ -569,7 +571,15 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		*bio_split;
 
+#ifdef CONFIG_BLK_DEBUG_FS
+	struct dentry		*debugfs_dir;
+	struct dentry		*mq_debugfs_dir;
+#endif
+
 	bool			mq_sysfs_init_done;
+
+	size_t			cmd_size;
+	void			*rq_alloc_data;
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
@@ -600,6 +610,7 @@ struct request_queue {
 #define QUEUE_FLAG_FLUSH_NQ    25	/* flush not queueuable */
 #define QUEUE_FLAG_DAX         26	/* device supports DAX */
 #define QUEUE_FLAG_STATS       27	/* track rq completion times */
+#define QUEUE_FLAG_RESTART     28	/* queue needs restart at completion */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
@@ -695,9 +706,10 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 	((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
 			     REQ_FAILFAST_DRIVER))
 
-#define blk_account_rq(rq) \
-	(((rq)->rq_flags & RQF_STARTED) && \
-	 ((rq)->cmd_type == REQ_TYPE_FS))
+static inline bool blk_account_rq(struct request *rq)
+{
+	return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq);
+}
 
 #define blk_rq_cpu_valid(rq)	((rq)->cpu != -1)
 #define blk_bidi_rq(rq)		((rq)->next_rq != NULL)
@@ -772,7 +784,7 @@ static inline void blk_clear_rl_full(struct request_list *rl, bool sync)
 
 static inline bool rq_mergeable(struct request *rq)
 {
-	if (rq->cmd_type != REQ_TYPE_FS)
+	if (blk_rq_is_passthrough(rq))
 		return false;
 
 	if (req_op(rq) == REQ_OP_FLUSH)
@@ -910,7 +922,6 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
-extern void blk_rq_set_block_pc(struct request *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
@@ -1047,7 +1058,7 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
 {
 	struct request_queue *q = rq->q;
 
-	if (unlikely(rq->cmd_type != REQ_TYPE_FS))
+	if (blk_rq_is_passthrough(rq))
 		return q->limits.max_hw_sectors;
 
 	if (!q->limits.chunk_sectors ||
@@ -1129,14 +1140,15 @@ extern void blk_unprep_request(struct request *);
 extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn,
 					spinlock_t *lock, int node_id);
 extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *);
-extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
-						      request_fn_proc *, spinlock_t *);
+extern int blk_init_allocated_queue(struct request_queue *);
 extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_segments(struct request_queue *, unsigned short);
+extern void blk_queue_max_discard_segments(struct request_queue *,
+		unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
@@ -1179,8 +1191,16 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable);
 extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
-extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 
+/*
+ * Number of physical segments as sent to the device.
+ *
+ * Normally this is the number of discontiguous data segments sent by the
+ * submitter.  But for data-less command like discard we might have no
+ * actual data segments submitted, but the driver might have to add it's
+ * own special payload.  In that case we still return 1 here so that this
+ * special payload will be mapped.
+ */
 static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
 {
 	if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
@@ -1188,6 +1208,15 @@ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq)
 	return rq->nr_phys_segments;
 }
 
+/*
+ * Number of discard segments (or ranges) the driver needs to fill in.
+ * Each discard bio merged into a request is counted as one segment.
+ */
+static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
+{
+	return max_t(unsigned short, rq->nr_phys_segments, 1);
+}
+
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
 extern long nr_blockdev_pages(void);
@@ -1376,6 +1405,11 @@ static inline unsigned short queue_max_segments(struct request_queue *q)
 	return q->limits.max_segments;
 }
 
+static inline unsigned short queue_max_discard_segments(struct request_queue *q)
+{
+	return q->limits.max_discard_segments;
+}
+
 static inline unsigned int queue_max_segment_size(struct request_queue *q)
 {
 	return q->limits.max_segment_size;
@@ -1620,6 +1654,25 @@ static inline bool bvec_gap_to_prev(struct request_queue *q,
 	return __bvec_gap_to_prev(q, bprv, offset);
 }
 
+/*
+ * Check if the two bvecs from two bios can be merged to one segment.
+ * If yes, no need to check gap between the two bios since the 1st bio
+ * and the 1st bvec in the 2nd bio can be handled in one segment.
+ */
+static inline bool bios_segs_mergeable(struct request_queue *q,
+		struct bio *prev, struct bio_vec *prev_last_bv,
+		struct bio_vec *next_first_bv)
+{
+	if (!BIOVEC_PHYS_MERGEABLE(prev_last_bv, next_first_bv))
+		return false;
+	if (!BIOVEC_SEG_BOUNDARY(q, prev_last_bv, next_first_bv))
+		return false;
+	if (prev->bi_seg_back_size + next_first_bv->bv_len >
+			queue_max_segment_size(q))
+		return false;
+	return true;
+}
+
 static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
 			 struct bio *next)
 {
@@ -1629,7 +1682,8 @@ static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
 		bio_get_last_bvec(prev, &pb);
 		bio_get_first_bvec(next, &nb);
 
-		return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
+		if (!bios_segs_mergeable(q, prev, &pb, &nb))
+			return __bvec_gap_to_prev(q, &pb, nb.bv_offset);
 	}
 
 	return false;
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index e417f080219a..d2e908586e3d 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -30,9 +30,6 @@ struct blk_trace {
 
 extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
 extern void blk_trace_shutdown(struct request_queue *);
-extern int do_blk_trace_setup(struct request_queue *q, char *name,
-			      dev_t dev, struct block_device *bdev,
-			      struct blk_user_trace_setup *buts);
 extern __printf(2, 3)
 void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 
@@ -80,7 +77,6 @@ extern struct attribute_group blk_trace_attr_group;
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
 # define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
 # define blk_trace_shutdown(q)				do { } while (0)
-# define do_blk_trace_setup(q, name, dev, bdev, buts)	(-ENOTTY)
 # define blk_add_driver_data(q, rq, data, len)		do {} while (0)
 # define blk_trace_setup(q, name, dev, bdev, arg)	(-ENOTTY)
 # define blk_trace_startstop(q, start)			(-ENOTTY)
@@ -110,16 +106,16 @@ struct compat_blk_user_trace_setup {
 
 #endif
 
-#if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK)
+extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes);
 
-static inline int blk_cmd_buf_len(struct request *rq)
+static inline sector_t blk_rq_trace_sector(struct request *rq)
 {
-	return (rq->cmd_type == REQ_TYPE_BLOCK_PC) ? rq->cmd_len * 3 : 1;
+	return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq);
 }
 
-extern void blk_dump_cmd(char *buf, struct request *rq);
-extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes);
-
-#endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
+static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq)
+{
+	return blk_rq_is_passthrough(rq) ? 0 : blk_rq_sectors(rq);
+}
 
 #endif
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 92bc89ae7e20..c970a25d2a49 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -21,20 +21,19 @@ struct cgroup_bpf {
 	 */
 	struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE];
 	struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE];
+	bool disallow_override[MAX_BPF_ATTACH_TYPE];
 };
 
 void cgroup_bpf_put(struct cgroup *cgrp);
 void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent);
 
-void __cgroup_bpf_update(struct cgroup *cgrp,
-			 struct cgroup *parent,
-			 struct bpf_prog *prog,
-			 enum bpf_attach_type type);
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+			struct bpf_prog *prog, enum bpf_attach_type type,
+			bool overridable);
 
 /* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */
-void cgroup_bpf_update(struct cgroup *cgrp,
-		       struct bpf_prog *prog,
-		       enum bpf_attach_type type);
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, bool overridable);
 
 int __cgroup_bpf_run_filter_skb(struct sock *sk,
 				struct sk_buff *skb,
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 05cf951df3fe..3ed1f3b1d594 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -247,6 +247,8 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_precharge_memlock(u32 pages);
+void *bpf_map_area_alloc(size_t size);
+void bpf_map_area_free(void *base);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index 657a718c27d2..e34dde2da0ef 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -66,9 +66,8 @@ struct bsg_job {
 
 void bsg_job_done(struct bsg_job *job, int result,
 		  unsigned int reply_payload_rcv_len);
-int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name,
-		    bsg_job_fn *job_fn, int dd_job_size);
-void bsg_request_fn(struct request_queue *q);
+struct request_queue *bsg_setup_queue(struct device *dev, char *name,
+		bsg_job_fn *job_fn, int dd_job_size);
 void bsg_job_put(struct bsg_job *job);
 int __must_check bsg_job_get(struct bsg_job *job);
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index d67ab83823ad..79591c3660cc 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -243,12 +243,10 @@ static inline int block_page_mkwrite_return(int err)
 {
 	if (err == 0)
 		return VM_FAULT_LOCKED;
-	if (err == -EFAULT)
+	if (err == -EFAULT || err == -EAGAIN)
 		return VM_FAULT_NOPAGE;
 	if (err == -ENOMEM)
 		return VM_FAULT_OOM;
-	if (err == -EAGAIN)
-		return VM_FAULT_RETRY;
 	/* -ENOSPC, -EDQUOT, -EIO ... */
 	return VM_FAULT_SIGBUS;
 }
diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index a0875001b13c..df08a41d5be5 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -45,10 +45,9 @@ struct can_proto {
 extern int  can_proto_register(const struct can_proto *cp);
 extern void can_proto_unregister(const struct can_proto *cp);
 
-extern int  can_rx_register(struct net_device *dev, canid_t can_id,
-			    canid_t mask,
-			    void (*func)(struct sk_buff *, void *),
-			    void *data, char *ident);
+int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
+		    void (*func)(struct sk_buff *, void *),
+		    void *data, char *ident, struct sock *sk);
 
 extern void can_rx_unregister(struct net_device *dev, canid_t can_id,
 			      canid_t mask,
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 8609d577bb66..6e8f209a6dff 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -36,7 +36,7 @@ struct packet_command
 
 /* Uniform cdrom data structures for cdrom.c */
 struct cdrom_device_info {
-	struct cdrom_device_ops  *ops;  /* link to device_ops */
+	const struct cdrom_device_ops *ops; /* link to device_ops */
 	struct list_head list;		/* linked list of all device_info */
 	struct gendisk *disk;		/* matching block layer disk */
 	void *handle;		        /* driver-dependent data */
@@ -87,7 +87,6 @@ struct cdrom_device_ops {
 
 /* driver specifications */
 	const int capability;   /* capability flags */
-	int n_minors;           /* number of active minor devices */
 	/* handle uniform packets for scsi type devices (scsi,atapi) */
 	int (*generic_packet) (struct cdrom_device_info *,
 			       struct packet_command *);
@@ -123,6 +122,8 @@ extern int cdrom_mode_sense(struct cdrom_device_info *cdi,
 			    int page_code, int page_control);
 extern void init_cdrom_command(struct packet_command *cgc,
 			       void *buffer, int len, int type);
+extern int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi,
+				      struct packet_command *cgc);
 
 /* The SCSI spec says there could be 256 slots. */
 #define CDROM_MAX_SLOTS	256
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 0d442e34c349..5d3053c34fb3 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -224,4 +224,13 @@ static inline void tick_setup_hrtimer_broadcast(void) { }
 
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
+#define CLOCKEVENT_OF_DECLARE(name, compat, fn) \
+	OF_DECLARE_1_RET(clkevt, name, compat, fn)
+
+#ifdef CONFIG_CLKEVT_PROBE
+extern int clockevent_probe(void);
+#els
+static inline int clockevent_probe(void) { return 0; }
+#endif
+
 #endif /* _LINUX_CLOCKCHIPS_H */
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index e315d04a2fd9..cfc75848a35d 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -62,6 +62,8 @@ struct module;
  * @archdata:		arch-specific data
  * @suspend:		suspend function for the clocksource, if necessary
  * @resume:		resume function for the clocksource, if necessary
+ * @mark_unstable:	Optional function to inform the clocksource driver that
+ *			the watchdog marked the clocksource unstable
  * @owner:		module reference, must be set by clocksource in modules
  *
  * Note: This struct is not used in hotpathes of the timekeeping code
@@ -93,6 +95,7 @@ struct clocksource {
 	unsigned long flags;
 	void (*suspend)(struct clocksource *cs);
 	void (*resume)(struct clocksource *cs);
+	void (*mark_unstable)(struct clocksource *cs);
 
 	/* private: */
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 63609398ef9f..9e40be522793 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -731,7 +731,25 @@ asmlinkage long compat_sys_fanotify_mark(int, unsigned int, __u32, __u32,
 static inline bool in_compat_syscall(void) { return is_compat_task(); }
 #endif
 
-#else
+/**
+ * ns_to_compat_timeval - Compat version of ns_to_timeval
+ * @nsec:	the nanoseconds value to be converted
+ *
+ * Returns the compat_timeval representation of the nsec parameter.
+ */
+static inline struct compat_timeval ns_to_compat_timeval(s64 nsec)
+{
+	struct timeval tv;
+	struct compat_timeval ctv;
+
+	tv = ns_to_timeval(nsec);
+	ctv.tv_sec = tv.tv_sec;
+	ctv.tv_usec = tv.tv_usec;
+
+	return ctv;
+}
+
+#else /* !CONFIG_COMPAT */
 
 #define is_compat_task() (0)
 static inline bool in_compat_syscall(void) { return false; }
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 7e05c5e4e45c..87165f06a307 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -31,7 +31,7 @@
 
 #define CPUFREQ_ETERNAL			(-1)
 #define CPUFREQ_NAME_LEN		16
-/* Print length for names. Extra 1 space for accomodating '\n' in prints */
+/* Print length for names. Extra 1 space for accommodating '\n' in prints */
 #define CPUFREQ_NAME_PLEN		(CPUFREQ_NAME_LEN + 1)
 
 struct cpufreq_governor;
@@ -115,7 +115,7 @@ struct cpufreq_policy {
 	 *   guarantee that frequency can be changed on any CPU sharing the
 	 *   policy and that the change will affect all of the policy CPUs then.
 	 * - fast_switch_enabled is to be set by governors that support fast
-	 *   freqnency switching with the help of cpufreq_enable_fast_switch().
+	 *   frequency switching with the help of cpufreq_enable_fast_switch().
 	 */
 	bool			fast_switch_possible;
 	bool			fast_switch_enabled;
@@ -415,9 +415,6 @@ static inline void cpufreq_resume(void) {}
 /* Policy Notifiers  */
 #define CPUFREQ_ADJUST			(0)
 #define CPUFREQ_NOTIFY			(1)
-#define CPUFREQ_START			(2)
-#define CPUFREQ_CREATE_POLICY		(3)
-#define CPUFREQ_REMOVE_POLICY		(4)
 
 #ifdef CONFIG_CPU_FREQ
 int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index d936a0021839..921acaaa1601 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -8,9 +8,7 @@ enum cpuhp_state {
 	CPUHP_CREATE_THREADS,
 	CPUHP_PERF_PREPARE,
 	CPUHP_PERF_X86_PREPARE,
-	CPUHP_PERF_X86_UNCORE_PREP,
 	CPUHP_PERF_X86_AMD_UNCORE_PREP,
-	CPUHP_PERF_X86_RAPL_PREP,
 	CPUHP_PERF_BFIN,
 	CPUHP_PERF_POWER,
 	CPUHP_PERF_SUPERH,
@@ -86,7 +84,6 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
-	CPUHP_AP_PERF_X86_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_STARTING,
 	CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index c717f5ea88cb..96f1e88b767c 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -560,7 +560,7 @@ static inline void cpumask_copy(struct cpumask *dstp,
 static inline int cpumask_parse_user(const char __user *buf, int len,
 				     struct cpumask *dstp)
 {
-	return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpu_ids);
+	return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
@@ -575,7 +575,7 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
 				     struct cpumask *dstp)
 {
 	return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
-				     nr_cpu_ids);
+				     nr_cpumask_bits);
 }
 
 /**
@@ -590,7 +590,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
 	char *nl = strchr(buf, '\n');
 	unsigned int len = nl ? (unsigned int)(nl - buf) : strlen(buf);
 
-	return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpu_ids);
+	return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
@@ -602,7 +602,7 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
  */
 static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
 {
-	return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpu_ids);
+	return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
@@ -649,11 +649,15 @@ static inline size_t cpumask_size(void)
  * used. Please use this_cpu_cpumask_var_t in those cases. The direct use
  * of this_cpu_ptr() or this_cpu_read() will lead to failures when the
  * other type of cpumask_var_t implementation is configured.
+ *
+ * Please also note that __cpumask_var_read_mostly can be used to declare
+ * a cpumask_var_t variable itself (not its content) as read mostly.
  */
 #ifdef CONFIG_CPUMASK_OFFSTACK
 typedef struct cpumask *cpumask_var_t;
 
-#define this_cpu_cpumask_var_ptr(x) this_cpu_read(x)
+#define this_cpu_cpumask_var_ptr(x)	this_cpu_read(x)
+#define __cpumask_var_read_mostly	__read_mostly
 
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
@@ -667,6 +671,7 @@ void free_bootmem_cpumask_var(cpumask_var_t mask);
 typedef struct cpumask cpumask_var_t[1];
 
 #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
+#define __cpumask_var_read_mostly
 
 static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
diff --git a/include/linux/cputime.h b/include/linux/cputime.h
index f2eb2ee535ca..a691dc4ddc13 100644
--- a/include/linux/cputime.h
+++ b/include/linux/cputime.h
@@ -1,6 +1,7 @@
 #ifndef __LINUX_CPUTIME_H
 #define __LINUX_CPUTIME_H
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 #include <asm/cputime.h>
 
 #ifndef cputime_to_nsecs
@@ -8,9 +9,5 @@
 	(cputime_to_usecs(__ct) * NSEC_PER_USEC)
 #endif
 
-#ifndef nsecs_to_cputime
-# define nsecs_to_cputime(__nsecs)	\
-	usecs_to_cputime((__nsecs) / NSEC_PER_USEC)
-#endif
-
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #endif /* __LINUX_CPUTIME_H */
diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h
index f4754282c9c2..3252799832cf 100644
--- a/include/linux/cryptohash.h
+++ b/include/linux/cryptohash.h
@@ -15,6 +15,4 @@ void sha_transform(__u32 *digest, const char *data, __u32 *W);
 
 void md5_transform(__u32 *hash, __u32 const *in);
 
-__u32 half_md4_transform(__u32 buf[4], __u32 const in[8]);
-
 #endif
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index 014cc564d1c4..c0befcf41b58 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -80,6 +80,8 @@ static const struct file_operations __fops = {				\
 
 #if defined(CONFIG_DEBUG_FS)
 
+struct dentry *debugfs_lookup(const char *name, struct dentry *parent);
+
 struct dentry *debugfs_create_file(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops);
@@ -181,6 +183,12 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
  * want to duplicate the design decision mistakes of procfs and devfs again.
  */
 
+static inline struct dentry *debugfs_lookup(const char *name,
+					    struct dentry *parent)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline struct dentry *debugfs_create_file(const char *name, umode_t mode,
 					struct dentry *parent, void *data,
 					const struct file_operations *fops)
diff --git a/include/linux/delay.h b/include/linux/delay.h
index a6ecb34cf547..2ecb3c46b20a 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -5,6 +5,17 @@
  * Copyright (C) 1993 Linus Torvalds
  *
  * Delay routines, using a pre-computed "loops_per_jiffy" value.
+ *
+ * Please note that ndelay(), udelay() and mdelay() may return early for
+ * several reasons:
+ *  1. computed loops_per_jiffy too low (due to the time taken to
+ *     execute the timer interrupt.)
+ *  2. cache behaviour affecting the time it takes to execute the
+ *     loop function.
+ *  3. CPU clock rate changes.
+ *
+ * Please see this thread:
+ *   http://lists.openwall.net/linux-kernel/2011/01/09/56
  */
 
 #include <linux/kernel.h>
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 6cee17c22313..00e60f79a9cc 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -17,6 +17,7 @@
 #ifndef _LINUX_DELAYACCT_H
 #define _LINUX_DELAYACCT_H
 
+#include <uapi/linux/taskstats.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 2de4e2eea180..e0acb0e5243b 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -104,6 +104,8 @@ struct devfreq_dev_profile {
  * struct devfreq_governor - Devfreq policy governor
  * @node:		list node - contains registered devfreq governors
  * @name:		Governor's name
+ * @immutable:		Immutable flag for governor. If the value is 1,
+ *			this govenror is never changeable to other governor.
  * @get_target_freq:	Returns desired operating frequency for the device.
  *			Basically, get_target_freq will run
  *			devfreq_dev_profile.get_dev_status() to get the
@@ -121,6 +123,7 @@ struct devfreq_governor {
 	struct list_head node;
 
 	const char name[DEVFREQ_NAME_LEN];
+	const unsigned int immutable;
 	int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
 	int (*event_handler)(struct devfreq *devfreq,
 				unsigned int event, void *data);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index ef7962e84444..a7e6903866fd 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -55,8 +55,6 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti);
  * = 2: The target wants to push back the io
  */
 typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio);
-typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone,
-				  union map_info *map_context);
 typedef int (*dm_clone_and_map_request_fn) (struct dm_target *ti,
 					    struct request *rq,
 					    union map_info *map_context,
@@ -163,7 +161,6 @@ struct target_type {
 	dm_ctr_fn ctr;
 	dm_dtr_fn dtr;
 	dm_map_fn map;
-	dm_map_request_fn map_rq;
 	dm_clone_and_map_request_fn clone_and_map_rq;
 	dm_release_clone_request_fn release_clone_rq;
 	dm_endio_fn end_io;
diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index 7f7e9a7e3839..5725c94b1f12 100644
--- a/include/linux/dma-iommu.h
+++ b/include/linux/dma-iommu.h
@@ -27,6 +27,7 @@ int iommu_dma_init(void);
 
 /* Domain management interface for IOMMU drivers */
 int iommu_get_dma_cookie(struct iommu_domain *domain);
+int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base);
 void iommu_put_dma_cookie(struct iommu_domain *domain);
 
 /* Setup call for arch DMA mapping code */
@@ -34,7 +35,8 @@ int iommu_dma_init_domain(struct iommu_domain *domain, dma_addr_t base,
 		u64 size, struct device *dev);
 
 /* General helpers for DMA-API <-> IOMMU-API interaction */
-int dma_direction_to_prot(enum dma_data_direction dir, bool coherent);
+int dma_info_to_prot(enum dma_data_direction dir, bool coherent,
+		     unsigned long attrs);
 
 /*
  * These implement the bulk of the relevant DMA mapping callbacks, but require
@@ -65,7 +67,6 @@ dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
 void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
-int iommu_dma_supported(struct device *dev, u64 mask);
 int iommu_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
 
 /* The DMA API isn't _quite_ the whole story, though... */
@@ -86,6 +87,11 @@ static inline int iommu_get_dma_cookie(struct iommu_domain *domain)
 	return -ENODEV;
 }
 
+static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
+{
+	return -ENODEV;
+}
+
 static inline void iommu_put_dma_cookie(struct iommu_domain *domain)
 {
 }
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 10c5a17b1f51..c24721a33b4c 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -63,6 +63,13 @@
 #define DMA_ATTR_NO_WARN	(1UL << 8)
 
 /*
+ * DMA_ATTR_PRIVILEGED: used to indicate that the buffer is fully
+ * accessible at an elevated privilege level (and ideally inaccessible or
+ * at least read-only at lesser-privileged levels).
+ */
+#define DMA_ATTR_PRIVILEGED		(1UL << 9)
+
+/*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.
  * It can be given to a device to use as a DMA source or target.  A CPU cannot
  * reference a dma_addr_t directly because there may be translation between
diff --git a/include/linux/edac.h b/include/linux/edac.h
index 07c52c0af62d..5b6adf964248 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -190,8 +190,8 @@ static inline char *mc_event_error_type(const unsigned int err_type)
  *			part of the memory details to the memory controller.
  * @MEM_RMBS:		Rambus DRAM, used on a few Pentium III/IV controllers.
  * @MEM_DDR2:		DDR2 RAM, as described at JEDEC JESD79-2F.
- *			Those memories are labed as "PC2-" instead of "PC" to
- *			differenciate from DDR.
+ *			Those memories are labeled as "PC2-" instead of "PC" to
+ *			differentiate from DDR.
  * @MEM_FB_DDR2:	Fully-Buffered DDR2, as described at JEDEC Std No. 205
  *			and JESD206.
  *			Those memories are accessed per DIMM slot, and not by
diff --git a/include/linux/efi-bgrt.h b/include/linux/efi-bgrt.h
index 051b21fedf68..2fd3993c370b 100644
--- a/include/linux/efi-bgrt.h
+++ b/include/linux/efi-bgrt.h
@@ -1,20 +1,19 @@
 #ifndef _LINUX_EFI_BGRT_H
 #define _LINUX_EFI_BGRT_H
 
-#ifdef CONFIG_ACPI_BGRT
-
 #include <linux/acpi.h>
 
-void efi_bgrt_init(void);
+#ifdef CONFIG_ACPI_BGRT
+
+void efi_bgrt_init(struct acpi_table_header *table);
 
 /* The BGRT data itself; only valid if bgrt_image != NULL. */
-extern void *bgrt_image;
 extern size_t bgrt_image_size;
-extern struct acpi_table_bgrt *bgrt_tab;
+extern struct acpi_table_bgrt bgrt_tab;
 
 #else /* !CONFIG_ACPI_BGRT */
 
-static inline void efi_bgrt_init(void) {}
+static inline void efi_bgrt_init(struct acpi_table_header *table) {}
 
 #endif /* !CONFIG_ACPI_BGRT */
 
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 5b1af30ece55..94d34e0be24f 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -509,24 +509,6 @@ typedef struct {
 	u64 query_variable_info;
 } efi_runtime_services_64_t;
 
-typedef struct {
-	efi_table_hdr_t hdr;
-	void *get_time;
-	void *set_time;
-	void *get_wakeup_time;
-	void *set_wakeup_time;
-	void *set_virtual_address_map;
-	void *convert_pointer;
-	void *get_variable;
-	void *get_next_variable;
-	void *set_variable;
-	void *get_next_high_mono_count;
-	void *reset_system;
-	void *update_capsule;
-	void *query_capsule_caps;
-	void *query_variable_info;
-} efi_runtime_services_t;
-
 typedef efi_status_t efi_get_time_t (efi_time_t *tm, efi_time_cap_t *tc);
 typedef efi_status_t efi_set_time_t (efi_time_t *tm);
 typedef efi_status_t efi_get_wakeup_time_t (efi_bool_t *enabled, efi_bool_t *pending,
@@ -561,6 +543,24 @@ typedef efi_status_t efi_query_variable_store_t(u32 attributes,
 						unsigned long size,
 						bool nonblocking);
 
+typedef struct {
+	efi_table_hdr_t			hdr;
+	efi_get_time_t			*get_time;
+	efi_set_time_t			*set_time;
+	efi_get_wakeup_time_t		*get_wakeup_time;
+	efi_set_wakeup_time_t		*set_wakeup_time;
+	efi_set_virtual_address_map_t	*set_virtual_address_map;
+	void				*convert_pointer;
+	efi_get_variable_t		*get_variable;
+	efi_get_next_variable_t		*get_next_variable;
+	efi_set_variable_t		*set_variable;
+	efi_get_next_high_mono_count_t	*get_next_high_mono_count;
+	efi_reset_system_t		*reset_system;
+	efi_update_capsule_t		*update_capsule;
+	efi_query_capsule_caps_t	*query_capsule_caps;
+	efi_query_variable_info_t	*query_variable_info;
+} efi_runtime_services_t;
+
 void efi_native_runtime_setup(void);
 
 /*
@@ -611,6 +611,9 @@ void efi_native_runtime_setup(void);
 #define EFI_CONSOLE_OUT_DEVICE_GUID		EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4,  0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
 #define APPLE_PROPERTIES_PROTOCOL_GUID		EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb,  0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0)
 
+#define EFI_IMAGE_SECURITY_DATABASE_GUID	EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596,  0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f)
+#define EFI_SHIM_LOCK_GUID			EFI_GUID(0x605dab50, 0xe046, 0x4300,  0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23)
+
 /*
  * This GUID is used to pass to the kernel proper the struct screen_info
  * structure that was populated by the stub based on the GOP protocol instance
@@ -1065,6 +1068,7 @@ extern int __init efi_setup_pcdp_console(char *);
 #define EFI_ARCH_1		7	/* First arch-specific bit */
 #define EFI_DBG			8	/* Print additional debug info at runtime */
 #define EFI_NX_PE_DATA		9	/* Can runtime data regions be mapped non-executable? */
+#define EFI_MEM_ATTR		10	/* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */
 
 #ifdef CONFIG_EFI
 /*
@@ -1240,17 +1244,17 @@ struct efivar_entry {
 	bool deleting;
 };
 
-struct efi_simple_text_output_protocol_32 {
+typedef struct {
 	u32 reset;
 	u32 output_string;
 	u32 test_string;
-};
+} efi_simple_text_output_protocol_32_t;
 
-struct efi_simple_text_output_protocol_64 {
+typedef struct {
 	u64 reset;
 	u64 output_string;
 	u64 test_string;
-};
+} efi_simple_text_output_protocol_64_t;
 
 struct efi_simple_text_output_protocol {
 	void *reset;
@@ -1476,6 +1480,14 @@ efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg,
 bool efi_runtime_disabled(void);
 extern void efi_call_virt_check_flags(unsigned long flags, const char *call);
 
+enum efi_secureboot_mode {
+	efi_secureboot_mode_unset,
+	efi_secureboot_mode_unknown,
+	efi_secureboot_mode_disabled,
+	efi_secureboot_mode_enabled,
+};
+enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table);
+
 /*
  * Arch code can implement the following three template macros, avoiding
  * reptition for the void/non-void return cases of {__,}efi_call_virt():
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index b276e9ef0e0b..aebecc4ed088 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -9,12 +9,22 @@
 struct io_cq;
 struct elevator_type;
 
-typedef int (elevator_merge_fn) (struct request_queue *, struct request **,
+/*
+ * Return values from elevator merger
+ */
+enum elv_merge {
+	ELEVATOR_NO_MERGE	= 0,
+	ELEVATOR_FRONT_MERGE	= 1,
+	ELEVATOR_BACK_MERGE	= 2,
+	ELEVATOR_DISCARD_MERGE	= 3,
+};
+
+typedef enum elv_merge (elevator_merge_fn) (struct request_queue *, struct request **,
 				 struct bio *);
 
 typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *, struct request *);
 
-typedef void (elevator_merged_fn) (struct request_queue *, struct request *, int);
+typedef void (elevator_merged_fn) (struct request_queue *, struct request *, enum elv_merge);
 
 typedef int (elevator_allow_bio_merge_fn) (struct request_queue *,
 					   struct request *, struct bio *);
@@ -77,6 +87,34 @@ struct elevator_ops
 	elevator_registered_fn *elevator_registered_fn;
 };
 
+struct blk_mq_alloc_data;
+struct blk_mq_hw_ctx;
+
+struct elevator_mq_ops {
+	int (*init_sched)(struct request_queue *, struct elevator_type *);
+	void (*exit_sched)(struct elevator_queue *);
+
+	bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
+	bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);
+	int (*request_merge)(struct request_queue *q, struct request **, struct bio *);
+	void (*request_merged)(struct request_queue *, struct request *, enum elv_merge);
+	void (*requests_merged)(struct request_queue *, struct request *, struct request *);
+	struct request *(*get_request)(struct request_queue *, unsigned int, struct blk_mq_alloc_data *);
+	void (*put_request)(struct request *);
+	void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool);
+	struct request *(*dispatch_request)(struct blk_mq_hw_ctx *);
+	bool (*has_work)(struct blk_mq_hw_ctx *);
+	void (*completed_request)(struct blk_mq_hw_ctx *, struct request *);
+	void (*started_request)(struct request *);
+	void (*requeue_request)(struct request *);
+	struct request *(*former_request)(struct request_queue *, struct request *);
+	struct request *(*next_request)(struct request_queue *, struct request *);
+	int (*get_rq_priv)(struct request_queue *, struct request *, struct bio *);
+	void (*put_rq_priv)(struct request_queue *, struct request *);
+	void (*init_icq)(struct io_cq *);
+	void (*exit_icq)(struct io_cq *);
+};
+
 #define ELV_NAME_MAX	(16)
 
 struct elv_fs_entry {
@@ -94,12 +132,16 @@ struct elevator_type
 	struct kmem_cache *icq_cache;
 
 	/* fields provided by elevator implementation */
-	struct elevator_ops ops;
+	union {
+		struct elevator_ops sq;
+		struct elevator_mq_ops mq;
+	} ops;
 	size_t icq_size;	/* see iocontext.h */
 	size_t icq_align;	/* ditto */
 	struct elv_fs_entry *elevator_attrs;
 	char elevator_name[ELV_NAME_MAX];
 	struct module *elevator_owner;
+	bool uses_mq;
 
 	/* managed by elevator core */
 	char icq_cache_name[ELV_NAME_MAX + 5];	/* elvname + "_io_cq" */
@@ -123,6 +165,7 @@ struct elevator_queue
 	struct kobject kobj;
 	struct mutex sysfs_lock;
 	unsigned int registered:1;
+	unsigned int uses_mq:1;
 	DECLARE_HASHTABLE(hash, ELV_HASH_BITS);
 };
 
@@ -133,12 +176,15 @@ extern void elv_dispatch_sort(struct request_queue *, struct request *);
 extern void elv_dispatch_add_tail(struct request_queue *, struct request *);
 extern void elv_add_request(struct request_queue *, struct request *, int);
 extern void __elv_add_request(struct request_queue *, struct request *, int);
-extern int elv_merge(struct request_queue *, struct request **, struct bio *);
+extern enum elv_merge elv_merge(struct request_queue *, struct request **,
+		struct bio *);
 extern void elv_merge_requests(struct request_queue *, struct request *,
 			       struct request *);
-extern void elv_merged_request(struct request_queue *, struct request *, int);
+extern void elv_merged_request(struct request_queue *, struct request *,
+		enum elv_merge);
 extern void elv_bio_merged(struct request_queue *q, struct request *,
 				struct bio *);
+extern bool elv_attempt_insert_merge(struct request_queue *, struct request *);
 extern void elv_requeue_request(struct request_queue *, struct request *);
 extern struct request *elv_former_request(struct request_queue *, struct request *);
 extern struct request *elv_latter_request(struct request_queue *, struct request *);
@@ -185,13 +231,6 @@ extern void elv_rb_del(struct rb_root *, struct request *);
 extern struct request *elv_rb_find(struct rb_root *, sector_t);
 
 /*
- * Return values from elevator merger
- */
-#define ELEVATOR_NO_MERGE	0
-#define ELEVATOR_FRONT_MERGE	1
-#define ELEVATOR_BACK_MERGE	2
-
-/*
  * Insertion selection
  */
 #define ELEVATOR_INSERT_FRONT	1
diff --git a/include/linux/export.h b/include/linux/export.h
index 2a0f61fbc731..1a1dfdb2a5c6 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -43,12 +43,19 @@ extern struct module __this_module;
 #ifdef CONFIG_MODVERSIONS
 /* Mark the CRC weak since genksyms apparently decides not to
  * generate a checksums for some symbols */
+#if defined(CONFIG_MODULE_REL_CRCS)
 #define __CRC_SYMBOL(sym, sec)						\
-	extern __visible void *__crc_##sym __attribute__((weak));	\
-	static const unsigned long __kcrctab_##sym			\
-	__used								\
-	__attribute__((section("___kcrctab" sec "+" #sym), used))	\
-	= (unsigned long) &__crc_##sym;
+	asm("	.section \"___kcrctab" sec "+" #sym "\", \"a\"	\n"	\
+	    "	.weak	" VMLINUX_SYMBOL_STR(__crc_##sym) "	\n"	\
+	    "	.long	" VMLINUX_SYMBOL_STR(__crc_##sym) " - .	\n"	\
+	    "	.previous					\n");
+#else
+#define __CRC_SYMBOL(sym, sec)						\
+	asm("	.section \"___kcrctab" sec "+" #sym "\", \"a\"	\n"	\
+	    "	.weak	" VMLINUX_SYMBOL_STR(__crc_##sym) "	\n"	\
+	    "	.long	" VMLINUX_SYMBOL_STR(__crc_##sym) "	\n"	\
+	    "	.previous					\n");
+#endif
 #else
 #define __CRC_SYMBOL(sym, sec)
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2ba074328894..c930cbc19342 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -423,6 +423,7 @@ struct block_device {
 	int			bd_invalidated;
 	struct gendisk *	bd_disk;
 	struct request_queue *  bd_queue;
+	struct backing_dev_info *bd_bdi;
 	struct list_head	bd_list;
 	/*
 	 * Private data.  You must have bd_claim'ed the block_device
@@ -2342,6 +2343,7 @@ extern struct kmem_cache *names_cachep;
 #ifdef CONFIG_BLOCK
 extern int register_blkdev(unsigned int, const char *);
 extern void unregister_blkdev(unsigned int, const char *);
+extern void bdev_unhash_inode(dev_t dev);
 extern struct block_device *bdget(dev_t);
 extern struct block_device *bdgrab(struct block_device *bdev);
 extern void bd_set_size(struct block_device *, loff_t size);
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index 13ba552e6c09..4c467ef50159 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -360,6 +360,7 @@ struct fscache_object {
 #define FSCACHE_OBJECT_IS_AVAILABLE	5	/* T if object has become active */
 #define FSCACHE_OBJECT_RETIRED		6	/* T if object was retired on relinquishment */
 #define FSCACHE_OBJECT_KILLED_BY_CACHE	7	/* T if object was killed by the cache */
+#define FSCACHE_OBJECT_RUN_AFTER_DEAD	8	/* T if object has been dispatched after death */
 
 	struct list_head	cache_link;	/* link in cache->object_list */
 	struct hlist_node	cookie_link;	/* link in cookie->backing_objects */
diff --git a/include/linux/fscrypt_common.h b/include/linux/fscrypt_common.h
new file mode 100644
index 000000000000..547f81592ba1
--- /dev/null
+++ b/include/linux/fscrypt_common.h
@@ -0,0 +1,146 @@
+/*
+ * fscrypt_common.h: common declarations for per-file encryption
+ *
+ * Copyright (C) 2015, Google, Inc.
+ *
+ * Written by Michael Halcrow, 2015.
+ * Modified by Jaegeuk Kim, 2015.
+ */
+
+#ifndef _LINUX_FSCRYPT_COMMON_H
+#define _LINUX_FSCRYPT_COMMON_H
+
+#include <linux/key.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/bio.h>
+#include <linux/dcache.h>
+#include <crypto/skcipher.h>
+#include <uapi/linux/fs.h>
+
+#define FS_CRYPTO_BLOCK_SIZE		16
+
+struct fscrypt_info;
+
+struct fscrypt_ctx {
+	union {
+		struct {
+			struct page *bounce_page;	/* Ciphertext page */
+			struct page *control_page;	/* Original page  */
+		} w;
+		struct {
+			struct bio *bio;
+			struct work_struct work;
+		} r;
+		struct list_head free_list;	/* Free list */
+	};
+	u8 flags;				/* Flags */
+};
+
+/**
+ * For encrypted symlinks, the ciphertext length is stored at the beginning
+ * of the string in little-endian format.
+ */
+struct fscrypt_symlink_data {
+	__le16 len;
+	char encrypted_path[1];
+} __packed;
+
+/**
+ * This function is used to calculate the disk space required to
+ * store a filename of length l in encrypted symlink format.
+ */
+static inline u32 fscrypt_symlink_data_len(u32 l)
+{
+	if (l < FS_CRYPTO_BLOCK_SIZE)
+		l = FS_CRYPTO_BLOCK_SIZE;
+	return (l + sizeof(struct fscrypt_symlink_data) - 1);
+}
+
+struct fscrypt_str {
+	unsigned char *name;
+	u32 len;
+};
+
+struct fscrypt_name {
+	const struct qstr *usr_fname;
+	struct fscrypt_str disk_name;
+	u32 hash;
+	u32 minor_hash;
+	struct fscrypt_str crypto_buf;
+};
+
+#define FSTR_INIT(n, l)		{ .name = n, .len = l }
+#define FSTR_TO_QSTR(f)		QSTR_INIT((f)->name, (f)->len)
+#define fname_name(p)		((p)->disk_name.name)
+#define fname_len(p)		((p)->disk_name.len)
+
+/*
+ * fscrypt superblock flags
+ */
+#define FS_CFLG_OWN_PAGES (1U << 1)
+
+/*
+ * crypto opertions for filesystems
+ */
+struct fscrypt_operations {
+	unsigned int flags;
+	const char *key_prefix;
+	int (*get_context)(struct inode *, void *, size_t);
+	int (*prepare_context)(struct inode *);
+	int (*set_context)(struct inode *, const void *, size_t, void *);
+	int (*dummy_context)(struct inode *);
+	bool (*is_encrypted)(struct inode *);
+	bool (*empty_dir)(struct inode *);
+	unsigned (*max_namelen)(struct inode *);
+};
+
+static inline bool fscrypt_dummy_context_enabled(struct inode *inode)
+{
+	if (inode->i_sb->s_cop->dummy_context &&
+				inode->i_sb->s_cop->dummy_context(inode))
+		return true;
+	return false;
+}
+
+static inline bool fscrypt_valid_contents_enc_mode(u32 mode)
+{
+	return (mode == FS_ENCRYPTION_MODE_AES_256_XTS);
+}
+
+static inline bool fscrypt_valid_filenames_enc_mode(u32 mode)
+{
+	return (mode == FS_ENCRYPTION_MODE_AES_256_CTS);
+}
+
+static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
+{
+	if (str->len == 1 && str->name[0] == '.')
+		return true;
+
+	if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
+		return true;
+
+	return false;
+}
+
+static inline struct page *fscrypt_control_page(struct page *page)
+{
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	return ((struct fscrypt_ctx *)page_private(page))->w.control_page;
+#else
+	WARN_ON_ONCE(1);
+	return ERR_PTR(-EINVAL);
+#endif
+}
+
+static inline int fscrypt_has_encryption_key(const struct inode *inode)
+{
+#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
+	return (inode->i_crypt_info != NULL);
+#else
+	return 0;
+#endif
+}
+
+#endif	/* _LINUX_FSCRYPT_COMMON_H */
diff --git a/include/linux/fscrypt_notsupp.h b/include/linux/fscrypt_notsupp.h
new file mode 100644
index 000000000000..3511ca798804
--- /dev/null
+++ b/include/linux/fscrypt_notsupp.h
@@ -0,0 +1,168 @@
+/*
+ * fscrypt_notsupp.h
+ *
+ * This stubs out the fscrypt functions for filesystems configured without
+ * encryption support.
+ */
+
+#ifndef _LINUX_FSCRYPT_NOTSUPP_H
+#define _LINUX_FSCRYPT_NOTSUPP_H
+
+#include <linux/fscrypt_common.h>
+
+/* crypto.c */
+static inline struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *inode,
+						  gfp_t gfp_flags)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx)
+{
+	return;
+}
+
+static inline struct page *fscrypt_encrypt_page(const struct inode *inode,
+						struct page *page,
+						unsigned int len,
+						unsigned int offs,
+						u64 lblk_num, gfp_t gfp_flags)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline int fscrypt_decrypt_page(const struct inode *inode,
+				       struct page *page,
+				       unsigned int len, unsigned int offs,
+				       u64 lblk_num)
+{
+	return -EOPNOTSUPP;
+}
+
+
+static inline void fscrypt_restore_control_page(struct page *page)
+{
+	return;
+}
+
+static inline void fscrypt_set_d_op(struct dentry *dentry)
+{
+	return;
+}
+
+static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
+{
+	return;
+}
+
+/* policy.c */
+static inline int fscrypt_ioctl_set_policy(struct file *filp,
+					   const void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_has_permitted_context(struct inode *parent,
+						struct inode *child)
+{
+	return 0;
+}
+
+static inline int fscrypt_inherit_context(struct inode *parent,
+					  struct inode *child,
+					  void *fs_data, bool preload)
+{
+	return -EOPNOTSUPP;
+}
+
+/* keyinfo.c */
+static inline int fscrypt_get_encryption_info(struct inode *inode)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_put_encryption_info(struct inode *inode,
+					       struct fscrypt_info *ci)
+{
+	return;
+}
+
+ /* fname.c */
+static inline int fscrypt_setup_filename(struct inode *dir,
+					 const struct qstr *iname,
+					 int lookup, struct fscrypt_name *fname)
+{
+	if (dir->i_sb->s_cop->is_encrypted(dir))
+		return -EOPNOTSUPP;
+
+	memset(fname, 0, sizeof(struct fscrypt_name));
+	fname->usr_fname = iname;
+	fname->disk_name.name = (unsigned char *)iname->name;
+	fname->disk_name.len = iname->len;
+	return 0;
+}
+
+static inline void fscrypt_free_filename(struct fscrypt_name *fname)
+{
+	return;
+}
+
+static inline u32 fscrypt_fname_encrypted_size(const struct inode *inode,
+					       u32 ilen)
+{
+	/* never happens */
+	WARN_ON(1);
+	return 0;
+}
+
+static inline int fscrypt_fname_alloc_buffer(const struct inode *inode,
+					     u32 ilen,
+					     struct fscrypt_str *crypto_str)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str)
+{
+	return;
+}
+
+static inline int fscrypt_fname_disk_to_usr(struct inode *inode,
+					    u32 hash, u32 minor_hash,
+					    const struct fscrypt_str *iname,
+					    struct fscrypt_str *oname)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int fscrypt_fname_usr_to_disk(struct inode *inode,
+					    const struct qstr *iname,
+					    struct fscrypt_str *oname)
+{
+	return -EOPNOTSUPP;
+}
+
+/* bio.c */
+static inline void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx,
+					     struct bio *bio)
+{
+	return;
+}
+
+static inline void fscrypt_pullback_bio_page(struct page **page, bool restore)
+{
+	return;
+}
+
+static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
+					sector_t pblk, unsigned int len)
+{
+	return -EOPNOTSUPP;
+}
+
+#endif	/* _LINUX_FSCRYPT_NOTSUPP_H */
diff --git a/include/linux/fscrypt_supp.h b/include/linux/fscrypt_supp.h
new file mode 100644
index 000000000000..a140f47e9b27
--- /dev/null
+++ b/include/linux/fscrypt_supp.h
@@ -0,0 +1,66 @@
+/*
+ * fscrypt_supp.h
+ *
+ * This is included by filesystems configured with encryption support.
+ */
+
+#ifndef _LINUX_FSCRYPT_SUPP_H
+#define _LINUX_FSCRYPT_SUPP_H
+
+#include <linux/fscrypt_common.h>
+
+/* crypto.c */
+extern struct kmem_cache *fscrypt_info_cachep;
+extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t);
+extern void fscrypt_release_ctx(struct fscrypt_ctx *);
+extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *,
+						unsigned int, unsigned int,
+						u64, gfp_t);
+extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int,
+				unsigned int, u64);
+extern void fscrypt_restore_control_page(struct page *);
+
+extern const struct dentry_operations fscrypt_d_ops;
+
+static inline void fscrypt_set_d_op(struct dentry *dentry)
+{
+	d_set_d_op(dentry, &fscrypt_d_ops);
+}
+
+static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
+	spin_unlock(&dentry->d_lock);
+}
+
+/* policy.c */
+extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
+extern int fscrypt_ioctl_get_policy(struct file *, void __user *);
+extern int fscrypt_has_permitted_context(struct inode *, struct inode *);
+extern int fscrypt_inherit_context(struct inode *, struct inode *,
+					void *, bool);
+/* keyinfo.c */
+extern int fscrypt_get_encryption_info(struct inode *);
+extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *);
+
+/* fname.c */
+extern int fscrypt_setup_filename(struct inode *, const struct qstr *,
+				int lookup, struct fscrypt_name *);
+extern void fscrypt_free_filename(struct fscrypt_name *);
+extern u32 fscrypt_fname_encrypted_size(const struct inode *, u32);
+extern int fscrypt_fname_alloc_buffer(const struct inode *, u32,
+				struct fscrypt_str *);
+extern void fscrypt_fname_free_buffer(struct fscrypt_str *);
+extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32,
+			const struct fscrypt_str *, struct fscrypt_str *);
+extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *,
+			struct fscrypt_str *);
+
+/* bio.c */
+extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *);
+extern void fscrypt_pullback_bio_page(struct page **, bool);
+extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t,
+				 unsigned int);
+
+#endif	/* _LINUX_FSCRYPT_SUPP_H */
diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h
deleted file mode 100644
index c074b670aa99..000000000000
--- a/include/linux/fscrypto.h
+++ /dev/null
@@ -1,345 +0,0 @@
-/*
- * General per-file encryption definition
- *
- * Copyright (C) 2015, Google, Inc.
- *
- * Written by Michael Halcrow, 2015.
- * Modified by Jaegeuk Kim, 2015.
- */
-
-#ifndef _LINUX_FSCRYPTO_H
-#define _LINUX_FSCRYPTO_H
-
-#include <linux/key.h>
-#include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/bio.h>
-#include <linux/dcache.h>
-#include <crypto/skcipher.h>
-#include <uapi/linux/fs.h>
-
-#define FS_CRYPTO_BLOCK_SIZE		16
-
-struct fscrypt_info;
-
-struct fscrypt_ctx {
-	union {
-		struct {
-			struct page *bounce_page;	/* Ciphertext page */
-			struct page *control_page;	/* Original page  */
-		} w;
-		struct {
-			struct bio *bio;
-			struct work_struct work;
-		} r;
-		struct list_head free_list;	/* Free list */
-	};
-	u8 flags;				/* Flags */
-	u8 mode;				/* Encryption mode for tfm */
-};
-
-/**
- * For encrypted symlinks, the ciphertext length is stored at the beginning
- * of the string in little-endian format.
- */
-struct fscrypt_symlink_data {
-	__le16 len;
-	char encrypted_path[1];
-} __packed;
-
-/**
- * This function is used to calculate the disk space required to
- * store a filename of length l in encrypted symlink format.
- */
-static inline u32 fscrypt_symlink_data_len(u32 l)
-{
-	if (l < FS_CRYPTO_BLOCK_SIZE)
-		l = FS_CRYPTO_BLOCK_SIZE;
-	return (l + sizeof(struct fscrypt_symlink_data) - 1);
-}
-
-struct fscrypt_str {
-	unsigned char *name;
-	u32 len;
-};
-
-struct fscrypt_name {
-	const struct qstr *usr_fname;
-	struct fscrypt_str disk_name;
-	u32 hash;
-	u32 minor_hash;
-	struct fscrypt_str crypto_buf;
-};
-
-#define FSTR_INIT(n, l)		{ .name = n, .len = l }
-#define FSTR_TO_QSTR(f)		QSTR_INIT((f)->name, (f)->len)
-#define fname_name(p)		((p)->disk_name.name)
-#define fname_len(p)		((p)->disk_name.len)
-
-/*
- * fscrypt superblock flags
- */
-#define FS_CFLG_OWN_PAGES (1U << 1)
-
-/*
- * crypto opertions for filesystems
- */
-struct fscrypt_operations {
-	unsigned int flags;
-	int (*get_context)(struct inode *, void *, size_t);
-	int (*key_prefix)(struct inode *, u8 **);
-	int (*prepare_context)(struct inode *);
-	int (*set_context)(struct inode *, const void *, size_t, void *);
-	int (*dummy_context)(struct inode *);
-	bool (*is_encrypted)(struct inode *);
-	bool (*empty_dir)(struct inode *);
-	unsigned (*max_namelen)(struct inode *);
-};
-
-static inline bool fscrypt_dummy_context_enabled(struct inode *inode)
-{
-	if (inode->i_sb->s_cop->dummy_context &&
-				inode->i_sb->s_cop->dummy_context(inode))
-		return true;
-	return false;
-}
-
-static inline bool fscrypt_valid_contents_enc_mode(u32 mode)
-{
-	return (mode == FS_ENCRYPTION_MODE_AES_256_XTS);
-}
-
-static inline bool fscrypt_valid_filenames_enc_mode(u32 mode)
-{
-	return (mode == FS_ENCRYPTION_MODE_AES_256_CTS);
-}
-
-static inline bool fscrypt_is_dot_dotdot(const struct qstr *str)
-{
-	if (str->len == 1 && str->name[0] == '.')
-		return true;
-
-	if (str->len == 2 && str->name[0] == '.' && str->name[1] == '.')
-		return true;
-
-	return false;
-}
-
-static inline struct page *fscrypt_control_page(struct page *page)
-{
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-	return ((struct fscrypt_ctx *)page_private(page))->w.control_page;
-#else
-	WARN_ON_ONCE(1);
-	return ERR_PTR(-EINVAL);
-#endif
-}
-
-static inline int fscrypt_has_encryption_key(const struct inode *inode)
-{
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-	return (inode->i_crypt_info != NULL);
-#else
-	return 0;
-#endif
-}
-
-static inline void fscrypt_set_encrypted_dentry(struct dentry *dentry)
-{
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-	spin_lock(&dentry->d_lock);
-	dentry->d_flags |= DCACHE_ENCRYPTED_WITH_KEY;
-	spin_unlock(&dentry->d_lock);
-#endif
-}
-
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-extern const struct dentry_operations fscrypt_d_ops;
-#endif
-
-static inline void fscrypt_set_d_op(struct dentry *dentry)
-{
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-	d_set_d_op(dentry, &fscrypt_d_ops);
-#endif
-}
-
-#if IS_ENABLED(CONFIG_FS_ENCRYPTION)
-/* crypto.c */
-extern struct kmem_cache *fscrypt_info_cachep;
-extern struct fscrypt_ctx *fscrypt_get_ctx(const struct inode *, gfp_t);
-extern void fscrypt_release_ctx(struct fscrypt_ctx *);
-extern struct page *fscrypt_encrypt_page(const struct inode *, struct page *,
-						unsigned int, unsigned int,
-						u64, gfp_t);
-extern int fscrypt_decrypt_page(const struct inode *, struct page *, unsigned int,
-				unsigned int, u64);
-extern void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *, struct bio *);
-extern void fscrypt_pullback_bio_page(struct page **, bool);
-extern void fscrypt_restore_control_page(struct page *);
-extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t,
-						unsigned int);
-/* policy.c */
-extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
-extern int fscrypt_ioctl_get_policy(struct file *, void __user *);
-extern int fscrypt_has_permitted_context(struct inode *, struct inode *);
-extern int fscrypt_inherit_context(struct inode *, struct inode *,
-					void *, bool);
-/* keyinfo.c */
-extern int fscrypt_get_encryption_info(struct inode *);
-extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *);
-
-/* fname.c */
-extern int fscrypt_setup_filename(struct inode *, const struct qstr *,
-				int lookup, struct fscrypt_name *);
-extern void fscrypt_free_filename(struct fscrypt_name *);
-extern u32 fscrypt_fname_encrypted_size(const struct inode *, u32);
-extern int fscrypt_fname_alloc_buffer(const struct inode *, u32,
-				struct fscrypt_str *);
-extern void fscrypt_fname_free_buffer(struct fscrypt_str *);
-extern int fscrypt_fname_disk_to_usr(struct inode *, u32, u32,
-			const struct fscrypt_str *, struct fscrypt_str *);
-extern int fscrypt_fname_usr_to_disk(struct inode *, const struct qstr *,
-			struct fscrypt_str *);
-#endif
-
-/* crypto.c */
-static inline struct fscrypt_ctx *fscrypt_notsupp_get_ctx(const struct inode *i,
-							gfp_t f)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
-static inline void fscrypt_notsupp_release_ctx(struct fscrypt_ctx *c)
-{
-	return;
-}
-
-static inline struct page *fscrypt_notsupp_encrypt_page(const struct inode *i,
-						struct page *p,
-						unsigned int len,
-						unsigned int offs,
-						u64 lblk_num, gfp_t f)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
-static inline int fscrypt_notsupp_decrypt_page(const struct inode *i, struct page *p,
-						unsigned int len, unsigned int offs,
-						u64 lblk_num)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline void fscrypt_notsupp_decrypt_bio_pages(struct fscrypt_ctx *c,
-						struct bio *b)
-{
-	return;
-}
-
-static inline void fscrypt_notsupp_pullback_bio_page(struct page **p, bool b)
-{
-	return;
-}
-
-static inline void fscrypt_notsupp_restore_control_page(struct page *p)
-{
-	return;
-}
-
-static inline int fscrypt_notsupp_zeroout_range(const struct inode *i, pgoff_t p,
-					sector_t s, unsigned int f)
-{
-	return -EOPNOTSUPP;
-}
-
-/* policy.c */
-static inline int fscrypt_notsupp_ioctl_set_policy(struct file *f,
-				const void __user *arg)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int fscrypt_notsupp_ioctl_get_policy(struct file *f,
-				void __user *arg)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int fscrypt_notsupp_has_permitted_context(struct inode *p,
-				struct inode *i)
-{
-	return 0;
-}
-
-static inline int fscrypt_notsupp_inherit_context(struct inode *p,
-				struct inode *i, void *v, bool b)
-{
-	return -EOPNOTSUPP;
-}
-
-/* keyinfo.c */
-static inline int fscrypt_notsupp_get_encryption_info(struct inode *i)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline void fscrypt_notsupp_put_encryption_info(struct inode *i,
-					struct fscrypt_info *f)
-{
-	return;
-}
-
- /* fname.c */
-static inline int fscrypt_notsupp_setup_filename(struct inode *dir,
-			const struct qstr *iname,
-			int lookup, struct fscrypt_name *fname)
-{
-	if (dir->i_sb->s_cop->is_encrypted(dir))
-		return -EOPNOTSUPP;
-
-	memset(fname, 0, sizeof(struct fscrypt_name));
-	fname->usr_fname = iname;
-	fname->disk_name.name = (unsigned char *)iname->name;
-	fname->disk_name.len = iname->len;
-	return 0;
-}
-
-static inline void fscrypt_notsupp_free_filename(struct fscrypt_name *fname)
-{
-	return;
-}
-
-static inline u32 fscrypt_notsupp_fname_encrypted_size(struct inode *i, u32 s)
-{
-	/* never happens */
-	WARN_ON(1);
-	return 0;
-}
-
-static inline int fscrypt_notsupp_fname_alloc_buffer(struct inode *inode,
-				u32 ilen, struct fscrypt_str *crypto_str)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline void fscrypt_notsupp_fname_free_buffer(struct fscrypt_str *c)
-{
-	return;
-}
-
-static inline int fscrypt_notsupp_fname_disk_to_usr(struct inode *inode,
-			u32 hash, u32 minor_hash,
-			const struct fscrypt_str *iname,
-			struct fscrypt_str *oname)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int fscrypt_notsupp_fname_usr_to_disk(struct inode *inode,
-			const struct qstr *iname,
-			struct fscrypt_str *oname)
-{
-	return -EOPNOTSUPP;
-}
-#endif	/* _LINUX_FSCRYPTO_H */
diff --git a/include/linux/fsl_ifc.h b/include/linux/fsl_ifc.h
index 3f9778cbc79d..c332f0a45607 100644
--- a/include/linux/fsl_ifc.h
+++ b/include/linux/fsl_ifc.h
@@ -733,8 +733,12 @@ struct fsl_ifc_nand {
 	__be32 nand_erattr1;
 	u32 res19[0x10];
 	__be32 nand_fsr;
-	u32 res20[0x3];
-	__be32 nand_eccstat[6];
+	u32 res20;
+	/* The V1 nand_eccstat is actually 4 words that overlaps the
+	 * V2 nand_eccstat.
+	 */
+	__be32 v1_nand_eccstat[2];
+	__be32 v2_nand_eccstat[6];
 	u32 res21[0x1c];
 	__be32 nanndcr;
 	u32 res22[0x2];
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 76f39754e7b0..a999d281a2f1 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -167,6 +167,13 @@ struct blk_integrity {
 };
 
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
+struct disk_devt {
+	atomic_t count;
+	void (*release)(struct disk_devt *disk_devt);
+};
+
+void put_disk_devt(struct disk_devt *disk_devt);
+void get_disk_devt(struct disk_devt *disk_devt);
 
 struct gendisk {
 	/* major, first_minor and minors are input parameters only,
@@ -176,6 +183,7 @@ struct gendisk {
 	int first_minor;
 	int minors;                     /* maximum number of minors, =1 for
                                          * disks that can't be partitioned. */
+	struct disk_devt *disk_devt;
 
 	char disk_name[DISK_NAME_LEN];	/* name of major driver */
 	char *(*devnode)(struct gendisk *gd, umode_t *mode);
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index c2748accea71..e973faba69dc 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -274,37 +274,67 @@ void gpiochip_set_nested_irqchip(struct gpio_chip *gpiochip,
 		struct irq_chip *irqchip,
 		int parent_irq);
 
-int _gpiochip_irqchip_add(struct gpio_chip *gpiochip,
+int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip,
+			     struct irq_chip *irqchip,
+			     unsigned int first_irq,
+			     irq_flow_handler_t handler,
+			     unsigned int type,
+			     bool nested,
+			     struct lock_class_key *lock_key);
+
+#ifdef CONFIG_LOCKDEP
+
+/*
+ * Lockdep requires that each irqchip instance be created with a
+ * unique key so as to avoid unnecessary warnings. This upfront
+ * boilerplate static inlines provides such a key for each
+ * unique instance.
+ */
+static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
+				       struct irq_chip *irqchip,
+				       unsigned int first_irq,
+				       irq_flow_handler_t handler,
+				       unsigned int type)
+{
+	static struct lock_class_key key;
+
+	return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq,
+					handler, type, false, &key);
+}
+
+static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip,
 			  struct irq_chip *irqchip,
 			  unsigned int first_irq,
 			  irq_flow_handler_t handler,
-			  unsigned int type,
-			  bool nested,
-			  struct lock_class_key *lock_key);
+			  unsigned int type)
+{
+
+	static struct lock_class_key key;
+
+	return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq,
+					handler, type, true, &key);
+}
+#else
+static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip,
+				       struct irq_chip *irqchip,
+				       unsigned int first_irq,
+				       irq_flow_handler_t handler,
+				       unsigned int type)
+{
+	return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq,
+					handler, type, false, NULL);
+}
 
-/* FIXME: I assume threaded IRQchips do not have the lockdep problem */
 static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip,
 			  struct irq_chip *irqchip,
 			  unsigned int first_irq,
 			  irq_flow_handler_t handler,
 			  unsigned int type)
 {
-	return _gpiochip_irqchip_add(gpiochip, irqchip, first_irq,
-				     handler, type, true, NULL);
+	return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq,
+					handler, type, true, NULL);
 }
-
-#ifdef CONFIG_LOCKDEP
-#define gpiochip_irqchip_add(...)				\
-(								\
-	({							\
-		static struct lock_class_key _key;		\
-		_gpiochip_irqchip_add(__VA_ARGS__, false, &_key); \
-	})							\
-)
-#else
-#define gpiochip_irqchip_add(...)				\
-	_gpiochip_irqchip_add(__VA_ARGS__, false, NULL)
-#endif
+#endif /* CONFIG_LOCKDEP */
 
 #endif /* CONFIG_GPIOLIB_IRQCHIP */
 
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index cdab81ba29f8..e52b427223ba 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -88,12 +88,6 @@ enum hrtimer_restart {
  * @base:	pointer to the timer base (per cpu and per clock)
  * @state:	state information (See bit values above)
  * @is_rel:	Set if the timer was armed relative
- * @start_pid:  timer statistics field to store the pid of the task which
- *		started the timer
- * @start_site:	timer statistics field to store the site where the timer
- *		was started
- * @start_comm: timer statistics field to store the name of the process which
- *		started the timer
  *
  * The hrtimer structure must be initialized by hrtimer_init()
  */
@@ -104,11 +98,6 @@ struct hrtimer {
 	struct hrtimer_clock_base	*base;
 	u8				state;
 	u8				is_rel;
-#ifdef CONFIG_TIMER_STATS
-	int				start_pid;
-	void				*start_site;
-	char				start_comm[16];
-#endif
 };
 
 /**
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 42fe43fb0c80..183efde54269 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -128,6 +128,7 @@ struct hv_ring_buffer_info {
 	u32 ring_data_startoffset;
 	u32 priv_write_index;
 	u32 priv_read_index;
+	u32 cached_read_index;
 };
 
 /*
@@ -180,6 +181,19 @@ static inline u32 hv_get_bytes_to_write(struct hv_ring_buffer_info *rbi)
 	return write;
 }
 
+static inline u32 hv_get_cached_bytes_to_write(
+	const struct hv_ring_buffer_info *rbi)
+{
+	u32 read_loc, write_loc, dsize, write;
+
+	dsize = rbi->ring_datasize;
+	read_loc = rbi->cached_read_index;
+	write_loc = rbi->ring_buffer->write_index;
+
+	write = write_loc >= read_loc ? dsize - (write_loc - read_loc) :
+		read_loc - write_loc;
+	return write;
+}
 /*
  * VMBUS version is 32 bit entity broken up into
  * two 16 bit quantities: major_number. minor_number.
@@ -1488,7 +1502,7 @@ hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info)
 
 static inline  void hv_signal_on_read(struct vmbus_channel *channel)
 {
-	u32 cur_write_sz;
+	u32 cur_write_sz, cached_write_sz;
 	u32 pending_sz;
 	struct hv_ring_buffer_info *rbi = &channel->inbound;
 
@@ -1512,12 +1526,24 @@ static inline  void hv_signal_on_read(struct vmbus_channel *channel)
 
 	cur_write_sz = hv_get_bytes_to_write(rbi);
 
-	if (cur_write_sz >= pending_sz)
+	if (cur_write_sz < pending_sz)
+		return;
+
+	cached_write_sz = hv_get_cached_bytes_to_write(rbi);
+	if (cached_write_sz < pending_sz)
 		vmbus_setevent(channel);
 
 	return;
 }
 
+static inline void
+init_cached_read_index(struct vmbus_channel *channel)
+{
+	struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+	rbi->cached_read_index = rbi->ring_buffer->read_index;
+}
+
 /*
  * An API to support in-place processing of incoming VMBUS packets.
  */
@@ -1569,6 +1595,8 @@ static inline void put_pkt_raw(struct vmbus_channel *channel,
  * This call commits the read index and potentially signals the host.
  * Here is the pattern for using the "in-place" consumption APIs:
  *
+ * init_cached_read_index();
+ *
  * while (get_next_pkt_raw() {
  *	process the packet "in-place";
  *	put_pkt_raw();
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 4b45ec46161f..7b23a3316dcb 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -51,6 +51,7 @@ enum i2c_slave_event;
 typedef int (*i2c_slave_cb_t)(struct i2c_client *, enum i2c_slave_event, u8 *);
 
 struct module;
+struct property_entry;
 
 #if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE)
 /*
@@ -299,6 +300,7 @@ static inline int i2c_slave_event(struct i2c_client *client,
  * @archdata: copied into i2c_client.dev.archdata
  * @of_node: pointer to OpenFirmware device node
  * @fwnode: device node supplied by the platform firmware
+ * @properties: additional device properties for the device
  * @irq: stored in i2c_client.irq
  *
  * I2C doesn't actually support hardware probing, although controllers and
@@ -320,6 +322,7 @@ struct i2c_board_info {
 	struct dev_archdata	*archdata;
 	struct device_node *of_node;
 	struct fwnode_handle *fwnode;
+	const struct property_entry *properties;
 	int		irq;
 };
 
diff --git a/include/linux/ide.h b/include/linux/ide.h
index a633898f36ac..2f51c1724b5a 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -20,6 +20,7 @@
 #include <linux/mutex.h>
 /* for request_sense */
 #include <linux/cdrom.h>
+#include <scsi/scsi_cmnd.h>
 #include <asm/byteorder.h>
 #include <asm/io.h>
 
@@ -39,18 +40,53 @@
 
 struct device;
 
-/* IDE-specific values for req->cmd_type */
-enum ata_cmd_type_bits {
-	REQ_TYPE_ATA_TASKFILE = REQ_TYPE_DRV_PRIV + 1,
-	REQ_TYPE_ATA_PC,
-	REQ_TYPE_ATA_SENSE,	/* sense request */
-	REQ_TYPE_ATA_PM_SUSPEND,/* suspend request */
-	REQ_TYPE_ATA_PM_RESUME,	/* resume request */
+/* values for ide_request.type */
+enum ata_priv_type {
+	ATA_PRIV_MISC,
+	ATA_PRIV_TASKFILE,
+	ATA_PRIV_PC,
+	ATA_PRIV_SENSE,		/* sense request */
+	ATA_PRIV_PM_SUSPEND,	/* suspend request */
+	ATA_PRIV_PM_RESUME,	/* resume request */
 };
 
-#define ata_pm_request(rq)	\
-	((rq)->cmd_type == REQ_TYPE_ATA_PM_SUSPEND || \
-	 (rq)->cmd_type == REQ_TYPE_ATA_PM_RESUME)
+struct ide_request {
+	struct scsi_request sreq;
+	u8 sense[SCSI_SENSE_BUFFERSIZE];
+	u8 type;
+};
+
+static inline struct ide_request *ide_req(struct request *rq)
+{
+	return blk_mq_rq_to_pdu(rq);
+}
+
+static inline bool ata_misc_request(struct request *rq)
+{
+	return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_MISC;
+}
+
+static inline bool ata_taskfile_request(struct request *rq)
+{
+	return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_TASKFILE;
+}
+
+static inline bool ata_pc_request(struct request *rq)
+{
+	return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_PC;
+}
+
+static inline bool ata_sense_request(struct request *rq)
+{
+	return blk_rq_is_private(rq) && ide_req(rq)->type == ATA_PRIV_SENSE;
+}
+
+static inline bool ata_pm_request(struct request *rq)
+{
+	return blk_rq_is_private(rq) &&
+		(ide_req(rq)->type == ATA_PRIV_PM_SUSPEND ||
+		 ide_req(rq)->type == ATA_PRIV_PM_RESUME);
+}
 
 /* Error codes returned in rq->errors to the higher part of the driver. */
 enum {
@@ -579,7 +615,7 @@ struct ide_drive_s {
 
 	/* current sense rq and buffer */
 	bool sense_rq_armed;
-	struct request sense_rq;
+	struct request *sense_rq;
 	struct request_sense sense_data;
 };
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 325f649d77ff..3a85d61f7614 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -42,6 +42,27 @@ extern struct fs_struct init_fs;
 #define INIT_PREV_CPUTIME(x)
 #endif
 
+#ifdef CONFIG_POSIX_TIMERS
+#define INIT_POSIX_TIMERS(s)						\
+	.posix_timers = LIST_HEAD_INIT(s.posix_timers),
+#define INIT_CPU_TIMERS(s)						\
+	.cpu_timers = {							\
+		LIST_HEAD_INIT(s.cpu_timers[0]),			\
+		LIST_HEAD_INIT(s.cpu_timers[1]),			\
+		LIST_HEAD_INIT(s.cpu_timers[2]),								\
+	},
+#define INIT_CPUTIMER(s)						\
+	.cputimer	= { 						\
+		.cputime_atomic	= INIT_CPUTIME_ATOMIC,			\
+		.running	= false,				\
+		.checking_timer = false,				\
+	},
+#else
+#define INIT_POSIX_TIMERS(s)
+#define INIT_CPU_TIMERS(s)
+#define INIT_CPUTIMER(s)
+#endif
+
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
 	.thread_head	= LIST_HEAD_INIT(init_task.thread_node),	\
@@ -49,14 +70,10 @@ extern struct fs_struct init_fs;
 	.shared_pending	= { 						\
 		.list = LIST_HEAD_INIT(sig.shared_pending.list),	\
 		.signal =  {{0}}},					\
-	.posix_timers	 = LIST_HEAD_INIT(sig.posix_timers),		\
-	.cpu_timers	= INIT_CPU_TIMERS(sig.cpu_timers),		\
+	INIT_POSIX_TIMERS(sig)						\
+	INIT_CPU_TIMERS(sig)						\
 	.rlim		= INIT_RLIMITS,					\
-	.cputimer	= { 						\
-		.cputime_atomic	= INIT_CPUTIME_ATOMIC,			\
-		.running	= false,				\
-		.checking_timer = false,				\
-	},								\
+	INIT_CPUTIMER(sig)						\
 	INIT_PREV_CPUTIME(sig)						\
 	.cred_guard_mutex =						\
 		 __MUTEX_INITIALIZER(sig.cred_guard_mutex),		\
@@ -247,7 +264,7 @@ extern struct task_group root_task_group;
 	.blocked	= {{0}},					\
 	.alloc_lock	= __SPIN_LOCK_UNLOCKED(tsk.alloc_lock),		\
 	.journal_info	= NULL,						\
-	.cpu_timers	= INIT_CPU_TIMERS(tsk.cpu_timers),		\
+	INIT_CPU_TIMERS(tsk)						\
 	.pi_lock	= __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock),	\
 	.timer_slack_ns = 50000, /* 50 usec default slack */		\
 	.pids = {							\
@@ -274,13 +291,6 @@ extern struct task_group root_task_group;
 }
 
 
-#define INIT_CPU_TIMERS(cpu_timers)					\
-{									\
-	LIST_HEAD_INIT(cpu_timers[0]),					\
-	LIST_HEAD_INIT(cpu_timers[1]),					\
-	LIST_HEAD_INIT(cpu_timers[2]),					\
-}
-
 /* Attach to the init_task data structure for proper alignment */
 #define __init_task_data __attribute__((__section__(".data..init_task")))
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index d49e26c6cdc7..c573a52ae440 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -29,6 +29,7 @@
 #include <linux/dma_remapping.h>
 #include <linux/mmu_notifier.h>
 #include <linux/list.h>
+#include <linux/iommu.h>
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
 
@@ -153,8 +154,8 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60)
 #define DMA_TLB_DSI_FLUSH (((u64)2) << 60)
 #define DMA_TLB_PSI_FLUSH (((u64)3) << 60)
-#define DMA_TLB_IIRG(type) ((type >> 60) & 7)
-#define DMA_TLB_IAIG(val) (((val) >> 57) & 7)
+#define DMA_TLB_IIRG(type) ((type >> 60) & 3)
+#define DMA_TLB_IAIG(val) (((val) >> 57) & 3)
 #define DMA_TLB_READ_DRAIN (((u64)1) << 49)
 #define DMA_TLB_WRITE_DRAIN (((u64)1) << 48)
 #define DMA_TLB_DID(id)	(((u64)((id) & 0xffff)) << 32)
@@ -164,9 +165,9 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 
 /* INVALID_DESC */
 #define DMA_CCMD_INVL_GRANU_OFFSET  61
-#define DMA_ID_TLB_GLOBAL_FLUSH	(((u64)1) << 3)
-#define DMA_ID_TLB_DSI_FLUSH	(((u64)2) << 3)
-#define DMA_ID_TLB_PSI_FLUSH	(((u64)3) << 3)
+#define DMA_ID_TLB_GLOBAL_FLUSH	(((u64)1) << 4)
+#define DMA_ID_TLB_DSI_FLUSH	(((u64)2) << 4)
+#define DMA_ID_TLB_PSI_FLUSH	(((u64)3) << 4)
 #define DMA_ID_TLB_READ_DRAIN	(((u64)1) << 7)
 #define DMA_ID_TLB_WRITE_DRAIN	(((u64)1) << 6)
 #define DMA_ID_TLB_DID(id)	(((u64)((id & 0xffff) << 16)))
@@ -316,8 +317,8 @@ enum {
 #define QI_DEV_EIOTLB_SIZE	(((u64)1) << 11)
 #define QI_DEV_EIOTLB_GLOB(g)	((u64)g)
 #define QI_DEV_EIOTLB_PASID(p)	(((u64)p) << 32)
-#define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 32)
-#define QI_DEV_EIOTLB_QDEP(qd)	(((qd) & 0x1f) << 16)
+#define QI_DEV_EIOTLB_SID(sid)	((u64)((sid) & 0xffff) << 16)
+#define QI_DEV_EIOTLB_QDEP(qd)	((u64)((qd) & 0x1f) << 4)
 #define QI_DEV_EIOTLB_MAX_INVS	32
 
 #define QI_PGRP_IDX(idx)	(((u64)(idx)) << 55)
@@ -439,7 +440,7 @@ struct intel_iommu {
 	struct irq_domain *ir_domain;
 	struct irq_domain *ir_msi_domain;
 #endif
-	struct device	*iommu_dev; /* IOMMU-sysfs device */
+	struct iommu_device iommu;  /* IOMMU core code handle */
 	int		node;
 	u32		flags;      /* Software defined flags */
 };
diff --git a/include/linux/intel_pmic_gpio.h b/include/linux/intel_pmic_gpio.h
deleted file mode 100644
index 920109a29191..000000000000
--- a/include/linux/intel_pmic_gpio.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef LINUX_INTEL_PMIC_H
-#define LINUX_INTEL_PMIC_H
-
-struct intel_pmic_gpio_platform_data {
-	/* the first IRQ of the chip */
-	unsigned	irq_base;
-	/* number assigned to the first GPIO */
-	unsigned	gpio_base;
-	/* sram address for gpiointr register, the langwell chip will map
-	 * the PMIC spi GPIO expander's GPIOINTR register in sram.
-	 */
-	unsigned	gpiointr;
-};
-
-#endif
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 0ff5111f6959..6a6de187ddc0 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -31,6 +31,13 @@
 #define IOMMU_CACHE	(1 << 2) /* DMA cache coherency */
 #define IOMMU_NOEXEC	(1 << 3)
 #define IOMMU_MMIO	(1 << 4) /* e.g. things like MSI doorbells */
+/*
+ * This is to make the IOMMU API setup privileged
+ * mapppings accessible by the master only at higher
+ * privileged execution level and inaccessible at
+ * less privileged levels.
+ */
+#define IOMMU_PRIV	(1 << 5)
 
 struct iommu_ops;
 struct iommu_group;
@@ -117,18 +124,25 @@ enum iommu_attr {
 	DOMAIN_ATTR_MAX,
 };
 
+/* These are the possible reserved region types */
+#define IOMMU_RESV_DIRECT	(1 << 0)
+#define IOMMU_RESV_RESERVED	(1 << 1)
+#define IOMMU_RESV_MSI		(1 << 2)
+
 /**
- * struct iommu_dm_region - descriptor for a direct mapped memory region
+ * struct iommu_resv_region - descriptor for a reserved memory region
  * @list: Linked list pointers
  * @start: System physical start address of the region
  * @length: Length of the region in bytes
  * @prot: IOMMU Protection flags (READ/WRITE/...)
+ * @type: Type of the reserved region
  */
-struct iommu_dm_region {
+struct iommu_resv_region {
 	struct list_head	list;
 	phys_addr_t		start;
 	size_t			length;
 	int			prot;
+	int			type;
 };
 
 #ifdef CONFIG_IOMMU_API
@@ -150,9 +164,9 @@ struct iommu_dm_region {
  * @device_group: find iommu group for a particular device
  * @domain_get_attr: Query domain attributes
  * @domain_set_attr: Change domain attributes
- * @get_dm_regions: Request list of direct mapping requirements for a device
- * @put_dm_regions: Free list of direct mapping requirements for a device
- * @apply_dm_region: Temporary helper call-back for iova reserved ranges
+ * @get_resv_regions: Request list of reserved regions for a device
+ * @put_resv_regions: Free list of reserved regions for a device
+ * @apply_resv_region: Temporary helper call-back for iova reserved ranges
  * @domain_window_enable: Configure and enable a particular window for a domain
  * @domain_window_disable: Disable a particular window for a domain
  * @domain_set_windows: Set the number of windows for a domain
@@ -184,11 +198,12 @@ struct iommu_ops {
 	int (*domain_set_attr)(struct iommu_domain *domain,
 			       enum iommu_attr attr, void *data);
 
-	/* Request/Free a list of direct mapping requirements for a device */
-	void (*get_dm_regions)(struct device *dev, struct list_head *list);
-	void (*put_dm_regions)(struct device *dev, struct list_head *list);
-	void (*apply_dm_region)(struct device *dev, struct iommu_domain *domain,
-				struct iommu_dm_region *region);
+	/* Request/Free a list of reserved regions for a device */
+	void (*get_resv_regions)(struct device *dev, struct list_head *list);
+	void (*put_resv_regions)(struct device *dev, struct list_head *list);
+	void (*apply_resv_region)(struct device *dev,
+				  struct iommu_domain *domain,
+				  struct iommu_resv_region *region);
 
 	/* Window handling functions */
 	int (*domain_window_enable)(struct iommu_domain *domain, u32 wnd_nr,
@@ -204,6 +219,42 @@ struct iommu_ops {
 	unsigned long pgsize_bitmap;
 };
 
+/**
+ * struct iommu_device - IOMMU core representation of one IOMMU hardware
+ *			 instance
+ * @list: Used by the iommu-core to keep a list of registered iommus
+ * @ops: iommu-ops for talking to this iommu
+ * @dev: struct device for sysfs handling
+ */
+struct iommu_device {
+	struct list_head list;
+	const struct iommu_ops *ops;
+	struct fwnode_handle *fwnode;
+	struct device dev;
+};
+
+int  iommu_device_register(struct iommu_device *iommu);
+void iommu_device_unregister(struct iommu_device *iommu);
+int  iommu_device_sysfs_add(struct iommu_device *iommu,
+			    struct device *parent,
+			    const struct attribute_group **groups,
+			    const char *fmt, ...) __printf(4, 5);
+void iommu_device_sysfs_remove(struct iommu_device *iommu);
+int  iommu_device_link(struct iommu_device   *iommu, struct device *link);
+void iommu_device_unlink(struct iommu_device *iommu, struct device *link);
+
+static inline void iommu_device_set_ops(struct iommu_device *iommu,
+					const struct iommu_ops *ops)
+{
+	iommu->ops = ops;
+}
+
+static inline void iommu_device_set_fwnode(struct iommu_device *iommu,
+					   struct fwnode_handle *fwnode)
+{
+	iommu->fwnode = fwnode;
+}
+
 #define IOMMU_GROUP_NOTIFY_ADD_DEVICE		1 /* Device added */
 #define IOMMU_GROUP_NOTIFY_DEL_DEVICE		2 /* Pre Device removed */
 #define IOMMU_GROUP_NOTIFY_BIND_DRIVER		3 /* Pre Driver bind */
@@ -233,9 +284,13 @@ extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t io
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
 
-extern void iommu_get_dm_regions(struct device *dev, struct list_head *list);
-extern void iommu_put_dm_regions(struct device *dev, struct list_head *list);
+extern void iommu_get_resv_regions(struct device *dev, struct list_head *list);
+extern void iommu_put_resv_regions(struct device *dev, struct list_head *list);
 extern int iommu_request_dm_for_dev(struct device *dev);
+extern struct iommu_resv_region *
+iommu_alloc_resv_region(phys_addr_t start, size_t length, int prot, int type);
+extern int iommu_get_group_resv_regions(struct iommu_group *group,
+					struct list_head *head);
 
 extern int iommu_attach_group(struct iommu_domain *domain,
 			      struct iommu_group *group);
@@ -267,12 +322,6 @@ extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr,
 				 void *data);
 extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr,
 				 void *data);
-struct device *iommu_device_create(struct device *parent, void *drvdata,
-				   const struct attribute_group **groups,
-				   const char *fmt, ...) __printf(4, 5);
-void iommu_device_destroy(struct device *dev);
-int iommu_device_link(struct device *dev, struct device *link);
-void iommu_device_unlink(struct device *dev, struct device *link);
 
 /* Window handling function prototypes */
 extern int iommu_domain_window_enable(struct iommu_domain *domain, u32 wnd_nr,
@@ -352,15 +401,14 @@ int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
 		      const struct iommu_ops *ops);
 void iommu_fwspec_free(struct device *dev);
 int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids);
-void iommu_register_instance(struct fwnode_handle *fwnode,
-			     const struct iommu_ops *ops);
-const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode);
+const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode);
 
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
 struct iommu_group {};
 struct iommu_fwspec {};
+struct iommu_device {};
 
 static inline bool iommu_present(struct bus_type *bus)
 {
@@ -443,16 +491,22 @@ static inline void iommu_set_fault_handler(struct iommu_domain *domain,
 {
 }
 
-static inline void iommu_get_dm_regions(struct device *dev,
+static inline void iommu_get_resv_regions(struct device *dev,
 					struct list_head *list)
 {
 }
 
-static inline void iommu_put_dm_regions(struct device *dev,
+static inline void iommu_put_resv_regions(struct device *dev,
 					struct list_head *list)
 {
 }
 
+static inline int iommu_get_group_resv_regions(struct iommu_group *group,
+					       struct list_head *head)
+{
+	return -ENODEV;
+}
+
 static inline int iommu_request_dm_for_dev(struct device *dev)
 {
 	return -ENODEV;
@@ -546,15 +600,34 @@ static inline int iommu_domain_set_attr(struct iommu_domain *domain,
 	return -EINVAL;
 }
 
-static inline struct device *iommu_device_create(struct device *parent,
-					void *drvdata,
-					const struct attribute_group **groups,
-					const char *fmt, ...)
+static inline int  iommu_device_register(struct iommu_device *iommu)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_device_set_ops(struct iommu_device *iommu,
+					const struct iommu_ops *ops)
+{
+}
+
+static inline void iommu_device_set_fwnode(struct iommu_device *iommu,
+					   struct fwnode_handle *fwnode)
+{
+}
+
+static inline void iommu_device_unregister(struct iommu_device *iommu)
 {
-	return ERR_PTR(-ENODEV);
 }
 
-static inline void iommu_device_destroy(struct device *dev)
+static inline int  iommu_device_sysfs_add(struct iommu_device *iommu,
+					  struct device *parent,
+					  const struct attribute_group **groups,
+					  const char *fmt, ...)
+{
+	return -ENODEV;
+}
+
+static inline void iommu_device_sysfs_remove(struct iommu_device *iommu)
 {
 }
 
@@ -584,13 +657,8 @@ static inline int iommu_fwspec_add_ids(struct device *dev, u32 *ids,
 	return -ENODEV;
 }
 
-static inline void iommu_register_instance(struct fwnode_handle *fwnode,
-					   const struct iommu_ops *ops)
-{
-}
-
 static inline
-const struct iommu_ops *iommu_get_instance(struct fwnode_handle *fwnode)
+const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
 {
 	return NULL;
 }
diff --git a/include/linux/irq.h b/include/linux/irq.h
index e79875574b39..f887351aa80e 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -184,6 +184,7 @@ struct irq_data {
  *
  * IRQD_TRIGGER_MASK		- Mask for the trigger type bits
  * IRQD_SETAFFINITY_PENDING	- Affinity setting is pending
+ * IRQD_ACTIVATED		- Interrupt has already been activated
  * IRQD_NO_BALANCING		- Balancing disabled for this IRQ
  * IRQD_PER_CPU			- Interrupt is per cpu
  * IRQD_AFFINITY_SET		- Interrupt affinity was set
@@ -202,6 +203,7 @@ struct irq_data {
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
 	IRQD_SETAFFINITY_PENDING	= (1 <<  8),
+	IRQD_ACTIVATED			= (1 <<  9),
 	IRQD_NO_BALANCING		= (1 << 10),
 	IRQD_PER_CPU			= (1 << 11),
 	IRQD_AFFINITY_SET		= (1 << 12),
@@ -312,6 +314,21 @@ static inline bool irqd_affinity_is_managed(struct irq_data *d)
 	return __irqd_to_state(d) & IRQD_AFFINITY_MANAGED;
 }
 
+static inline bool irqd_is_activated(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_ACTIVATED;
+}
+
+static inline void irqd_set_activated(struct irq_data *d)
+{
+	__irqd_to_state(d) |= IRQD_ACTIVATED;
+}
+
+static inline void irqd_clr_activated(struct irq_data *d)
+{
+	__irqd_to_state(d) &= ~IRQD_ACTIVATED;
+}
+
 #undef __irqd_to_state
 
 static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
@@ -715,6 +732,10 @@ unsigned int arch_dynirq_lower_bound(unsigned int from);
 int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 		      struct module *owner, const struct cpumask *affinity);
 
+int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from,
+			   unsigned int cnt, int node, struct module *owner,
+			   const struct cpumask *affinity);
+
 /* use macros to avoid needing export.h for THIS_MODULE */
 #define irq_alloc_descs(irq, from, cnt, node)	\
 	__irq_alloc_descs(irq, from, cnt, node, THIS_MODULE, NULL)
@@ -731,6 +752,21 @@ int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 #define irq_alloc_descs_from(from, cnt, node)	\
 	irq_alloc_descs(-1, from, cnt, node)
 
+#define devm_irq_alloc_descs(dev, irq, from, cnt, node)		\
+	__devm_irq_alloc_descs(dev, irq, from, cnt, node, THIS_MODULE, NULL)
+
+#define devm_irq_alloc_desc(dev, node)				\
+	devm_irq_alloc_descs(dev, -1, 0, 1, node)
+
+#define devm_irq_alloc_desc_at(dev, at, node)			\
+	devm_irq_alloc_descs(dev, at, at, 1, node)
+
+#define devm_irq_alloc_desc_from(dev, from, node)		\
+	devm_irq_alloc_descs(dev, -1, from, 1, node)
+
+#define devm_irq_alloc_descs_from(dev, from, cnt, node)		\
+	devm_irq_alloc_descs(dev, -1, from, cnt, node)
+
 void irq_free_descs(unsigned int irq, unsigned int cnt);
 static inline void irq_free_desc(unsigned int irq)
 {
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index e808f8ae6f14..725e86b506f3 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -73,7 +73,6 @@
 
 #define GICD_TYPER_ID_BITS(typer)	((((typer) >> 19) & 0x1f) + 1)
 #define GICD_TYPER_IRQS(typer)		((((typer) & 0x1f) + 1) * 32)
-#define GICD_TYPER_LPIS			(1U << 17)
 
 #define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
 #define GICD_IROUTER_SPI_MODE_ANY	(1U << 31)
@@ -306,7 +305,7 @@
 #define GITS_BASER_TYPE_NONE		0
 #define GITS_BASER_TYPE_DEVICE		1
 #define GITS_BASER_TYPE_VCPU		2
-#define GITS_BASER_TYPE_CPU		3
+#define GITS_BASER_TYPE_RESERVED3	3
 #define GITS_BASER_TYPE_COLLECTION	4
 #define GITS_BASER_TYPE_RESERVED5	5
 #define GITS_BASER_TYPE_RESERVED6	6
@@ -320,8 +319,6 @@
 #define GITS_CMD_MAPD			0x08
 #define GITS_CMD_MAPC			0x09
 #define GITS_CMD_MAPTI			0x0a
-/* older GIC documentation used MAPVI for this command */
-#define GITS_CMD_MAPVI			GITS_CMD_MAPTI
 #define GITS_CMD_MAPI			0x0b
 #define GITS_CMD_MOVI			0x01
 #define GITS_CMD_DISCARD		0x0f
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index ffb84604c1de..188eced6813e 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -183,6 +183,12 @@ enum {
 	/* Irq domain is an IPI domain with single virq */
 	IRQ_DOMAIN_FLAG_IPI_SINGLE	= (1 << 3),
 
+	/* Irq domain implements MSIs */
+	IRQ_DOMAIN_FLAG_MSI		= (1 << 4),
+
+	/* Irq domain implements MSI remapping */
+	IRQ_DOMAIN_FLAG_MSI_REMAP	= (1 << 5),
+
 	/*
 	 * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved
 	 * for implementation specific purposes and ignored by the
@@ -216,6 +222,7 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
 					 void *host_data);
 extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
 						   enum irq_domain_bus_token bus_token);
+extern bool irq_domain_check_msi_remap(void);
 extern void irq_set_default_host(struct irq_domain *host);
 extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
 				  irq_hw_number_t hwirq, int node,
@@ -446,6 +453,19 @@ static inline bool irq_domain_is_ipi_single(struct irq_domain *domain)
 {
 	return domain->flags & IRQ_DOMAIN_FLAG_IPI_SINGLE;
 }
+
+static inline bool irq_domain_is_msi(struct irq_domain *domain)
+{
+	return domain->flags & IRQ_DOMAIN_FLAG_MSI;
+}
+
+static inline bool irq_domain_is_msi_remap(struct irq_domain *domain)
+{
+	return domain->flags & IRQ_DOMAIN_FLAG_MSI_REMAP;
+}
+
+extern bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain);
+
 #else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 static inline void irq_domain_activate_irq(struct irq_data *data) { }
 static inline void irq_domain_deactivate_irq(struct irq_data *data) { }
@@ -477,6 +497,22 @@ static inline bool irq_domain_is_ipi_single(struct irq_domain *domain)
 {
 	return false;
 }
+
+static inline bool irq_domain_is_msi(struct irq_domain *domain)
+{
+	return false;
+}
+
+static inline bool irq_domain_is_msi_remap(struct irq_domain *domain)
+{
+	return false;
+}
+
+static inline bool
+irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain)
+{
+	return false;
+}
 #endif	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 
 #else /* CONFIG_IRQ_DOMAIN */
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 589d14e970ad..624215cebee5 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -293,6 +293,8 @@ static inline u64 jiffies_to_nsecs(const unsigned long j)
 	return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC;
 }
 
+extern u64 jiffies64_to_nsecs(u64 j);
+
 extern unsigned long __msecs_to_jiffies(const unsigned int m);
 #if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ)
 /*
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index a0547c571800..b63d6b7b0db0 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -402,6 +402,6 @@ extern bool ____wrong_branch_error(void);
 #define static_branch_enable(x)		static_key_enable(&(x)->key)
 #define static_branch_disable(x)	static_key_disable(&(x)->key)
 
-#endif	/* _LINUX_JUMP_LABEL_H */
-
 #endif /* __ASSEMBLY__ */
+
+#endif	/* _LINUX_JUMP_LABEL_H */
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 00f776816aa3..66be8b6beceb 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -9,7 +9,6 @@
 #include <linux/sched.h>
 #include <linux/vtime.h>
 #include <asm/irq.h>
-#include <linux/cputime.h>
 
 /*
  * 'kernel_stat.h' contains the definitions needed for doing
@@ -78,15 +77,18 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu)
 	return kstat_cpu(cpu).irqs_sum;
 }
 
-extern void account_user_time(struct task_struct *, cputime_t);
-extern void account_system_time(struct task_struct *, int, cputime_t);
-extern void account_steal_time(cputime_t);
-extern void account_idle_time(cputime_t);
+extern void account_user_time(struct task_struct *, u64);
+extern void account_guest_time(struct task_struct *, u64);
+extern void account_system_time(struct task_struct *, int, u64);
+extern void account_system_index_time(struct task_struct *, u64,
+				      enum cpu_usage_stat);
+extern void account_steal_time(u64);
+extern void account_idle_time(u64);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 static inline void account_process_tick(struct task_struct *tsk, int user)
 {
-	vtime_account_user(tsk);
+	vtime_flush(tsk);
 }
 #else
 extern void account_process_tick(struct task_struct *, int user);
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 8f6849084248..16ddfb8b304a 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -278,9 +278,13 @@ struct kprobe_insn_cache {
 	int nr_garbage;
 };
 
+#ifdef __ARCH_WANT_KPROBES_INSN_SLOT
 extern kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c);
 extern void __free_insn_slot(struct kprobe_insn_cache *c,
 			     kprobe_opcode_t *slot, int dirty);
+/* sleep-less address checking routine  */
+extern bool __is_insn_slot_addr(struct kprobe_insn_cache *c,
+				unsigned long addr);
 
 #define DEFINE_INSN_CACHE_OPS(__name)					\
 extern struct kprobe_insn_cache kprobe_##__name##_slots;		\
@@ -294,6 +298,18 @@ static inline void free_##__name##_slot(kprobe_opcode_t *slot, int dirty)\
 {									\
 	__free_insn_slot(&kprobe_##__name##_slots, slot, dirty);	\
 }									\
+									\
+static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
+{									\
+	return __is_insn_slot_addr(&kprobe_##__name##_slots, addr);	\
+}
+#else /* __ARCH_WANT_KPROBES_INSN_SLOT */
+#define DEFINE_INSN_CACHE_OPS(__name)					\
+static inline bool is_kprobe_##__name##_slot(unsigned long addr)	\
+{									\
+	return 0;							\
+}
+#endif
 
 DEFINE_INSN_CACHE_OPS(insn);
 
@@ -330,7 +346,6 @@ extern int proc_kprobes_optimization_handler(struct ctl_table *table,
 					     int write, void __user *buffer,
 					     size_t *length, loff_t *ppos);
 #endif
-
 #endif /* CONFIG_OPTPROBES */
 #ifdef CONFIG_KPROBES_ON_FTRACE
 extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
@@ -481,6 +496,19 @@ static inline int enable_jprobe(struct jprobe *jp)
 	return enable_kprobe(&jp->kp);
 }
 
+#ifndef CONFIG_KPROBES
+static inline bool is_kprobe_insn_slot(unsigned long addr)
+{
+	return false;
+}
+#endif
+#ifndef CONFIG_OPTPROBES
+static inline bool is_kprobe_optinsn_slot(unsigned long addr)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_KPROBES
 /*
  * Blacklist ganerating macro. Specify functions which is not probed
diff --git a/include/linux/kref.h b/include/linux/kref.h
index e15828fd71f1..f4156f88f557 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -15,22 +15,27 @@
 #ifndef _KREF_H_
 #define _KREF_H_
 
-#include <linux/bug.h>
-#include <linux/atomic.h>
-#include <linux/kernel.h>
-#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/refcount.h>
 
 struct kref {
-	atomic_t refcount;
+	refcount_t refcount;
 };
 
+#define KREF_INIT(n)	{ .refcount = REFCOUNT_INIT(n), }
+
 /**
  * kref_init - initialize object.
  * @kref: object in question.
  */
 static inline void kref_init(struct kref *kref)
 {
-	atomic_set(&kref->refcount, 1);
+	refcount_set(&kref->refcount, 1);
+}
+
+static inline unsigned int kref_read(const struct kref *kref)
+{
+	return refcount_read(&kref->refcount);
 }
 
 /**
@@ -39,17 +44,12 @@ static inline void kref_init(struct kref *kref)
  */
 static inline void kref_get(struct kref *kref)
 {
-	/* If refcount was 0 before incrementing then we have a race
-	 * condition when this kref is freeing by some other thread right now.
-	 * In this case one should use kref_get_unless_zero()
-	 */
-	WARN_ON_ONCE(atomic_inc_return(&kref->refcount) < 2);
+	refcount_inc(&kref->refcount);
 }
 
 /**
- * kref_sub - subtract a number of refcounts for object.
+ * kref_put - decrement refcount for object.
  * @kref: object.
- * @count: Number of recounts to subtract.
  * @release: pointer to the function that will clean up the object when the
  *	     last reference to the object is released.
  *	     This pointer is required, and it is not acceptable to pass kfree
@@ -58,57 +58,43 @@ static inline void kref_get(struct kref *kref)
  *	     maintainer, and anyone else who happens to notice it.  You have
  *	     been warned.
  *
- * Subtract @count from the refcount, and if 0, call release().
+ * Decrement the refcount, and if 0, call release().
  * Return 1 if the object was removed, otherwise return 0.  Beware, if this
  * function returns 0, you still can not count on the kref from remaining in
  * memory.  Only use the return value if you want to see if the kref is now
  * gone, not present.
  */
-static inline int kref_sub(struct kref *kref, unsigned int count,
-	     void (*release)(struct kref *kref))
+static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref))
 {
 	WARN_ON(release == NULL);
 
-	if (atomic_sub_and_test((int) count, &kref->refcount)) {
+	if (refcount_dec_and_test(&kref->refcount)) {
 		release(kref);
 		return 1;
 	}
 	return 0;
 }
 
-/**
- * kref_put - decrement refcount for object.
- * @kref: object.
- * @release: pointer to the function that will clean up the object when the
- *	     last reference to the object is released.
- *	     This pointer is required, and it is not acceptable to pass kfree
- *	     in as this function.  If the caller does pass kfree to this
- *	     function, you will be publicly mocked mercilessly by the kref
- *	     maintainer, and anyone else who happens to notice it.  You have
- *	     been warned.
- *
- * Decrement the refcount, and if 0, call release().
- * Return 1 if the object was removed, otherwise return 0.  Beware, if this
- * function returns 0, you still can not count on the kref from remaining in
- * memory.  Only use the return value if you want to see if the kref is now
- * gone, not present.
- */
-static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref))
-{
-	return kref_sub(kref, 1, release);
-}
-
 static inline int kref_put_mutex(struct kref *kref,
 				 void (*release)(struct kref *kref),
 				 struct mutex *lock)
 {
 	WARN_ON(release == NULL);
-	if (unlikely(!atomic_add_unless(&kref->refcount, -1, 1))) {
-		mutex_lock(lock);
-		if (unlikely(!atomic_dec_and_test(&kref->refcount))) {
-			mutex_unlock(lock);
-			return 0;
-		}
+
+	if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) {
+		release(kref);
+		return 1;
+	}
+	return 0;
+}
+
+static inline int kref_put_lock(struct kref *kref,
+				void (*release)(struct kref *kref),
+				spinlock_t *lock)
+{
+	WARN_ON(release == NULL);
+
+	if (refcount_dec_and_lock(&kref->refcount, lock)) {
 		release(kref);
 		return 1;
 	}
@@ -133,6 +119,6 @@ static inline int kref_put_mutex(struct kref *kref,
  */
 static inline int __must_check kref_get_unless_zero(struct kref *kref)
 {
-	return atomic_add_unless(&kref->refcount, 1, 0);
+	return refcount_inc_not_zero(&kref->refcount);
 }
 #endif /* _KREF_H_ */
diff --git a/include/linux/leds.h b/include/linux/leds.h
index 569cb531094c..38c0bd7ca107 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -13,6 +13,7 @@
 #define __LINUX_LEDS_H_INCLUDED
 
 #include <linux/device.h>
+#include <linux/kernfs.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
@@ -27,6 +28,7 @@ struct device;
 
 enum led_brightness {
 	LED_OFF		= 0,
+	LED_ON		= 1,
 	LED_HALF	= 127,
 	LED_FULL	= 255,
 };
@@ -46,6 +48,7 @@ struct led_classdev {
 #define LED_DEV_CAP_FLASH	(1 << 18)
 #define LED_HW_PLUGGABLE	(1 << 19)
 #define LED_PANIC_INDICATOR	(1 << 20)
+#define LED_BRIGHT_HW_CHANGED	(1 << 21)
 
 	/* set_brightness_work / blink_timer flags, atomic, private. */
 	unsigned long		work_flags;
@@ -110,6 +113,11 @@ struct led_classdev {
 	bool			activated;
 #endif
 
+#ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED
+	int			 brightness_hw_changed;
+	struct kernfs_node	*brightness_hw_changed_kn;
+#endif
+
 	/* Ensures consistent access to the LED Flash Class device */
 	struct mutex		led_access;
 };
@@ -422,4 +430,12 @@ static inline void ledtrig_cpu(enum cpu_led_event evt)
 }
 #endif
 
+#ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED
+extern void led_classdev_notify_brightness_hw_changed(
+	struct led_classdev *led_cdev, enum led_brightness brightness);
+#else
+static inline void led_classdev_notify_brightness_hw_changed(
+	struct led_classdev *led_cdev, enum led_brightness brightness) { }
+#endif
+
 #endif		/* __LINUX_LEDS_H_INCLUDED */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index c170be548b7f..46e18c0619c6 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1130,6 +1130,7 @@ extern int ata_sas_port_start(struct ata_port *ap);
 extern void ata_sas_port_stop(struct ata_port *ap);
 extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *);
 extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap);
+extern enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd);
 extern int sata_scr_valid(struct ata_link *link);
 extern int sata_scr_read(struct ata_link *link, int reg, u32 *val);
 extern int sata_scr_write(struct ata_link *link, int reg, u32 val);
@@ -1355,6 +1356,7 @@ extern struct device_attribute *ata_common_sdev_attrs[];
 	.proc_name		= drv_name,			\
 	.slave_configure	= ata_scsi_slave_config,	\
 	.slave_destroy		= ata_scsi_slave_destroy,	\
+	.eh_timed_out		= ata_scsi_timed_out,		\
 	.bios_param		= ata_std_bios_param,		\
 	.unlock_native_capacity	= ata_scsi_unlock_native_capacity, \
 	.sdev_attrs		= ata_common_sdev_attrs
diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h
index 7c273bbc5351..ca45e4a088a9 100644
--- a/include/linux/lightnvm.h
+++ b/include/linux/lightnvm.h
@@ -80,8 +80,6 @@ struct nvm_dev_ops {
 	unsigned int		max_phys_sect;
 };
 
-
-
 #ifdef CONFIG_NVM
 
 #include <linux/blkdev.h>
@@ -109,6 +107,7 @@ enum {
 	NVM_RSP_ERR_FAILWRITE	= 0x40ff,
 	NVM_RSP_ERR_EMPTYPAGE	= 0x42ff,
 	NVM_RSP_ERR_FAILECC	= 0x4281,
+	NVM_RSP_ERR_FAILCRC	= 0x4004,
 	NVM_RSP_WARN_HIGHECC	= 0x4700,
 
 	/* Device opcodes */
@@ -202,11 +201,10 @@ struct nvm_addr_format {
 struct nvm_id {
 	u8	ver_id;
 	u8	vmnt;
-	u8	cgrps;
 	u32	cap;
 	u32	dom;
 	struct nvm_addr_format ppaf;
-	struct nvm_id_group groups[4];
+	struct nvm_id_group grp;
 } __packed;
 
 struct nvm_target {
@@ -216,10 +214,6 @@ struct nvm_target {
 	struct gendisk *disk;
 };
 
-struct nvm_tgt_instance {
-	struct nvm_tgt_type *tt;
-};
-
 #define ADDR_EMPTY (~0ULL)
 
 #define NVM_VERSION_MAJOR 1
@@ -230,7 +224,6 @@ struct nvm_rq;
 typedef void (nvm_end_io_fn)(struct nvm_rq *);
 
 struct nvm_rq {
-	struct nvm_tgt_instance *ins;
 	struct nvm_tgt_dev *dev;
 
 	struct bio *bio;
@@ -254,6 +247,8 @@ struct nvm_rq {
 
 	u64 ppa_status; /* ppa media status */
 	int error;
+
+	void *private;
 };
 
 static inline struct nvm_rq *nvm_rq_from_pdu(void *pdu)
@@ -272,15 +267,6 @@ enum {
 	NVM_BLK_ST_BAD =	0x8,	/* Bad block */
 };
 
-/* system block cpu representation */
-struct nvm_sb_info {
-	unsigned long		seqnr;
-	unsigned long		erase_cnt;
-	unsigned int		version;
-	char			mmtype[NVM_MMTYPE_LEN];
-	struct ppa_addr		fs_ppa;
-};
-
 /* Device generic information */
 struct nvm_geo {
 	int nr_chnls;
@@ -308,6 +294,7 @@ struct nvm_geo {
 	int sec_per_lun;
 };
 
+/* sub-device structure */
 struct nvm_tgt_dev {
 	/* Device information */
 	struct nvm_geo geo;
@@ -329,17 +316,10 @@ struct nvm_dev {
 
 	struct list_head devices;
 
-	/* Media manager */
-	struct nvmm_type *mt;
-	void *mp;
-
-	/* System blocks */
-	struct nvm_sb_info sb;
-
 	/* Device information */
 	struct nvm_geo geo;
 
-	/* lower page table */
+	  /* lower page table */
 	int lps_per_blk;
 	int *lptbl;
 
@@ -359,6 +339,10 @@ struct nvm_dev {
 
 	struct mutex mlock;
 	spinlock_t lock;
+
+	/* target management */
+	struct list_head area_list;
+	struct list_head targets;
 };
 
 static inline struct ppa_addr linear_to_generic_addr(struct nvm_geo *geo,
@@ -391,10 +375,10 @@ static inline struct ppa_addr linear_to_generic_addr(struct nvm_geo *geo,
 	return l;
 }
 
-static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev,
-						struct ppa_addr r)
+static inline struct ppa_addr generic_to_dev_addr(struct nvm_tgt_dev *tgt_dev,
+						  struct ppa_addr r)
 {
-	struct nvm_geo *geo = &dev->geo;
+	struct nvm_geo *geo = &tgt_dev->geo;
 	struct ppa_addr l;
 
 	l.ppa = ((u64)r.g.blk) << geo->ppaf.blk_offset;
@@ -407,10 +391,10 @@ static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev,
 	return l;
 }
 
-static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev,
-						struct ppa_addr r)
+static inline struct ppa_addr dev_to_generic_addr(struct nvm_tgt_dev *tgt_dev,
+						  struct ppa_addr r)
 {
-	struct nvm_geo *geo = &dev->geo;
+	struct nvm_geo *geo = &tgt_dev->geo;
 	struct ppa_addr l;
 
 	l.ppa = 0;
@@ -452,15 +436,12 @@ static inline int ppa_cmp_blk(struct ppa_addr ppa1, struct ppa_addr ppa2)
 					(ppa1.g.blk == ppa2.g.blk));
 }
 
-static inline int ppa_to_slc(struct nvm_dev *dev, int slc_pg)
-{
-	return dev->lptbl[slc_pg];
-}
-
 typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *);
 typedef sector_t (nvm_tgt_capacity_fn)(void *);
 typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *);
 typedef void (nvm_tgt_exit_fn)(void *);
+typedef int (nvm_tgt_sysfs_init_fn)(struct gendisk *);
+typedef void (nvm_tgt_sysfs_exit_fn)(struct gendisk *);
 
 struct nvm_tgt_type {
 	const char *name;
@@ -469,12 +450,15 @@ struct nvm_tgt_type {
 	/* target entry points */
 	nvm_tgt_make_rq_fn *make_rq;
 	nvm_tgt_capacity_fn *capacity;
-	nvm_end_io_fn *end_io;
 
 	/* module-specific init/teardown */
 	nvm_tgt_init_fn *init;
 	nvm_tgt_exit_fn *exit;
 
+	/* sysfs */
+	nvm_tgt_sysfs_init_fn *sysfs_init;
+	nvm_tgt_sysfs_exit_fn *sysfs_exit;
+
 	/* For internal use */
 	struct list_head list;
 };
@@ -487,103 +471,29 @@ extern void nvm_unregister_tgt_type(struct nvm_tgt_type *);
 extern void *nvm_dev_dma_alloc(struct nvm_dev *, gfp_t, dma_addr_t *);
 extern void nvm_dev_dma_free(struct nvm_dev *, void *, dma_addr_t);
 
-typedef int (nvmm_register_fn)(struct nvm_dev *);
-typedef void (nvmm_unregister_fn)(struct nvm_dev *);
-
-typedef int (nvmm_create_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_create *);
-typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *);
-typedef int (nvmm_submit_io_fn)(struct nvm_tgt_dev *, struct nvm_rq *);
-typedef int (nvmm_erase_blk_fn)(struct nvm_tgt_dev *, struct ppa_addr *, int);
-typedef int (nvmm_get_area_fn)(struct nvm_dev *, sector_t *, sector_t);
-typedef void (nvmm_put_area_fn)(struct nvm_dev *, sector_t);
-typedef struct ppa_addr (nvmm_trans_ppa_fn)(struct nvm_tgt_dev *,
-					    struct ppa_addr, int);
-typedef void (nvmm_part_to_tgt_fn)(struct nvm_dev *, sector_t*, int);
-
-enum {
-	TRANS_TGT_TO_DEV =	0x0,
-	TRANS_DEV_TO_TGT =	0x1,
-};
-
-struct nvmm_type {
-	const char *name;
-	unsigned int version[3];
-
-	nvmm_register_fn *register_mgr;
-	nvmm_unregister_fn *unregister_mgr;
-
-	nvmm_create_tgt_fn *create_tgt;
-	nvmm_remove_tgt_fn *remove_tgt;
-
-	nvmm_submit_io_fn *submit_io;
-	nvmm_erase_blk_fn *erase_blk;
-
-	nvmm_get_area_fn *get_area;
-	nvmm_put_area_fn *put_area;
-
-	nvmm_trans_ppa_fn *trans_ppa;
-	nvmm_part_to_tgt_fn *part_to_tgt;
-
-	struct list_head list;
-};
-
-extern int nvm_register_mgr(struct nvmm_type *);
-extern void nvm_unregister_mgr(struct nvmm_type *);
-
 extern struct nvm_dev *nvm_alloc_dev(int);
 extern int nvm_register(struct nvm_dev *);
 extern void nvm_unregister(struct nvm_dev *);
 
-extern int nvm_set_bb_tbl(struct nvm_dev *, struct ppa_addr *, int, int);
 extern int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr *,
 			      int, int);
 extern int nvm_max_phys_sects(struct nvm_tgt_dev *);
 extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *);
-extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *);
-extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *);
 extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *,
 					const struct ppa_addr *, int, int);
 extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *);
-extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int, int);
 extern int nvm_erase_blk(struct nvm_tgt_dev *, struct ppa_addr *, int);
 extern int nvm_get_l2p_tbl(struct nvm_tgt_dev *, u64, u32, nvm_l2p_update_fn *,
 			   void *);
 extern int nvm_get_area(struct nvm_tgt_dev *, sector_t *, sector_t);
 extern void nvm_put_area(struct nvm_tgt_dev *, sector_t);
-extern void nvm_end_io(struct nvm_rq *, int);
-extern int nvm_submit_ppa(struct nvm_dev *, struct ppa_addr *, int, int, int,
-								void *, int);
-extern int nvm_submit_ppa_list(struct nvm_dev *, struct ppa_addr *, int, int,
-							int, void *, int);
+extern void nvm_end_io(struct nvm_rq *);
 extern int nvm_bb_tbl_fold(struct nvm_dev *, u8 *, int);
-extern int nvm_get_bb_tbl(struct nvm_dev *, struct ppa_addr, u8 *);
 extern int nvm_get_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr, u8 *);
 
-/* sysblk.c */
-#define NVM_SYSBLK_MAGIC 0x4E564D53 /* "NVMS" */
-
-/* system block on disk representation */
-struct nvm_system_block {
-	__be32			magic;		/* magic signature */
-	__be32			seqnr;		/* sequence number */
-	__be32			erase_cnt;	/* erase count */
-	__be16			version;	/* version number */
-	u8			mmtype[NVM_MMTYPE_LEN]; /* media manager name */
-	__be64			fs_ppa;		/* PPA for media manager
-						 * superblock */
-};
-
-extern int nvm_get_sysblock(struct nvm_dev *, struct nvm_sb_info *);
-extern int nvm_update_sysblock(struct nvm_dev *, struct nvm_sb_info *);
-extern int nvm_init_sysblock(struct nvm_dev *, struct nvm_sb_info *);
-
 extern int nvm_dev_factory(struct nvm_dev *, int flags);
 
-#define nvm_for_each_lun_ppa(geo, ppa, chid, lunid)			\
-	for ((chid) = 0, (ppa).ppa = 0; (chid) < (geo)->nr_chnls;	\
-					(chid)++, (ppa).g.ch = (chid))	\
-		for ((lunid) = 0; (lunid) < (geo)->luns_per_chnl;	\
-					(lunid)++, (ppa).g.lun = (lunid))
+extern void nvm_part_to_tgt(struct nvm_dev *, sector_t *, int);
 
 #else /* CONFIG_NVM */
 struct nvm_dev_ops;
diff --git a/include/linux/llist.h b/include/linux/llist.h
index fd4ca0b4fe0f..171baa90f6f6 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -3,28 +3,33 @@
 /*
  * Lock-less NULL terminated single linked list
  *
- * If there are multiple producers and multiple consumers, llist_add
- * can be used in producers and llist_del_all can be used in
- * consumers.  They can work simultaneously without lock.  But
- * llist_del_first can not be used here.  Because llist_del_first
- * depends on list->first->next does not changed if list->first is not
- * changed during its operation, but llist_del_first, llist_add,
- * llist_add (or llist_del_all, llist_add, llist_add) sequence in
- * another consumer may violate that.
- *
- * If there are multiple producers and one consumer, llist_add can be
- * used in producers and llist_del_all or llist_del_first can be used
- * in the consumer.
- *
- * This can be summarized as follow:
+ * Cases where locking is not needed:
+ * If there are multiple producers and multiple consumers, llist_add can be
+ * used in producers and llist_del_all can be used in consumers simultaneously
+ * without locking. Also a single consumer can use llist_del_first while
+ * multiple producers simultaneously use llist_add, without any locking.
+ *
+ * Cases where locking is needed:
+ * If we have multiple consumers with llist_del_first used in one consumer, and
+ * llist_del_first or llist_del_all used in other consumers, then a lock is
+ * needed.  This is because llist_del_first depends on list->first->next not
+ * changing, but without lock protection, there's no way to be sure about that
+ * if a preemption happens in the middle of the delete operation and on being
+ * preempted back, the list->first is the same as before causing the cmpxchg in
+ * llist_del_first to succeed. For example, while a llist_del_first operation
+ * is in progress in one consumer, then a llist_del_first, llist_add,
+ * llist_add (or llist_del_all, llist_add, llist_add) sequence in another
+ * consumer may cause violations.
+ *
+ * This can be summarized as follows:
  *
  *           |   add    | del_first |  del_all
  * add       |    -     |     -     |     -
  * del_first |          |     L     |     L
  * del_all   |          |           |     -
  *
- * Where "-" stands for no lock is needed, while "L" stands for lock
- * is needed.
+ * Where, a particular row's operation can happen concurrently with a column's
+ * operation, with "-" being no lock needed, while "L" being lock is needed.
  *
  * The list entries deleted via llist_del_all can be traversed with
  * traversing function such as llist_for_each etc.  But the list
diff --git a/include/linux/log2.h b/include/linux/log2.h
index fd7ff3d91e6a..ef3d4f67118c 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -203,6 +203,17 @@ unsigned long __rounddown_pow_of_two(unsigned long n)
  *  ... and so on.
  */
 
-#define order_base_2(n) ilog2(roundup_pow_of_two(n))
+static inline __attribute_const__
+int __order_base_2(unsigned long n)
+{
+	return n > 1 ? ilog2(n - 1) + 1 : 0;
+}
 
+#define order_base_2(n)				\
+(						\
+	__builtin_constant_p(n) ? (		\
+		((n) == 0 || (n) == 1) ? 0 :	\
+		ilog2((n) - 1) + 1) :		\
+	__order_base_2(n)			\
+)
 #endif /* _LINUX_LOG2_H */
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 6e8b5b270ffe..80690c96c734 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -133,6 +133,16 @@ __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
 	return ret;
 }
 
+#ifndef mul_u32_u32
+/*
+ * Many a GCC version messes this up and generates a 64x64 mult :-(
+ */
+static inline u64 mul_u32_u32(u32 a, u32 b)
+{
+	return (u64)a * b;
+}
+#endif
+
 #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
 
 #ifndef mul_u64_u32_shr
@@ -160,9 +170,9 @@ static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
 	al = a;
 	ah = a >> 32;
 
-	ret = ((u64)al * mul) >> shift;
+	ret = mul_u32_u32(al, mul) >> shift;
 	if (ah)
-		ret += ((u64)ah * mul) << (32 - shift);
+		ret += mul_u32_u32(ah, mul) << (32 - shift);
 
 	return ret;
 }
@@ -186,10 +196,10 @@ static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift)
 	a0.ll = a;
 	b0.ll = b;
 
-	rl.ll = (u64)a0.l.low * b0.l.low;
-	rm.ll = (u64)a0.l.low * b0.l.high;
-	rn.ll = (u64)a0.l.high * b0.l.low;
-	rh.ll = (u64)a0.l.high * b0.l.high;
+	rl.ll = mul_u32_u32(a0.l.low, b0.l.low);
+	rm.ll = mul_u32_u32(a0.l.low, b0.l.high);
+	rn.ll = mul_u32_u32(a0.l.high, b0.l.low);
+	rh.ll = mul_u32_u32(a0.l.high, b0.l.high);
 
 	/*
 	 * Each of these lines computes a 64-bit intermediate result into "c",
@@ -229,8 +239,8 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor)
 	} u, rl, rh;
 
 	u.ll = a;
-	rl.ll = (u64)u.l.low * mul;
-	rh.ll = (u64)u.l.high * mul + rl.l.high;
+	rl.ll = mul_u32_u32(u.l.low, mul);
+	rh.ll = mul_u32_u32(u.l.high, mul) + rl.l.high;
 
 	/* Bits 32-63 of the result will be in rh.l.low. */
 	rl.l.high = do_div(rh.ll, divisor);
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 01033fadea47..134a2f69c21a 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -85,7 +85,8 @@ extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
 extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
 /* VM interface that may be used by firmware interface */
 extern int online_pages(unsigned long, unsigned long, int);
-extern int test_pages_in_a_zone(unsigned long, unsigned long);
+extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
+	unsigned long *valid_start, unsigned long *valid_end);
 extern void __offline_isolated_pages(unsigned long, unsigned long);
 
 typedef void (*online_page_callback_t)(struct page *page);
@@ -284,7 +285,7 @@ extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
 		unsigned long map_offset);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
-extern int zone_can_shift(unsigned long pfn, unsigned long nr_pages,
-			  enum zone_type target);
+extern bool zone_can_shift(unsigned long pfn, unsigned long nr_pages,
+			  enum zone_type target, int *zone_shift);
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h
index a4860bc9b73d..f848ee86a339 100644
--- a/include/linux/mfd/axp20x.h
+++ b/include/linux/mfd/axp20x.h
@@ -13,7 +13,7 @@
 
 #include <linux/regmap.h>
 
-enum {
+enum axp20x_variants {
 	AXP152_ID = 0,
 	AXP202_ID,
 	AXP209_ID,
@@ -532,35 +532,6 @@ struct axp20x_dev {
 	const struct regmap_irq_chip	*regmap_irq_chip;
 };
 
-#define BATTID_LEN				64
-#define OCV_CURVE_SIZE			32
-#define MAX_THERM_CURVE_SIZE	25
-#define PD_DEF_MIN_TEMP			0
-#define PD_DEF_MAX_TEMP			55
-
-struct axp20x_fg_pdata {
-	char battid[BATTID_LEN + 1];
-	int design_cap;
-	int min_volt;
-	int max_volt;
-	int max_temp;
-	int min_temp;
-	int cap1;
-	int cap0;
-	int rdc1;
-	int rdc0;
-	int ocv_curve[OCV_CURVE_SIZE];
-	int tcsz;
-	int thermistor_curve[MAX_THERM_CURVE_SIZE][2];
-};
-
-struct axp20x_chrg_pdata {
-	int max_cc;
-	int max_cv;
-	int def_cc;
-	int def_cv;
-};
-
 struct axp288_extcon_pdata {
 	/* GPIO pin control to switch D+/D- lines b/w PMIC and SOC */
 	struct gpio_desc *gpio_mux_cntl;
diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h
index 2b300b44f994..fba8fcb54f8c 100644
--- a/include/linux/mfd/lpc_ich.h
+++ b/include/linux/mfd/lpc_ich.h
@@ -20,6 +20,8 @@
 #ifndef LPC_ICH_H
 #define LPC_ICH_H
 
+#include <linux/platform_data/intel-spi.h>
+
 /* GPIO resources */
 #define ICH_RES_GPIO	0
 #define ICH_RES_GPE0	1
@@ -40,6 +42,7 @@ struct lpc_ich_info {
 	char name[32];
 	unsigned int iTCO_version;
 	unsigned int gpio_version;
+	enum intel_spi_type spi_type;
 	u8 use_gpio;
 };
 
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
index fba44abd05ba..a1520d88ebf3 100644
--- a/include/linux/mfd/tmio.h
+++ b/include/linux/mfd/tmio.h
@@ -94,10 +94,8 @@
  */
 #define TMIO_MMC_HAVE_CMD12_CTRL	(1 << 7)
 
-/*
- * Some controllers needs to set 1 on SDIO status reserved bits
- */
-#define TMIO_MMC_SDIO_STATUS_QUIRK	(1 << 8)
+/* Controller has some SDIO status bits which must be 1 */
+#define TMIO_MMC_SDIO_STATUS_SETBITS	(1 << 8)
 
 /*
  * Some controllers have a 32-bit wide data port register
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 257173e0095e..f541da68d1e7 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -35,6 +35,8 @@
 #define PHY_ID_KSZ886X		0x00221430
 #define PHY_ID_KSZ8863		0x00221435
 
+#define PHY_ID_KSZ8795		0x00221550
+
 /* struct phy_device dev_flags definitions */
 #define MICREL_PHY_50MHZ_CLK	0x00000001
 #define MICREL_PHY_FXEN		0x00000002
diff --git a/include/linux/mmc/boot.h b/include/linux/mmc/boot.h
deleted file mode 100644
index 23acc3baa07d..000000000000
--- a/include/linux/mmc/boot.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef LINUX_MMC_BOOT_H
-#define LINUX_MMC_BOOT_H
-
-enum { MMC_PROGRESS_ENTER, MMC_PROGRESS_INIT,
-       MMC_PROGRESS_LOAD, MMC_PROGRESS_DONE };
-
-#endif /* LINUX_MMC_BOOT_H */
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index 95d69d498296..77e61e0a216a 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -11,7 +11,6 @@
 #define LINUX_MMC_CARD_H
 
 #include <linux/device.h>
-#include <linux/mmc/core.h>
 #include <linux/mod_devicetable.h>
 
 struct mmc_cid {
@@ -84,6 +83,7 @@ struct mmc_ext_csd {
 	unsigned int		hpi_cmd;		/* cmd used as HPI */
 	bool			bkops;		/* background support bit */
 	bool			man_bkops_en;	/* manual bkops enable bit */
+	bool			auto_bkops_en;	/* auto bkops enable bit */
 	unsigned int            data_sector_size;       /* 512 bytes or 4KB */
 	unsigned int            data_tag_unit_size;     /* DATA TAG UNIT size */
 	unsigned int		boot_ro_lock;		/* ro lock support */
@@ -121,6 +121,9 @@ struct mmc_ext_csd {
 	u8			raw_pwr_cl_ddr_200_360;	/* 253 */
 	u8			raw_bkops_status;	/* 246 */
 	u8			raw_sectors[4];		/* 212 - 4 bytes */
+	u8			pre_eol_info;		/* 267 */
+	u8			device_life_time_est_typ_a;	/* 268 */
+	u8			device_life_time_est_typ_b;	/* 269 */
 
 	unsigned int            feature_support;
 #define MMC_DISCARD_FEATURE	BIT(0)                  /* CMD38 feature */
@@ -203,7 +206,6 @@ struct sdio_cis {
 };
 
 struct mmc_host;
-struct mmc_ios;
 struct sdio_func;
 struct sdio_func_tuple;
 
@@ -247,13 +249,6 @@ struct mmc_card {
 #define MMC_TYPE_SDIO		2		/* SDIO card */
 #define MMC_TYPE_SD_COMBO	3		/* SD combo (IO+mem) card */
 	unsigned int		state;		/* (our) card state */
-#define MMC_STATE_PRESENT	(1<<0)		/* present in sysfs */
-#define MMC_STATE_READONLY	(1<<1)		/* card is read-only */
-#define MMC_STATE_BLOCKADDR	(1<<2)		/* card uses block-addressing */
-#define MMC_CARD_SDXC		(1<<3)		/* card is SDXC */
-#define MMC_CARD_REMOVED	(1<<4)		/* card has been removed */
-#define MMC_STATE_DOING_BKOPS	(1<<5)		/* card is doing BKOPS */
-#define MMC_STATE_SUSPENDED	(1<<6)		/* card is suspended */
 	unsigned int		quirks; 	/* card quirks */
 #define MMC_QUIRK_LENIENT_FN0	(1<<0)		/* allow SDIO FN0 writes outside of the VS CCCR range */
 #define MMC_QUIRK_BLKSZ_FOR_BYTE_MODE (1<<1)	/* use func->cur_blksize */
@@ -272,7 +267,6 @@ struct mmc_card {
 #define MMC_QUIRK_TRIM_BROKEN	(1<<12)		/* Skip trim */
 #define MMC_QUIRK_BROKEN_HPI	(1<<13)		/* Disable broken HPI support */
 
-
 	unsigned int		erase_size;	/* erase size in sectors */
  	unsigned int		erase_shift;	/* if erase unit is power 2 */
  	unsigned int		pref_erase;	/* in sectors */
@@ -308,245 +302,13 @@ struct mmc_card {
 	unsigned int    nr_parts;
 };
 
-/*
- * This function fill contents in mmc_part.
- */
-static inline void mmc_part_add(struct mmc_card *card, unsigned int size,
-			unsigned int part_cfg, char *name, int idx, bool ro,
-			int area_type)
-{
-	card->part[card->nr_parts].size = size;
-	card->part[card->nr_parts].part_cfg = part_cfg;
-	sprintf(card->part[card->nr_parts].name, name, idx);
-	card->part[card->nr_parts].force_ro = ro;
-	card->part[card->nr_parts].area_type = area_type;
-	card->nr_parts++;
-}
-
 static inline bool mmc_large_sector(struct mmc_card *card)
 {
 	return card->ext_csd.data_sector_size == 4096;
 }
 
-/*
- *  The world is not perfect and supplies us with broken mmc/sdio devices.
- *  For at least some of these bugs we need a work-around.
- */
-
-struct mmc_fixup {
-	/* CID-specific fields. */
-	const char *name;
-
-	/* Valid revision range */
-	u64 rev_start, rev_end;
-
-	unsigned int manfid;
-	unsigned short oemid;
-
-	/* SDIO-specfic fields. You can use SDIO_ANY_ID here of course */
-	u16 cis_vendor, cis_device;
-
-	/* for MMC cards */
-	unsigned int ext_csd_rev;
-
-	void (*vendor_fixup)(struct mmc_card *card, int data);
-	int data;
-};
-
-#define CID_MANFID_ANY (-1u)
-#define CID_OEMID_ANY ((unsigned short) -1)
-#define CID_NAME_ANY (NULL)
-
-#define EXT_CSD_REV_ANY (-1u)
-
-#define CID_MANFID_SANDISK      0x2
-#define CID_MANFID_TOSHIBA      0x11
-#define CID_MANFID_MICRON       0x13
-#define CID_MANFID_SAMSUNG      0x15
-#define CID_MANFID_KINGSTON     0x70
-#define CID_MANFID_HYNIX	0x90
-
-#define END_FIXUP { NULL }
-
-#define _FIXUP_EXT(_name, _manfid, _oemid, _rev_start, _rev_end,	\
-		   _cis_vendor, _cis_device,				\
-		   _fixup, _data, _ext_csd_rev)				\
-	{						   \
-		.name = (_name),			   \
-		.manfid = (_manfid),			   \
-		.oemid = (_oemid),			   \
-		.rev_start = (_rev_start),		   \
-		.rev_end = (_rev_end),			   \
-		.cis_vendor = (_cis_vendor),		   \
-		.cis_device = (_cis_device),		   \
-		.vendor_fixup = (_fixup),		   \
-		.data = (_data),			   \
-		.ext_csd_rev = (_ext_csd_rev),		   \
-	 }
-
-#define MMC_FIXUP_REV(_name, _manfid, _oemid, _rev_start, _rev_end,	\
-		      _fixup, _data, _ext_csd_rev)			\
-	_FIXUP_EXT(_name, _manfid,					\
-		   _oemid, _rev_start, _rev_end,			\
-		   SDIO_ANY_ID, SDIO_ANY_ID,				\
-		   _fixup, _data, _ext_csd_rev)				\
-
-#define MMC_FIXUP(_name, _manfid, _oemid, _fixup, _data) \
-	MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data,	\
-		      EXT_CSD_REV_ANY)
-
-#define MMC_FIXUP_EXT_CSD_REV(_name, _manfid, _oemid, _fixup, _data,	\
-			      _ext_csd_rev)				\
-	MMC_FIXUP_REV(_name, _manfid, _oemid, 0, -1ull, _fixup, _data,	\
-		      _ext_csd_rev)
-
-#define SDIO_FIXUP(_vendor, _device, _fixup, _data)			\
-	_FIXUP_EXT(CID_NAME_ANY, CID_MANFID_ANY,			\
-		    CID_OEMID_ANY, 0, -1ull,				\
-		   _vendor, _device,					\
-		   _fixup, _data, EXT_CSD_REV_ANY)			\
-
-#define cid_rev(hwrev, fwrev, year, month)	\
-	(((u64) hwrev) << 40 |                  \
-	 ((u64) fwrev) << 32 |                  \
-	 ((u64) year) << 16 |                   \
-	 ((u64) month))
-
-#define cid_rev_card(card)		  \
-	cid_rev(card->cid.hwrev,	  \
-		    card->cid.fwrev,      \
-		    card->cid.year,	  \
-		    card->cid.month)
-
-/*
- * Unconditionally quirk add/remove.
- */
-
-static inline void __maybe_unused add_quirk(struct mmc_card *card, int data)
-{
-	card->quirks |= data;
-}
-
-static inline void __maybe_unused remove_quirk(struct mmc_card *card, int data)
-{
-	card->quirks &= ~data;
-}
-
 #define mmc_card_mmc(c)		((c)->type == MMC_TYPE_MMC)
 #define mmc_card_sd(c)		((c)->type == MMC_TYPE_SD)
 #define mmc_card_sdio(c)	((c)->type == MMC_TYPE_SDIO)
 
-#define mmc_card_present(c)	((c)->state & MMC_STATE_PRESENT)
-#define mmc_card_readonly(c)	((c)->state & MMC_STATE_READONLY)
-#define mmc_card_blockaddr(c)	((c)->state & MMC_STATE_BLOCKADDR)
-#define mmc_card_ext_capacity(c) ((c)->state & MMC_CARD_SDXC)
-#define mmc_card_removed(c)	((c) && ((c)->state & MMC_CARD_REMOVED))
-#define mmc_card_doing_bkops(c)	((c)->state & MMC_STATE_DOING_BKOPS)
-#define mmc_card_suspended(c)	((c)->state & MMC_STATE_SUSPENDED)
-
-#define mmc_card_set_present(c)	((c)->state |= MMC_STATE_PRESENT)
-#define mmc_card_set_readonly(c) ((c)->state |= MMC_STATE_READONLY)
-#define mmc_card_set_blockaddr(c) ((c)->state |= MMC_STATE_BLOCKADDR)
-#define mmc_card_set_ext_capacity(c) ((c)->state |= MMC_CARD_SDXC)
-#define mmc_card_set_removed(c) ((c)->state |= MMC_CARD_REMOVED)
-#define mmc_card_set_doing_bkops(c)	((c)->state |= MMC_STATE_DOING_BKOPS)
-#define mmc_card_clr_doing_bkops(c)	((c)->state &= ~MMC_STATE_DOING_BKOPS)
-#define mmc_card_set_suspended(c) ((c)->state |= MMC_STATE_SUSPENDED)
-#define mmc_card_clr_suspended(c) ((c)->state &= ~MMC_STATE_SUSPENDED)
-
-/*
- * Quirk add/remove for MMC products.
- */
-
-static inline void __maybe_unused add_quirk_mmc(struct mmc_card *card, int data)
-{
-	if (mmc_card_mmc(card))
-		card->quirks |= data;
-}
-
-static inline void __maybe_unused remove_quirk_mmc(struct mmc_card *card,
-						   int data)
-{
-	if (mmc_card_mmc(card))
-		card->quirks &= ~data;
-}
-
-/*
- * Quirk add/remove for SD products.
- */
-
-static inline void __maybe_unused add_quirk_sd(struct mmc_card *card, int data)
-{
-	if (mmc_card_sd(card))
-		card->quirks |= data;
-}
-
-static inline void __maybe_unused remove_quirk_sd(struct mmc_card *card,
-						   int data)
-{
-	if (mmc_card_sd(card))
-		card->quirks &= ~data;
-}
-
-static inline int mmc_card_lenient_fn0(const struct mmc_card *c)
-{
-	return c->quirks & MMC_QUIRK_LENIENT_FN0;
-}
-
-static inline int mmc_blksz_for_byte_mode(const struct mmc_card *c)
-{
-	return c->quirks & MMC_QUIRK_BLKSZ_FOR_BYTE_MODE;
-}
-
-static inline int mmc_card_disable_cd(const struct mmc_card *c)
-{
-	return c->quirks & MMC_QUIRK_DISABLE_CD;
-}
-
-static inline int mmc_card_nonstd_func_interface(const struct mmc_card *c)
-{
-	return c->quirks & MMC_QUIRK_NONSTD_FUNC_IF;
-}
-
-static inline int mmc_card_broken_byte_mode_512(const struct mmc_card *c)
-{
-	return c->quirks & MMC_QUIRK_BROKEN_BYTE_MODE_512;
-}
-
-static inline int mmc_card_long_read_time(const struct mmc_card *c)
-{
-	return c->quirks & MMC_QUIRK_LONG_READ_TIME;
-}
-
-static inline int mmc_card_broken_irq_polling(const struct mmc_card *c)
-{
-	return c->quirks & MMC_QUIRK_BROKEN_IRQ_POLLING;
-}
-
-static inline int mmc_card_broken_hpi(const struct mmc_card *c)
-{
-	return c->quirks & MMC_QUIRK_BROKEN_HPI;
-}
-
-#define mmc_card_name(c)	((c)->cid.prod_name)
-#define mmc_card_id(c)		(dev_name(&(c)->dev))
-
-#define mmc_dev_to_card(d)	container_of(d, struct mmc_card, dev)
-
-/*
- * MMC device driver (e.g., Flash card, I/O card...)
- */
-struct mmc_driver {
-	struct device_driver drv;
-	int (*probe)(struct mmc_card *);
-	void (*remove)(struct mmc_card *);
-	void (*shutdown)(struct mmc_card *);
-};
-
-extern int mmc_register_driver(struct mmc_driver *);
-extern void mmc_unregister_driver(struct mmc_driver *);
-
-extern void mmc_fixup_device(struct mmc_card *card,
-			     const struct mmc_fixup *table);
-
 #endif /* LINUX_MMC_CARD_H */
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index e33cc748dcfe..a0c63ea28796 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -8,10 +8,9 @@
 #ifndef LINUX_MMC_CORE_H
 #define LINUX_MMC_CORE_H
 
-#include <linux/interrupt.h>
 #include <linux/completion.h>
+#include <linux/types.h>
 
-struct request;
 struct mmc_data;
 struct mmc_request;
 
@@ -159,79 +158,14 @@ struct mmc_request {
 struct mmc_card;
 struct mmc_async_req;
 
-extern int mmc_stop_bkops(struct mmc_card *);
-extern int mmc_read_bkops_status(struct mmc_card *);
-extern struct mmc_async_req *mmc_start_req(struct mmc_host *,
-					   struct mmc_async_req *,
-					   enum mmc_blk_status *);
-extern int mmc_interrupt_hpi(struct mmc_card *);
-extern void mmc_wait_for_req(struct mmc_host *, struct mmc_request *);
-extern void mmc_wait_for_req_done(struct mmc_host *host,
-				  struct mmc_request *mrq);
-extern bool mmc_is_req_done(struct mmc_host *host, struct mmc_request *mrq);
-extern int mmc_wait_for_cmd(struct mmc_host *, struct mmc_command *, int);
-extern int mmc_app_cmd(struct mmc_host *, struct mmc_card *);
-extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *,
-	struct mmc_command *, int);
-extern void mmc_start_bkops(struct mmc_card *card, bool from_exception);
-extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int);
-extern int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error);
-extern int mmc_abort_tuning(struct mmc_host *host, u32 opcode);
-extern int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd);
-
-#define MMC_ERASE_ARG		0x00000000
-#define MMC_SECURE_ERASE_ARG	0x80000000
-#define MMC_TRIM_ARG		0x00000001
-#define MMC_DISCARD_ARG		0x00000003
-#define MMC_SECURE_TRIM1_ARG	0x80000001
-#define MMC_SECURE_TRIM2_ARG	0x80008000
-
-#define MMC_SECURE_ARGS		0x80000000
-#define MMC_TRIM_ARGS		0x00008001
-
-extern int mmc_erase(struct mmc_card *card, unsigned int from, unsigned int nr,
-		     unsigned int arg);
-extern int mmc_can_erase(struct mmc_card *card);
-extern int mmc_can_trim(struct mmc_card *card);
-extern int mmc_can_discard(struct mmc_card *card);
-extern int mmc_can_sanitize(struct mmc_card *card);
-extern int mmc_can_secure_erase_trim(struct mmc_card *card);
-extern int mmc_erase_group_aligned(struct mmc_card *card, unsigned int from,
-				   unsigned int nr);
-extern unsigned int mmc_calc_max_discard(struct mmc_card *card);
-
-extern int mmc_set_blocklen(struct mmc_card *card, unsigned int blocklen);
-extern int mmc_set_blockcount(struct mmc_card *card, unsigned int blockcount,
-			      bool is_rel_write);
-extern int mmc_hw_reset(struct mmc_host *host);
-extern int mmc_can_reset(struct mmc_card *card);
-
-extern void mmc_set_data_timeout(struct mmc_data *, const struct mmc_card *);
-extern unsigned int mmc_align_data_size(struct mmc_card *, unsigned int);
-
-extern int __mmc_claim_host(struct mmc_host *host, atomic_t *abort);
-extern void mmc_release_host(struct mmc_host *host);
-
-extern void mmc_get_card(struct mmc_card *card);
-extern void mmc_put_card(struct mmc_card *card);
-
-extern int mmc_flush_cache(struct mmc_card *);
-
-extern int mmc_detect_card_removed(struct mmc_host *host);
-
-/**
- *	mmc_claim_host - exclusively claim a host
- *	@host: mmc host to claim
- *
- *	Claim a host for a set of operations.
- */
-static inline void mmc_claim_host(struct mmc_host *host)
-{
-	__mmc_claim_host(host, NULL);
-}
-
-struct device_node;
-extern u32 mmc_vddrange_to_ocrmask(int vdd_min, int vdd_max);
-extern int mmc_of_parse_voltage(struct device_node *np, u32 *mask);
+struct mmc_async_req *mmc_start_areq(struct mmc_host *host,
+				struct mmc_async_req *areq,
+				enum mmc_blk_status *ret_stat);
+void mmc_wait_for_req(struct mmc_host *host, struct mmc_request *mrq);
+int mmc_wait_for_cmd(struct mmc_host *host, struct mmc_command *cmd,
+		int retries);
+
+int mmc_hw_reset(struct mmc_host *host);
+void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card);
 
 #endif /* LINUX_MMC_CORE_H */
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
deleted file mode 100644
index 15db6f83f53f..000000000000
--- a/include/linux/mmc/dw_mmc.h
+++ /dev/null
@@ -1,274 +0,0 @@
-/*
- * Synopsys DesignWare Multimedia Card Interface driver
- *  (Based on NXP driver for lpc 31xx)
- *
- * Copyright (C) 2009 NXP Semiconductors
- * Copyright (C) 2009, 2010 Imagination Technologies Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef LINUX_MMC_DW_MMC_H
-#define LINUX_MMC_DW_MMC_H
-
-#include <linux/scatterlist.h>
-#include <linux/mmc/core.h>
-#include <linux/dmaengine.h>
-#include <linux/reset.h>
-
-#define MAX_MCI_SLOTS	2
-
-enum dw_mci_state {
-	STATE_IDLE = 0,
-	STATE_SENDING_CMD,
-	STATE_SENDING_DATA,
-	STATE_DATA_BUSY,
-	STATE_SENDING_STOP,
-	STATE_DATA_ERROR,
-	STATE_SENDING_CMD11,
-	STATE_WAITING_CMD11_DONE,
-};
-
-enum {
-	EVENT_CMD_COMPLETE = 0,
-	EVENT_XFER_COMPLETE,
-	EVENT_DATA_COMPLETE,
-	EVENT_DATA_ERROR,
-};
-
-enum dw_mci_cookie {
-	COOKIE_UNMAPPED,
-	COOKIE_PRE_MAPPED,	/* mapped by pre_req() of dwmmc */
-	COOKIE_MAPPED,		/* mapped by prepare_data() of dwmmc */
-};
-
-struct mmc_data;
-
-enum {
-	TRANS_MODE_PIO = 0,
-	TRANS_MODE_IDMAC,
-	TRANS_MODE_EDMAC
-};
-
-struct dw_mci_dma_slave {
-	struct dma_chan *ch;
-	enum dma_transfer_direction direction;
-};
-
-/**
- * struct dw_mci - MMC controller state shared between all slots
- * @lock: Spinlock protecting the queue and associated data.
- * @irq_lock: Spinlock protecting the INTMASK setting.
- * @regs: Pointer to MMIO registers.
- * @fifo_reg: Pointer to MMIO registers for data FIFO
- * @sg: Scatterlist entry currently being processed by PIO code, if any.
- * @sg_miter: PIO mapping scatterlist iterator.
- * @cur_slot: The slot which is currently using the controller.
- * @mrq: The request currently being processed on @cur_slot,
- *	or NULL if the controller is idle.
- * @cmd: The command currently being sent to the card, or NULL.
- * @data: The data currently being transferred, or NULL if no data
- *	transfer is in progress.
- * @stop_abort: The command currently prepared for stoping transfer.
- * @prev_blksz: The former transfer blksz record.
- * @timing: Record of current ios timing.
- * @use_dma: Whether DMA channel is initialized or not.
- * @using_dma: Whether DMA is in use for the current transfer.
- * @dma_64bit_address: Whether DMA supports 64-bit address mode or not.
- * @sg_dma: Bus address of DMA buffer.
- * @sg_cpu: Virtual address of DMA buffer.
- * @dma_ops: Pointer to platform-specific DMA callbacks.
- * @cmd_status: Snapshot of SR taken upon completion of the current
- * @ring_size: Buffer size for idma descriptors.
- *	command. Only valid when EVENT_CMD_COMPLETE is pending.
- * @dms: structure of slave-dma private data.
- * @phy_regs: physical address of controller's register map
- * @data_status: Snapshot of SR taken upon completion of the current
- *	data transfer. Only valid when EVENT_DATA_COMPLETE or
- *	EVENT_DATA_ERROR is pending.
- * @stop_cmdr: Value to be loaded into CMDR when the stop command is
- *	to be sent.
- * @dir_status: Direction of current transfer.
- * @tasklet: Tasklet running the request state machine.
- * @pending_events: Bitmask of events flagged by the interrupt handler
- *	to be processed by the tasklet.
- * @completed_events: Bitmask of events which the state machine has
- *	processed.
- * @state: Tasklet state.
- * @queue: List of slots waiting for access to the controller.
- * @bus_hz: The rate of @mck in Hz. This forms the basis for MMC bus
- *	rate and timeout calculations.
- * @current_speed: Configured rate of the controller.
- * @num_slots: Number of slots available.
- * @fifoth_val: The value of FIFOTH register.
- * @verid: Denote Version ID.
- * @dev: Device associated with the MMC controller.
- * @pdata: Platform data associated with the MMC controller.
- * @drv_data: Driver specific data for identified variant of the controller
- * @priv: Implementation defined private data.
- * @biu_clk: Pointer to bus interface unit clock instance.
- * @ciu_clk: Pointer to card interface unit clock instance.
- * @slot: Slots sharing this MMC controller.
- * @fifo_depth: depth of FIFO.
- * @data_shift: log2 of FIFO item size.
- * @part_buf_start: Start index in part_buf.
- * @part_buf_count: Bytes of partial data in part_buf.
- * @part_buf: Simple buffer for partial fifo reads/writes.
- * @push_data: Pointer to FIFO push function.
- * @pull_data: Pointer to FIFO pull function.
- * @vqmmc_enabled: Status of vqmmc, should be true or false.
- * @irq_flags: The flags to be passed to request_irq.
- * @irq: The irq value to be passed to request_irq.
- * @sdio_id0: Number of slot0 in the SDIO interrupt registers.
- * @cmd11_timer: Timer for SD3.0 voltage switch over scheme.
- * @dto_timer: Timer for broken data transfer over scheme.
- *
- * Locking
- * =======
- *
- * @lock is a softirq-safe spinlock protecting @queue as well as
- * @cur_slot, @mrq and @state. These must always be updated
- * at the same time while holding @lock.
- *
- * @irq_lock is an irq-safe spinlock protecting the INTMASK register
- * to allow the interrupt handler to modify it directly.  Held for only long
- * enough to read-modify-write INTMASK and no other locks are grabbed when
- * holding this one.
- *
- * The @mrq field of struct dw_mci_slot is also protected by @lock,
- * and must always be written at the same time as the slot is added to
- * @queue.
- *
- * @pending_events and @completed_events are accessed using atomic bit
- * operations, so they don't need any locking.
- *
- * None of the fields touched by the interrupt handler need any
- * locking. However, ordering is important: Before EVENT_DATA_ERROR or
- * EVENT_DATA_COMPLETE is set in @pending_events, all data-related
- * interrupts must be disabled and @data_status updated with a
- * snapshot of SR. Similarly, before EVENT_CMD_COMPLETE is set, the
- * CMDRDY interrupt must be disabled and @cmd_status updated with a
- * snapshot of SR, and before EVENT_XFER_COMPLETE can be set, the
- * bytes_xfered field of @data must be written. This is ensured by
- * using barriers.
- */
-struct dw_mci {
-	spinlock_t		lock;
-	spinlock_t		irq_lock;
-	void __iomem		*regs;
-	void __iomem		*fifo_reg;
-
-	struct scatterlist	*sg;
-	struct sg_mapping_iter	sg_miter;
-
-	struct dw_mci_slot	*cur_slot;
-	struct mmc_request	*mrq;
-	struct mmc_command	*cmd;
-	struct mmc_data		*data;
-	struct mmc_command	stop_abort;
-	unsigned int		prev_blksz;
-	unsigned char		timing;
-
-	/* DMA interface members*/
-	int			use_dma;
-	int			using_dma;
-	int			dma_64bit_address;
-
-	dma_addr_t		sg_dma;
-	void			*sg_cpu;
-	const struct dw_mci_dma_ops	*dma_ops;
-	/* For idmac */
-	unsigned int		ring_size;
-
-	/* For edmac */
-	struct dw_mci_dma_slave *dms;
-	/* Registers's physical base address */
-	resource_size_t		phy_regs;
-
-	u32			cmd_status;
-	u32			data_status;
-	u32			stop_cmdr;
-	u32			dir_status;
-	struct tasklet_struct	tasklet;
-	unsigned long		pending_events;
-	unsigned long		completed_events;
-	enum dw_mci_state	state;
-	struct list_head	queue;
-
-	u32			bus_hz;
-	u32			current_speed;
-	u32			num_slots;
-	u32			fifoth_val;
-	u16			verid;
-	struct device		*dev;
-	struct dw_mci_board	*pdata;
-	const struct dw_mci_drv_data	*drv_data;
-	void			*priv;
-	struct clk		*biu_clk;
-	struct clk		*ciu_clk;
-	struct dw_mci_slot	*slot[MAX_MCI_SLOTS];
-
-	/* FIFO push and pull */
-	int			fifo_depth;
-	int			data_shift;
-	u8			part_buf_start;
-	u8			part_buf_count;
-	union {
-		u16		part_buf16;
-		u32		part_buf32;
-		u64		part_buf;
-	};
-	void (*push_data)(struct dw_mci *host, void *buf, int cnt);
-	void (*pull_data)(struct dw_mci *host, void *buf, int cnt);
-
-	bool			vqmmc_enabled;
-	unsigned long		irq_flags; /* IRQ flags */
-	int			irq;
-
-	int			sdio_id0;
-
-	struct timer_list       cmd11_timer;
-	struct timer_list       dto_timer;
-};
-
-/* DMA ops for Internal/External DMAC interface */
-struct dw_mci_dma_ops {
-	/* DMA Ops */
-	int (*init)(struct dw_mci *host);
-	int (*start)(struct dw_mci *host, unsigned int sg_len);
-	void (*complete)(void *host);
-	void (*stop)(struct dw_mci *host);
-	void (*cleanup)(struct dw_mci *host);
-	void (*exit)(struct dw_mci *host);
-};
-
-struct dma_pdata;
-
-/* Board platform data */
-struct dw_mci_board {
-	u32 num_slots;
-
-	unsigned int bus_hz; /* Clock speed at the cclk_in pad */
-
-	u32 caps;	/* Capabilities */
-	u32 caps2;	/* More capabilities */
-	u32 pm_caps;	/* PM capabilities */
-	/*
-	 * Override fifo depth. If 0, autodetect it from the FIFOTH register,
-	 * but note that this may not be reliable after a bootloader has used
-	 * it.
-	 */
-	unsigned int fifo_depth;
-
-	/* delay in mS before detecting cards after interrupt */
-	u32 detect_delay_ms;
-
-	struct reset_control *rstc;
-	struct dw_mci_dma_ops *dma_ops;
-	struct dma_pdata *data;
-};
-
-#endif /* LINUX_MMC_DW_MMC_H */
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 8bc884121465..83f1c4a9f03b 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -10,16 +10,12 @@
 #ifndef LINUX_MMC_HOST_H
 #define LINUX_MMC_HOST_H
 
-#include <linux/leds.h>
-#include <linux/mutex.h>
-#include <linux/timer.h>
 #include <linux/sched.h>
 #include <linux/device.h>
 #include <linux/fault-inject.h>
 
 #include <linux/mmc/core.h>
 #include <linux/mmc/card.h>
-#include <linux/mmc/mmc.h>
 #include <linux/mmc/pm.h>
 
 struct mmc_ios {
@@ -82,6 +78,8 @@ struct mmc_ios {
 	bool enhanced_strobe;			/* hs400es selection */
 };
 
+struct mmc_host;
+
 struct mmc_host_ops {
 	/*
 	 * It is optional for the host to implement pre_req and post_req in
@@ -162,9 +160,6 @@ struct mmc_host_ops {
 				  unsigned int direction, int blk_size);
 };
 
-struct mmc_card;
-struct device;
-
 struct mmc_async_req {
 	/* active mmc request */
 	struct mmc_request	*mrq;
@@ -264,17 +259,16 @@ struct mmc_host {
 #define MMC_CAP_NONREMOVABLE	(1 << 8)	/* Nonremovable e.g. eMMC */
 #define MMC_CAP_WAIT_WHILE_BUSY	(1 << 9)	/* Waits while card is busy */
 #define MMC_CAP_ERASE		(1 << 10)	/* Allow erase/trim commands */
-#define MMC_CAP_1_8V_DDR	(1 << 11)	/* can support */
-						/* DDR mode at 1.8V */
-#define MMC_CAP_1_2V_DDR	(1 << 12)	/* can support */
-						/* DDR mode at 1.2V */
-#define MMC_CAP_POWER_OFF_CARD	(1 << 13)	/* Can power off after boot */
-#define MMC_CAP_BUS_WIDTH_TEST	(1 << 14)	/* CMD14/CMD19 bus width ok */
-#define MMC_CAP_UHS_SDR12	(1 << 15)	/* Host supports UHS SDR12 mode */
-#define MMC_CAP_UHS_SDR25	(1 << 16)	/* Host supports UHS SDR25 mode */
-#define MMC_CAP_UHS_SDR50	(1 << 17)	/* Host supports UHS SDR50 mode */
-#define MMC_CAP_UHS_SDR104	(1 << 18)	/* Host supports UHS SDR104 mode */
-#define MMC_CAP_UHS_DDR50	(1 << 19)	/* Host supports UHS DDR50 mode */
+#define MMC_CAP_3_3V_DDR	(1 << 11)	/* Host supports eMMC DDR 3.3V */
+#define MMC_CAP_1_8V_DDR	(1 << 12)	/* Host supports eMMC DDR 1.8V */
+#define MMC_CAP_1_2V_DDR	(1 << 13)	/* Host supports eMMC DDR 1.2V */
+#define MMC_CAP_POWER_OFF_CARD	(1 << 14)	/* Can power off after boot */
+#define MMC_CAP_BUS_WIDTH_TEST	(1 << 15)	/* CMD14/CMD19 bus width ok */
+#define MMC_CAP_UHS_SDR12	(1 << 16)	/* Host supports UHS SDR12 mode */
+#define MMC_CAP_UHS_SDR25	(1 << 17)	/* Host supports UHS SDR25 mode */
+#define MMC_CAP_UHS_SDR50	(1 << 18)	/* Host supports UHS SDR50 mode */
+#define MMC_CAP_UHS_SDR104	(1 << 19)	/* Host supports UHS SDR104 mode */
+#define MMC_CAP_UHS_DDR50	(1 << 20)	/* Host supports UHS DDR50 mode */
 #define MMC_CAP_DRIVER_TYPE_A	(1 << 23)	/* Host supports Driver Type A */
 #define MMC_CAP_DRIVER_TYPE_C	(1 << 24)	/* Host supports Driver Type C */
 #define MMC_CAP_DRIVER_TYPE_D	(1 << 25)	/* Host supports Driver Type D */
@@ -397,11 +391,14 @@ struct mmc_host {
 	unsigned long		private[0] ____cacheline_aligned;
 };
 
+struct device_node;
+
 struct mmc_host *mmc_alloc_host(int extra, struct device *);
 int mmc_add_host(struct mmc_host *);
 void mmc_remove_host(struct mmc_host *);
 void mmc_free_host(struct mmc_host *);
 int mmc_of_parse(struct mmc_host *host);
+int mmc_of_parse_voltage(struct device_node *np, u32 *mask);
 
 static inline void *mmc_priv(struct mmc_host *host)
 {
@@ -457,6 +454,7 @@ static inline int mmc_regulator_set_vqmmc(struct mmc_host *mmc,
 }
 #endif
 
+u32 mmc_vddrange_to_ocrmask(int vdd_min, int vdd_max);
 int mmc_regulator_get_supply(struct mmc_host *mmc);
 
 static inline int mmc_card_is_removable(struct mmc_host *host)
@@ -474,56 +472,20 @@ static inline int mmc_card_wake_sdio_irq(struct mmc_host *host)
 	return host->pm_flags & MMC_PM_WAKE_SDIO_IRQ;
 }
 
-static inline int mmc_host_cmd23(struct mmc_host *host)
-{
-	return host->caps & MMC_CAP_CMD23;
-}
-
-static inline int mmc_boot_partition_access(struct mmc_host *host)
-{
-	return !(host->caps2 & MMC_CAP2_BOOTPART_NOACC);
-}
-
-static inline int mmc_host_uhs(struct mmc_host *host)
-{
-	return host->caps &
-		(MMC_CAP_UHS_SDR12 | MMC_CAP_UHS_SDR25 |
-		 MMC_CAP_UHS_SDR50 | MMC_CAP_UHS_SDR104 |
-		 MMC_CAP_UHS_DDR50);
-}
-
+/* TODO: Move to private header */
 static inline int mmc_card_hs(struct mmc_card *card)
 {
 	return card->host->ios.timing == MMC_TIMING_SD_HS ||
 		card->host->ios.timing == MMC_TIMING_MMC_HS;
 }
 
+/* TODO: Move to private header */
 static inline int mmc_card_uhs(struct mmc_card *card)
 {
 	return card->host->ios.timing >= MMC_TIMING_UHS_SDR12 &&
 		card->host->ios.timing <= MMC_TIMING_UHS_DDR50;
 }
 
-static inline bool mmc_card_hs200(struct mmc_card *card)
-{
-	return card->host->ios.timing == MMC_TIMING_MMC_HS200;
-}
-
-static inline bool mmc_card_ddr52(struct mmc_card *card)
-{
-	return card->host->ios.timing == MMC_TIMING_MMC_DDR52;
-}
-
-static inline bool mmc_card_hs400(struct mmc_card *card)
-{
-	return card->host->ios.timing == MMC_TIMING_MMC_HS400;
-}
-
-static inline bool mmc_card_hs400es(struct mmc_card *card)
-{
-	return card->host->ios.enhanced_strobe;
-}
-
 void mmc_retune_timer_stop(struct mmc_host *host);
 
 static inline void mmc_retune_needed(struct mmc_host *host)
@@ -532,18 +494,12 @@ static inline void mmc_retune_needed(struct mmc_host *host)
 		host->need_retune = 1;
 }
 
-static inline void mmc_retune_recheck(struct mmc_host *host)
-{
-	if (host->hold_retune <= 1)
-		host->retune_now = 1;
-}
-
 static inline bool mmc_can_retune(struct mmc_host *host)
 {
 	return host->can_retune == 1;
 }
 
-void mmc_retune_pause(struct mmc_host *host);
-void mmc_retune_unpause(struct mmc_host *host);
+int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error);
+int mmc_abort_tuning(struct mmc_host *host, u32 opcode);
 
 #endif /* LINUX_MMC_HOST_H */
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 672730acc705..3ffc27aaeeaf 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -24,6 +24,8 @@
 #ifndef LINUX_MMC_MMC_H
 #define LINUX_MMC_MMC_H
 
+#include <linux/types.h>
+
 /* Standard MMC commands (4.1)           type  argument     response */
    /* class 1 */
 #define MMC_GO_IDLE_STATE         0   /* bc                          */
@@ -182,50 +184,6 @@ static inline bool mmc_op_multi(u32 opcode)
 #define R2_SPI_OUT_OF_RANGE	(1 << 15)	/* or CSD overwrite */
 #define R2_SPI_CSD_OVERWRITE	R2_SPI_OUT_OF_RANGE
 
-/* These are unpacked versions of the actual responses */
-
-struct _mmc_csd {
-	u8  csd_structure;
-	u8  spec_vers;
-	u8  taac;
-	u8  nsac;
-	u8  tran_speed;
-	u16 ccc;
-	u8  read_bl_len;
-	u8  read_bl_partial;
-	u8  write_blk_misalign;
-	u8  read_blk_misalign;
-	u8  dsr_imp;
-	u16 c_size;
-	u8  vdd_r_curr_min;
-	u8  vdd_r_curr_max;
-	u8  vdd_w_curr_min;
-	u8  vdd_w_curr_max;
-	u8  c_size_mult;
-	union {
-		struct { /* MMC system specification version 3.1 */
-			u8  erase_grp_size;
-			u8  erase_grp_mult;
-		} v31;
-		struct { /* MMC system specification version 2.2 */
-			u8  sector_size;
-			u8  erase_grp_size;
-		} v22;
-	} erase;
-	u8  wp_grp_size;
-	u8  wp_grp_enable;
-	u8  default_ecc;
-	u8  r2w_factor;
-	u8  write_bl_len;
-	u8  write_bl_partial;
-	u8  file_format_grp;
-	u8  copy;
-	u8  perm_write_protect;
-	u8  tmp_write_protect;
-	u8  file_format;
-	u8  ecc;
-};
-
 /*
  * OCR bits are mostly in host.h
  */
@@ -339,6 +297,9 @@ struct _mmc_csd {
 #define EXT_CSD_CACHE_SIZE		249	/* RO, 4 bytes */
 #define EXT_CSD_PWR_CL_DDR_200_360	253	/* RO */
 #define EXT_CSD_FIRMWARE_VERSION	254	/* RO, 8 bytes */
+#define EXT_CSD_PRE_EOL_INFO		267	/* RO */
+#define EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_A	268	/* RO */
+#define EXT_CSD_DEVICE_LIFE_TIME_EST_TYP_B	269	/* RO */
 #define EXT_CSD_CMDQ_DEPTH		307	/* RO */
 #define EXT_CSD_CMDQ_SUPPORT		308	/* RO */
 #define EXT_CSD_SUPPORTED_MODE		493	/* RO */
@@ -446,6 +407,7 @@ struct _mmc_csd {
  * BKOPS modes
  */
 #define EXT_CSD_MANUAL_BKOPS_MASK	0x01
+#define EXT_CSD_AUTO_BKOPS_MASK		0x02
 
 /*
  * Command Queue
@@ -457,12 +419,23 @@ struct _mmc_csd {
 /*
  * MMC_SWITCH access modes
  */
-
 #define MMC_SWITCH_MODE_CMD_SET		0x00	/* Change the command set */
 #define MMC_SWITCH_MODE_SET_BITS	0x01	/* Set bits which are 1 in value */
 #define MMC_SWITCH_MODE_CLEAR_BITS	0x02	/* Clear bits which are 1 in value */
 #define MMC_SWITCH_MODE_WRITE_BYTE	0x03	/* Set target to value */
 
+/*
+ * Erase/trim/discard
+ */
+#define MMC_ERASE_ARG			0x00000000
+#define MMC_SECURE_ERASE_ARG		0x80000000
+#define MMC_TRIM_ARG			0x00000001
+#define MMC_DISCARD_ARG			0x00000003
+#define MMC_SECURE_TRIM1_ARG		0x80000001
+#define MMC_SECURE_TRIM2_ARG		0x80008000
+#define MMC_SECURE_ARGS			0x80000000
+#define MMC_TRIM_ARGS			0x00008001
+
 #define mmc_driver_type_mask(n)		(1 << (n))
 
 #endif /* LINUX_MMC_MMC_H */
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index d43ef96bf075..46794a7a531c 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -51,6 +51,7 @@
 #define SDIO_DEVICE_ID_MARVELL_LIBERTAS		0x9103
 #define SDIO_DEVICE_ID_MARVELL_8688WLAN		0x9104
 #define SDIO_DEVICE_ID_MARVELL_8688BT		0x9105
+#define SDIO_DEVICE_ID_MARVELL_8797_F0		0x9128
 
 #define SDIO_VENDOR_ID_SIANO			0x039a
 #define SDIO_DEVICE_ID_SIANO_NOVA_B0		0x0201
@@ -60,4 +61,10 @@
 #define SDIO_DEVICE_ID_SIANO_NOVA_A0		0x1100
 #define SDIO_DEVICE_ID_SIANO_STELLAR 		0x5347
 
+#define SDIO_VENDOR_ID_TI			0x0097
+#define SDIO_DEVICE_ID_TI_WL1271		0x4076
+
+#define SDIO_VENDOR_ID_STE			0x0020
+#define SDIO_DEVICE_ID_STE_CW1200		0x2280
+
 #endif /* LINUX_MMC_SDIO_IDS_H */
diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h
index ccd8fb2cad52..a7baa29484c3 100644
--- a/include/linux/mmc/sh_mmcif.h
+++ b/include/linux/mmc/sh_mmcif.h
@@ -32,13 +32,8 @@
  */
 
 struct sh_mmcif_plat_data {
-	int (*get_cd)(struct platform_device *pdef);
 	unsigned int		slave_id_tx;	/* embedded slave_id_[tr]x */
 	unsigned int		slave_id_rx;
-	bool			use_cd_gpio : 1;
-	bool			ccs_unsupported : 1;
-	bool			clk_ctrl2_present : 1;
-	unsigned int		cd_gpio;
 	u8			sup_pclk;	/* 1 :SH7757, 0: SH7724/SH7372 */
 	unsigned long		caps;
 	u32			ocr;
diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h
index a7972cd3bc14..82f0d289f110 100644
--- a/include/linux/mmc/slot-gpio.h
+++ b/include/linux/mmc/slot-gpio.h
@@ -11,6 +11,9 @@
 #ifndef MMC_SLOT_GPIO_H
 #define MMC_SLOT_GPIO_H
 
+#include <linux/types.h>
+#include <linux/irqreturn.h>
+
 struct mmc_host;
 
 int mmc_gpio_get_ro(struct mmc_host *host);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 36d9896fbc1e..f4aac87adcc3 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -972,12 +972,16 @@ static __always_inline struct zoneref *next_zones_zonelist(struct zoneref *z,
  * @zonelist - The zonelist to search for a suitable zone
  * @highest_zoneidx - The zone index of the highest zone to return
  * @nodes - An optional nodemask to filter the zonelist with
- * @zone - The first suitable zone found is returned via this parameter
+ * @return - Zoneref pointer for the first suitable zone found (see below)
  *
  * This function returns the first zone at or below a given zone index that is
  * within the allowed nodemask. The zoneref returned is a cursor that can be
  * used to iterate the zonelist with next_zones_zonelist by advancing it by
  * one before calling.
+ *
+ * When no eligible zone is found, zoneref->zone is NULL (zoneref itself is
+ * never NULL). This may happen either genuinely, or due to concurrent nodemask
+ * update due to cpuset modification.
  */
 static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 					enum zone_type highest_zoneidx,
diff --git a/include/linux/module.h b/include/linux/module.h
index 7c84273d60b9..cc7cba219b20 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -346,7 +346,7 @@ struct module {
 
 	/* Exported symbols */
 	const struct kernel_symbol *syms;
-	const unsigned long *crcs;
+	const s32 *crcs;
 	unsigned int num_syms;
 
 	/* Kernel parameters. */
@@ -359,18 +359,18 @@ struct module {
 	/* GPL-only exported symbols. */
 	unsigned int num_gpl_syms;
 	const struct kernel_symbol *gpl_syms;
-	const unsigned long *gpl_crcs;
+	const s32 *gpl_crcs;
 
 #ifdef CONFIG_UNUSED_SYMBOLS
 	/* unused exported symbols. */
 	const struct kernel_symbol *unused_syms;
-	const unsigned long *unused_crcs;
+	const s32 *unused_crcs;
 	unsigned int num_unused_syms;
 
 	/* GPL-only, unused exported symbols. */
 	unsigned int num_unused_gpl_syms;
 	const struct kernel_symbol *unused_gpl_syms;
-	const unsigned long *unused_gpl_crcs;
+	const s32 *unused_gpl_crcs;
 #endif
 
 #ifdef CONFIG_MODULE_SIG
@@ -382,7 +382,7 @@ struct module {
 
 	/* symbols that will be GPL-only in the near future. */
 	const struct kernel_symbol *gpl_future_syms;
-	const unsigned long *gpl_future_crcs;
+	const s32 *gpl_future_crcs;
 	unsigned int num_gpl_future_syms;
 
 	/* Exception table */
@@ -523,7 +523,7 @@ struct module *find_module(const char *name);
 
 struct symsearch {
 	const struct kernel_symbol *start, *stop;
-	const unsigned long *crcs;
+	const s32 *crcs;
 	enum {
 		NOT_GPL_ONLY,
 		GPL_ONLY,
@@ -539,7 +539,7 @@ struct symsearch {
  */
 const struct kernel_symbol *find_symbol(const char *name,
 					struct module **owner,
-					const unsigned long **crc,
+					const s32 **crc,
 					bool gplok,
 					bool warn);
 
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 0db320b7bb15..a83b84ff70e5 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -17,7 +17,13 @@ struct msi_desc;
 struct pci_dev;
 struct platform_msi_priv_data;
 void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+#ifdef CONFIG_GENERIC_MSI_IRQ
 void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
+#else
+static inline void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
+{
+}
+#endif
 
 typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc,
 				    struct msi_msg *msg);
@@ -116,11 +122,15 @@ struct msi_desc {
 
 struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc);
 void *msi_desc_to_pci_sysdata(struct msi_desc *desc);
+void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg);
 #else /* CONFIG_PCI_MSI */
 static inline void *msi_desc_to_pci_sysdata(struct msi_desc *desc)
 {
 	return NULL;
 }
+static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg)
+{
+}
 #endif /* CONFIG_PCI_MSI */
 
 struct msi_desc *alloc_msi_entry(struct device *dev, int nvec,
@@ -128,7 +138,6 @@ struct msi_desc *alloc_msi_entry(struct device *dev, int nvec,
 void free_msi_entry(struct msi_desc *entry);
 void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
-void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg);
 
 u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag);
 u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
diff --git a/include/linux/mtd/fsmc.h b/include/linux/mtd/fsmc.h
deleted file mode 100644
index ad3c3488073c..000000000000
--- a/include/linux/mtd/fsmc.h
+++ /dev/null
@@ -1,156 +0,0 @@
-/*
- * incude/mtd/fsmc.h
- *
- * ST Microelectronics
- * Flexible Static Memory Controller (FSMC)
- * platform data interface and header file
- *
- * Copyright © 2010 ST Microelectronics
- * Vipin Kumar <vipin.kumar@st.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __MTD_FSMC_H
-#define __MTD_FSMC_H
-
-#include <linux/io.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/physmap.h>
-#include <linux/types.h>
-#include <linux/mtd/partitions.h>
-#include <asm/param.h>
-
-#define FSMC_NAND_BW8		1
-#define FSMC_NAND_BW16		2
-
-#define FSMC_MAX_NOR_BANKS	4
-#define FSMC_MAX_NAND_BANKS	4
-
-#define FSMC_FLASH_WIDTH8	1
-#define FSMC_FLASH_WIDTH16	2
-
-/* fsmc controller registers for NOR flash */
-#define CTRL			0x0
-	/* ctrl register definitions */
-	#define BANK_ENABLE		(1 << 0)
-	#define MUXED			(1 << 1)
-	#define NOR_DEV			(2 << 2)
-	#define WIDTH_8			(0 << 4)
-	#define WIDTH_16		(1 << 4)
-	#define RSTPWRDWN		(1 << 6)
-	#define WPROT			(1 << 7)
-	#define WRT_ENABLE		(1 << 12)
-	#define WAIT_ENB		(1 << 13)
-
-#define CTRL_TIM		0x4
-	/* ctrl_tim register definitions */
-
-#define FSMC_NOR_BANK_SZ	0x8
-#define FSMC_NOR_REG_SIZE	0x40
-
-#define FSMC_NOR_REG(base, bank, reg)		(base + \
-						FSMC_NOR_BANK_SZ * (bank) + \
-						reg)
-
-/* fsmc controller registers for NAND flash */
-#define PC			0x00
-	/* pc register definitions */
-	#define FSMC_RESET		(1 << 0)
-	#define FSMC_WAITON		(1 << 1)
-	#define FSMC_ENABLE		(1 << 2)
-	#define FSMC_DEVTYPE_NAND	(1 << 3)
-	#define FSMC_DEVWID_8		(0 << 4)
-	#define FSMC_DEVWID_16		(1 << 4)
-	#define FSMC_ECCEN		(1 << 6)
-	#define FSMC_ECCPLEN_512	(0 << 7)
-	#define FSMC_ECCPLEN_256	(1 << 7)
-	#define FSMC_TCLR_1		(1)
-	#define FSMC_TCLR_SHIFT		(9)
-	#define FSMC_TCLR_MASK		(0xF)
-	#define FSMC_TAR_1		(1)
-	#define FSMC_TAR_SHIFT		(13)
-	#define FSMC_TAR_MASK		(0xF)
-#define STS			0x04
-	/* sts register definitions */
-	#define FSMC_CODE_RDY		(1 << 15)
-#define COMM			0x08
-	/* comm register definitions */
-	#define FSMC_TSET_0		0
-	#define FSMC_TSET_SHIFT		0
-	#define FSMC_TSET_MASK		0xFF
-	#define FSMC_TWAIT_6		6
-	#define FSMC_TWAIT_SHIFT	8
-	#define FSMC_TWAIT_MASK		0xFF
-	#define FSMC_THOLD_4		4
-	#define FSMC_THOLD_SHIFT	16
-	#define FSMC_THOLD_MASK		0xFF
-	#define FSMC_THIZ_1		1
-	#define FSMC_THIZ_SHIFT		24
-	#define FSMC_THIZ_MASK		0xFF
-#define ATTRIB			0x0C
-#define IOATA			0x10
-#define ECC1			0x14
-#define ECC2			0x18
-#define ECC3			0x1C
-#define FSMC_NAND_BANK_SZ	0x20
-
-#define FSMC_NAND_REG(base, bank, reg)		(base + FSMC_NOR_REG_SIZE + \
-						(FSMC_NAND_BANK_SZ * (bank)) + \
-						reg)
-
-#define FSMC_BUSY_WAIT_TIMEOUT	(1 * HZ)
-
-struct fsmc_nand_timings {
-	uint8_t tclr;
-	uint8_t tar;
-	uint8_t thiz;
-	uint8_t thold;
-	uint8_t twait;
-	uint8_t tset;
-};
-
-enum access_mode {
-	USE_DMA_ACCESS = 1,
-	USE_WORD_ACCESS,
-};
-
-/**
- * fsmc_nand_platform_data - platform specific NAND controller config
- * @nand_timings: timing setup for the physical NAND interface
- * @partitions: partition table for the platform, use a default fallback
- * if this is NULL
- * @nr_partitions: the number of partitions in the previous entry
- * @options: different options for the driver
- * @width: bus width
- * @bank: default bank
- * @select_bank: callback to select a certain bank, this is
- * platform-specific. If the controller only supports one bank
- * this may be set to NULL
- */
-struct fsmc_nand_platform_data {
-	struct fsmc_nand_timings *nand_timings;
-	struct mtd_partition	*partitions;
-	unsigned int		nr_partitions;
-	unsigned int		options;
-	unsigned int		width;
-	unsigned int		bank;
-
-	enum access_mode	mode;
-
-	void			(*select_bank)(uint32_t bank, uint32_t busw);
-
-	/* priv structures for dma accesses */
-	void			*read_dma_priv;
-	void			*write_dma_priv;
-};
-
-extern int __init fsmc_nor_init(struct platform_device *pdev,
-		unsigned long base, uint32_t bank, uint32_t width);
-extern void __init fsmc_init_board_info(struct platform_device *pdev,
-		struct mtd_partition *partitions, unsigned int nr_partitions,
-		unsigned int width);
-
-#endif /* __MTD_FSMC_H */
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 13f8052b9ff9..eebdc63cf6af 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -24,6 +24,7 @@
 #include <linux/uio.h>
 #include <linux/notifier.h>
 #include <linux/device.h>
+#include <linux/of.h>
 
 #include <mtd/mtd-abi.h>
 
@@ -322,6 +323,7 @@ struct mtd_info {
 	int (*_block_isreserved) (struct mtd_info *mtd, loff_t ofs);
 	int (*_block_isbad) (struct mtd_info *mtd, loff_t ofs);
 	int (*_block_markbad) (struct mtd_info *mtd, loff_t ofs);
+	int (*_max_bad_blocks) (struct mtd_info *mtd, loff_t ofs, size_t len);
 	int (*_suspend) (struct mtd_info *mtd);
 	void (*_resume) (struct mtd_info *mtd);
 	void (*_reboot) (struct mtd_info *mtd);
@@ -385,6 +387,8 @@ static inline void mtd_set_of_node(struct mtd_info *mtd,
 				   struct device_node *np)
 {
 	mtd->dev.of_node = np;
+	if (!mtd->name)
+		of_property_read_string(np, "label", &mtd->name);
 }
 
 static inline struct device_node *mtd_get_of_node(struct mtd_info *mtd)
@@ -397,6 +401,18 @@ static inline int mtd_oobavail(struct mtd_info *mtd, struct mtd_oob_ops *ops)
 	return ops->mode == MTD_OPS_AUTO_OOB ? mtd->oobavail : mtd->oobsize;
 }
 
+static inline int mtd_max_bad_blocks(struct mtd_info *mtd,
+				     loff_t ofs, size_t len)
+{
+	if (!mtd->_max_bad_blocks)
+		return -ENOTSUPP;
+
+	if (mtd->size < (len + ofs) || ofs < 0)
+		return -EINVAL;
+
+	return mtd->_max_bad_blocks(mtd, ofs, len);
+}
+
 int mtd_wunit_to_pairing_info(struct mtd_info *mtd, int wunit,
 			      struct mtd_pairing_info *info);
 int mtd_pairing_info_to_wunit(struct mtd_info *mtd,
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index c5f3a012ae62..9591e0fbe5bd 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -615,7 +615,7 @@ struct nand_buffers {
  * @tALS_min: ALE setup time
  * @tAR_min: ALE to RE# delay
  * @tCEA_max: CE# access time
- * @tCEH_min:
+ * @tCEH_min: CE# high hold time
  * @tCH_min:  CE# hold time
  * @tCHZ_max: CE# high to output hi-Z
  * @tCLH_min: CLE hold time
@@ -801,6 +801,10 @@ nand_get_sdr_timings(const struct nand_data_interface *conf)
  *			supported, 0 otherwise.
  * @jedec_params:	[INTERN] holds the JEDEC parameter page when JEDEC is
  *			supported, 0 otherwise.
+ * @max_bb_per_die:	[INTERN] the max number of bad blocks each die of a
+ *			this nand device will encounter their life times.
+ * @blocks_per_die:	[INTERN] The number of PEBs in a die
+ * @data_interface:	[INTERN] NAND interface timing information
  * @read_retries:	[INTERN] the number of read retry modes supported
  * @onfi_set_features:	[REPLACEABLE] set the features for ONFI nand
  * @onfi_get_features:	[REPLACEABLE] get the features for ONFI nand
@@ -883,6 +887,8 @@ struct nand_chip {
 		struct nand_onfi_params	onfi_params;
 		struct nand_jedec_params jedec_params;
 	};
+	u16 max_bb_per_die;
+	u32 blocks_per_die;
 
 	struct nand_data_interface *data_interface;
 
@@ -958,6 +964,7 @@ static inline void nand_set_controller_data(struct nand_chip *chip, void *priv)
 #define NAND_MFR_SANDISK	0x45
 #define NAND_MFR_INTEL		0x89
 #define NAND_MFR_ATO		0x9b
+#define NAND_MFR_WINBOND	0xef
 
 /* The maximum expected count of bytes in the NAND ID sequence */
 #define NAND_MAX_ID_LEN 8
diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h
index 70736e1e6c8f..06df1e06b6e0 100644
--- a/include/linux/mtd/partitions.h
+++ b/include/linux/mtd/partitions.h
@@ -41,6 +41,7 @@ struct mtd_partition {
 	uint64_t size;			/* partition size */
 	uint64_t offset;		/* offset within the master MTD space */
 	uint32_t mask_flags;		/* master MTD flags to mask out for this partition */
+	struct device_node *of_node;
 };
 
 #define MTDPART_OFS_RETAIN	(-3)
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index c425c7b4c2a0..f2a718030476 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -43,9 +43,13 @@
 #define SPINOR_OP_WRSR		0x01	/* Write status register 1 byte */
 #define SPINOR_OP_READ		0x03	/* Read data bytes (low frequency) */
 #define SPINOR_OP_READ_FAST	0x0b	/* Read data bytes (high frequency) */
-#define SPINOR_OP_READ_1_1_2	0x3b	/* Read data bytes (Dual SPI) */
-#define SPINOR_OP_READ_1_1_4	0x6b	/* Read data bytes (Quad SPI) */
+#define SPINOR_OP_READ_1_1_2	0x3b	/* Read data bytes (Dual Output SPI) */
+#define SPINOR_OP_READ_1_2_2	0xbb	/* Read data bytes (Dual I/O SPI) */
+#define SPINOR_OP_READ_1_1_4	0x6b	/* Read data bytes (Quad Output SPI) */
+#define SPINOR_OP_READ_1_4_4	0xeb	/* Read data bytes (Quad I/O SPI) */
 #define SPINOR_OP_PP		0x02	/* Page program (up to 256 bytes) */
+#define SPINOR_OP_PP_1_1_4	0x32	/* Quad page program */
+#define SPINOR_OP_PP_1_4_4	0x38	/* Quad page program */
 #define SPINOR_OP_BE_4K		0x20	/* Erase 4KiB block */
 #define SPINOR_OP_BE_4K_PMC	0xd7	/* Erase 4KiB block on PMC chips */
 #define SPINOR_OP_BE_32K	0x52	/* Erase 32KiB block */
@@ -56,11 +60,17 @@
 #define SPINOR_OP_RDFSR		0x70	/* Read flag status register */
 
 /* 4-byte address opcodes - used on Spansion and some Macronix flashes. */
-#define SPINOR_OP_READ4		0x13	/* Read data bytes (low frequency) */
-#define SPINOR_OP_READ4_FAST	0x0c	/* Read data bytes (high frequency) */
-#define SPINOR_OP_READ4_1_1_2	0x3c	/* Read data bytes (Dual SPI) */
-#define SPINOR_OP_READ4_1_1_4	0x6c	/* Read data bytes (Quad SPI) */
+#define SPINOR_OP_READ_4B	0x13	/* Read data bytes (low frequency) */
+#define SPINOR_OP_READ_FAST_4B	0x0c	/* Read data bytes (high frequency) */
+#define SPINOR_OP_READ_1_1_2_4B	0x3c	/* Read data bytes (Dual Output SPI) */
+#define SPINOR_OP_READ_1_2_2_4B	0xbc	/* Read data bytes (Dual I/O SPI) */
+#define SPINOR_OP_READ_1_1_4_4B	0x6c	/* Read data bytes (Quad Output SPI) */
+#define SPINOR_OP_READ_1_4_4_4B	0xec	/* Read data bytes (Quad I/O SPI) */
 #define SPINOR_OP_PP_4B		0x12	/* Page program (up to 256 bytes) */
+#define SPINOR_OP_PP_1_1_4_4B	0x34	/* Quad page program */
+#define SPINOR_OP_PP_1_4_4_4B	0x3e	/* Quad page program */
+#define SPINOR_OP_BE_4K_4B	0x21	/* Erase 4KiB block */
+#define SPINOR_OP_BE_32K_4B	0x5c	/* Erase 32KiB block */
 #define SPINOR_OP_SE_4B		0xdc	/* Sector erase (usually 64KiB) */
 
 /* Used for SST flashes only. */
@@ -68,6 +78,15 @@
 #define SPINOR_OP_WRDI		0x04	/* Write disable */
 #define SPINOR_OP_AAI_WP	0xad	/* Auto address increment word program */
 
+/* Used for S3AN flashes only */
+#define SPINOR_OP_XSE		0x50	/* Sector erase */
+#define SPINOR_OP_XPP		0x82	/* Page program */
+#define SPINOR_OP_XRDSR		0xd7	/* Read status register */
+
+#define XSR_PAGESIZE		BIT(0)	/* Page size in Po2 or Linear */
+#define XSR_RDY			BIT(7)	/* Ready */
+
+
 /* Used for Macronix and Winbond flashes. */
 #define SPINOR_OP_EN4B		0xb7	/* Enter 4-byte mode */
 #define SPINOR_OP_EX4B		0xe9	/* Exit 4-byte mode */
@@ -119,6 +138,9 @@ enum spi_nor_ops {
 enum spi_nor_option_flags {
 	SNOR_F_USE_FSR		= BIT(0),
 	SNOR_F_HAS_SR_TB	= BIT(1),
+	SNOR_F_NO_OP_CHIP_ERASE	= BIT(2),
+	SNOR_F_S3AN_ADDR_DEFAULT = BIT(3),
+	SNOR_F_READY_XSR_RDY	= BIT(4),
 };
 
 /**
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index b97870f2debd..1127fe31645d 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -20,6 +20,8 @@
 #include <linux/osq_lock.h>
 #include <linux/debug_locks.h>
 
+struct ww_acquire_ctx;
+
 /*
  * Simple, straightforward mutexes with strict semantics:
  *
@@ -65,7 +67,7 @@ struct mutex {
 
 static inline struct task_struct *__mutex_owner(struct mutex *lock)
 {
-	return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x03);
+	return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x07);
 }
 
 /*
@@ -75,6 +77,7 @@ static inline struct task_struct *__mutex_owner(struct mutex *lock)
 struct mutex_waiter {
 	struct list_head	list;
 	struct task_struct	*task;
+	struct ww_acquire_ctx	*ww_ctx;
 #ifdef CONFIG_DEBUG_MUTEXES
 	void			*magic;
 #endif
@@ -156,10 +159,12 @@ extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock,
 					unsigned int subclass);
 extern int __must_check mutex_lock_killable_nested(struct mutex *lock,
 					unsigned int subclass);
+extern void mutex_lock_io_nested(struct mutex *lock, unsigned int subclass);
 
 #define mutex_lock(lock) mutex_lock_nested(lock, 0)
 #define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0)
 #define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0)
+#define mutex_lock_io(lock) mutex_lock_io_nested(lock, 0)
 
 #define mutex_lock_nest_lock(lock, nest_lock)				\
 do {									\
@@ -171,11 +176,13 @@ do {									\
 extern void mutex_lock(struct mutex *lock);
 extern int __must_check mutex_lock_interruptible(struct mutex *lock);
 extern int __must_check mutex_lock_killable(struct mutex *lock);
+extern void mutex_lock_io(struct mutex *lock);
 
 # define mutex_lock_nested(lock, subclass) mutex_lock(lock)
 # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
 # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
 # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
+# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock)
 #endif
 
 /*
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9bde9558b596..27914672602d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -866,11 +866,15 @@ struct netdev_xdp {
  *	of useless work if you return NETDEV_TX_BUSY.
  *	Required; cannot be NULL.
  *
- * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
- *		netdev_features_t features);
- *	Adjusts the requested feature flags according to device-specific
- *	constraints, and returns the resulting flags. Must not modify
- *	the device state.
+ * netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
+ *					   struct net_device *dev
+ *					   netdev_features_t features);
+ *	Called by core transmit path to determine if device is capable of
+ *	performing offload operations on a given packet. This is to give
+ *	the device an opportunity to implement any restrictions that cannot
+ *	be otherwise expressed by feature flags. The check is called with
+ *	the set of features that the stack has calculated and it returns
+ *	those the driver believes to be appropriate.
  *
  * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
  *                         void *accel_priv, select_queue_fallback_t fallback);
@@ -1028,6 +1032,12 @@ struct netdev_xdp {
  *	Called to release previously enslaved netdev.
  *
  *      Feature/offload setting functions.
+ * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
+ *		netdev_features_t features);
+ *	Adjusts the requested feature flags according to device-specific
+ *	constraints, and returns the resulting flags. Must not modify
+ *	the device state.
+ *
  * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features);
  *	Called to update device configuration to new features. Passed
  *	feature set might be less than what was returned by ndo_fix_features()).
@@ -1100,15 +1110,6 @@ struct netdev_xdp {
  *	Callback to use for xmit over the accelerated station. This
  *	is used in place of ndo_start_xmit on accelerated net
  *	devices.
- * netdev_features_t (*ndo_features_check)(struct sk_buff *skb,
- *					   struct net_device *dev
- *					   netdev_features_t features);
- *	Called by core transmit path to determine if device is capable of
- *	performing offload operations on a given packet. This is to give
- *	the device an opportunity to implement any restrictions that cannot
- *	be otherwise expressed by feature flags. The check is called with
- *	the set of features that the stack has calculated and it returns
- *	those the driver believes to be appropriate.
  * int (*ndo_set_tx_maxrate)(struct net_device *dev,
  *			     int queue_index, u32 maxrate);
  *	Called when a user wants to set a max-rate limitation of specific
@@ -1510,6 +1511,7 @@ enum netdev_priv_flags {
  *	@max_mtu:	Interface Maximum MTU value
  *	@type:		Interface hardware type
  *	@hard_header_len: Maximum hardware header length.
+ *	@min_header_len:  Minimum hardware header length
  *
  *	@needed_headroom: Extra headroom the hardware may need, but not in all
  *			  cases can this be guaranteed
@@ -1727,6 +1729,7 @@ struct net_device {
 	unsigned int		max_mtu;
 	unsigned short		type;
 	unsigned short		hard_header_len;
+	unsigned short		min_header_len;
 
 	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;
@@ -2693,6 +2696,8 @@ static inline bool dev_validate_header(const struct net_device *dev,
 {
 	if (likely(len >= dev->hard_header_len))
 		return true;
+	if (len < dev->min_header_len)
+		return false;
 
 	if (capable(CAP_SYS_RAWIO)) {
 		memset(ll_header + len, 0, dev->hard_header_len - len);
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index bca536341d1a..1b1ca04820a3 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -282,7 +282,7 @@ enum nfsstat4 {
 
 static inline bool seqid_mutating_err(u32 err)
 {
-	/* rfc 3530 section 8.1.5: */
+	/* See RFC 7530, section 9.1.7 */
 	switch (err) {
 	case NFS4ERR_STALE_CLIENTID:
 	case NFS4ERR_STALE_STATEID:
@@ -291,6 +291,7 @@ static inline bool seqid_mutating_err(u32 err)
 	case NFS4ERR_BADXDR:
 	case NFS4ERR_RESOURCE:
 	case NFS4ERR_NOFILEHANDLE:
+	case NFS4ERR_MOVED:
 		return false;
 	};
 	return true;
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index aacca824a6ae..0a3fadc32693 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -110,6 +110,7 @@ extern int watchdog_user_enabled;
 extern int watchdog_thresh;
 extern unsigned long watchdog_enabled;
 extern unsigned long *watchdog_cpumask_bits;
+extern atomic_t watchdog_park_in_progress;
 #ifdef CONFIG_SMP
 extern int sysctl_softlockup_all_cpu_backtrace;
 extern int sysctl_hardlockup_all_cpu_backtrace;
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 3d1c6f1b15c9..0b676a02cf3e 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -244,6 +244,7 @@ enum {
 	NVME_CTRL_ONCS_DSM			= 1 << 2,
 	NVME_CTRL_ONCS_WRITE_ZEROES		= 1 << 3,
 	NVME_CTRL_VWC_PRESENT			= 1 << 0,
+	NVME_CTRL_OACS_SEC_SUPP                 = 1 << 0,
 };
 
 struct nvme_lbaf {
@@ -553,6 +554,8 @@ enum {
 	NVME_DSMGMT_AD		= 1 << 2,
 };
 
+#define NVME_DSM_MAX_RANGES	256
+
 struct nvme_dsm_range {
 	__le32			cattr;
 	__le32			nlb;
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 6a7fc5051099..13394ac83c66 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -31,17 +31,6 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
 
 #endif	/* CONFIG_OF_IOMMU */
 
-static inline void of_iommu_set_ops(struct device_node *np,
-				    const struct iommu_ops *ops)
-{
-	iommu_register_instance(&np->fwnode, ops);
-}
-
-static inline const struct iommu_ops *of_iommu_get_ops(struct device_node *np)
-{
-	return iommu_get_instance(&np->fwnode);
-}
-
 extern struct of_device_id __iommu_of_table;
 
 typedef int (*of_iommu_init_fn)(struct device_node *);
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 1c7eec09e5eb..3a481a49546e 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -204,7 +204,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref)
 static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 {
 	unsigned long __percpu *percpu_count;
-	int ret;
+	bool ret;
 
 	rcu_read_lock_sched();
 
@@ -238,7 +238,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 {
 	unsigned long __percpu *percpu_count;
-	int ret = false;
+	bool ret = false;
 
 	rcu_read_lock_sched();
 
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 5b2e6159b744..93664f022ecf 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -4,15 +4,15 @@
 #include <linux/atomic.h>
 #include <linux/rwsem.h>
 #include <linux/percpu.h>
-#include <linux/wait.h>
+#include <linux/rcuwait.h>
 #include <linux/rcu_sync.h>
 #include <linux/lockdep.h>
 
 struct percpu_rw_semaphore {
 	struct rcu_sync		rss;
 	unsigned int __percpu	*read_count;
-	struct rw_semaphore	rw_sem;
-	wait_queue_head_t	writer;
+	struct rw_semaphore	rw_sem; /* slowpath */
+	struct rcuwait          writer; /* blocked writer */
 	int			readers_block;
 };
 
@@ -22,7 +22,7 @@ static struct percpu_rw_semaphore name = {				\
 	.rss = __RCU_SYNC_INITIALIZER(name.rss, RCU_SCHED_SYNC),	\
 	.read_count = &__percpu_rwsem_rc_##name,			\
 	.rw_sem = __RWSEM_INITIALIZER(name.rw_sem),			\
-	.writer = __WAIT_QUEUE_HEAD_INITIALIZER(name.writer),		\
+	.writer = __RCUWAIT_INITIALIZER(name.writer),			\
 }
 
 extern int __percpu_down_read(struct percpu_rw_semaphore *, int);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 78ed8105e64d..000fdb211c7d 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -482,6 +482,7 @@ struct perf_addr_filter {
  * @list:	list of filters for this event
  * @lock:	spinlock that serializes accesses to the @list and event's
  *		(and its children's) filter generations.
+ * @nr_file_filters:	number of file-based filters
  *
  * A child event will use parent's @list (and therefore @lock), so they are
  * bundled together; see perf_event_addr_filters().
@@ -489,6 +490,7 @@ struct perf_addr_filter {
 struct perf_addr_filters_head {
 	struct list_head	list;
 	raw_spinlock_t		lock;
+	unsigned int		nr_file_filters;
 };
 
 /**
@@ -785,9 +787,9 @@ struct perf_cpu_context {
 	ktime_t				hrtimer_interval;
 	unsigned int			hrtimer_active;
 
-	struct pmu			*unique_pmu;
 #ifdef CONFIG_CGROUP_PERF
 	struct perf_cgroup		*cgrp;
+	struct list_head		cgrp_cpuctx_entry;
 #endif
 
 	struct list_head		sched_cb_entry;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index f7d95f644eed..7fc1105605bf 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -25,7 +25,6 @@
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/mod_devicetable.h>
-#include <linux/phy_led_triggers.h>
 
 #include <linux/atomic.h>
 
diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h
index a2daea0a37d2..b37b05bfd1a6 100644
--- a/include/linux/phy_led_triggers.h
+++ b/include/linux/phy_led_triggers.h
@@ -18,11 +18,11 @@ struct phy_device;
 #ifdef CONFIG_LED_TRIGGER_PHY
 
 #include <linux/leds.h>
+#include <linux/phy.h>
 
 #define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE	10
-#define PHY_MII_BUS_ID_SIZE	(20 - 3)
 
-#define PHY_LINK_LED_TRIGGER_NAME_SIZE (PHY_MII_BUS_ID_SIZE + \
+#define PHY_LINK_LED_TRIGGER_NAME_SIZE (MII_BUS_ID_SIZE + \
 				       FIELD_SIZEOF(struct mdio_device, addr)+\
 				       PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE)
 
diff --git a/include/linux/platform_data/intel-spi.h b/include/linux/platform_data/intel-spi.h
new file mode 100644
index 000000000000..942b0c3f8f08
--- /dev/null
+++ b/include/linux/platform_data/intel-spi.h
@@ -0,0 +1,31 @@
+/*
+ * Intel PCH/PCU SPI flash driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef INTEL_SPI_PDATA_H
+#define INTEL_SPI_PDATA_H
+
+enum intel_spi_type {
+	INTEL_SPI_BYT = 1,
+	INTEL_SPI_LPT,
+	INTEL_SPI_BXT,
+};
+
+/**
+ * struct intel_spi_boardinfo - Board specific data for Intel SPI driver
+ * @type: Type which this controller is compatible with
+ * @writeable: The chip is writeable
+ */
+struct intel_spi_boardinfo {
+	enum intel_spi_type type;
+	bool writeable;
+};
+
+#endif /* INTEL_SPI_PDATA_H */
diff --git a/include/linux/platform_data/mmc-mxcmmc.h b/include/linux/platform_data/mmc-mxcmmc.h
index 29115f405af9..b0fdaa9bd185 100644
--- a/include/linux/platform_data/mmc-mxcmmc.h
+++ b/include/linux/platform_data/mmc-mxcmmc.h
@@ -1,6 +1,7 @@
 #ifndef ASMARM_ARCH_MMC_H
 #define ASMARM_ARCH_MMC_H
 
+#include <linux/interrupt.h>
 #include <linux/mmc/host.h>
 
 struct device;
diff --git a/include/linux/platform_data/spi-ep93xx.h b/include/linux/platform_data/spi-ep93xx.h
index 9bb63ac13f04..171a271c2cbd 100644
--- a/include/linux/platform_data/spi-ep93xx.h
+++ b/include/linux/platform_data/spi-ep93xx.h
@@ -5,25 +5,14 @@ struct spi_device;
 
 /**
  * struct ep93xx_spi_info - EP93xx specific SPI descriptor
- * @num_chipselect: number of chip selects on this board, must be
- *                  at least one
+ * @chipselect: array of gpio numbers to use as chip selects
+ * @num_chipselect: ARRAY_SIZE(chipselect)
  * @use_dma: use DMA for the transfers
  */
 struct ep93xx_spi_info {
+	int	*chipselect;
 	int	num_chipselect;
 	bool	use_dma;
 };
 
-/**
- * struct ep93xx_spi_chip_ops - operation callbacks for SPI slave device
- * @setup: setup the chip select mechanism
- * @cleanup: cleanup the chip select mechanism
- * @cs_control: control the device chip select
- */
-struct ep93xx_spi_chip_ops {
-	int	(*setup)(struct spi_device *spi);
-	void	(*cleanup)(struct spi_device *spi);
-	void	(*cs_control)(struct spi_device *spi, int value);
-};
-
 #endif /* __ASM_MACH_EP93XX_SPI_H */
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 81ece61075df..5339ed5bd6f9 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -182,6 +182,9 @@ static inline int pm_genpd_remove(struct generic_pm_domain *genpd)
 {
 	return -ENOTSUPP;
 }
+
+#define simple_qos_governor		(*(struct dev_power_governor *)(NULL))
+#define pm_domain_always_on_gov		(*(struct dev_power_governor *)(NULL))
 #endif
 
 static inline int pm_genpd_add_device(struct generic_pm_domain *genpd,
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 0edd88f93904..a6685b3dde26 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -78,6 +78,9 @@ struct dev_pm_set_opp_data {
 
 #if defined(CONFIG_PM_OPP)
 
+struct opp_table *dev_pm_opp_get_opp_table(struct device *dev);
+void dev_pm_opp_put_opp_table(struct opp_table *opp_table);
+
 unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp);
 
 unsigned long dev_pm_opp_get_freq(struct dev_pm_opp *opp);
@@ -88,7 +91,7 @@ int dev_pm_opp_get_opp_count(struct device *dev);
 unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev);
 unsigned long dev_pm_opp_get_max_volt_latency(struct device *dev);
 unsigned long dev_pm_opp_get_max_transition_latency(struct device *dev);
-struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev);
+unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev);
 
 struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 					      unsigned long freq,
@@ -99,6 +102,7 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq);
+void dev_pm_opp_put(struct dev_pm_opp *opp);
 
 int dev_pm_opp_add(struct device *dev, unsigned long freq,
 		   unsigned long u_volt);
@@ -108,22 +112,30 @@ int dev_pm_opp_enable(struct device *dev, unsigned long freq);
 
 int dev_pm_opp_disable(struct device *dev, unsigned long freq);
 
-struct srcu_notifier_head *dev_pm_opp_get_notifier(struct device *dev);
-int dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions,
-				unsigned int count);
-void dev_pm_opp_put_supported_hw(struct device *dev);
-int dev_pm_opp_set_prop_name(struct device *dev, const char *name);
-void dev_pm_opp_put_prop_name(struct device *dev);
+int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb);
+int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb);
+
+struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev, const u32 *versions, unsigned int count);
+void dev_pm_opp_put_supported_hw(struct opp_table *opp_table);
+struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name);
+void dev_pm_opp_put_prop_name(struct opp_table *opp_table);
 struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count);
 void dev_pm_opp_put_regulators(struct opp_table *opp_table);
-int dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data));
-void dev_pm_opp_register_put_opp_helper(struct device *dev);
+struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data));
+void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table);
 int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq);
 int dev_pm_opp_set_sharing_cpus(struct device *cpu_dev, const struct cpumask *cpumask);
 int dev_pm_opp_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
 void dev_pm_opp_remove_table(struct device *dev);
 void dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask);
 #else
+static inline struct opp_table *dev_pm_opp_get_opp_table(struct device *dev)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+
+static inline void dev_pm_opp_put_opp_table(struct opp_table *opp_table) {}
+
 static inline unsigned long dev_pm_opp_get_voltage(struct dev_pm_opp *opp)
 {
 	return 0;
@@ -159,9 +171,9 @@ static inline unsigned long dev_pm_opp_get_max_transition_latency(struct device
 	return 0;
 }
 
-static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev)
+static inline unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
 {
-	return NULL;
+	return 0;
 }
 
 static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
@@ -182,6 +194,8 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 	return ERR_PTR(-ENOTSUPP);
 }
 
+static inline void dev_pm_opp_put(struct dev_pm_opp *opp) {}
+
 static inline int dev_pm_opp_add(struct device *dev, unsigned long freq,
 					unsigned long u_volt)
 {
@@ -202,35 +216,39 @@ static inline int dev_pm_opp_disable(struct device *dev, unsigned long freq)
 	return 0;
 }
 
-static inline struct srcu_notifier_head *dev_pm_opp_get_notifier(
-							struct device *dev)
+static inline int dev_pm_opp_register_notifier(struct device *dev, struct notifier_block *nb)
 {
-	return ERR_PTR(-ENOTSUPP);
+	return -ENOTSUPP;
 }
 
-static inline int dev_pm_opp_set_supported_hw(struct device *dev,
-					      const u32 *versions,
-					      unsigned int count)
+static inline int dev_pm_opp_unregister_notifier(struct device *dev, struct notifier_block *nb)
 {
 	return -ENOTSUPP;
 }
 
-static inline void dev_pm_opp_put_supported_hw(struct device *dev) {}
+static inline struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
+							    const u32 *versions,
+							    unsigned int count)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
 
-static inline int dev_pm_opp_register_set_opp_helper(struct device *dev,
+static inline void dev_pm_opp_put_supported_hw(struct opp_table *opp_table) {}
+
+static inline struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 			int (*set_opp)(struct dev_pm_set_opp_data *data))
 {
-	return -ENOTSUPP;
+	return ERR_PTR(-ENOTSUPP);
 }
 
-static inline void dev_pm_opp_register_put_opp_helper(struct device *dev) {}
+static inline void dev_pm_opp_register_put_opp_helper(struct opp_table *opp_table) {}
 
-static inline int dev_pm_opp_set_prop_name(struct device *dev, const char *name)
+static inline struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
-	return -ENOTSUPP;
+	return ERR_PTR(-ENOTSUPP);
 }
 
-static inline void dev_pm_opp_put_prop_name(struct device *dev) {}
+static inline void dev_pm_opp_put_prop_name(struct opp_table *opp_table) {}
 
 static inline struct opp_table *dev_pm_opp_set_regulators(struct device *dev, const char * const names[], unsigned int count)
 {
@@ -270,6 +288,7 @@ void dev_pm_opp_of_remove_table(struct device *dev);
 int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask);
 void dev_pm_opp_of_cpumask_remove_table(const struct cpumask *cpumask);
 int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask);
+struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev);
 #else
 static inline int dev_pm_opp_of_add_table(struct device *dev)
 {
@@ -293,6 +312,11 @@ static inline int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev, struct
 {
 	return -ENOTSUPP;
 }
+
+static inline struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev)
+{
+	return NULL;
+}
 #endif
 
 #endif		/* __LINUX_OPP_H__ */
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 0f65d36c2a75..d4d34791e463 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -6,7 +6,6 @@
  */
 #include <linux/plist.h>
 #include <linux/notifier.h>
-#include <linux/miscdevice.h>
 #include <linux/device.h>
 #include <linux/workqueue.h>
 
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 51334edec506..a39540326417 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -80,6 +80,7 @@
 /********** kernel/mutexes **********/
 #define MUTEX_DEBUG_INIT	0x11
 #define MUTEX_DEBUG_FREE	0x22
+#define MUTEX_POISON_WW_CTX	((void *) 0x500 + POISON_POINTER_DELTA)
 
 /********** lib/flex_array.c **********/
 #define FLEX_ARRAY_FREE	0x6c	/* for use-after-free poisoning */
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 62d44c176071..64aa189efe21 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -8,19 +8,9 @@
 #include <linux/alarmtimer.h>
 
 
-static inline unsigned long long cputime_to_expires(cputime_t expires)
-{
-	return (__force unsigned long long)expires;
-}
-
-static inline cputime_t expires_to_cputime(unsigned long long expires)
-{
-	return (__force cputime_t)expires;
-}
-
 struct cpu_timer_list {
 	struct list_head entry;
-	unsigned long long expires, incr;
+	u64 expires, incr;
 	struct task_struct *task;
 	int firing;
 };
@@ -129,7 +119,7 @@ void run_posix_cpu_timers(struct task_struct *task);
 void posix_cpu_timers_exit(struct task_struct *task);
 void posix_cpu_timers_exit_group(struct task_struct *task);
 void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
-			   cputime_t *newval, cputime_t *oldval);
+			   u64 *newval, u64 *oldval);
 
 long clock_nanosleep_restart(struct restart_block *restart_block);
 
diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h
index bed9557b69e7..b312bcef53da 100644
--- a/include/linux/power/bq27xxx_battery.h
+++ b/include/linux/power/bq27xxx_battery.h
@@ -4,8 +4,16 @@
 enum bq27xxx_chip {
 	BQ27000 = 1, /* bq27000, bq27200 */
 	BQ27010, /* bq27010, bq27210 */
-	BQ27500, /* bq27500 */
-	BQ27510, /* bq27510, bq27520 */
+	BQ2750X, /* bq27500 deprecated alias */
+	BQ2751X, /* bq27510, bq27520 deprecated alias */
+	BQ27500, /* bq27500/1 */
+	BQ27510G1, /* bq27510G1 */
+	BQ27510G2, /* bq27510G2 */
+	BQ27510G3, /* bq27510G3 */
+	BQ27520G1, /* bq27520G1 */
+	BQ27520G2, /* bq27520G2 */
+	BQ27520G3, /* bq27520G3 */
+	BQ27520G4, /* bq27520G4 */
 	BQ27530, /* bq27530, bq27531 */
 	BQ27541, /* bq27541, bq27542, bq27546, bq27742 */
 	BQ27545, /* bq27545 */
diff --git a/include/linux/property.h b/include/linux/property.h
index 856e50b2140c..64e3a9c6d95f 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -160,12 +160,12 @@ struct property_entry {
 	bool is_string;
 	union {
 		union {
-			void *raw_data;
-			u8 *u8_data;
-			u16 *u16_data;
-			u32 *u32_data;
-			u64 *u64_data;
-			const char **str;
+			const void *raw_data;
+			const u8 *u8_data;
+			const u16 *u16_data;
+			const u32 *u32_data;
+			const u64 *u64_data;
+			const char * const *str;
 		} pointer;
 		union {
 			unsigned long long raw_data;
@@ -241,8 +241,13 @@ struct property_entry {
 	.name = _name_,				\
 }
 
+struct property_entry *
+property_entries_dup(const struct property_entry *properties);
+
+void property_entries_free(const struct property_entry *properties);
+
 int device_add_properties(struct device *dev,
-			  struct property_entry *properties);
+			  const struct property_entry *properties);
 void device_remove_properties(struct device *dev);
 
 bool device_dma_supported(struct device *dev);
diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 2d6f0c39ed68..a0522328d7aa 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -90,9 +90,9 @@
 #define SSSR_RFL_MASK	(0xf << 12)	/* Receive FIFO Level mask */
 
 #define SSCR1_TFT	(0x000003c0)	/* Transmit FIFO Threshold (mask) */
-#define SSCR1_TxTresh(x) (((x) - 1) << 6) /* level [1..16] */
+#define SSCR1_TxTresh(x) (((x) - 1) << 6)	/* level [1..16] */
 #define SSCR1_RFT	(0x00003c00)	/* Receive FIFO Threshold (mask) */
-#define SSCR1_RxTresh(x) (((x) - 1) << 10) /* level [1..16] */
+#define SSCR1_RxTresh(x) (((x) - 1) << 10)	/* level [1..16] */
 
 #define RX_THRESH_CE4100_DFLT	2
 #define TX_THRESH_CE4100_DFLT	2
@@ -106,9 +106,9 @@
 #define CE4100_SSCR1_RxTresh(x) (((x) - 1) << 10)	/* level [1..4] */
 
 /* QUARK_X1000 SSCR0 bit definition */
-#define QUARK_X1000_SSCR0_DSS	(0x1F)		/* Data Size Select (mask) */
-#define QUARK_X1000_SSCR0_DataSize(x)  ((x) - 1)	/* Data Size Select [4..32] */
-#define QUARK_X1000_SSCR0_FRF	(0x3 << 5)	/* FRame Format (mask) */
+#define QUARK_X1000_SSCR0_DSS		(0x1F << 0)	/* Data Size Select (mask) */
+#define QUARK_X1000_SSCR0_DataSize(x)	((x) - 1)	/* Data Size Select [4..32] */
+#define QUARK_X1000_SSCR0_FRF		(0x3 << 5)	/* FRame Format (mask) */
 #define QUARK_X1000_SSCR0_Motorola	(0x0 << 5)	/* Motorola's Serial Peripheral Interface (SPI) */
 
 #define RX_THRESH_QUARK_X1000_DFLT	1
@@ -121,8 +121,8 @@
 #define QUARK_X1000_SSCR1_TxTresh(x) (((x) - 1) << 6)	/* level [1..32] */
 #define QUARK_X1000_SSCR1_RFT	(0x1F << 11)	/* Receive FIFO Threshold (mask) */
 #define QUARK_X1000_SSCR1_RxTresh(x) (((x) - 1) << 11)	/* level [1..32] */
-#define QUARK_X1000_SSCR1_STRF       (1 << 17)		/* Select FIFO or EFWR */
-#define QUARK_X1000_SSCR1_EFWR	(1 << 16)		/* Enable FIFO Write/Read */
+#define QUARK_X1000_SSCR1_STRF	(1 << 17)	/* Select FIFO or EFWR */
+#define QUARK_X1000_SSCR1_EFWR	(1 << 16)	/* Enable FIFO Write/Read */
 
 /* extra bits in PXA255, PXA26x and PXA27x SSP ports */
 #define SSCR0_TISSP		(1 << 4)	/* TI Sync Serial Protocol */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 01f71e1d2e94..6ade6a52d9d4 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -1161,5 +1161,17 @@ do { \
 		ftrace_dump(oops_dump_mode); \
 } while (0)
 
+/*
+ * Place this after a lock-acquisition primitive to guarantee that
+ * an UNLOCK+LOCK pair acts as a full barrier.  This guarantee applies
+ * if the UNLOCK and LOCK are executed by the same CPU or if the
+ * UNLOCK and LOCK operate on the same lock variable.
+ */
+#ifdef CONFIG_PPC
+#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
+#else /* #ifdef CONFIG_PPC */
+#define smp_mb__after_unlock_lock()	do { } while (0)
+#endif /* #else #ifdef CONFIG_PPC */
+
 
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index ac81e4063b40..4f9b2fa2173d 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -27,6 +27,12 @@
 
 #include <linux/cache.h>
 
+struct rcu_dynticks;
+static inline int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
+{
+	return 0;
+}
+
 static inline unsigned long get_state_synchronize_rcu(void)
 {
 	return 0;
diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h
new file mode 100644
index 000000000000..a4ede51b3e7c
--- /dev/null
+++ b/include/linux/rcuwait.h
@@ -0,0 +1,63 @@
+#ifndef _LINUX_RCUWAIT_H_
+#define _LINUX_RCUWAIT_H_
+
+#include <linux/rcupdate.h>
+
+/*
+ * rcuwait provides a way of blocking and waking up a single
+ * task in an rcu-safe manner; where it is forbidden to use
+ * after exit_notify(). task_struct is not properly rcu protected,
+ * unless dealing with rcu-aware lists, ie: find_task_by_*().
+ *
+ * Alternatively we have task_rcu_dereference(), but the return
+ * semantics have different implications which would break the
+ * wakeup side. The only time @task is non-nil is when a user is
+ * blocked (or checking if it needs to) on a condition, and reset
+ * as soon as we know that the condition has succeeded and are
+ * awoken.
+ */
+struct rcuwait {
+	struct task_struct *task;
+};
+
+#define __RCUWAIT_INITIALIZER(name)		\
+	{ .task = NULL, }
+
+static inline void rcuwait_init(struct rcuwait *w)
+{
+	w->task = NULL;
+}
+
+extern void rcuwait_wake_up(struct rcuwait *w);
+
+/*
+ * The caller is responsible for locking around rcuwait_wait_event(),
+ * such that writes to @task are properly serialized.
+ */
+#define rcuwait_wait_event(w, condition)				\
+({									\
+	/*								\
+	 * Complain if we are called after do_exit()/exit_notify(),     \
+	 * as we cannot rely on the rcu critical region for the		\
+	 * wakeup side.							\
+	 */                                                             \
+	WARN_ON(current->exit_state);                                   \
+									\
+	rcu_assign_pointer((w)->task, current);				\
+	for (;;) {							\
+		/*							\
+		 * Implicit barrier (A) pairs with (B) in		\
+		 * rcuwait_wake_up().					\
+		 */							\
+		set_current_state(TASK_UNINTERRUPTIBLE);		\
+		if (condition)						\
+			break;						\
+									\
+		schedule();						\
+	}								\
+									\
+	WRITE_ONCE((w)->task, NULL);					\
+	__set_current_state(TASK_RUNNING);				\
+})
+
+#endif /* _LINUX_RCUWAIT_H_ */
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
new file mode 100644
index 000000000000..600aadf9cca4
--- /dev/null
+++ b/include/linux/refcount.h
@@ -0,0 +1,294 @@
+#ifndef _LINUX_REFCOUNT_H
+#define _LINUX_REFCOUNT_H
+
+/*
+ * Variant of atomic_t specialized for reference counts.
+ *
+ * The interface matches the atomic_t interface (to aid in porting) but only
+ * provides the few functions one should use for reference counting.
+ *
+ * It differs in that the counter saturates at UINT_MAX and will not move once
+ * there. This avoids wrapping the counter and causing 'spurious'
+ * use-after-free issues.
+ *
+ * Memory ordering rules are slightly relaxed wrt regular atomic_t functions
+ * and provide only what is strictly required for refcounts.
+ *
+ * The increments are fully relaxed; these will not provide ordering. The
+ * rationale is that whatever is used to obtain the object we're increasing the
+ * reference count on will provide the ordering. For locked data structures,
+ * its the lock acquire, for RCU/lockless data structures its the dependent
+ * load.
+ *
+ * Do note that inc_not_zero() provides a control dependency which will order
+ * future stores against the inc, this ensures we'll never modify the object
+ * if we did not in fact acquire a reference.
+ *
+ * The decrements will provide release order, such that all the prior loads and
+ * stores will be issued before, it also provides a control dependency, which
+ * will order us against the subsequent free().
+ *
+ * The control dependency is against the load of the cmpxchg (ll/sc) that
+ * succeeded. This means the stores aren't fully ordered, but this is fine
+ * because the 1->0 transition indicates no concurrency.
+ *
+ * Note that the allocator is responsible for ordering things between free()
+ * and alloc().
+ *
+ */
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_DEBUG_REFCOUNT
+#define REFCOUNT_WARN(cond, str) WARN_ON(cond)
+#define __refcount_check	__must_check
+#else
+#define REFCOUNT_WARN(cond, str) (void)(cond)
+#define __refcount_check
+#endif
+
+typedef struct refcount_struct {
+	atomic_t refs;
+} refcount_t;
+
+#define REFCOUNT_INIT(n)	{ .refs = ATOMIC_INIT(n), }
+
+static inline void refcount_set(refcount_t *r, unsigned int n)
+{
+	atomic_set(&r->refs, n);
+}
+
+static inline unsigned int refcount_read(const refcount_t *r)
+{
+	return atomic_read(&r->refs);
+}
+
+static inline __refcount_check
+bool refcount_add_not_zero(unsigned int i, refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		if (!val)
+			return false;
+
+		if (unlikely(val == UINT_MAX))
+			return true;
+
+		new = val + i;
+		if (new < val)
+			new = UINT_MAX;
+		old = atomic_cmpxchg_relaxed(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+
+	return true;
+}
+
+static inline void refcount_add(unsigned int i, refcount_t *r)
+{
+	REFCOUNT_WARN(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+}
+
+/*
+ * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller has guaranteed the
+ * object memory to be stable (RCU, etc.). It does provide a control dependency
+ * and thereby orders future stores. See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_inc_not_zero(refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		new = val + 1;
+
+		if (!val)
+			return false;
+
+		if (unlikely(!new))
+			return true;
+
+		old = atomic_cmpxchg_relaxed(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+
+	return true;
+}
+
+/*
+ * Similar to atomic_inc(), will saturate at UINT_MAX and WARN.
+ *
+ * Provides no memory ordering, it is assumed the caller already has a
+ * reference on the object, will WARN when this is not so.
+ */
+static inline void refcount_inc(refcount_t *r)
+{
+	REFCOUNT_WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+}
+
+/*
+ * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
+ * decrement when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		if (unlikely(val == UINT_MAX))
+			return false;
+
+		new = val - i;
+		if (new > val) {
+			REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			return false;
+		}
+
+		old = atomic_cmpxchg_release(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	return !new;
+}
+
+static inline __refcount_check
+bool refcount_dec_and_test(refcount_t *r)
+{
+	return refcount_sub_and_test(1, r);
+}
+
+/*
+ * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
+ * when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before.
+ */
+static inline
+void refcount_dec(refcount_t *r)
+{
+	REFCOUNT_WARN(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+}
+
+/*
+ * No atomic_t counterpart, it attempts a 1 -> 0 transition and returns the
+ * success thereof.
+ *
+ * Like all decrement operations, it provides release memory order and provides
+ * a control dependency.
+ *
+ * It can be used like a try-delete operator; this explicit case is provided
+ * and not cmpxchg in generic, because that would allow implementing unsafe
+ * operations.
+ */
+static inline __refcount_check
+bool refcount_dec_if_one(refcount_t *r)
+{
+	return atomic_cmpxchg_release(&r->refs, 1, 0) == 1;
+}
+
+/*
+ * No atomic_t counterpart, it decrements unless the value is 1, in which case
+ * it will return false.
+ *
+ * Was often done like: atomic_add_unless(&var, -1, 1)
+ */
+static inline __refcount_check
+bool refcount_dec_not_one(refcount_t *r)
+{
+	unsigned int old, new, val = atomic_read(&r->refs);
+
+	for (;;) {
+		if (unlikely(val == UINT_MAX))
+			return true;
+
+		if (val == 1)
+			return false;
+
+		new = val - 1;
+		if (new > val) {
+			REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			return true;
+		}
+
+		old = atomic_cmpxchg_release(&r->refs, val, new);
+		if (old == val)
+			break;
+
+		val = old;
+	}
+
+	return true;
+}
+
+/*
+ * Similar to atomic_dec_and_mutex_lock(), it will WARN on underflow and fail
+ * to decrement when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock)
+{
+	if (refcount_dec_not_one(r))
+		return false;
+
+	mutex_lock(lock);
+	if (!refcount_dec_and_test(r)) {
+		mutex_unlock(lock);
+		return false;
+	}
+
+	return true;
+}
+
+/*
+ * Similar to atomic_dec_and_lock(), it will WARN on underflow and fail to
+ * decrement when saturated at UINT_MAX.
+ *
+ * Provides release memory ordering, such that prior loads and stores are done
+ * before, and provides a control dependency such that free() must come after.
+ * See the comment on top.
+ */
+static inline __refcount_check
+bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock)
+{
+	if (refcount_dec_not_one(r))
+		return false;
+
+	spin_lock(lock);
+	if (!refcount_dec_and_test(r)) {
+		spin_unlock(lock);
+		return false;
+	}
+
+	return true;
+}
+
+#endif /* _LINUX_REFCOUNT_H */
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index f6673132431d..e88649225a60 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -40,12 +40,13 @@ enum regcache_type {
 };
 
 /**
- * Default value for a register.  We use an array of structs rather
- * than a simple array as many modern devices have very sparse
- * register maps.
+ * struct reg_default - Default value for a register.
  *
  * @reg: Register address.
  * @def: Register default value.
+ *
+ * We use an array of structs rather than a simple array as many modern devices
+ * have very sparse register maps.
  */
 struct reg_default {
 	unsigned int reg;
@@ -53,12 +54,14 @@ struct reg_default {
 };
 
 /**
- * Register/value pairs for sequences of writes with an optional delay in
- * microseconds to be applied after each write.
+ * struct reg_sequence - An individual write from a sequence of writes.
  *
  * @reg: Register address.
  * @def: Register value.
  * @delay_us: Delay to be applied after the register write in microseconds
+ *
+ * Register/value pairs for sequences of writes with an optional delay in
+ * microseconds to be applied after each write.
  */
 struct reg_sequence {
 	unsigned int reg;
@@ -98,6 +101,7 @@ struct reg_sequence {
 
 /**
  * regmap_read_poll_timeout - Poll until a condition is met or a timeout occurs
+ *
  * @map: Regmap to read from
  * @addr: Address to poll
  * @val: Unsigned integer variable to read the value into
@@ -146,8 +150,8 @@ enum regmap_endian {
 };
 
 /**
- * A register range, used for access related checks
- * (readable/writeable/volatile/precious checks)
+ * struct regmap_range - A register range, used for access related checks
+ *                       (readable/writeable/volatile/precious checks)
  *
  * @range_min: address of first register
  * @range_max: address of last register
@@ -159,16 +163,18 @@ struct regmap_range {
 
 #define regmap_reg_range(low, high) { .range_min = low, .range_max = high, }
 
-/*
- * A table of ranges including some yes ranges and some no ranges.
- * If a register belongs to a no_range, the corresponding check function
- * will return false. If a register belongs to a yes range, the corresponding
- * check function will return true. "no_ranges" are searched first.
+/**
+ * struct regmap_access_table - A table of register ranges for access checks
  *
  * @yes_ranges : pointer to an array of regmap ranges used as "yes ranges"
  * @n_yes_ranges: size of the above array
  * @no_ranges: pointer to an array of regmap ranges used as "no ranges"
  * @n_no_ranges: size of the above array
+ *
+ * A table of ranges including some yes ranges and some no ranges.
+ * If a register belongs to a no_range, the corresponding check function
+ * will return false. If a register belongs to a yes range, the corresponding
+ * check function will return true. "no_ranges" are searched first.
  */
 struct regmap_access_table {
 	const struct regmap_range *yes_ranges;
@@ -181,7 +187,7 @@ typedef void (*regmap_lock)(void *);
 typedef void (*regmap_unlock)(void *);
 
 /**
- * Configuration for the register map of a device.
+ * struct regmap_config - Configuration for the register map of a device.
  *
  * @name: Optional name of the regmap. Useful when a device has multiple
  *        register regions.
@@ -314,22 +320,24 @@ struct regmap_config {
 };
 
 /**
- * Configuration for indirectly accessed or paged registers.
- * Registers, mapped to this virtual range, are accessed in two steps:
- *     1. page selector register update;
- *     2. access through data window registers.
+ * struct regmap_range_cfg - Configuration for indirectly accessed or paged
+ *                           registers.
  *
  * @name: Descriptive name for diagnostics
  *
  * @range_min: Address of the lowest register address in virtual range.
  * @range_max: Address of the highest register in virtual range.
  *
- * @page_sel_reg: Register with selector field.
- * @page_sel_mask: Bit shift for selector value.
- * @page_sel_shift: Bit mask for selector value.
+ * @selector_reg: Register with selector field.
+ * @selector_mask: Bit shift for selector value.
+ * @selector_shift: Bit mask for selector value.
  *
  * @window_start: Address of first (lowest) register in data window.
  * @window_len: Number of registers in data window.
+ *
+ * Registers, mapped to this virtual range, are accessed in two steps:
+ *     1. page selector register update;
+ *     2. access through data window registers.
  */
 struct regmap_range_cfg {
 	const char *name;
@@ -372,7 +380,8 @@ typedef struct regmap_async *(*regmap_hw_async_alloc)(void);
 typedef void (*regmap_hw_free_context)(void *context);
 
 /**
- * Description of a hardware bus for the register map infrastructure.
+ * struct regmap_bus - Description of a hardware bus for the register map
+ *                     infrastructure.
  *
  * @fast_io: Register IO is fast. Use a spinlock instead of a mutex
  *	     to perform locking. This field is ignored if custom lock/unlock
@@ -385,6 +394,10 @@ typedef void (*regmap_hw_free_context)(void *context);
  *               must serialise with respect to non-async I/O.
  * @reg_write: Write a single register value to the given register address. This
  *             write operation has to complete when returning from the function.
+ * @reg_update_bits: Update bits operation to be used against volatile
+ *                   registers, intended for devices supporting some mechanism
+ *                   for setting clearing bits without having to
+ *                   read/modify/write.
  * @read: Read operation.  Data is returned in the buffer used to transmit
  *         data.
  * @reg_read: Read a single register value from a given register address.
@@ -514,7 +527,7 @@ struct regmap *__devm_regmap_init_ac97(struct snd_ac97 *ac97,
 #endif
 
 /**
- * regmap_init(): Initialise register map
+ * regmap_init() - Initialise register map
  *
  * @dev: Device that will be interacted with
  * @bus: Bus-specific callbacks to use with device
@@ -532,7 +545,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 		      const struct regmap_config *config);
 
 /**
- * regmap_init_i2c(): Initialise register map
+ * regmap_init_i2c() - Initialise register map
  *
  * @i2c: Device that will be interacted with
  * @config: Configuration for register map
@@ -545,9 +558,9 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 				i2c, config)
 
 /**
- * regmap_init_spi(): Initialise register map
+ * regmap_init_spi() - Initialise register map
  *
- * @spi: Device that will be interacted with
+ * @dev: Device that will be interacted with
  * @config: Configuration for register map
  *
  * The return value will be an ERR_PTR() on error or a valid pointer to
@@ -558,8 +571,9 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 				dev, config)
 
 /**
- * regmap_init_spmi_base(): Create regmap for the Base register space
- * @sdev:	SPMI device that will be interacted with
+ * regmap_init_spmi_base() - Create regmap for the Base register space
+ *
+ * @dev:	SPMI device that will be interacted with
  * @config:	Configuration for register map
  *
  * The return value will be an ERR_PTR() on error or a valid pointer to
@@ -570,8 +584,9 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 				dev, config)
 
 /**
- * regmap_init_spmi_ext(): Create regmap for Ext register space
- * @sdev:	Device that will be interacted with
+ * regmap_init_spmi_ext() - Create regmap for Ext register space
+ *
+ * @dev:	Device that will be interacted with
  * @config:	Configuration for register map
  *
  * The return value will be an ERR_PTR() on error or a valid pointer to
@@ -582,7 +597,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 				dev, config)
 
 /**
- * regmap_init_mmio_clk(): Initialise register map with register clock
+ * regmap_init_mmio_clk() - Initialise register map with register clock
  *
  * @dev: Device that will be interacted with
  * @clk_id: register clock consumer ID
@@ -597,7 +612,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 				dev, clk_id, regs, config)
 
 /**
- * regmap_init_mmio(): Initialise register map
+ * regmap_init_mmio() - Initialise register map
  *
  * @dev: Device that will be interacted with
  * @regs: Pointer to memory-mapped IO region
@@ -610,7 +625,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 	regmap_init_mmio_clk(dev, NULL, regs, config)
 
 /**
- * regmap_init_ac97(): Initialise AC'97 register map
+ * regmap_init_ac97() - Initialise AC'97 register map
  *
  * @ac97: Device that will be interacted with
  * @config: Configuration for register map
@@ -624,7 +639,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 
 /**
- * devm_regmap_init(): Initialise managed register map
+ * devm_regmap_init() - Initialise managed register map
  *
  * @dev: Device that will be interacted with
  * @bus: Bus-specific callbacks to use with device
@@ -641,7 +656,7 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 				dev, bus, bus_context, config)
 
 /**
- * devm_regmap_init_i2c(): Initialise managed register map
+ * devm_regmap_init_i2c() - Initialise managed register map
  *
  * @i2c: Device that will be interacted with
  * @config: Configuration for register map
@@ -655,9 +670,9 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 				i2c, config)
 
 /**
- * devm_regmap_init_spi(): Initialise register map
+ * devm_regmap_init_spi() - Initialise register map
  *
- * @spi: Device that will be interacted with
+ * @dev: Device that will be interacted with
  * @config: Configuration for register map
  *
  * The return value will be an ERR_PTR() on error or a valid pointer
@@ -669,8 +684,9 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 				dev, config)
 
 /**
- * devm_regmap_init_spmi_base(): Create managed regmap for Base register space
- * @sdev:	SPMI device that will be interacted with
+ * devm_regmap_init_spmi_base() - Create managed regmap for Base register space
+ *
+ * @dev:	SPMI device that will be interacted with
  * @config:	Configuration for register map
  *
  * The return value will be an ERR_PTR() on error or a valid pointer
@@ -682,8 +698,9 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 				dev, config)
 
 /**
- * devm_regmap_init_spmi_ext(): Create managed regmap for Ext register space
- * @sdev:	SPMI device that will be interacted with
+ * devm_regmap_init_spmi_ext() - Create managed regmap for Ext register space
+ *
+ * @dev:	SPMI device that will be interacted with
  * @config:	Configuration for register map
  *
  * The return value will be an ERR_PTR() on error or a valid pointer
@@ -695,7 +712,7 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 				dev, config)
 
 /**
- * devm_regmap_init_mmio_clk(): Initialise managed register map with clock
+ * devm_regmap_init_mmio_clk() - Initialise managed register map with clock
  *
  * @dev: Device that will be interacted with
  * @clk_id: register clock consumer ID
@@ -711,7 +728,7 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 				dev, clk_id, regs, config)
 
 /**
- * devm_regmap_init_mmio(): Initialise managed register map
+ * devm_regmap_init_mmio() - Initialise managed register map
  *
  * @dev: Device that will be interacted with
  * @regs: Pointer to memory-mapped IO region
@@ -725,7 +742,7 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 	devm_regmap_init_mmio_clk(dev, NULL, regs, config)
 
 /**
- * devm_regmap_init_ac97(): Initialise AC'97 register map
+ * devm_regmap_init_ac97() - Initialise AC'97 register map
  *
  * @ac97: Device that will be interacted with
  * @config: Configuration for register map
@@ -800,7 +817,7 @@ bool regmap_reg_in_ranges(unsigned int reg,
 			  unsigned int nranges);
 
 /**
- * Description of an register field
+ * struct reg_field - Description of an register field
  *
  * @reg: Offset of the register within the regmap bank
  * @lsb: lsb of the register field.
@@ -841,7 +858,7 @@ int regmap_fields_update_bits_base(struct regmap_field *field,  unsigned int id,
 				   bool *change, bool async, bool force);
 
 /**
- * Description of an IRQ for the generic regmap irq_chip.
+ * struct regmap_irq - Description of an IRQ for the generic regmap irq_chip.
  *
  * @reg_offset: Offset of the status/mask register within the bank
  * @mask:       Mask used to flag/control the register.
@@ -861,9 +878,7 @@ struct regmap_irq {
 	[_irq] = { .reg_offset = (_off), .mask = (_mask) }
 
 /**
- * Description of a generic regmap irq_chip.  This is not intended to
- * handle every possible interrupt controller, but it should handle a
- * substantial proportion of those that are found in the wild.
+ * struct regmap_irq_chip - Description of a generic regmap irq_chip.
  *
  * @name:        Descriptive name for IRQ controller.
  *
@@ -897,6 +912,10 @@ struct regmap_irq {
  *		     after handling the interrupts in regmap_irq_handler().
  * @irq_drv_data:    Driver specific IRQ data which is passed as parameter when
  *		     driver specific pre/post interrupt handler is called.
+ *
+ * This is not intended to handle every possible interrupt controller, but
+ * it should handle a substantial proportion of those that are found in the
+ * wild.
  */
 struct regmap_irq_chip {
 	const char *name;
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index f017fd6e69c4..d4e0a204c118 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -259,6 +259,26 @@ static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr)
 unsigned int sbitmap_weight(const struct sbitmap *sb);
 
 /**
+ * sbitmap_show() - Dump &struct sbitmap information to a &struct seq_file.
+ * @sb: Bitmap to show.
+ * @m: struct seq_file to write to.
+ *
+ * This is intended for debugging. The format may change at any time.
+ */
+void sbitmap_show(struct sbitmap *sb, struct seq_file *m);
+
+/**
+ * sbitmap_bitmap_show() - Write a hex dump of a &struct sbitmap to a &struct
+ * seq_file.
+ * @sb: Bitmap to show.
+ * @m: struct seq_file to write to.
+ *
+ * This is intended for debugging. The output isn't guaranteed to be internally
+ * consistent.
+ */
+void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m);
+
+/**
  * sbitmap_queue_init_node() - Initialize a &struct sbitmap_queue on a specific
  * memory node.
  * @sbq: Bitmap queue to initialize.
@@ -370,4 +390,14 @@ static inline struct sbq_wait_state *sbq_wait_ptr(struct sbitmap_queue *sbq,
  */
 void sbitmap_queue_wake_all(struct sbitmap_queue *sbq);
 
+/**
+ * sbitmap_queue_show() - Dump &struct sbitmap_queue information to a &struct
+ * seq_file.
+ * @sbq: Bitmap queue to show.
+ * @m: struct seq_file to write to.
+ *
+ * This is intended for debugging. The format may change at any time.
+ */
+void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m);
+
 #endif /* __LINUX_SCALE_BITMAP_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ad3ec9ec61f7..c8e519d0b4a3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -29,7 +29,6 @@ struct sched_param {
 
 #include <asm/page.h>
 #include <asm/ptrace.h>
-#include <linux/cputime.h>
 
 #include <linux/smp.h>
 #include <linux/sem.h>
@@ -227,7 +226,7 @@ extern void proc_sched_set_task(struct task_struct *p);
 extern char ___assert_task_state[1 - 2*!!(
 		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
 
-/* Convenience macros for the sake of set_task_state */
+/* Convenience macros for the sake of set_current_state */
 #define TASK_KILLABLE		(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
 #define TASK_STOPPED		(TASK_WAKEKILL | __TASK_STOPPED)
 #define TASK_TRACED		(TASK_WAKEKILL | __TASK_TRACED)
@@ -254,17 +253,6 @@ extern char ___assert_task_state[1 - 2*!!(
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
-#define __set_task_state(tsk, state_value)			\
-	do {							\
-		(tsk)->task_state_change = _THIS_IP_;		\
-		(tsk)->state = (state_value);			\
-	} while (0)
-#define set_task_state(tsk, state_value)			\
-	do {							\
-		(tsk)->task_state_change = _THIS_IP_;		\
-		smp_store_mb((tsk)->state, (state_value));	\
-	} while (0)
-
 #define __set_current_state(state_value)			\
 	do {							\
 		current->task_state_change = _THIS_IP_;		\
@@ -277,20 +265,6 @@ extern char ___assert_task_state[1 - 2*!!(
 	} while (0)
 
 #else
-
-/*
- * @tsk had better be current, or you get to keep the pieces.
- *
- * The only reason is that computing current can be more expensive than
- * using a pointer that's already available.
- *
- * Therefore, see set_current_state().
- */
-#define __set_task_state(tsk, state_value)		\
-	do { (tsk)->state = (state_value); } while (0)
-#define set_task_state(tsk, state_value)		\
-	smp_store_mb((tsk)->state, (state_value))
-
 /*
  * set_current_state() includes a barrier so that the write of current->state
  * is correctly serialised wrt the caller's subsequent test of whether to
@@ -461,12 +435,10 @@ extern signed long schedule_timeout_idle(signed long timeout);
 asmlinkage void schedule(void);
 extern void schedule_preempt_disabled(void);
 
+extern int __must_check io_schedule_prepare(void);
+extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
-
-static inline void io_schedule(void)
-{
-	io_schedule_timeout(MAX_SCHEDULE_TIMEOUT);
-}
+extern void io_schedule(void);
 
 void __noreturn do_task_dead(void);
 
@@ -565,15 +537,13 @@ struct pacct_struct {
 	int			ac_flag;
 	long			ac_exitcode;
 	unsigned long		ac_mem;
-	cputime_t		ac_utime, ac_stime;
+	u64			ac_utime, ac_stime;
 	unsigned long		ac_minflt, ac_majflt;
 };
 
 struct cpu_itimer {
-	cputime_t expires;
-	cputime_t incr;
-	u32 error;
-	u32 incr_error;
+	u64 expires;
+	u64 incr;
 };
 
 /**
@@ -587,8 +557,8 @@ struct cpu_itimer {
  */
 struct prev_cputime {
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	cputime_t utime;
-	cputime_t stime;
+	u64 utime;
+	u64 stime;
 	raw_spinlock_t lock;
 #endif
 };
@@ -603,8 +573,8 @@ static inline void prev_cputime_init(struct prev_cputime *prev)
 
 /**
  * struct task_cputime - collected CPU time counts
- * @utime:		time spent in user mode, in &cputime_t units
- * @stime:		time spent in kernel mode, in &cputime_t units
+ * @utime:		time spent in user mode, in nanoseconds
+ * @stime:		time spent in kernel mode, in nanoseconds
  * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
  *
  * This structure groups together three kinds of CPU time that are tracked for
@@ -612,8 +582,8 @@ static inline void prev_cputime_init(struct prev_cputime *prev)
  * these counts together and treat all three of them in parallel.
  */
 struct task_cputime {
-	cputime_t utime;
-	cputime_t stime;
+	u64 utime;
+	u64 stime;
 	unsigned long long sum_exec_runtime;
 };
 
@@ -622,13 +592,6 @@ struct task_cputime {
 #define prof_exp	stime
 #define sched_exp	sum_exec_runtime
 
-#define INIT_CPUTIME	\
-	(struct task_cputime) {					\
-		.utime = 0,					\
-		.stime = 0,					\
-		.sum_exec_runtime = 0,				\
-	}
-
 /*
  * This is the atomic variant of task_cputime, which can be used for
  * storing and updating task_cputime statistics without locking.
@@ -734,13 +697,14 @@ struct signal_struct {
 	unsigned int		is_child_subreaper:1;
 	unsigned int		has_child_subreaper:1;
 
+#ifdef CONFIG_POSIX_TIMERS
+
 	/* POSIX.1b Interval Timers */
 	int			posix_timer_id;
 	struct list_head	posix_timers;
 
 	/* ITIMER_REAL timer for the process */
 	struct hrtimer real_timer;
-	struct pid *leader_pid;
 	ktime_t it_real_incr;
 
 	/*
@@ -759,12 +723,16 @@ struct signal_struct {
 	/* Earliest-expiration cache. */
 	struct task_cputime cputime_expires;
 
+	struct list_head cpu_timers[3];
+
+#endif
+
+	struct pid *leader_pid;
+
 #ifdef CONFIG_NO_HZ_FULL
 	atomic_t tick_dep_mask;
 #endif
 
-	struct list_head cpu_timers[3];
-
 	struct pid *tty_old_pgrp;
 
 	/* boolean value for session group leader */
@@ -782,9 +750,9 @@ struct signal_struct {
 	 * in __exit_signal, except for the group leader.
 	 */
 	seqlock_t stats_lock;
-	cputime_t utime, stime, cutime, cstime;
-	cputime_t gtime;
-	cputime_t cgtime;
+	u64 utime, stime, cutime, cstime;
+	u64 gtime;
+	u64 cgtime;
 	struct prev_cputime prev_cputime;
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
 	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
@@ -1025,8 +993,8 @@ enum cpu_idle_type {
  *
  * The DEFINE_WAKE_Q macro declares and initializes the list head.
  * wake_up_q() does NOT reinitialize the list; it's expected to be
- * called near the end of a function, where the fact that the queue is
- * not used again will be easy to see by inspection.
+ * called near the end of a function. Otherwise, the list can be
+ * re-initialized for later re-use by wake_q_init().
  *
  * Note that this can cause spurious wakeups. schedule() callers
  * must ensure the call is done inside a loop, confirming that the
@@ -1046,6 +1014,12 @@ struct wake_q_head {
 #define DEFINE_WAKE_Q(name)				\
 	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
 
+static inline void wake_q_init(struct wake_q_head *head)
+{
+	head->first = WAKE_Q_TAIL;
+	head->lastp = &head->first;
+}
+
 extern void wake_q_add(struct wake_q_head *head,
 		       struct task_struct *task);
 extern void wake_up_q(struct wake_q_head *head);
@@ -1663,11 +1637,11 @@ struct task_struct {
 	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
 	int __user *clear_child_tid;		/* CLONE_CHILD_CLEARTID */
 
-	cputime_t utime, stime;
+	u64 utime, stime;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
-	cputime_t utimescaled, stimescaled;
+	u64 utimescaled, stimescaled;
 #endif
-	cputime_t gtime;
+	u64 gtime;
 	struct prev_cputime prev_cputime;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 	seqcount_t vtime_seqcount;
@@ -1691,8 +1665,10 @@ struct task_struct {
 /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
 	unsigned long min_flt, maj_flt;
 
+#ifdef CONFIG_POSIX_TIMERS
 	struct task_cputime cputime_expires;
 	struct list_head cpu_timers[3];
+#endif
 
 /* process credentials */
 	const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */
@@ -1817,7 +1793,7 @@ struct task_struct {
 #if defined(CONFIG_TASK_XACCT)
 	u64 acct_rss_mem1;	/* accumulated rss usage */
 	u64 acct_vm_mem1;	/* accumulated virtual memory usage */
-	cputime_t acct_timexpd;	/* stime + utime since last update */
+	u64 acct_timexpd;	/* stime + utime since last update */
 #endif
 #ifdef CONFIG_CPUSETS
 	nodemask_t mems_allowed;	/* Protected by alloc_lock */
@@ -2262,17 +2238,17 @@ struct task_struct *try_get_task_struct(struct task_struct **ptask);
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 extern void task_cputime(struct task_struct *t,
-			 cputime_t *utime, cputime_t *stime);
-extern cputime_t task_gtime(struct task_struct *t);
+			 u64 *utime, u64 *stime);
+extern u64 task_gtime(struct task_struct *t);
 #else
 static inline void task_cputime(struct task_struct *t,
-				cputime_t *utime, cputime_t *stime)
+				u64 *utime, u64 *stime)
 {
 	*utime = t->utime;
 	*stime = t->stime;
 }
 
-static inline cputime_t task_gtime(struct task_struct *t)
+static inline u64 task_gtime(struct task_struct *t)
 {
 	return t->gtime;
 }
@@ -2280,23 +2256,23 @@ static inline cputime_t task_gtime(struct task_struct *t)
 
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 static inline void task_cputime_scaled(struct task_struct *t,
-				       cputime_t *utimescaled,
-				       cputime_t *stimescaled)
+				       u64 *utimescaled,
+				       u64 *stimescaled)
 {
 	*utimescaled = t->utimescaled;
 	*stimescaled = t->stimescaled;
 }
 #else
 static inline void task_cputime_scaled(struct task_struct *t,
-				       cputime_t *utimescaled,
-				       cputime_t *stimescaled)
+				       u64 *utimescaled,
+				       u64 *stimescaled)
 {
 	task_cputime(t, utimescaled, stimescaled);
 }
 #endif
 
-extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
-extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
+extern void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
+extern void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st);
 
 /*
  * Per process flags
@@ -2515,10 +2491,18 @@ extern u64 sched_clock_cpu(int cpu);
 extern void sched_clock_init(void);
 
 #ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static inline void sched_clock_init_late(void)
+{
+}
+
 static inline void sched_clock_tick(void)
 {
 }
 
+static inline void clear_sched_clock_stable(void)
+{
+}
+
 static inline void sched_clock_idle_sleep_event(void)
 {
 }
@@ -2537,6 +2521,7 @@ static inline u64 local_clock(void)
 	return sched_clock();
 }
 #else
+extern void sched_clock_init_late(void);
 /*
  * Architectures can set this to 1 if they have specified
  * CONFIG_HAVE_UNSTABLE_SCHED_CLOCK in their arch Kconfig,
@@ -2544,7 +2529,6 @@ static inline u64 local_clock(void)
  * is reliable after all:
  */
 extern int sched_clock_stable(void);
-extern void set_sched_clock_stable(void);
 extern void clear_sched_clock_stable(void);
 
 extern void sched_clock_tick(void);
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 441145351301..49308e142aae 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -59,6 +59,7 @@ extern unsigned int sysctl_sched_cfs_bandwidth_slice;
 extern unsigned int sysctl_sched_autogroup_enabled;
 #endif
 
+extern int sysctl_sched_rr_timeslice;
 extern int sched_rr_timeslice;
 
 extern int sched_rr_handler(struct ctl_table *table, int write,
diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h
new file mode 100644
index 000000000000..deee23d012e7
--- /dev/null
+++ b/include/linux/sed-opal.h
@@ -0,0 +1,70 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Authors:
+ *    Rafael Antognolli <rafael.antognolli@intel.com>
+ *    Scott  Bauer      <scott.bauer@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef LINUX_OPAL_H
+#define LINUX_OPAL_H
+
+#include <uapi/linux/sed-opal.h>
+#include <linux/kernel.h>
+
+struct opal_dev;
+
+typedef int (sec_send_recv)(void *data, u16 spsp, u8 secp, void *buffer,
+		size_t len, bool send);
+
+#ifdef CONFIG_BLK_SED_OPAL
+bool opal_unlock_from_suspend(struct opal_dev *dev);
+struct opal_dev *init_opal_dev(void *data, sec_send_recv *send_recv);
+int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *ioctl_ptr);
+
+static inline bool is_sed_ioctl(unsigned int cmd)
+{
+	switch (cmd) {
+	case IOC_OPAL_SAVE:
+	case IOC_OPAL_LOCK_UNLOCK:
+	case IOC_OPAL_TAKE_OWNERSHIP:
+	case IOC_OPAL_ACTIVATE_LSP:
+	case IOC_OPAL_SET_PW:
+	case IOC_OPAL_ACTIVATE_USR:
+	case IOC_OPAL_REVERT_TPR:
+	case IOC_OPAL_LR_SETUP:
+	case IOC_OPAL_ADD_USR_TO_LR:
+	case IOC_OPAL_ENABLE_DISABLE_MBR:
+	case IOC_OPAL_ERASE_LR:
+	case IOC_OPAL_SECURE_ERASE_LR:
+		return true;
+	}
+	return false;
+}
+#else
+static inline bool is_sed_ioctl(unsigned int cmd)
+{
+	return false;
+}
+
+static inline int sed_ioctl(struct opal_dev *dev, unsigned int cmd,
+			    void __user *ioctl_ptr)
+{
+	return 0;
+}
+static inline bool opal_unlock_from_suspend(struct opal_dev *dev)
+{
+	return false;
+}
+#define init_opal_dev(data, send_recv)		NULL
+#endif /* CONFIG_BLK_SED_OPAL */
+#endif /* LINUX_OPAL_H */
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 47dd0cebd204..59248dcc6ef3 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -180,8 +180,6 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define raw_spin_lock_nested(lock, subclass) \
 	_raw_spin_lock_nested(lock, subclass)
-# define raw_spin_lock_bh_nested(lock, subclass) \
-	_raw_spin_lock_bh_nested(lock, subclass)
 
 # define raw_spin_lock_nest_lock(lock, nest_lock)			\
 	 do {								\
@@ -197,7 +195,6 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 # define raw_spin_lock_nested(lock, subclass)		\
 	_raw_spin_lock(((void)(subclass), (lock)))
 # define raw_spin_lock_nest_lock(lock, nest_lock)	_raw_spin_lock(lock)
-# define raw_spin_lock_bh_nested(lock, subclass)	_raw_spin_lock_bh(lock)
 #endif
 
 #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
@@ -317,11 +314,6 @@ do {								\
 	raw_spin_lock_nested(spinlock_check(lock), subclass);	\
 } while (0)
 
-#define spin_lock_bh_nested(lock, subclass)			\
-do {								\
-	raw_spin_lock_bh_nested(spinlock_check(lock), subclass);\
-} while (0)
-
 #define spin_lock_nest_lock(lock, nest_lock)				\
 do {									\
 	raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock);	\
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index 5344268e6e62..42dfab89e740 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -22,8 +22,6 @@ int in_lock_functions(unsigned long addr);
 void __lockfunc _raw_spin_lock(raw_spinlock_t *lock)		__acquires(lock);
 void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
 								__acquires(lock);
-void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass)
-								__acquires(lock);
 void __lockfunc
 _raw_spin_lock_nest_lock(raw_spinlock_t *lock, struct lockdep_map *map)
 								__acquires(lock);
diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h
index d3afef9d8dbe..d0d188861ad6 100644
--- a/include/linux/spinlock_api_up.h
+++ b/include/linux/spinlock_api_up.h
@@ -57,7 +57,6 @@
 
 #define _raw_spin_lock(lock)			__LOCK(lock)
 #define _raw_spin_lock_nested(lock, subclass)	__LOCK(lock)
-#define _raw_spin_lock_bh_nested(lock, subclass) __LOCK(lock)
 #define _raw_read_lock(lock)			__LOCK(lock)
 #define _raw_write_lock(lock)			__LOCK(lock)
 #define _raw_spin_lock_bh(lock)			__LOCK_BH(lock)
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index dc8eb63c6568..a598cf3ac70c 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -33,9 +33,9 @@
 #include <linux/rcupdate.h>
 #include <linux/workqueue.h>
 
-struct srcu_struct_array {
-	unsigned long c[2];
-	unsigned long seq[2];
+struct srcu_array {
+	unsigned long lock_count[2];
+	unsigned long unlock_count[2];
 };
 
 struct rcu_batch {
@@ -46,7 +46,7 @@ struct rcu_batch {
 
 struct srcu_struct {
 	unsigned long completed;
-	struct srcu_struct_array __percpu *per_cpu_ref;
+	struct srcu_array __percpu *per_cpu_ref;
 	spinlock_t queue_lock; /* protect ->batch_queue, ->running */
 	bool running;
 	/* callbacks just queued */
@@ -118,7 +118,7 @@ void process_srcu(struct work_struct *work);
  * See include/linux/percpu-defs.h for the rules on per-CPU variables.
  */
 #define __DEFINE_SRCU(name, is_static)					\
-	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
+	static DEFINE_PER_CPU(struct srcu_array, name##_srcu_array);\
 	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
 #define DEFINE_SRCU(name)		__DEFINE_SRCU(name, /* not static */)
 #define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, static)
diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h
index 62a60eeacb0a..8a511c0985aa 100644
--- a/include/linux/sunrpc/cache.h
+++ b/include/linux/sunrpc/cache.h
@@ -198,7 +198,7 @@ static inline struct cache_head  *cache_get(struct cache_head *h)
 
 static inline void cache_put(struct cache_head *h, struct cache_detail *cd)
 {
-	if (atomic_read(&h->ref.refcount) <= 2 &&
+	if (kref_read(&h->ref) <= 2 &&
 	    h->expiry_time < cd->nextcheck)
 		cd->nextcheck = h->expiry_time;
 	kref_put(&h->ref, cd->cache_put);
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 85cc819676e8..333ad11b3dd9 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -216,5 +216,6 @@ void rpc_clnt_xprt_switch_put(struct rpc_clnt *);
 void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *);
 bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt,
 			const struct sockaddr *sap);
+void rpc_cleanup_clids(void);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_CLNT_H */
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 0c729c3c8549..d9718378a8be 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -194,8 +194,6 @@ struct platform_freeze_ops {
 };
 
 #ifdef CONFIG_SUSPEND
-extern suspend_state_t mem_sleep_default;
-
 /**
  * suspend_set_ops - set platform dependent suspend operations
  * @ops: The new suspend operations to set.
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 51d601f192d4..5a209b84fd9e 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -20,11 +20,6 @@ struct timer_list {
 	unsigned long		data;
 	u32			flags;
 
-#ifdef CONFIG_TIMER_STATS
-	int			start_pid;
-	void			*start_site;
-	char			start_comm[16];
-#endif
 #ifdef CONFIG_LOCKDEP
 	struct lockdep_map	lockdep_map;
 #endif
@@ -197,46 +192,6 @@ extern int mod_timer_pending(struct timer_list *timer, unsigned long expires);
  */
 #define NEXT_TIMER_MAX_DELTA	((1UL << 30) - 1)
 
-/*
- * Timer-statistics info:
- */
-#ifdef CONFIG_TIMER_STATS
-
-extern int timer_stats_active;
-
-extern void init_timer_stats(void);
-
-extern void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
-				     void *timerf, char *comm, u32 flags);
-
-extern void __timer_stats_timer_set_start_info(struct timer_list *timer,
-					       void *addr);
-
-static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
-{
-	if (likely(!timer_stats_active))
-		return;
-	__timer_stats_timer_set_start_info(timer, __builtin_return_address(0));
-}
-
-static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
-{
-	timer->start_site = NULL;
-}
-#else
-static inline void init_timer_stats(void)
-{
-}
-
-static inline void timer_stats_timer_set_start_info(struct timer_list *timer)
-{
-}
-
-static inline void timer_stats_timer_clear_start_info(struct timer_list *timer)
-{
-}
-#endif
-
 extern void add_timer(struct timer_list *timer);
 
 extern int try_to_del_timer_sync(struct timer_list *timer);
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 66204007d7ac..5209b5ed2a64 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -56,7 +56,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 					  struct virtio_net_hdr *hdr,
-					  bool little_endian)
+					  bool little_endian,
+					  bool has_data_valid)
 {
 	memset(hdr, 0, sizeof(*hdr));   /* no info leak */
 
@@ -91,7 +92,8 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 				skb_checksum_start_offset(skb));
 		hdr->csum_offset = __cpu_to_virtio16(little_endian,
 				skb->csum_offset);
-	} else if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
+	} else if (has_data_valid &&
+		   skb->ip_summed == CHECKSUM_UNNECESSARY) {
 		hdr->flags = VIRTIO_NET_HDR_F_DATA_VALID;
 	} /* else everything is zero */
 
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index aa9bfea8804a..0681fe25abeb 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -58,27 +58,28 @@ static inline void vtime_task_switch(struct task_struct *prev)
 
 extern void vtime_account_system(struct task_struct *tsk);
 extern void vtime_account_idle(struct task_struct *tsk);
-extern void vtime_account_user(struct task_struct *tsk);
 
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 static inline void vtime_task_switch(struct task_struct *prev) { }
 static inline void vtime_account_system(struct task_struct *tsk) { }
-static inline void vtime_account_user(struct task_struct *tsk) { }
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 extern void arch_vtime_task_switch(struct task_struct *tsk);
+extern void vtime_account_user(struct task_struct *tsk);
 extern void vtime_user_enter(struct task_struct *tsk);
 
 static inline void vtime_user_exit(struct task_struct *tsk)
 {
 	vtime_account_user(tsk);
 }
+
 extern void vtime_guest_enter(struct task_struct *tsk);
 extern void vtime_guest_exit(struct task_struct *tsk);
 extern void vtime_init_idle(struct task_struct *tsk, int cpu);
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN  */
+static inline void vtime_account_user(struct task_struct *tsk) { }
 static inline void vtime_user_enter(struct task_struct *tsk) { }
 static inline void vtime_user_exit(struct task_struct *tsk) { }
 static inline void vtime_guest_enter(struct task_struct *tsk) { }
@@ -93,9 +94,11 @@ static inline void vtime_account_irq_exit(struct task_struct *tsk)
 	/* On hard|softirq exit we always account to hard|softirq cputime */
 	vtime_account_system(tsk);
 }
+extern void vtime_flush(struct task_struct *tsk);
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 static inline void vtime_account_irq_enter(struct task_struct *tsk) { }
 static inline void vtime_account_irq_exit(struct task_struct *tsk) { }
+static inline void vtime_flush(struct task_struct *tsk) { }
 #endif
 
 
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index 7b0066814fa0..5dd9a7682227 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -51,10 +51,10 @@ struct ww_mutex {
 };
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class) \
-		, .ww_class = &ww_class
+# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) \
+		, .ww_class = class
 #else
-# define __WW_CLASS_MUTEX_INITIALIZER(lockname, ww_class)
+# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class)
 #endif
 
 #define __WW_CLASS_INITIALIZER(ww_class) \
@@ -63,7 +63,7 @@ struct ww_mutex {
 		, .mutex_name = #ww_class "_mutex" }
 
 #define __WW_MUTEX_INITIALIZER(lockname, class) \
-		{ .base = { \__MUTEX_INITIALIZER(lockname) } \
+		{ .base =  __MUTEX_INITIALIZER(lockname.base) \
 		__WW_CLASS_MUTEX_INITIALIZER(lockname, class) }
 
 #define DEFINE_WW_CLASS(classname) \
@@ -186,11 +186,6 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx)
 #endif
 }
 
-extern int __must_check __ww_mutex_lock(struct ww_mutex *lock,
-					struct ww_acquire_ctx *ctx);
-extern int __must_check __ww_mutex_lock_interruptible(struct ww_mutex *lock,
-						      struct ww_acquire_ctx *ctx);
-
 /**
  * ww_mutex_lock - acquire the w/w mutex
  * @lock: the mutex to be acquired
@@ -220,14 +215,7 @@ extern int __must_check __ww_mutex_lock_interruptible(struct ww_mutex *lock,
  *
  * A mutex acquired with this function must be released with ww_mutex_unlock.
  */
-static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
-{
-	if (ctx)
-		return __ww_mutex_lock(lock, ctx);
-
-	mutex_lock(&lock->base);
-	return 0;
-}
+extern int /* __must_check */ ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx);
 
 /**
  * ww_mutex_lock_interruptible - acquire the w/w mutex, interruptible
@@ -259,14 +247,8 @@ static inline int ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ct
  *
  * A mutex acquired with this function must be released with ww_mutex_unlock.
  */
-static inline int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock,
-							   struct ww_acquire_ctx *ctx)
-{
-	if (ctx)
-		return __ww_mutex_lock_interruptible(lock, ctx);
-	else
-		return mutex_lock_interruptible(&lock->base);
-}
+extern int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock,
+						    struct ww_acquire_ctx *ctx);
 
 /**
  * ww_mutex_lock_slow - slowpath acquiring of the w/w mutex
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 554671c81f4a..90708f68cc02 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -987,7 +987,7 @@ static inline void hci_conn_drop(struct hci_conn *conn)
 static inline void hci_dev_put(struct hci_dev *d)
 {
 	BT_DBG("%s orig refcnt %d", d->name,
-	       atomic_read(&d->dev.kobj.kref.refcount));
+	       kref_read(&d->dev.kobj.kref));
 
 	put_device(&d->dev);
 }
@@ -995,7 +995,7 @@ static inline void hci_dev_put(struct hci_dev *d)
 static inline struct hci_dev *hci_dev_hold(struct hci_dev *d)
 {
 	BT_DBG("%s orig refcnt %d", d->name,
-	       atomic_read(&d->dev.kobj.kref.refcount));
+	       kref_read(&d->dev.kobj.kref));
 
 	get_device(&d->dev);
 	return d;
diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h
index 3ebb168b9afc..a34b141f125f 100644
--- a/include/net/cipso_ipv4.h
+++ b/include/net/cipso_ipv4.h
@@ -309,6 +309,10 @@ static inline int cipso_v4_validate(const struct sk_buff *skb,
 	}
 
 	for (opt_iter = 6; opt_iter < opt_len;) {
+		if (opt_iter + 1 == opt_len) {
+			err_offset = opt_iter;
+			goto out;
+		}
 		tag_len = opt[opt_iter + 1];
 		if ((tag_len == 0) || (tag_len > (opt_len - opt_iter))) {
 			err_offset = opt_iter + 1;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 487e57391664..dbf0abba33b8 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -776,6 +776,11 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 {
 	u32 hash;
 
+	/* @flowlabel may include more than a flow label, eg, the traffic class.
+	 * Here we want only the flow label value.
+	 */
+	flowlabel &= IPV6_FLOWLABEL_MASK;
+
 	if (flowlabel ||
 	    net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF ||
 	    (!autolabel &&
@@ -871,7 +876,7 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
  *	upper-layer output functions
  */
 int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
-	     struct ipv6_txoptions *opt, int tclass);
+	     __u32 mark, struct ipv6_txoptions *opt, int tclass);
 
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr);
 
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index d4c1c75b8862..0388b9c5f5e2 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -44,6 +44,8 @@ struct lwtunnel_encap_ops {
 	int (*get_encap_size)(struct lwtunnel_state *lwtstate);
 	int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b);
 	int (*xmit)(struct sk_buff *skb);
+
+	struct module *owner;
 };
 
 #ifdef CONFIG_LWTUNNEL
@@ -105,6 +107,8 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
 			   unsigned int num);
 int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
 			   unsigned int num);
+int lwtunnel_valid_encap_type(u16 encap_type);
+int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len);
 int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
 			 struct nlattr *encap,
 			 unsigned int family, const void *cfg,
@@ -168,6 +172,18 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
 	return -EOPNOTSUPP;
 }
 
+static inline int lwtunnel_valid_encap_type(u16 encap_type)
+{
+	return -EOPNOTSUPP;
+}
+static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len)
+{
+	/* return 0 since we are not walking attr looking for
+	 * RTA_ENCAP_TYPE attribute on nexthops.
+	 */
+	return 0;
+}
+
 static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
 				       struct nlattr *encap,
 				       unsigned int family, const void *cfg,
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 924325c46aab..7dfdb517f0be 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -207,9 +207,9 @@ struct nft_set_iter {
 	unsigned int	skip;
 	int		err;
 	int		(*fn)(const struct nft_ctx *ctx,
-			      const struct nft_set *set,
+			      struct nft_set *set,
 			      const struct nft_set_iter *iter,
-			      const struct nft_set_elem *elem);
+			      struct nft_set_elem *elem);
 };
 
 /**
@@ -301,7 +301,7 @@ struct nft_set_ops {
 	void				(*remove)(const struct nft_set *set,
 						  const struct nft_set_elem *elem);
 	void				(*walk)(const struct nft_ctx *ctx,
-						const struct nft_set *set,
+						struct nft_set *set,
 						struct nft_set_iter *iter);
 
 	unsigned int			(*privsize)(const struct nlattr * const nla[]);
diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h
index cbedda077db2..5ceb2205e4e3 100644
--- a/include/net/netfilter/nft_fib.h
+++ b/include/net/netfilter/nft_fib.h
@@ -9,6 +9,12 @@ struct nft_fib {
 
 extern const struct nla_policy nft_fib_policy[];
 
+static inline bool
+nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in)
+{
+	return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK;
+}
+
 int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr);
 int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		 const struct nlattr * const tb[]);
diff --git a/include/net/sock.h b/include/net/sock.h
index f0e867f58722..c4f5e6fca17c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2006,7 +2006,9 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer,
 void sk_stop_timer(struct sock *sk, struct timer_list *timer);
 
 int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
-			unsigned int flags);
+			unsigned int flags,
+			void (*destructor)(struct sock *sk,
+					   struct sk_buff *skb));
 int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 958a24d8fae7..b567e4452a47 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -352,6 +352,20 @@ static inline int ib_mtu_enum_to_int(enum ib_mtu mtu)
 	}
 }
 
+static inline enum ib_mtu ib_mtu_int_to_enum(int mtu)
+{
+	if (mtu >= 4096)
+		return IB_MTU_4096;
+	else if (mtu >= 2048)
+		return IB_MTU_2048;
+	else if (mtu >= 1024)
+		return IB_MTU_1024;
+	else if (mtu >= 512)
+		return IB_MTU_512;
+	else
+		return IB_MTU_256;
+}
+
 enum ib_port_state {
 	IB_PORT_NOP		= 0,
 	IB_PORT_DOWN		= 1,
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 4d1c46aac331..b0e275de6dec 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -383,6 +383,7 @@ extern int iscsi_eh_recover_target(struct scsi_cmnd *sc);
 extern int iscsi_eh_session_reset(struct scsi_cmnd *sc);
 extern int iscsi_eh_device_reset(struct scsi_cmnd *sc);
 extern int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc);
+extern enum blk_eh_timer_return iscsi_eh_cmd_timed_out(struct scsi_cmnd *sc);
 
 /*
  * iSCSI host helpers.
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index 8ec7c30e35af..a1e1930b7a87 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -29,16 +29,6 @@ enum scsi_timeouts {
  */
 #define SCAN_WILD_CARD	~0
 
-#ifdef CONFIG_ACPI
-struct acpi_bus_type;
-
-extern int
-scsi_register_acpi_bus_type(struct acpi_bus_type *bus);
-
-extern void
-scsi_unregister_acpi_bus_type(struct acpi_bus_type *bus);
-#endif
-
 /** scsi_status_is_good - check the status return.
  *
  * @status: the status passed up from the driver (including host and
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 9fc1aecfc813..b379f93a2c48 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -8,6 +8,7 @@
 #include <linux/timer.h>
 #include <linux/scatterlist.h>
 #include <scsi/scsi_device.h>
+#include <scsi/scsi_request.h>
 
 struct Scsi_Host;
 struct scsi_driver;
@@ -57,6 +58,7 @@ struct scsi_pointer {
 #define SCMD_TAGGED		(1 << 0)
 
 struct scsi_cmnd {
+	struct scsi_request req;
 	struct scsi_device *device;
 	struct list_head list;  /* scsi_cmnd participates in queue lists */
 	struct list_head eh_entry; /* entry for the host eh_cmd_q */
@@ -149,7 +151,7 @@ static inline void *scsi_cmd_priv(struct scsi_cmnd *cmd)
 	return cmd + 1;
 }
 
-/* make sure not to use it with REQ_TYPE_BLOCK_PC commands */
+/* make sure not to use it with passthrough commands */
 static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd)
 {
 	return *(struct scsi_driver **)cmd->request->rq_disk->private_data;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 36680f13270d..3cd8c3bec638 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -551,9 +551,6 @@ struct Scsi_Host {
 	struct list_head	__devices;
 	struct list_head	__targets;
 	
-	struct scsi_host_cmd_pool *cmd_pool;
-	spinlock_t		free_list_lock;
-	struct list_head	free_list; /* backup store of cmd structs */
 	struct list_head	starved_list;
 
 	spinlock_t		default_lock;
@@ -826,8 +823,6 @@ extern void scsi_block_requests(struct Scsi_Host *);
 
 struct class_container;
 
-extern struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
-						void (*) (struct request_queue *));
 /*
  * These two functions are used to allocate and free a pseudo device
  * which will connect to the host adapter itself rather than any
diff --git a/include/scsi/scsi_request.h b/include/scsi/scsi_request.h
new file mode 100644
index 000000000000..ba0aeb980f7e
--- /dev/null
+++ b/include/scsi/scsi_request.h
@@ -0,0 +1,30 @@
+#ifndef _SCSI_SCSI_REQUEST_H
+#define _SCSI_SCSI_REQUEST_H
+
+#include <linux/blk-mq.h>
+
+#define BLK_MAX_CDB	16
+
+struct scsi_request {
+	unsigned char	__cmd[BLK_MAX_CDB];
+	unsigned char	*cmd;
+	unsigned short	cmd_len;
+	unsigned int	sense_len;
+	unsigned int	resid_len;	/* residual count */
+	void		*sense;
+};
+
+static inline struct scsi_request *scsi_req(struct request *rq)
+{
+	return blk_mq_rq_to_pdu(rq);
+}
+
+static inline void scsi_req_free_cmd(struct scsi_request *req)
+{
+	if (req->cmd != req->__cmd)
+		kfree(req->cmd);
+}
+
+void scsi_req_init(struct request *);
+
+#endif /* _SCSI_SCSI_REQUEST_H */
diff --git a/include/scsi/scsi_transport.h b/include/scsi/scsi_transport.h
index 81292392adbc..a3dcb1bfb362 100644
--- a/include/scsi/scsi_transport.h
+++ b/include/scsi/scsi_transport.h
@@ -56,29 +56,6 @@ struct scsi_transport_template {
 	 * Allows a transport to override the default error handler.
 	 */
 	void (* eh_strategy_handler)(struct Scsi_Host *);
-
-	/*
-	 * This is an optional routine that allows the transport to become
-	 * involved when a scsi io timer fires. The return value tells the
-	 * timer routine how to finish the io timeout handling:
-	 * EH_HANDLED:		I fixed the error, please complete the command
-	 * EH_RESET_TIMER:	I need more time, reset the timer and
-	 *			begin counting again
-	 * EH_NOT_HANDLED	Begin normal error recovery
-	 */
-	enum blk_eh_timer_return (*eh_timed_out)(struct scsi_cmnd *);
-
-	/*
-	 * Used as callback for the completion of i_t_nexus request
-	 * for target drivers.
-	 */
-	int (* it_nexus_response)(struct Scsi_Host *, u64, int);
-
-	/*
-	 * Used as callback for the completion of task management
-	 * request for target drivers.
-	 */
-	int (* tsk_mgmt_response)(struct Scsi_Host *, u64, u64, int);
 };
 
 #define transport_class_to_shost(tc) \
@@ -119,4 +96,6 @@ scsi_transport_device_data(struct scsi_device *sdev)
 		+ shost->transportt->device_private_offset;
 }
 
+void __scsi_init_queue(struct Scsi_Host *shost, struct request_queue *q);
+
 #endif /* SCSI_TRANSPORT_H */
diff --git a/include/scsi/scsi_transport_fc.h b/include/scsi/scsi_transport_fc.h
index 924c8e614b45..b21b8aa58c4d 100644
--- a/include/scsi/scsi_transport_fc.h
+++ b/include/scsi/scsi_transport_fc.h
@@ -808,6 +808,7 @@ struct fc_vport *fc_vport_create(struct Scsi_Host *shost, int channel,
 		struct fc_vport_identifiers *);
 int fc_vport_terminate(struct fc_vport *vport);
 int fc_block_scsi_eh(struct scsi_cmnd *cmnd);
+enum blk_eh_timer_return fc_eh_timed_out(struct scsi_cmnd *scmd);
 
 static inline struct Scsi_Host *fc_bsg_to_shost(struct bsg_job *job)
 {
diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h
index d40d3ef25707..dd096330734e 100644
--- a/include/scsi/scsi_transport_srp.h
+++ b/include/scsi/scsi_transport_srp.h
@@ -88,10 +88,6 @@ struct srp_rport {
  * @terminate_rport_io: Callback function for terminating all outstanding I/O
  *     requests for an rport.
  * @rport_delete: Callback function that deletes an rport.
- *
- * Fields that are only relevant for SRP target drivers:
- * @tsk_mgmt_response: Callback function for sending a task management response.
- * @it_nexus_response: Callback function for processing an IT nexus response.
  */
 struct srp_function_template {
 	/* for initiator drivers */
@@ -103,9 +99,6 @@ struct srp_function_template {
 	int (*reconnect)(struct srp_rport *rport);
 	void (*terminate_rport_io)(struct srp_rport *rport);
 	void (*rport_delete)(struct srp_rport *rport);
-	/* for target drivers */
-	int (* tsk_mgmt_response)(struct Scsi_Host *, u64, u64, int);
-	int (* it_nexus_response)(struct Scsi_Host *, u64, int);
 };
 
 extern struct scsi_transport_template *
@@ -124,6 +117,7 @@ extern int srp_reconnect_rport(struct srp_rport *rport);
 extern void srp_start_tl_fail_timers(struct srp_rport *rport);
 extern void srp_remove_host(struct Scsi_Host *);
 extern void srp_stop_rport_timers(struct srp_rport *rport);
+enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd);
 
 /**
  * srp_chkready() - evaluate the transport layer state before I/O
diff --git a/include/soc/arc/mcip.h b/include/soc/arc/mcip.h
index 6902c2a8bd23..4b6b489a8d7c 100644
--- a/include/soc/arc/mcip.h
+++ b/include/soc/arc/mcip.h
@@ -55,17 +55,17 @@ struct mcip_cmd {
 
 struct mcip_bcr {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-		unsigned int pad3:8,
-			     idu:1, llm:1, num_cores:6,
-			     iocoh:1,  gfrc:1, dbg:1, pad2:1,
-			     msg:1, sem:1, ipi:1, pad:1,
+		unsigned int pad4:6, pw_dom:1, pad3:1,
+			     idu:1, pad2:1, num_cores:6,
+			     pad:1,  gfrc:1, dbg:1, pw:1,
+			     msg:1, sem:1, ipi:1, slv:1,
 			     ver:8;
 #else
 		unsigned int ver:8,
-			     pad:1, ipi:1, sem:1, msg:1,
-			     pad2:1, dbg:1, gfrc:1, iocoh:1,
-			     num_cores:6, llm:1, idu:1,
-			     pad3:8;
+			     slv:1, ipi:1, sem:1, msg:1,
+			     pw:1, dbg:1, gfrc:1, pad:1,
+			     num_cores:6, pad2:1, idu:1,
+			     pad3:1, pw_dom:1, pad4:6;
 #endif
 };
 
diff --git a/include/soc/at91/at91sam9_ddrsdr.h b/include/soc/at91/at91sam9_ddrsdr.h
index dc10c52e0e91..393362bdb860 100644
--- a/include/soc/at91/at91sam9_ddrsdr.h
+++ b/include/soc/at91/at91sam9_ddrsdr.h
@@ -81,6 +81,7 @@
 #define			AT91_DDRSDRC_LPCB_POWER_DOWN		2
 #define			AT91_DDRSDRC_LPCB_DEEP_POWER_DOWN	3
 #define		AT91_DDRSDRC_CLKFR	(1 << 2)	/* Clock Frozen */
+#define		AT91_DDRSDRC_LPDDR2_PWOFF	(1 << 3)	/* LPDDR Power Off */
 #define		AT91_DDRSDRC_PASR	(7 << 4)	/* Partial Array Self Refresh */
 #define		AT91_DDRSDRC_TCSR	(3 << 8)	/* Temperature Compensated Self Refresh */
 #define		AT91_DDRSDRC_DS		(3 << 10)	/* Drive Strength */
@@ -96,7 +97,9 @@
 #define			AT91_DDRSDRC_MD_SDR		0
 #define			AT91_DDRSDRC_MD_LOW_POWER_SDR	1
 #define			AT91_DDRSDRC_MD_LOW_POWER_DDR	3
+#define			AT91_DDRSDRC_MD_LPDDR3		5
 #define			AT91_DDRSDRC_MD_DDR2		6	/* [SAM9 Only] */
+#define			AT91_DDRSDRC_MD_LPDDR2		7
 #define		AT91_DDRSDRC_DBW	(1 << 4)		/* Data Bus Width */
 #define			AT91_DDRSDRC_DBW_32BITS		(0 <<  4)
 #define			AT91_DDRSDRC_DBW_16BITS		(1 <<  4)
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 43edf82e54ff..da854fb4530f 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -538,6 +538,7 @@ struct se_node_acl {
 	char			initiatorname[TRANSPORT_IQN_LEN];
 	/* Used to signal demo mode created ACL, disabled by default */
 	bool			dynamic_node_acl;
+	bool			dynamic_stop;
 	u32			queue_depth;
 	u32			acl_index;
 	enum target_prot_type	saved_prot_type;
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 3e02e3a25413..a88ed13446ff 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -73,19 +73,17 @@ DECLARE_EVENT_CLASS(block_rq_with_error,
 		__field(  unsigned int,	nr_sector		)
 		__field(  int,		errors			)
 		__array(  char,		rwbs,	RWBS_LEN	)
-		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+		__dynamic_array( char,	cmd,	1		)
 	),
 
 	TP_fast_assign(
 		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
-		__entry->sector    = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
-					0 : blk_rq_pos(rq);
-		__entry->nr_sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
-					0 : blk_rq_sectors(rq);
+		__entry->sector    = blk_rq_trace_sector(rq);
+		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
 		__entry->errors    = rq->errors;
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
-		blk_dump_cmd(__get_str(cmd), rq);
+		__get_str(cmd)[0] = '\0';
 	),
 
 	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
@@ -153,7 +151,7 @@ TRACE_EVENT(block_rq_complete,
 		__field(  unsigned int,	nr_sector		)
 		__field(  int,		errors			)
 		__array(  char,		rwbs,	RWBS_LEN	)
-		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+		__dynamic_array( char,	cmd,	1		)
 	),
 
 	TP_fast_assign(
@@ -163,7 +161,7 @@ TRACE_EVENT(block_rq_complete,
 		__entry->errors    = rq->errors;
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, nr_bytes);
-		blk_dump_cmd(__get_str(cmd), rq);
+		__get_str(cmd)[0] = '\0';
 	),
 
 	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
@@ -186,20 +184,17 @@ DECLARE_EVENT_CLASS(block_rq,
 		__field(  unsigned int,	bytes			)
 		__array(  char,		rwbs,	RWBS_LEN	)
 		__array(  char,         comm,   TASK_COMM_LEN   )
-		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+		__dynamic_array( char,	cmd,	1		)
 	),
 
 	TP_fast_assign(
 		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
-		__entry->sector    = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
-					0 : blk_rq_pos(rq);
-		__entry->nr_sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
-					0 : blk_rq_sectors(rq);
-		__entry->bytes     = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
-					blk_rq_bytes(rq) : 0;
+		__entry->sector    = blk_rq_trace_sector(rq);
+		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
+		__entry->bytes     = blk_rq_bytes(rq);
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq));
-		blk_dump_cmd(__get_str(cmd), rq);
+		__get_str(cmd)[0] = '\0';
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 9d4f9b3a2b7b..e3facb356838 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -385,11 +385,11 @@ TRACE_EVENT(rcu_quiescent_state_report,
 
 /*
  * Tracepoint for quiescent states detected by force_quiescent_state().
- * These trace events include the type of RCU, the grace-period number
- * that was blocked by the CPU, the CPU itself, and the type of quiescent
- * state, which can be "dti" for dyntick-idle mode, "ofl" for CPU offline,
- * or "kick" when kicking a CPU that has been in dyntick-idle mode for
- * too long.
+ * These trace events include the type of RCU, the grace-period number that
+ * was blocked by the CPU, the CPU itself, and the type of quiescent state,
+ * which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, "kick"
+ * when kicking a CPU that has been in dyntick-idle mode for too long, or
+ * "rqc" if the CPU got a quiescent state via its rcu_qs_ctr.
  */
 TRACE_EVENT(rcu_fqs,
 
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 1448637616d6..1bca99dbb98f 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -269,17 +269,17 @@ DEFINE_EVENT(hrtimer_class, hrtimer_cancel,
 TRACE_EVENT(itimer_state,
 
 	TP_PROTO(int which, const struct itimerval *const value,
-		 cputime_t expires),
+		 unsigned long long expires),
 
 	TP_ARGS(which, value, expires),
 
 	TP_STRUCT__entry(
-		__field(	int,		which		)
-		__field(	cputime_t,	expires		)
-		__field(	long,		value_sec	)
-		__field(	long,		value_usec	)
-		__field(	long,		interval_sec	)
-		__field(	long,		interval_usec	)
+		__field(	int,			which		)
+		__field(	unsigned long long,	expires		)
+		__field(	long,			value_sec	)
+		__field(	long,			value_usec	)
+		__field(	long,			interval_sec	)
+		__field(	long,			interval_usec	)
 	),
 
 	TP_fast_assign(
@@ -292,7 +292,7 @@ TRACE_EVENT(itimer_state,
 	),
 
 	TP_printk("which=%d expires=%llu it_value=%ld.%ld it_interval=%ld.%ld",
-		  __entry->which, (unsigned long long)__entry->expires,
+		  __entry->which, __entry->expires,
 		  __entry->value_sec, __entry->value_usec,
 		  __entry->interval_sec, __entry->interval_usec)
 );
@@ -305,14 +305,14 @@ TRACE_EVENT(itimer_state,
  */
 TRACE_EVENT(itimer_expire,
 
-	TP_PROTO(int which, struct pid *pid, cputime_t now),
+	TP_PROTO(int which, struct pid *pid, unsigned long long now),
 
 	TP_ARGS(which, pid, now),
 
 	TP_STRUCT__entry(
-		__field( int ,		which	)
-		__field( pid_t,		pid	)
-		__field( cputime_t,	now	)
+		__field( int ,			which	)
+		__field( pid_t,			pid	)
+		__field( unsigned long long,	now	)
 	),
 
 	TP_fast_assign(
@@ -322,7 +322,7 @@ TRACE_EVENT(itimer_expire,
 	),
 
 	TP_printk("which=%d pid=%d now=%llu", __entry->which,
-		  (int) __entry->pid, (unsigned long long)__entry->now)
+		  (int) __entry->pid, __entry->now)
 );
 
 #ifdef CONFIG_NO_HZ_COMMON
diff --git a/include/trace/events/ufs.h b/include/trace/events/ufs.h
new file mode 100644
index 000000000000..bf6f82673492
--- /dev/null
+++ b/include/trace/events/ufs.h
@@ -0,0 +1,263 @@
+/*
+ * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM ufs
+
+#if !defined(_TRACE_UFS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_UFS_H
+
+#include <linux/tracepoint.h>
+
+#define UFS_LINK_STATES			\
+	EM(UIC_LINK_OFF_STATE)		\
+	EM(UIC_LINK_ACTIVE_STATE)	\
+	EMe(UIC_LINK_HIBERN8_STATE)
+
+#define UFS_PWR_MODES			\
+	EM(UFS_ACTIVE_PWR_MODE)		\
+	EM(UFS_SLEEP_PWR_MODE)		\
+	EMe(UFS_POWERDOWN_PWR_MODE)
+
+#define UFSCHD_CLK_GATING_STATES	\
+	EM(CLKS_OFF)			\
+	EM(CLKS_ON)			\
+	EM(REQ_CLKS_OFF)		\
+	EMe(REQ_CLKS_ON)
+
+/* Enums require being exported to userspace, for user tool parsing */
+#undef EM
+#undef EMe
+#define EM(a)	TRACE_DEFINE_ENUM(a);
+#define EMe(a)	TRACE_DEFINE_ENUM(a);
+
+UFS_LINK_STATES;
+UFS_PWR_MODES;
+UFSCHD_CLK_GATING_STATES;
+
+/*
+ * Now redefine the EM() and EMe() macros to map the enums to the strings
+ * that will be printed in the output.
+ */
+#undef EM
+#undef EMe
+#define EM(a)	{ a, #a },
+#define EMe(a)	{ a, #a }
+
+TRACE_EVENT(ufshcd_clk_gating,
+
+	TP_PROTO(const char *dev_name, int state),
+
+	TP_ARGS(dev_name, state),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name)
+		__field(int, state)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name);
+		__entry->state = state;
+	),
+
+	TP_printk("%s: gating state changed to %s",
+		__get_str(dev_name),
+		__print_symbolic(__entry->state, UFSCHD_CLK_GATING_STATES))
+);
+
+TRACE_EVENT(ufshcd_clk_scaling,
+
+	TP_PROTO(const char *dev_name, const char *state, const char *clk,
+		u32 prev_state, u32 curr_state),
+
+	TP_ARGS(dev_name, state, clk, prev_state, curr_state),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name)
+		__string(state, state)
+		__string(clk, clk)
+		__field(u32, prev_state)
+		__field(u32, curr_state)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name);
+		__assign_str(state, state);
+		__assign_str(clk, clk);
+		__entry->prev_state = prev_state;
+		__entry->curr_state = curr_state;
+	),
+
+	TP_printk("%s: %s %s from %u to %u Hz",
+		__get_str(dev_name), __get_str(state), __get_str(clk),
+		__entry->prev_state, __entry->curr_state)
+);
+
+TRACE_EVENT(ufshcd_auto_bkops_state,
+
+	TP_PROTO(const char *dev_name, const char *state),
+
+	TP_ARGS(dev_name, state),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name)
+		__string(state, state)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name);
+		__assign_str(state, state);
+	),
+
+	TP_printk("%s: auto bkops - %s",
+		__get_str(dev_name), __get_str(state))
+);
+
+DECLARE_EVENT_CLASS(ufshcd_profiling_template,
+	TP_PROTO(const char *dev_name, const char *profile_info, s64 time_us,
+		 int err),
+
+	TP_ARGS(dev_name, profile_info, time_us, err),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name)
+		__string(profile_info, profile_info)
+		__field(s64, time_us)
+		__field(int, err)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name);
+		__assign_str(profile_info, profile_info);
+		__entry->time_us = time_us;
+		__entry->err = err;
+	),
+
+	TP_printk("%s: %s: took %lld usecs, err %d",
+		__get_str(dev_name), __get_str(profile_info),
+		__entry->time_us, __entry->err)
+);
+
+DEFINE_EVENT(ufshcd_profiling_template, ufshcd_profile_hibern8,
+	TP_PROTO(const char *dev_name, const char *profile_info, s64 time_us,
+		 int err),
+	TP_ARGS(dev_name, profile_info, time_us, err));
+
+DEFINE_EVENT(ufshcd_profiling_template, ufshcd_profile_clk_gating,
+	TP_PROTO(const char *dev_name, const char *profile_info, s64 time_us,
+		 int err),
+	TP_ARGS(dev_name, profile_info, time_us, err));
+
+DEFINE_EVENT(ufshcd_profiling_template, ufshcd_profile_clk_scaling,
+	TP_PROTO(const char *dev_name, const char *profile_info, s64 time_us,
+		 int err),
+	TP_ARGS(dev_name, profile_info, time_us, err));
+
+DECLARE_EVENT_CLASS(ufshcd_template,
+	TP_PROTO(const char *dev_name, int err, s64 usecs,
+		 int dev_state, int link_state),
+
+	TP_ARGS(dev_name, err, usecs, dev_state, link_state),
+
+	TP_STRUCT__entry(
+		__field(s64, usecs)
+		__field(int, err)
+		__string(dev_name, dev_name)
+		__field(int, dev_state)
+		__field(int, link_state)
+	),
+
+	TP_fast_assign(
+		__entry->usecs = usecs;
+		__entry->err = err;
+		__assign_str(dev_name, dev_name);
+		__entry->dev_state = dev_state;
+		__entry->link_state = link_state;
+	),
+
+	TP_printk(
+		"%s: took %lld usecs, dev_state: %s, link_state: %s, err %d",
+		__get_str(dev_name),
+		__entry->usecs,
+		__print_symbolic(__entry->dev_state, UFS_PWR_MODES),
+		__print_symbolic(__entry->link_state, UFS_LINK_STATES),
+		__entry->err
+	)
+);
+
+DEFINE_EVENT(ufshcd_template, ufshcd_system_suspend,
+	     TP_PROTO(const char *dev_name, int err, s64 usecs,
+		      int dev_state, int link_state),
+	     TP_ARGS(dev_name, err, usecs, dev_state, link_state));
+
+DEFINE_EVENT(ufshcd_template, ufshcd_system_resume,
+	     TP_PROTO(const char *dev_name, int err, s64 usecs,
+		      int dev_state, int link_state),
+	     TP_ARGS(dev_name, err, usecs, dev_state, link_state));
+
+DEFINE_EVENT(ufshcd_template, ufshcd_runtime_suspend,
+	     TP_PROTO(const char *dev_name, int err, s64 usecs,
+		      int dev_state, int link_state),
+	     TP_ARGS(dev_name, err, usecs, dev_state, link_state));
+
+DEFINE_EVENT(ufshcd_template, ufshcd_runtime_resume,
+	     TP_PROTO(const char *dev_name, int err, s64 usecs,
+		      int dev_state, int link_state),
+	     TP_ARGS(dev_name, err, usecs, dev_state, link_state));
+
+DEFINE_EVENT(ufshcd_template, ufshcd_init,
+	     TP_PROTO(const char *dev_name, int err, s64 usecs,
+		      int dev_state, int link_state),
+	     TP_ARGS(dev_name, err, usecs, dev_state, link_state));
+
+TRACE_EVENT(ufshcd_command,
+	TP_PROTO(const char *dev_name, const char *str, unsigned int tag,
+			u32 doorbell, int transfer_len, u32 intr, u64 lba,
+			u8 opcode),
+
+	TP_ARGS(dev_name, str, tag, doorbell, transfer_len, intr, lba, opcode),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name)
+		__string(str, str)
+		__field(unsigned int, tag)
+		__field(u32, doorbell)
+		__field(int, transfer_len)
+		__field(u32, intr)
+		__field(u64, lba)
+		__field(u8, opcode)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name);
+		__assign_str(str, str);
+		__entry->tag = tag;
+		__entry->doorbell = doorbell;
+		__entry->transfer_len = transfer_len;
+		__entry->intr = intr;
+		__entry->lba = lba;
+		__entry->opcode = opcode;
+	),
+
+	TP_printk(
+		"%s: %s: tag: %u, DB: 0x%x, size: %d, IS: %u, LBA: %llu, opcode: 0x%x",
+		__get_str(str), __get_str(dev_name), __entry->tag,
+		__entry->doorbell, __entry->transfer_len,
+		__entry->intr, __entry->lba, (u32)__entry->opcode
+	)
+);
+
+#endif /* if !defined(_TRACE_UFS_H) || defined(TRACE_HEADER_MULTI_READ) */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0eb0e87dbe9f..d2b0ac799d03 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -116,6 +116,12 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
+ * to the given target_fd cgroup the descendent cgroup will be able to
+ * override effective bpf program that was inherited from this cgroup
+ */
+#define BPF_F_ALLOW_OVERRIDE	(1U << 0)
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -171,6 +177,7 @@ union bpf_attr {
 		__u32		target_fd;	/* container object to attach to */
 		__u32		attach_bpf_fd;	/* eBPF program to attach */
 		__u32		attach_type;
+		__u32		attach_flags;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h
index 3cbc327801d6..c451eec42a83 100644
--- a/include/uapi/linux/cec-funcs.h
+++ b/include/uapi/linux/cec-funcs.h
@@ -1665,14 +1665,15 @@ static inline void cec_msg_report_current_latency(struct cec_msg *msg,
 						  __u8 audio_out_compensated,
 						  __u8 audio_out_delay)
 {
-	msg->len = 7;
+	msg->len = 6;
 	msg->msg[0] |= 0xf; /* broadcast */
 	msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY;
 	msg->msg[2] = phys_addr >> 8;
 	msg->msg[3] = phys_addr & 0xff;
 	msg->msg[4] = video_latency;
 	msg->msg[5] = (low_latency_mode << 2) | audio_out_compensated;
-	msg->msg[6] = audio_out_delay;
+	if (audio_out_compensated == 3)
+		msg->msg[msg->len++] = audio_out_delay;
 }
 
 static inline void cec_ops_report_current_latency(const struct cec_msg *msg,
@@ -1686,7 +1687,10 @@ static inline void cec_ops_report_current_latency(const struct cec_msg *msg,
 	*video_latency = msg->msg[4];
 	*low_latency_mode = (msg->msg[5] >> 2) & 1;
 	*audio_out_compensated = msg->msg[5] & 3;
-	*audio_out_delay = msg->msg[6];
+	if (*audio_out_compensated == 3 && msg->len >= 7)
+		*audio_out_delay = msg->msg[6];
+	else
+		*audio_out_delay = 0;
 }
 
 static inline void cec_msg_request_current_latency(struct cec_msg *msg,
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index f0db7788f887..3dc91a46e8b8 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1384,6 +1384,8 @@ enum ethtool_link_mode_bit_indices {
 	ETHTOOL_LINK_MODE_10000baseLR_Full_BIT	= 44,
 	ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT	= 45,
 	ETHTOOL_LINK_MODE_10000baseER_Full_BIT	= 46,
+	ETHTOOL_LINK_MODE_2500baseT_Full_BIT	= 47,
+	ETHTOOL_LINK_MODE_5000baseT_Full_BIT	= 48,
 
 
 	/* Last allowed bit for __ETHTOOL_LINK_MODE_LEGACY_MASK is bit
@@ -1393,7 +1395,7 @@ enum ethtool_link_mode_bit_indices {
 	 */
 
 	__ETHTOOL_LINK_MODE_LAST
-	  = ETHTOOL_LINK_MODE_10000baseER_Full_BIT,
+	  = ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
 };
 
 #define __ETHTOOL_LINK_MODE_LEGACY_MASK(base_name)	\
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 85ddb74fcd1c..b23c1914a182 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -9,9 +9,8 @@
 
 #include <linux/types.h>
 #include <linux/socket.h>
-#ifndef __KERNEL__
-#include <netinet/in.h>
-#endif
+#include <linux/in.h>
+#include <linux/in6.h>
 
 #define IPPROTO_L2TP		115
 
@@ -31,7 +30,7 @@ struct sockaddr_l2tpip {
 	__u32		l2tp_conn_id;	/* Connection ID of tunnel */
 
 	/* Pad to size of `struct sockaddr'. */
-	unsigned char	__pad[sizeof(struct sockaddr) -
+	unsigned char	__pad[__SOCK_SIZE__ -
 			      sizeof(__kernel_sa_family_t) -
 			      sizeof(__be16) - sizeof(struct in_addr) -
 			      sizeof(__u32)];
diff --git a/include/uapi/linux/lightnvm.h b/include/uapi/linux/lightnvm.h
index 774a43128a7a..fd19f36b3129 100644
--- a/include/uapi/linux/lightnvm.h
+++ b/include/uapi/linux/lightnvm.h
@@ -122,6 +122,44 @@ struct nvm_ioctl_dev_factory {
 	__u32 flags;
 };
 
+struct nvm_user_vio {
+	__u8 opcode;
+	__u8 flags;
+	__u16 control;
+	__u16 nppas;
+	__u16 rsvd;
+	__u64 metadata;
+	__u64 addr;
+	__u64 ppa_list;
+	__u32 metadata_len;
+	__u32 data_len;
+	__u64 status;
+	__u32 result;
+	__u32 rsvd3[3];
+};
+
+struct nvm_passthru_vio {
+	__u8 opcode;
+	__u8 flags;
+	__u8 rsvd[2];
+	__u32 nsid;
+	__u32 cdw2;
+	__u32 cdw3;
+	__u64 metadata;
+	__u64 addr;
+	__u32 metadata_len;
+	__u32 data_len;
+	__u64 ppa_list;
+	__u16 nppas;
+	__u16 control;
+	__u32 cdw13;
+	__u32 cdw14;
+	__u32 cdw15;
+	__u64 status;
+	__u32 result;
+	__u32 timeout_ms;
+};
+
 /* The ioctl type, 'L', 0x20 - 0x2F documented in ioctl-number.txt */
 enum {
 	/* top level cmds */
@@ -137,6 +175,11 @@ enum {
 
 	/* Factory reset device */
 	NVM_DEV_FACTORY_CMD,
+
+	/* Vector user I/O */
+	NVM_DEV_VIO_ADMIN_CMD = 0x41,
+	NVM_DEV_VIO_CMD = 0x42,
+	NVM_DEV_VIO_USER_CMD = 0x43,
 };
 
 #define NVM_IOCTL 'L' /* 0x4c */
@@ -154,6 +197,13 @@ enum {
 #define NVM_DEV_FACTORY		_IOW(NVM_IOCTL, NVM_DEV_FACTORY_CMD, \
 						struct nvm_ioctl_dev_factory)
 
+#define NVME_NVM_IOCTL_IO_VIO		_IOWR(NVM_IOCTL, NVM_DEV_VIO_USER_CMD, \
+						struct nvm_passthru_vio)
+#define NVME_NVM_IOCTL_ADMIN_VIO	_IOWR(NVM_IOCTL, NVM_DEV_VIO_ADMIN_CMD,\
+						struct nvm_passthru_vio)
+#define NVME_NVM_IOCTL_SUBMIT_VIO	_IOWR(NVM_IOCTL, NVM_DEV_VIO_CMD,\
+						struct nvm_user_vio)
+
 #define NVM_VERSION_MAJOR	1
 #define NVM_VERSION_MINOR	0
 #define NVM_VERSION_PATCHLEVEL	0
diff --git a/include/uapi/linux/netfilter/nf_log.h b/include/uapi/linux/netfilter/nf_log.h
index 8be21e02387d..d0b5fa91ff54 100644
--- a/include/uapi/linux/netfilter/nf_log.h
+++ b/include/uapi/linux/netfilter/nf_log.h
@@ -9,4 +9,6 @@
 #define NF_LOG_MACDECODE	0x20	/* Decode MAC header */
 #define NF_LOG_MASK		0x2f
 
+#define NF_LOG_PREFIXLEN	128
+
 #endif /* _NETFILTER_NF_LOG_H */
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 881d49e94569..e3f27e09eb2b 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -235,7 +235,7 @@ enum nft_rule_compat_flags {
 /**
  * enum nft_rule_compat_attributes - nf_tables rule compat attributes
  *
- * @NFTA_RULE_COMPAT_PROTO: numerice value of handled protocol (NLA_U32)
+ * @NFTA_RULE_COMPAT_PROTO: numeric value of handled protocol (NLA_U32)
  * @NFTA_RULE_COMPAT_FLAGS: bitmask of enum nft_rule_compat_flags (NLA_U32)
  */
 enum nft_rule_compat_attributes {
@@ -499,7 +499,7 @@ enum nft_bitwise_attributes {
  * enum nft_byteorder_ops - nf_tables byteorder operators
  *
  * @NFT_BYTEORDER_NTOH: network to host operator
- * @NFT_BYTEORDER_HTON: host to network opertaor
+ * @NFT_BYTEORDER_HTON: host to network operator
  */
 enum nft_byteorder_ops {
 	NFT_BYTEORDER_NTOH,
diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h
new file mode 100644
index 000000000000..c72e0735532d
--- /dev/null
+++ b/include/uapi/linux/sed-opal.h
@@ -0,0 +1,119 @@
+/*
+ * Copyright © 2016 Intel Corporation
+ *
+ * Authors:
+ *    Rafael Antognolli <rafael.antognolli@intel.com>
+ *    Scott  Bauer      <scott.bauer@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#ifndef _UAPI_SED_OPAL_H
+#define _UAPI_SED_OPAL_H
+
+#include <linux/types.h>
+
+#define OPAL_KEY_MAX 256
+#define OPAL_MAX_LRS 9
+
+enum opal_mbr {
+	OPAL_MBR_ENABLE = 0x0,
+	OPAL_MBR_DISABLE = 0x01,
+};
+
+enum opal_user {
+	OPAL_ADMIN1 = 0x0,
+	OPAL_USER1 = 0x01,
+	OPAL_USER2 = 0x02,
+	OPAL_USER3 = 0x03,
+	OPAL_USER4 = 0x04,
+	OPAL_USER5 = 0x05,
+	OPAL_USER6 = 0x06,
+	OPAL_USER7 = 0x07,
+	OPAL_USER8 = 0x08,
+	OPAL_USER9 = 0x09,
+};
+
+enum opal_lock_state {
+	OPAL_RO = 0x01, /* 0001 */
+	OPAL_RW = 0x02, /* 0010 */
+	OPAL_LK = 0x04, /* 0100 */
+};
+
+struct opal_key {
+	__u8 lr;
+	__u8 key_len;
+	__u8 __align[6];
+	__u8 key[OPAL_KEY_MAX];
+};
+
+struct opal_lr_act {
+	struct opal_key key;
+	__u32 sum;
+	__u8    num_lrs;
+	__u8 lr[OPAL_MAX_LRS];
+	__u8 align[2]; /* Align to 8 byte boundary */
+};
+
+struct opal_session_info {
+	__u32 sum;
+	__u32 who;
+	struct opal_key opal_key;
+};
+
+struct opal_user_lr_setup {
+	__u64 range_start;
+	__u64 range_length;
+	__u32 RLE; /* Read Lock enabled */
+	__u32 WLE; /* Write Lock Enabled */
+	struct opal_session_info session;
+};
+
+struct opal_lock_unlock {
+	struct opal_session_info session;
+	__u32 l_state;
+	__u8 __align[4];
+};
+
+struct opal_new_pw {
+	struct opal_session_info session;
+
+	/* When we're not operating in sum, and we first set
+	 * passwords we need to set them via ADMIN authority.
+	 * After passwords are changed, we can set them via,
+	 * User authorities.
+	 * Because of this restriction we need to know about
+	 * Two different users. One in 'session' which we will use
+	 * to start the session and new_userr_pw as the user we're
+	 * chaning the pw for.
+	 */
+	struct opal_session_info new_user_pw;
+};
+
+struct opal_mbr_data {
+	struct opal_key key;
+	__u8 enable_disable;
+	__u8 __align[7];
+};
+
+#define IOC_OPAL_SAVE		    _IOW('p', 220, struct opal_lock_unlock)
+#define IOC_OPAL_LOCK_UNLOCK	    _IOW('p', 221, struct opal_lock_unlock)
+#define IOC_OPAL_TAKE_OWNERSHIP	    _IOW('p', 222, struct opal_key)
+#define IOC_OPAL_ACTIVATE_LSP       _IOW('p', 223, struct opal_lr_act)
+#define IOC_OPAL_SET_PW             _IOW('p', 224, struct opal_new_pw)
+#define IOC_OPAL_ACTIVATE_USR       _IOW('p', 225, struct opal_session_info)
+#define IOC_OPAL_REVERT_TPR         _IOW('p', 226, struct opal_key)
+#define IOC_OPAL_LR_SETUP           _IOW('p', 227, struct opal_user_lr_setup)
+#define IOC_OPAL_ADD_USR_TO_LR      _IOW('p', 228, struct opal_lock_unlock)
+#define IOC_OPAL_ENABLE_DISABLE_MBR _IOW('p', 229, struct opal_mbr_data)
+#define IOC_OPAL_ERASE_LR           _IOW('p', 230, struct opal_session_info)
+#define IOC_OPAL_SECURE_ERASE_LR    _IOW('p', 231, struct opal_session_info)
+
+#endif /* _UAPI_SED_OPAL_H */
diff --git a/include/uapi/linux/seg6.h b/include/uapi/linux/seg6.h
index c396a8052f73..052799e4d751 100644
--- a/include/uapi/linux/seg6.h
+++ b/include/uapi/linux/seg6.h
@@ -23,14 +23,12 @@ struct ipv6_sr_hdr {
 	__u8	type;
 	__u8	segments_left;
 	__u8	first_segment;
-	__u8	flag_1;
-	__u8	flag_2;
-	__u8	reserved;
+	__u8	flags;
+	__u16	reserved;
 
 	struct in6_addr segments[0];
 };
 
-#define SR6_FLAG1_CLEANUP	(1 << 7)
 #define SR6_FLAG1_PROTECTED	(1 << 6)
 #define SR6_FLAG1_OAM		(1 << 5)
 #define SR6_FLAG1_ALERT		(1 << 4)
@@ -42,8 +40,7 @@ struct ipv6_sr_hdr {
 #define SR6_TLV_PADDING		4
 #define SR6_TLV_HMAC		5
 
-#define sr_has_cleanup(srh) ((srh)->flag_1 & SR6_FLAG1_CLEANUP)
-#define sr_has_hmac(srh) ((srh)->flag_1 & SR6_FLAG1_HMAC)
+#define sr_has_hmac(srh) ((srh)->flags & SR6_FLAG1_HMAC)
 
 struct sr6_tlv {
 	__u8 type;
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 46e8a2e369f9..45184a2ef66c 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -362,8 +362,8 @@ enum v4l2_quantization {
 	/*
 	 * The default for R'G'B' quantization is always full range, except
 	 * for the BT2020 colorspace. For Y'CbCr the quantization is always
-	 * limited range, except for COLORSPACE_JPEG, SRGB, ADOBERGB,
-	 * XV601 or XV709: those are full range.
+	 * limited range, except for COLORSPACE_JPEG, XV601 or XV709: those
+	 * are full range.
 	 */
 	V4L2_QUANTIZATION_DEFAULT     = 0,
 	V4L2_QUANTIZATION_FULL_RANGE  = 1,
@@ -379,8 +379,7 @@ enum v4l2_quantization {
 	(((is_rgb_or_hsv) && (colsp) == V4L2_COLORSPACE_BT2020) ? \
 	 V4L2_QUANTIZATION_LIM_RANGE : \
 	 (((is_rgb_or_hsv) || (ycbcr_enc) == V4L2_YCBCR_ENC_XV601 || \
-	  (ycbcr_enc) == V4L2_YCBCR_ENC_XV709 || (colsp) == V4L2_COLORSPACE_JPEG) || \
-	  (colsp) == V4L2_COLORSPACE_ADOBERGB || (colsp) == V4L2_COLORSPACE_SRGB ? \
+	  (ycbcr_enc) == V4L2_YCBCR_ENC_XV709 || (colsp) == V4L2_COLORSPACE_JPEG) ? \
 	 V4L2_QUANTIZATION_FULL_RANGE : V4L2_QUANTIZATION_LIM_RANGE))
 
 enum v4l2_priority {
diff --git a/include/uapi/rdma/Kbuild b/include/uapi/rdma/Kbuild
index 82bdf5626859..bb68cb1b04ed 100644
--- a/include/uapi/rdma/Kbuild
+++ b/include/uapi/rdma/Kbuild
@@ -16,3 +16,4 @@ header-y += nes-abi.h
 header-y += ocrdma-abi.h
 header-y += hns-abi.h
 header-y += vmw_pvrdma-abi.h
+header-y += qedr-abi.h
diff --git a/include/uapi/rdma/cxgb3-abi.h b/include/uapi/rdma/cxgb3-abi.h
index 48a19bda071b..d24eee12128f 100644
--- a/include/uapi/rdma/cxgb3-abi.h
+++ b/include/uapi/rdma/cxgb3-abi.h
@@ -30,7 +30,7 @@
  * SOFTWARE.
  */
 #ifndef CXGB3_ABI_USER_H
-#define CXBG3_ABI_USER_H
+#define CXGB3_ABI_USER_H
 
 #include <linux/types.h>
 
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index dfdfe4e92d31..f4f87cff6dc6 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -37,7 +37,6 @@
 #define IB_USER_VERBS_H
 
 #include <linux/types.h>
-#include <rdma/ib_verbs.h>
 
 /*
  * Increment this value if any changes that break userspace ABI
@@ -548,11 +547,17 @@ enum {
 };
 
 enum {
-	IB_USER_LEGACY_LAST_QP_ATTR_MASK = IB_QP_DEST_QPN
+	/*
+	 * This value is equal to IB_QP_DEST_QPN.
+	 */
+	IB_USER_LEGACY_LAST_QP_ATTR_MASK = 1ULL << 20,
 };
 
 enum {
-	IB_USER_LAST_QP_ATTR_MASK = IB_QP_RATE_LIMIT
+	/*
+	 * This value is equal to IB_QP_RATE_LIMIT.
+	 */
+	IB_USER_LAST_QP_ATTR_MASK = 1ULL << 25,
 };
 
 struct ib_uverbs_ex_create_qp {
diff --git a/include/uapi/scsi/cxlflash_ioctl.h b/include/uapi/scsi/cxlflash_ioctl.h
index 6bf1f8a022b1..e9fdc12ad984 100644
--- a/include/uapi/scsi/cxlflash_ioctl.h
+++ b/include/uapi/scsi/cxlflash_ioctl.h
@@ -40,6 +40,7 @@ struct dk_cxlflash_hdr {
  */
 #define DK_CXLFLASH_ALL_PORTS_ACTIVE	0x0000000000000001ULL
 #define DK_CXLFLASH_APP_CLOSE_ADAP_FD	0x0000000000000002ULL
+#define DK_CXLFLASH_CONTEXT_SQ_CMD_MODE	0x0000000000000004ULL
 
 /*
  * General Notes:
diff --git a/init/Kconfig b/init/Kconfig
index e1a937348a3e..2655abb8f310 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -529,7 +529,6 @@ config SRCU
 config TASKS_RCU
 	bool
 	default n
-	depends on !UML
 	select SRCU
 	help
 	  This option enables a task-based RCU implementation that uses
@@ -781,19 +780,6 @@ config RCU_NOCB_CPU_ALL
 
 endchoice
 
-config RCU_EXPEDITE_BOOT
-	bool
-	default n
-	help
-	  This option enables expedited grace periods at boot time,
-	  as if rcu_expedite_gp() had been invoked early in boot.
-	  The corresponding rcu_unexpedite_gp() is invoked from
-	  rcu_end_inkernel_boot(), which is intended to be invoked
-	  at the end of the kernel-only boot sequence, just before
-	  init is exec'ed.
-
-	  Accept the default if unsure.
-
 endmenu # "RCU Subsystem"
 
 config BUILD_BIN2C
@@ -1987,6 +1973,10 @@ config MODVERSIONS
 	  make them incompatible with the kernel you are running.  If
 	  unsure, say N.
 
+config MODULE_REL_CRCS
+	bool
+	depends on MODVERSIONS
+
 config MODULE_SRCVERSION_ALL
 	bool "Source checksum for all modules"
 	help
diff --git a/init/main.c b/init/main.c
index b0c9d6facef9..6ced14a3df12 100644
--- a/init/main.c
+++ b/init/main.c
@@ -625,7 +625,6 @@ asmlinkage __visible void __init start_kernel(void)
 	numa_policy_init();
 	if (late_time_init)
 		late_time_init();
-	sched_clock_init();
 	calibrate_delay();
 	pidmap_init();
 	anon_vma_init();
@@ -663,7 +662,6 @@ asmlinkage __visible void __init start_kernel(void)
 	sfi_init_late();
 
 	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
-		efi_late_init();
 		efi_free_boot_services();
 	}
 
diff --git a/init/version.c b/init/version.c
index fe41a63efed6..5606341e9efd 100644
--- a/init/version.c
+++ b/init/version.c
@@ -23,9 +23,7 @@ int version_string(LINUX_VERSION_CODE);
 #endif
 
 struct uts_namespace init_uts_ns = {
-	.kref = {
-		.refcount	= ATOMIC_INIT(2),
-	},
+	.kref = KREF_INIT(2),
 	.name = {
 		.sysname	= UTS_SYSNAME,
 		.nodename	= UTS_NODENAME,
diff --git a/kernel/acct.c b/kernel/acct.c
index 74963d192c5d..ca9cb55b5855 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -453,8 +453,8 @@ static void fill_ac(acct_t *ac)
 	spin_lock_irq(&current->sighand->siglock);
 	tty = current->signal->tty;	/* Safe as we hold the siglock */
 	ac->ac_tty = tty ? old_encode_dev(tty_devnum(tty)) : 0;
-	ac->ac_utime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_utime)));
-	ac->ac_stime = encode_comp_t(jiffies_to_AHZ(cputime_to_jiffies(pacct->ac_stime)));
+	ac->ac_utime = encode_comp_t(nsec_to_AHZ(pacct->ac_utime));
+	ac->ac_stime = encode_comp_t(nsec_to_AHZ(pacct->ac_stime));
 	ac->ac_flag = pacct->ac_flag;
 	ac->ac_mem = encode_comp_t(pacct->ac_mem);
 	ac->ac_minflt = encode_comp_t(pacct->ac_minflt);
@@ -530,7 +530,7 @@ out:
 void acct_collect(long exitcode, int group_dead)
 {
 	struct pacct_struct *pacct = &current->signal->pacct;
-	cputime_t utime, stime;
+	u64 utime, stime;
 	unsigned long vsize = 0;
 
 	if (group_dead && current->mm) {
@@ -559,6 +559,7 @@ void acct_collect(long exitcode, int group_dead)
 		pacct->ac_flag |= ACORE;
 	if (current->flags & PF_SIGNALED)
 		pacct->ac_flag |= AXSIG;
+
 	task_cputime(current, &utime, &stime);
 	pacct->ac_utime += utime;
 	pacct->ac_stime += stime;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 229a5d5df977..3d55d95dcf49 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -11,7 +11,6 @@
  */
 #include <linux/bpf.h>
 #include <linux/err.h>
-#include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/filter.h>
@@ -74,14 +73,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 	if (array_size >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-ENOMEM);
 
-
 	/* allocate all map elements and zero-initialize them */
-	array = kzalloc(array_size, GFP_USER | __GFP_NOWARN);
-	if (!array) {
-		array = vzalloc(array_size);
-		if (!array)
-			return ERR_PTR(-ENOMEM);
-	}
+	array = bpf_map_area_alloc(array_size);
+	if (!array)
+		return ERR_PTR(-ENOMEM);
 
 	/* copy mandatory map attributes */
 	array->map.map_type = attr->map_type;
@@ -97,7 +92,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
 	if (array_size >= U32_MAX - PAGE_SIZE ||
 	    elem_size > PCPU_MIN_UNIT_SIZE || bpf_array_alloc_percpu(array)) {
-		kvfree(array);
+		bpf_map_area_free(array);
 		return ERR_PTR(-ENOMEM);
 	}
 out:
@@ -262,7 +257,7 @@ static void array_map_free(struct bpf_map *map)
 	if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
 		bpf_array_free_percpu(array);
 
-	kvfree(array);
+	bpf_map_area_free(array);
 }
 
 static const struct bpf_map_ops array_ops = {
@@ -319,7 +314,8 @@ static void fd_array_map_free(struct bpf_map *map)
 	/* make sure it's empty */
 	for (i = 0; i < array->map.max_entries; i++)
 		BUG_ON(array->ptrs[i] != NULL);
-	kvfree(array);
+
+	bpf_map_area_free(array);
 }
 
 static void *fd_array_map_lookup_elem(struct bpf_map *map, void *key)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index a515f7b007c6..da0f53690295 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -52,6 +52,7 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
 		e = rcu_dereference_protected(parent->bpf.effective[type],
 					      lockdep_is_held(&cgroup_mutex));
 		rcu_assign_pointer(cgrp->bpf.effective[type], e);
+		cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type];
 	}
 }
 
@@ -82,30 +83,63 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
  *
  * Must be called with cgroup_mutex held.
  */
-void __cgroup_bpf_update(struct cgroup *cgrp,
-			 struct cgroup *parent,
-			 struct bpf_prog *prog,
-			 enum bpf_attach_type type)
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+			struct bpf_prog *prog, enum bpf_attach_type type,
+			bool new_overridable)
 {
-	struct bpf_prog *old_prog, *effective;
+	struct bpf_prog *old_prog, *effective = NULL;
 	struct cgroup_subsys_state *pos;
+	bool overridable = true;
 
-	old_prog = xchg(cgrp->bpf.prog + type, prog);
+	if (parent) {
+		overridable = !parent->bpf.disallow_override[type];
+		effective = rcu_dereference_protected(parent->bpf.effective[type],
+						      lockdep_is_held(&cgroup_mutex));
+	}
+
+	if (prog && effective && !overridable)
+		/* if parent has non-overridable prog attached, disallow
+		 * attaching new programs to descendent cgroup
+		 */
+		return -EPERM;
+
+	if (prog && effective && overridable != new_overridable)
+		/* if parent has overridable prog attached, only
+		 * allow overridable programs in descendent cgroup
+		 */
+		return -EPERM;
 
-	effective = (!prog && parent) ?
-		rcu_dereference_protected(parent->bpf.effective[type],
-					  lockdep_is_held(&cgroup_mutex)) :
-		prog;
+	old_prog = cgrp->bpf.prog[type];
+
+	if (prog) {
+		overridable = new_overridable;
+		effective = prog;
+		if (old_prog &&
+		    cgrp->bpf.disallow_override[type] == new_overridable)
+			/* disallow attaching non-overridable on top
+			 * of existing overridable in this cgroup
+			 * and vice versa
+			 */
+			return -EPERM;
+	}
+
+	if (!prog && !old_prog)
+		/* report error when trying to detach and nothing is attached */
+		return -ENOENT;
+
+	cgrp->bpf.prog[type] = prog;
 
 	css_for_each_descendant_pre(pos, &cgrp->self) {
 		struct cgroup *desc = container_of(pos, struct cgroup, self);
 
 		/* skip the subtree if the descendant has its own program */
-		if (desc->bpf.prog[type] && desc != cgrp)
+		if (desc->bpf.prog[type] && desc != cgrp) {
 			pos = css_rightmost_descendant(pos);
-		else
+		} else {
 			rcu_assign_pointer(desc->bpf.effective[type],
 					   effective);
+			desc->bpf.disallow_override[type] = !overridable;
+		}
 	}
 
 	if (prog)
@@ -115,6 +149,7 @@ void __cgroup_bpf_update(struct cgroup *cgrp,
 		bpf_prog_put(old_prog);
 		static_branch_dec(&cgroup_bpf_enabled_key);
 	}
+	return 0;
 }
 
 /**
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3f2bb58952d8..a753bbe7df0a 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -13,7 +13,6 @@
 #include <linux/bpf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
-#include <linux/vmalloc.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
 
@@ -103,7 +102,7 @@ static void htab_free_elems(struct bpf_htab *htab)
 		free_percpu(pptr);
 	}
 free_elems:
-	vfree(htab->elems);
+	bpf_map_area_free(htab->elems);
 }
 
 static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
@@ -125,7 +124,8 @@ static int prealloc_init(struct bpf_htab *htab)
 {
 	int err = -ENOMEM, i;
 
-	htab->elems = vzalloc(htab->elem_size * htab->map.max_entries);
+	htab->elems = bpf_map_area_alloc(htab->elem_size *
+					 htab->map.max_entries);
 	if (!htab->elems)
 		return -ENOMEM;
 
@@ -320,14 +320,10 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 		goto free_htab;
 
 	err = -ENOMEM;
-	htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct bucket),
-				      GFP_USER | __GFP_NOWARN);
-
-	if (!htab->buckets) {
-		htab->buckets = vmalloc(htab->n_buckets * sizeof(struct bucket));
-		if (!htab->buckets)
-			goto free_htab;
-	}
+	htab->buckets = bpf_map_area_alloc(htab->n_buckets *
+					   sizeof(struct bucket));
+	if (!htab->buckets)
+		goto free_htab;
 
 	for (i = 0; i < htab->n_buckets; i++) {
 		INIT_HLIST_HEAD(&htab->buckets[i].head);
@@ -354,7 +350,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
 free_extra_elems:
 	free_percpu(htab->extra_elems);
 free_buckets:
-	kvfree(htab->buckets);
+	bpf_map_area_free(htab->buckets);
 free_htab:
 	kfree(htab);
 	return ERR_PTR(err);
@@ -1014,7 +1010,7 @@ static void htab_map_free(struct bpf_map *map)
 		prealloc_destroy(htab);
 
 	free_percpu(htab->extra_elems);
-	kvfree(htab->buckets);
+	bpf_map_area_free(htab->buckets);
 	kfree(htab);
 }
 
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 732ae16d12b7..be8519148c25 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -7,7 +7,6 @@
 #include <linux/bpf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
-#include <linux/vmalloc.h>
 #include <linux/stacktrace.h>
 #include <linux/perf_event.h>
 #include "percpu_freelist.h"
@@ -32,7 +31,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
 	u32 elem_size = sizeof(struct stack_map_bucket) + smap->map.value_size;
 	int err;
 
-	smap->elems = vzalloc(elem_size * smap->map.max_entries);
+	smap->elems = bpf_map_area_alloc(elem_size * smap->map.max_entries);
 	if (!smap->elems)
 		return -ENOMEM;
 
@@ -45,7 +44,7 @@ static int prealloc_elems_and_freelist(struct bpf_stack_map *smap)
 	return 0;
 
 free_elems:
-	vfree(smap->elems);
+	bpf_map_area_free(smap->elems);
 	return err;
 }
 
@@ -76,12 +75,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	if (cost >= U32_MAX - PAGE_SIZE)
 		return ERR_PTR(-E2BIG);
 
-	smap = kzalloc(cost, GFP_USER | __GFP_NOWARN);
-	if (!smap) {
-		smap = vzalloc(cost);
-		if (!smap)
-			return ERR_PTR(-ENOMEM);
-	}
+	smap = bpf_map_area_alloc(cost);
+	if (!smap)
+		return ERR_PTR(-ENOMEM);
 
 	err = -E2BIG;
 	cost += n_buckets * (value_size + sizeof(struct stack_map_bucket));
@@ -112,7 +108,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 put_buffers:
 	put_callchain_buffers();
 free_smap:
-	kvfree(smap);
+	bpf_map_area_free(smap);
 	return ERR_PTR(err);
 }
 
@@ -262,9 +258,9 @@ static void stack_map_free(struct bpf_map *map)
 	/* wait for bpf programs to complete before freeing stack map */
 	synchronize_rcu();
 
-	vfree(smap->elems);
+	bpf_map_area_free(smap->elems);
 	pcpu_freelist_destroy(&smap->freelist);
-	kvfree(smap);
+	bpf_map_area_free(smap);
 	put_callchain_buffers();
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1d6b29e4e2c3..bbb016adbaeb 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -12,6 +12,8 @@
 #include <linux/bpf.h>
 #include <linux/syscalls.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/mmzone.h>
 #include <linux/anon_inodes.h>
 #include <linux/file.h>
 #include <linux/license.h>
@@ -49,6 +51,30 @@ void bpf_register_map_type(struct bpf_map_type_list *tl)
 	list_add(&tl->list_node, &bpf_map_types);
 }
 
+void *bpf_map_area_alloc(size_t size)
+{
+	/* We definitely need __GFP_NORETRY, so OOM killer doesn't
+	 * trigger under memory pressure as we really just want to
+	 * fail instead.
+	 */
+	const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO;
+	void *area;
+
+	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
+		area = kmalloc(size, GFP_USER | flags);
+		if (area != NULL)
+			return area;
+	}
+
+	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | flags,
+			 PAGE_KERNEL);
+}
+
+void bpf_map_area_free(void *area)
+{
+	kvfree(area);
+}
+
 int bpf_map_precharge_memlock(u32 pages)
 {
 	struct user_struct *user = get_current_user();
@@ -894,13 +920,14 @@ static int bpf_obj_get(const union bpf_attr *attr)
 
 #ifdef CONFIG_CGROUP_BPF
 
-#define BPF_PROG_ATTACH_LAST_FIELD attach_type
+#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
 
 static int bpf_prog_attach(const union bpf_attr *attr)
 {
+	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
 	struct cgroup *cgrp;
-	enum bpf_prog_type ptype;
+	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -908,6 +935,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_PROG_ATTACH))
 		return -EINVAL;
 
+	if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE)
+		return -EINVAL;
+
 	switch (attr->attach_type) {
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
@@ -930,10 +960,13 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		return PTR_ERR(cgrp);
 	}
 
-	cgroup_bpf_update(cgrp, prog, attr->attach_type);
+	ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
+				attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
+	if (ret)
+		bpf_prog_put(prog);
 	cgroup_put(cgrp);
 
-	return 0;
+	return ret;
 }
 
 #define BPF_PROG_DETACH_LAST_FIELD attach_type
@@ -941,6 +974,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 static int bpf_prog_detach(const union bpf_attr *attr)
 {
 	struct cgroup *cgrp;
+	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -956,7 +990,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		if (IS_ERR(cgrp))
 			return PTR_ERR(cgrp);
 
-		cgroup_bpf_update(cgrp, NULL, attr->attach_type);
+		ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
 		cgroup_put(cgrp);
 		break;
 
@@ -964,7 +998,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		return -EINVAL;
 	}
 
-	return 0;
+	return ret;
 }
 #endif /* CONFIG_CGROUP_BPF */
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2ee9ec3051b2..53bbca7c4859 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -5221,6 +5221,11 @@ err_free_css:
 	return ERR_PTR(err);
 }
 
+/*
+ * The returned cgroup is fully initialized including its control mask, but
+ * it isn't associated with its kernfs_node and doesn't have the control
+ * mask applied.
+ */
 static struct cgroup *cgroup_create(struct cgroup *parent)
 {
 	struct cgroup_root *root = parent->root;
@@ -5288,11 +5293,6 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 
 	cgroup_propagate_control(cgrp);
 
-	/* @cgrp doesn't have dir yet so the following will only create csses */
-	ret = cgroup_apply_control_enable(cgrp);
-	if (ret)
-		goto out_destroy;
-
 	return cgrp;
 
 out_cancel_ref:
@@ -5300,9 +5300,6 @@ out_cancel_ref:
 out_free_cgrp:
 	kfree(cgrp);
 	return ERR_PTR(ret);
-out_destroy:
-	cgroup_destroy_locked(cgrp);
-	return ERR_PTR(ret);
 }
 
 static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
@@ -6501,15 +6498,16 @@ static __init int cgroup_namespaces_init(void)
 subsys_initcall(cgroup_namespaces_init);
 
 #ifdef CONFIG_CGROUP_BPF
-void cgroup_bpf_update(struct cgroup *cgrp,
-		       struct bpf_prog *prog,
-		       enum bpf_attach_type type)
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, bool overridable)
 {
 	struct cgroup *parent = cgroup_parent(cgrp);
+	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	__cgroup_bpf_update(cgrp, parent, prog, type);
+	ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
 	mutex_unlock(&cgroup_mutex);
+	return ret;
 }
 #endif /* CONFIG_CGROUP_BPF */
 
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 435c14a45118..660549656991 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -82,19 +82,19 @@ void __delayacct_blkio_end(void)
 
 int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 {
-	cputime_t utime, stime, stimescaled, utimescaled;
+	u64 utime, stime, stimescaled, utimescaled;
 	unsigned long long t2, t3;
 	unsigned long flags, t1;
 	s64 tmp;
 
 	task_cputime(tsk, &utime, &stime);
 	tmp = (s64)d->cpu_run_real_total;
-	tmp += cputime_to_nsecs(utime + stime);
+	tmp += utime + stime;
 	d->cpu_run_real_total = (tmp < (s64)d->cpu_run_real_total) ? 0 : tmp;
 
 	task_cputime_scaled(tsk, &utimescaled, &stimescaled);
 	tmp = (s64)d->cpu_scaled_run_real_total;
-	tmp += cputime_to_nsecs(utimescaled + stimescaled);
+	tmp += utimescaled + stimescaled;
 	d->cpu_scaled_run_real_total =
 		(tmp < (s64)d->cpu_scaled_run_real_total) ? 0 : tmp;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 110b38a58493..77a932b54a64 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -355,6 +355,8 @@ enum event_type_t {
 	EVENT_FLEXIBLE = 0x1,
 	EVENT_PINNED = 0x2,
 	EVENT_TIME = 0x4,
+	/* see ctx_resched() for details */
+	EVENT_CPU = 0x8,
 	EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
 };
 
@@ -678,6 +680,8 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 	info->timestamp = ctx->timestamp;
 }
 
+static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);
+
 #define PERF_CGROUP_SWOUT	0x1 /* cgroup switch out every event */
 #define PERF_CGROUP_SWIN	0x2 /* cgroup switch in events based on task */
 
@@ -690,61 +694,46 @@ perf_cgroup_set_timestamp(struct task_struct *task,
 static void perf_cgroup_switch(struct task_struct *task, int mode)
 {
 	struct perf_cpu_context *cpuctx;
-	struct pmu *pmu;
+	struct list_head *list;
 	unsigned long flags;
 
 	/*
-	 * disable interrupts to avoid geting nr_cgroup
-	 * changes via __perf_event_disable(). Also
-	 * avoids preemption.
+	 * Disable interrupts and preemption to avoid this CPU's
+	 * cgrp_cpuctx_entry to change under us.
 	 */
 	local_irq_save(flags);
 
-	/*
-	 * we reschedule only in the presence of cgroup
-	 * constrained events.
-	 */
-
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->unique_pmu != pmu)
-			continue; /* ensure we process each cpuctx once */
+	list = this_cpu_ptr(&cgrp_cpuctx_list);
+	list_for_each_entry(cpuctx, list, cgrp_cpuctx_entry) {
+		WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
 
-		/*
-		 * perf_cgroup_events says at least one
-		 * context on this CPU has cgroup events.
-		 *
-		 * ctx->nr_cgroups reports the number of cgroup
-		 * events for a context.
-		 */
-		if (cpuctx->ctx.nr_cgroups > 0) {
-			perf_ctx_lock(cpuctx, cpuctx->task_ctx);
-			perf_pmu_disable(cpuctx->ctx.pmu);
+		perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+		perf_pmu_disable(cpuctx->ctx.pmu);
 
-			if (mode & PERF_CGROUP_SWOUT) {
-				cpu_ctx_sched_out(cpuctx, EVENT_ALL);
-				/*
-				 * must not be done before ctxswout due
-				 * to event_filter_match() in event_sched_out()
-				 */
-				cpuctx->cgrp = NULL;
-			}
+		if (mode & PERF_CGROUP_SWOUT) {
+			cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+			/*
+			 * must not be done before ctxswout due
+			 * to event_filter_match() in event_sched_out()
+			 */
+			cpuctx->cgrp = NULL;
+		}
 
-			if (mode & PERF_CGROUP_SWIN) {
-				WARN_ON_ONCE(cpuctx->cgrp);
-				/*
-				 * set cgrp before ctxsw in to allow
-				 * event_filter_match() to not have to pass
-				 * task around
-				 * we pass the cpuctx->ctx to perf_cgroup_from_task()
-				 * because cgorup events are only per-cpu
-				 */
-				cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx);
-				cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
-			}
-			perf_pmu_enable(cpuctx->ctx.pmu);
-			perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+		if (mode & PERF_CGROUP_SWIN) {
+			WARN_ON_ONCE(cpuctx->cgrp);
+			/*
+			 * set cgrp before ctxsw in to allow
+			 * event_filter_match() to not have to pass
+			 * task around
+			 * we pass the cpuctx->ctx to perf_cgroup_from_task()
+			 * because cgorup events are only per-cpu
+			 */
+			cpuctx->cgrp = perf_cgroup_from_task(task,
+							     &cpuctx->ctx);
+			cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
 		}
+		perf_pmu_enable(cpuctx->ctx.pmu);
+		perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
 	}
 
 	local_irq_restore(flags);
@@ -889,6 +878,7 @@ list_update_cgroup_event(struct perf_event *event,
 			 struct perf_event_context *ctx, bool add)
 {
 	struct perf_cpu_context *cpuctx;
+	struct list_head *cpuctx_entry;
 
 	if (!is_cgroup_event(event))
 		return;
@@ -902,15 +892,16 @@ list_update_cgroup_event(struct perf_event *event,
 	 * this will always be called from the right CPU.
 	 */
 	cpuctx = __get_cpu_context(ctx);
-
-	/*
-	 * cpuctx->cgrp is NULL until a cgroup event is sched in or
-	 * ctx->nr_cgroup == 0 .
-	 */
-	if (add && perf_cgroup_from_task(current, ctx) == event->cgrp)
-		cpuctx->cgrp = event->cgrp;
-	else if (!add)
+	cpuctx_entry = &cpuctx->cgrp_cpuctx_entry;
+	/* cpuctx->cgrp is NULL unless a cgroup event is active in this CPU .*/
+	if (add) {
+		list_add(cpuctx_entry, this_cpu_ptr(&cgrp_cpuctx_list));
+		if (perf_cgroup_from_task(current, ctx) == event->cgrp)
+			cpuctx->cgrp = event->cgrp;
+	} else {
+		list_del(cpuctx_entry);
 		cpuctx->cgrp = NULL;
+	}
 }
 
 #else /* !CONFIG_CGROUP_PERF */
@@ -1453,6 +1444,20 @@ static void update_group_times(struct perf_event *leader)
 		update_event_times(event);
 }
 
+static enum event_type_t get_event_type(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	enum event_type_t event_type;
+
+	lockdep_assert_held(&ctx->lock);
+
+	event_type = event->attr.pinned ? EVENT_PINNED : EVENT_FLEXIBLE;
+	if (!ctx->task)
+		event_type |= EVENT_CPU;
+
+	return event_type;
+}
+
 static struct list_head *
 ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 {
@@ -1469,7 +1474,6 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx)
 static void
 list_add_event(struct perf_event *event, struct perf_event_context *ctx)
 {
-
 	lockdep_assert_held(&ctx->lock);
 
 	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
@@ -1624,6 +1628,8 @@ static void perf_group_attach(struct perf_event *event)
 {
 	struct perf_event *group_leader = event->group_leader, *pos;
 
+	lockdep_assert_held(&event->ctx->lock);
+
 	/*
 	 * We can have double attach due to group movement in perf_event_open.
 	 */
@@ -1697,6 +1703,8 @@ static void perf_group_detach(struct perf_event *event)
 	struct perf_event *sibling, *tmp;
 	struct list_head *list = NULL;
 
+	lockdep_assert_held(&event->ctx->lock);
+
 	/*
 	 * We can have double detach due to exit/hot-unplug + close.
 	 */
@@ -1895,9 +1903,29 @@ __perf_remove_from_context(struct perf_event *event,
  */
 static void perf_remove_from_context(struct perf_event *event, unsigned long flags)
 {
-	lockdep_assert_held(&event->ctx->mutex);
+	struct perf_event_context *ctx = event->ctx;
+
+	lockdep_assert_held(&ctx->mutex);
 
 	event_function_call(event, __perf_remove_from_context, (void *)flags);
+
+	/*
+	 * The above event_function_call() can NO-OP when it hits
+	 * TASK_TOMBSTONE. In that case we must already have been detached
+	 * from the context (by perf_event_exit_event()) but the grouping
+	 * might still be in-tact.
+	 */
+	WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT);
+	if ((flags & DETACH_GROUP) &&
+	    (event->attach_state & PERF_ATTACH_GROUP)) {
+		/*
+		 * Since in that case we cannot possibly be scheduled, simply
+		 * detach now.
+		 */
+		raw_spin_lock_irq(&ctx->lock);
+		perf_group_detach(event);
+		raw_spin_unlock_irq(&ctx->lock);
+	}
 }
 
 /*
@@ -2203,7 +2231,8 @@ ctx_sched_in(struct perf_event_context *ctx,
 	     struct task_struct *task);
 
 static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
-			       struct perf_event_context *ctx)
+			       struct perf_event_context *ctx,
+			       enum event_type_t event_type)
 {
 	if (!cpuctx->task_ctx)
 		return;
@@ -2211,7 +2240,7 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
 	if (WARN_ON_ONCE(ctx != cpuctx->task_ctx))
 		return;
 
-	ctx_sched_out(ctx, cpuctx, EVENT_ALL);
+	ctx_sched_out(ctx, cpuctx, event_type);
 }
 
 static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
@@ -2226,13 +2255,51 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
 		ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
 }
 
+/*
+ * We want to maintain the following priority of scheduling:
+ *  - CPU pinned (EVENT_CPU | EVENT_PINNED)
+ *  - task pinned (EVENT_PINNED)
+ *  - CPU flexible (EVENT_CPU | EVENT_FLEXIBLE)
+ *  - task flexible (EVENT_FLEXIBLE).
+ *
+ * In order to avoid unscheduling and scheduling back in everything every
+ * time an event is added, only do it for the groups of equal priority and
+ * below.
+ *
+ * This can be called after a batch operation on task events, in which case
+ * event_type is a bit mask of the types of events involved. For CPU events,
+ * event_type is only either EVENT_PINNED or EVENT_FLEXIBLE.
+ */
 static void ctx_resched(struct perf_cpu_context *cpuctx,
-			struct perf_event_context *task_ctx)
+			struct perf_event_context *task_ctx,
+			enum event_type_t event_type)
 {
+	enum event_type_t ctx_event_type = event_type & EVENT_ALL;
+	bool cpu_event = !!(event_type & EVENT_CPU);
+
+	/*
+	 * If pinned groups are involved, flexible groups also need to be
+	 * scheduled out.
+	 */
+	if (event_type & EVENT_PINNED)
+		event_type |= EVENT_FLEXIBLE;
+
 	perf_pmu_disable(cpuctx->ctx.pmu);
 	if (task_ctx)
-		task_ctx_sched_out(cpuctx, task_ctx);
-	cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+		task_ctx_sched_out(cpuctx, task_ctx, event_type);
+
+	/*
+	 * Decide which cpu ctx groups to schedule out based on the types
+	 * of events that caused rescheduling:
+	 *  - EVENT_CPU: schedule out corresponding groups;
+	 *  - EVENT_PINNED task events: schedule out EVENT_FLEXIBLE groups;
+	 *  - otherwise, do nothing more.
+	 */
+	if (cpu_event)
+		cpu_ctx_sched_out(cpuctx, ctx_event_type);
+	else if (ctx_event_type & EVENT_PINNED)
+		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+
 	perf_event_sched_in(cpuctx, task_ctx, current);
 	perf_pmu_enable(cpuctx->ctx.pmu);
 }
@@ -2279,7 +2346,7 @@ static int  __perf_install_in_context(void *info)
 	if (reprogram) {
 		ctx_sched_out(ctx, cpuctx, EVENT_TIME);
 		add_event_to_ctx(event, ctx);
-		ctx_resched(cpuctx, task_ctx);
+		ctx_resched(cpuctx, task_ctx, get_event_type(event));
 	} else {
 		add_event_to_ctx(event, ctx);
 	}
@@ -2446,7 +2513,7 @@ static void __perf_event_enable(struct perf_event *event,
 	if (ctx->task)
 		WARN_ON_ONCE(task_ctx != ctx);
 
-	ctx_resched(cpuctx, task_ctx);
+	ctx_resched(cpuctx, task_ctx, get_event_type(event));
 }
 
 /*
@@ -2873,7 +2940,7 @@ unlock:
 
 	if (do_switch) {
 		raw_spin_lock(&ctx->lock);
-		task_ctx_sched_out(cpuctx, ctx);
+		task_ctx_sched_out(cpuctx, ctx, EVENT_ALL);
 		raw_spin_unlock(&ctx->lock);
 	}
 }
@@ -2920,7 +2987,7 @@ static void perf_pmu_sched_task(struct task_struct *prev,
 		return;
 
 	list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
-		pmu = cpuctx->unique_pmu; /* software PMUs will not have sched_task */
+		pmu = cpuctx->ctx.pmu; /* software PMUs will not have sched_task */
 
 		if (WARN_ON_ONCE(!pmu->sched_task))
 			continue;
@@ -3110,8 +3177,12 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 	 * We want to keep the following priority order:
 	 * cpu pinned (that don't need to move), task pinned,
 	 * cpu flexible, task flexible.
+	 *
+	 * However, if task's ctx is not carrying any pinned
+	 * events, no need to flip the cpuctx's events around.
 	 */
-	cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
+	if (!list_empty(&ctx->pinned_groups))
+		cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
 	perf_event_sched_in(cpuctx, ctx, task);
 	perf_pmu_enable(ctx->pmu);
 	perf_ctx_unlock(cpuctx, ctx);
@@ -3426,6 +3497,7 @@ static int event_enable_on_exec(struct perf_event *event,
 static void perf_event_enable_on_exec(int ctxn)
 {
 	struct perf_event_context *ctx, *clone_ctx = NULL;
+	enum event_type_t event_type = 0;
 	struct perf_cpu_context *cpuctx;
 	struct perf_event *event;
 	unsigned long flags;
@@ -3439,15 +3511,17 @@ static void perf_event_enable_on_exec(int ctxn)
 	cpuctx = __get_cpu_context(ctx);
 	perf_ctx_lock(cpuctx, ctx);
 	ctx_sched_out(ctx, cpuctx, EVENT_TIME);
-	list_for_each_entry(event, &ctx->event_list, event_entry)
+	list_for_each_entry(event, &ctx->event_list, event_entry) {
 		enabled |= event_enable_on_exec(event, ctx);
+		event_type |= get_event_type(event);
+	}
 
 	/*
 	 * Unclone and reschedule this context if we enabled any event.
 	 */
 	if (enabled) {
 		clone_ctx = unclone_ctx(ctx);
-		ctx_resched(cpuctx, ctx);
+		ctx_resched(cpuctx, ctx, event_type);
 	}
 	perf_ctx_unlock(cpuctx, ctx);
 
@@ -3464,14 +3538,15 @@ struct perf_read_data {
 	int ret;
 };
 
-static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
 {
-	int event_cpu = event->oncpu;
 	u16 local_pkg, event_pkg;
 
 	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
-		event_pkg =  topology_physical_package_id(event_cpu);
-		local_pkg =  topology_physical_package_id(local_cpu);
+		int local_cpu = smp_processor_id();
+
+		event_pkg = topology_physical_package_id(event_cpu);
+		local_pkg = topology_physical_package_id(local_cpu);
 
 		if (event_pkg == local_pkg)
 			return local_cpu;
@@ -3601,7 +3676,7 @@ u64 perf_event_read_local(struct perf_event *event)
 
 static int perf_event_read(struct perf_event *event, bool group)
 {
-	int ret = 0, cpu_to_read, local_cpu;
+	int event_cpu, ret = 0;
 
 	/*
 	 * If event is enabled and currently active on a CPU, update the
@@ -3614,21 +3689,25 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.ret = 0,
 		};
 
-		local_cpu = get_cpu();
-		cpu_to_read = find_cpu_to_read(event, local_cpu);
-		put_cpu();
+		event_cpu = READ_ONCE(event->oncpu);
+		if ((unsigned)event_cpu >= nr_cpu_ids)
+			return 0;
+
+		preempt_disable();
+		event_cpu = __perf_event_read_cpu(event, event_cpu);
 
 		/*
 		 * Purposely ignore the smp_call_function_single() return
 		 * value.
 		 *
-		 * If event->oncpu isn't a valid CPU it means the event got
+		 * If event_cpu isn't a valid CPU it means the event got
 		 * scheduled out and that will have updated the event count.
 		 *
 		 * Therefore, either way, we'll have an up-to-date event count
 		 * after this.
 		 */
-		(void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
+		(void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1);
+		preempt_enable();
 		ret = data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;
@@ -6609,6 +6688,27 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 	char *buf = NULL;
 	char *name;
 
+	if (vma->vm_flags & VM_READ)
+		prot |= PROT_READ;
+	if (vma->vm_flags & VM_WRITE)
+		prot |= PROT_WRITE;
+	if (vma->vm_flags & VM_EXEC)
+		prot |= PROT_EXEC;
+
+	if (vma->vm_flags & VM_MAYSHARE)
+		flags = MAP_SHARED;
+	else
+		flags = MAP_PRIVATE;
+
+	if (vma->vm_flags & VM_DENYWRITE)
+		flags |= MAP_DENYWRITE;
+	if (vma->vm_flags & VM_MAYEXEC)
+		flags |= MAP_EXECUTABLE;
+	if (vma->vm_flags & VM_LOCKED)
+		flags |= MAP_LOCKED;
+	if (vma->vm_flags & VM_HUGETLB)
+		flags |= MAP_HUGETLB;
+
 	if (file) {
 		struct inode *inode;
 		dev_t dev;
@@ -6635,27 +6735,6 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		maj = MAJOR(dev);
 		min = MINOR(dev);
 
-		if (vma->vm_flags & VM_READ)
-			prot |= PROT_READ;
-		if (vma->vm_flags & VM_WRITE)
-			prot |= PROT_WRITE;
-		if (vma->vm_flags & VM_EXEC)
-			prot |= PROT_EXEC;
-
-		if (vma->vm_flags & VM_MAYSHARE)
-			flags = MAP_SHARED;
-		else
-			flags = MAP_PRIVATE;
-
-		if (vma->vm_flags & VM_DENYWRITE)
-			flags |= MAP_DENYWRITE;
-		if (vma->vm_flags & VM_MAYEXEC)
-			flags |= MAP_EXECUTABLE;
-		if (vma->vm_flags & VM_LOCKED)
-			flags |= MAP_LOCKED;
-		if (vma->vm_flags & VM_HUGETLB)
-			flags |= MAP_HUGETLB;
-
 		goto got_name;
 	} else {
 		if (vma->vm_ops && vma->vm_ops->name) {
@@ -8016,6 +8095,9 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	if (task == TASK_TOMBSTONE)
 		return;
 
+	if (!ifh->nr_file_filters)
+		return;
+
 	mm = get_task_mm(event->ctx->task);
 	if (!mm)
 		goto restart;
@@ -8186,6 +8268,7 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 		 * attribute.
 		 */
 		if (state == IF_STATE_END) {
+			ret = -EINVAL;
 			if (kernel && event->attr.exclude_kernel)
 				goto fail;
 
@@ -8193,6 +8276,18 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 				if (!filename)
 					goto fail;
 
+				/*
+				 * For now, we only support file-based filters
+				 * in per-task events; doing so for CPU-wide
+				 * events requires additional context switching
+				 * trickery, since same object code will be
+				 * mapped at different virtual addresses in
+				 * different processes.
+				 */
+				ret = -EOPNOTSUPP;
+				if (!event->ctx->task)
+					goto fail_free_name;
+
 				/* look up the path and grab its inode */
 				ret = kern_path(filename, LOOKUP_FOLLOW, &path);
 				if (ret)
@@ -8208,6 +8303,8 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr,
 				    !S_ISREG(filter->inode->i_mode))
 					/* free_filters_list() will iput() */
 					goto fail;
+
+				event->addr_filters.nr_file_filters++;
 			}
 
 			/* ready to consume more filters */
@@ -8247,24 +8344,13 @@ perf_event_set_addr_filter(struct perf_event *event, char *filter_str)
 	if (WARN_ON_ONCE(event->parent))
 		return -EINVAL;
 
-	/*
-	 * For now, we only support filtering in per-task events; doing so
-	 * for CPU-wide events requires additional context switching trickery,
-	 * since same object code will be mapped at different virtual
-	 * addresses in different processes.
-	 */
-	if (!event->ctx->task)
-		return -EOPNOTSUPP;
-
 	ret = perf_event_parse_addr_filter(event, filter_str, &filters);
 	if (ret)
-		return ret;
+		goto fail_clear_files;
 
 	ret = event->pmu->addr_filters_validate(&filters);
-	if (ret) {
-		free_filters_list(&filters);
-		return ret;
-	}
+	if (ret)
+		goto fail_free_filters;
 
 	/* remove existing filters, if any */
 	perf_addr_filters_splice(event, &filters);
@@ -8273,6 +8359,14 @@ perf_event_set_addr_filter(struct perf_event *event, char *filter_str)
 	perf_event_for_each_child(event, perf_event_addr_filters_apply);
 
 	return ret;
+
+fail_free_filters:
+	free_filters_list(&filters);
+
+fail_clear_files:
+	event->addr_filters.nr_file_filters = 0;
+
+	return ret;
 }
 
 static int perf_event_set_filter(struct perf_event *event, void __user *arg)
@@ -8624,37 +8718,10 @@ static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
 	return NULL;
 }
 
-static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct perf_cpu_context *cpuctx;
-
-		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
-
-		if (cpuctx->unique_pmu == old_pmu)
-			cpuctx->unique_pmu = pmu;
-	}
-}
-
 static void free_pmu_context(struct pmu *pmu)
 {
-	struct pmu *i;
-
 	mutex_lock(&pmus_lock);
-	/*
-	 * Like a real lame refcount.
-	 */
-	list_for_each_entry(i, &pmus, entry) {
-		if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
-			update_pmu_context(i, pmu);
-			goto out;
-		}
-	}
-
 	free_percpu(pmu->pmu_cpu_context);
-out:
 	mutex_unlock(&pmus_lock);
 }
 
@@ -8858,8 +8925,6 @@ skip_type:
 		cpuctx->ctx.pmu = pmu;
 
 		__perf_mux_hrtimer_init(cpuctx, cpu);
-
-		cpuctx->unique_pmu = pmu;
 	}
 
 got_cpu_context:
@@ -8977,6 +9042,14 @@ static struct pmu *perf_init_event(struct perf_event *event)
 
 	idx = srcu_read_lock(&pmus_srcu);
 
+	/* Try parent's PMU first: */
+	if (event->parent && event->parent->pmu) {
+		pmu = event->parent->pmu;
+		ret = perf_try_init_event(pmu, event);
+		if (!ret)
+			goto unlock;
+	}
+
 	rcu_read_lock();
 	pmu = idr_find(&pmu_idr, event->attr.type);
 	rcu_read_unlock();
@@ -10237,7 +10310,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
 	 * in.
 	 */
 	raw_spin_lock_irq(&child_ctx->lock);
-	task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx);
+	task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx, EVENT_ALL);
 
 	/*
 	 * Now that the context is inactive, destroy the task <-> ctx relation
@@ -10686,6 +10759,9 @@ static void __init perf_event_init_all_cpus(void)
 		INIT_LIST_HEAD(&per_cpu(pmu_sb_events.list, cpu));
 		raw_spin_lock_init(&per_cpu(pmu_sb_events.lock, cpu));
 
+#ifdef CONFIG_CGROUP_PERF
+		INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
+#endif
 		INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
 	}
 }
diff --git a/kernel/exit.c b/kernel/exit.c
index 8f14b866f9f6..b67c57faa705 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -55,6 +55,7 @@
 #include <linux/shm.h>
 #include <linux/kcov.h>
 #include <linux/random.h>
+#include <linux/rcuwait.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -86,7 +87,7 @@ static void __exit_signal(struct task_struct *tsk)
 	bool group_dead = thread_group_leader(tsk);
 	struct sighand_struct *sighand;
 	struct tty_struct *uninitialized_var(tty);
-	cputime_t utime, stime;
+	u64 utime, stime;
 
 	sighand = rcu_dereference_check(tsk->sighand,
 					lockdep_tasklist_lock_is_held());
@@ -282,6 +283,35 @@ retry:
 	return task;
 }
 
+void rcuwait_wake_up(struct rcuwait *w)
+{
+	struct task_struct *task;
+
+	rcu_read_lock();
+
+	/*
+	 * Order condition vs @task, such that everything prior to the load
+	 * of @task is visible. This is the condition as to why the user called
+	 * rcuwait_trywake() in the first place. Pairs with set_current_state()
+	 * barrier (A) in rcuwait_wait_event().
+	 *
+	 *    WAIT                WAKE
+	 *    [S] tsk = current	  [S] cond = true
+	 *        MB (A)	      MB (B)
+	 *    [L] cond		  [L] tsk
+	 */
+	smp_rmb(); /* (B) */
+
+	/*
+	 * Avoid using task_rcu_dereference() magic as long as we are careful,
+	 * see comment in rcuwait_wait_event() regarding ->exit_state.
+	 */
+	task = rcu_dereference(w->task);
+	if (task)
+		wake_up_process(task);
+	rcu_read_unlock();
+}
+
 struct task_struct *try_get_task_struct(struct task_struct **ptask)
 {
 	struct task_struct *task;
@@ -468,12 +498,12 @@ assign_new_owner:
  * Turn us into a lazy TLB process if we
  * aren't already..
  */
-static void exit_mm(struct task_struct *tsk)
+static void exit_mm(void)
 {
-	struct mm_struct *mm = tsk->mm;
+	struct mm_struct *mm = current->mm;
 	struct core_state *core_state;
 
-	mm_release(tsk, mm);
+	mm_release(current, mm);
 	if (!mm)
 		return;
 	sync_mm_rss(mm);
@@ -491,7 +521,7 @@ static void exit_mm(struct task_struct *tsk)
 
 		up_read(&mm->mmap_sem);
 
-		self.task = tsk;
+		self.task = current;
 		self.next = xchg(&core_state->dumper.next, &self);
 		/*
 		 * Implies mb(), the result of xchg() must be visible
@@ -501,22 +531,22 @@ static void exit_mm(struct task_struct *tsk)
 			complete(&core_state->startup);
 
 		for (;;) {
-			set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+			set_current_state(TASK_UNINTERRUPTIBLE);
 			if (!self.task) /* see coredump_finish() */
 				break;
 			freezable_schedule();
 		}
-		__set_task_state(tsk, TASK_RUNNING);
+		__set_current_state(TASK_RUNNING);
 		down_read(&mm->mmap_sem);
 	}
 	atomic_inc(&mm->mm_count);
-	BUG_ON(mm != tsk->active_mm);
+	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
-	task_lock(tsk);
-	tsk->mm = NULL;
+	task_lock(current);
+	current->mm = NULL;
 	up_read(&mm->mmap_sem);
 	enter_lazy_tlb(mm, current);
-	task_unlock(tsk);
+	task_unlock(current);
 	mm_update_next_owner(mm);
 	mmput(mm);
 	if (test_thread_flag(TIF_MEMDIE))
@@ -823,7 +853,7 @@ void __noreturn do_exit(long code)
 	tsk->exit_code = code;
 	taskstats_exit(tsk, group_dead);
 
-	exit_mm(tsk);
+	exit_mm();
 
 	if (group_dead)
 		acct_process();
@@ -1091,7 +1121,7 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		struct signal_struct *sig = p->signal;
 		struct signal_struct *psig = current->signal;
 		unsigned long maxrss;
-		cputime_t tgutime, tgstime;
+		u64 tgutime, tgstime;
 
 		/*
 		 * The resource counters for the group leader are in its
diff --git a/kernel/extable.c b/kernel/extable.c
index e3beec4a2339..e1359474baa5 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/init.h>
+#include <linux/kprobes.h>
 
 #include <asm/sections.h>
 #include <linux/uaccess.h>
@@ -104,6 +105,8 @@ int __kernel_text_address(unsigned long addr)
 		return 1;
 	if (is_ftrace_trampoline(addr))
 		return 1;
+	if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
+		return 1;
 	/*
 	 * There might be init symbols in saved stacktraces.
 	 * Give those symbols a chance to be printed in
@@ -123,7 +126,11 @@ int kernel_text_address(unsigned long addr)
 		return 1;
 	if (is_module_text_address(addr))
 		return 1;
-	return is_ftrace_trampoline(addr);
+	if (is_ftrace_trampoline(addr))
+		return 1;
+	if (is_kprobe_optinsn_slot(addr) || is_kprobe_insn_slot(addr))
+		return 1;
+	return 0;
 }
 
 /*
diff --git a/kernel/fork.c b/kernel/fork.c
index 11c5c8ab827c..ff82e24573b6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -432,11 +432,13 @@ void __init fork_init(void)
 	int i;
 #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
 #ifndef ARCH_MIN_TASKALIGN
-#define ARCH_MIN_TASKALIGN	L1_CACHE_BYTES
+#define ARCH_MIN_TASKALIGN	0
 #endif
+	int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN);
+
 	/* create a slab on which task_structs can be allocated */
 	task_struct_cachep = kmem_cache_create("task_struct",
-			arch_task_struct_size, ARCH_MIN_TASKALIGN,
+			arch_task_struct_size, align,
 			SLAB_PANIC|SLAB_NOTRACK|SLAB_ACCOUNT, NULL);
 #endif
 
@@ -1304,6 +1306,7 @@ void __cleanup_sighand(struct sighand_struct *sighand)
 	}
 }
 
+#ifdef CONFIG_POSIX_TIMERS
 /*
  * Initialize POSIX timer handling for a thread group.
  */
@@ -1313,7 +1316,7 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 
 	cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
 	if (cpu_limit != RLIM_INFINITY) {
-		sig->cputime_expires.prof_exp = secs_to_cputime(cpu_limit);
+		sig->cputime_expires.prof_exp = cpu_limit * NSEC_PER_SEC;
 		sig->cputimer.running = true;
 	}
 
@@ -1322,6 +1325,9 @@ static void posix_cpu_timers_init_group(struct signal_struct *sig)
 	INIT_LIST_HEAD(&sig->cpu_timers[1]);
 	INIT_LIST_HEAD(&sig->cpu_timers[2]);
 }
+#else
+static inline void posix_cpu_timers_init_group(struct signal_struct *sig) { }
+#endif
 
 static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
@@ -1346,11 +1352,11 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	init_waitqueue_head(&sig->wait_chldexit);
 	sig->curr_target = tsk;
 	init_sigpending(&sig->shared_pending);
-	INIT_LIST_HEAD(&sig->posix_timers);
 	seqlock_init(&sig->stats_lock);
 	prev_cputime_init(&sig->prev_cputime);
 
 #ifdef CONFIG_POSIX_TIMERS
+	INIT_LIST_HEAD(&sig->posix_timers);
 	hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	sig->real_timer.function = it_real_fn;
 #endif
@@ -1425,6 +1431,7 @@ static void rt_mutex_init_task(struct task_struct *p)
 #endif
 }
 
+#ifdef CONFIG_POSIX_TIMERS
 /*
  * Initialize POSIX timer handling for a single task.
  */
@@ -1437,6 +1444,9 @@ static void posix_cpu_timers_init(struct task_struct *tsk)
 	INIT_LIST_HEAD(&tsk->cpu_timers[1]);
 	INIT_LIST_HEAD(&tsk->cpu_timers[2]);
 }
+#else
+static inline void posix_cpu_timers_init(struct task_struct *tsk) { }
+#endif
 
 static inline void
 init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
diff --git a/kernel/futex.c b/kernel/futex.c
index 0842c8ca534b..cdf365036141 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -3323,4 +3323,4 @@ static int __init futex_init(void)
 
 	return 0;
 }
-__initcall(futex_init);
+core_initcall(futex_init);
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index 74d90a754268..1613bfd48365 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -2,6 +2,7 @@
 #include <linux/interrupt.h>
 #include <linux/device.h>
 #include <linux/gfp.h>
+#include <linux/irq.h>
 
 /*
  * Device resource management aware IRQ request/free implementation.
@@ -33,7 +34,7 @@ static int devm_irq_match(struct device *dev, void *res, void *data)
  *	@thread_fn: function to be called in a threaded interrupt context. NULL
  *		    for devices which handle everything in @handler
  *	@irqflags: Interrupt type flags
- *	@devname: An ascii name for the claiming device
+ *	@devname: An ascii name for the claiming device, dev_name(dev) if NULL
  *	@dev_id: A cookie passed back to the handler function
  *
  *	Except for the extra @dev argument, this function takes the
@@ -57,6 +58,9 @@ int devm_request_threaded_irq(struct device *dev, unsigned int irq,
 	if (!dr)
 		return -ENOMEM;
 
+	if (!devname)
+		devname = dev_name(dev);
+
 	rc = request_threaded_irq(irq, handler, thread_fn, irqflags, devname,
 				  dev_id);
 	if (rc) {
@@ -80,7 +84,7 @@ EXPORT_SYMBOL(devm_request_threaded_irq);
  *	@thread_fn: function to be called in a threaded interrupt context. NULL
  *		    for devices which handle everything in @handler
  *	@irqflags: Interrupt type flags
- *	@devname: An ascii name for the claiming device
+ *	@devname: An ascii name for the claiming device, dev_name(dev) if NULL
  *	@dev_id: A cookie passed back to the handler function
  *
  *	Except for the extra @dev argument, this function takes the
@@ -103,6 +107,9 @@ int devm_request_any_context_irq(struct device *dev, unsigned int irq,
 	if (!dr)
 		return -ENOMEM;
 
+	if (!devname)
+		devname = dev_name(dev);
+
 	rc = request_any_context_irq(irq, handler, irqflags, devname, dev_id);
 	if (rc < 0) {
 		devres_free(dr);
@@ -137,3 +144,57 @@ void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id)
 	free_irq(irq, dev_id);
 }
 EXPORT_SYMBOL(devm_free_irq);
+
+struct irq_desc_devres {
+	unsigned int from;
+	unsigned int cnt;
+};
+
+static void devm_irq_desc_release(struct device *dev, void *res)
+{
+	struct irq_desc_devres *this = res;
+
+	irq_free_descs(this->from, this->cnt);
+}
+
+/**
+ * __devm_irq_alloc_descs - Allocate and initialize a range of irq descriptors
+ *			    for a managed device
+ * @dev:	Device to allocate the descriptors for
+ * @irq:	Allocate for specific irq number if irq >= 0
+ * @from:	Start the search from this irq number
+ * @cnt:	Number of consecutive irqs to allocate
+ * @node:	Preferred node on which the irq descriptor should be allocated
+ * @owner:	Owning module (can be NULL)
+ * @affinity:	Optional pointer to an affinity mask array of size @cnt
+ *		which hints where the irq descriptors should be allocated
+ *		and which default affinities to use
+ *
+ * Returns the first irq number or error code.
+ *
+ * Note: Use the provided wrappers (devm_irq_alloc_desc*) for simplicity.
+ */
+int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from,
+			   unsigned int cnt, int node, struct module *owner,
+			   const struct cpumask *affinity)
+{
+	struct irq_desc_devres *dr;
+	int base;
+
+	dr = devres_alloc(devm_irq_desc_release, sizeof(*dr), GFP_KERNEL);
+	if (!dr)
+		return -ENOMEM;
+
+	base = __irq_alloc_descs(irq, from, cnt, node, owner, affinity);
+	if (base < 0) {
+		devres_free(dr);
+		return base;
+	}
+
+	dr->from = base;
+	dr->cnt = cnt;
+	devres_add(dev, dr);
+
+	return base;
+}
+EXPORT_SYMBOL_GPL(__devm_irq_alloc_descs);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 8c0a0ae43521..31805f237396 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -278,6 +278,31 @@ struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
 EXPORT_SYMBOL_GPL(irq_find_matching_fwspec);
 
 /**
+ * irq_domain_check_msi_remap - Check whether all MSI irq domains implement
+ * IRQ remapping
+ *
+ * Return: false if any MSI irq domain does not support IRQ remapping,
+ * true otherwise (including if there is no MSI irq domain)
+ */
+bool irq_domain_check_msi_remap(void)
+{
+	struct irq_domain *h;
+	bool ret = true;
+
+	mutex_lock(&irq_domain_mutex);
+	list_for_each_entry(h, &irq_domain_list, link) {
+		if (irq_domain_is_msi(h) &&
+		    !irq_domain_hierarchical_is_msi_remap(h)) {
+			ret = false;
+			break;
+		}
+	}
+	mutex_unlock(&irq_domain_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(irq_domain_check_msi_remap);
+
+/**
  * irq_set_default_host() - Set a "default" irq domain
  * @domain: default domain pointer
  *
@@ -1346,6 +1371,30 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain,
 }
 EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent);
 
+static void __irq_domain_activate_irq(struct irq_data *irq_data)
+{
+	if (irq_data && irq_data->domain) {
+		struct irq_domain *domain = irq_data->domain;
+
+		if (irq_data->parent_data)
+			__irq_domain_activate_irq(irq_data->parent_data);
+		if (domain->ops->activate)
+			domain->ops->activate(domain, irq_data);
+	}
+}
+
+static void __irq_domain_deactivate_irq(struct irq_data *irq_data)
+{
+	if (irq_data && irq_data->domain) {
+		struct irq_domain *domain = irq_data->domain;
+
+		if (domain->ops->deactivate)
+			domain->ops->deactivate(domain, irq_data);
+		if (irq_data->parent_data)
+			__irq_domain_deactivate_irq(irq_data->parent_data);
+	}
+}
+
 /**
  * irq_domain_activate_irq - Call domain_ops->activate recursively to activate
  *			     interrupt
@@ -1356,13 +1405,9 @@ EXPORT_SYMBOL_GPL(irq_domain_free_irqs_parent);
  */
 void irq_domain_activate_irq(struct irq_data *irq_data)
 {
-	if (irq_data && irq_data->domain) {
-		struct irq_domain *domain = irq_data->domain;
-
-		if (irq_data->parent_data)
-			irq_domain_activate_irq(irq_data->parent_data);
-		if (domain->ops->activate)
-			domain->ops->activate(domain, irq_data);
+	if (!irqd_is_activated(irq_data)) {
+		__irq_domain_activate_irq(irq_data);
+		irqd_set_activated(irq_data);
 	}
 }
 
@@ -1376,13 +1421,9 @@ void irq_domain_activate_irq(struct irq_data *irq_data)
  */
 void irq_domain_deactivate_irq(struct irq_data *irq_data)
 {
-	if (irq_data && irq_data->domain) {
-		struct irq_domain *domain = irq_data->domain;
-
-		if (domain->ops->deactivate)
-			domain->ops->deactivate(domain, irq_data);
-		if (irq_data->parent_data)
-			irq_domain_deactivate_irq(irq_data->parent_data);
+	if (irqd_is_activated(irq_data)) {
+		__irq_domain_deactivate_irq(irq_data);
+		irqd_clr_activated(irq_data);
 	}
 }
 
@@ -1392,6 +1433,20 @@ static void irq_domain_check_hierarchy(struct irq_domain *domain)
 	if (domain->ops->alloc)
 		domain->flags |= IRQ_DOMAIN_FLAG_HIERARCHY;
 }
+
+/**
+ * irq_domain_hierarchical_is_msi_remap - Check if the domain or any
+ * parent has MSI remapping support
+ * @domain: domain pointer
+ */
+bool irq_domain_hierarchical_is_msi_remap(struct irq_domain *domain)
+{
+	for (; domain; domain = domain->parent) {
+		if (irq_domain_is_msi_remap(domain))
+			return true;
+	}
+	return false;
+}
 #else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 /**
  * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index ee230063f033..ddc2f5427f75 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -270,8 +270,8 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
 		msi_domain_update_chip_ops(info);
 
-	return irq_domain_create_hierarchy(parent, 0, 0, fwnode,
-					   &msi_domain_ops, info);
+	return irq_domain_create_hierarchy(parent, IRQ_DOMAIN_FLAG_MSI, 0,
+					   fwnode, &msi_domain_ops, info);
 }
 
 int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index feaa813b84a9..c53edad7b459 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -487,6 +487,8 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 	if (desc->irq_data.domain)
 		seq_printf(p, " %*d", prec, (int) desc->irq_data.hwirq);
+	else
+		seq_printf(p, " %*s", prec, "");
 #ifdef CONFIG_GENERIC_IRQ_SHOW_LEVEL
 	seq_printf(p, " %-8s", irqd_is_level_type(&desc->irq_data) ? "Level" : "Edge");
 #endif
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 5707f97a3e6a..061ba7eed4ed 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -175,7 +175,9 @@ out:
 
 static inline int bad_action_ret(irqreturn_t action_ret)
 {
-	if (likely(action_ret <= (IRQ_HANDLED | IRQ_WAKE_THREAD)))
+	unsigned int r = action_ret;
+
+	if (likely(r <= (IRQ_HANDLED | IRQ_WAKE_THREAD)))
 		return 0;
 	return 1;
 }
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 43460104f119..ebb4dadca66b 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -149,9 +149,11 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 	struct kprobe_insn_page *kip;
 	kprobe_opcode_t *slot = NULL;
 
+	/* Since the slot array is not protected by rcu, we need a mutex */
 	mutex_lock(&c->mutex);
  retry:
-	list_for_each_entry(kip, &c->pages, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
 		if (kip->nused < slots_per_page(c)) {
 			int i;
 			for (i = 0; i < slots_per_page(c); i++) {
@@ -159,6 +161,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 					kip->slot_used[i] = SLOT_USED;
 					kip->nused++;
 					slot = kip->insns + (i * c->insn_size);
+					rcu_read_unlock();
 					goto out;
 				}
 			}
@@ -167,6 +170,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 			WARN_ON(1);
 		}
 	}
+	rcu_read_unlock();
 
 	/* If there are any garbage slots, collect it and try again. */
 	if (c->nr_garbage && collect_garbage_slots(c) == 0)
@@ -193,7 +197,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c)
 	kip->nused = 1;
 	kip->ngarbage = 0;
 	kip->cache = c;
-	list_add(&kip->list, &c->pages);
+	list_add_rcu(&kip->list, &c->pages);
 	slot = kip->insns;
 out:
 	mutex_unlock(&c->mutex);
@@ -213,7 +217,8 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * next time somebody inserts a probe.
 		 */
 		if (!list_is_singular(&kip->list)) {
-			list_del(&kip->list);
+			list_del_rcu(&kip->list);
+			synchronize_rcu();
 			kip->cache->free(kip->insns);
 			kfree(kip);
 		}
@@ -235,8 +240,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c)
 			continue;
 		kip->ngarbage = 0;	/* we will collect all garbages */
 		for (i = 0; i < slots_per_page(c); i++) {
-			if (kip->slot_used[i] == SLOT_DIRTY &&
-			    collect_one_slot(kip, i))
+			if (kip->slot_used[i] == SLOT_DIRTY && collect_one_slot(kip, i))
 				break;
 		}
 	}
@@ -248,29 +252,60 @@ void __free_insn_slot(struct kprobe_insn_cache *c,
 		      kprobe_opcode_t *slot, int dirty)
 {
 	struct kprobe_insn_page *kip;
+	long idx;
 
 	mutex_lock(&c->mutex);
-	list_for_each_entry(kip, &c->pages, list) {
-		long idx = ((long)slot - (long)kip->insns) /
-				(c->insn_size * sizeof(kprobe_opcode_t));
-		if (idx >= 0 && idx < slots_per_page(c)) {
-			WARN_ON(kip->slot_used[idx] != SLOT_USED);
-			if (dirty) {
-				kip->slot_used[idx] = SLOT_DIRTY;
-				kip->ngarbage++;
-				if (++c->nr_garbage > slots_per_page(c))
-					collect_garbage_slots(c);
-			} else
-				collect_one_slot(kip, idx);
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		idx = ((long)slot - (long)kip->insns) /
+			(c->insn_size * sizeof(kprobe_opcode_t));
+		if (idx >= 0 && idx < slots_per_page(c))
 			goto out;
-		}
 	}
-	/* Could not free this slot. */
+	/* Could not find this slot. */
 	WARN_ON(1);
+	kip = NULL;
 out:
+	rcu_read_unlock();
+	/* Mark and sweep: this may sleep */
+	if (kip) {
+		/* Check double free */
+		WARN_ON(kip->slot_used[idx] != SLOT_USED);
+		if (dirty) {
+			kip->slot_used[idx] = SLOT_DIRTY;
+			kip->ngarbage++;
+			if (++c->nr_garbage > slots_per_page(c))
+				collect_garbage_slots(c);
+		} else {
+			collect_one_slot(kip, idx);
+		}
+	}
 	mutex_unlock(&c->mutex);
 }
 
+/*
+ * Check given address is on the page of kprobe instruction slots.
+ * This will be used for checking whether the address on a stack
+ * is on a text area or not.
+ */
+bool __is_insn_slot_addr(struct kprobe_insn_cache *c, unsigned long addr)
+{
+	struct kprobe_insn_page *kip;
+	bool ret = false;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kip, &c->pages, list) {
+		if (addr >= (unsigned long)kip->insns &&
+		    addr < (unsigned long)kip->insns + PAGE_SIZE) {
+			ret = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 #ifdef CONFIG_OPTPROBES
 /* For optimized_kprobe buffer */
 struct kprobe_insn_cache kprobe_optinsn_slots = {
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 2318fba86277..8461a4372e8a 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -850,7 +850,6 @@ void __kthread_queue_delayed_work(struct kthread_worker *worker,
 
 	list_add(&work->node, &worker->delayed_work_list);
 	work->worker = worker;
-	timer_stats_timer_set_start_info(&dwork->timer);
 	timer->expires = jiffies + delay;
 	add_timer(timer);
 }
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 6f88e352cd4f..760158d9d98d 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -28,3 +28,4 @@ obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
 obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
 obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
+obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 7c38f8f3d97b..9812e5dd409e 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2203,7 +2203,7 @@ cache_hit:
 	 * Important for check_no_collision().
 	 */
 	if (unlikely(nr_chain_hlocks > MAX_LOCKDEP_CHAIN_HLOCKS)) {
-		if (debug_locks_off_graph_unlock())
+		if (!debug_locks_off_graph_unlock())
 			return 0;
 
 		print_lockdep_off("BUG: MAX_LOCKDEP_CHAIN_HLOCKS too low!");
@@ -4412,13 +4412,13 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s)
 #endif /* #ifdef CONFIG_PROVE_RCU_REPEATEDLY */
 	/* Note: the following can be executed concurrently, so be careful. */
 	printk("\n");
-	printk("===============================\n");
-	printk("[ INFO: suspicious RCU usage. ]\n");
+	pr_err("===============================\n");
+	pr_err("[ ERR: suspicious RCU usage.  ]\n");
 	print_kernel_ident();
-	printk("-------------------------------\n");
-	printk("%s:%d %s!\n", file, line, s);
-	printk("\nother info that might help us debug this:\n\n");
-	printk("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
+	pr_err("-------------------------------\n");
+	pr_err("%s:%d %s!\n", file, line, s);
+	pr_err("\nother info that might help us debug this:\n\n");
+	pr_err("\n%srcu_scheduler_active = %d, debug_locks = %d\n",
 	       !rcu_lockdep_current_cpu_online()
 			? "RCU used illegally from offline CPU!\n"
 			: !rcu_is_watching()
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index f8c5af52a131..28350dc8ecbb 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -372,6 +372,78 @@ static struct lock_torture_ops mutex_lock_ops = {
 	.name		= "mutex_lock"
 };
 
+#include <linux/ww_mutex.h>
+static DEFINE_WW_CLASS(torture_ww_class);
+static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class);
+static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class);
+static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class);
+
+static int torture_ww_mutex_lock(void)
+__acquires(torture_ww_mutex_0)
+__acquires(torture_ww_mutex_1)
+__acquires(torture_ww_mutex_2)
+{
+	LIST_HEAD(list);
+	struct reorder_lock {
+		struct list_head link;
+		struct ww_mutex *lock;
+	} locks[3], *ll, *ln;
+	struct ww_acquire_ctx ctx;
+
+	locks[0].lock = &torture_ww_mutex_0;
+	list_add(&locks[0].link, &list);
+
+	locks[1].lock = &torture_ww_mutex_1;
+	list_add(&locks[1].link, &list);
+
+	locks[2].lock = &torture_ww_mutex_2;
+	list_add(&locks[2].link, &list);
+
+	ww_acquire_init(&ctx, &torture_ww_class);
+
+	list_for_each_entry(ll, &list, link) {
+		int err;
+
+		err = ww_mutex_lock(ll->lock, &ctx);
+		if (!err)
+			continue;
+
+		ln = ll;
+		list_for_each_entry_continue_reverse(ln, &list, link)
+			ww_mutex_unlock(ln->lock);
+
+		if (err != -EDEADLK)
+			return err;
+
+		ww_mutex_lock_slow(ll->lock, &ctx);
+		list_move(&ll->link, &list);
+	}
+
+	ww_acquire_fini(&ctx);
+	return 0;
+}
+
+static void torture_ww_mutex_unlock(void)
+__releases(torture_ww_mutex_0)
+__releases(torture_ww_mutex_1)
+__releases(torture_ww_mutex_2)
+{
+	ww_mutex_unlock(&torture_ww_mutex_0);
+	ww_mutex_unlock(&torture_ww_mutex_1);
+	ww_mutex_unlock(&torture_ww_mutex_2);
+}
+
+static struct lock_torture_ops ww_mutex_lock_ops = {
+	.writelock	= torture_ww_mutex_lock,
+	.write_delay	= torture_mutex_delay,
+	.task_boost     = torture_boost_dummy,
+	.writeunlock	= torture_ww_mutex_unlock,
+	.readlock       = NULL,
+	.read_delay     = NULL,
+	.readunlock     = NULL,
+	.name		= "ww_mutex_lock"
+};
+
 #ifdef CONFIG_RT_MUTEXES
 static DEFINE_RT_MUTEX(torture_rtmutex);
 
@@ -780,6 +852,10 @@ static void lock_torture_cleanup(void)
 	else
 		lock_torture_print_module_parms(cxt.cur_ops,
 						"End of test: SUCCESS");
+
+	kfree(cxt.lwsa);
+	kfree(cxt.lrsa);
+
 end:
 	torture_cleanup_end();
 }
@@ -793,6 +869,7 @@ static int __init lock_torture_init(void)
 		&spin_lock_ops, &spin_lock_irq_ops,
 		&rw_lock_ops, &rw_lock_irq_ops,
 		&mutex_lock_ops,
+		&ww_mutex_lock_ops,
 #ifdef CONFIG_RT_MUTEXES
 		&rtmutex_lock_ops,
 #endif
@@ -924,6 +1001,8 @@ static int __init lock_torture_init(void)
 				       GFP_KERNEL);
 		if (reader_tasks == NULL) {
 			VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory");
+			kfree(writer_tasks);
+			writer_tasks = NULL;
 			firsterr = -ENOMEM;
 			goto unwind;
 		}
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index a459faa48987..4174417d5309 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -26,20 +26,3 @@ extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 extern void debug_mutex_unlock(struct mutex *lock);
 extern void debug_mutex_init(struct mutex *lock, const char *name,
 			     struct lock_class_key *key);
-
-#define spin_lock_mutex(lock, flags)			\
-	do {						\
-		struct mutex *l = container_of(lock, struct mutex, wait_lock); \
-							\
-		DEBUG_LOCKS_WARN_ON(in_interrupt());	\
-		local_irq_save(flags);			\
-		arch_spin_lock(&(lock)->rlock.raw_lock);\
-		DEBUG_LOCKS_WARN_ON(l->magic != l);	\
-	} while (0)
-
-#define spin_unlock_mutex(lock, flags)				\
-	do {							\
-		arch_spin_unlock(&(lock)->rlock.raw_lock);	\
-		local_irq_restore(flags);			\
-		preempt_check_resched();			\
-	} while (0)
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 9b349619f431..ad2d9e22697b 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -50,16 +50,17 @@ EXPORT_SYMBOL(__mutex_init);
 /*
  * @owner: contains: 'struct task_struct *' to the current lock owner,
  * NULL means not owned. Since task_struct pointers are aligned at
- * ARCH_MIN_TASKALIGN (which is at least sizeof(void *)), we have low
- * bits to store extra state.
+ * at least L1_CACHE_BYTES, we have low bits to store extra state.
  *
  * Bit0 indicates a non-empty waiter list; unlock must issue a wakeup.
  * Bit1 indicates unlock needs to hand the lock to the top-waiter
+ * Bit2 indicates handoff has been done and we're waiting for pickup.
  */
 #define MUTEX_FLAG_WAITERS	0x01
 #define MUTEX_FLAG_HANDOFF	0x02
+#define MUTEX_FLAG_PICKUP	0x04
 
-#define MUTEX_FLAGS		0x03
+#define MUTEX_FLAGS		0x07
 
 static inline struct task_struct *__owner_task(unsigned long owner)
 {
@@ -72,38 +73,29 @@ static inline unsigned long __owner_flags(unsigned long owner)
 }
 
 /*
- * Actual trylock that will work on any unlocked state.
- *
- * When setting the owner field, we must preserve the low flag bits.
- *
- * Be careful with @handoff, only set that in a wait-loop (where you set
- * HANDOFF) to avoid recursive lock attempts.
+ * Trylock variant that retuns the owning task on failure.
  */
-static inline bool __mutex_trylock(struct mutex *lock, const bool handoff)
+static inline struct task_struct *__mutex_trylock_or_owner(struct mutex *lock)
 {
 	unsigned long owner, curr = (unsigned long)current;
 
 	owner = atomic_long_read(&lock->owner);
 	for (;;) { /* must loop, can race against a flag */
 		unsigned long old, flags = __owner_flags(owner);
+		unsigned long task = owner & ~MUTEX_FLAGS;
 
-		if (__owner_task(owner)) {
-			if (handoff && unlikely(__owner_task(owner) == current)) {
-				/*
-				 * Provide ACQUIRE semantics for the lock-handoff.
-				 *
-				 * We cannot easily use load-acquire here, since
-				 * the actual load is a failed cmpxchg, which
-				 * doesn't imply any barriers.
-				 *
-				 * Also, this is a fairly unlikely scenario, and
-				 * this contains the cost.
-				 */
-				smp_mb(); /* ACQUIRE */
-				return true;
-			}
+		if (task) {
+			if (likely(task != curr))
+				break;
 
-			return false;
+			if (likely(!(flags & MUTEX_FLAG_PICKUP)))
+				break;
+
+			flags &= ~MUTEX_FLAG_PICKUP;
+		} else {
+#ifdef CONFIG_DEBUG_MUTEXES
+			DEBUG_LOCKS_WARN_ON(flags & MUTEX_FLAG_PICKUP);
+#endif
 		}
 
 		/*
@@ -111,15 +103,24 @@ static inline bool __mutex_trylock(struct mutex *lock, const bool handoff)
 		 * past the point where we acquire it. This would be possible
 		 * if we (accidentally) set the bit on an unlocked mutex.
 		 */
-		if (handoff)
-			flags &= ~MUTEX_FLAG_HANDOFF;
+		flags &= ~MUTEX_FLAG_HANDOFF;
 
 		old = atomic_long_cmpxchg_acquire(&lock->owner, owner, curr | flags);
 		if (old == owner)
-			return true;
+			return NULL;
 
 		owner = old;
 	}
+
+	return __owner_task(owner);
+}
+
+/*
+ * Actual trylock that will work on any unlocked state.
+ */
+static inline bool __mutex_trylock(struct mutex *lock)
+{
+	return !__mutex_trylock_or_owner(lock);
 }
 
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
@@ -171,9 +172,9 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait
 
 /*
  * Give up ownership to a specific task, when @task = NULL, this is equivalent
- * to a regular unlock. Clears HANDOFF, preserves WAITERS. Provides RELEASE
- * semantics like a regular unlock, the __mutex_trylock() provides matching
- * ACQUIRE semantics for the handoff.
+ * to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves
+ * WAITERS. Provides RELEASE semantics like a regular unlock, the
+ * __mutex_trylock() provides a matching ACQUIRE semantics for the handoff.
  */
 static void __mutex_handoff(struct mutex *lock, struct task_struct *task)
 {
@@ -184,10 +185,13 @@ static void __mutex_handoff(struct mutex *lock, struct task_struct *task)
 
 #ifdef CONFIG_DEBUG_MUTEXES
 		DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current);
+		DEBUG_LOCKS_WARN_ON(owner & MUTEX_FLAG_PICKUP);
 #endif
 
 		new = (owner & MUTEX_FLAG_WAITERS);
 		new |= (unsigned long)task;
+		if (task)
+			new |= MUTEX_FLAG_PICKUP;
 
 		old = atomic_long_cmpxchg_release(&lock->owner, owner, new);
 		if (old == owner)
@@ -237,8 +241,8 @@ void __sched mutex_lock(struct mutex *lock)
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
-static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
-						   struct ww_acquire_ctx *ww_ctx)
+static __always_inline void
+ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
 {
 #ifdef CONFIG_DEBUG_MUTEXES
 	/*
@@ -277,17 +281,50 @@ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
 	ww_ctx->acquired++;
 }
 
+static inline bool __sched
+__ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b)
+{
+	return a->stamp - b->stamp <= LONG_MAX &&
+	       (a->stamp != b->stamp || a > b);
+}
+
+/*
+ * Wake up any waiters that may have to back off when the lock is held by the
+ * given context.
+ *
+ * Due to the invariants on the wait list, this can only affect the first
+ * waiter with a context.
+ *
+ * The current task must not be on the wait list.
+ */
+static void __sched
+__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
+{
+	struct mutex_waiter *cur;
+
+	lockdep_assert_held(&lock->wait_lock);
+
+	list_for_each_entry(cur, &lock->wait_list, list) {
+		if (!cur->ww_ctx)
+			continue;
+
+		if (cur->ww_ctx->acquired > 0 &&
+		    __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) {
+			debug_mutex_wake_waiter(lock, cur);
+			wake_up_process(cur->task);
+		}
+
+		break;
+	}
+}
+
 /*
  * After acquiring lock with fastpath or when we lost out in contested
  * slowpath, set ctx and wake up any waiters so they can recheck.
  */
 static __always_inline void
-ww_mutex_set_context_fastpath(struct ww_mutex *lock,
-			       struct ww_acquire_ctx *ctx)
+ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
-	unsigned long flags;
-	struct mutex_waiter *cur;
-
 	ww_mutex_lock_acquired(lock, ctx);
 
 	lock->ctx = ctx;
@@ -311,46 +348,79 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock,
 	 * Uh oh, we raced in fastpath, wake up everyone in this case,
 	 * so they can see the new lock->ctx.
 	 */
-	spin_lock_mutex(&lock->base.wait_lock, flags);
-	list_for_each_entry(cur, &lock->base.wait_list, list) {
-		debug_mutex_wake_waiter(&lock->base, cur);
-		wake_up_process(cur->task);
-	}
-	spin_unlock_mutex(&lock->base.wait_lock, flags);
+	spin_lock(&lock->base.wait_lock);
+	__ww_mutex_wakeup_for_backoff(&lock->base, ctx);
+	spin_unlock(&lock->base.wait_lock);
 }
 
 /*
- * After acquiring lock in the slowpath set ctx and wake up any
- * waiters so they can recheck.
+ * After acquiring lock in the slowpath set ctx.
+ *
+ * Unlike for the fast path, the caller ensures that waiters are woken up where
+ * necessary.
  *
  * Callers must hold the mutex wait_lock.
  */
 static __always_inline void
-ww_mutex_set_context_slowpath(struct ww_mutex *lock,
-			      struct ww_acquire_ctx *ctx)
+ww_mutex_set_context_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
-	struct mutex_waiter *cur;
-
 	ww_mutex_lock_acquired(lock, ctx);
 	lock->ctx = ctx;
+}
+
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+
+static inline
+bool ww_mutex_spin_on_owner(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
+			    struct mutex_waiter *waiter)
+{
+	struct ww_mutex *ww;
+
+	ww = container_of(lock, struct ww_mutex, base);
 
 	/*
-	 * Give any possible sleeping processes the chance to wake up,
-	 * so they can recheck if they have to back off.
+	 * If ww->ctx is set the contents are undefined, only
+	 * by acquiring wait_lock there is a guarantee that
+	 * they are not invalid when reading.
+	 *
+	 * As such, when deadlock detection needs to be
+	 * performed the optimistic spinning cannot be done.
+	 *
+	 * Check this in every inner iteration because we may
+	 * be racing against another thread's ww_mutex_lock.
 	 */
-	list_for_each_entry(cur, &lock->base.wait_list, list) {
-		debug_mutex_wake_waiter(&lock->base, cur);
-		wake_up_process(cur->task);
-	}
+	if (ww_ctx->acquired > 0 && READ_ONCE(ww->ctx))
+		return false;
+
+	/*
+	 * If we aren't on the wait list yet, cancel the spin
+	 * if there are waiters. We want  to avoid stealing the
+	 * lock from a waiter with an earlier stamp, since the
+	 * other thread may already own a lock that we also
+	 * need.
+	 */
+	if (!waiter && (atomic_long_read(&lock->owner) & MUTEX_FLAG_WAITERS))
+		return false;
+
+	/*
+	 * Similarly, stop spinning if we are no longer the
+	 * first waiter.
+	 */
+	if (waiter && !__mutex_waiter_is_first(lock, waiter))
+		return false;
+
+	return true;
 }
 
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 /*
- * Look out! "owner" is an entirely speculative pointer
- * access and not reliable.
+ * Look out! "owner" is an entirely speculative pointer access and not
+ * reliable.
+ *
+ * "noinline" so that this function shows up on perf profiles.
  */
 static noinline
-bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
+bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner,
+			 struct ww_acquire_ctx *ww_ctx, struct mutex_waiter *waiter)
 {
 	bool ret = true;
 
@@ -373,6 +443,11 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 			break;
 		}
 
+		if (ww_ctx && !ww_mutex_spin_on_owner(lock, ww_ctx, waiter)) {
+			ret = false;
+			break;
+		}
+
 		cpu_relax();
 	}
 	rcu_read_unlock();
@@ -431,12 +506,10 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
  * with the spinner at the head of the OSQ, if present, until the owner is
  * changed to itself.
  */
-static bool mutex_optimistic_spin(struct mutex *lock,
-				  struct ww_acquire_ctx *ww_ctx,
-				  const bool use_ww_ctx, const bool waiter)
+static __always_inline bool
+mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
+		      const bool use_ww_ctx, struct mutex_waiter *waiter)
 {
-	struct task_struct *task = current;
-
 	if (!waiter) {
 		/*
 		 * The purpose of the mutex_can_spin_on_owner() function is
@@ -460,40 +533,17 @@ static bool mutex_optimistic_spin(struct mutex *lock,
 	for (;;) {
 		struct task_struct *owner;
 
-		if (use_ww_ctx && ww_ctx->acquired > 0) {
-			struct ww_mutex *ww;
-
-			ww = container_of(lock, struct ww_mutex, base);
-			/*
-			 * If ww->ctx is set the contents are undefined, only
-			 * by acquiring wait_lock there is a guarantee that
-			 * they are not invalid when reading.
-			 *
-			 * As such, when deadlock detection needs to be
-			 * performed the optimistic spinning cannot be done.
-			 */
-			if (READ_ONCE(ww->ctx))
-				goto fail_unlock;
-		}
+		/* Try to acquire the mutex... */
+		owner = __mutex_trylock_or_owner(lock);
+		if (!owner)
+			break;
 
 		/*
-		 * If there's an owner, wait for it to either
+		 * There's an owner, wait for it to either
 		 * release the lock or go to sleep.
 		 */
-		owner = __mutex_owner(lock);
-		if (owner) {
-			if (waiter && owner == task) {
-				smp_mb(); /* ACQUIRE */
-				break;
-			}
-
-			if (!mutex_spin_on_owner(lock, owner))
-				goto fail_unlock;
-		}
-
-		/* Try to acquire the mutex if it is unlocked. */
-		if (__mutex_trylock(lock, waiter))
-			break;
+		if (!mutex_spin_on_owner(lock, owner, ww_ctx, waiter))
+			goto fail_unlock;
 
 		/*
 		 * The cpu_relax() call is a compiler barrier which forces
@@ -532,9 +582,9 @@ fail:
 	return false;
 }
 #else
-static bool mutex_optimistic_spin(struct mutex *lock,
-				  struct ww_acquire_ctx *ww_ctx,
-				  const bool use_ww_ctx, const bool waiter)
+static __always_inline bool
+mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
+		      const bool use_ww_ctx, struct mutex_waiter *waiter)
 {
 	return false;
 }
@@ -594,23 +644,88 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock)
 EXPORT_SYMBOL(ww_mutex_unlock);
 
 static inline int __sched
-__ww_mutex_lock_check_stamp(struct mutex *lock, struct ww_acquire_ctx *ctx)
+__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter,
+			    struct ww_acquire_ctx *ctx)
 {
 	struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
 	struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx);
+	struct mutex_waiter *cur;
+
+	if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx))
+		goto deadlock;
+
+	/*
+	 * If there is a waiter in front of us that has a context, then its
+	 * stamp is earlier than ours and we must back off.
+	 */
+	cur = waiter;
+	list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) {
+		if (cur->ww_ctx)
+			goto deadlock;
+	}
+
+	return 0;
 
-	if (!hold_ctx)
+deadlock:
+#ifdef CONFIG_DEBUG_MUTEXES
+	DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
+	ctx->contending_lock = ww;
+#endif
+	return -EDEADLK;
+}
+
+static inline int __sched
+__ww_mutex_add_waiter(struct mutex_waiter *waiter,
+		      struct mutex *lock,
+		      struct ww_acquire_ctx *ww_ctx)
+{
+	struct mutex_waiter *cur;
+	struct list_head *pos;
+
+	if (!ww_ctx) {
+		list_add_tail(&waiter->list, &lock->wait_list);
 		return 0;
+	}
 
-	if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
-	    (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
+	/*
+	 * Add the waiter before the first waiter with a higher stamp.
+	 * Waiters without a context are skipped to avoid starving
+	 * them.
+	 */
+	pos = &lock->wait_list;
+	list_for_each_entry_reverse(cur, &lock->wait_list, list) {
+		if (!cur->ww_ctx)
+			continue;
+
+		if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) {
+			/* Back off immediately if necessary. */
+			if (ww_ctx->acquired > 0) {
 #ifdef CONFIG_DEBUG_MUTEXES
-		DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
-		ctx->contending_lock = ww;
+				struct ww_mutex *ww;
+
+				ww = container_of(lock, struct ww_mutex, base);
+				DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
+				ww_ctx->contending_lock = ww;
 #endif
-		return -EDEADLK;
+				return -EDEADLK;
+			}
+
+			break;
+		}
+
+		pos = &cur->list;
+
+		/*
+		 * Wake up the waiter so that it gets a chance to back
+		 * off.
+		 */
+		if (cur->ww_ctx->acquired > 0) {
+			debug_mutex_wake_waiter(lock, cur);
+			wake_up_process(cur->task);
+		}
 	}
 
+	list_add_tail(&waiter->list, pos);
 	return 0;
 }
 
@@ -622,15 +737,15 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		    struct lockdep_map *nest_lock, unsigned long ip,
 		    struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
 {
-	struct task_struct *task = current;
 	struct mutex_waiter waiter;
-	unsigned long flags;
 	bool first = false;
 	struct ww_mutex *ww;
 	int ret;
 
-	if (use_ww_ctx) {
-		ww = container_of(lock, struct ww_mutex, base);
+	might_sleep();
+
+	ww = container_of(lock, struct ww_mutex, base);
+	if (use_ww_ctx && ww_ctx) {
 		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
 			return -EALREADY;
 	}
@@ -638,36 +753,54 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	preempt_disable();
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
-	if (__mutex_trylock(lock, false) ||
-	    mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, false)) {
+	if (__mutex_trylock(lock) ||
+	    mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, NULL)) {
 		/* got the lock, yay! */
 		lock_acquired(&lock->dep_map, ip);
-		if (use_ww_ctx)
+		if (use_ww_ctx && ww_ctx)
 			ww_mutex_set_context_fastpath(ww, ww_ctx);
 		preempt_enable();
 		return 0;
 	}
 
-	spin_lock_mutex(&lock->wait_lock, flags);
+	spin_lock(&lock->wait_lock);
 	/*
 	 * After waiting to acquire the wait_lock, try again.
 	 */
-	if (__mutex_trylock(lock, false))
+	if (__mutex_trylock(lock)) {
+		if (use_ww_ctx && ww_ctx)
+			__ww_mutex_wakeup_for_backoff(lock, ww_ctx);
+
 		goto skip_wait;
+	}
 
 	debug_mutex_lock_common(lock, &waiter);
-	debug_mutex_add_waiter(lock, &waiter, task);
+	debug_mutex_add_waiter(lock, &waiter, current);
+
+	lock_contended(&lock->dep_map, ip);
 
-	/* add waiting tasks to the end of the waitqueue (FIFO): */
-	list_add_tail(&waiter.list, &lock->wait_list);
-	waiter.task = task;
+	if (!use_ww_ctx) {
+		/* add waiting tasks to the end of the waitqueue (FIFO): */
+		list_add_tail(&waiter.list, &lock->wait_list);
+
+#ifdef CONFIG_DEBUG_MUTEXES
+		waiter.ww_ctx = MUTEX_POISON_WW_CTX;
+#endif
+	} else {
+		/* Add in stamp order, waking up waiters that must back off. */
+		ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx);
+		if (ret)
+			goto err_early_backoff;
+
+		waiter.ww_ctx = ww_ctx;
+	}
+
+	waiter.task = current;
 
 	if (__mutex_waiter_is_first(lock, &waiter))
 		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
 
-	lock_contended(&lock->dep_map, ip);
-
-	set_task_state(task, state);
+	set_current_state(state);
 	for (;;) {
 		/*
 		 * Once we hold wait_lock, we're serialized against
@@ -675,7 +808,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * before testing the error conditions to make sure we pick up
 		 * the handoff.
 		 */
-		if (__mutex_trylock(lock, first))
+		if (__mutex_trylock(lock))
 			goto acquired;
 
 		/*
@@ -683,42 +816,47 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 * wait_lock. This ensures the lock cancellation is ordered
 		 * against mutex_unlock() and wake-ups do not go missing.
 		 */
-		if (unlikely(signal_pending_state(state, task))) {
+		if (unlikely(signal_pending_state(state, current))) {
 			ret = -EINTR;
 			goto err;
 		}
 
-		if (use_ww_ctx && ww_ctx->acquired > 0) {
-			ret = __ww_mutex_lock_check_stamp(lock, ww_ctx);
+		if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) {
+			ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx);
 			if (ret)
 				goto err;
 		}
 
-		spin_unlock_mutex(&lock->wait_lock, flags);
+		spin_unlock(&lock->wait_lock);
 		schedule_preempt_disabled();
 
-		if (!first && __mutex_waiter_is_first(lock, &waiter)) {
-			first = true;
-			__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
+		/*
+		 * ww_mutex needs to always recheck its position since its waiter
+		 * list is not FIFO ordered.
+		 */
+		if ((use_ww_ctx && ww_ctx) || !first) {
+			first = __mutex_waiter_is_first(lock, &waiter);
+			if (first)
+				__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
 		}
 
-		set_task_state(task, state);
+		set_current_state(state);
 		/*
 		 * Here we order against unlock; we must either see it change
 		 * state back to RUNNING and fall through the next schedule(),
 		 * or we must see its unlock and acquire.
 		 */
-		if ((first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, true)) ||
-		     __mutex_trylock(lock, first))
+		if (__mutex_trylock(lock) ||
+		    (first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, &waiter)))
 			break;
 
-		spin_lock_mutex(&lock->wait_lock, flags);
+		spin_lock(&lock->wait_lock);
 	}
-	spin_lock_mutex(&lock->wait_lock, flags);
+	spin_lock(&lock->wait_lock);
 acquired:
-	__set_task_state(task, TASK_RUNNING);
+	__set_current_state(TASK_RUNNING);
 
-	mutex_remove_waiter(lock, &waiter, task);
+	mutex_remove_waiter(lock, &waiter, current);
 	if (likely(list_empty(&lock->wait_list)))
 		__mutex_clear_flag(lock, MUTEX_FLAGS);
 
@@ -728,30 +866,44 @@ skip_wait:
 	/* got the lock - cleanup and rejoice! */
 	lock_acquired(&lock->dep_map, ip);
 
-	if (use_ww_ctx)
+	if (use_ww_ctx && ww_ctx)
 		ww_mutex_set_context_slowpath(ww, ww_ctx);
 
-	spin_unlock_mutex(&lock->wait_lock, flags);
+	spin_unlock(&lock->wait_lock);
 	preempt_enable();
 	return 0;
 
 err:
-	__set_task_state(task, TASK_RUNNING);
-	mutex_remove_waiter(lock, &waiter, task);
-	spin_unlock_mutex(&lock->wait_lock, flags);
+	__set_current_state(TASK_RUNNING);
+	mutex_remove_waiter(lock, &waiter, current);
+err_early_backoff:
+	spin_unlock(&lock->wait_lock);
 	debug_mutex_free_waiter(&waiter);
 	mutex_release(&lock->dep_map, 1, ip);
 	preempt_enable();
 	return ret;
 }
 
+static int __sched
+__mutex_lock(struct mutex *lock, long state, unsigned int subclass,
+	     struct lockdep_map *nest_lock, unsigned long ip)
+{
+	return __mutex_lock_common(lock, state, subclass, nest_lock, ip, NULL, false);
+}
+
+static int __sched
+__ww_mutex_lock(struct mutex *lock, long state, unsigned int subclass,
+		struct lockdep_map *nest_lock, unsigned long ip,
+		struct ww_acquire_ctx *ww_ctx)
+{
+	return __mutex_lock_common(lock, state, subclass, nest_lock, ip, ww_ctx, true);
+}
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 void __sched
 mutex_lock_nested(struct mutex *lock, unsigned int subclass)
 {
-	might_sleep();
-	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
-			    subclass, NULL, _RET_IP_, NULL, 0);
+	__mutex_lock(lock, TASK_UNINTERRUPTIBLE, subclass, NULL, _RET_IP_);
 }
 
 EXPORT_SYMBOL_GPL(mutex_lock_nested);
@@ -759,30 +911,38 @@ EXPORT_SYMBOL_GPL(mutex_lock_nested);
 void __sched
 _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
 {
-	might_sleep();
-	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
-			    0, nest, _RET_IP_, NULL, 0);
+	__mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_);
 }
 EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
 
 int __sched
 mutex_lock_killable_nested(struct mutex *lock, unsigned int subclass)
 {
-	might_sleep();
-	return __mutex_lock_common(lock, TASK_KILLABLE,
-				   subclass, NULL, _RET_IP_, NULL, 0);
+	return __mutex_lock(lock, TASK_KILLABLE, subclass, NULL, _RET_IP_);
 }
 EXPORT_SYMBOL_GPL(mutex_lock_killable_nested);
 
 int __sched
 mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
 {
-	might_sleep();
-	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
-				   subclass, NULL, _RET_IP_, NULL, 0);
+	return __mutex_lock(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_);
 }
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
 
+void __sched
+mutex_lock_io_nested(struct mutex *lock, unsigned int subclass)
+{
+	int token;
+
+	might_sleep();
+
+	token = io_schedule_prepare();
+	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
+			    subclass, NULL, _RET_IP_, NULL, 0);
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_io_nested);
+
 static inline int
 ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
@@ -810,35 +970,37 @@ ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 }
 
 int __sched
-__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
 	int ret;
 
 	might_sleep();
-	ret =  __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE,
-				   0, &ctx->dep_map, _RET_IP_, ctx, 1);
-	if (!ret && ctx->acquired > 1)
+	ret =  __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE,
+			       0, ctx ? &ctx->dep_map : NULL, _RET_IP_,
+			       ctx);
+	if (!ret && ctx && ctx->acquired > 1)
 		return ww_mutex_deadlock_injection(lock, ctx);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__ww_mutex_lock);
+EXPORT_SYMBOL_GPL(ww_mutex_lock);
 
 int __sched
-__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
 	int ret;
 
 	might_sleep();
-	ret = __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE,
-				  0, &ctx->dep_map, _RET_IP_, ctx, 1);
+	ret = __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE,
+			      0, ctx ? &ctx->dep_map : NULL, _RET_IP_,
+			      ctx);
 
-	if (!ret && ctx->acquired > 1)
+	if (!ret && ctx && ctx->acquired > 1)
 		return ww_mutex_deadlock_injection(lock, ctx);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
+EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible);
 
 #endif
 
@@ -848,8 +1010,8 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
 static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip)
 {
 	struct task_struct *next = NULL;
-	unsigned long owner, flags;
 	DEFINE_WAKE_Q(wake_q);
+	unsigned long owner;
 
 	mutex_release(&lock->dep_map, 1, ip);
 
@@ -866,6 +1028,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 
 #ifdef CONFIG_DEBUG_MUTEXES
 		DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current);
+		DEBUG_LOCKS_WARN_ON(owner & MUTEX_FLAG_PICKUP);
 #endif
 
 		if (owner & MUTEX_FLAG_HANDOFF)
@@ -883,7 +1046,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		owner = old;
 	}
 
-	spin_lock_mutex(&lock->wait_lock, flags);
+	spin_lock(&lock->wait_lock);
 	debug_mutex_unlock(lock);
 	if (!list_empty(&lock->wait_list)) {
 		/* get the first entry from the wait-list: */
@@ -900,7 +1063,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 	if (owner & MUTEX_FLAG_HANDOFF)
 		__mutex_handoff(lock, next);
 
-	spin_unlock_mutex(&lock->wait_lock, flags);
+	spin_unlock(&lock->wait_lock);
 
 	wake_up_q(&wake_q);
 }
@@ -950,40 +1113,47 @@ int __sched mutex_lock_killable(struct mutex *lock)
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
+void __sched mutex_lock_io(struct mutex *lock)
+{
+	int token;
+
+	token = io_schedule_prepare();
+	mutex_lock(lock);
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(mutex_lock_io);
+
 static noinline void __sched
 __mutex_lock_slowpath(struct mutex *lock)
 {
-	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0,
-			    NULL, _RET_IP_, NULL, 0);
+	__mutex_lock(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_);
 }
 
 static noinline int __sched
 __mutex_lock_killable_slowpath(struct mutex *lock)
 {
-	return __mutex_lock_common(lock, TASK_KILLABLE, 0,
-				   NULL, _RET_IP_, NULL, 0);
+	return __mutex_lock(lock, TASK_KILLABLE, 0, NULL, _RET_IP_);
 }
 
 static noinline int __sched
 __mutex_lock_interruptible_slowpath(struct mutex *lock)
 {
-	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0,
-				   NULL, _RET_IP_, NULL, 0);
+	return __mutex_lock(lock, TASK_INTERRUPTIBLE, 0, NULL, _RET_IP_);
 }
 
 static noinline int __sched
 __ww_mutex_lock_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
-	return __mutex_lock_common(&lock->base, TASK_UNINTERRUPTIBLE, 0,
-				   NULL, _RET_IP_, ctx, 1);
+	return __ww_mutex_lock(&lock->base, TASK_UNINTERRUPTIBLE, 0, NULL,
+			       _RET_IP_, ctx);
 }
 
 static noinline int __sched
 __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
 					    struct ww_acquire_ctx *ctx)
 {
-	return __mutex_lock_common(&lock->base, TASK_INTERRUPTIBLE, 0,
-				   NULL, _RET_IP_, ctx, 1);
+	return __ww_mutex_lock(&lock->base, TASK_INTERRUPTIBLE, 0, NULL,
+			       _RET_IP_, ctx);
 }
 
 #endif
@@ -1004,7 +1174,7 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
  */
 int __sched mutex_trylock(struct mutex *lock)
 {
-	bool locked = __mutex_trylock(lock, false);
+	bool locked = __mutex_trylock(lock);
 
 	if (locked)
 		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
@@ -1015,32 +1185,34 @@ EXPORT_SYMBOL(mutex_trylock);
 
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
 int __sched
-__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
 	might_sleep();
 
 	if (__mutex_trylock_fast(&lock->base)) {
-		ww_mutex_set_context_fastpath(lock, ctx);
+		if (ctx)
+			ww_mutex_set_context_fastpath(lock, ctx);
 		return 0;
 	}
 
 	return __ww_mutex_lock_slowpath(lock, ctx);
 }
-EXPORT_SYMBOL(__ww_mutex_lock);
+EXPORT_SYMBOL(ww_mutex_lock);
 
 int __sched
-__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
 	might_sleep();
 
 	if (__mutex_trylock_fast(&lock->base)) {
-		ww_mutex_set_context_fastpath(lock, ctx);
+		if (ctx)
+			ww_mutex_set_context_fastpath(lock, ctx);
 		return 0;
 	}
 
 	return __ww_mutex_lock_interruptible_slowpath(lock, ctx);
 }
-EXPORT_SYMBOL(__ww_mutex_lock_interruptible);
+EXPORT_SYMBOL(ww_mutex_lock_interruptible);
 
 #endif
 
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 4410a4af42a3..6ebc1902f779 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -9,10 +9,6 @@
  * !CONFIG_DEBUG_MUTEXES case. Most of them are NOPs:
  */
 
-#define spin_lock_mutex(lock, flags) \
-		do { spin_lock(lock); (void)(flags); } while (0)
-#define spin_unlock_mutex(lock, flags) \
-		do { spin_unlock(lock); (void)(flags); } while (0)
 #define mutex_remove_waiter(lock, waiter, task) \
 		__list_del((waiter)->list.prev, (waiter)->list.next)
 
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index ce182599cf2e..883cf1b92d90 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -1,7 +1,6 @@
 #include <linux/atomic.h>
 #include <linux/rwsem.h>
 #include <linux/percpu.h>
-#include <linux/wait.h>
 #include <linux/lockdep.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/rcupdate.h>
@@ -18,7 +17,7 @@ int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
 	/* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
 	rcu_sync_init(&sem->rss, RCU_SCHED_SYNC);
 	__init_rwsem(&sem->rw_sem, name, rwsem_key);
-	init_waitqueue_head(&sem->writer);
+	rcuwait_init(&sem->writer);
 	sem->readers_block = 0;
 	return 0;
 }
@@ -103,7 +102,7 @@ void __percpu_up_read(struct percpu_rw_semaphore *sem)
 	__this_cpu_dec(*sem->read_count);
 
 	/* Prod writer to recheck readers_active */
-	wake_up(&sem->writer);
+	rcuwait_wake_up(&sem->writer);
 }
 EXPORT_SYMBOL_GPL(__percpu_up_read);
 
@@ -160,7 +159,7 @@ void percpu_down_write(struct percpu_rw_semaphore *sem)
 	 */
 
 	/* Wait for all now active readers to complete. */
-	wait_event(sem->writer, readers_active_check(sem));
+	rcuwait_wait_event(&sem->writer, readers_active_check(sem));
 }
 EXPORT_SYMBOL_GPL(percpu_down_write);
 
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index e3b5520005db..e6b2f7ad3e51 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -263,7 +263,7 @@ pv_wait_early(struct pv_node *prev, int loop)
 	if ((loop & PV_PREV_CHECK_MASK) != 0)
 		return false;
 
-	return READ_ONCE(prev->state) != vcpu_running;
+	return READ_ONCE(prev->state) != vcpu_running || vcpu_is_preempted(prev->cpu);
 }
 
 /*
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2f443ed2320a..d340be3a488f 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1179,7 +1179,7 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		 * TASK_INTERRUPTIBLE checks for signals and
 		 * timeout. Ignored otherwise.
 		 */
-		if (unlikely(state == TASK_INTERRUPTIBLE)) {
+		if (likely(state == TASK_INTERRUPTIBLE)) {
 			/* Signal pending? */
 			if (signal_pending(current))
 				ret = -EINTR;
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
index 1591f6b3539f..5eacab880f67 100644
--- a/kernel/locking/rwsem-spinlock.c
+++ b/kernel/locking/rwsem-spinlock.c
@@ -128,7 +128,6 @@ __rwsem_wake_one_writer(struct rw_semaphore *sem)
 void __sched __down_read(struct rw_semaphore *sem)
 {
 	struct rwsem_waiter waiter;
-	struct task_struct *tsk;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
@@ -140,13 +139,12 @@ void __sched __down_read(struct rw_semaphore *sem)
 		goto out;
 	}
 
-	tsk = current;
-	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	set_current_state(TASK_UNINTERRUPTIBLE);
 
 	/* set up my own style of waitqueue */
-	waiter.task = tsk;
+	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_READ;
-	get_task_struct(tsk);
+	get_task_struct(current);
 
 	list_add_tail(&waiter.list, &sem->wait_list);
 
@@ -158,10 +156,10 @@ void __sched __down_read(struct rw_semaphore *sem)
 		if (!waiter.task)
 			break;
 		schedule();
-		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE);
 	}
 
-	__set_task_state(tsk, TASK_RUNNING);
+	__set_current_state(TASK_RUNNING);
  out:
 	;
 }
@@ -194,15 +192,13 @@ int __down_read_trylock(struct rw_semaphore *sem)
 int __sched __down_write_common(struct rw_semaphore *sem, int state)
 {
 	struct rwsem_waiter waiter;
-	struct task_struct *tsk;
 	unsigned long flags;
 	int ret = 0;
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	/* set up my own style of waitqueue */
-	tsk = current;
-	waiter.task = tsk;
+	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_WRITE;
 	list_add_tail(&waiter.list, &sem->wait_list);
 
@@ -220,7 +216,7 @@ int __sched __down_write_common(struct rw_semaphore *sem, int state)
 			ret = -EINTR;
 			goto out;
 		}
-		set_task_state(tsk, state);
+		set_current_state(state);
 		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		schedule();
 		raw_spin_lock_irqsave(&sem->wait_lock, flags);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 631506004f9e..2ad8d8dc3bb1 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -224,10 +224,9 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 {
 	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
 	struct rwsem_waiter waiter;
-	struct task_struct *tsk = current;
 	DEFINE_WAKE_Q(wake_q);
 
-	waiter.task = tsk;
+	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_READ;
 
 	raw_spin_lock_irq(&sem->wait_lock);
@@ -254,13 +253,13 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 
 	/* wait to be given the lock */
 	while (true) {
-		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE);
 		if (!waiter.task)
 			break;
 		schedule();
 	}
 
-	__set_task_state(tsk, TASK_RUNNING);
+	__set_current_state(TASK_RUNNING);
 	return sem;
 }
 EXPORT_SYMBOL(rwsem_down_read_failed);
@@ -503,8 +502,6 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 		 * wake any read locks that were queued ahead of us.
 		 */
 		if (count > RWSEM_WAITING_BIAS) {
-			DEFINE_WAKE_Q(wake_q);
-
 			__rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q);
 			/*
 			 * The wakeup is normally called _after_ the wait_lock
@@ -514,6 +511,11 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 			 * for attempting rwsem_try_write_lock().
 			 */
 			wake_up_q(&wake_q);
+
+			/*
+			 * Reinitialize wake_q after use.
+			 */
+			wake_q_init(&wake_q);
 		}
 
 	} else
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index b8120abe594b..9512e37637dc 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -204,19 +204,18 @@ struct semaphore_waiter {
 static inline int __sched __down_common(struct semaphore *sem, long state,
 								long timeout)
 {
-	struct task_struct *task = current;
 	struct semaphore_waiter waiter;
 
 	list_add_tail(&waiter.list, &sem->wait_list);
-	waiter.task = task;
+	waiter.task = current;
 	waiter.up = false;
 
 	for (;;) {
-		if (signal_pending_state(state, task))
+		if (signal_pending_state(state, current))
 			goto interrupted;
 		if (unlikely(timeout <= 0))
 			goto timed_out;
-		__set_task_state(task, state);
+		__set_current_state(state);
 		raw_spin_unlock_irq(&sem->lock);
 		timeout = schedule_timeout(timeout);
 		raw_spin_lock_irq(&sem->lock);
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index db3ccb1dd614..4b082b5cac9e 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -363,14 +363,6 @@ void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
 }
 EXPORT_SYMBOL(_raw_spin_lock_nested);
 
-void __lockfunc _raw_spin_lock_bh_nested(raw_spinlock_t *lock, int subclass)
-{
-	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_LOCK_OFFSET);
-	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock);
-}
-EXPORT_SYMBOL(_raw_spin_lock_bh_nested);
-
 unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock,
 						   int subclass)
 {
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 0374a596cffa..9aa0fccd5d43 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -103,38 +103,14 @@ static inline void debug_spin_unlock(raw_spinlock_t *lock)
 	lock->owner_cpu = -1;
 }
 
-static void __spin_lock_debug(raw_spinlock_t *lock)
-{
-	u64 i;
-	u64 loops = loops_per_jiffy * HZ;
-
-	for (i = 0; i < loops; i++) {
-		if (arch_spin_trylock(&lock->raw_lock))
-			return;
-		__delay(1);
-	}
-	/* lockup suspected: */
-	spin_dump(lock, "lockup suspected");
-#ifdef CONFIG_SMP
-	trigger_all_cpu_backtrace();
-#endif
-
-	/*
-	 * The trylock above was causing a livelock.  Give the lower level arch
-	 * specific lock code a chance to acquire the lock. We have already
-	 * printed a warning/backtrace at this point. The non-debug arch
-	 * specific code might actually succeed in acquiring the lock.  If it is
-	 * not successful, the end-result is the same - there is no forward
-	 * progress.
-	 */
-	arch_spin_lock(&lock->raw_lock);
-}
-
+/*
+ * We are now relying on the NMI watchdog to detect lockup instead of doing
+ * the detection here with an unfair lock which can cause problem of its own.
+ */
 void do_raw_spin_lock(raw_spinlock_t *lock)
 {
 	debug_spin_lock_before(lock);
-	if (unlikely(!arch_spin_trylock(&lock->raw_lock)))
-		__spin_lock_debug(lock);
+	arch_spin_lock(&lock->raw_lock);
 	debug_spin_lock_after(lock);
 }
 
@@ -172,32 +148,6 @@ static void rwlock_bug(rwlock_t *lock, const char *msg)
 
 #define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg)
 
-#if 0		/* __write_lock_debug() can lock up - maybe this can too? */
-static void __read_lock_debug(rwlock_t *lock)
-{
-	u64 i;
-	u64 loops = loops_per_jiffy * HZ;
-	int print_once = 1;
-
-	for (;;) {
-		for (i = 0; i < loops; i++) {
-			if (arch_read_trylock(&lock->raw_lock))
-				return;
-			__delay(1);
-		}
-		/* lockup suspected: */
-		if (print_once) {
-			print_once = 0;
-			printk(KERN_EMERG "BUG: read-lock lockup on CPU#%d, "
-					"%s/%d, %p\n",
-				raw_smp_processor_id(), current->comm,
-				current->pid, lock);
-			dump_stack();
-		}
-	}
-}
-#endif
-
 void do_raw_read_lock(rwlock_t *lock)
 {
 	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
@@ -247,32 +197,6 @@ static inline void debug_write_unlock(rwlock_t *lock)
 	lock->owner_cpu = -1;
 }
 
-#if 0		/* This can cause lockups */
-static void __write_lock_debug(rwlock_t *lock)
-{
-	u64 i;
-	u64 loops = loops_per_jiffy * HZ;
-	int print_once = 1;
-
-	for (;;) {
-		for (i = 0; i < loops; i++) {
-			if (arch_write_trylock(&lock->raw_lock))
-				return;
-			__delay(1);
-		}
-		/* lockup suspected: */
-		if (print_once) {
-			print_once = 0;
-			printk(KERN_EMERG "BUG: write-lock lockup on CPU#%d, "
-					"%s/%d, %p\n",
-				raw_smp_processor_id(), current->comm,
-				current->pid, lock);
-			dump_stack();
-		}
-	}
-}
-#endif
-
 void do_raw_write_lock(rwlock_t *lock)
 {
 	debug_write_lock_before(lock);
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
new file mode 100644
index 000000000000..da6c9a34f62f
--- /dev/null
+++ b/kernel/locking/test-ww_mutex.c
@@ -0,0 +1,646 @@
+/*
+ * Module-based API test facility for ww_mutexes
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, you can access it online at
+ * http://www.gnu.org/licenses/gpl-2.0.html.
+ */
+
+#include <linux/kernel.h>
+
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/ww_mutex.h>
+
+static DEFINE_WW_CLASS(ww_class);
+struct workqueue_struct *wq;
+
+struct test_mutex {
+	struct work_struct work;
+	struct ww_mutex mutex;
+	struct completion ready, go, done;
+	unsigned int flags;
+};
+
+#define TEST_MTX_SPIN BIT(0)
+#define TEST_MTX_TRY BIT(1)
+#define TEST_MTX_CTX BIT(2)
+#define __TEST_MTX_LAST BIT(3)
+
+static void test_mutex_work(struct work_struct *work)
+{
+	struct test_mutex *mtx = container_of(work, typeof(*mtx), work);
+
+	complete(&mtx->ready);
+	wait_for_completion(&mtx->go);
+
+	if (mtx->flags & TEST_MTX_TRY) {
+		while (!ww_mutex_trylock(&mtx->mutex))
+			cpu_relax();
+	} else {
+		ww_mutex_lock(&mtx->mutex, NULL);
+	}
+	complete(&mtx->done);
+	ww_mutex_unlock(&mtx->mutex);
+}
+
+static int __test_mutex(unsigned int flags)
+{
+#define TIMEOUT (HZ / 16)
+	struct test_mutex mtx;
+	struct ww_acquire_ctx ctx;
+	int ret;
+
+	ww_mutex_init(&mtx.mutex, &ww_class);
+	ww_acquire_init(&ctx, &ww_class);
+
+	INIT_WORK_ONSTACK(&mtx.work, test_mutex_work);
+	init_completion(&mtx.ready);
+	init_completion(&mtx.go);
+	init_completion(&mtx.done);
+	mtx.flags = flags;
+
+	schedule_work(&mtx.work);
+
+	wait_for_completion(&mtx.ready);
+	ww_mutex_lock(&mtx.mutex, (flags & TEST_MTX_CTX) ? &ctx : NULL);
+	complete(&mtx.go);
+	if (flags & TEST_MTX_SPIN) {
+		unsigned long timeout = jiffies + TIMEOUT;
+
+		ret = 0;
+		do {
+			if (completion_done(&mtx.done)) {
+				ret = -EINVAL;
+				break;
+			}
+			cpu_relax();
+		} while (time_before(jiffies, timeout));
+	} else {
+		ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);
+	}
+	ww_mutex_unlock(&mtx.mutex);
+	ww_acquire_fini(&ctx);
+
+	if (ret) {
+		pr_err("%s(flags=%x): mutual exclusion failure\n",
+		       __func__, flags);
+		ret = -EINVAL;
+	}
+
+	flush_work(&mtx.work);
+	destroy_work_on_stack(&mtx.work);
+	return ret;
+#undef TIMEOUT
+}
+
+static int test_mutex(void)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < __TEST_MTX_LAST; i++) {
+		ret = __test_mutex(i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int test_aa(void)
+{
+	struct ww_mutex mutex;
+	struct ww_acquire_ctx ctx;
+	int ret;
+
+	ww_mutex_init(&mutex, &ww_class);
+	ww_acquire_init(&ctx, &ww_class);
+
+	ww_mutex_lock(&mutex, &ctx);
+
+	if (ww_mutex_trylock(&mutex))  {
+		pr_err("%s: trylocked itself!\n", __func__);
+		ww_mutex_unlock(&mutex);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = ww_mutex_lock(&mutex, &ctx);
+	if (ret != -EALREADY) {
+		pr_err("%s: missed deadlock for recursing, ret=%d\n",
+		       __func__, ret);
+		if (!ret)
+			ww_mutex_unlock(&mutex);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = 0;
+out:
+	ww_mutex_unlock(&mutex);
+	ww_acquire_fini(&ctx);
+	return ret;
+}
+
+struct test_abba {
+	struct work_struct work;
+	struct ww_mutex a_mutex;
+	struct ww_mutex b_mutex;
+	struct completion a_ready;
+	struct completion b_ready;
+	bool resolve;
+	int result;
+};
+
+static void test_abba_work(struct work_struct *work)
+{
+	struct test_abba *abba = container_of(work, typeof(*abba), work);
+	struct ww_acquire_ctx ctx;
+	int err;
+
+	ww_acquire_init(&ctx, &ww_class);
+	ww_mutex_lock(&abba->b_mutex, &ctx);
+
+	complete(&abba->b_ready);
+	wait_for_completion(&abba->a_ready);
+
+	err = ww_mutex_lock(&abba->a_mutex, &ctx);
+	if (abba->resolve && err == -EDEADLK) {
+		ww_mutex_unlock(&abba->b_mutex);
+		ww_mutex_lock_slow(&abba->a_mutex, &ctx);
+		err = ww_mutex_lock(&abba->b_mutex, &ctx);
+	}
+
+	if (!err)
+		ww_mutex_unlock(&abba->a_mutex);
+	ww_mutex_unlock(&abba->b_mutex);
+	ww_acquire_fini(&ctx);
+
+	abba->result = err;
+}
+
+static int test_abba(bool resolve)
+{
+	struct test_abba abba;
+	struct ww_acquire_ctx ctx;
+	int err, ret;
+
+	ww_mutex_init(&abba.a_mutex, &ww_class);
+	ww_mutex_init(&abba.b_mutex, &ww_class);
+	INIT_WORK_ONSTACK(&abba.work, test_abba_work);
+	init_completion(&abba.a_ready);
+	init_completion(&abba.b_ready);
+	abba.resolve = resolve;
+
+	schedule_work(&abba.work);
+
+	ww_acquire_init(&ctx, &ww_class);
+	ww_mutex_lock(&abba.a_mutex, &ctx);
+
+	complete(&abba.a_ready);
+	wait_for_completion(&abba.b_ready);
+
+	err = ww_mutex_lock(&abba.b_mutex, &ctx);
+	if (resolve && err == -EDEADLK) {
+		ww_mutex_unlock(&abba.a_mutex);
+		ww_mutex_lock_slow(&abba.b_mutex, &ctx);
+		err = ww_mutex_lock(&abba.a_mutex, &ctx);
+	}
+
+	if (!err)
+		ww_mutex_unlock(&abba.b_mutex);
+	ww_mutex_unlock(&abba.a_mutex);
+	ww_acquire_fini(&ctx);
+
+	flush_work(&abba.work);
+	destroy_work_on_stack(&abba.work);
+
+	ret = 0;
+	if (resolve) {
+		if (err || abba.result) {
+			pr_err("%s: failed to resolve ABBA deadlock, A err=%d, B err=%d\n",
+			       __func__, err, abba.result);
+			ret = -EINVAL;
+		}
+	} else {
+		if (err != -EDEADLK && abba.result != -EDEADLK) {
+			pr_err("%s: missed ABBA deadlock, A err=%d, B err=%d\n",
+			       __func__, err, abba.result);
+			ret = -EINVAL;
+		}
+	}
+	return ret;
+}
+
+struct test_cycle {
+	struct work_struct work;
+	struct ww_mutex a_mutex;
+	struct ww_mutex *b_mutex;
+	struct completion *a_signal;
+	struct completion b_signal;
+	int result;
+};
+
+static void test_cycle_work(struct work_struct *work)
+{
+	struct test_cycle *cycle = container_of(work, typeof(*cycle), work);
+	struct ww_acquire_ctx ctx;
+	int err;
+
+	ww_acquire_init(&ctx, &ww_class);
+	ww_mutex_lock(&cycle->a_mutex, &ctx);
+
+	complete(cycle->a_signal);
+	wait_for_completion(&cycle->b_signal);
+
+	err = ww_mutex_lock(cycle->b_mutex, &ctx);
+	if (err == -EDEADLK) {
+		ww_mutex_unlock(&cycle->a_mutex);
+		ww_mutex_lock_slow(cycle->b_mutex, &ctx);
+		err = ww_mutex_lock(&cycle->a_mutex, &ctx);
+	}
+
+	if (!err)
+		ww_mutex_unlock(cycle->b_mutex);
+	ww_mutex_unlock(&cycle->a_mutex);
+	ww_acquire_fini(&ctx);
+
+	cycle->result = err;
+}
+
+static int __test_cycle(unsigned int nthreads)
+{
+	struct test_cycle *cycles;
+	unsigned int n, last = nthreads - 1;
+	int ret;
+
+	cycles = kmalloc_array(nthreads, sizeof(*cycles), GFP_KERNEL);
+	if (!cycles)
+		return -ENOMEM;
+
+	for (n = 0; n < nthreads; n++) {
+		struct test_cycle *cycle = &cycles[n];
+
+		ww_mutex_init(&cycle->a_mutex, &ww_class);
+		if (n == last)
+			cycle->b_mutex = &cycles[0].a_mutex;
+		else
+			cycle->b_mutex = &cycles[n + 1].a_mutex;
+
+		if (n == 0)
+			cycle->a_signal = &cycles[last].b_signal;
+		else
+			cycle->a_signal = &cycles[n - 1].b_signal;
+		init_completion(&cycle->b_signal);
+
+		INIT_WORK(&cycle->work, test_cycle_work);
+		cycle->result = 0;
+	}
+
+	for (n = 0; n < nthreads; n++)
+		queue_work(wq, &cycles[n].work);
+
+	flush_workqueue(wq);
+
+	ret = 0;
+	for (n = 0; n < nthreads; n++) {
+		struct test_cycle *cycle = &cycles[n];
+
+		if (!cycle->result)
+			continue;
+
+		pr_err("cylic deadlock not resolved, ret[%d/%d] = %d\n",
+		       n, nthreads, cycle->result);
+		ret = -EINVAL;
+		break;
+	}
+
+	for (n = 0; n < nthreads; n++)
+		ww_mutex_destroy(&cycles[n].a_mutex);
+	kfree(cycles);
+	return ret;
+}
+
+static int test_cycle(unsigned int ncpus)
+{
+	unsigned int n;
+	int ret;
+
+	for (n = 2; n <= ncpus + 1; n++) {
+		ret = __test_cycle(n);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+struct stress {
+	struct work_struct work;
+	struct ww_mutex *locks;
+	int nlocks;
+	int nloops;
+};
+
+static int *get_random_order(int count)
+{
+	int *order;
+	int n, r, tmp;
+
+	order = kmalloc_array(count, sizeof(*order), GFP_TEMPORARY);
+	if (!order)
+		return order;
+
+	for (n = 0; n < count; n++)
+		order[n] = n;
+
+	for (n = count - 1; n > 1; n--) {
+		r = get_random_int() % (n + 1);
+		if (r != n) {
+			tmp = order[n];
+			order[n] = order[r];
+			order[r] = tmp;
+		}
+	}
+
+	return order;
+}
+
+static void dummy_load(struct stress *stress)
+{
+	usleep_range(1000, 2000);
+}
+
+static void stress_inorder_work(struct work_struct *work)
+{
+	struct stress *stress = container_of(work, typeof(*stress), work);
+	const int nlocks = stress->nlocks;
+	struct ww_mutex *locks = stress->locks;
+	struct ww_acquire_ctx ctx;
+	int *order;
+
+	order = get_random_order(nlocks);
+	if (!order)
+		return;
+
+	ww_acquire_init(&ctx, &ww_class);
+
+	do {
+		int contended = -1;
+		int n, err;
+
+retry:
+		err = 0;
+		for (n = 0; n < nlocks; n++) {
+			if (n == contended)
+				continue;
+
+			err = ww_mutex_lock(&locks[order[n]], &ctx);
+			if (err < 0)
+				break;
+		}
+		if (!err)
+			dummy_load(stress);
+
+		if (contended > n)
+			ww_mutex_unlock(&locks[order[contended]]);
+		contended = n;
+		while (n--)
+			ww_mutex_unlock(&locks[order[n]]);
+
+		if (err == -EDEADLK) {
+			ww_mutex_lock_slow(&locks[order[contended]], &ctx);
+			goto retry;
+		}
+
+		if (err) {
+			pr_err_once("stress (%s) failed with %d\n",
+				    __func__, err);
+			break;
+		}
+	} while (--stress->nloops);
+
+	ww_acquire_fini(&ctx);
+
+	kfree(order);
+	kfree(stress);
+}
+
+struct reorder_lock {
+	struct list_head link;
+	struct ww_mutex *lock;
+};
+
+static void stress_reorder_work(struct work_struct *work)
+{
+	struct stress *stress = container_of(work, typeof(*stress), work);
+	LIST_HEAD(locks);
+	struct ww_acquire_ctx ctx;
+	struct reorder_lock *ll, *ln;
+	int *order;
+	int n, err;
+
+	order = get_random_order(stress->nlocks);
+	if (!order)
+		return;
+
+	for (n = 0; n < stress->nlocks; n++) {
+		ll = kmalloc(sizeof(*ll), GFP_KERNEL);
+		if (!ll)
+			goto out;
+
+		ll->lock = &stress->locks[order[n]];
+		list_add(&ll->link, &locks);
+	}
+	kfree(order);
+	order = NULL;
+
+	ww_acquire_init(&ctx, &ww_class);
+
+	do {
+		list_for_each_entry(ll, &locks, link) {
+			err = ww_mutex_lock(ll->lock, &ctx);
+			if (!err)
+				continue;
+
+			ln = ll;
+			list_for_each_entry_continue_reverse(ln, &locks, link)
+				ww_mutex_unlock(ln->lock);
+
+			if (err != -EDEADLK) {
+				pr_err_once("stress (%s) failed with %d\n",
+					    __func__, err);
+				break;
+			}
+
+			ww_mutex_lock_slow(ll->lock, &ctx);
+			list_move(&ll->link, &locks); /* restarts iteration */
+		}
+
+		dummy_load(stress);
+		list_for_each_entry(ll, &locks, link)
+			ww_mutex_unlock(ll->lock);
+	} while (--stress->nloops);
+
+	ww_acquire_fini(&ctx);
+
+out:
+	list_for_each_entry_safe(ll, ln, &locks, link)
+		kfree(ll);
+	kfree(order);
+	kfree(stress);
+}
+
+static void stress_one_work(struct work_struct *work)
+{
+	struct stress *stress = container_of(work, typeof(*stress), work);
+	const int nlocks = stress->nlocks;
+	struct ww_mutex *lock = stress->locks + (get_random_int() % nlocks);
+	int err;
+
+	do {
+		err = ww_mutex_lock(lock, NULL);
+		if (!err) {
+			dummy_load(stress);
+			ww_mutex_unlock(lock);
+		} else {
+			pr_err_once("stress (%s) failed with %d\n",
+				    __func__, err);
+			break;
+		}
+	} while (--stress->nloops);
+
+	kfree(stress);
+}
+
+#define STRESS_INORDER BIT(0)
+#define STRESS_REORDER BIT(1)
+#define STRESS_ONE BIT(2)
+#define STRESS_ALL (STRESS_INORDER | STRESS_REORDER | STRESS_ONE)
+
+static int stress(int nlocks, int nthreads, int nloops, unsigned int flags)
+{
+	struct ww_mutex *locks;
+	int n;
+
+	locks = kmalloc_array(nlocks, sizeof(*locks), GFP_KERNEL);
+	if (!locks)
+		return -ENOMEM;
+
+	for (n = 0; n < nlocks; n++)
+		ww_mutex_init(&locks[n], &ww_class);
+
+	for (n = 0; nthreads; n++) {
+		struct stress *stress;
+		void (*fn)(struct work_struct *work);
+
+		fn = NULL;
+		switch (n & 3) {
+		case 0:
+			if (flags & STRESS_INORDER)
+				fn = stress_inorder_work;
+			break;
+		case 1:
+			if (flags & STRESS_REORDER)
+				fn = stress_reorder_work;
+			break;
+		case 2:
+			if (flags & STRESS_ONE)
+				fn = stress_one_work;
+			break;
+		}
+
+		if (!fn)
+			continue;
+
+		stress = kmalloc(sizeof(*stress), GFP_KERNEL);
+		if (!stress)
+			break;
+
+		INIT_WORK(&stress->work, fn);
+		stress->locks = locks;
+		stress->nlocks = nlocks;
+		stress->nloops = nloops;
+
+		queue_work(wq, &stress->work);
+		nthreads--;
+	}
+
+	flush_workqueue(wq);
+
+	for (n = 0; n < nlocks; n++)
+		ww_mutex_destroy(&locks[n]);
+	kfree(locks);
+
+	return 0;
+}
+
+static int __init test_ww_mutex_init(void)
+{
+	int ncpus = num_online_cpus();
+	int ret;
+
+	wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0);
+	if (!wq)
+		return -ENOMEM;
+
+	ret = test_mutex();
+	if (ret)
+		return ret;
+
+	ret = test_aa();
+	if (ret)
+		return ret;
+
+	ret = test_abba(false);
+	if (ret)
+		return ret;
+
+	ret = test_abba(true);
+	if (ret)
+		return ret;
+
+	ret = test_cycle(ncpus);
+	if (ret)
+		return ret;
+
+	ret = stress(16, 2*ncpus, 1<<10, STRESS_INORDER);
+	if (ret)
+		return ret;
+
+	ret = stress(16, 2*ncpus, 1<<10, STRESS_REORDER);
+	if (ret)
+		return ret;
+
+	ret = stress(4096, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void __exit test_ww_mutex_exit(void)
+{
+	destroy_workqueue(wq);
+}
+
+module_init(test_ww_mutex_init);
+module_exit(test_ww_mutex_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Intel Corporation");
diff --git a/kernel/membarrier.c b/kernel/membarrier.c
index 536c727a56e9..9f9284f37f8d 100644
--- a/kernel/membarrier.c
+++ b/kernel/membarrier.c
@@ -16,6 +16,7 @@
 
 #include <linux/syscalls.h>
 #include <linux/membarrier.h>
+#include <linux/tick.h>
 
 /*
  * Bitmask made from a "or" of all commands within enum membarrier_cmd,
@@ -51,6 +52,9 @@
  */
 SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
 {
+	/* MEMBARRIER_CMD_SHARED is not compatible with nohz_full. */
+	if (tick_nohz_full_enabled())
+		return -ENOSYS;
 	if (unlikely(flags))
 		return -EINVAL;
 	switch (cmd) {
diff --git a/kernel/module.c b/kernel/module.c
index 38d4270925d4..3d8f126208e3 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -389,16 +389,16 @@ extern const struct kernel_symbol __start___ksymtab_gpl[];
 extern const struct kernel_symbol __stop___ksymtab_gpl[];
 extern const struct kernel_symbol __start___ksymtab_gpl_future[];
 extern const struct kernel_symbol __stop___ksymtab_gpl_future[];
-extern const unsigned long __start___kcrctab[];
-extern const unsigned long __start___kcrctab_gpl[];
-extern const unsigned long __start___kcrctab_gpl_future[];
+extern const s32 __start___kcrctab[];
+extern const s32 __start___kcrctab_gpl[];
+extern const s32 __start___kcrctab_gpl_future[];
 #ifdef CONFIG_UNUSED_SYMBOLS
 extern const struct kernel_symbol __start___ksymtab_unused[];
 extern const struct kernel_symbol __stop___ksymtab_unused[];
 extern const struct kernel_symbol __start___ksymtab_unused_gpl[];
 extern const struct kernel_symbol __stop___ksymtab_unused_gpl[];
-extern const unsigned long __start___kcrctab_unused[];
-extern const unsigned long __start___kcrctab_unused_gpl[];
+extern const s32 __start___kcrctab_unused[];
+extern const s32 __start___kcrctab_unused_gpl[];
 #endif
 
 #ifndef CONFIG_MODVERSIONS
@@ -497,7 +497,7 @@ struct find_symbol_arg {
 
 	/* Output */
 	struct module *owner;
-	const unsigned long *crc;
+	const s32 *crc;
 	const struct kernel_symbol *sym;
 };
 
@@ -563,7 +563,7 @@ static bool find_symbol_in_section(const struct symsearch *syms,
  * (optional) module which owns it.  Needs preempt disabled or module_mutex. */
 const struct kernel_symbol *find_symbol(const char *name,
 					struct module **owner,
-					const unsigned long **crc,
+					const s32 **crc,
 					bool gplok,
 					bool warn)
 {
@@ -1249,23 +1249,17 @@ static int try_to_force_load(struct module *mod, const char *reason)
 }
 
 #ifdef CONFIG_MODVERSIONS
-/* If the arch applies (non-zero) relocations to kernel kcrctab, unapply it. */
-static unsigned long maybe_relocated(unsigned long crc,
-				     const struct module *crc_owner)
+
+static u32 resolve_rel_crc(const s32 *crc)
 {
-#ifdef ARCH_RELOCATES_KCRCTAB
-	if (crc_owner == NULL)
-		return crc - (unsigned long)reloc_start;
-#endif
-	return crc;
+	return *(u32 *)((void *)crc + *crc);
 }
 
 static int check_version(Elf_Shdr *sechdrs,
 			 unsigned int versindex,
 			 const char *symname,
 			 struct module *mod,
-			 const unsigned long *crc,
-			 const struct module *crc_owner)
+			 const s32 *crc)
 {
 	unsigned int i, num_versions;
 	struct modversion_info *versions;
@@ -1283,13 +1277,19 @@ static int check_version(Elf_Shdr *sechdrs,
 		/ sizeof(struct modversion_info);
 
 	for (i = 0; i < num_versions; i++) {
+		u32 crcval;
+
 		if (strcmp(versions[i].name, symname) != 0)
 			continue;
 
-		if (versions[i].crc == maybe_relocated(*crc, crc_owner))
+		if (IS_ENABLED(CONFIG_MODULE_REL_CRCS))
+			crcval = resolve_rel_crc(crc);
+		else
+			crcval = *crc;
+		if (versions[i].crc == crcval)
 			return 1;
-		pr_debug("Found checksum %lX vs module %lX\n",
-		       maybe_relocated(*crc, crc_owner), versions[i].crc);
+		pr_debug("Found checksum %X vs module %lX\n",
+			 crcval, versions[i].crc);
 		goto bad_version;
 	}
 
@@ -1307,7 +1307,7 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
 					  unsigned int versindex,
 					  struct module *mod)
 {
-	const unsigned long *crc;
+	const s32 *crc;
 
 	/*
 	 * Since this should be found in kernel (which can't be removed), no
@@ -1321,8 +1321,7 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
 	}
 	preempt_enable();
 	return check_version(sechdrs, versindex,
-			     VMLINUX_SYMBOL_STR(module_layout), mod, crc,
-			     NULL);
+			     VMLINUX_SYMBOL_STR(module_layout), mod, crc);
 }
 
 /* First part is kernel version, which we ignore if module has crcs. */
@@ -1340,8 +1339,7 @@ static inline int check_version(Elf_Shdr *sechdrs,
 				unsigned int versindex,
 				const char *symname,
 				struct module *mod,
-				const unsigned long *crc,
-				const struct module *crc_owner)
+				const s32 *crc)
 {
 	return 1;
 }
@@ -1368,7 +1366,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod,
 {
 	struct module *owner;
 	const struct kernel_symbol *sym;
-	const unsigned long *crc;
+	const s32 *crc;
 	int err;
 
 	/*
@@ -1383,8 +1381,7 @@ static const struct kernel_symbol *resolve_symbol(struct module *mod,
 	if (!sym)
 		goto unlock;
 
-	if (!check_version(info->sechdrs, info->index.vers, name, mod, crc,
-			   owner)) {
+	if (!check_version(info->sechdrs, info->index.vers, name, mod, crc)) {
 		sym = ERR_PTR(-EINVAL);
 		goto getname;
 	}
diff --git a/kernel/panic.c b/kernel/panic.c
index 901c4fb46002..08aa88dde7de 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -249,7 +249,7 @@ void panic(const char *fmt, ...)
 		 * Delay timeout seconds before rebooting the machine.
 		 * We can't use the "normal" timers since we just panicked.
 		 */
-		pr_emerg("Rebooting in %d seconds..", panic_timeout);
+		pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
 
 		for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
 			touch_nmi_watchdog();
diff --git a/kernel/pid.c b/kernel/pid.c
index f66162f2359b..0291804151b5 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -68,9 +68,7 @@ static inline int mk_pid(struct pid_namespace *pid_ns,
  * the scheme scales to up to 4 million PIDs, runtime.
  */
 struct pid_namespace init_pid_ns = {
-	.kref = {
-		.refcount       = ATOMIC_INIT(2),
-	},
+	.kref = KREF_INIT(2),
 	.pidmap = {
 		[ 0 ... PIDMAP_ENTRIES-1] = { ATOMIC_INIT(BITS_PER_PAGE), NULL }
 	},
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index f67ceb7768b8..15e6baef5c73 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -46,7 +46,7 @@ static const char * const mem_sleep_labels[] = {
 const char *mem_sleep_states[PM_SUSPEND_MAX];
 
 suspend_state_t mem_sleep_current = PM_SUSPEND_FREEZE;
-suspend_state_t mem_sleep_default = PM_SUSPEND_MAX;
+static suspend_state_t mem_sleep_default = PM_SUSPEND_MEM;
 
 unsigned int pm_suspend_global_flags;
 EXPORT_SYMBOL_GPL(pm_suspend_global_flags);
@@ -168,7 +168,7 @@ void suspend_set_ops(const struct platform_suspend_ops *ops)
 	}
 	if (valid_state(PM_SUSPEND_MEM)) {
 		mem_sleep_states[PM_SUSPEND_MEM] = mem_sleep_labels[PM_SUSPEND_MEM];
-		if (mem_sleep_default >= PM_SUSPEND_MEM)
+		if (mem_sleep_default == PM_SUSPEND_MEM)
 			mem_sleep_current = PM_SUSPEND_MEM;
 	}
 
diff --git a/kernel/power/suspend_test.c b/kernel/power/suspend_test.c
index bdff5ed57f10..5db217051232 100644
--- a/kernel/power/suspend_test.c
+++ b/kernel/power/suspend_test.c
@@ -166,7 +166,7 @@ static int __init setup_test_suspend(char *value)
 			return 0;
 	}
 
-	for (i = 0; pm_labels[i]; i++)
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
 		if (!strcmp(pm_labels[i], suspend_type)) {
 			test_state_label = pm_labels[i];
 			return 0;
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 32e0c232efba..f80fd33639e0 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -201,7 +201,7 @@ void free_all_swap_pages(int swap)
 		struct swsusp_extent *ext;
 		unsigned long offset;
 
-		ext = container_of(node, struct swsusp_extent, node);
+		ext = rb_entry(node, struct swsusp_extent, node);
 		rb_erase(node, &swsusp_extents);
 		for (offset = ext->start; offset <= ext->end; offset++)
 			swap_free(swp_entry(swap, offset));
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 8b2696420abb..4ba3d34938c0 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1516,7 +1516,7 @@ static void call_console_drivers(int level,
 {
 	struct console *con;
 
-	trace_console(text, len);
+	trace_console_rcuidle(text, len);
 
 	if (!console_drivers)
 		return;
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 87c51225ceec..d81345be730e 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -564,10 +564,25 @@ static void srcu_torture_stats(void)
 	pr_alert("%s%s per-CPU(idx=%d):",
 		 torture_type, TORTURE_FLAG, idx);
 	for_each_possible_cpu(cpu) {
+		unsigned long l0, l1;
+		unsigned long u0, u1;
 		long c0, c1;
+		struct srcu_array *counts = per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu);
 
-		c0 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[!idx];
-		c1 = (long)per_cpu_ptr(srcu_ctlp->per_cpu_ref, cpu)->c[idx];
+		u0 = counts->unlock_count[!idx];
+		u1 = counts->unlock_count[idx];
+
+		/*
+		 * Make sure that a lock is always counted if the corresponding
+		 * unlock is counted.
+		 */
+		smp_rmb();
+
+		l0 = counts->lock_count[!idx];
+		l1 = counts->lock_count[idx];
+
+		c0 = l0 - u0;
+		c1 = l1 - u1;
 		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
 	}
 	pr_cont("\n");
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 9b9cdd549caa..e773129c8b08 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -106,7 +106,7 @@ static int init_srcu_struct_fields(struct srcu_struct *sp)
 	rcu_batch_init(&sp->batch_check1);
 	rcu_batch_init(&sp->batch_done);
 	INIT_DELAYED_WORK(&sp->work, process_srcu);
-	sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array);
+	sp->per_cpu_ref = alloc_percpu(struct srcu_array);
 	return sp->per_cpu_ref ? 0 : -ENOMEM;
 }
 
@@ -141,114 +141,77 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
 #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
 /*
- * Returns approximate total of the readers' ->seq[] values for the
+ * Returns approximate total of the readers' ->lock_count[] values for the
  * rank of per-CPU counters specified by idx.
  */
-static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx)
+static unsigned long srcu_readers_lock_idx(struct srcu_struct *sp, int idx)
 {
 	int cpu;
 	unsigned long sum = 0;
-	unsigned long t;
 
 	for_each_possible_cpu(cpu) {
-		t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]);
-		sum += t;
+		struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+
+		sum += READ_ONCE(cpuc->lock_count[idx]);
 	}
 	return sum;
 }
 
 /*
- * Returns approximate number of readers active on the specified rank
- * of the per-CPU ->c[] counters.
+ * Returns approximate total of the readers' ->unlock_count[] values for the
+ * rank of per-CPU counters specified by idx.
  */
-static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx)
+static unsigned long srcu_readers_unlock_idx(struct srcu_struct *sp, int idx)
 {
 	int cpu;
 	unsigned long sum = 0;
-	unsigned long t;
 
 	for_each_possible_cpu(cpu) {
-		t = READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]);
-		sum += t;
+		struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+
+		sum += READ_ONCE(cpuc->unlock_count[idx]);
 	}
 	return sum;
 }
 
 /*
  * Return true if the number of pre-existing readers is determined to
- * be stably zero.  An example unstable zero can occur if the call
- * to srcu_readers_active_idx() misses an __srcu_read_lock() increment,
- * but due to task migration, sees the corresponding __srcu_read_unlock()
- * decrement.  This can happen because srcu_readers_active_idx() takes
- * time to sum the array, and might in fact be interrupted or preempted
- * partway through the summation.
+ * be zero.
  */
 static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx)
 {
-	unsigned long seq;
+	unsigned long unlocks;
 
-	seq = srcu_readers_seq_idx(sp, idx);
+	unlocks = srcu_readers_unlock_idx(sp, idx);
 
 	/*
-	 * The following smp_mb() A pairs with the smp_mb() B located in
-	 * __srcu_read_lock().  This pairing ensures that if an
-	 * __srcu_read_lock() increments its counter after the summation
-	 * in srcu_readers_active_idx(), then the corresponding SRCU read-side
-	 * critical section will see any changes made prior to the start
-	 * of the current SRCU grace period.
+	 * Make sure that a lock is always counted if the corresponding unlock
+	 * is counted. Needs to be a smp_mb() as the read side may contain a
+	 * read from a variable that is written to before the synchronize_srcu()
+	 * in the write side. In this case smp_mb()s A and B act like the store
+	 * buffering pattern.
 	 *
-	 * Also, if the above call to srcu_readers_seq_idx() saw the
-	 * increment of ->seq[], then the call to srcu_readers_active_idx()
-	 * must see the increment of ->c[].
+	 * This smp_mb() also pairs with smp_mb() C to prevent accesses after the
+	 * synchronize_srcu() from being executed before the grace period ends.
 	 */
 	smp_mb(); /* A */
 
 	/*
-	 * Note that srcu_readers_active_idx() can incorrectly return
-	 * zero even though there is a pre-existing reader throughout.
-	 * To see this, suppose that task A is in a very long SRCU
-	 * read-side critical section that started on CPU 0, and that
-	 * no other reader exists, so that the sum of the counters
-	 * is equal to one.  Then suppose that task B starts executing
-	 * srcu_readers_active_idx(), summing up to CPU 1, and then that
-	 * task C starts reading on CPU 0, so that its increment is not
-	 * summed, but finishes reading on CPU 2, so that its decrement
-	 * -is- summed.  Then when task B completes its sum, it will
-	 * incorrectly get zero, despite the fact that task A has been
-	 * in its SRCU read-side critical section the whole time.
-	 *
-	 * We therefore do a validation step should srcu_readers_active_idx()
-	 * return zero.
-	 */
-	if (srcu_readers_active_idx(sp, idx) != 0)
-		return false;
-
-	/*
-	 * The remainder of this function is the validation step.
-	 * The following smp_mb() D pairs with the smp_mb() C in
-	 * __srcu_read_unlock().  If the __srcu_read_unlock() was seen
-	 * by srcu_readers_active_idx() above, then any destructive
-	 * operation performed after the grace period will happen after
-	 * the corresponding SRCU read-side critical section.
+	 * If the locks are the same as the unlocks, then there must have
+	 * been no readers on this index at some time in between. This does not
+	 * mean that there are no more readers, as one could have read the
+	 * current index but not have incremented the lock counter yet.
 	 *
-	 * Note that there can be at most NR_CPUS worth of readers using
-	 * the old index, which is not enough to overflow even a 32-bit
-	 * integer.  (Yes, this does mean that systems having more than
-	 * a billion or so CPUs need to be 64-bit systems.)  Therefore,
-	 * the sum of the ->seq[] counters cannot possibly overflow.
-	 * Therefore, the only way that the return values of the two
-	 * calls to srcu_readers_seq_idx() can be equal is if there were
-	 * no increments of the corresponding rank of ->seq[] counts
-	 * in the interim.  But the missed-increment scenario laid out
-	 * above includes an increment of the ->seq[] counter by
-	 * the corresponding __srcu_read_lock().  Therefore, if this
-	 * scenario occurs, the return values from the two calls to
-	 * srcu_readers_seq_idx() will differ, and thus the validation
-	 * step below suffices.
+	 * Possible bug: There is no guarantee that there haven't been ULONG_MAX
+	 * increments of ->lock_count[] since the unlocks were counted, meaning
+	 * that this could return true even if there are still active readers.
+	 * Since there are no memory barriers around srcu_flip(), the CPU is not
+	 * required to increment ->completed before running
+	 * srcu_readers_unlock_idx(), which means that there could be an
+	 * arbitrarily large number of critical sections that execute after
+	 * srcu_readers_unlock_idx() but use the old value of ->completed.
 	 */
-	smp_mb(); /* D */
-
-	return srcu_readers_seq_idx(sp, idx) == seq;
+	return srcu_readers_lock_idx(sp, idx) == unlocks;
 }
 
 /**
@@ -266,8 +229,12 @@ static bool srcu_readers_active(struct srcu_struct *sp)
 	unsigned long sum = 0;
 
 	for_each_possible_cpu(cpu) {
-		sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]);
-		sum += READ_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]);
+		struct srcu_array *cpuc = per_cpu_ptr(sp->per_cpu_ref, cpu);
+
+		sum += READ_ONCE(cpuc->lock_count[0]);
+		sum += READ_ONCE(cpuc->lock_count[1]);
+		sum -= READ_ONCE(cpuc->unlock_count[0]);
+		sum -= READ_ONCE(cpuc->unlock_count[1]);
 	}
 	return sum;
 }
@@ -298,9 +265,8 @@ int __srcu_read_lock(struct srcu_struct *sp)
 	int idx;
 
 	idx = READ_ONCE(sp->completed) & 0x1;
-	__this_cpu_inc(sp->per_cpu_ref->c[idx]);
+	__this_cpu_inc(sp->per_cpu_ref->lock_count[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
-	__this_cpu_inc(sp->per_cpu_ref->seq[idx]);
 	return idx;
 }
 EXPORT_SYMBOL_GPL(__srcu_read_lock);
@@ -314,7 +280,7 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock);
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
 	smp_mb(); /* C */  /* Avoid leaking the critical section. */
-	this_cpu_dec(sp->per_cpu_ref->c[idx]);
+	this_cpu_inc(sp->per_cpu_ref->unlock_count[idx]);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -349,12 +315,21 @@ static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount)
 
 /*
  * Increment the ->completed counter so that future SRCU readers will
- * use the other rank of the ->c[] and ->seq[] arrays.  This allows
+ * use the other rank of the ->(un)lock_count[] arrays.  This allows
  * us to wait for pre-existing readers in a starvation-free manner.
  */
 static void srcu_flip(struct srcu_struct *sp)
 {
-	sp->completed++;
+	WRITE_ONCE(sp->completed, sp->completed + 1);
+
+	/*
+	 * Ensure that if the updater misses an __srcu_read_unlock()
+	 * increment, that task's next __srcu_read_lock() will see the
+	 * above counter update.  Note that both this memory barrier
+	 * and the one in srcu_readers_active_idx_check() provide the
+	 * guarantee for __srcu_read_lock().
+	 */
+	smp_mb(); /* D */  /* Pairs with C. */
 }
 
 /*
@@ -392,6 +367,7 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head,
 	head->next = NULL;
 	head->func = func;
 	spin_lock_irqsave(&sp->queue_lock, flags);
+	smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */
 	rcu_batch_queue(&sp->batch_queue, head);
 	if (!sp->running) {
 		sp->running = true;
@@ -425,6 +401,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
 	head->next = NULL;
 	head->func = wakeme_after_rcu;
 	spin_lock_irq(&sp->queue_lock);
+	smp_mb__after_unlock_lock(); /* Caller's prior accesses before GP. */
 	if (!sp->running) {
 		/* steal the processing owner */
 		sp->running = true;
@@ -444,8 +421,11 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount)
 		spin_unlock_irq(&sp->queue_lock);
 	}
 
-	if (!done)
+	if (!done) {
 		wait_for_completion(&rcu.completion);
+		smp_mb(); /* Caller's later accesses after GP. */
+	}
+
 }
 
 /**
@@ -613,7 +593,8 @@ static void srcu_advance_batches(struct srcu_struct *sp, int trycount)
 /*
  * Invoke a limited number of SRCU callbacks that have passed through
  * their grace period.  If there are more to do, SRCU will reschedule
- * the workqueue.
+ * the workqueue.  Note that needed memory barriers have been executed
+ * in this task's context by srcu_readers_active_idx_check().
  */
 static void srcu_invoke_callbacks(struct srcu_struct *sp)
 {
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index b23a4d076f3d..fa6a48d3917b 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -41,8 +41,6 @@
 
 /* Forward declarations for tiny_plugin.h. */
 struct rcu_ctrlblk;
-static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp);
-static void rcu_process_callbacks(struct softirq_action *unused);
 static void __call_rcu(struct rcu_head *head,
 		       rcu_callback_t func,
 		       struct rcu_ctrlblk *rcp);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cb4e2056ccf3..d80e0d2f68c6 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -281,6 +281,116 @@ static DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = {
 #endif /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
 };
 
+/*
+ * Record entry into an extended quiescent state.  This is only to be
+ * called when not already in an extended quiescent state.
+ */
+static void rcu_dynticks_eqs_enter(void)
+{
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int special;
+
+	/*
+	 * CPUs seeing atomic_inc_return() must see prior RCU read-side
+	 * critical sections, and we also must force ordering with the
+	 * next idle sojourn.
+	 */
+	special = atomic_inc_return(&rdtp->dynticks);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && special & 0x1);
+}
+
+/*
+ * Record exit from an extended quiescent state.  This is only to be
+ * called from an extended quiescent state.
+ */
+static void rcu_dynticks_eqs_exit(void)
+{
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int special;
+
+	/*
+	 * CPUs seeing atomic_inc_return() must see prior idle sojourns,
+	 * and we also must force ordering with the next RCU read-side
+	 * critical section.
+	 */
+	special = atomic_inc_return(&rdtp->dynticks);
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) && !(special & 0x1));
+}
+
+/*
+ * Reset the current CPU's ->dynticks counter to indicate that the
+ * newly onlined CPU is no longer in an extended quiescent state.
+ * This will either leave the counter unchanged, or increment it
+ * to the next non-quiescent value.
+ *
+ * The non-atomic test/increment sequence works because the upper bits
+ * of the ->dynticks counter are manipulated only by the corresponding CPU,
+ * or when the corresponding CPU is offline.
+ */
+static void rcu_dynticks_eqs_online(void)
+{
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+
+	if (atomic_read(&rdtp->dynticks) & 0x1)
+		return;
+	atomic_add(0x1, &rdtp->dynticks);
+}
+
+/*
+ * Is the current CPU in an extended quiescent state?
+ *
+ * No ordering, as we are sampling CPU-local information.
+ */
+bool rcu_dynticks_curr_cpu_in_eqs(void)
+{
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+
+	return !(atomic_read(&rdtp->dynticks) & 0x1);
+}
+
+/*
+ * Snapshot the ->dynticks counter with full ordering so as to allow
+ * stable comparison of this counter with past and future snapshots.
+ */
+int rcu_dynticks_snap(struct rcu_dynticks *rdtp)
+{
+	int snap = atomic_add_return(0, &rdtp->dynticks);
+
+	return snap;
+}
+
+/*
+ * Return true if the snapshot returned from rcu_dynticks_snap()
+ * indicates that RCU is in an extended quiescent state.
+ */
+static bool rcu_dynticks_in_eqs(int snap)
+{
+	return !(snap & 0x1);
+}
+
+/*
+ * Return true if the CPU corresponding to the specified rcu_dynticks
+ * structure has spent some time in an extended quiescent state since
+ * rcu_dynticks_snap() returned the specified snapshot.
+ */
+static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap)
+{
+	return snap != rcu_dynticks_snap(rdtp);
+}
+
+/*
+ * Do a double-increment of the ->dynticks counter to emulate a
+ * momentary idle-CPU quiescent state.
+ */
+static void rcu_dynticks_momentary_idle(void)
+{
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int special = atomic_add_return(2, &rdtp->dynticks);
+
+	/* It is illegal to call this from idle state. */
+	WARN_ON_ONCE(!(special & 0x1));
+}
+
 DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, rcu_qs_ctr);
 EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
 
@@ -300,7 +410,6 @@ EXPORT_PER_CPU_SYMBOL_GPL(rcu_qs_ctr);
 static void rcu_momentary_dyntick_idle(void)
 {
 	struct rcu_data *rdp;
-	struct rcu_dynticks *rdtp;
 	int resched_mask;
 	struct rcu_state *rsp;
 
@@ -327,10 +436,7 @@ static void rcu_momentary_dyntick_idle(void)
 		 * quiescent state, with no need for this CPU to do anything
 		 * further.
 		 */
-		rdtp = this_cpu_ptr(&rcu_dynticks);
-		smp_mb__before_atomic(); /* Earlier stuff before QS. */
-		atomic_add(2, &rdtp->dynticks);  /* QS. */
-		smp_mb__after_atomic(); /* Later stuff after QS. */
+		rcu_dynticks_momentary_idle();
 		break;
 	}
 }
@@ -611,7 +717,7 @@ static int
 cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp)
 {
 	return &rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL] &&
-	       rdp->nxttail[RCU_DONE_TAIL] != NULL;
+	       rdp->nxttail[RCU_NEXT_TAIL] != NULL;
 }
 
 /*
@@ -673,7 +779,7 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 {
 	struct rcu_state *rsp;
 	struct rcu_data *rdp;
-	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);)
 
 	trace_rcu_dyntick(TPS("Start"), oldval, rdtp->dynticks_nesting);
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
@@ -692,12 +798,7 @@ static void rcu_eqs_enter_common(long long oldval, bool user)
 		do_nocb_deferred_wakeup(rdp);
 	}
 	rcu_prepare_for_idle();
-	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
-	smp_mb__before_atomic();  /* See above. */
-	atomic_inc(&rdtp->dynticks);
-	smp_mb__after_atomic();  /* Force ordering with next sojourn. */
-	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     atomic_read(&rdtp->dynticks) & 0x1);
+	rcu_dynticks_eqs_enter();
 	rcu_dynticks_task_enter();
 
 	/*
@@ -826,15 +927,10 @@ void rcu_irq_exit_irqson(void)
  */
 static void rcu_eqs_exit_common(long long oldval, int user)
 {
-	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	RCU_TRACE(struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);)
 
 	rcu_dynticks_task_exit();
-	smp_mb__before_atomic();  /* Force ordering w/previous sojourn. */
-	atomic_inc(&rdtp->dynticks);
-	/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
-	smp_mb__after_atomic();  /* See above. */
-	WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
-		     !(atomic_read(&rdtp->dynticks) & 0x1));
+	rcu_dynticks_eqs_exit();
 	rcu_cleanup_after_idle();
 	trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
 	if (IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
@@ -980,12 +1076,8 @@ void rcu_nmi_enter(void)
 	 * to be in the outermost NMI handler that interrupted an RCU-idle
 	 * period (observation due to Andy Lutomirski).
 	 */
-	if (!(atomic_read(&rdtp->dynticks) & 0x1)) {
-		smp_mb__before_atomic();  /* Force delay from prior write. */
-		atomic_inc(&rdtp->dynticks);
-		/* atomic_inc() before later RCU read-side crit sects */
-		smp_mb__after_atomic();  /* See above. */
-		WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+	if (rcu_dynticks_curr_cpu_in_eqs()) {
+		rcu_dynticks_eqs_exit();
 		incby = 1;
 	}
 	rdtp->dynticks_nmi_nesting += incby;
@@ -1010,7 +1102,7 @@ void rcu_nmi_exit(void)
 	 * to us!)
 	 */
 	WARN_ON_ONCE(rdtp->dynticks_nmi_nesting <= 0);
-	WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
+	WARN_ON_ONCE(rcu_dynticks_curr_cpu_in_eqs());
 
 	/*
 	 * If the nesting level is not 1, the CPU wasn't RCU-idle, so
@@ -1023,11 +1115,7 @@ void rcu_nmi_exit(void)
 
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
 	rdtp->dynticks_nmi_nesting = 0;
-	/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
-	smp_mb__before_atomic();  /* See above. */
-	atomic_inc(&rdtp->dynticks);
-	smp_mb__after_atomic();  /* Force delay to next write. */
-	WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
+	rcu_dynticks_eqs_enter();
 }
 
 /**
@@ -1040,7 +1128,7 @@ void rcu_nmi_exit(void)
  */
 bool notrace __rcu_is_watching(void)
 {
-	return atomic_read(this_cpu_ptr(&rcu_dynticks.dynticks)) & 0x1;
+	return !rcu_dynticks_curr_cpu_in_eqs();
 }
 
 /**
@@ -1123,9 +1211,9 @@ static int rcu_is_cpu_rrupt_from_idle(void)
 static int dyntick_save_progress_counter(struct rcu_data *rdp,
 					 bool *isidle, unsigned long *maxj)
 {
-	rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks);
+	rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks);
 	rcu_sysidle_check_cpu(rdp, isidle, maxj);
-	if ((rdp->dynticks_snap & 0x1) == 0) {
+	if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
 		if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4,
 				 rdp->mynode->gpnum))
@@ -1144,12 +1232,10 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp,
 static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 				    bool *isidle, unsigned long *maxj)
 {
-	unsigned int curr;
+	unsigned long jtsq;
 	int *rcrmp;
-	unsigned int snap;
-
-	curr = (unsigned int)atomic_add_return(0, &rdp->dynticks->dynticks);
-	snap = (unsigned int)rdp->dynticks_snap;
+	unsigned long rjtsc;
+	struct rcu_node *rnp;
 
 	/*
 	 * If the CPU passed through or entered a dynticks idle phase with
@@ -1159,27 +1245,39 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	 * read-side critical section that started before the beginning
 	 * of the current RCU grace period.
 	 */
-	if ((curr & 0x1) == 0 || UINT_CMP_GE(curr, snap + 2)) {
+	if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
 		rdp->dynticks_fqs++;
 		return 1;
 	}
 
+	/* Compute and saturate jiffies_till_sched_qs. */
+	jtsq = jiffies_till_sched_qs;
+	rjtsc = rcu_jiffies_till_stall_check();
+	if (jtsq > rjtsc / 2) {
+		WRITE_ONCE(jiffies_till_sched_qs, rjtsc);
+		jtsq = rjtsc / 2;
+	} else if (jtsq < 1) {
+		WRITE_ONCE(jiffies_till_sched_qs, 1);
+		jtsq = 1;
+	}
+
 	/*
-	 * Check for the CPU being offline, but only if the grace period
-	 * is old enough.  We don't need to worry about the CPU changing
-	 * state: If we see it offline even once, it has been through a
-	 * quiescent state.
-	 *
-	 * The reason for insisting that the grace period be at least
-	 * one jiffy old is that CPUs that are not quite online and that
-	 * have just gone offline can still execute RCU read-side critical
-	 * sections.
+	 * Has this CPU encountered a cond_resched_rcu_qs() since the
+	 * beginning of the grace period?  For this to be the case,
+	 * the CPU has to have noticed the current grace period.  This
+	 * might not be the case for nohz_full CPUs looping in the kernel.
 	 */
-	if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies))
-		return 0;  /* Grace period is not old enough. */
-	barrier();
-	if (cpu_is_offline(rdp->cpu)) {
+	rnp = rdp->mynode;
+	if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
+	    READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_qs_ctr, rdp->cpu) &&
+	    READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) {
+		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
+		return 1;
+	}
+
+	/* Check for the CPU being offline. */
+	if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl"));
 		rdp->offline_fqs++;
 		return 1;
@@ -1207,9 +1305,8 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 	 * warning delay.
 	 */
 	rcrmp = &per_cpu(rcu_sched_qs_mask, rdp->cpu);
-	if (ULONG_CMP_GE(jiffies,
-			 rdp->rsp->gp_start + jiffies_till_sched_qs) ||
-	    ULONG_CMP_GE(jiffies, rdp->rsp->jiffies_resched)) {
+	if (time_after(jiffies, rdp->rsp->gp_start + jtsq) ||
+	    time_after(jiffies, rdp->rsp->jiffies_resched)) {
 		if (!(READ_ONCE(*rcrmp) & rdp->rsp->flavor_mask)) {
 			WRITE_ONCE(rdp->cond_resched_completed,
 				   READ_ONCE(rdp->mynode->completed));
@@ -1220,11 +1317,12 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp,
 		rdp->rsp->jiffies_resched += 5; /* Re-enable beating. */
 	}
 
-	/* And if it has been a really long time, kick the CPU as well. */
-	if (ULONG_CMP_GE(jiffies,
-			 rdp->rsp->gp_start + 2 * jiffies_till_sched_qs) ||
-	    ULONG_CMP_GE(jiffies, rdp->rsp->gp_start + jiffies_till_sched_qs))
-		resched_cpu(rdp->cpu);  /* Force CPU into scheduler. */
+	/*
+	 * If more than halfway to RCU CPU stall-warning time, do
+	 * a resched_cpu() to try to loosen things up a bit.
+	 */
+	if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2)
+		resched_cpu(rdp->cpu);
 
 	return 0;
 }
@@ -1277,7 +1375,10 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 }
 
 /*
- * Dump stacks of all tasks running on stalled CPUs.
+ * Dump stacks of all tasks running on stalled CPUs.  First try using
+ * NMIs, but fall back to manual remote stack tracing on architectures
+ * that don't support NMI-based stack dumps.  The NMI-triggered stack
+ * traces are more accurate because they are printed by the target CPU.
  */
 static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
 {
@@ -1287,11 +1388,10 @@ static void rcu_dump_cpu_stacks(struct rcu_state *rsp)
 
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		if (rnp->qsmask != 0) {
-			for_each_leaf_node_possible_cpu(rnp, cpu)
-				if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+		for_each_leaf_node_possible_cpu(rnp, cpu)
+			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+				if (!trigger_single_cpu_backtrace(cpu))
 					dump_cpu_task(cpu);
-		}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
 }
@@ -1379,6 +1479,9 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	       (long)rsp->gpnum, (long)rsp->completed, totqlen);
 	if (ndetected) {
 		rcu_dump_cpu_stacks(rsp);
+
+		/* Complain about tasks blocking the grace period. */
+		rcu_print_detail_task_stall(rsp);
 	} else {
 		if (READ_ONCE(rsp->gpnum) != gpnum ||
 		    READ_ONCE(rsp->completed) == gpnum) {
@@ -1395,9 +1498,6 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 		}
 	}
 
-	/* Complain about tasks blocking the grace period. */
-	rcu_print_detail_task_stall(rsp);
-
 	rcu_check_gp_kthread_starvation(rsp);
 
 	panic_on_rcu_stall();
@@ -2467,10 +2567,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	if ((rdp->cpu_no_qs.b.norm &&
-	     rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) ||
-	    rdp->gpnum != rnp->gpnum || rnp->completed == rnp->gpnum ||
-	    rdp->gpwrap) {
+	if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum ||
+	    rnp->completed == rnp->gpnum || rdp->gpwrap) {
 
 		/*
 		 * The grace period in which this quiescent state was
@@ -2525,8 +2623,7 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
 	 * Was there a quiescent state since the beginning of the grace
 	 * period? If no, then exit and wait for the next call.
 	 */
-	if (rdp->cpu_no_qs.b.norm &&
-	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr))
+	if (rdp->cpu_no_qs.b.norm)
 		return;
 
 	/*
@@ -3480,9 +3577,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	    rdp->core_needs_qs && rdp->cpu_no_qs.b.norm &&
 	    rdp->rcu_qs_ctr_snap == __this_cpu_read(rcu_qs_ctr)) {
 		rdp->n_rp_core_needs_qs++;
-	} else if (rdp->core_needs_qs &&
-		   (!rdp->cpu_no_qs.b.norm ||
-		    rdp->rcu_qs_ctr_snap != __this_cpu_read(rcu_qs_ctr))) {
+	} else if (rdp->core_needs_qs && !rdp->cpu_no_qs.b.norm) {
 		rdp->n_rp_report_qs++;
 		return 1;
 	}
@@ -3748,7 +3843,7 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->grpmask = leaf_node_cpu_bit(rdp->mynode, cpu);
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE);
-	WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1);
+	WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	rcu_boot_init_nocb_percpu_data(rdp);
@@ -3765,7 +3860,6 @@ static void
 rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
 	unsigned long flags;
-	unsigned long mask;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
@@ -3778,8 +3872,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 		init_callback_list(rdp);  /* Re-enable callbacks on this CPU. */
 	rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE;
 	rcu_sysidle_init_percpu_data(rdp->dynticks);
-	atomic_set(&rdp->dynticks->dynticks,
-		   (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1);
+	rcu_dynticks_eqs_online();
 	raw_spin_unlock_rcu_node(rnp);		/* irqs remain disabled. */
 
 	/*
@@ -3788,7 +3881,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	 * of the next grace period.
 	 */
 	rnp = rdp->mynode;
-	mask = rdp->grpmask;
 	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
 	if (!rdp->beenonline)
 		WRITE_ONCE(rsp->ncpus, READ_ONCE(rsp->ncpus) + 1);
@@ -3872,7 +3964,7 @@ void rcu_cpu_starting(unsigned int cpu)
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp) {
-		rdp = this_cpu_ptr(rsp->rda);
+		rdp = per_cpu_ptr(rsp->rda, cpu);
 		rnp = rdp->mynode;
 		mask = rdp->grpmask;
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index fe98dd24adf8..b60f2b6caa14 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -521,7 +521,6 @@ struct rcu_state {
 	struct mutex exp_mutex;			/* Serialize expedited GP. */
 	struct mutex exp_wake_mutex;		/* Serialize wakeup. */
 	unsigned long expedited_sequence;	/* Take a ticket. */
-	atomic_long_t expedited_normal;		/* # fallbacks to normal. */
 	atomic_t expedited_need_qs;		/* # CPUs left to check in. */
 	struct swait_queue_head expedited_wq;	/* Wait for check-ins. */
 	int ncpus_snap;				/* # CPUs seen last time. */
@@ -595,6 +594,8 @@ extern struct rcu_state rcu_bh_state;
 extern struct rcu_state rcu_preempt_state;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 
+int rcu_dynticks_snap(struct rcu_dynticks *rdtp);
+
 #ifdef CONFIG_RCU_BOOST
 DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status);
 DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu);
@@ -688,18 +689,6 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll)
 #endif /* #ifdef CONFIG_RCU_TRACE */
 
 /*
- * Place this after a lock-acquisition primitive to guarantee that
- * an UNLOCK+LOCK pair act as a full barrier.  This guarantee applies
- * if the UNLOCK and LOCK are executed by the same CPU or if the
- * UNLOCK and LOCK operate on the same lock variable.
- */
-#ifdef CONFIG_PPC
-#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
-#else /* #ifdef CONFIG_PPC */
-#define smp_mb__after_unlock_lock()	do { } while (0)
-#endif /* #else #ifdef CONFIG_PPC */
-
-/*
  * Wrappers for the rcu_node::lock acquire and release.
  *
  * Because the rcu_nodes form a tree, the tree traversal locking will observe
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index e59e1849b89a..a7b639ccd46e 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -20,16 +20,26 @@
  * Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
  */
 
-/* Wrapper functions for expedited grace periods.  */
+/*
+ * Record the start of an expedited grace period.
+ */
 static void rcu_exp_gp_seq_start(struct rcu_state *rsp)
 {
 	rcu_seq_start(&rsp->expedited_sequence);
 }
+
+/*
+ * Record the end of an expedited grace period.
+ */
 static void rcu_exp_gp_seq_end(struct rcu_state *rsp)
 {
 	rcu_seq_end(&rsp->expedited_sequence);
 	smp_mb(); /* Ensure that consecutive grace periods serialize. */
 }
+
+/*
+ * Take a snapshot of the expedited-grace-period counter.
+ */
 static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
 {
 	unsigned long s;
@@ -39,6 +49,12 @@ static unsigned long rcu_exp_gp_seq_snap(struct rcu_state *rsp)
 	trace_rcu_exp_grace_period(rsp->name, s, TPS("snap"));
 	return s;
 }
+
+/*
+ * Given a counter snapshot from rcu_exp_gp_seq_snap(), return true
+ * if a full expedited grace period has elapsed since that snapshot
+ * was taken.
+ */
 static bool rcu_exp_gp_seq_done(struct rcu_state *rsp, unsigned long s)
 {
 	return rcu_seq_done(&rsp->expedited_sequence, s);
@@ -356,12 +372,11 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		mask_ofl_test = 0;
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
 			rdp->exp_dynticks_snap =
-				atomic_add_return(0, &rdtp->dynticks);
+				rcu_dynticks_snap(rdp->dynticks);
 			if (raw_smp_processor_id() == cpu ||
-			    !(rdp->exp_dynticks_snap & 0x1) ||
+			    rcu_dynticks_in_eqs(rdp->exp_dynticks_snap) ||
 			    !(rnp->qsmaskinitnext & rdp->grpmask))
 				mask_ofl_test |= rdp->grpmask;
 		}
@@ -380,13 +395,12 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			unsigned long mask = leaf_node_cpu_bit(rnp, cpu);
 			struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
-			struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu);
 
 			if (!(mask_ofl_ipi & mask))
 				continue;
 retry_ipi:
-			if (atomic_add_return(0, &rdtp->dynticks) !=
-			    rdp->exp_dynticks_snap) {
+			if (rcu_dynticks_in_eqs_since(rdp->dynticks,
+						      rdp->exp_dynticks_snap)) {
 				mask_ofl_test |= mask;
 				continue;
 			}
@@ -623,6 +637,11 @@ void synchronize_sched_expedited(void)
 {
 	struct rcu_state *rsp = &rcu_sched_state;
 
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+			 lock_is_held(&rcu_lock_map) ||
+			 lock_is_held(&rcu_sched_lock_map),
+			 "Illegal synchronize_sched_expedited() in RCU read-side critical section");
+
 	/* If only one CPU, this is automatically a grace period. */
 	if (rcu_blocking_is_gp())
 		return;
@@ -692,6 +711,11 @@ void synchronize_rcu_expedited(void)
 {
 	struct rcu_state *rsp = rcu_state_p;
 
+	RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) ||
+			 lock_is_held(&rcu_lock_map) ||
+			 lock_is_held(&rcu_sched_lock_map),
+			 "Illegal synchronize_rcu_expedited() in RCU read-side critical section");
+
 	if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE)
 		return;
 	_synchronize_rcu_expedited(rsp, sync_rcu_exp_handler);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 56583e764ebf..a240f3308be6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1643,7 +1643,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
 	       "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
 	       ticks_value, ticks_title,
-	       atomic_read(&rdtp->dynticks) & 0xfff,
+	       rcu_dynticks_snap(rdtp) & 0xfff,
 	       rdtp->dynticks_nesting, rdtp->dynticks_nmi_nesting,
 	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
 	       READ_ONCE(rsp->n_force_qs) - rsp->n_force_qs_gpstart,
@@ -2366,8 +2366,9 @@ static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp)
 	}
 
 	/*
-	 * Each pass through this loop sets up one rcu_data structure and
-	 * spawns one rcu_nocb_kthread().
+	 * Each pass through this loop sets up one rcu_data structure.
+	 * Should the corresponding CPU come online in the future, then
+	 * we will spawn the needed set of rcu_nocb_kthread() kthreads.
 	 */
 	for_each_cpu(cpu, rcu_nocb_mask) {
 		rdp = per_cpu_ptr(rsp->rda, cpu);
diff --git a/kernel/rcu/tree_trace.c b/kernel/rcu/tree_trace.c
index b1f28972872c..8751a748499a 100644
--- a/kernel/rcu/tree_trace.c
+++ b/kernel/rcu/tree_trace.c
@@ -124,7 +124,7 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp)
 		   rdp->rcu_qs_ctr_snap == per_cpu(rcu_qs_ctr, rdp->cpu),
 		   rdp->core_needs_qs);
 	seq_printf(m, " dt=%d/%llx/%d df=%lu",
-		   atomic_read(&rdp->dynticks->dynticks),
+		   rcu_dynticks_snap(rdp->dynticks),
 		   rdp->dynticks->dynticks_nesting,
 		   rdp->dynticks->dynticks_nmi_nesting,
 		   rdp->dynticks_fqs);
@@ -194,9 +194,8 @@ static int show_rcuexp(struct seq_file *m, void *v)
 		s2 += atomic_long_read(&rdp->exp_workdone2);
 		s3 += atomic_long_read(&rdp->exp_workdone3);
 	}
-	seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu n=%lu enq=%d sc=%lu\n",
+	seq_printf(m, "s=%lu wd0=%lu wd1=%lu wd2=%lu wd3=%lu enq=%d sc=%lu\n",
 		   rsp->expedited_sequence, s0, s1, s2, s3,
-		   atomic_long_read(&rsp->expedited_normal),
 		   atomic_read(&rsp->expedited_need_qs),
 		   rsp->expedited_sequence / 2);
 	return 0;
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4f6db7e6a117..9e03db9ea9c0 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -132,8 +132,7 @@ bool rcu_gp_is_normal(void)
 }
 EXPORT_SYMBOL_GPL(rcu_gp_is_normal);
 
-static atomic_t rcu_expedited_nesting =
-	ATOMIC_INIT(IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT) ? 1 : 0);
+static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1);
 
 /*
  * Should normal grace-period primitives be expedited?  Intended for
@@ -182,8 +181,7 @@ EXPORT_SYMBOL_GPL(rcu_unexpedite_gp);
  */
 void rcu_end_inkernel_boot(void)
 {
-	if (IS_ENABLED(CONFIG_RCU_EXPEDITE_BOOT))
-		rcu_unexpedite_gp();
+	rcu_unexpedite_gp();
 	if (rcu_normal_after_boot)
 		WRITE_ONCE(rcu_normal, 1);
 }
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 5e59b832ae2b..89ab6758667b 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -18,8 +18,8 @@ endif
 obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
 obj-y += wait.o swait.o completion.o idle.o
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
-obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o
+obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
diff --git a/kernel/sched/auto_group.c b/kernel/sched/autogroup.c
index da39489d2d80..da39489d2d80 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/autogroup.c
diff --git a/kernel/sched/auto_group.h b/kernel/sched/autogroup.h
index 890c95f2587a..890c95f2587a 100644
--- a/kernel/sched/auto_group.h
+++ b/kernel/sched/autogroup.h
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index e85a725e5c34..ad64efe41722 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -77,41 +77,88 @@ EXPORT_SYMBOL_GPL(sched_clock);
 
 __read_mostly int sched_clock_running;
 
+void sched_clock_init(void)
+{
+	sched_clock_running = 1;
+}
+
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
-static int __sched_clock_stable_early;
+/*
+ * We must start with !__sched_clock_stable because the unstable -> stable
+ * transition is accurate, while the stable -> unstable transition is not.
+ *
+ * Similarly we start with __sched_clock_stable_early, thereby assuming we
+ * will become stable, such that there's only a single 1 -> 0 transition.
+ */
+static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
+static int __sched_clock_stable_early = 1;
 
-int sched_clock_stable(void)
+/*
+ * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset
+ */
+static __read_mostly u64 raw_offset;
+static __read_mostly u64 gtod_offset;
+
+struct sched_clock_data {
+	u64			tick_raw;
+	u64			tick_gtod;
+	u64			clock;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
+
+static inline struct sched_clock_data *this_scd(void)
 {
-	return static_key_false(&__sched_clock_stable);
+	return this_cpu_ptr(&sched_clock_data);
 }
 
-static void __set_sched_clock_stable(void)
+static inline struct sched_clock_data *cpu_sdc(int cpu)
 {
-	if (!sched_clock_stable())
-		static_key_slow_inc(&__sched_clock_stable);
+	return &per_cpu(sched_clock_data, cpu);
+}
 
-	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
+int sched_clock_stable(void)
+{
+	return static_branch_likely(&__sched_clock_stable);
 }
 
-void set_sched_clock_stable(void)
+static void __set_sched_clock_stable(void)
 {
-	__sched_clock_stable_early = 1;
+	struct sched_clock_data *scd = this_scd();
 
-	smp_mb(); /* matches sched_clock_init() */
+	/*
+	 * Attempt to make the (initial) unstable->stable transition continuous.
+	 */
+	raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw);
 
-	if (!sched_clock_running)
-		return;
+	printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
+			scd->tick_gtod, gtod_offset,
+			scd->tick_raw,  raw_offset);
 
-	__set_sched_clock_stable();
+	static_branch_enable(&__sched_clock_stable);
+	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
 static void __clear_sched_clock_stable(struct work_struct *work)
 {
-	/* XXX worry about clock continuity */
-	if (sched_clock_stable())
-		static_key_slow_dec(&__sched_clock_stable);
+	struct sched_clock_data *scd = this_scd();
+
+	/*
+	 * Attempt to make the stable->unstable transition continuous.
+	 *
+	 * Trouble is, this is typically called from the TSC watchdog
+	 * timer, which is late per definition. This means the tick
+	 * values can already be screwy.
+	 *
+	 * Still do what we can.
+	 */
+	gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod);
+
+	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
+			scd->tick_gtod, gtod_offset,
+			scd->tick_raw,  raw_offset);
 
+	static_branch_disable(&__sched_clock_stable);
 	tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
@@ -121,47 +168,15 @@ void clear_sched_clock_stable(void)
 {
 	__sched_clock_stable_early = 0;
 
-	smp_mb(); /* matches sched_clock_init() */
-
-	if (!sched_clock_running)
-		return;
+	smp_mb(); /* matches sched_clock_init_late() */
 
-	schedule_work(&sched_clock_work);
+	if (sched_clock_running == 2)
+		schedule_work(&sched_clock_work);
 }
 
-struct sched_clock_data {
-	u64			tick_raw;
-	u64			tick_gtod;
-	u64			clock;
-};
-
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
-
-static inline struct sched_clock_data *this_scd(void)
+void sched_clock_init_late(void)
 {
-	return this_cpu_ptr(&sched_clock_data);
-}
-
-static inline struct sched_clock_data *cpu_sdc(int cpu)
-{
-	return &per_cpu(sched_clock_data, cpu);
-}
-
-void sched_clock_init(void)
-{
-	u64 ktime_now = ktime_to_ns(ktime_get());
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct sched_clock_data *scd = cpu_sdc(cpu);
-
-		scd->tick_raw = 0;
-		scd->tick_gtod = ktime_now;
-		scd->clock = ktime_now;
-	}
-
-	sched_clock_running = 1;
-
+	sched_clock_running = 2;
 	/*
 	 * Ensure that it is impossible to not do a static_key update.
 	 *
@@ -173,8 +188,6 @@ void sched_clock_init(void)
 
 	if (__sched_clock_stable_early)
 		__set_sched_clock_stable();
-	else
-		__clear_sched_clock_stable(NULL);
 }
 
 /*
@@ -216,7 +229,7 @@ again:
 	 *		      scd->tick_gtod + TICK_NSEC);
 	 */
 
-	clock = scd->tick_gtod + delta;
+	clock = scd->tick_gtod + gtod_offset + delta;
 	min_clock = wrap_max(scd->tick_gtod, old_clock);
 	max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
 
@@ -302,7 +315,7 @@ u64 sched_clock_cpu(int cpu)
 	u64 clock;
 
 	if (sched_clock_stable())
-		return sched_clock();
+		return sched_clock() + raw_offset;
 
 	if (unlikely(!sched_clock_running))
 		return 0ull;
@@ -323,23 +336,22 @@ EXPORT_SYMBOL_GPL(sched_clock_cpu);
 void sched_clock_tick(void)
 {
 	struct sched_clock_data *scd;
-	u64 now, now_gtod;
-
-	if (sched_clock_stable())
-		return;
-
-	if (unlikely(!sched_clock_running))
-		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
 
+	/*
+	 * Update these values even if sched_clock_stable(), because it can
+	 * become unstable at any point in time at which point we need some
+	 * values to fall back on.
+	 *
+	 * XXX arguably we can skip this if we expose tsc_clocksource_reliable
+	 */
 	scd = this_scd();
-	now_gtod = ktime_to_ns(ktime_get());
-	now = sched_clock();
+	scd->tick_raw  = sched_clock();
+	scd->tick_gtod = ktime_get_ns();
 
-	scd->tick_raw = now;
-	scd->tick_gtod = now_gtod;
-	sched_clock_local(scd);
+	if (!sched_clock_stable() && likely(sched_clock_running))
+		sched_clock_local(scd);
 }
 
 /*
@@ -366,11 +378,6 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
-void sched_clock_init(void)
-{
-	sched_clock_running = 1;
-}
-
 u64 sched_clock_cpu(int cpu)
 {
 	if (unlikely(!sched_clock_running))
@@ -378,6 +385,7 @@ u64 sched_clock_cpu(int cpu)
 
 	return sched_clock();
 }
+
 #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
 /*
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 8d0f35debf35..f063a25d4449 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -31,7 +31,8 @@ void complete(struct completion *x)
 	unsigned long flags;
 
 	spin_lock_irqsave(&x->wait.lock, flags);
-	x->done++;
+	if (x->done != UINT_MAX)
+		x->done++;
 	__wake_up_locked(&x->wait, TASK_NORMAL, 1);
 	spin_unlock_irqrestore(&x->wait.lock, flags);
 }
@@ -51,7 +52,7 @@ void complete_all(struct completion *x)
 	unsigned long flags;
 
 	spin_lock_irqsave(&x->wait.lock, flags);
-	x->done += UINT_MAX/2;
+	x->done = UINT_MAX;
 	__wake_up_locked(&x->wait, TASK_NORMAL, 0);
 	spin_unlock_irqrestore(&x->wait.lock, flags);
 }
@@ -79,7 +80,8 @@ do_wait_for_common(struct completion *x,
 		if (!x->done)
 			return timeout;
 	}
-	x->done--;
+	if (x->done != UINT_MAX)
+		x->done--;
 	return timeout ?: 1;
 }
 
@@ -280,7 +282,7 @@ bool try_wait_for_completion(struct completion *x)
 	spin_lock_irqsave(&x->wait.lock, flags);
 	if (!x->done)
 		ret = 0;
-	else
+	else if (x->done != UINT_MAX)
 		x->done--;
 	spin_unlock_irqrestore(&x->wait.lock, flags);
 	return ret;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c56fb57f2991..e1ae6ac15eac 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1,85 +1,28 @@
 /*
  *  kernel/sched/core.c
  *
- *  Kernel scheduler and related syscalls
+ *  Core kernel scheduler code and related syscalls
  *
  *  Copyright (C) 1991-2002  Linus Torvalds
- *
- *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
- *		make semaphores SMP safe
- *  1998-11-19	Implemented schedule_timeout() and related stuff
- *		by Andrea Arcangeli
- *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
- *		hybrid priority-list and round-robin design with
- *		an array-switch method of distributing timeslices
- *		and per-CPU runqueues.  Cleanups and useful suggestions
- *		by Davide Libenzi, preemptible kernel bits by Robert Love.
- *  2003-09-03	Interactivity tuning by Con Kolivas.
- *  2004-04-02	Scheduler domains code by Nick Piggin
- *  2007-04-15  Work begun on replacing all interactivity tuning with a
- *              fair scheduling design by Con Kolivas.
- *  2007-05-05  Load balancing (smp-nice) and other improvements
- *              by Peter Williams
- *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
- *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri
- *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins,
- *              Thomas Gleixner, Mike Kravetz
  */
-
-#include <linux/kasan.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/nmi.h>
-#include <linux/init.h>
-#include <linux/uaccess.h>
-#include <linux/highmem.h>
-#include <linux/mmu_context.h>
-#include <linux/interrupt.h>
-#include <linux/capability.h>
-#include <linux/completion.h>
-#include <linux/kernel_stat.h>
-#include <linux/debug_locks.h>
-#include <linux/perf_event.h>
-#include <linux/security.h>
-#include <linux/notifier.h>
-#include <linux/profile.h>
-#include <linux/freezer.h>
-#include <linux/vmalloc.h>
-#include <linux/blkdev.h>
-#include <linux/delay.h>
-#include <linux/pid_namespace.h>
-#include <linux/smp.h>
-#include <linux/threads.h>
-#include <linux/timer.h>
-#include <linux/rcupdate.h>
-#include <linux/cpu.h>
+#include <linux/sched.h>
 #include <linux/cpuset.h>
-#include <linux/percpu.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/sysctl.h>
-#include <linux/syscalls.h>
-#include <linux/times.h>
-#include <linux/tsacct_kern.h>
-#include <linux/kprobes.h>
 #include <linux/delayacct.h>
-#include <linux/unistd.h>
-#include <linux/pagemap.h>
-#include <linux/hrtimer.h>
-#include <linux/tick.h>
-#include <linux/ctype.h>
-#include <linux/ftrace.h>
-#include <linux/slab.h>
 #include <linux/init_task.h>
 #include <linux/context_tracking.h>
-#include <linux/compiler.h>
-#include <linux/frame.h>
+
+#include <linux/blkdev.h>
+#include <linux/kprobes.h>
+#include <linux/mmu_context.h>
+#include <linux/module.h>
+#include <linux/nmi.h>
 #include <linux/prefetch.h>
-#include <linux/mutex.h>
+#include <linux/profile.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
-#include <asm/irq_regs.h>
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #endif
@@ -91,27 +34,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
-DEFINE_MUTEX(sched_domains_mutex);
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static void update_rq_clock_task(struct rq *rq, s64 delta);
-
-void update_rq_clock(struct rq *rq)
-{
-	s64 delta;
-
-	lockdep_assert_held(&rq->lock);
-
-	if (rq->clock_skip_update & RQCF_ACT_SKIP)
-		return;
-
-	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
-	if (delta < 0)
-		return;
-	rq->clock += delta;
-	update_rq_clock_task(rq, delta);
-}
-
 /*
  * Debugging: various feature bits
  */
@@ -140,7 +64,7 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
 const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
 
 /*
- * period over which we measure -rt task cpu usage in us.
+ * period over which we measure -rt task CPU usage in us.
  * default: 1s
  */
 unsigned int sysctl_sched_rt_period = 1000000;
@@ -153,7 +77,7 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
-/* cpus with isolated domains */
+/* CPUs with isolated domains */
 cpumask_var_t cpu_isolated_map;
 
 /*
@@ -185,7 +109,7 @@ struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
-			rf->cookie = lockdep_pin_lock(&rq->lock);
+			rq_pin_lock(rq, rf);
 			return rq;
 		}
 		raw_spin_unlock(&rq->lock);
@@ -221,11 +145,11 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 		 * If we observe the old cpu in task_rq_lock, the acquire of
 		 * the old rq->lock will fully serialize against the stores.
 		 *
-		 * If we observe the new cpu in task_rq_lock, the acquire will
+		 * If we observe the new CPU in task_rq_lock, the acquire will
 		 * pair with the WMB to ensure we must then also see migrating.
 		 */
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
-			rf->cookie = lockdep_pin_lock(&rq->lock);
+			rq_pin_lock(rq, rf);
 			return rq;
 		}
 		raw_spin_unlock(&rq->lock);
@@ -236,6 +160,84 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	}
 }
 
+/*
+ * RQ-clock updating methods:
+ */
+
+static void update_rq_clock_task(struct rq *rq, s64 delta)
+{
+/*
+ * In theory, the compile should just see 0 here, and optimize out the call
+ * to sched_rt_avg_update. But I don't trust it...
+ */
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	s64 steal = 0, irq_delta = 0;
+#endif
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+	/*
+	 * Since irq_time is only updated on {soft,}irq_exit, we might run into
+	 * this case when a previous update_rq_clock() happened inside a
+	 * {soft,}irq region.
+	 *
+	 * When this happens, we stop ->clock_task and only update the
+	 * prev_irq_time stamp to account for the part that fit, so that a next
+	 * update will consume the rest. This ensures ->clock_task is
+	 * monotonic.
+	 *
+	 * It does however cause some slight miss-attribution of {soft,}irq
+	 * time, a more accurate solution would be to update the irq_time using
+	 * the current rq->clock timestamp, except that would require using
+	 * atomic ops.
+	 */
+	if (irq_delta > delta)
+		irq_delta = delta;
+
+	rq->prev_irq_time += irq_delta;
+	delta -= irq_delta;
+#endif
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+	if (static_key_false((&paravirt_steal_rq_enabled))) {
+		steal = paravirt_steal_clock(cpu_of(rq));
+		steal -= rq->prev_steal_time_rq;
+
+		if (unlikely(steal > delta))
+			steal = delta;
+
+		rq->prev_steal_time_rq += steal;
+		delta -= steal;
+	}
+#endif
+
+	rq->clock_task += delta;
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
+		sched_rt_avg_update(rq, irq_delta + steal);
+#endif
+}
+
+void update_rq_clock(struct rq *rq)
+{
+	s64 delta;
+
+	lockdep_assert_held(&rq->lock);
+
+	if (rq->clock_update_flags & RQCF_ACT_SKIP)
+		return;
+
+#ifdef CONFIG_SCHED_DEBUG
+	rq->clock_update_flags |= RQCF_UPDATED;
+#endif
+	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+	if (delta < 0)
+		return;
+	rq->clock += delta;
+	update_rq_clock_task(rq, delta);
+}
+
+
 #ifdef CONFIG_SCHED_HRTICK
 /*
  * Use HR-timers to deliver accurate preemption points.
@@ -458,7 +460,7 @@ void wake_up_q(struct wake_q_head *head)
 
 		task = container_of(node, struct task_struct, wake_q);
 		BUG_ON(!task);
-		/* task can safely be re-inserted now */
+		/* Task can safely be re-inserted now: */
 		node = node->next;
 		task->wake_q.next = NULL;
 
@@ -516,12 +518,12 @@ void resched_cpu(int cpu)
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ_COMMON
 /*
- * In the semi idle case, use the nearest busy cpu for migrating timers
- * from an idle cpu.  This is good for power-savings.
+ * In the semi idle case, use the nearest busy CPU for migrating timers
+ * from an idle CPU.  This is good for power-savings.
  *
  * We don't do similar optimization for completely idle system, as
- * selecting an idle cpu will add more delays to the timers than intended
- * (as that cpu's timer base may not be uptodate wrt jiffies etc).
+ * selecting an idle CPU will add more delays to the timers than intended
+ * (as that CPU's timer base may not be uptodate wrt jiffies etc).
  */
 int get_nohz_timer_target(void)
 {
@@ -550,6 +552,7 @@ unlock:
 	rcu_read_unlock();
 	return cpu;
 }
+
 /*
  * When add_timer_on() enqueues a timer into the timer wheel of an
  * idle CPU then this timer might expire before the next timer event
@@ -784,60 +787,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_task(rq, p, flags);
 }
 
-static void update_rq_clock_task(struct rq *rq, s64 delta)
-{
-/*
- * In theory, the compile should just see 0 here, and optimize out the call
- * to sched_rt_avg_update. But I don't trust it...
- */
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	s64 steal = 0, irq_delta = 0;
-#endif
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
-
-	/*
-	 * Since irq_time is only updated on {soft,}irq_exit, we might run into
-	 * this case when a previous update_rq_clock() happened inside a
-	 * {soft,}irq region.
-	 *
-	 * When this happens, we stop ->clock_task and only update the
-	 * prev_irq_time stamp to account for the part that fit, so that a next
-	 * update will consume the rest. This ensures ->clock_task is
-	 * monotonic.
-	 *
-	 * It does however cause some slight miss-attribution of {soft,}irq
-	 * time, a more accurate solution would be to update the irq_time using
-	 * the current rq->clock timestamp, except that would require using
-	 * atomic ops.
-	 */
-	if (irq_delta > delta)
-		irq_delta = delta;
-
-	rq->prev_irq_time += irq_delta;
-	delta -= irq_delta;
-#endif
-#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-	if (static_key_false((&paravirt_steal_rq_enabled))) {
-		steal = paravirt_steal_clock(cpu_of(rq));
-		steal -= rq->prev_steal_time_rq;
-
-		if (unlikely(steal > delta))
-			steal = delta;
-
-		rq->prev_steal_time_rq += steal;
-		delta -= steal;
-	}
-#endif
-
-	rq->clock_task += delta;
-
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
-		sched_rt_avg_update(rq, irq_delta + steal);
-#endif
-}
-
 void sched_set_stop_task(int cpu, struct task_struct *stop)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
@@ -1018,7 +967,7 @@ struct migration_arg {
 };
 
 /*
- * Move (not current) task off this cpu, onto dest cpu. We're doing
+ * Move (not current) task off this CPU, onto the destination CPU. We're doing
  * this because either it can't run here any more (set_cpus_allowed()
  * away from this CPU, or CPU going down), or because we're
  * attempting to rebalance this task on exec (sched_exec).
@@ -1052,8 +1001,8 @@ static int migration_cpu_stop(void *data)
 	struct rq *rq = this_rq();
 
 	/*
-	 * The original target cpu might have gone down and we might
-	 * be on another cpu but it doesn't matter.
+	 * The original target CPU might have gone down and we might
+	 * be on another CPU but it doesn't matter.
 	 */
 	local_irq_disable();
 	/*
@@ -1171,7 +1120,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	if (p->flags & PF_KTHREAD) {
 		/*
 		 * For kernel threads that do indeed end up on online &&
-		 * !active we want to ensure they are strict per-cpu threads.
+		 * !active we want to ensure they are strict per-CPU threads.
 		 */
 		WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) &&
 			!cpumask_intersects(new_mask, cpu_active_mask) &&
@@ -1195,9 +1144,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		 * OK, since we're going to drop the lock immediately
 		 * afterwards anyway.
 		 */
-		lockdep_unpin_lock(&rq->lock, rf.cookie);
+		rq_unpin_lock(rq, &rf);
 		rq = move_queued_task(rq, p, dest_cpu);
-		lockdep_repin_lock(&rq->lock, rf.cookie);
+		rq_repin_lock(rq, &rf);
 	}
 out:
 	task_rq_unlock(rq, p, &rf);
@@ -1276,7 +1225,7 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		/*
 		 * Task isn't running anymore; make it appear like we migrated
 		 * it before it went to sleep. This means on wakeup we make the
-		 * previous cpu our target instead of where it really is.
+		 * previous CPU our target instead of where it really is.
 		 */
 		p->wake_cpu = cpu;
 	}
@@ -1508,12 +1457,12 @@ EXPORT_SYMBOL_GPL(kick_process);
  *
  *  - on cpu-up we allow per-cpu kthreads on the online && !active cpu,
  *    see __set_cpus_allowed_ptr(). At this point the newly online
- *    cpu isn't yet part of the sched domains, and balancing will not
+ *    CPU isn't yet part of the sched domains, and balancing will not
  *    see it.
  *
- *  - on cpu-down we clear cpu_active() to mask the sched domains and
+ *  - on CPU-down we clear cpu_active() to mask the sched domains and
  *    avoid the load balancer to place new tasks on the to be removed
- *    cpu. Existing tasks will remain running there and will be taken
+ *    CPU. Existing tasks will remain running there and will be taken
  *    off.
  *
  * This means that fallback selection must not select !active CPUs.
@@ -1529,9 +1478,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	int dest_cpu;
 
 	/*
-	 * If the node that the cpu is on has been offlined, cpu_to_node()
-	 * will return -1. There is no cpu on the node, and we should
-	 * select the cpu on the other node.
+	 * If the node that the CPU is on has been offlined, cpu_to_node()
+	 * will return -1. There is no CPU on the node, and we should
+	 * select the CPU on the other node.
 	 */
 	if (nid != -1) {
 		nodemask = cpumask_of_node(nid);
@@ -1563,7 +1512,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 				state = possible;
 				break;
 			}
-			/* fall-through */
+			/* Fall-through */
 		case possible:
 			do_set_cpus_allowed(p, cpu_possible_mask);
 			state = fail;
@@ -1607,7 +1556,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
 	 * to rely on ttwu() to place the task on a valid ->cpus_allowed
-	 * cpu.
+	 * CPU.
 	 *
 	 * Since this is common to all placement strategies, this lives here.
 	 *
@@ -1681,7 +1630,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl
 	activate_task(rq, p, en_flags);
 	p->on_rq = TASK_ON_RQ_QUEUED;
 
-	/* if a worker is waking up, notify workqueue */
+	/* If a worker is waking up, notify the workqueue: */
 	if (p->flags & PF_WQ_WORKER)
 		wq_worker_waking_up(p, cpu_of(rq));
 }
@@ -1690,7 +1639,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl
  * Mark the task runnable and perform wakeup-preemption.
  */
 static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
-			   struct pin_cookie cookie)
+			   struct rq_flags *rf)
 {
 	check_preempt_curr(rq, p, wake_flags);
 	p->state = TASK_RUNNING;
@@ -1702,9 +1651,9 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 		 * Our task @p is fully woken up and running; so its safe to
 		 * drop the rq->lock, hereafter rq is only used for statistics.
 		 */
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq_unpin_lock(rq, rf);
 		p->sched_class->task_woken(rq, p);
-		lockdep_repin_lock(&rq->lock, cookie);
+		rq_repin_lock(rq, rf);
 	}
 
 	if (rq->idle_stamp) {
@@ -1723,7 +1672,7 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 
 static void
 ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
-		 struct pin_cookie cookie)
+		 struct rq_flags *rf)
 {
 	int en_flags = ENQUEUE_WAKEUP;
 
@@ -1738,7 +1687,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 #endif
 
 	ttwu_activate(rq, p, en_flags);
-	ttwu_do_wakeup(rq, p, wake_flags, cookie);
+	ttwu_do_wakeup(rq, p, wake_flags, rf);
 }
 
 /*
@@ -1757,7 +1706,7 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 	if (task_on_rq_queued(p)) {
 		/* check_preempt_curr() may use rq clock */
 		update_rq_clock(rq);
-		ttwu_do_wakeup(rq, p, wake_flags, rf.cookie);
+		ttwu_do_wakeup(rq, p, wake_flags, &rf);
 		ret = 1;
 	}
 	__task_rq_unlock(rq, &rf);
@@ -1770,15 +1719,15 @@ void sched_ttwu_pending(void)
 {
 	struct rq *rq = this_rq();
 	struct llist_node *llist = llist_del_all(&rq->wake_list);
-	struct pin_cookie cookie;
 	struct task_struct *p;
 	unsigned long flags;
+	struct rq_flags rf;
 
 	if (!llist)
 		return;
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
-	cookie = lockdep_pin_lock(&rq->lock);
+	rq_pin_lock(rq, &rf);
 
 	while (llist) {
 		int wake_flags = 0;
@@ -1789,10 +1738,10 @@ void sched_ttwu_pending(void)
 		if (p->sched_remote_wakeup)
 			wake_flags = WF_MIGRATED;
 
-		ttwu_do_activate(rq, p, wake_flags, cookie);
+		ttwu_do_activate(rq, p, wake_flags, &rf);
 	}
 
-	lockdep_unpin_lock(&rq->lock, cookie);
+	rq_unpin_lock(rq, &rf);
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
@@ -1864,7 +1813,7 @@ void wake_up_if_idle(int cpu)
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (is_idle_task(rq->curr))
 			smp_send_reschedule(cpu);
-		/* Else cpu is not in idle, do nothing here */
+		/* Else CPU is not idle, do nothing here: */
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}
 
@@ -1881,20 +1830,20 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct pin_cookie cookie;
+	struct rq_flags rf;
 
 #if defined(CONFIG_SMP)
 	if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
-		sched_clock_cpu(cpu); /* sync clocks x-cpu */
+		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
 		ttwu_queue_remote(p, cpu, wake_flags);
 		return;
 	}
 #endif
 
 	raw_spin_lock(&rq->lock);
-	cookie = lockdep_pin_lock(&rq->lock);
-	ttwu_do_activate(rq, p, wake_flags, cookie);
-	lockdep_unpin_lock(&rq->lock, cookie);
+	rq_pin_lock(rq, &rf);
+	ttwu_do_activate(rq, p, wake_flags, &rf);
+	rq_unpin_lock(rq, &rf);
 	raw_spin_unlock(&rq->lock);
 }
 
@@ -1904,8 +1853,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *  MIGRATION
  *
  * The basic program-order guarantee on SMP systems is that when a task [t]
- * migrates, all its activity on its old cpu [c0] happens-before any subsequent
- * execution on its new cpu [c1].
+ * migrates, all its activity on its old CPU [c0] happens-before any subsequent
+ * execution on its new CPU [c1].
  *
  * For migration (of runnable tasks) this is provided by the following means:
  *
@@ -1916,7 +1865,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *
  * Transitivity guarantees that B happens after A and C after B.
  * Note: we only require RCpc transitivity.
- * Note: the cpu doing B need not be c0 or c1
+ * Note: the CPU doing B need not be c0 or c1
  *
  * Example:
  *
@@ -2024,7 +1973,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	trace_sched_waking(p);
 
-	success = 1; /* we're going to change ->state */
+	/* We're going to change ->state: */
+	success = 1;
 	cpu = task_cpu(p);
 
 	/*
@@ -2073,7 +2023,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	smp_rmb();
 
 	/*
-	 * If the owning (remote) cpu is still in the middle of schedule() with
+	 * If the owning (remote) CPU is still in the middle of schedule() with
 	 * this task as prev, wait until its done referencing the task.
 	 *
 	 * Pairs with the smp_store_release() in finish_lock_switch().
@@ -2086,11 +2036,24 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	p->sched_contributes_to_load = !!task_contributes_to_load(p);
 	p->state = TASK_WAKING;
 
+	if (p->in_iowait) {
+		delayacct_blkio_end();
+		atomic_dec(&task_rq(p)->nr_iowait);
+	}
+
 	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
 		set_task_cpu(p, cpu);
 	}
+
+#else /* CONFIG_SMP */
+
+	if (p->in_iowait) {
+		delayacct_blkio_end();
+		atomic_dec(&task_rq(p)->nr_iowait);
+	}
+
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu, wake_flags);
@@ -2111,7 +2074,7 @@ out:
  * ensure that this_rq() is locked, @p is bound to this_rq() and not
  * the current task.
  */
-static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie)
+static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
 {
 	struct rq *rq = task_rq(p);
 
@@ -2128,11 +2091,11 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie
 		 * disabled avoiding further scheduler activity on it and we've
 		 * not yet picked a replacement task.
 		 */
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq_unpin_lock(rq, rf);
 		raw_spin_unlock(&rq->lock);
 		raw_spin_lock(&p->pi_lock);
 		raw_spin_lock(&rq->lock);
-		lockdep_repin_lock(&rq->lock, cookie);
+		rq_repin_lock(rq, rf);
 	}
 
 	if (!(p->state & TASK_NORMAL))
@@ -2140,10 +2103,15 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie
 
 	trace_sched_waking(p);
 
-	if (!task_on_rq_queued(p))
+	if (!task_on_rq_queued(p)) {
+		if (p->in_iowait) {
+			delayacct_blkio_end();
+			atomic_dec(&rq->nr_iowait);
+		}
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+	}
 
-	ttwu_do_wakeup(rq, p, 0, cookie);
+	ttwu_do_wakeup(rq, p, 0, rf);
 	ttwu_stat(p, smp_processor_id(), 0);
 out:
 	raw_spin_unlock(&p->pi_lock);
@@ -2427,7 +2395,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	/*
-	 * We're setting the cpu for the first time, we don't migrate,
+	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
 	 */
 	__set_task_cpu(p, cpu);
@@ -2570,7 +2538,7 @@ void wake_up_new_task(struct task_struct *p)
 	/*
 	 * Fork balancing, do it here and not earlier because:
 	 *  - cpus_allowed can change in the fork path
-	 *  - any previously selected cpu might disappear through hotplug
+	 *  - any previously selected CPU might disappear through hotplug
 	 *
 	 * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
 	 * as we're not fully set-up yet.
@@ -2578,6 +2546,7 @@ void wake_up_new_task(struct task_struct *p)
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
+	update_rq_clock(rq);
 	post_init_entity_util_avg(&p->se);
 
 	activate_task(rq, p, 0);
@@ -2590,9 +2559,9 @@ void wake_up_new_task(struct task_struct *p)
 		 * Nothing relies on rq->lock after this, so its fine to
 		 * drop it.
 		 */
-		lockdep_unpin_lock(&rq->lock, rf.cookie);
+		rq_unpin_lock(rq, &rf);
 		p->sched_class->task_woken(rq, p);
-		lockdep_repin_lock(&rq->lock, rf.cookie);
+		rq_repin_lock(rq, &rf);
 	}
 #endif
 	task_rq_unlock(rq, p, &rf);
@@ -2861,7 +2830,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
  */
 static __always_inline struct rq *
 context_switch(struct rq *rq, struct task_struct *prev,
-	       struct task_struct *next, struct pin_cookie cookie)
+	       struct task_struct *next, struct rq_flags *rf)
 {
 	struct mm_struct *mm, *oldmm;
 
@@ -2887,13 +2856,16 @@ context_switch(struct rq *rq, struct task_struct *prev,
 		prev->active_mm = NULL;
 		rq->prev_mm = oldmm;
 	}
+
+	rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
+
 	/*
 	 * Since the runqueue lock will be released by the next
 	 * task (which is an invalid locking op but in the case
 	 * of the scheduler it's an obvious special-case), so we
 	 * do an early lockdep release here:
 	 */
-	lockdep_unpin_lock(&rq->lock, cookie);
+	rq_unpin_lock(rq, rf);
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 
 	/* Here we just switch the register state and the stack. */
@@ -2920,7 +2892,7 @@ unsigned long nr_running(void)
 }
 
 /*
- * Check if only the current task is running on the cpu.
+ * Check if only the current task is running on the CPU.
  *
  * Caution: this function does not check that the caller has disabled
  * preemption, thus the result might have a time-of-check-to-time-of-use
@@ -2949,6 +2921,36 @@ unsigned long long nr_context_switches(void)
 	return sum;
 }
 
+/*
+ * IO-wait accounting, and how its mostly bollocks (on SMP).
+ *
+ * The idea behind IO-wait account is to account the idle time that we could
+ * have spend running if it were not for IO. That is, if we were to improve the
+ * storage performance, we'd have a proportional reduction in IO-wait time.
+ *
+ * This all works nicely on UP, where, when a task blocks on IO, we account
+ * idle time as IO-wait, because if the storage were faster, it could've been
+ * running and we'd not be idle.
+ *
+ * This has been extended to SMP, by doing the same for each CPU. This however
+ * is broken.
+ *
+ * Imagine for instance the case where two tasks block on one CPU, only the one
+ * CPU will have IO-wait accounted, while the other has regular idle. Even
+ * though, if the storage were faster, both could've ran at the same time,
+ * utilising both CPUs.
+ *
+ * This means, that when looking globally, the current IO-wait accounting on
+ * SMP is a lower bound, by reason of under accounting.
+ *
+ * Worse, since the numbers are provided per CPU, they are sometimes
+ * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
+ * associated with any one particular CPU, it can wake to another CPU than it
+ * blocked on. This means the per CPU IO-wait number is meaningless.
+ *
+ * Task CPU affinities can make all that even more 'interesting'.
+ */
+
 unsigned long nr_iowait(void)
 {
 	unsigned long i, sum = 0;
@@ -2959,6 +2961,13 @@ unsigned long nr_iowait(void)
 	return sum;
 }
 
+/*
+ * Consumers of these two interfaces, like for example the cpufreq menu
+ * governor are using nonsensical data. Boosting frequency for a CPU that has
+ * IO-wait which might not even end up running the task when it does become
+ * runnable.
+ */
+
 unsigned long nr_iowait_cpu(int cpu)
 {
 	struct rq *this = cpu_rq(cpu);
@@ -3042,8 +3051,8 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	 * So we have a optimization chance when the task's delta_exec is 0.
 	 * Reading ->on_cpu is racy, but this is ok.
 	 *
-	 * If we race with it leaving cpu, we'll take a lock. So we're correct.
-	 * If we race with it entering cpu, unaccounted time is 0. This is
+	 * If we race with it leaving CPU, we'll take a lock. So we're correct.
+	 * If we race with it entering CPU, unaccounted time is 0. This is
 	 * indistinguishable from the read occurring a few cycles earlier.
 	 * If we see ->on_cpu without ->on_rq, the task is leaving, and has
 	 * been accounted, so we're correct here as well.
@@ -3257,31 +3266,30 @@ static inline void schedule_debug(struct task_struct *prev)
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	const struct sched_class *class = &fair_sched_class;
+	const struct sched_class *class;
 	struct task_struct *p;
 
 	/*
 	 * Optimization: we know that if all tasks are in
 	 * the fair class we can call that function directly:
 	 */
-	if (likely(prev->sched_class == class &&
-		   rq->nr_running == rq->cfs.h_nr_running)) {
-		p = fair_sched_class.pick_next_task(rq, prev, cookie);
+	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
+		p = fair_sched_class.pick_next_task(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
 			goto again;
 
-		/* assumes fair_sched_class->next == idle_sched_class */
+		/* Assumes fair_sched_class->next == idle_sched_class */
 		if (unlikely(!p))
-			p = idle_sched_class.pick_next_task(rq, prev, cookie);
+			p = idle_sched_class.pick_next_task(rq, prev, rf);
 
 		return p;
 	}
 
 again:
 	for_each_class(class) {
-		p = class->pick_next_task(rq, prev, cookie);
+		p = class->pick_next_task(rq, prev, rf);
 		if (p) {
 			if (unlikely(p == RETRY_TASK))
 				goto again;
@@ -3289,7 +3297,8 @@ again:
 		}
 	}
 
-	BUG(); /* the idle class will always have a runnable task */
+	/* The idle class should always have a runnable task: */
+	BUG();
 }
 
 /*
@@ -3335,7 +3344,7 @@ static void __sched notrace __schedule(bool preempt)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
-	struct pin_cookie cookie;
+	struct rq_flags rf;
 	struct rq *rq;
 	int cpu;
 
@@ -3358,9 +3367,10 @@ static void __sched notrace __schedule(bool preempt)
 	 */
 	smp_mb__before_spinlock();
 	raw_spin_lock(&rq->lock);
-	cookie = lockdep_pin_lock(&rq->lock);
+	rq_pin_lock(rq, &rf);
 
-	rq->clock_skip_update <<= 1; /* promote REQ to ACT */
+	/* Promote REQ to ACT */
+	rq->clock_update_flags <<= 1;
 
 	switch_count = &prev->nivcsw;
 	if (!preempt && prev->state) {
@@ -3370,6 +3380,11 @@ static void __sched notrace __schedule(bool preempt)
 			deactivate_task(rq, prev, DEQUEUE_SLEEP);
 			prev->on_rq = 0;
 
+			if (prev->in_iowait) {
+				atomic_inc(&rq->nr_iowait);
+				delayacct_blkio_start();
+			}
+
 			/*
 			 * If a worker went to sleep, notify and ask workqueue
 			 * whether it wants to wake up a task to maintain
@@ -3380,7 +3395,7 @@ static void __sched notrace __schedule(bool preempt)
 
 				to_wakeup = wq_worker_sleeping(prev);
 				if (to_wakeup)
-					try_to_wake_up_local(to_wakeup, cookie);
+					try_to_wake_up_local(to_wakeup, &rf);
 			}
 		}
 		switch_count = &prev->nvcsw;
@@ -3389,10 +3404,9 @@ static void __sched notrace __schedule(bool preempt)
 	if (task_on_rq_queued(prev))
 		update_rq_clock(rq);
 
-	next = pick_next_task(rq, prev, cookie);
+	next = pick_next_task(rq, prev, &rf);
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
-	rq->clock_skip_update = 0;
 
 	if (likely(prev != next)) {
 		rq->nr_switches++;
@@ -3400,9 +3414,12 @@ static void __sched notrace __schedule(bool preempt)
 		++*switch_count;
 
 		trace_sched_switch(preempt, prev, next);
-		rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */
+
+		/* Also unlocks the rq: */
+		rq = context_switch(rq, prev, next, &rf);
 	} else {
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
+		rq_unpin_lock(rq, &rf);
 		raw_spin_unlock_irq(&rq->lock);
 	}
 
@@ -3426,14 +3443,18 @@ void __noreturn do_task_dead(void)
 	smp_mb();
 	raw_spin_unlock_wait(&current->pi_lock);
 
-	/* causes final put_task_struct in finish_task_switch(). */
+	/* Causes final put_task_struct in finish_task_switch(): */
 	__set_current_state(TASK_DEAD);
-	current->flags |= PF_NOFREEZE;	/* tell freezer to ignore us */
+
+	/* Tell freezer to ignore us: */
+	current->flags |= PF_NOFREEZE;
+
 	__schedule(false);
 	BUG();
-	/* Avoid "noreturn function does return".  */
+
+	/* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
 	for (;;)
-		cpu_relax();	/* For when BUG is null */
+		cpu_relax();
 }
 
 static inline void sched_submit_work(struct task_struct *tsk)
@@ -3651,6 +3672,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 	BUG_ON(prio > MAX_PRIO);
 
 	rq = __task_rq_lock(p, &rf);
+	update_rq_clock(rq);
 
 	/*
 	 * Idle task boosting is a nono in general. There is one
@@ -3725,7 +3747,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
 	check_class_changed(rq, p, prev_class, oldprio);
 out_unlock:
-	preempt_disable(); /* avoid rq from going away on us */
+	/* Avoid rq from going away on us: */
+	preempt_disable();
 	__task_rq_unlock(rq, &rf);
 
 	balance_callback(rq);
@@ -3747,6 +3770,8 @@ void set_user_nice(struct task_struct *p, long nice)
 	 * the task might be in the middle of scheduling on another CPU.
 	 */
 	rq = task_rq_lock(p, &rf);
+	update_rq_clock(rq);
+
 	/*
 	 * The RT priorities are set via sched_setscheduler(), but we still
 	 * allow the 'normal' nice value to be set - but as expected
@@ -3793,7 +3818,7 @@ EXPORT_SYMBOL(set_user_nice);
  */
 int can_nice(const struct task_struct *p, const int nice)
 {
-	/* convert nice value [19,-20] to rlimit style value [1,40] */
+	/* Convert nice value [19,-20] to rlimit style value [1,40]: */
 	int nice_rlim = nice_to_rlimit(nice);
 
 	return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
@@ -3849,7 +3874,7 @@ int task_prio(const struct task_struct *p)
 }
 
 /**
- * idle_cpu - is a given cpu idle currently?
+ * idle_cpu - is a given CPU idle currently?
  * @cpu: the processor in question.
  *
  * Return: 1 if the CPU is currently idle. 0 otherwise.
@@ -3873,10 +3898,10 @@ int idle_cpu(int cpu)
 }
 
 /**
- * idle_task - return the idle task for a given cpu.
+ * idle_task - return the idle task for a given CPU.
  * @cpu: the processor in question.
  *
- * Return: The idle task for the cpu @cpu.
+ * Return: The idle task for the CPU @cpu.
  */
 struct task_struct *idle_task(int cpu)
 {
@@ -4042,7 +4067,7 @@ __checkparam_dl(const struct sched_attr *attr)
 }
 
 /*
- * check the target process has a UID that matches the current process's
+ * Check the target process has a UID that matches the current process's:
  */
 static bool check_same_owner(struct task_struct *p)
 {
@@ -4057,8 +4082,7 @@ static bool check_same_owner(struct task_struct *p)
 	return match;
 }
 
-static bool dl_param_changed(struct task_struct *p,
-		const struct sched_attr *attr)
+static bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
 
@@ -4085,10 +4109,10 @@ static int __sched_setscheduler(struct task_struct *p,
 	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
 	struct rq *rq;
 
-	/* may grab non-irq protected spin_locks */
+	/* May grab non-irq protected spin_locks: */
 	BUG_ON(in_interrupt());
 recheck:
-	/* double check policy once rq lock held */
+	/* Double check policy once rq lock held: */
 	if (policy < 0) {
 		reset_on_fork = p->sched_reset_on_fork;
 		policy = oldpolicy = p->policy;
@@ -4128,11 +4152,11 @@ recheck:
 			unsigned long rlim_rtprio =
 					task_rlimit(p, RLIMIT_RTPRIO);
 
-			/* can't set/change the rt policy */
+			/* Can't set/change the rt policy: */
 			if (policy != p->policy && !rlim_rtprio)
 				return -EPERM;
 
-			/* can't increase priority */
+			/* Can't increase priority: */
 			if (attr->sched_priority > p->rt_priority &&
 			    attr->sched_priority > rlim_rtprio)
 				return -EPERM;
@@ -4156,11 +4180,11 @@ recheck:
 				return -EPERM;
 		}
 
-		/* can't change other user's priorities */
+		/* Can't change other user's priorities: */
 		if (!check_same_owner(p))
 			return -EPERM;
 
-		/* Normal users shall not reset the sched_reset_on_fork flag */
+		/* Normal users shall not reset the sched_reset_on_fork flag: */
 		if (p->sched_reset_on_fork && !reset_on_fork)
 			return -EPERM;
 	}
@@ -4172,16 +4196,17 @@ recheck:
 	}
 
 	/*
-	 * make sure no PI-waiters arrive (or leave) while we are
+	 * Make sure no PI-waiters arrive (or leave) while we are
 	 * changing the priority of the task:
 	 *
 	 * To be able to change p->policy safely, the appropriate
 	 * runqueue lock must be held.
 	 */
 	rq = task_rq_lock(p, &rf);
+	update_rq_clock(rq);
 
 	/*
-	 * Changing the policy of the stop threads its a very bad idea
+	 * Changing the policy of the stop threads its a very bad idea:
 	 */
 	if (p == rq->stop) {
 		task_rq_unlock(rq, p, &rf);
@@ -4237,7 +4262,7 @@ change:
 #endif
 	}
 
-	/* recheck policy now with rq lock held */
+	/* Re-check policy now with rq lock held: */
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
 		policy = oldpolicy = -1;
 		task_rq_unlock(rq, p, &rf);
@@ -4294,15 +4319,15 @@ change:
 		set_curr_task(rq, p);
 
 	check_class_changed(rq, p, prev_class, oldprio);
-	preempt_disable(); /* avoid rq from going away on us */
+
+	/* Avoid rq from going away on us: */
+	preempt_disable();
 	task_rq_unlock(rq, p, &rf);
 
 	if (pi)
 		rt_mutex_adjust_pi(p);
 
-	/*
-	 * Run balance callbacks after we've adjusted the PI chain.
-	 */
+	/* Run balance callbacks after we've adjusted the PI chain: */
 	balance_callback(rq);
 	preempt_enable();
 
@@ -4395,8 +4420,7 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 /*
  * Mimics kernel/events/core.c perf_copy_attr().
  */
-static int sched_copy_attr(struct sched_attr __user *uattr,
-			   struct sched_attr *attr)
+static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr)
 {
 	u32 size;
 	int ret;
@@ -4404,19 +4428,19 @@ static int sched_copy_attr(struct sched_attr __user *uattr,
 	if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0))
 		return -EFAULT;
 
-	/*
-	 * zero the full structure, so that a short copy will be nice.
-	 */
+	/* Zero the full structure, so that a short copy will be nice: */
 	memset(attr, 0, sizeof(*attr));
 
 	ret = get_user(size, &uattr->size);
 	if (ret)
 		return ret;
 
-	if (size > PAGE_SIZE)	/* silly large */
+	/* Bail out on silly large: */
+	if (size > PAGE_SIZE)
 		goto err_size;
 
-	if (!size)		/* abi compat */
+	/* ABI compatibility quirk: */
+	if (!size)
 		size = SCHED_ATTR_SIZE_VER0;
 
 	if (size < SCHED_ATTR_SIZE_VER0)
@@ -4451,7 +4475,7 @@ static int sched_copy_attr(struct sched_attr __user *uattr,
 		return -EFAULT;
 
 	/*
-	 * XXX: do we want to be lenient like existing syscalls; or do we want
+	 * XXX: Do we want to be lenient like existing syscalls; or do we want
 	 * to be strict and return an error on out-of-bounds values?
 	 */
 	attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE);
@@ -4471,10 +4495,8 @@ err_size:
  *
  * Return: 0 on success. An error code otherwise.
  */
-SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
-		struct sched_param __user *, param)
+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
 {
-	/* negative values for policy are not valid */
 	if (policy < 0)
 		return -EINVAL;
 
@@ -4784,10 +4806,10 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
 }
 
 /**
- * sys_sched_setaffinity - set the cpu affinity of a process
+ * sys_sched_setaffinity - set the CPU affinity of a process
  * @pid: pid of the process
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
- * @user_mask_ptr: user-space pointer to the new cpu mask
+ * @user_mask_ptr: user-space pointer to the new CPU mask
  *
  * Return: 0 on success. An error code otherwise.
  */
@@ -4835,10 +4857,10 @@ out_unlock:
 }
 
 /**
- * sys_sched_getaffinity - get the cpu affinity of a process
+ * sys_sched_getaffinity - get the CPU affinity of a process
  * @pid: pid of the process
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
- * @user_mask_ptr: user-space pointer to hold the current cpu mask
+ * @user_mask_ptr: user-space pointer to hold the current CPU mask
  *
  * Return: size of CPU mask copied to user_mask_ptr on success. An
  * error code otherwise.
@@ -4966,7 +4988,7 @@ EXPORT_SYMBOL(__cond_resched_softirq);
  * Typical broken usage is:
  *
  * while (!event)
- * 	yield();
+ *	yield();
  *
  * where one assumes that yield() will let 'the other' process run that will
  * make event true. If the current task is a SCHED_FIFO task that will never
@@ -5057,31 +5079,48 @@ out_irq:
 }
 EXPORT_SYMBOL_GPL(yield_to);
 
+int io_schedule_prepare(void)
+{
+	int old_iowait = current->in_iowait;
+
+	current->in_iowait = 1;
+	blk_schedule_flush_plug(current);
+
+	return old_iowait;
+}
+
+void io_schedule_finish(int token)
+{
+	current->in_iowait = token;
+}
+
 /*
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
  */
 long __sched io_schedule_timeout(long timeout)
 {
-	int old_iowait = current->in_iowait;
-	struct rq *rq;
+	int token;
 	long ret;
 
-	current->in_iowait = 1;
-	blk_schedule_flush_plug(current);
-
-	delayacct_blkio_start();
-	rq = raw_rq();
-	atomic_inc(&rq->nr_iowait);
+	token = io_schedule_prepare();
 	ret = schedule_timeout(timeout);
-	current->in_iowait = old_iowait;
-	atomic_dec(&rq->nr_iowait);
-	delayacct_blkio_end();
+	io_schedule_finish(token);
 
 	return ret;
 }
 EXPORT_SYMBOL(io_schedule_timeout);
 
+void io_schedule(void)
+{
+	int token;
+
+	token = io_schedule_prepare();
+	schedule();
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL(io_schedule);
+
 /**
  * sys_sched_get_priority_max - return maximum RT priority.
  * @policy: scheduling class.
@@ -5264,7 +5303,7 @@ void init_idle_bootup_task(struct task_struct *idle)
 /**
  * init_idle - set up an idle thread for a given CPU
  * @idle: task in question
- * @cpu: cpu the idle task belongs to
+ * @cpu: CPU the idle task belongs to
  *
  * NOTE: this function does not set the idle thread's NEED_RESCHED
  * flag, to make booting more robust.
@@ -5295,7 +5334,7 @@ void init_idle(struct task_struct *idle, int cpu)
 #endif
 	/*
 	 * We're having a chicken and egg problem, even though we are
-	 * holding rq->lock, the cpu isn't yet set to this cpu so the
+	 * holding rq->lock, the CPU isn't yet set to this CPU so the
 	 * lockdep check in task_group() will fail.
 	 *
 	 * Similar case to sched_fork(). / Alternatively we could
@@ -5360,7 +5399,7 @@ int task_can_attach(struct task_struct *p,
 
 	/*
 	 * Kthreads which disallow setaffinity shouldn't be moved
-	 * to a new cpuset; we don't want to change their cpu
+	 * to a new cpuset; we don't want to change their CPU
 	 * affinity and isolating such threads by their set of
 	 * allowed nodes is unnecessary.  Thus, cpusets are not
 	 * applicable for such threads.  This prevents checking for
@@ -5409,7 +5448,7 @@ out:
 
 #ifdef CONFIG_SMP
 
-static bool sched_smp_initialized __read_mostly;
+bool sched_smp_initialized __read_mostly;
 
 #ifdef CONFIG_NUMA_BALANCING
 /* Migrate current task p to target_cpu */
@@ -5461,7 +5500,7 @@ void sched_setnuma(struct task_struct *p, int nid)
 
 #ifdef CONFIG_HOTPLUG_CPU
 /*
- * Ensures that the idle task is using init_mm right before its cpu goes
+ * Ensure that the idle task is using init_mm right before its CPU goes
  * offline.
  */
 void idle_task_exit(void)
@@ -5521,7 +5560,7 @@ static void migrate_tasks(struct rq *dead_rq)
 {
 	struct rq *rq = dead_rq;
 	struct task_struct *next, *stop = rq->stop;
-	struct pin_cookie cookie;
+	struct rq_flags rf, old_rf;
 	int dest_cpu;
 
 	/*
@@ -5545,16 +5584,16 @@ static void migrate_tasks(struct rq *dead_rq)
 	for (;;) {
 		/*
 		 * There's this thread running, bail when that's the only
-		 * remaining thread.
+		 * remaining thread:
 		 */
 		if (rq->nr_running == 1)
 			break;
 
 		/*
-		 * pick_next_task assumes pinned rq->lock.
+		 * pick_next_task() assumes pinned rq->lock:
 		 */
-		cookie = lockdep_pin_lock(&rq->lock);
-		next = pick_next_task(rq, &fake_task, cookie);
+		rq_pin_lock(rq, &rf);
+		next = pick_next_task(rq, &fake_task, &rf);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 
@@ -5567,7 +5606,7 @@ static void migrate_tasks(struct rq *dead_rq)
 		 * because !cpu_active at this point, which means load-balance
 		 * will not interfere. Also, stop-machine.
 		 */
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq_unpin_lock(rq, &rf);
 		raw_spin_unlock(&rq->lock);
 		raw_spin_lock(&next->pi_lock);
 		raw_spin_lock(&rq->lock);
@@ -5582,6 +5621,13 @@ static void migrate_tasks(struct rq *dead_rq)
 			continue;
 		}
 
+		/*
+		 * __migrate_task() may return with a different
+		 * rq->lock held and a new cookie in 'rf', but we need
+		 * to preserve rf::clock_update_flags for 'dead_rq'.
+		 */
+		old_rf = rf;
+
 		/* Find suitable destination for @next, with force if needed. */
 		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
 
@@ -5590,6 +5636,7 @@ static void migrate_tasks(struct rq *dead_rq)
 			raw_spin_unlock(&rq->lock);
 			rq = dead_rq;
 			raw_spin_lock(&rq->lock);
+			rf = old_rf;
 		}
 		raw_spin_unlock(&next->pi_lock);
 	}
@@ -5598,7 +5645,7 @@ static void migrate_tasks(struct rq *dead_rq)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static void set_rq_online(struct rq *rq)
+void set_rq_online(struct rq *rq)
 {
 	if (!rq->online) {
 		const struct sched_class *class;
@@ -5613,7 +5660,7 @@ static void set_rq_online(struct rq *rq)
 	}
 }
 
-static void set_rq_offline(struct rq *rq)
+void set_rq_offline(struct rq *rq)
 {
 	if (rq->online) {
 		const struct sched_class *class;
@@ -5635,1647 +5682,10 @@ static void set_cpu_rq_start_time(unsigned int cpu)
 	rq->age_stamp = sched_clock_cpu(cpu);
 }
 
-static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
-
-#ifdef CONFIG_SCHED_DEBUG
-
-static __read_mostly int sched_debug_enabled;
-
-static int __init sched_debug_setup(char *str)
-{
-	sched_debug_enabled = 1;
-
-	return 0;
-}
-early_param("sched_debug", sched_debug_setup);
-
-static inline bool sched_debug(void)
-{
-	return sched_debug_enabled;
-}
-
-static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
-				  struct cpumask *groupmask)
-{
-	struct sched_group *group = sd->groups;
-
-	cpumask_clear(groupmask);
-
-	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
-
-	if (!(sd->flags & SD_LOAD_BALANCE)) {
-		printk("does not load-balance\n");
-		if (sd->parent)
-			printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
-					" has parent");
-		return -1;
-	}
-
-	printk(KERN_CONT "span %*pbl level %s\n",
-	       cpumask_pr_args(sched_domain_span(sd)), sd->name);
-
-	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
-		printk(KERN_ERR "ERROR: domain->span does not contain "
-				"CPU%d\n", cpu);
-	}
-	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
-		printk(KERN_ERR "ERROR: domain->groups does not contain"
-				" CPU%d\n", cpu);
-	}
-
-	printk(KERN_DEBUG "%*s groups:", level + 1, "");
-	do {
-		if (!group) {
-			printk("\n");
-			printk(KERN_ERR "ERROR: group is NULL\n");
-			break;
-		}
-
-		if (!cpumask_weight(sched_group_cpus(group))) {
-			printk(KERN_CONT "\n");
-			printk(KERN_ERR "ERROR: empty group\n");
-			break;
-		}
-
-		if (!(sd->flags & SD_OVERLAP) &&
-		    cpumask_intersects(groupmask, sched_group_cpus(group))) {
-			printk(KERN_CONT "\n");
-			printk(KERN_ERR "ERROR: repeated CPUs\n");
-			break;
-		}
-
-		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
-
-		printk(KERN_CONT " %*pbl",
-		       cpumask_pr_args(sched_group_cpus(group)));
-		if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
-			printk(KERN_CONT " (cpu_capacity = %lu)",
-				group->sgc->capacity);
-		}
-
-		group = group->next;
-	} while (group != sd->groups);
-	printk(KERN_CONT "\n");
-
-	if (!cpumask_equal(sched_domain_span(sd), groupmask))
-		printk(KERN_ERR "ERROR: groups don't span domain->span\n");
-
-	if (sd->parent &&
-	    !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
-		printk(KERN_ERR "ERROR: parent span is not a superset "
-			"of domain->span\n");
-	return 0;
-}
-
-static void sched_domain_debug(struct sched_domain *sd, int cpu)
-{
-	int level = 0;
-
-	if (!sched_debug_enabled)
-		return;
-
-	if (!sd) {
-		printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
-		return;
-	}
-
-	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
-
-	for (;;) {
-		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
-			break;
-		level++;
-		sd = sd->parent;
-		if (!sd)
-			break;
-	}
-}
-#else /* !CONFIG_SCHED_DEBUG */
-
-# define sched_debug_enabled 0
-# define sched_domain_debug(sd, cpu) do { } while (0)
-static inline bool sched_debug(void)
-{
-	return false;
-}
-#endif /* CONFIG_SCHED_DEBUG */
-
-static int sd_degenerate(struct sched_domain *sd)
-{
-	if (cpumask_weight(sched_domain_span(sd)) == 1)
-		return 1;
-
-	/* Following flags need at least 2 groups */
-	if (sd->flags & (SD_LOAD_BALANCE |
-			 SD_BALANCE_NEWIDLE |
-			 SD_BALANCE_FORK |
-			 SD_BALANCE_EXEC |
-			 SD_SHARE_CPUCAPACITY |
-			 SD_ASYM_CPUCAPACITY |
-			 SD_SHARE_PKG_RESOURCES |
-			 SD_SHARE_POWERDOMAIN)) {
-		if (sd->groups != sd->groups->next)
-			return 0;
-	}
-
-	/* Following flags don't use groups */
-	if (sd->flags & (SD_WAKE_AFFINE))
-		return 0;
-
-	return 1;
-}
-
-static int
-sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
-{
-	unsigned long cflags = sd->flags, pflags = parent->flags;
-
-	if (sd_degenerate(parent))
-		return 1;
-
-	if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
-		return 0;
-
-	/* Flags needing groups don't count if only 1 group in parent */
-	if (parent->groups == parent->groups->next) {
-		pflags &= ~(SD_LOAD_BALANCE |
-				SD_BALANCE_NEWIDLE |
-				SD_BALANCE_FORK |
-				SD_BALANCE_EXEC |
-				SD_ASYM_CPUCAPACITY |
-				SD_SHARE_CPUCAPACITY |
-				SD_SHARE_PKG_RESOURCES |
-				SD_PREFER_SIBLING |
-				SD_SHARE_POWERDOMAIN);
-		if (nr_node_ids == 1)
-			pflags &= ~SD_SERIALIZE;
-	}
-	if (~cflags & pflags)
-		return 0;
-
-	return 1;
-}
-
-static void free_rootdomain(struct rcu_head *rcu)
-{
-	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
-
-	cpupri_cleanup(&rd->cpupri);
-	cpudl_cleanup(&rd->cpudl);
-	free_cpumask_var(rd->dlo_mask);
-	free_cpumask_var(rd->rto_mask);
-	free_cpumask_var(rd->online);
-	free_cpumask_var(rd->span);
-	kfree(rd);
-}
-
-static void rq_attach_root(struct rq *rq, struct root_domain *rd)
-{
-	struct root_domain *old_rd = NULL;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&rq->lock, flags);
-
-	if (rq->rd) {
-		old_rd = rq->rd;
-
-		if (cpumask_test_cpu(rq->cpu, old_rd->online))
-			set_rq_offline(rq);
-
-		cpumask_clear_cpu(rq->cpu, old_rd->span);
-
-		/*
-		 * If we dont want to free the old_rd yet then
-		 * set old_rd to NULL to skip the freeing later
-		 * in this function:
-		 */
-		if (!atomic_dec_and_test(&old_rd->refcount))
-			old_rd = NULL;
-	}
-
-	atomic_inc(&rd->refcount);
-	rq->rd = rd;
-
-	cpumask_set_cpu(rq->cpu, rd->span);
-	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
-		set_rq_online(rq);
-
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
-
-	if (old_rd)
-		call_rcu_sched(&old_rd->rcu, free_rootdomain);
-}
-
-static int init_rootdomain(struct root_domain *rd)
-{
-	memset(rd, 0, sizeof(*rd));
-
-	if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
-		goto out;
-	if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
-		goto free_span;
-	if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
-		goto free_online;
-	if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
-		goto free_dlo_mask;
-
-	init_dl_bw(&rd->dl_bw);
-	if (cpudl_init(&rd->cpudl) != 0)
-		goto free_dlo_mask;
-
-	if (cpupri_init(&rd->cpupri) != 0)
-		goto free_rto_mask;
-	return 0;
-
-free_rto_mask:
-	free_cpumask_var(rd->rto_mask);
-free_dlo_mask:
-	free_cpumask_var(rd->dlo_mask);
-free_online:
-	free_cpumask_var(rd->online);
-free_span:
-	free_cpumask_var(rd->span);
-out:
-	return -ENOMEM;
-}
-
 /*
- * By default the system creates a single root-domain with all cpus as
- * members (mimicking the global state we have today).
+ * used to mark begin/end of suspend/resume:
  */
-struct root_domain def_root_domain;
-
-static void init_defrootdomain(void)
-{
-	init_rootdomain(&def_root_domain);
-
-	atomic_set(&def_root_domain.refcount, 1);
-}
-
-static struct root_domain *alloc_rootdomain(void)
-{
-	struct root_domain *rd;
-
-	rd = kmalloc(sizeof(*rd), GFP_KERNEL);
-	if (!rd)
-		return NULL;
-
-	if (init_rootdomain(rd) != 0) {
-		kfree(rd);
-		return NULL;
-	}
-
-	return rd;
-}
-
-static void free_sched_groups(struct sched_group *sg, int free_sgc)
-{
-	struct sched_group *tmp, *first;
-
-	if (!sg)
-		return;
-
-	first = sg;
-	do {
-		tmp = sg->next;
-
-		if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
-			kfree(sg->sgc);
-
-		kfree(sg);
-		sg = tmp;
-	} while (sg != first);
-}
-
-static void destroy_sched_domain(struct sched_domain *sd)
-{
-	/*
-	 * If its an overlapping domain it has private groups, iterate and
-	 * nuke them all.
-	 */
-	if (sd->flags & SD_OVERLAP) {
-		free_sched_groups(sd->groups, 1);
-	} else if (atomic_dec_and_test(&sd->groups->ref)) {
-		kfree(sd->groups->sgc);
-		kfree(sd->groups);
-	}
-	if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
-		kfree(sd->shared);
-	kfree(sd);
-}
-
-static void destroy_sched_domains_rcu(struct rcu_head *rcu)
-{
-	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
-
-	while (sd) {
-		struct sched_domain *parent = sd->parent;
-		destroy_sched_domain(sd);
-		sd = parent;
-	}
-}
-
-static void destroy_sched_domains(struct sched_domain *sd)
-{
-	if (sd)
-		call_rcu(&sd->rcu, destroy_sched_domains_rcu);
-}
-
-/*
- * Keep a special pointer to the highest sched_domain that has
- * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
- * allows us to avoid some pointer chasing select_idle_sibling().
- *
- * Also keep a unique ID per domain (we use the first cpu number in
- * the cpumask of the domain), this allows us to quickly tell if
- * two cpus are in the same cache domain, see cpus_share_cache().
- */
-DEFINE_PER_CPU(struct sched_domain *, sd_llc);
-DEFINE_PER_CPU(int, sd_llc_size);
-DEFINE_PER_CPU(int, sd_llc_id);
-DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym);
-
-static void update_top_cache_domain(int cpu)
-{
-	struct sched_domain_shared *sds = NULL;
-	struct sched_domain *sd;
-	int id = cpu;
-	int size = 1;
-
-	sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
-	if (sd) {
-		id = cpumask_first(sched_domain_span(sd));
-		size = cpumask_weight(sched_domain_span(sd));
-		sds = sd->shared;
-	}
-
-	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
-	per_cpu(sd_llc_size, cpu) = size;
-	per_cpu(sd_llc_id, cpu) = id;
-	rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
-
-	sd = lowest_flag_domain(cpu, SD_NUMA);
-	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
-
-	sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
-	rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
-}
-
-/*
- * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
- * hold the hotplug lock.
- */
-static void
-cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-	struct sched_domain *tmp;
-
-	/* Remove the sched domains which do not contribute to scheduling. */
-	for (tmp = sd; tmp; ) {
-		struct sched_domain *parent = tmp->parent;
-		if (!parent)
-			break;
-
-		if (sd_parent_degenerate(tmp, parent)) {
-			tmp->parent = parent->parent;
-			if (parent->parent)
-				parent->parent->child = tmp;
-			/*
-			 * Transfer SD_PREFER_SIBLING down in case of a
-			 * degenerate parent; the spans match for this
-			 * so the property transfers.
-			 */
-			if (parent->flags & SD_PREFER_SIBLING)
-				tmp->flags |= SD_PREFER_SIBLING;
-			destroy_sched_domain(parent);
-		} else
-			tmp = tmp->parent;
-	}
-
-	if (sd && sd_degenerate(sd)) {
-		tmp = sd;
-		sd = sd->parent;
-		destroy_sched_domain(tmp);
-		if (sd)
-			sd->child = NULL;
-	}
-
-	sched_domain_debug(sd, cpu);
-
-	rq_attach_root(rq, rd);
-	tmp = rq->sd;
-	rcu_assign_pointer(rq->sd, sd);
-	destroy_sched_domains(tmp);
-
-	update_top_cache_domain(cpu);
-}
-
-/* Setup the mask of cpus configured for isolated domains */
-static int __init isolated_cpu_setup(char *str)
-{
-	int ret;
-
-	alloc_bootmem_cpumask_var(&cpu_isolated_map);
-	ret = cpulist_parse(str, cpu_isolated_map);
-	if (ret) {
-		pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids);
-		return 0;
-	}
-	return 1;
-}
-__setup("isolcpus=", isolated_cpu_setup);
-
-struct s_data {
-	struct sched_domain ** __percpu sd;
-	struct root_domain	*rd;
-};
-
-enum s_alloc {
-	sa_rootdomain,
-	sa_sd,
-	sa_sd_storage,
-	sa_none,
-};
-
-/*
- * Build an iteration mask that can exclude certain CPUs from the upwards
- * domain traversal.
- *
- * Asymmetric node setups can result in situations where the domain tree is of
- * unequal depth, make sure to skip domains that already cover the entire
- * range.
- *
- * In that case build_sched_domains() will have terminated the iteration early
- * and our sibling sd spans will be empty. Domains should always include the
- * cpu they're built on, so check that.
- *
- */
-static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
-{
-	const struct cpumask *span = sched_domain_span(sd);
-	struct sd_data *sdd = sd->private;
-	struct sched_domain *sibling;
-	int i;
-
-	for_each_cpu(i, span) {
-		sibling = *per_cpu_ptr(sdd->sd, i);
-		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
-			continue;
-
-		cpumask_set_cpu(i, sched_group_mask(sg));
-	}
-}
-
-/*
- * Return the canonical balance cpu for this group, this is the first cpu
- * of this group that's also in the iteration mask.
- */
-int group_balance_cpu(struct sched_group *sg)
-{
-	return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
-}
-
-static int
-build_overlap_sched_groups(struct sched_domain *sd, int cpu)
-{
-	struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
-	const struct cpumask *span = sched_domain_span(sd);
-	struct cpumask *covered = sched_domains_tmpmask;
-	struct sd_data *sdd = sd->private;
-	struct sched_domain *sibling;
-	int i;
-
-	cpumask_clear(covered);
-
-	for_each_cpu(i, span) {
-		struct cpumask *sg_span;
-
-		if (cpumask_test_cpu(i, covered))
-			continue;
-
-		sibling = *per_cpu_ptr(sdd->sd, i);
-
-		/* See the comment near build_group_mask(). */
-		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
-			continue;
-
-		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
-				GFP_KERNEL, cpu_to_node(cpu));
-
-		if (!sg)
-			goto fail;
-
-		sg_span = sched_group_cpus(sg);
-		if (sibling->child)
-			cpumask_copy(sg_span, sched_domain_span(sibling->child));
-		else
-			cpumask_set_cpu(i, sg_span);
-
-		cpumask_or(covered, covered, sg_span);
-
-		sg->sgc = *per_cpu_ptr(sdd->sgc, i);
-		if (atomic_inc_return(&sg->sgc->ref) == 1)
-			build_group_mask(sd, sg);
-
-		/*
-		 * Initialize sgc->capacity such that even if we mess up the
-		 * domains and no possible iteration will get us here, we won't
-		 * die on a /0 trap.
-		 */
-		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
-		sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
-
-		/*
-		 * Make sure the first group of this domain contains the
-		 * canonical balance cpu. Otherwise the sched_domain iteration
-		 * breaks. See update_sg_lb_stats().
-		 */
-		if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
-		    group_balance_cpu(sg) == cpu)
-			groups = sg;
-
-		if (!first)
-			first = sg;
-		if (last)
-			last->next = sg;
-		last = sg;
-		last->next = first;
-	}
-	sd->groups = groups;
-
-	return 0;
-
-fail:
-	free_sched_groups(first, 0);
-
-	return -ENOMEM;
-}
-
-static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
-{
-	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
-	struct sched_domain *child = sd->child;
-
-	if (child)
-		cpu = cpumask_first(sched_domain_span(child));
-
-	if (sg) {
-		*sg = *per_cpu_ptr(sdd->sg, cpu);
-		(*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
-		atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */
-	}
-
-	return cpu;
-}
-
-/*
- * build_sched_groups will build a circular linked list of the groups
- * covered by the given span, and will set each group's ->cpumask correctly,
- * and ->cpu_capacity to 0.
- *
- * Assumes the sched_domain tree is fully constructed
- */
-static int
-build_sched_groups(struct sched_domain *sd, int cpu)
-{
-	struct sched_group *first = NULL, *last = NULL;
-	struct sd_data *sdd = sd->private;
-	const struct cpumask *span = sched_domain_span(sd);
-	struct cpumask *covered;
-	int i;
-
-	get_group(cpu, sdd, &sd->groups);
-	atomic_inc(&sd->groups->ref);
-
-	if (cpu != cpumask_first(span))
-		return 0;
-
-	lockdep_assert_held(&sched_domains_mutex);
-	covered = sched_domains_tmpmask;
-
-	cpumask_clear(covered);
-
-	for_each_cpu(i, span) {
-		struct sched_group *sg;
-		int group, j;
-
-		if (cpumask_test_cpu(i, covered))
-			continue;
-
-		group = get_group(i, sdd, &sg);
-		cpumask_setall(sched_group_mask(sg));
-
-		for_each_cpu(j, span) {
-			if (get_group(j, sdd, NULL) != group)
-				continue;
-
-			cpumask_set_cpu(j, covered);
-			cpumask_set_cpu(j, sched_group_cpus(sg));
-		}
-
-		if (!first)
-			first = sg;
-		if (last)
-			last->next = sg;
-		last = sg;
-	}
-	last->next = first;
-
-	return 0;
-}
-
-/*
- * Initialize sched groups cpu_capacity.
- *
- * cpu_capacity indicates the capacity of sched group, which is used while
- * distributing the load between different sched groups in a sched domain.
- * Typically cpu_capacity for all the groups in a sched domain will be same
- * unless there are asymmetries in the topology. If there are asymmetries,
- * group having more cpu_capacity will pickup more load compared to the
- * group having less cpu_capacity.
- */
-static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
-{
-	struct sched_group *sg = sd->groups;
-
-	WARN_ON(!sg);
-
-	do {
-		int cpu, max_cpu = -1;
-
-		sg->group_weight = cpumask_weight(sched_group_cpus(sg));
-
-		if (!(sd->flags & SD_ASYM_PACKING))
-			goto next;
-
-		for_each_cpu(cpu, sched_group_cpus(sg)) {
-			if (max_cpu < 0)
-				max_cpu = cpu;
-			else if (sched_asym_prefer(cpu, max_cpu))
-				max_cpu = cpu;
-		}
-		sg->asym_prefer_cpu = max_cpu;
-
-next:
-		sg = sg->next;
-	} while (sg != sd->groups);
-
-	if (cpu != group_balance_cpu(sg))
-		return;
-
-	update_group_capacity(sd, cpu);
-}
-
-/*
- * Initializers for schedule domains
- * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
- */
-
-static int default_relax_domain_level = -1;
-int sched_domain_level_max;
-
-static int __init setup_relax_domain_level(char *str)
-{
-	if (kstrtoint(str, 0, &default_relax_domain_level))
-		pr_warn("Unable to set relax_domain_level\n");
-
-	return 1;
-}
-__setup("relax_domain_level=", setup_relax_domain_level);
-
-static void set_domain_attribute(struct sched_domain *sd,
-				 struct sched_domain_attr *attr)
-{
-	int request;
-
-	if (!attr || attr->relax_domain_level < 0) {
-		if (default_relax_domain_level < 0)
-			return;
-		else
-			request = default_relax_domain_level;
-	} else
-		request = attr->relax_domain_level;
-	if (request < sd->level) {
-		/* turn off idle balance on this domain */
-		sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
-	} else {
-		/* turn on idle balance on this domain */
-		sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
-	}
-}
-
-static void __sdt_free(const struct cpumask *cpu_map);
-static int __sdt_alloc(const struct cpumask *cpu_map);
-
-static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
-				 const struct cpumask *cpu_map)
-{
-	switch (what) {
-	case sa_rootdomain:
-		if (!atomic_read(&d->rd->refcount))
-			free_rootdomain(&d->rd->rcu); /* fall through */
-	case sa_sd:
-		free_percpu(d->sd); /* fall through */
-	case sa_sd_storage:
-		__sdt_free(cpu_map); /* fall through */
-	case sa_none:
-		break;
-	}
-}
-
-static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
-						   const struct cpumask *cpu_map)
-{
-	memset(d, 0, sizeof(*d));
-
-	if (__sdt_alloc(cpu_map))
-		return sa_sd_storage;
-	d->sd = alloc_percpu(struct sched_domain *);
-	if (!d->sd)
-		return sa_sd_storage;
-	d->rd = alloc_rootdomain();
-	if (!d->rd)
-		return sa_sd;
-	return sa_rootdomain;
-}
-
-/*
- * NULL the sd_data elements we've used to build the sched_domain and
- * sched_group structure so that the subsequent __free_domain_allocs()
- * will not free the data we're using.
- */
-static void claim_allocations(int cpu, struct sched_domain *sd)
-{
-	struct sd_data *sdd = sd->private;
-
-	WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
-	*per_cpu_ptr(sdd->sd, cpu) = NULL;
-
-	if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref))
-		*per_cpu_ptr(sdd->sds, cpu) = NULL;
-
-	if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
-		*per_cpu_ptr(sdd->sg, cpu) = NULL;
-
-	if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref))
-		*per_cpu_ptr(sdd->sgc, cpu) = NULL;
-}
-
-#ifdef CONFIG_NUMA
-static int sched_domains_numa_levels;
-enum numa_topology_type sched_numa_topology_type;
-static int *sched_domains_numa_distance;
-int sched_max_numa_distance;
-static struct cpumask ***sched_domains_numa_masks;
-static int sched_domains_curr_level;
-#endif
-
-/*
- * SD_flags allowed in topology descriptions.
- *
- * These flags are purely descriptive of the topology and do not prescribe
- * behaviour. Behaviour is artificial and mapped in the below sd_init()
- * function:
- *
- *   SD_SHARE_CPUCAPACITY   - describes SMT topologies
- *   SD_SHARE_PKG_RESOURCES - describes shared caches
- *   SD_NUMA                - describes NUMA topologies
- *   SD_SHARE_POWERDOMAIN   - describes shared power domain
- *   SD_ASYM_CPUCAPACITY    - describes mixed capacity topologies
- *
- * Odd one out, which beside describing the topology has a quirk also
- * prescribes the desired behaviour that goes along with it:
- *
- *   SD_ASYM_PACKING        - describes SMT quirks
- */
-#define TOPOLOGY_SD_FLAGS		\
-	(SD_SHARE_CPUCAPACITY |		\
-	 SD_SHARE_PKG_RESOURCES |	\
-	 SD_NUMA |			\
-	 SD_ASYM_PACKING |		\
-	 SD_ASYM_CPUCAPACITY |		\
-	 SD_SHARE_POWERDOMAIN)
-
-static struct sched_domain *
-sd_init(struct sched_domain_topology_level *tl,
-	const struct cpumask *cpu_map,
-	struct sched_domain *child, int cpu)
-{
-	struct sd_data *sdd = &tl->data;
-	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
-	int sd_id, sd_weight, sd_flags = 0;
-
-#ifdef CONFIG_NUMA
-	/*
-	 * Ugly hack to pass state to sd_numa_mask()...
-	 */
-	sched_domains_curr_level = tl->numa_level;
-#endif
-
-	sd_weight = cpumask_weight(tl->mask(cpu));
-
-	if (tl->sd_flags)
-		sd_flags = (*tl->sd_flags)();
-	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
-			"wrong sd_flags in topology description\n"))
-		sd_flags &= ~TOPOLOGY_SD_FLAGS;
-
-	*sd = (struct sched_domain){
-		.min_interval		= sd_weight,
-		.max_interval		= 2*sd_weight,
-		.busy_factor		= 32,
-		.imbalance_pct		= 125,
-
-		.cache_nice_tries	= 0,
-		.busy_idx		= 0,
-		.idle_idx		= 0,
-		.newidle_idx		= 0,
-		.wake_idx		= 0,
-		.forkexec_idx		= 0,
-
-		.flags			= 1*SD_LOAD_BALANCE
-					| 1*SD_BALANCE_NEWIDLE
-					| 1*SD_BALANCE_EXEC
-					| 1*SD_BALANCE_FORK
-					| 0*SD_BALANCE_WAKE
-					| 1*SD_WAKE_AFFINE
-					| 0*SD_SHARE_CPUCAPACITY
-					| 0*SD_SHARE_PKG_RESOURCES
-					| 0*SD_SERIALIZE
-					| 0*SD_PREFER_SIBLING
-					| 0*SD_NUMA
-					| sd_flags
-					,
-
-		.last_balance		= jiffies,
-		.balance_interval	= sd_weight,
-		.smt_gain		= 0,
-		.max_newidle_lb_cost	= 0,
-		.next_decay_max_lb_cost	= jiffies,
-		.child			= child,
-#ifdef CONFIG_SCHED_DEBUG
-		.name			= tl->name,
-#endif
-	};
-
-	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
-	sd_id = cpumask_first(sched_domain_span(sd));
-
-	/*
-	 * Convert topological properties into behaviour.
-	 */
-
-	if (sd->flags & SD_ASYM_CPUCAPACITY) {
-		struct sched_domain *t = sd;
-
-		for_each_lower_domain(t)
-			t->flags |= SD_BALANCE_WAKE;
-	}
-
-	if (sd->flags & SD_SHARE_CPUCAPACITY) {
-		sd->flags |= SD_PREFER_SIBLING;
-		sd->imbalance_pct = 110;
-		sd->smt_gain = 1178; /* ~15% */
-
-	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
-		sd->imbalance_pct = 117;
-		sd->cache_nice_tries = 1;
-		sd->busy_idx = 2;
-
-#ifdef CONFIG_NUMA
-	} else if (sd->flags & SD_NUMA) {
-		sd->cache_nice_tries = 2;
-		sd->busy_idx = 3;
-		sd->idle_idx = 2;
-
-		sd->flags |= SD_SERIALIZE;
-		if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
-			sd->flags &= ~(SD_BALANCE_EXEC |
-				       SD_BALANCE_FORK |
-				       SD_WAKE_AFFINE);
-		}
-
-#endif
-	} else {
-		sd->flags |= SD_PREFER_SIBLING;
-		sd->cache_nice_tries = 1;
-		sd->busy_idx = 2;
-		sd->idle_idx = 1;
-	}
-
-	/*
-	 * For all levels sharing cache; connect a sched_domain_shared
-	 * instance.
-	 */
-	if (sd->flags & SD_SHARE_PKG_RESOURCES) {
-		sd->shared = *per_cpu_ptr(sdd->sds, sd_id);
-		atomic_inc(&sd->shared->ref);
-		atomic_set(&sd->shared->nr_busy_cpus, sd_weight);
-	}
-
-	sd->private = sdd;
-
-	return sd;
-}
-
-/*
- * Topology list, bottom-up.
- */
-static struct sched_domain_topology_level default_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
-#endif
-#ifdef CONFIG_SCHED_MC
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
-#endif
-	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
-	{ NULL, },
-};
-
-static struct sched_domain_topology_level *sched_domain_topology =
-	default_topology;
-
-#define for_each_sd_topology(tl)			\
-	for (tl = sched_domain_topology; tl->mask; tl++)
-
-void set_sched_topology(struct sched_domain_topology_level *tl)
-{
-	if (WARN_ON_ONCE(sched_smp_initialized))
-		return;
-
-	sched_domain_topology = tl;
-}
-
-#ifdef CONFIG_NUMA
-
-static const struct cpumask *sd_numa_mask(int cpu)
-{
-	return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
-}
-
-static void sched_numa_warn(const char *str)
-{
-	static int done = false;
-	int i,j;
-
-	if (done)
-		return;
-
-	done = true;
-
-	printk(KERN_WARNING "ERROR: %s\n\n", str);
-
-	for (i = 0; i < nr_node_ids; i++) {
-		printk(KERN_WARNING "  ");
-		for (j = 0; j < nr_node_ids; j++)
-			printk(KERN_CONT "%02d ", node_distance(i,j));
-		printk(KERN_CONT "\n");
-	}
-	printk(KERN_WARNING "\n");
-}
-
-bool find_numa_distance(int distance)
-{
-	int i;
-
-	if (distance == node_distance(0, 0))
-		return true;
-
-	for (i = 0; i < sched_domains_numa_levels; i++) {
-		if (sched_domains_numa_distance[i] == distance)
-			return true;
-	}
-
-	return false;
-}
-
-/*
- * A system can have three types of NUMA topology:
- * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system
- * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes
- * NUMA_BACKPLANE: nodes can reach other nodes through a backplane
- *
- * The difference between a glueless mesh topology and a backplane
- * topology lies in whether communication between not directly
- * connected nodes goes through intermediary nodes (where programs
- * could run), or through backplane controllers. This affects
- * placement of programs.
- *
- * The type of topology can be discerned with the following tests:
- * - If the maximum distance between any nodes is 1 hop, the system
- *   is directly connected.
- * - If for two nodes A and B, located N > 1 hops away from each other,
- *   there is an intermediary node C, which is < N hops away from both
- *   nodes A and B, the system is a glueless mesh.
- */
-static void init_numa_topology_type(void)
-{
-	int a, b, c, n;
-
-	n = sched_max_numa_distance;
-
-	if (sched_domains_numa_levels <= 1) {
-		sched_numa_topology_type = NUMA_DIRECT;
-		return;
-	}
-
-	for_each_online_node(a) {
-		for_each_online_node(b) {
-			/* Find two nodes furthest removed from each other. */
-			if (node_distance(a, b) < n)
-				continue;
-
-			/* Is there an intermediary node between a and b? */
-			for_each_online_node(c) {
-				if (node_distance(a, c) < n &&
-				    node_distance(b, c) < n) {
-					sched_numa_topology_type =
-							NUMA_GLUELESS_MESH;
-					return;
-				}
-			}
-
-			sched_numa_topology_type = NUMA_BACKPLANE;
-			return;
-		}
-	}
-}
-
-static void sched_init_numa(void)
-{
-	int next_distance, curr_distance = node_distance(0, 0);
-	struct sched_domain_topology_level *tl;
-	int level = 0;
-	int i, j, k;
-
-	sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
-	if (!sched_domains_numa_distance)
-		return;
-
-	/*
-	 * O(nr_nodes^2) deduplicating selection sort -- in order to find the
-	 * unique distances in the node_distance() table.
-	 *
-	 * Assumes node_distance(0,j) includes all distances in
-	 * node_distance(i,j) in order to avoid cubic time.
-	 */
-	next_distance = curr_distance;
-	for (i = 0; i < nr_node_ids; i++) {
-		for (j = 0; j < nr_node_ids; j++) {
-			for (k = 0; k < nr_node_ids; k++) {
-				int distance = node_distance(i, k);
-
-				if (distance > curr_distance &&
-				    (distance < next_distance ||
-				     next_distance == curr_distance))
-					next_distance = distance;
-
-				/*
-				 * While not a strong assumption it would be nice to know
-				 * about cases where if node A is connected to B, B is not
-				 * equally connected to A.
-				 */
-				if (sched_debug() && node_distance(k, i) != distance)
-					sched_numa_warn("Node-distance not symmetric");
-
-				if (sched_debug() && i && !find_numa_distance(distance))
-					sched_numa_warn("Node-0 not representative");
-			}
-			if (next_distance != curr_distance) {
-				sched_domains_numa_distance[level++] = next_distance;
-				sched_domains_numa_levels = level;
-				curr_distance = next_distance;
-			} else break;
-		}
-
-		/*
-		 * In case of sched_debug() we verify the above assumption.
-		 */
-		if (!sched_debug())
-			break;
-	}
-
-	if (!level)
-		return;
-
-	/*
-	 * 'level' contains the number of unique distances, excluding the
-	 * identity distance node_distance(i,i).
-	 *
-	 * The sched_domains_numa_distance[] array includes the actual distance
-	 * numbers.
-	 */
-
-	/*
-	 * Here, we should temporarily reset sched_domains_numa_levels to 0.
-	 * If it fails to allocate memory for array sched_domains_numa_masks[][],
-	 * the array will contain less then 'level' members. This could be
-	 * dangerous when we use it to iterate array sched_domains_numa_masks[][]
-	 * in other functions.
-	 *
-	 * We reset it to 'level' at the end of this function.
-	 */
-	sched_domains_numa_levels = 0;
-
-	sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
-	if (!sched_domains_numa_masks)
-		return;
-
-	/*
-	 * Now for each level, construct a mask per node which contains all
-	 * cpus of nodes that are that many hops away from us.
-	 */
-	for (i = 0; i < level; i++) {
-		sched_domains_numa_masks[i] =
-			kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
-		if (!sched_domains_numa_masks[i])
-			return;
-
-		for (j = 0; j < nr_node_ids; j++) {
-			struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
-			if (!mask)
-				return;
-
-			sched_domains_numa_masks[i][j] = mask;
-
-			for_each_node(k) {
-				if (node_distance(j, k) > sched_domains_numa_distance[i])
-					continue;
-
-				cpumask_or(mask, mask, cpumask_of_node(k));
-			}
-		}
-	}
-
-	/* Compute default topology size */
-	for (i = 0; sched_domain_topology[i].mask; i++);
-
-	tl = kzalloc((i + level + 1) *
-			sizeof(struct sched_domain_topology_level), GFP_KERNEL);
-	if (!tl)
-		return;
-
-	/*
-	 * Copy the default topology bits..
-	 */
-	for (i = 0; sched_domain_topology[i].mask; i++)
-		tl[i] = sched_domain_topology[i];
-
-	/*
-	 * .. and append 'j' levels of NUMA goodness.
-	 */
-	for (j = 0; j < level; i++, j++) {
-		tl[i] = (struct sched_domain_topology_level){
-			.mask = sd_numa_mask,
-			.sd_flags = cpu_numa_flags,
-			.flags = SDTL_OVERLAP,
-			.numa_level = j,
-			SD_INIT_NAME(NUMA)
-		};
-	}
-
-	sched_domain_topology = tl;
-
-	sched_domains_numa_levels = level;
-	sched_max_numa_distance = sched_domains_numa_distance[level - 1];
-
-	init_numa_topology_type();
-}
-
-static void sched_domains_numa_masks_set(unsigned int cpu)
-{
-	int node = cpu_to_node(cpu);
-	int i, j;
-
-	for (i = 0; i < sched_domains_numa_levels; i++) {
-		for (j = 0; j < nr_node_ids; j++) {
-			if (node_distance(j, node) <= sched_domains_numa_distance[i])
-				cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
-		}
-	}
-}
-
-static void sched_domains_numa_masks_clear(unsigned int cpu)
-{
-	int i, j;
-
-	for (i = 0; i < sched_domains_numa_levels; i++) {
-		for (j = 0; j < nr_node_ids; j++)
-			cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
-	}
-}
-
-#else
-static inline void sched_init_numa(void) { }
-static void sched_domains_numa_masks_set(unsigned int cpu) { }
-static void sched_domains_numa_masks_clear(unsigned int cpu) { }
-#endif /* CONFIG_NUMA */
-
-static int __sdt_alloc(const struct cpumask *cpu_map)
-{
-	struct sched_domain_topology_level *tl;
-	int j;
-
-	for_each_sd_topology(tl) {
-		struct sd_data *sdd = &tl->data;
-
-		sdd->sd = alloc_percpu(struct sched_domain *);
-		if (!sdd->sd)
-			return -ENOMEM;
-
-		sdd->sds = alloc_percpu(struct sched_domain_shared *);
-		if (!sdd->sds)
-			return -ENOMEM;
-
-		sdd->sg = alloc_percpu(struct sched_group *);
-		if (!sdd->sg)
-			return -ENOMEM;
-
-		sdd->sgc = alloc_percpu(struct sched_group_capacity *);
-		if (!sdd->sgc)
-			return -ENOMEM;
-
-		for_each_cpu(j, cpu_map) {
-			struct sched_domain *sd;
-			struct sched_domain_shared *sds;
-			struct sched_group *sg;
-			struct sched_group_capacity *sgc;
-
-			sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
-					GFP_KERNEL, cpu_to_node(j));
-			if (!sd)
-				return -ENOMEM;
-
-			*per_cpu_ptr(sdd->sd, j) = sd;
-
-			sds = kzalloc_node(sizeof(struct sched_domain_shared),
-					GFP_KERNEL, cpu_to_node(j));
-			if (!sds)
-				return -ENOMEM;
-
-			*per_cpu_ptr(sdd->sds, j) = sds;
-
-			sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
-					GFP_KERNEL, cpu_to_node(j));
-			if (!sg)
-				return -ENOMEM;
-
-			sg->next = sg;
-
-			*per_cpu_ptr(sdd->sg, j) = sg;
-
-			sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(),
-					GFP_KERNEL, cpu_to_node(j));
-			if (!sgc)
-				return -ENOMEM;
-
-			*per_cpu_ptr(sdd->sgc, j) = sgc;
-		}
-	}
-
-	return 0;
-}
-
-static void __sdt_free(const struct cpumask *cpu_map)
-{
-	struct sched_domain_topology_level *tl;
-	int j;
-
-	for_each_sd_topology(tl) {
-		struct sd_data *sdd = &tl->data;
-
-		for_each_cpu(j, cpu_map) {
-			struct sched_domain *sd;
-
-			if (sdd->sd) {
-				sd = *per_cpu_ptr(sdd->sd, j);
-				if (sd && (sd->flags & SD_OVERLAP))
-					free_sched_groups(sd->groups, 0);
-				kfree(*per_cpu_ptr(sdd->sd, j));
-			}
-
-			if (sdd->sds)
-				kfree(*per_cpu_ptr(sdd->sds, j));
-			if (sdd->sg)
-				kfree(*per_cpu_ptr(sdd->sg, j));
-			if (sdd->sgc)
-				kfree(*per_cpu_ptr(sdd->sgc, j));
-		}
-		free_percpu(sdd->sd);
-		sdd->sd = NULL;
-		free_percpu(sdd->sds);
-		sdd->sds = NULL;
-		free_percpu(sdd->sg);
-		sdd->sg = NULL;
-		free_percpu(sdd->sgc);
-		sdd->sgc = NULL;
-	}
-}
-
-struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
-		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
-		struct sched_domain *child, int cpu)
-{
-	struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu);
-
-	if (child) {
-		sd->level = child->level + 1;
-		sched_domain_level_max = max(sched_domain_level_max, sd->level);
-		child->parent = sd;
-
-		if (!cpumask_subset(sched_domain_span(child),
-				    sched_domain_span(sd))) {
-			pr_err("BUG: arch topology borken\n");
-#ifdef CONFIG_SCHED_DEBUG
-			pr_err("     the %s domain not a subset of the %s domain\n",
-					child->name, sd->name);
-#endif
-			/* Fixup, ensure @sd has at least @child cpus. */
-			cpumask_or(sched_domain_span(sd),
-				   sched_domain_span(sd),
-				   sched_domain_span(child));
-		}
-
-	}
-	set_domain_attribute(sd, attr);
-
-	return sd;
-}
-
-/*
- * Build sched domains for a given set of cpus and attach the sched domains
- * to the individual cpus
- */
-static int build_sched_domains(const struct cpumask *cpu_map,
-			       struct sched_domain_attr *attr)
-{
-	enum s_alloc alloc_state;
-	struct sched_domain *sd;
-	struct s_data d;
-	struct rq *rq = NULL;
-	int i, ret = -ENOMEM;
-
-	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
-	if (alloc_state != sa_rootdomain)
-		goto error;
-
-	/* Set up domains for cpus specified by the cpu_map. */
-	for_each_cpu(i, cpu_map) {
-		struct sched_domain_topology_level *tl;
-
-		sd = NULL;
-		for_each_sd_topology(tl) {
-			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
-			if (tl == sched_domain_topology)
-				*per_cpu_ptr(d.sd, i) = sd;
-			if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
-				sd->flags |= SD_OVERLAP;
-			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
-				break;
-		}
-	}
-
-	/* Build the groups for the domains */
-	for_each_cpu(i, cpu_map) {
-		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
-			sd->span_weight = cpumask_weight(sched_domain_span(sd));
-			if (sd->flags & SD_OVERLAP) {
-				if (build_overlap_sched_groups(sd, i))
-					goto error;
-			} else {
-				if (build_sched_groups(sd, i))
-					goto error;
-			}
-		}
-	}
-
-	/* Calculate CPU capacity for physical packages and nodes */
-	for (i = nr_cpumask_bits-1; i >= 0; i--) {
-		if (!cpumask_test_cpu(i, cpu_map))
-			continue;
-
-		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
-			claim_allocations(i, sd);
-			init_sched_groups_capacity(i, sd);
-		}
-	}
-
-	/* Attach the domains */
-	rcu_read_lock();
-	for_each_cpu(i, cpu_map) {
-		rq = cpu_rq(i);
-		sd = *per_cpu_ptr(d.sd, i);
-
-		/* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
-		if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
-			WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
-
-		cpu_attach_domain(sd, d.rd, i);
-	}
-	rcu_read_unlock();
-
-	if (rq && sched_debug_enabled) {
-		pr_info("span: %*pbl (max cpu_capacity = %lu)\n",
-			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
-	}
-
-	ret = 0;
-error:
-	__free_domain_allocs(&d, alloc_state, cpu_map);
-	return ret;
-}
-
-static cpumask_var_t *doms_cur;	/* current sched domains */
-static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
-static struct sched_domain_attr *dattr_cur;
-				/* attribues of custom domains in 'doms_cur' */
-
-/*
- * Special case: If a kmalloc of a doms_cur partition (array of
- * cpumask) fails, then fallback to a single sched domain,
- * as determined by the single cpumask fallback_doms.
- */
-static cpumask_var_t fallback_doms;
-
-/*
- * arch_update_cpu_topology lets virtualized architectures update the
- * cpu core maps. It is supposed to return 1 if the topology changed
- * or 0 if it stayed the same.
- */
-int __weak arch_update_cpu_topology(void)
-{
-	return 0;
-}
-
-cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
-{
-	int i;
-	cpumask_var_t *doms;
-
-	doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
-	if (!doms)
-		return NULL;
-	for (i = 0; i < ndoms; i++) {
-		if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
-			free_sched_domains(doms, i);
-			return NULL;
-		}
-	}
-	return doms;
-}
-
-void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
-{
-	unsigned int i;
-	for (i = 0; i < ndoms; i++)
-		free_cpumask_var(doms[i]);
-	kfree(doms);
-}
-
-/*
- * Set up scheduler domains and groups. Callers must hold the hotplug lock.
- * For now this just excludes isolated cpus, but could be used to
- * exclude other special cases in the future.
- */
-static int init_sched_domains(const struct cpumask *cpu_map)
-{
-	int err;
-
-	arch_update_cpu_topology();
-	ndoms_cur = 1;
-	doms_cur = alloc_sched_domains(ndoms_cur);
-	if (!doms_cur)
-		doms_cur = &fallback_doms;
-	cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
-	err = build_sched_domains(doms_cur[0], NULL);
-	register_sched_domain_sysctl();
-
-	return err;
-}
-
-/*
- * Detach sched domains from a group of cpus specified in cpu_map
- * These cpus will now be attached to the NULL domain
- */
-static void detach_destroy_domains(const struct cpumask *cpu_map)
-{
-	int i;
-
-	rcu_read_lock();
-	for_each_cpu(i, cpu_map)
-		cpu_attach_domain(NULL, &def_root_domain, i);
-	rcu_read_unlock();
-}
-
-/* handle null as "default" */
-static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
-			struct sched_domain_attr *new, int idx_new)
-{
-	struct sched_domain_attr tmp;
-
-	/* fast path */
-	if (!new && !cur)
-		return 1;
-
-	tmp = SD_ATTR_INIT;
-	return !memcmp(cur ? (cur + idx_cur) : &tmp,
-			new ? (new + idx_new) : &tmp,
-			sizeof(struct sched_domain_attr));
-}
-
-/*
- * Partition sched domains as specified by the 'ndoms_new'
- * cpumasks in the array doms_new[] of cpumasks. This compares
- * doms_new[] to the current sched domain partitioning, doms_cur[].
- * It destroys each deleted domain and builds each new domain.
- *
- * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
- * The masks don't intersect (don't overlap.) We should setup one
- * sched domain for each mask. CPUs not in any of the cpumasks will
- * not be load balanced. If the same cpumask appears both in the
- * current 'doms_cur' domains and in the new 'doms_new', we can leave
- * it as it is.
- *
- * The passed in 'doms_new' should be allocated using
- * alloc_sched_domains.  This routine takes ownership of it and will
- * free_sched_domains it when done with it. If the caller failed the
- * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
- * and partition_sched_domains() will fallback to the single partition
- * 'fallback_doms', it also forces the domains to be rebuilt.
- *
- * If doms_new == NULL it will be replaced with cpu_online_mask.
- * ndoms_new == 0 is a special case for destroying existing domains,
- * and it will not create the default domain.
- *
- * Call with hotplug lock held
- */
-void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-			     struct sched_domain_attr *dattr_new)
-{
-	int i, j, n;
-	int new_topology;
-
-	mutex_lock(&sched_domains_mutex);
-
-	/* always unregister in case we don't destroy any domains */
-	unregister_sched_domain_sysctl();
-
-	/* Let architecture update cpu core mappings. */
-	new_topology = arch_update_cpu_topology();
-
-	n = doms_new ? ndoms_new : 0;
-
-	/* Destroy deleted domains */
-	for (i = 0; i < ndoms_cur; i++) {
-		for (j = 0; j < n && !new_topology; j++) {
-			if (cpumask_equal(doms_cur[i], doms_new[j])
-			    && dattrs_equal(dattr_cur, i, dattr_new, j))
-				goto match1;
-		}
-		/* no match - a current sched domain not in new doms_new[] */
-		detach_destroy_domains(doms_cur[i]);
-match1:
-		;
-	}
-
-	n = ndoms_cur;
-	if (doms_new == NULL) {
-		n = 0;
-		doms_new = &fallback_doms;
-		cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
-		WARN_ON_ONCE(dattr_new);
-	}
-
-	/* Build new domains */
-	for (i = 0; i < ndoms_new; i++) {
-		for (j = 0; j < n && !new_topology; j++) {
-			if (cpumask_equal(doms_new[i], doms_cur[j])
-			    && dattrs_equal(dattr_new, i, dattr_cur, j))
-				goto match2;
-		}
-		/* no match - add a new doms_new */
-		build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
-match2:
-		;
-	}
-
-	/* Remember the new sched domains */
-	if (doms_cur != &fallback_doms)
-		free_sched_domains(doms_cur, ndoms_cur);
-	kfree(dattr_cur);	/* kfree(NULL) is safe */
-	doms_cur = doms_new;
-	dattr_cur = dattr_new;
-	ndoms_cur = ndoms_new;
-
-	register_sched_domain_sysctl();
-
-	mutex_unlock(&sched_domains_mutex);
-}
-
-static int num_cpus_frozen;	/* used to mark begin/end of suspend/resume */
+static int num_cpus_frozen;
 
 /*
  * Update cpusets according to cpu_active mask.  If cpusets are
@@ -7352,7 +5762,7 @@ int sched_cpu_activate(unsigned int cpu)
 	 * Put the rq online, if not already. This happens:
 	 *
 	 * 1) In the early boot process, because we build the real domains
-	 *    after all cpus have been brought up.
+	 *    after all CPUs have been brought up.
 	 *
 	 * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
 	 *    domains.
@@ -7467,7 +5877,7 @@ void __init sched_init_smp(void)
 
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
-	 * cpu masks are stable and all blatant races in the below code cannot
+	 * CPU masks are stable and all blatant races in the below code cannot
 	 * happen.
 	 */
 	mutex_lock(&sched_domains_mutex);
@@ -7487,6 +5897,7 @@ void __init sched_init_smp(void)
 	init_sched_dl_class();
 
 	sched_init_smt();
+	sched_clock_init_late();
 
 	sched_smp_initialized = true;
 }
@@ -7502,6 +5913,7 @@ early_initcall(migration_init);
 void __init sched_init_smp(void)
 {
 	sched_init_granularity();
+	sched_clock_init_late();
 }
 #endif /* CONFIG_SMP */
 
@@ -7545,6 +5957,8 @@ void __init sched_init(void)
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
+	sched_clock_init();
+
 	for (i = 0; i < WAIT_TABLE_SIZE; i++)
 		init_waitqueue_head(bit_wait_table + i);
 
@@ -7583,10 +5997,8 @@ void __init sched_init(void)
 	}
 #endif /* CONFIG_CPUMASK_OFFSTACK */
 
-	init_rt_bandwidth(&def_rt_bandwidth,
-			global_rt_period(), global_rt_runtime());
-	init_dl_bandwidth(&def_dl_bandwidth,
-			global_rt_period(), global_rt_runtime());
+	init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
+	init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime());
 
 #ifdef CONFIG_SMP
 	init_defrootdomain();
@@ -7622,18 +6034,18 @@ void __init sched_init(void)
 		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
 		rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
 		/*
-		 * How much cpu bandwidth does root_task_group get?
+		 * How much CPU bandwidth does root_task_group get?
 		 *
 		 * In case of task-groups formed thr' the cgroup filesystem, it
-		 * gets 100% of the cpu resources in the system. This overall
-		 * system cpu resource is divided among the tasks of
+		 * gets 100% of the CPU resources in the system. This overall
+		 * system CPU resource is divided among the tasks of
 		 * root_task_group and its child task-groups in a fair manner,
 		 * based on each entity's (task or task-group's) weight
 		 * (se->load.weight).
 		 *
 		 * In other words, if root_task_group has 10 tasks of weight
 		 * 1024) and two child groups A0 and A1 (of weight 1024 each),
-		 * then A0's share of the cpu resource is:
+		 * then A0's share of the CPU resource is:
 		 *
 		 *	A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
 		 *
@@ -7742,10 +6154,14 @@ EXPORT_SYMBOL(__might_sleep);
 
 void ___might_sleep(const char *file, int line, int preempt_offset)
 {
-	static unsigned long prev_jiffy;	/* ratelimiting */
+	/* Ratelimiting timestamp: */
+	static unsigned long prev_jiffy;
+
 	unsigned long preempt_disable_ip;
 
-	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
+	/* WARN_ON_ONCE() by default, no rate limit required: */
+	rcu_sleep_check();
+
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
 	     !is_idle_task(current)) ||
 	    system_state != SYSTEM_RUNNING || oops_in_progress)
@@ -7754,7 +6170,7 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 		return;
 	prev_jiffy = jiffies;
 
-	/* Save this before calling printk(), since that will clobber it */
+	/* Save this before calling printk(), since that will clobber it: */
 	preempt_disable_ip = get_preempt_disable_ip(current);
 
 	printk(KERN_ERR
@@ -7833,7 +6249,7 @@ void normalize_rt_tasks(void)
  */
 
 /**
- * curr_task - return the current task for a given cpu.
+ * curr_task - return the current task for a given CPU.
  * @cpu: the processor in question.
  *
  * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
@@ -7849,13 +6265,13 @@ struct task_struct *curr_task(int cpu)
 
 #ifdef CONFIG_IA64
 /**
- * set_curr_task - set the current task for a given cpu.
+ * set_curr_task - set the current task for a given CPU.
  * @cpu: the processor in question.
  * @p: the task pointer to set.
  *
  * Description: This function must only be used when non-maskable interrupts
  * are serviced on a separate stack. It allows the architecture to switch the
- * notion of the current task on a cpu in a non-blocking manner. This function
+ * notion of the current task on a CPU in a non-blocking manner. This function
  * must be called with all CPU's synchronized, and interrupts disabled, the
  * and caller must save the original value of the current task (see
  * curr_task() above) and restore that value before reenabling interrupts and
@@ -7911,7 +6327,8 @@ void sched_online_group(struct task_group *tg, struct task_group *parent)
 	spin_lock_irqsave(&task_group_lock, flags);
 	list_add_rcu(&tg->list, &task_groups);
 
-	WARN_ON(!parent); /* root should already exist */
+	/* Root should already exist: */
+	WARN_ON(!parent);
 
 	tg->parent = parent;
 	INIT_LIST_HEAD(&tg->children);
@@ -7924,13 +6341,13 @@ void sched_online_group(struct task_group *tg, struct task_group *parent)
 /* rcu callback to free various structures associated with a task group */
 static void sched_free_group_rcu(struct rcu_head *rhp)
 {
-	/* now it should be safe to free those cfs_rqs */
+	/* Now it should be safe to free those cfs_rqs: */
 	sched_free_group(container_of(rhp, struct task_group, rcu));
 }
 
 void sched_destroy_group(struct task_group *tg)
 {
-	/* wait for possible concurrent references to cfs_rqs complete */
+	/* Wait for possible concurrent references to cfs_rqs complete: */
 	call_rcu(&tg->rcu, sched_free_group_rcu);
 }
 
@@ -7938,7 +6355,7 @@ void sched_offline_group(struct task_group *tg)
 {
 	unsigned long flags;
 
-	/* end participation in shares distribution */
+	/* End participation in shares distribution: */
 	unregister_fair_sched_group(tg);
 
 	spin_lock_irqsave(&task_group_lock, flags);
@@ -7983,20 +6400,21 @@ void sched_move_task(struct task_struct *tsk)
 	struct rq *rq;
 
 	rq = task_rq_lock(tsk, &rf);
+	update_rq_clock(rq);
 
 	running = task_current(rq, tsk);
 	queued = task_on_rq_queued(tsk);
 
 	if (queued)
 		dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE);
-	if (unlikely(running))
+	if (running)
 		put_prev_task(rq, tsk);
 
 	sched_change_group(tsk, TASK_MOVE_GROUP);
 
 	if (queued)
 		enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE);
-	if (unlikely(running))
+	if (running)
 		set_curr_task(rq, tsk);
 
 	task_rq_unlock(rq, tsk, &rf);
@@ -8366,11 +6784,14 @@ int sched_rr_handler(struct ctl_table *table, int write,
 
 	mutex_lock(&mutex);
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-	/* make sure that internally we keep jiffies */
-	/* also, writing zero resets timeslice to default */
+	/*
+	 * Make sure that internally we keep jiffies.
+	 * Also, writing zero resets the timeslice to default:
+	 */
 	if (!ret && write) {
-		sched_rr_timeslice = sched_rr_timeslice <= 0 ?
-			RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice);
+		sched_rr_timeslice =
+			sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
+			msecs_to_jiffies(sysctl_sched_rr_timeslice);
 	}
 	mutex_unlock(&mutex);
 	return ret;
@@ -8431,6 +6852,7 @@ static void cpu_cgroup_fork(struct task_struct *task)
 
 	rq = task_rq_lock(task, &rf);
 
+	update_rq_clock(rq);
 	sched_change_group(task, TASK_SET_GROUP);
 
 	task_rq_unlock(rq, task, &rf);
@@ -8550,9 +6972,11 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 	cfs_b->quota = quota;
 
 	__refill_cfs_bandwidth_runtime(cfs_b);
-	/* restart the period timer (if active) to handle new period expiry */
+
+	/* Restart the period timer (if active) to handle new period expiry: */
 	if (runtime_enabled)
 		start_cfs_bandwidth(cfs_b);
+
 	raw_spin_unlock_irq(&cfs_b->lock);
 
 	for_each_online_cpu(i) {
@@ -8690,8 +7114,8 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
 		parent_quota = parent_b->hierarchical_quota;
 
 		/*
-		 * ensure max(child_quota) <= parent_quota, inherit when no
-		 * limit is set
+		 * Ensure max(child_quota) <= parent_quota, inherit when no
+		 * limit is set:
 		 */
 		if (quota == RUNTIME_INF)
 			quota = parent_quota;
@@ -8800,7 +7224,7 @@ static struct cftype cpu_files[] = {
 		.write_u64 = cpu_rt_period_write_uint,
 	},
 #endif
-	{ }	/* terminate */
+	{ }	/* Terminate */
 };
 
 struct cgroup_subsys cpu_cgrp_subsys = {
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index 9add206b5608..f95ab29a45d0 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -297,7 +297,7 @@ static int cpuacct_stats_show(struct seq_file *sf, void *v)
 	for (stat = 0; stat < CPUACCT_STAT_NSTATS; stat++) {
 		seq_printf(sf, "%s %lld\n",
 			   cpuacct_stat_desc[stat],
-			   (long long)cputime64_to_clock_t(val[stat]));
+			   (long long)nsec_to_clock_t(val[stat]));
 	}
 
 	return 0;
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 7700a9cba335..2ecec3a4f1ee 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -4,6 +4,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/static_key.h>
 #include <linux/context_tracking.h>
+#include <linux/cputime.h>
 #include "sched.h"
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
@@ -44,6 +45,7 @@ void disable_sched_clock_irqtime(void)
 void irqtime_account_irq(struct task_struct *curr)
 {
 	struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
 	s64 delta;
 	int cpu;
 
@@ -61,49 +63,34 @@ void irqtime_account_irq(struct task_struct *curr)
 	 * in that case, so as not to confuse scheduler with a special task
 	 * that do not consume any time, but still wants to run.
 	 */
-	if (hardirq_count())
-		irqtime->hardirq_time += delta;
-	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
-		irqtime->softirq_time += delta;
+	if (hardirq_count()) {
+		cpustat[CPUTIME_IRQ] += delta;
+		irqtime->tick_delta += delta;
+	} else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) {
+		cpustat[CPUTIME_SOFTIRQ] += delta;
+		irqtime->tick_delta += delta;
+	}
 
 	u64_stats_update_end(&irqtime->sync);
 }
 EXPORT_SYMBOL_GPL(irqtime_account_irq);
 
-static cputime_t irqtime_account_update(u64 irqtime, int idx, cputime_t maxtime)
+static u64 irqtime_tick_accounted(u64 maxtime)
 {
-	u64 *cpustat = kcpustat_this_cpu->cpustat;
-	cputime_t irq_cputime;
-
-	irq_cputime = nsecs_to_cputime64(irqtime) - cpustat[idx];
-	irq_cputime = min(irq_cputime, maxtime);
-	cpustat[idx] += irq_cputime;
+	struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+	u64 delta;
 
-	return irq_cputime;
-}
+	delta = min(irqtime->tick_delta, maxtime);
+	irqtime->tick_delta -= delta;
 
-static cputime_t irqtime_account_hi_update(cputime_t maxtime)
-{
-	return irqtime_account_update(__this_cpu_read(cpu_irqtime.hardirq_time),
-				      CPUTIME_IRQ, maxtime);
-}
-
-static cputime_t irqtime_account_si_update(cputime_t maxtime)
-{
-	return irqtime_account_update(__this_cpu_read(cpu_irqtime.softirq_time),
-				      CPUTIME_SOFTIRQ, maxtime);
+	return delta;
 }
 
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 #define sched_clock_irqtime	(0)
 
-static cputime_t irqtime_account_hi_update(cputime_t dummy)
-{
-	return 0;
-}
-
-static cputime_t irqtime_account_si_update(cputime_t dummy)
+static u64 irqtime_tick_accounted(u64 dummy)
 {
 	return 0;
 }
@@ -129,7 +116,7 @@ static inline void task_group_account_field(struct task_struct *p, int index,
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in user space since the last update
  */
-void account_user_time(struct task_struct *p, cputime_t cputime)
+void account_user_time(struct task_struct *p, u64 cputime)
 {
 	int index;
 
@@ -140,7 +127,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
 	index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
 
 	/* Add user time to cpustat. */
-	task_group_account_field(p, index, (__force u64) cputime);
+	task_group_account_field(p, index, cputime);
 
 	/* Account for user time used */
 	acct_account_cputime(p);
@@ -151,7 +138,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in virtual machine since the last update
  */
-static void account_guest_time(struct task_struct *p, cputime_t cputime)
+void account_guest_time(struct task_struct *p, u64 cputime)
 {
 	u64 *cpustat = kcpustat_this_cpu->cpustat;
 
@@ -162,11 +149,11 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime)
 
 	/* Add guest time to cpustat. */
 	if (task_nice(p) > 0) {
-		cpustat[CPUTIME_NICE] += (__force u64) cputime;
-		cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
+		cpustat[CPUTIME_NICE] += cputime;
+		cpustat[CPUTIME_GUEST_NICE] += cputime;
 	} else {
-		cpustat[CPUTIME_USER] += (__force u64) cputime;
-		cpustat[CPUTIME_GUEST] += (__force u64) cputime;
+		cpustat[CPUTIME_USER] += cputime;
+		cpustat[CPUTIME_GUEST] += cputime;
 	}
 }
 
@@ -176,15 +163,15 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime)
  * @cputime: the cpu time spent in kernel space since the last update
  * @index: pointer to cpustat field that has to be updated
  */
-static inline
-void __account_system_time(struct task_struct *p, cputime_t cputime, int index)
+void account_system_index_time(struct task_struct *p,
+			       u64 cputime, enum cpu_usage_stat index)
 {
 	/* Add system time to process. */
 	p->stime += cputime;
 	account_group_system_time(p, cputime);
 
 	/* Add system time to cpustat. */
-	task_group_account_field(p, index, (__force u64) cputime);
+	task_group_account_field(p, index, cputime);
 
 	/* Account for system time used */
 	acct_account_cputime(p);
@@ -196,8 +183,7 @@ void __account_system_time(struct task_struct *p, cputime_t cputime, int index)
  * @hardirq_offset: the offset to subtract from hardirq_count()
  * @cputime: the cpu time spent in kernel space since the last update
  */
-void account_system_time(struct task_struct *p, int hardirq_offset,
-			 cputime_t cputime)
+void account_system_time(struct task_struct *p, int hardirq_offset, u64 cputime)
 {
 	int index;
 
@@ -213,33 +199,33 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 	else
 		index = CPUTIME_SYSTEM;
 
-	__account_system_time(p, cputime, index);
+	account_system_index_time(p, cputime, index);
 }
 
 /*
  * Account for involuntary wait time.
  * @cputime: the cpu time spent in involuntary wait
  */
-void account_steal_time(cputime_t cputime)
+void account_steal_time(u64 cputime)
 {
 	u64 *cpustat = kcpustat_this_cpu->cpustat;
 
-	cpustat[CPUTIME_STEAL] += (__force u64) cputime;
+	cpustat[CPUTIME_STEAL] += cputime;
 }
 
 /*
  * Account for idle time.
  * @cputime: the cpu time spent in idle wait
  */
-void account_idle_time(cputime_t cputime)
+void account_idle_time(u64 cputime)
 {
 	u64 *cpustat = kcpustat_this_cpu->cpustat;
 	struct rq *rq = this_rq();
 
 	if (atomic_read(&rq->nr_iowait) > 0)
-		cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
+		cpustat[CPUTIME_IOWAIT] += cputime;
 	else
-		cpustat[CPUTIME_IDLE] += (__force u64) cputime;
+		cpustat[CPUTIME_IDLE] += cputime;
 }
 
 /*
@@ -247,21 +233,19 @@ void account_idle_time(cputime_t cputime)
  * ticks are not redelivered later. Due to that, this function may on
  * occasion account more time than the calling functions think elapsed.
  */
-static __always_inline cputime_t steal_account_process_time(cputime_t maxtime)
+static __always_inline u64 steal_account_process_time(u64 maxtime)
 {
 #ifdef CONFIG_PARAVIRT
 	if (static_key_false(&paravirt_steal_enabled)) {
-		cputime_t steal_cputime;
 		u64 steal;
 
 		steal = paravirt_steal_clock(smp_processor_id());
 		steal -= this_rq()->prev_steal_time;
+		steal = min(steal, maxtime);
+		account_steal_time(steal);
+		this_rq()->prev_steal_time += steal;
 
-		steal_cputime = min(nsecs_to_cputime(steal), maxtime);
-		account_steal_time(steal_cputime);
-		this_rq()->prev_steal_time += cputime_to_nsecs(steal_cputime);
-
-		return steal_cputime;
+		return steal;
 	}
 #endif
 	return 0;
@@ -270,9 +254,9 @@ static __always_inline cputime_t steal_account_process_time(cputime_t maxtime)
 /*
  * Account how much elapsed time was spent in steal, irq, or softirq time.
  */
-static inline cputime_t account_other_time(cputime_t max)
+static inline u64 account_other_time(u64 max)
 {
-	cputime_t accounted;
+	u64 accounted;
 
 	/* Shall be converted to a lockdep-enabled lightweight check */
 	WARN_ON_ONCE(!irqs_disabled());
@@ -280,10 +264,7 @@ static inline cputime_t account_other_time(cputime_t max)
 	accounted = steal_account_process_time(max);
 
 	if (accounted < max)
-		accounted += irqtime_account_hi_update(max - accounted);
-
-	if (accounted < max)
-		accounted += irqtime_account_si_update(max - accounted);
+		accounted += irqtime_tick_accounted(max - accounted);
 
 	return accounted;
 }
@@ -315,7 +296,7 @@ static u64 read_sum_exec_runtime(struct task_struct *t)
 void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 {
 	struct signal_struct *sig = tsk->signal;
-	cputime_t utime, stime;
+	u64 utime, stime;
 	struct task_struct *t;
 	unsigned int seq, nextseq;
 	unsigned long flags;
@@ -379,8 +360,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 					 struct rq *rq, int ticks)
 {
-	u64 cputime = (__force u64) cputime_one_jiffy * ticks;
-	cputime_t other;
+	u64 other, cputime = TICK_NSEC * ticks;
 
 	/*
 	 * When returning from idle, many ticks can get accounted at
@@ -392,6 +372,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 	other = account_other_time(ULONG_MAX);
 	if (other >= cputime)
 		return;
+
 	cputime -= other;
 
 	if (this_cpu_ksoftirqd() == p) {
@@ -400,7 +381,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 		 * So, we have to handle it separately here.
 		 * Also, p->stime needs to be updated for ksoftirqd.
 		 */
-		__account_system_time(p, cputime, CPUTIME_SOFTIRQ);
+		account_system_index_time(p, cputime, CPUTIME_SOFTIRQ);
 	} else if (user_tick) {
 		account_user_time(p, cputime);
 	} else if (p == rq->idle) {
@@ -408,7 +389,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 	} else if (p->flags & PF_VCPU) { /* System time or guest time */
 		account_guest_time(p, cputime);
 	} else {
-		__account_system_time(p, cputime, CPUTIME_SYSTEM);
+		account_system_index_time(p, cputime, CPUTIME_SYSTEM);
 	}
 }
 
@@ -437,9 +418,7 @@ void vtime_common_task_switch(struct task_struct *prev)
 	else
 		vtime_account_system(prev);
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	vtime_account_user(prev);
-#endif
+	vtime_flush(prev);
 	arch_vtime_task_switch(prev);
 }
 #endif
@@ -467,14 +446,14 @@ void vtime_account_irq_enter(struct task_struct *tsk)
 EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
 #endif /* __ARCH_HAS_VTIME_ACCOUNT */
 
-void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 {
 	*ut = p->utime;
 	*st = p->stime;
 }
 EXPORT_SYMBOL_GPL(task_cputime_adjusted);
 
-void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 {
 	struct task_cputime cputime;
 
@@ -491,7 +470,7 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime
  */
 void account_process_tick(struct task_struct *p, int user_tick)
 {
-	cputime_t cputime, steal;
+	u64 cputime, steal;
 	struct rq *rq = this_rq();
 
 	if (vtime_accounting_cpu_enabled())
@@ -502,7 +481,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 		return;
 	}
 
-	cputime = cputime_one_jiffy;
+	cputime = TICK_NSEC;
 	steal = steal_account_process_time(ULONG_MAX);
 
 	if (steal >= cputime)
@@ -524,14 +503,14 @@ void account_process_tick(struct task_struct *p, int user_tick)
  */
 void account_idle_ticks(unsigned long ticks)
 {
-	cputime_t cputime, steal;
+	u64 cputime, steal;
 
 	if (sched_clock_irqtime) {
 		irqtime_account_idle_ticks(ticks);
 		return;
 	}
 
-	cputime = jiffies_to_cputime(ticks);
+	cputime = ticks * TICK_NSEC;
 	steal = steal_account_process_time(ULONG_MAX);
 
 	if (steal >= cputime)
@@ -545,7 +524,7 @@ void account_idle_ticks(unsigned long ticks)
  * Perform (stime * rtime) / total, but avoid multiplication overflow by
  * loosing precision when the numbers are big.
  */
-static cputime_t scale_stime(u64 stime, u64 rtime, u64 total)
+static u64 scale_stime(u64 stime, u64 rtime, u64 total)
 {
 	u64 scaled;
 
@@ -582,7 +561,7 @@ drop_precision:
 	 * followed by a 64/32->64 divide.
 	 */
 	scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
-	return (__force cputime_t) scaled;
+	return scaled;
 }
 
 /*
@@ -607,14 +586,14 @@ drop_precision:
  */
 static void cputime_adjust(struct task_cputime *curr,
 			   struct prev_cputime *prev,
-			   cputime_t *ut, cputime_t *st)
+			   u64 *ut, u64 *st)
 {
-	cputime_t rtime, stime, utime;
+	u64 rtime, stime, utime;
 	unsigned long flags;
 
 	/* Serialize concurrent callers such that we can honour our guarantees */
 	raw_spin_lock_irqsave(&prev->lock, flags);
-	rtime = nsecs_to_cputime(curr->sum_exec_runtime);
+	rtime = curr->sum_exec_runtime;
 
 	/*
 	 * This is possible under two circumstances:
@@ -645,8 +624,7 @@ static void cputime_adjust(struct task_cputime *curr,
 		goto update;
 	}
 
-	stime = scale_stime((__force u64)stime, (__force u64)rtime,
-			    (__force u64)(stime + utime));
+	stime = scale_stime(stime, rtime, stime + utime);
 
 update:
 	/*
@@ -679,7 +657,7 @@ out:
 	raw_spin_unlock_irqrestore(&prev->lock, flags);
 }
 
-void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 {
 	struct task_cputime cputime = {
 		.sum_exec_runtime = p->se.sum_exec_runtime,
@@ -690,7 +668,7 @@ void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
 }
 EXPORT_SYMBOL_GPL(task_cputime_adjusted);
 
-void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st)
+void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 {
 	struct task_cputime cputime;
 
@@ -700,20 +678,20 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-static cputime_t vtime_delta(struct task_struct *tsk)
+static u64 vtime_delta(struct task_struct *tsk)
 {
 	unsigned long now = READ_ONCE(jiffies);
 
 	if (time_before(now, (unsigned long)tsk->vtime_snap))
 		return 0;
 
-	return jiffies_to_cputime(now - tsk->vtime_snap);
+	return jiffies_to_nsecs(now - tsk->vtime_snap);
 }
 
-static cputime_t get_vtime_delta(struct task_struct *tsk)
+static u64 get_vtime_delta(struct task_struct *tsk)
 {
 	unsigned long now = READ_ONCE(jiffies);
-	cputime_t delta, other;
+	u64 delta, other;
 
 	/*
 	 * Unlike tick based timing, vtime based timing never has lost
@@ -722,7 +700,7 @@ static cputime_t get_vtime_delta(struct task_struct *tsk)
 	 * elapsed time. Limit account_other_time to prevent rounding
 	 * errors from causing elapsed vtime to go negative.
 	 */
-	delta = jiffies_to_cputime(now - tsk->vtime_snap);
+	delta = jiffies_to_nsecs(now - tsk->vtime_snap);
 	other = account_other_time(delta);
 	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
 	tsk->vtime_snap = now;
@@ -732,9 +710,7 @@ static cputime_t get_vtime_delta(struct task_struct *tsk)
 
 static void __vtime_account_system(struct task_struct *tsk)
 {
-	cputime_t delta_cpu = get_vtime_delta(tsk);
-
-	account_system_time(tsk, irq_count(), delta_cpu);
+	account_system_time(tsk, irq_count(), get_vtime_delta(tsk));
 }
 
 void vtime_account_system(struct task_struct *tsk)
@@ -749,14 +725,10 @@ void vtime_account_system(struct task_struct *tsk)
 
 void vtime_account_user(struct task_struct *tsk)
 {
-	cputime_t delta_cpu;
-
 	write_seqcount_begin(&tsk->vtime_seqcount);
 	tsk->vtime_snap_whence = VTIME_SYS;
-	if (vtime_delta(tsk)) {
-		delta_cpu = get_vtime_delta(tsk);
-		account_user_time(tsk, delta_cpu);
-	}
+	if (vtime_delta(tsk))
+		account_user_time(tsk, get_vtime_delta(tsk));
 	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
@@ -797,9 +769,7 @@ EXPORT_SYMBOL_GPL(vtime_guest_exit);
 
 void vtime_account_idle(struct task_struct *tsk)
 {
-	cputime_t delta_cpu = get_vtime_delta(tsk);
-
-	account_idle_time(delta_cpu);
+	account_idle_time(get_vtime_delta(tsk));
 }
 
 void arch_vtime_task_switch(struct task_struct *prev)
@@ -826,10 +796,10 @@ void vtime_init_idle(struct task_struct *t, int cpu)
 	local_irq_restore(flags);
 }
 
-cputime_t task_gtime(struct task_struct *t)
+u64 task_gtime(struct task_struct *t)
 {
 	unsigned int seq;
-	cputime_t gtime;
+	u64 gtime;
 
 	if (!vtime_accounting_enabled())
 		return t->gtime;
@@ -851,9 +821,9 @@ cputime_t task_gtime(struct task_struct *t)
  * add up the pending nohz execution time since the last
  * cputime snapshot.
  */
-void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime)
+void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 {
-	cputime_t delta;
+	u64 delta;
 	unsigned int seq;
 
 	if (!vtime_accounting_enabled()) {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 70ef2b1901e4..27737f34757d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -663,9 +663,9 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 		 * Nothing relies on rq->lock after this, so its safe to drop
 		 * rq->lock.
 		 */
-		lockdep_unpin_lock(&rq->lock, rf.cookie);
+		rq_unpin_lock(rq, &rf);
 		push_dl_task(rq);
-		lockdep_repin_lock(&rq->lock, rf.cookie);
+		rq_repin_lock(rq, &rf);
 	}
 #endif
 
@@ -1118,7 +1118,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq,
 }
 
 struct task_struct *
-pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct sched_dl_entity *dl_se;
 	struct task_struct *p;
@@ -1133,9 +1133,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie coo
 		 * disabled avoiding further scheduler activity on it and we're
 		 * being very careful to re-start the picking loop.
 		 */
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq_unpin_lock(rq, rf);
 		pull_dl_task(rq);
-		lockdep_repin_lock(&rq->lock, cookie);
+		rq_repin_lock(rq, rf);
 		/*
 		 * pull_dl_task() can drop (and re-acquire) rq->lock; this
 		 * means a stop task can slip in, in which case we need to
@@ -1729,12 +1729,11 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 #ifdef CONFIG_SMP
 		if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded)
 			queue_push_tasks(rq);
-#else
+#endif
 		if (dl_task(rq->curr))
 			check_preempt_curr_dl(rq, p, 0);
 		else
 			resched_curr(rq);
-#endif
 	}
 }
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index fa178b62ea79..109adc0e9cb9 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -953,6 +953,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 #endif
 	P(policy);
 	P(prio);
+	if (p->policy == SCHED_DEADLINE) {
+		P(dl.runtime);
+		P(dl.deadline);
+	}
 #undef PN_SCHEDSTAT
 #undef PN
 #undef __PN
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6559d197e08a..274c747a01ce 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2657,6 +2657,18 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 	if (tg_weight)
 		shares /= tg_weight;
 
+	/*
+	 * MIN_SHARES has to be unscaled here to support per-CPU partitioning
+	 * of a group with small tg->shares value. It is a floor value which is
+	 * assigned as a minimum load.weight to the sched_entity representing
+	 * the group on a CPU.
+	 *
+	 * E.g. on 64-bit for a group with tg->shares of scale_load(15)=15*1024
+	 * on an 8-core system with 8 tasks each runnable on one CPU shares has
+	 * to be 15*1024*1/8=1920 instead of scale_load(MIN_SHARES)=2*1024. In
+	 * case no task is runnable on a CPU MIN_SHARES=2 should be returned
+	 * instead of 0.
+	 */
 	if (shares < MIN_SHARES)
 		shares = MIN_SHARES;
 	if (shares > tg->shares)
@@ -2689,16 +2701,20 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
 
-static void update_cfs_shares(struct cfs_rq *cfs_rq)
+static void update_cfs_shares(struct sched_entity *se)
 {
+	struct cfs_rq *cfs_rq = group_cfs_rq(se);
 	struct task_group *tg;
-	struct sched_entity *se;
 	long shares;
 
-	tg = cfs_rq->tg;
-	se = tg->se[cpu_of(rq_of(cfs_rq))];
-	if (!se || throttled_hierarchy(cfs_rq))
+	if (!cfs_rq)
+		return;
+
+	if (throttled_hierarchy(cfs_rq))
 		return;
+
+	tg = cfs_rq->tg;
+
 #ifndef CONFIG_SMP
 	if (likely(se->load.weight == tg->shares))
 		return;
@@ -2707,8 +2723,9 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq)
 
 	reweight_entity(cfs_rq_of(se), se, shares);
 }
+
 #else /* CONFIG_FAIR_GROUP_SCHED */
-static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
+static inline void update_cfs_shares(struct sched_entity *se)
 {
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -3424,7 +3441,7 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)
 	return cfs_rq->avg.load_avg;
 }
 
-static int idle_balance(struct rq *this_rq);
+static int idle_balance(struct rq *this_rq, struct rq_flags *rf);
 
 #else /* CONFIG_SMP */
 
@@ -3453,7 +3470,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 static inline void
 detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
 
-static inline int idle_balance(struct rq *rq)
+static inline int idle_balance(struct rq *rq, struct rq_flags *rf)
 {
 	return 0;
 }
@@ -3582,10 +3599,18 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	if (renorm && !curr)
 		se->vruntime += cfs_rq->min_vruntime;
 
+	/*
+	 * When enqueuing a sched_entity, we must:
+	 *   - Update loads to have both entity and cfs_rq synced with now.
+	 *   - Add its load to cfs_rq->runnable_avg
+	 *   - For group_entity, update its weight to reflect the new share of
+	 *     its group cfs_rq
+	 *   - Add its new weight to cfs_rq->load.weight
+	 */
 	update_load_avg(se, UPDATE_TG);
 	enqueue_entity_load_avg(cfs_rq, se);
+	update_cfs_shares(se);
 	account_entity_enqueue(cfs_rq, se);
-	update_cfs_shares(cfs_rq);
 
 	if (flags & ENQUEUE_WAKEUP)
 		place_entity(cfs_rq, se, 0);
@@ -3657,6 +3682,15 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
+
+	/*
+	 * When dequeuing a sched_entity, we must:
+	 *   - Update loads to have both entity and cfs_rq synced with now.
+	 *   - Substract its load from the cfs_rq->runnable_avg.
+	 *   - Substract its previous weight from cfs_rq->load.weight.
+	 *   - For group entity, update its weight to reflect the new share
+	 *     of its group cfs_rq.
+	 */
 	update_load_avg(se, UPDATE_TG);
 	dequeue_entity_load_avg(cfs_rq, se);
 
@@ -3681,7 +3715,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	/* return excess runtime on last dequeue */
 	return_cfs_rq_runtime(cfs_rq);
 
-	update_cfs_shares(cfs_rq);
+	update_cfs_shares(se);
 
 	/*
 	 * Now advance min_vruntime if @se was the entity holding it back,
@@ -3864,7 +3898,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	 * Ensure that runnable average is periodically updated.
 	 */
 	update_load_avg(curr, UPDATE_TG);
-	update_cfs_shares(cfs_rq);
+	update_cfs_shares(curr);
 
 #ifdef CONFIG_SCHED_HRTICK
 	/*
@@ -4761,7 +4795,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 			break;
 
 		update_load_avg(se, UPDATE_TG);
-		update_cfs_shares(cfs_rq);
+		update_cfs_shares(se);
 	}
 
 	if (!se)
@@ -4820,7 +4854,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 			break;
 
 		update_load_avg(se, UPDATE_TG);
-		update_cfs_shares(cfs_rq);
+		update_cfs_shares(se);
 	}
 
 	if (!se)
@@ -6213,7 +6247,7 @@ preempt:
 }
 
 static struct task_struct *
-pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
@@ -6320,15 +6354,8 @@ simple:
 	return p;
 
 idle:
-	/*
-	 * This is OK, because current is on_cpu, which avoids it being picked
-	 * for load-balance and preemption/IRQs are still disabled avoiding
-	 * further scheduler activity on it and we're being very careful to
-	 * re-start the picking loop.
-	 */
-	lockdep_unpin_lock(&rq->lock, cookie);
-	new_tasks = idle_balance(rq);
-	lockdep_repin_lock(&rq->lock, cookie);
+	new_tasks = idle_balance(rq, rf);
+
 	/*
 	 * Because idle_balance() releases (and re-acquires) rq->lock, it is
 	 * possible for any higher priority task to appear. In that case we
@@ -8077,6 +8104,7 @@ redo:
 
 more_balance:
 		raw_spin_lock_irqsave(&busiest->lock, flags);
+		update_rq_clock(busiest);
 
 		/*
 		 * cur_ld_moved - load moved in current iteration
@@ -8297,7 +8325,7 @@ update_next_balance(struct sched_domain *sd, unsigned long *next_balance)
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
-static int idle_balance(struct rq *this_rq)
+static int idle_balance(struct rq *this_rq, struct rq_flags *rf)
 {
 	unsigned long next_balance = jiffies + HZ;
 	int this_cpu = this_rq->cpu;
@@ -8311,6 +8339,14 @@ static int idle_balance(struct rq *this_rq)
 	 */
 	this_rq->idle_stamp = rq_clock(this_rq);
 
+	/*
+	 * This is OK, because current is on_cpu, which avoids it being picked
+	 * for load-balance and preemption/IRQs are still disabled avoiding
+	 * further scheduler activity on it and we're being very careful to
+	 * re-start the picking loop.
+	 */
+	rq_unpin_lock(this_rq, rf);
+
 	if (this_rq->avg_idle < sysctl_sched_migration_cost ||
 	    !this_rq->rd->overload) {
 		rcu_read_lock();
@@ -8388,6 +8424,8 @@ out:
 	if (pulled_task)
 		this_rq->idle_stamp = 0;
 
+	rq_repin_lock(this_rq, rf);
+
 	return pulled_task;
 }
 
@@ -8443,6 +8481,7 @@ static int active_load_balance_cpu_stop(void *data)
 		};
 
 		schedstat_inc(sd->alb_count);
+		update_rq_clock(busiest_rq);
 
 		p = detach_one_task(&env);
 		if (p) {
@@ -9264,6 +9303,7 @@ void online_fair_sched_group(struct task_group *tg)
 		se = tg->se[i];
 
 		raw_spin_lock_irq(&rq->lock);
+		update_rq_clock(rq);
 		attach_entity_cfs_rq(se);
 		sync_throttle(tg, i);
 		raw_spin_unlock_irq(&rq->lock);
@@ -9356,8 +9396,10 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 
 		/* Possible calls to update_curr() need rq clock */
 		update_rq_clock(rq);
-		for_each_sched_entity(se)
-			update_cfs_shares(group_cfs_rq(se));
+		for_each_sched_entity(se) {
+			update_load_avg(se, UPDATE_TG);
+			update_cfs_shares(se);
+		}
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}
 
diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index 5405d3feb112..0c00172db63e 100644
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -24,7 +24,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 }
 
 static struct task_struct *
-pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	put_prev_task(rq, prev);
 	update_idle_core(rq);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 2516b8df6dbb..e8836cfc4cdb 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -9,6 +9,7 @@
 #include <linux/irq_work.h>
 
 int sched_rr_timeslice = RR_TIMESLICE;
+int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
 
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
 
@@ -1523,7 +1524,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
 }
 
 static struct task_struct *
-pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct task_struct *p;
 	struct rt_rq *rt_rq = &rq->rt;
@@ -1535,9 +1536,9 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie coo
 		 * disabled avoiding further scheduler activity on it and we're
 		 * being very careful to re-start the picking loop.
 		 */
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq_unpin_lock(rq, rf);
 		pull_rt_task(rq);
-		lockdep_repin_lock(&rq->lock, cookie);
+		rq_repin_lock(rq, rf);
 		/*
 		 * pull_rt_task() can drop (and re-acquire) rq->lock; this
 		 * means a dl or stop task can slip in, in which case we need
@@ -2198,10 +2199,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 #ifdef CONFIG_SMP
 		if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded)
 			queue_push_tasks(rq);
-#else
+#endif /* CONFIG_SMP */
 		if (p->prio < rq->curr->prio)
 			resched_curr(rq);
-#endif /* CONFIG_SMP */
 	}
 }
 
@@ -2246,6 +2246,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 	}
 }
 
+#ifdef CONFIG_POSIX_TIMERS
 static void watchdog(struct rq *rq, struct task_struct *p)
 {
 	unsigned long soft, hard;
@@ -2267,6 +2268,9 @@ static void watchdog(struct rq *rq, struct task_struct *p)
 			p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
 	}
 }
+#else
+static inline void watchdog(struct rq *rq, struct task_struct *p) { }
+#endif
 
 static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7b34c7826ca5..71b10a9b73cf 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -4,6 +4,7 @@
 #include <linux/sched/rt.h>
 #include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
+#include <linux/kernel_stat.h>
 #include <linux/binfmts.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
@@ -222,7 +223,7 @@ bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
 	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
 }
 
-extern struct mutex sched_domains_mutex;
+extern void init_dl_bw(struct dl_bw *dl_b);
 
 #ifdef CONFIG_CGROUP_SCHED
 
@@ -583,6 +584,13 @@ struct root_domain {
 };
 
 extern struct root_domain def_root_domain;
+extern struct mutex sched_domains_mutex;
+extern cpumask_var_t fallback_doms;
+extern cpumask_var_t sched_domains_tmpmask;
+
+extern void init_defrootdomain(void);
+extern int init_sched_domains(const struct cpumask *cpu_map);
+extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
 
 #endif /* CONFIG_SMP */
 
@@ -644,7 +652,7 @@ struct rq {
 	unsigned long next_balance;
 	struct mm_struct *prev_mm;
 
-	unsigned int clock_skip_update;
+	unsigned int clock_update_flags;
 	u64 clock;
 	u64 clock_task;
 
@@ -768,28 +776,110 @@ static inline u64 __rq_clock_broken(struct rq *rq)
 	return READ_ONCE(rq->clock);
 }
 
+/*
+ * rq::clock_update_flags bits
+ *
+ * %RQCF_REQ_SKIP - will request skipping of clock update on the next
+ *  call to __schedule(). This is an optimisation to avoid
+ *  neighbouring rq clock updates.
+ *
+ * %RQCF_ACT_SKIP - is set from inside of __schedule() when skipping is
+ *  in effect and calls to update_rq_clock() are being ignored.
+ *
+ * %RQCF_UPDATED - is a debug flag that indicates whether a call has been
+ *  made to update_rq_clock() since the last time rq::lock was pinned.
+ *
+ * If inside of __schedule(), clock_update_flags will have been
+ * shifted left (a left shift is a cheap operation for the fast path
+ * to promote %RQCF_REQ_SKIP to %RQCF_ACT_SKIP), so you must use,
+ *
+ *	if (rq-clock_update_flags >= RQCF_UPDATED)
+ *
+ * to check if %RQCF_UPADTED is set. It'll never be shifted more than
+ * one position though, because the next rq_unpin_lock() will shift it
+ * back.
+ */
+#define RQCF_REQ_SKIP	0x01
+#define RQCF_ACT_SKIP	0x02
+#define RQCF_UPDATED	0x04
+
+static inline void assert_clock_updated(struct rq *rq)
+{
+	/*
+	 * The only reason for not seeing a clock update since the
+	 * last rq_pin_lock() is if we're currently skipping updates.
+	 */
+	SCHED_WARN_ON(rq->clock_update_flags < RQCF_ACT_SKIP);
+}
+
 static inline u64 rq_clock(struct rq *rq)
 {
 	lockdep_assert_held(&rq->lock);
+	assert_clock_updated(rq);
+
 	return rq->clock;
 }
 
 static inline u64 rq_clock_task(struct rq *rq)
 {
 	lockdep_assert_held(&rq->lock);
+	assert_clock_updated(rq);
+
 	return rq->clock_task;
 }
 
-#define RQCF_REQ_SKIP	0x01
-#define RQCF_ACT_SKIP	0x02
-
 static inline void rq_clock_skip_update(struct rq *rq, bool skip)
 {
 	lockdep_assert_held(&rq->lock);
 	if (skip)
-		rq->clock_skip_update |= RQCF_REQ_SKIP;
+		rq->clock_update_flags |= RQCF_REQ_SKIP;
 	else
-		rq->clock_skip_update &= ~RQCF_REQ_SKIP;
+		rq->clock_update_flags &= ~RQCF_REQ_SKIP;
+}
+
+struct rq_flags {
+	unsigned long flags;
+	struct pin_cookie cookie;
+#ifdef CONFIG_SCHED_DEBUG
+	/*
+	 * A copy of (rq::clock_update_flags & RQCF_UPDATED) for the
+	 * current pin context is stashed here in case it needs to be
+	 * restored in rq_repin_lock().
+	 */
+	unsigned int clock_update_flags;
+#endif
+};
+
+static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
+{
+	rf->cookie = lockdep_pin_lock(&rq->lock);
+
+#ifdef CONFIG_SCHED_DEBUG
+	rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
+	rf->clock_update_flags = 0;
+#endif
+}
+
+static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
+{
+#ifdef CONFIG_SCHED_DEBUG
+	if (rq->clock_update_flags > RQCF_ACT_SKIP)
+		rf->clock_update_flags = RQCF_UPDATED;
+#endif
+
+	lockdep_unpin_lock(&rq->lock, rf->cookie);
+}
+
+static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
+{
+	lockdep_repin_lock(&rq->lock, rf->cookie);
+
+#ifdef CONFIG_SCHED_DEBUG
+	/*
+	 * Restore the value we stashed in @rf for this pin context.
+	 */
+	rq->clock_update_flags |= rf->clock_update_flags;
+#endif
 }
 
 #ifdef CONFIG_NUMA
@@ -803,6 +893,16 @@ extern int sched_max_numa_distance;
 extern bool find_numa_distance(int distance);
 #endif
 
+#ifdef CONFIG_NUMA
+extern void sched_init_numa(void);
+extern void sched_domains_numa_masks_set(unsigned int cpu);
+extern void sched_domains_numa_masks_clear(unsigned int cpu);
+#else
+static inline void sched_init_numa(void) { }
+static inline void sched_domains_numa_masks_set(unsigned int cpu) { }
+static inline void sched_domains_numa_masks_clear(unsigned int cpu) { }
+#endif
+
 #ifdef CONFIG_NUMA_BALANCING
 /* The regions in numa_faults array from task_struct */
 enum numa_faults_stats {
@@ -969,7 +1069,7 @@ static inline void sched_ttwu_pending(void) { }
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
-#include "auto_group.h"
+#include "autogroup.h"
 
 #ifdef CONFIG_CGROUP_SCHED
 
@@ -1245,7 +1345,7 @@ struct sched_class {
 	 */
 	struct task_struct * (*pick_next_task) (struct rq *rq,
 						struct task_struct *prev,
-						struct pin_cookie cookie);
+						struct rq_flags *rf);
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
@@ -1501,11 +1601,6 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
 static inline void sched_avg_update(struct rq *rq) { }
 #endif
 
-struct rq_flags {
-	unsigned long flags;
-	struct pin_cookie cookie;
-};
-
 struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	__acquires(rq->lock);
 struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
@@ -1515,7 +1610,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
 	__releases(rq->lock)
 {
-	lockdep_unpin_lock(&rq->lock, rf->cookie);
+	rq_unpin_lock(rq, rf);
 	raw_spin_unlock(&rq->lock);
 }
 
@@ -1524,7 +1619,7 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	__releases(rq->lock)
 	__releases(p->pi_lock)
 {
-	lockdep_unpin_lock(&rq->lock, rf->cookie);
+	rq_unpin_lock(rq, rf);
 	raw_spin_unlock(&rq->lock);
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 }
@@ -1674,6 +1769,10 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 		__release(rq2->lock);
 }
 
+extern void set_rq_online (struct rq *rq);
+extern void set_rq_offline(struct rq *rq);
+extern bool sched_smp_initialized;
+
 #else /* CONFIG_SMP */
 
 /*
@@ -1750,8 +1849,7 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 struct irqtime {
-	u64			hardirq_time;
-	u64			softirq_time;
+	u64			tick_delta;
 	u64			irq_start_time;
 	struct u64_stats_sync	sync;
 };
@@ -1761,12 +1859,13 @@ DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
 static inline u64 irq_time_read(int cpu)
 {
 	struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
+	u64 *cpustat = kcpustat_cpu(cpu).cpustat;
 	unsigned int seq;
 	u64 total;
 
 	do {
 		seq = __u64_stats_fetch_begin(&irqtime->sync);
-		total = irqtime->softirq_time + irqtime->hardirq_time;
+		total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ];
 	} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
 
 	return total;
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 34659a853505..bf0da0aa0a14 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -172,18 +172,19 @@ sched_info_switch(struct rq *rq,
  */
 
 /**
- * cputimer_running - return true if cputimer is running
+ * get_running_cputimer - return &tsk->signal->cputimer if cputimer is running
  *
  * @tsk:	Pointer to target task.
  */
-static inline bool cputimer_running(struct task_struct *tsk)
-
+#ifdef CONFIG_POSIX_TIMERS
+static inline
+struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
 {
 	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
 
 	/* Check if cputimer isn't running. This is accessed without locking. */
 	if (!READ_ONCE(cputimer->running))
-		return false;
+		return NULL;
 
 	/*
 	 * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime
@@ -200,10 +201,17 @@ static inline bool cputimer_running(struct task_struct *tsk)
 	 * clock delta is behind the expiring timer value.
 	 */
 	if (unlikely(!tsk->sighand))
-		return false;
+		return NULL;
 
-	return true;
+	return cputimer;
+}
+#else
+static inline
+struct thread_group_cputimer *get_running_cputimer(struct task_struct *tsk)
+{
+	return NULL;
 }
+#endif
 
 /**
  * account_group_user_time - Maintain utime for a thread group.
@@ -216,11 +224,11 @@ static inline bool cputimer_running(struct task_struct *tsk)
  * running CPU and update the utime field there.
  */
 static inline void account_group_user_time(struct task_struct *tsk,
-					   cputime_t cputime)
+					   u64 cputime)
 {
-	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
 
-	if (!cputimer_running(tsk))
+	if (!cputimer)
 		return;
 
 	atomic64_add(cputime, &cputimer->cputime_atomic.utime);
@@ -237,11 +245,11 @@ static inline void account_group_user_time(struct task_struct *tsk,
  * running CPU and update the stime field there.
  */
 static inline void account_group_system_time(struct task_struct *tsk,
-					     cputime_t cputime)
+					     u64 cputime)
 {
-	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
 
-	if (!cputimer_running(tsk))
+	if (!cputimer)
 		return;
 
 	atomic64_add(cputime, &cputimer->cputime_atomic.stime);
@@ -260,9 +268,9 @@ static inline void account_group_system_time(struct task_struct *tsk,
 static inline void account_group_exec_runtime(struct task_struct *tsk,
 					      unsigned long long ns)
 {
-	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
+	struct thread_group_cputimer *cputimer = get_running_cputimer(tsk);
 
-	if (!cputimer_running(tsk))
+	if (!cputimer)
 		return;
 
 	atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime);
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 604297a08b3a..9f69fb630853 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -24,7 +24,7 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
 }
 
 static struct task_struct *
-pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie)
+pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct task_struct *stop = rq->stop;
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
new file mode 100644
index 000000000000..1b0b4fb12837
--- /dev/null
+++ b/kernel/sched/topology.c
@@ -0,0 +1,1658 @@
+/*
+ * Scheduler topology setup/handling methods
+ */
+#include <linux/sched.h>
+#include <linux/mutex.h>
+
+#include "sched.h"
+
+DEFINE_MUTEX(sched_domains_mutex);
+
+/* Protected by sched_domains_mutex: */
+cpumask_var_t sched_domains_tmpmask;
+
+#ifdef CONFIG_SCHED_DEBUG
+
+static __read_mostly int sched_debug_enabled;
+
+static int __init sched_debug_setup(char *str)
+{
+	sched_debug_enabled = 1;
+
+	return 0;
+}
+early_param("sched_debug", sched_debug_setup);
+
+static inline bool sched_debug(void)
+{
+	return sched_debug_enabled;
+}
+
+static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
+				  struct cpumask *groupmask)
+{
+	struct sched_group *group = sd->groups;
+
+	cpumask_clear(groupmask);
+
+	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+
+	if (!(sd->flags & SD_LOAD_BALANCE)) {
+		printk("does not load-balance\n");
+		if (sd->parent)
+			printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
+					" has parent");
+		return -1;
+	}
+
+	printk(KERN_CONT "span %*pbl level %s\n",
+	       cpumask_pr_args(sched_domain_span(sd)), sd->name);
+
+	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
+		printk(KERN_ERR "ERROR: domain->span does not contain "
+				"CPU%d\n", cpu);
+	}
+	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
+		printk(KERN_ERR "ERROR: domain->groups does not contain"
+				" CPU%d\n", cpu);
+	}
+
+	printk(KERN_DEBUG "%*s groups:", level + 1, "");
+	do {
+		if (!group) {
+			printk("\n");
+			printk(KERN_ERR "ERROR: group is NULL\n");
+			break;
+		}
+
+		if (!cpumask_weight(sched_group_cpus(group))) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: empty group\n");
+			break;
+		}
+
+		if (!(sd->flags & SD_OVERLAP) &&
+		    cpumask_intersects(groupmask, sched_group_cpus(group))) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: repeated CPUs\n");
+			break;
+		}
+
+		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
+
+		printk(KERN_CONT " %*pbl",
+		       cpumask_pr_args(sched_group_cpus(group)));
+		if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
+			printk(KERN_CONT " (cpu_capacity = %lu)",
+				group->sgc->capacity);
+		}
+
+		group = group->next;
+	} while (group != sd->groups);
+	printk(KERN_CONT "\n");
+
+	if (!cpumask_equal(sched_domain_span(sd), groupmask))
+		printk(KERN_ERR "ERROR: groups don't span domain->span\n");
+
+	if (sd->parent &&
+	    !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
+		printk(KERN_ERR "ERROR: parent span is not a superset "
+			"of domain->span\n");
+	return 0;
+}
+
+static void sched_domain_debug(struct sched_domain *sd, int cpu)
+{
+	int level = 0;
+
+	if (!sched_debug_enabled)
+		return;
+
+	if (!sd) {
+		printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+		return;
+	}
+
+	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+
+	for (;;) {
+		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
+			break;
+		level++;
+		sd = sd->parent;
+		if (!sd)
+			break;
+	}
+}
+#else /* !CONFIG_SCHED_DEBUG */
+
+# define sched_debug_enabled 0
+# define sched_domain_debug(sd, cpu) do { } while (0)
+static inline bool sched_debug(void)
+{
+	return false;
+}
+#endif /* CONFIG_SCHED_DEBUG */
+
+static int sd_degenerate(struct sched_domain *sd)
+{
+	if (cpumask_weight(sched_domain_span(sd)) == 1)
+		return 1;
+
+	/* Following flags need at least 2 groups */
+	if (sd->flags & (SD_LOAD_BALANCE |
+			 SD_BALANCE_NEWIDLE |
+			 SD_BALANCE_FORK |
+			 SD_BALANCE_EXEC |
+			 SD_SHARE_CPUCAPACITY |
+			 SD_ASYM_CPUCAPACITY |
+			 SD_SHARE_PKG_RESOURCES |
+			 SD_SHARE_POWERDOMAIN)) {
+		if (sd->groups != sd->groups->next)
+			return 0;
+	}
+
+	/* Following flags don't use groups */
+	if (sd->flags & (SD_WAKE_AFFINE))
+		return 0;
+
+	return 1;
+}
+
+static int
+sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
+{
+	unsigned long cflags = sd->flags, pflags = parent->flags;
+
+	if (sd_degenerate(parent))
+		return 1;
+
+	if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
+		return 0;
+
+	/* Flags needing groups don't count if only 1 group in parent */
+	if (parent->groups == parent->groups->next) {
+		pflags &= ~(SD_LOAD_BALANCE |
+				SD_BALANCE_NEWIDLE |
+				SD_BALANCE_FORK |
+				SD_BALANCE_EXEC |
+				SD_ASYM_CPUCAPACITY |
+				SD_SHARE_CPUCAPACITY |
+				SD_SHARE_PKG_RESOURCES |
+				SD_PREFER_SIBLING |
+				SD_SHARE_POWERDOMAIN);
+		if (nr_node_ids == 1)
+			pflags &= ~SD_SERIALIZE;
+	}
+	if (~cflags & pflags)
+		return 0;
+
+	return 1;
+}
+
+static void free_rootdomain(struct rcu_head *rcu)
+{
+	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
+
+	cpupri_cleanup(&rd->cpupri);
+	cpudl_cleanup(&rd->cpudl);
+	free_cpumask_var(rd->dlo_mask);
+	free_cpumask_var(rd->rto_mask);
+	free_cpumask_var(rd->online);
+	free_cpumask_var(rd->span);
+	kfree(rd);
+}
+
+void rq_attach_root(struct rq *rq, struct root_domain *rd)
+{
+	struct root_domain *old_rd = NULL;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&rq->lock, flags);
+
+	if (rq->rd) {
+		old_rd = rq->rd;
+
+		if (cpumask_test_cpu(rq->cpu, old_rd->online))
+			set_rq_offline(rq);
+
+		cpumask_clear_cpu(rq->cpu, old_rd->span);
+
+		/*
+		 * If we dont want to free the old_rd yet then
+		 * set old_rd to NULL to skip the freeing later
+		 * in this function:
+		 */
+		if (!atomic_dec_and_test(&old_rd->refcount))
+			old_rd = NULL;
+	}
+
+	atomic_inc(&rd->refcount);
+	rq->rd = rd;
+
+	cpumask_set_cpu(rq->cpu, rd->span);
+	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
+		set_rq_online(rq);
+
+	raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+	if (old_rd)
+		call_rcu_sched(&old_rd->rcu, free_rootdomain);
+}
+
+static int init_rootdomain(struct root_domain *rd)
+{
+	memset(rd, 0, sizeof(*rd));
+
+	if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL))
+		goto out;
+	if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL))
+		goto free_span;
+	if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
+		goto free_online;
+	if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+		goto free_dlo_mask;
+
+	init_dl_bw(&rd->dl_bw);
+	if (cpudl_init(&rd->cpudl) != 0)
+		goto free_rto_mask;
+
+	if (cpupri_init(&rd->cpupri) != 0)
+		goto free_cpudl;
+	return 0;
+
+free_cpudl:
+	cpudl_cleanup(&rd->cpudl);
+free_rto_mask:
+	free_cpumask_var(rd->rto_mask);
+free_dlo_mask:
+	free_cpumask_var(rd->dlo_mask);
+free_online:
+	free_cpumask_var(rd->online);
+free_span:
+	free_cpumask_var(rd->span);
+out:
+	return -ENOMEM;
+}
+
+/*
+ * By default the system creates a single root-domain with all CPUs as
+ * members (mimicking the global state we have today).
+ */
+struct root_domain def_root_domain;
+
+void init_defrootdomain(void)
+{
+	init_rootdomain(&def_root_domain);
+
+	atomic_set(&def_root_domain.refcount, 1);
+}
+
+static struct root_domain *alloc_rootdomain(void)
+{
+	struct root_domain *rd;
+
+	rd = kmalloc(sizeof(*rd), GFP_KERNEL);
+	if (!rd)
+		return NULL;
+
+	if (init_rootdomain(rd) != 0) {
+		kfree(rd);
+		return NULL;
+	}
+
+	return rd;
+}
+
+static void free_sched_groups(struct sched_group *sg, int free_sgc)
+{
+	struct sched_group *tmp, *first;
+
+	if (!sg)
+		return;
+
+	first = sg;
+	do {
+		tmp = sg->next;
+
+		if (free_sgc && atomic_dec_and_test(&sg->sgc->ref))
+			kfree(sg->sgc);
+
+		kfree(sg);
+		sg = tmp;
+	} while (sg != first);
+}
+
+static void destroy_sched_domain(struct sched_domain *sd)
+{
+	/*
+	 * If its an overlapping domain it has private groups, iterate and
+	 * nuke them all.
+	 */
+	if (sd->flags & SD_OVERLAP) {
+		free_sched_groups(sd->groups, 1);
+	} else if (atomic_dec_and_test(&sd->groups->ref)) {
+		kfree(sd->groups->sgc);
+		kfree(sd->groups);
+	}
+	if (sd->shared && atomic_dec_and_test(&sd->shared->ref))
+		kfree(sd->shared);
+	kfree(sd);
+}
+
+static void destroy_sched_domains_rcu(struct rcu_head *rcu)
+{
+	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
+
+	while (sd) {
+		struct sched_domain *parent = sd->parent;
+		destroy_sched_domain(sd);
+		sd = parent;
+	}
+}
+
+static void destroy_sched_domains(struct sched_domain *sd)
+{
+	if (sd)
+		call_rcu(&sd->rcu, destroy_sched_domains_rcu);
+}
+
+/*
+ * Keep a special pointer to the highest sched_domain that has
+ * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this
+ * allows us to avoid some pointer chasing select_idle_sibling().
+ *
+ * Also keep a unique ID per domain (we use the first CPU number in
+ * the cpumask of the domain), this allows us to quickly tell if
+ * two CPUs are in the same cache domain, see cpus_share_cache().
+ */
+DEFINE_PER_CPU(struct sched_domain *, sd_llc);
+DEFINE_PER_CPU(int, sd_llc_size);
+DEFINE_PER_CPU(int, sd_llc_id);
+DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
+DEFINE_PER_CPU(struct sched_domain *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym);
+
+static void update_top_cache_domain(int cpu)
+{
+	struct sched_domain_shared *sds = NULL;
+	struct sched_domain *sd;
+	int id = cpu;
+	int size = 1;
+
+	sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES);
+	if (sd) {
+		id = cpumask_first(sched_domain_span(sd));
+		size = cpumask_weight(sched_domain_span(sd));
+		sds = sd->shared;
+	}
+
+	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
+	per_cpu(sd_llc_size, cpu) = size;
+	per_cpu(sd_llc_id, cpu) = id;
+	rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
+
+	sd = lowest_flag_domain(cpu, SD_NUMA);
+	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
+
+	sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
+	rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
+}
+
+/*
+ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
+ * hold the hotplug lock.
+ */
+static void
+cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	struct sched_domain *tmp;
+
+	/* Remove the sched domains which do not contribute to scheduling. */
+	for (tmp = sd; tmp; ) {
+		struct sched_domain *parent = tmp->parent;
+		if (!parent)
+			break;
+
+		if (sd_parent_degenerate(tmp, parent)) {
+			tmp->parent = parent->parent;
+			if (parent->parent)
+				parent->parent->child = tmp;
+			/*
+			 * Transfer SD_PREFER_SIBLING down in case of a
+			 * degenerate parent; the spans match for this
+			 * so the property transfers.
+			 */
+			if (parent->flags & SD_PREFER_SIBLING)
+				tmp->flags |= SD_PREFER_SIBLING;
+			destroy_sched_domain(parent);
+		} else
+			tmp = tmp->parent;
+	}
+
+	if (sd && sd_degenerate(sd)) {
+		tmp = sd;
+		sd = sd->parent;
+		destroy_sched_domain(tmp);
+		if (sd)
+			sd->child = NULL;
+	}
+
+	sched_domain_debug(sd, cpu);
+
+	rq_attach_root(rq, rd);
+	tmp = rq->sd;
+	rcu_assign_pointer(rq->sd, sd);
+	destroy_sched_domains(tmp);
+
+	update_top_cache_domain(cpu);
+}
+
+/* Setup the mask of CPUs configured for isolated domains */
+static int __init isolated_cpu_setup(char *str)
+{
+	int ret;
+
+	alloc_bootmem_cpumask_var(&cpu_isolated_map);
+	ret = cpulist_parse(str, cpu_isolated_map);
+	if (ret) {
+		pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids);
+		return 0;
+	}
+	return 1;
+}
+__setup("isolcpus=", isolated_cpu_setup);
+
+struct s_data {
+	struct sched_domain ** __percpu sd;
+	struct root_domain	*rd;
+};
+
+enum s_alloc {
+	sa_rootdomain,
+	sa_sd,
+	sa_sd_storage,
+	sa_none,
+};
+
+/*
+ * Build an iteration mask that can exclude certain CPUs from the upwards
+ * domain traversal.
+ *
+ * Asymmetric node setups can result in situations where the domain tree is of
+ * unequal depth, make sure to skip domains that already cover the entire
+ * range.
+ *
+ * In that case build_sched_domains() will have terminated the iteration early
+ * and our sibling sd spans will be empty. Domains should always include the
+ * CPU they're built on, so check that.
+ */
+static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+{
+	const struct cpumask *span = sched_domain_span(sd);
+	struct sd_data *sdd = sd->private;
+	struct sched_domain *sibling;
+	int i;
+
+	for_each_cpu(i, span) {
+		sibling = *per_cpu_ptr(sdd->sd, i);
+		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+			continue;
+
+		cpumask_set_cpu(i, sched_group_mask(sg));
+	}
+}
+
+/*
+ * Return the canonical balance CPU for this group, this is the first CPU
+ * of this group that's also in the iteration mask.
+ */
+int group_balance_cpu(struct sched_group *sg)
+{
+	return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
+}
+
+static int
+build_overlap_sched_groups(struct sched_domain *sd, int cpu)
+{
+	struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
+	const struct cpumask *span = sched_domain_span(sd);
+	struct cpumask *covered = sched_domains_tmpmask;
+	struct sd_data *sdd = sd->private;
+	struct sched_domain *sibling;
+	int i;
+
+	cpumask_clear(covered);
+
+	for_each_cpu(i, span) {
+		struct cpumask *sg_span;
+
+		if (cpumask_test_cpu(i, covered))
+			continue;
+
+		sibling = *per_cpu_ptr(sdd->sd, i);
+
+		/* See the comment near build_group_mask(). */
+		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+			continue;
+
+		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+				GFP_KERNEL, cpu_to_node(cpu));
+
+		if (!sg)
+			goto fail;
+
+		sg_span = sched_group_cpus(sg);
+		if (sibling->child)
+			cpumask_copy(sg_span, sched_domain_span(sibling->child));
+		else
+			cpumask_set_cpu(i, sg_span);
+
+		cpumask_or(covered, covered, sg_span);
+
+		sg->sgc = *per_cpu_ptr(sdd->sgc, i);
+		if (atomic_inc_return(&sg->sgc->ref) == 1)
+			build_group_mask(sd, sg);
+
+		/*
+		 * Initialize sgc->capacity such that even if we mess up the
+		 * domains and no possible iteration will get us here, we won't
+		 * die on a /0 trap.
+		 */
+		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+		sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
+
+		/*
+		 * Make sure the first group of this domain contains the
+		 * canonical balance CPU. Otherwise the sched_domain iteration
+		 * breaks. See update_sg_lb_stats().
+		 */
+		if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
+		    group_balance_cpu(sg) == cpu)
+			groups = sg;
+
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
+		last->next = first;
+	}
+	sd->groups = groups;
+
+	return 0;
+
+fail:
+	free_sched_groups(first, 0);
+
+	return -ENOMEM;
+}
+
+static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
+{
+	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
+	struct sched_domain *child = sd->child;
+
+	if (child)
+		cpu = cpumask_first(sched_domain_span(child));
+
+	if (sg) {
+		*sg = *per_cpu_ptr(sdd->sg, cpu);
+		(*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+
+		/* For claim_allocations: */
+		atomic_set(&(*sg)->sgc->ref, 1);
+	}
+
+	return cpu;
+}
+
+/*
+ * build_sched_groups will build a circular linked list of the groups
+ * covered by the given span, and will set each group's ->cpumask correctly,
+ * and ->cpu_capacity to 0.
+ *
+ * Assumes the sched_domain tree is fully constructed
+ */
+static int
+build_sched_groups(struct sched_domain *sd, int cpu)
+{
+	struct sched_group *first = NULL, *last = NULL;
+	struct sd_data *sdd = sd->private;
+	const struct cpumask *span = sched_domain_span(sd);
+	struct cpumask *covered;
+	int i;
+
+	get_group(cpu, sdd, &sd->groups);
+	atomic_inc(&sd->groups->ref);
+
+	if (cpu != cpumask_first(span))
+		return 0;
+
+	lockdep_assert_held(&sched_domains_mutex);
+	covered = sched_domains_tmpmask;
+
+	cpumask_clear(covered);
+
+	for_each_cpu(i, span) {
+		struct sched_group *sg;
+		int group, j;
+
+		if (cpumask_test_cpu(i, covered))
+			continue;
+
+		group = get_group(i, sdd, &sg);
+		cpumask_setall(sched_group_mask(sg));
+
+		for_each_cpu(j, span) {
+			if (get_group(j, sdd, NULL) != group)
+				continue;
+
+			cpumask_set_cpu(j, covered);
+			cpumask_set_cpu(j, sched_group_cpus(sg));
+		}
+
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
+	}
+	last->next = first;
+
+	return 0;
+}
+
+/*
+ * Initialize sched groups cpu_capacity.
+ *
+ * cpu_capacity indicates the capacity of sched group, which is used while
+ * distributing the load between different sched groups in a sched domain.
+ * Typically cpu_capacity for all the groups in a sched domain will be same
+ * unless there are asymmetries in the topology. If there are asymmetries,
+ * group having more cpu_capacity will pickup more load compared to the
+ * group having less cpu_capacity.
+ */
+static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
+{
+	struct sched_group *sg = sd->groups;
+
+	WARN_ON(!sg);
+
+	do {
+		int cpu, max_cpu = -1;
+
+		sg->group_weight = cpumask_weight(sched_group_cpus(sg));
+
+		if (!(sd->flags & SD_ASYM_PACKING))
+			goto next;
+
+		for_each_cpu(cpu, sched_group_cpus(sg)) {
+			if (max_cpu < 0)
+				max_cpu = cpu;
+			else if (sched_asym_prefer(cpu, max_cpu))
+				max_cpu = cpu;
+		}
+		sg->asym_prefer_cpu = max_cpu;
+
+next:
+		sg = sg->next;
+	} while (sg != sd->groups);
+
+	if (cpu != group_balance_cpu(sg))
+		return;
+
+	update_group_capacity(sd, cpu);
+}
+
+/*
+ * Initializers for schedule domains
+ * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
+ */
+
+static int default_relax_domain_level = -1;
+int sched_domain_level_max;
+
+static int __init setup_relax_domain_level(char *str)
+{
+	if (kstrtoint(str, 0, &default_relax_domain_level))
+		pr_warn("Unable to set relax_domain_level\n");
+
+	return 1;
+}
+__setup("relax_domain_level=", setup_relax_domain_level);
+
+static void set_domain_attribute(struct sched_domain *sd,
+				 struct sched_domain_attr *attr)
+{
+	int request;
+
+	if (!attr || attr->relax_domain_level < 0) {
+		if (default_relax_domain_level < 0)
+			return;
+		else
+			request = default_relax_domain_level;
+	} else
+		request = attr->relax_domain_level;
+	if (request < sd->level) {
+		/* Turn off idle balance on this domain: */
+		sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
+	} else {
+		/* Turn on idle balance on this domain: */
+		sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
+	}
+}
+
+static void __sdt_free(const struct cpumask *cpu_map);
+static int __sdt_alloc(const struct cpumask *cpu_map);
+
+static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
+				 const struct cpumask *cpu_map)
+{
+	switch (what) {
+	case sa_rootdomain:
+		if (!atomic_read(&d->rd->refcount))
+			free_rootdomain(&d->rd->rcu);
+		/* Fall through */
+	case sa_sd:
+		free_percpu(d->sd);
+		/* Fall through */
+	case sa_sd_storage:
+		__sdt_free(cpu_map);
+		/* Fall through */
+	case sa_none:
+		break;
+	}
+}
+
+static enum s_alloc
+__visit_domain_allocation_hell(struct s_data *d, const struct cpumask *cpu_map)
+{
+	memset(d, 0, sizeof(*d));
+
+	if (__sdt_alloc(cpu_map))
+		return sa_sd_storage;
+	d->sd = alloc_percpu(struct sched_domain *);
+	if (!d->sd)
+		return sa_sd_storage;
+	d->rd = alloc_rootdomain();
+	if (!d->rd)
+		return sa_sd;
+	return sa_rootdomain;
+}
+
+/*
+ * NULL the sd_data elements we've used to build the sched_domain and
+ * sched_group structure so that the subsequent __free_domain_allocs()
+ * will not free the data we're using.
+ */
+static void claim_allocations(int cpu, struct sched_domain *sd)
+{
+	struct sd_data *sdd = sd->private;
+
+	WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
+	*per_cpu_ptr(sdd->sd, cpu) = NULL;
+
+	if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref))
+		*per_cpu_ptr(sdd->sds, cpu) = NULL;
+
+	if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
+		*per_cpu_ptr(sdd->sg, cpu) = NULL;
+
+	if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref))
+		*per_cpu_ptr(sdd->sgc, cpu) = NULL;
+}
+
+#ifdef CONFIG_NUMA
+static int sched_domains_numa_levels;
+enum numa_topology_type sched_numa_topology_type;
+static int *sched_domains_numa_distance;
+int sched_max_numa_distance;
+static struct cpumask ***sched_domains_numa_masks;
+static int sched_domains_curr_level;
+#endif
+
+/*
+ * SD_flags allowed in topology descriptions.
+ *
+ * These flags are purely descriptive of the topology and do not prescribe
+ * behaviour. Behaviour is artificial and mapped in the below sd_init()
+ * function:
+ *
+ *   SD_SHARE_CPUCAPACITY   - describes SMT topologies
+ *   SD_SHARE_PKG_RESOURCES - describes shared caches
+ *   SD_NUMA                - describes NUMA topologies
+ *   SD_SHARE_POWERDOMAIN   - describes shared power domain
+ *   SD_ASYM_CPUCAPACITY    - describes mixed capacity topologies
+ *
+ * Odd one out, which beside describing the topology has a quirk also
+ * prescribes the desired behaviour that goes along with it:
+ *
+ *   SD_ASYM_PACKING        - describes SMT quirks
+ */
+#define TOPOLOGY_SD_FLAGS		\
+	(SD_SHARE_CPUCAPACITY |		\
+	 SD_SHARE_PKG_RESOURCES |	\
+	 SD_NUMA |			\
+	 SD_ASYM_PACKING |		\
+	 SD_ASYM_CPUCAPACITY |		\
+	 SD_SHARE_POWERDOMAIN)
+
+static struct sched_domain *
+sd_init(struct sched_domain_topology_level *tl,
+	const struct cpumask *cpu_map,
+	struct sched_domain *child, int cpu)
+{
+	struct sd_data *sdd = &tl->data;
+	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
+	int sd_id, sd_weight, sd_flags = 0;
+
+#ifdef CONFIG_NUMA
+	/*
+	 * Ugly hack to pass state to sd_numa_mask()...
+	 */
+	sched_domains_curr_level = tl->numa_level;
+#endif
+
+	sd_weight = cpumask_weight(tl->mask(cpu));
+
+	if (tl->sd_flags)
+		sd_flags = (*tl->sd_flags)();
+	if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
+			"wrong sd_flags in topology description\n"))
+		sd_flags &= ~TOPOLOGY_SD_FLAGS;
+
+	*sd = (struct sched_domain){
+		.min_interval		= sd_weight,
+		.max_interval		= 2*sd_weight,
+		.busy_factor		= 32,
+		.imbalance_pct		= 125,
+
+		.cache_nice_tries	= 0,
+		.busy_idx		= 0,
+		.idle_idx		= 0,
+		.newidle_idx		= 0,
+		.wake_idx		= 0,
+		.forkexec_idx		= 0,
+
+		.flags			= 1*SD_LOAD_BALANCE
+					| 1*SD_BALANCE_NEWIDLE
+					| 1*SD_BALANCE_EXEC
+					| 1*SD_BALANCE_FORK
+					| 0*SD_BALANCE_WAKE
+					| 1*SD_WAKE_AFFINE
+					| 0*SD_SHARE_CPUCAPACITY
+					| 0*SD_SHARE_PKG_RESOURCES
+					| 0*SD_SERIALIZE
+					| 0*SD_PREFER_SIBLING
+					| 0*SD_NUMA
+					| sd_flags
+					,
+
+		.last_balance		= jiffies,
+		.balance_interval	= sd_weight,
+		.smt_gain		= 0,
+		.max_newidle_lb_cost	= 0,
+		.next_decay_max_lb_cost	= jiffies,
+		.child			= child,
+#ifdef CONFIG_SCHED_DEBUG
+		.name			= tl->name,
+#endif
+	};
+
+	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
+	sd_id = cpumask_first(sched_domain_span(sd));
+
+	/*
+	 * Convert topological properties into behaviour.
+	 */
+
+	if (sd->flags & SD_ASYM_CPUCAPACITY) {
+		struct sched_domain *t = sd;
+
+		for_each_lower_domain(t)
+			t->flags |= SD_BALANCE_WAKE;
+	}
+
+	if (sd->flags & SD_SHARE_CPUCAPACITY) {
+		sd->flags |= SD_PREFER_SIBLING;
+		sd->imbalance_pct = 110;
+		sd->smt_gain = 1178; /* ~15% */
+
+	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+		sd->imbalance_pct = 117;
+		sd->cache_nice_tries = 1;
+		sd->busy_idx = 2;
+
+#ifdef CONFIG_NUMA
+	} else if (sd->flags & SD_NUMA) {
+		sd->cache_nice_tries = 2;
+		sd->busy_idx = 3;
+		sd->idle_idx = 2;
+
+		sd->flags |= SD_SERIALIZE;
+		if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
+			sd->flags &= ~(SD_BALANCE_EXEC |
+				       SD_BALANCE_FORK |
+				       SD_WAKE_AFFINE);
+		}
+
+#endif
+	} else {
+		sd->flags |= SD_PREFER_SIBLING;
+		sd->cache_nice_tries = 1;
+		sd->busy_idx = 2;
+		sd->idle_idx = 1;
+	}
+
+	/*
+	 * For all levels sharing cache; connect a sched_domain_shared
+	 * instance.
+	 */
+	if (sd->flags & SD_SHARE_PKG_RESOURCES) {
+		sd->shared = *per_cpu_ptr(sdd->sds, sd_id);
+		atomic_inc(&sd->shared->ref);
+		atomic_set(&sd->shared->nr_busy_cpus, sd_weight);
+	}
+
+	sd->private = sdd;
+
+	return sd;
+}
+
+/*
+ * Topology list, bottom-up.
+ */
+static struct sched_domain_topology_level default_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+	{ cpu_cpu_mask, SD_INIT_NAME(DIE) },
+	{ NULL, },
+};
+
+static struct sched_domain_topology_level *sched_domain_topology =
+	default_topology;
+
+#define for_each_sd_topology(tl)			\
+	for (tl = sched_domain_topology; tl->mask; tl++)
+
+void set_sched_topology(struct sched_domain_topology_level *tl)
+{
+	if (WARN_ON_ONCE(sched_smp_initialized))
+		return;
+
+	sched_domain_topology = tl;
+}
+
+#ifdef CONFIG_NUMA
+
+static const struct cpumask *sd_numa_mask(int cpu)
+{
+	return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
+}
+
+static void sched_numa_warn(const char *str)
+{
+	static int done = false;
+	int i,j;
+
+	if (done)
+		return;
+
+	done = true;
+
+	printk(KERN_WARNING "ERROR: %s\n\n", str);
+
+	for (i = 0; i < nr_node_ids; i++) {
+		printk(KERN_WARNING "  ");
+		for (j = 0; j < nr_node_ids; j++)
+			printk(KERN_CONT "%02d ", node_distance(i,j));
+		printk(KERN_CONT "\n");
+	}
+	printk(KERN_WARNING "\n");
+}
+
+bool find_numa_distance(int distance)
+{
+	int i;
+
+	if (distance == node_distance(0, 0))
+		return true;
+
+	for (i = 0; i < sched_domains_numa_levels; i++) {
+		if (sched_domains_numa_distance[i] == distance)
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * A system can have three types of NUMA topology:
+ * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system
+ * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes
+ * NUMA_BACKPLANE: nodes can reach other nodes through a backplane
+ *
+ * The difference between a glueless mesh topology and a backplane
+ * topology lies in whether communication between not directly
+ * connected nodes goes through intermediary nodes (where programs
+ * could run), or through backplane controllers. This affects
+ * placement of programs.
+ *
+ * The type of topology can be discerned with the following tests:
+ * - If the maximum distance between any nodes is 1 hop, the system
+ *   is directly connected.
+ * - If for two nodes A and B, located N > 1 hops away from each other,
+ *   there is an intermediary node C, which is < N hops away from both
+ *   nodes A and B, the system is a glueless mesh.
+ */
+static void init_numa_topology_type(void)
+{
+	int a, b, c, n;
+
+	n = sched_max_numa_distance;
+
+	if (sched_domains_numa_levels <= 1) {
+		sched_numa_topology_type = NUMA_DIRECT;
+		return;
+	}
+
+	for_each_online_node(a) {
+		for_each_online_node(b) {
+			/* Find two nodes furthest removed from each other. */
+			if (node_distance(a, b) < n)
+				continue;
+
+			/* Is there an intermediary node between a and b? */
+			for_each_online_node(c) {
+				if (node_distance(a, c) < n &&
+				    node_distance(b, c) < n) {
+					sched_numa_topology_type =
+							NUMA_GLUELESS_MESH;
+					return;
+				}
+			}
+
+			sched_numa_topology_type = NUMA_BACKPLANE;
+			return;
+		}
+	}
+}
+
+void sched_init_numa(void)
+{
+	int next_distance, curr_distance = node_distance(0, 0);
+	struct sched_domain_topology_level *tl;
+	int level = 0;
+	int i, j, k;
+
+	sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
+	if (!sched_domains_numa_distance)
+		return;
+
+	/*
+	 * O(nr_nodes^2) deduplicating selection sort -- in order to find the
+	 * unique distances in the node_distance() table.
+	 *
+	 * Assumes node_distance(0,j) includes all distances in
+	 * node_distance(i,j) in order to avoid cubic time.
+	 */
+	next_distance = curr_distance;
+	for (i = 0; i < nr_node_ids; i++) {
+		for (j = 0; j < nr_node_ids; j++) {
+			for (k = 0; k < nr_node_ids; k++) {
+				int distance = node_distance(i, k);
+
+				if (distance > curr_distance &&
+				    (distance < next_distance ||
+				     next_distance == curr_distance))
+					next_distance = distance;
+
+				/*
+				 * While not a strong assumption it would be nice to know
+				 * about cases where if node A is connected to B, B is not
+				 * equally connected to A.
+				 */
+				if (sched_debug() && node_distance(k, i) != distance)
+					sched_numa_warn("Node-distance not symmetric");
+
+				if (sched_debug() && i && !find_numa_distance(distance))
+					sched_numa_warn("Node-0 not representative");
+			}
+			if (next_distance != curr_distance) {
+				sched_domains_numa_distance[level++] = next_distance;
+				sched_domains_numa_levels = level;
+				curr_distance = next_distance;
+			} else break;
+		}
+
+		/*
+		 * In case of sched_debug() we verify the above assumption.
+		 */
+		if (!sched_debug())
+			break;
+	}
+
+	if (!level)
+		return;
+
+	/*
+	 * 'level' contains the number of unique distances, excluding the
+	 * identity distance node_distance(i,i).
+	 *
+	 * The sched_domains_numa_distance[] array includes the actual distance
+	 * numbers.
+	 */
+
+	/*
+	 * Here, we should temporarily reset sched_domains_numa_levels to 0.
+	 * If it fails to allocate memory for array sched_domains_numa_masks[][],
+	 * the array will contain less then 'level' members. This could be
+	 * dangerous when we use it to iterate array sched_domains_numa_masks[][]
+	 * in other functions.
+	 *
+	 * We reset it to 'level' at the end of this function.
+	 */
+	sched_domains_numa_levels = 0;
+
+	sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
+	if (!sched_domains_numa_masks)
+		return;
+
+	/*
+	 * Now for each level, construct a mask per node which contains all
+	 * CPUs of nodes that are that many hops away from us.
+	 */
+	for (i = 0; i < level; i++) {
+		sched_domains_numa_masks[i] =
+			kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
+		if (!sched_domains_numa_masks[i])
+			return;
+
+		for (j = 0; j < nr_node_ids; j++) {
+			struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL);
+			if (!mask)
+				return;
+
+			sched_domains_numa_masks[i][j] = mask;
+
+			for_each_node(k) {
+				if (node_distance(j, k) > sched_domains_numa_distance[i])
+					continue;
+
+				cpumask_or(mask, mask, cpumask_of_node(k));
+			}
+		}
+	}
+
+	/* Compute default topology size */
+	for (i = 0; sched_domain_topology[i].mask; i++);
+
+	tl = kzalloc((i + level + 1) *
+			sizeof(struct sched_domain_topology_level), GFP_KERNEL);
+	if (!tl)
+		return;
+
+	/*
+	 * Copy the default topology bits..
+	 */
+	for (i = 0; sched_domain_topology[i].mask; i++)
+		tl[i] = sched_domain_topology[i];
+
+	/*
+	 * .. and append 'j' levels of NUMA goodness.
+	 */
+	for (j = 0; j < level; i++, j++) {
+		tl[i] = (struct sched_domain_topology_level){
+			.mask = sd_numa_mask,
+			.sd_flags = cpu_numa_flags,
+			.flags = SDTL_OVERLAP,
+			.numa_level = j,
+			SD_INIT_NAME(NUMA)
+		};
+	}
+
+	sched_domain_topology = tl;
+
+	sched_domains_numa_levels = level;
+	sched_max_numa_distance = sched_domains_numa_distance[level - 1];
+
+	init_numa_topology_type();
+}
+
+void sched_domains_numa_masks_set(unsigned int cpu)
+{
+	int node = cpu_to_node(cpu);
+	int i, j;
+
+	for (i = 0; i < sched_domains_numa_levels; i++) {
+		for (j = 0; j < nr_node_ids; j++) {
+			if (node_distance(j, node) <= sched_domains_numa_distance[i])
+				cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
+		}
+	}
+}
+
+void sched_domains_numa_masks_clear(unsigned int cpu)
+{
+	int i, j;
+
+	for (i = 0; i < sched_domains_numa_levels; i++) {
+		for (j = 0; j < nr_node_ids; j++)
+			cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]);
+	}
+}
+
+#endif /* CONFIG_NUMA */
+
+static int __sdt_alloc(const struct cpumask *cpu_map)
+{
+	struct sched_domain_topology_level *tl;
+	int j;
+
+	for_each_sd_topology(tl) {
+		struct sd_data *sdd = &tl->data;
+
+		sdd->sd = alloc_percpu(struct sched_domain *);
+		if (!sdd->sd)
+			return -ENOMEM;
+
+		sdd->sds = alloc_percpu(struct sched_domain_shared *);
+		if (!sdd->sds)
+			return -ENOMEM;
+
+		sdd->sg = alloc_percpu(struct sched_group *);
+		if (!sdd->sg)
+			return -ENOMEM;
+
+		sdd->sgc = alloc_percpu(struct sched_group_capacity *);
+		if (!sdd->sgc)
+			return -ENOMEM;
+
+		for_each_cpu(j, cpu_map) {
+			struct sched_domain *sd;
+			struct sched_domain_shared *sds;
+			struct sched_group *sg;
+			struct sched_group_capacity *sgc;
+
+			sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sd)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sd, j) = sd;
+
+			sds = kzalloc_node(sizeof(struct sched_domain_shared),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sds)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sds, j) = sds;
+
+			sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sg)
+				return -ENOMEM;
+
+			sg->next = sg;
+
+			*per_cpu_ptr(sdd->sg, j) = sg;
+
+			sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sgc)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sgc, j) = sgc;
+		}
+	}
+
+	return 0;
+}
+
+static void __sdt_free(const struct cpumask *cpu_map)
+{
+	struct sched_domain_topology_level *tl;
+	int j;
+
+	for_each_sd_topology(tl) {
+		struct sd_data *sdd = &tl->data;
+
+		for_each_cpu(j, cpu_map) {
+			struct sched_domain *sd;
+
+			if (sdd->sd) {
+				sd = *per_cpu_ptr(sdd->sd, j);
+				if (sd && (sd->flags & SD_OVERLAP))
+					free_sched_groups(sd->groups, 0);
+				kfree(*per_cpu_ptr(sdd->sd, j));
+			}
+
+			if (sdd->sds)
+				kfree(*per_cpu_ptr(sdd->sds, j));
+			if (sdd->sg)
+				kfree(*per_cpu_ptr(sdd->sg, j));
+			if (sdd->sgc)
+				kfree(*per_cpu_ptr(sdd->sgc, j));
+		}
+		free_percpu(sdd->sd);
+		sdd->sd = NULL;
+		free_percpu(sdd->sds);
+		sdd->sds = NULL;
+		free_percpu(sdd->sg);
+		sdd->sg = NULL;
+		free_percpu(sdd->sgc);
+		sdd->sgc = NULL;
+	}
+}
+
+struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
+		const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+		struct sched_domain *child, int cpu)
+{
+	struct sched_domain *sd = sd_init(tl, cpu_map, child, cpu);
+
+	if (child) {
+		sd->level = child->level + 1;
+		sched_domain_level_max = max(sched_domain_level_max, sd->level);
+		child->parent = sd;
+
+		if (!cpumask_subset(sched_domain_span(child),
+				    sched_domain_span(sd))) {
+			pr_err("BUG: arch topology borken\n");
+#ifdef CONFIG_SCHED_DEBUG
+			pr_err("     the %s domain not a subset of the %s domain\n",
+					child->name, sd->name);
+#endif
+			/* Fixup, ensure @sd has at least @child cpus. */
+			cpumask_or(sched_domain_span(sd),
+				   sched_domain_span(sd),
+				   sched_domain_span(child));
+		}
+
+	}
+	set_domain_attribute(sd, attr);
+
+	return sd;
+}
+
+/*
+ * Build sched domains for a given set of CPUs and attach the sched domains
+ * to the individual CPUs
+ */
+static int
+build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr)
+{
+	enum s_alloc alloc_state;
+	struct sched_domain *sd;
+	struct s_data d;
+	struct rq *rq = NULL;
+	int i, ret = -ENOMEM;
+
+	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
+	if (alloc_state != sa_rootdomain)
+		goto error;
+
+	/* Set up domains for CPUs specified by the cpu_map: */
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain_topology_level *tl;
+
+		sd = NULL;
+		for_each_sd_topology(tl) {
+			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
+			if (tl == sched_domain_topology)
+				*per_cpu_ptr(d.sd, i) = sd;
+			if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
+				sd->flags |= SD_OVERLAP;
+			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
+				break;
+		}
+	}
+
+	/* Build the groups for the domains */
+	for_each_cpu(i, cpu_map) {
+		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+			sd->span_weight = cpumask_weight(sched_domain_span(sd));
+			if (sd->flags & SD_OVERLAP) {
+				if (build_overlap_sched_groups(sd, i))
+					goto error;
+			} else {
+				if (build_sched_groups(sd, i))
+					goto error;
+			}
+		}
+	}
+
+	/* Calculate CPU capacity for physical packages and nodes */
+	for (i = nr_cpumask_bits-1; i >= 0; i--) {
+		if (!cpumask_test_cpu(i, cpu_map))
+			continue;
+
+		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+			claim_allocations(i, sd);
+			init_sched_groups_capacity(i, sd);
+		}
+	}
+
+	/* Attach the domains */
+	rcu_read_lock();
+	for_each_cpu(i, cpu_map) {
+		rq = cpu_rq(i);
+		sd = *per_cpu_ptr(d.sd, i);
+
+		/* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */
+		if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity))
+			WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig);
+
+		cpu_attach_domain(sd, d.rd, i);
+	}
+	rcu_read_unlock();
+
+	if (rq && sched_debug_enabled) {
+		pr_info("span: %*pbl (max cpu_capacity = %lu)\n",
+			cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity);
+	}
+
+	ret = 0;
+error:
+	__free_domain_allocs(&d, alloc_state, cpu_map);
+	return ret;
+}
+
+/* Current sched domains: */
+static cpumask_var_t			*doms_cur;
+
+/* Number of sched domains in 'doms_cur': */
+static int				ndoms_cur;
+
+/* Attribues of custom domains in 'doms_cur' */
+static struct sched_domain_attr		*dattr_cur;
+
+/*
+ * Special case: If a kmalloc() of a doms_cur partition (array of
+ * cpumask) fails, then fallback to a single sched domain,
+ * as determined by the single cpumask fallback_doms.
+ */
+cpumask_var_t				fallback_doms;
+
+/*
+ * arch_update_cpu_topology lets virtualized architectures update the
+ * CPU core maps. It is supposed to return 1 if the topology changed
+ * or 0 if it stayed the same.
+ */
+int __weak arch_update_cpu_topology(void)
+{
+	return 0;
+}
+
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
+{
+	int i;
+	cpumask_var_t *doms;
+
+	doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
+	if (!doms)
+		return NULL;
+	for (i = 0; i < ndoms; i++) {
+		if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
+			free_sched_domains(doms, i);
+			return NULL;
+		}
+	}
+	return doms;
+}
+
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
+{
+	unsigned int i;
+	for (i = 0; i < ndoms; i++)
+		free_cpumask_var(doms[i]);
+	kfree(doms);
+}
+
+/*
+ * Set up scheduler domains and groups. Callers must hold the hotplug lock.
+ * For now this just excludes isolated CPUs, but could be used to
+ * exclude other special cases in the future.
+ */
+int init_sched_domains(const struct cpumask *cpu_map)
+{
+	int err;
+
+	arch_update_cpu_topology();
+	ndoms_cur = 1;
+	doms_cur = alloc_sched_domains(ndoms_cur);
+	if (!doms_cur)
+		doms_cur = &fallback_doms;
+	cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
+	err = build_sched_domains(doms_cur[0], NULL);
+	register_sched_domain_sysctl();
+
+	return err;
+}
+
+/*
+ * Detach sched domains from a group of CPUs specified in cpu_map
+ * These CPUs will now be attached to the NULL domain
+ */
+static void detach_destroy_domains(const struct cpumask *cpu_map)
+{
+	int i;
+
+	rcu_read_lock();
+	for_each_cpu(i, cpu_map)
+		cpu_attach_domain(NULL, &def_root_domain, i);
+	rcu_read_unlock();
+}
+
+/* handle null as "default" */
+static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
+			struct sched_domain_attr *new, int idx_new)
+{
+	struct sched_domain_attr tmp;
+
+	/* Fast path: */
+	if (!new && !cur)
+		return 1;
+
+	tmp = SD_ATTR_INIT;
+	return !memcmp(cur ? (cur + idx_cur) : &tmp,
+			new ? (new + idx_new) : &tmp,
+			sizeof(struct sched_domain_attr));
+}
+
+/*
+ * Partition sched domains as specified by the 'ndoms_new'
+ * cpumasks in the array doms_new[] of cpumasks. This compares
+ * doms_new[] to the current sched domain partitioning, doms_cur[].
+ * It destroys each deleted domain and builds each new domain.
+ *
+ * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
+ * The masks don't intersect (don't overlap.) We should setup one
+ * sched domain for each mask. CPUs not in any of the cpumasks will
+ * not be load balanced. If the same cpumask appears both in the
+ * current 'doms_cur' domains and in the new 'doms_new', we can leave
+ * it as it is.
+ *
+ * The passed in 'doms_new' should be allocated using
+ * alloc_sched_domains.  This routine takes ownership of it and will
+ * free_sched_domains it when done with it. If the caller failed the
+ * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
+ * and partition_sched_domains() will fallback to the single partition
+ * 'fallback_doms', it also forces the domains to be rebuilt.
+ *
+ * If doms_new == NULL it will be replaced with cpu_online_mask.
+ * ndoms_new == 0 is a special case for destroying existing domains,
+ * and it will not create the default domain.
+ *
+ * Call with hotplug lock held
+ */
+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+			     struct sched_domain_attr *dattr_new)
+{
+	int i, j, n;
+	int new_topology;
+
+	mutex_lock(&sched_domains_mutex);
+
+	/* Always unregister in case we don't destroy any domains: */
+	unregister_sched_domain_sysctl();
+
+	/* Let the architecture update CPU core mappings: */
+	new_topology = arch_update_cpu_topology();
+
+	n = doms_new ? ndoms_new : 0;
+
+	/* Destroy deleted domains: */
+	for (i = 0; i < ndoms_cur; i++) {
+		for (j = 0; j < n && !new_topology; j++) {
+			if (cpumask_equal(doms_cur[i], doms_new[j])
+			    && dattrs_equal(dattr_cur, i, dattr_new, j))
+				goto match1;
+		}
+		/* No match - a current sched domain not in new doms_new[] */
+		detach_destroy_domains(doms_cur[i]);
+match1:
+		;
+	}
+
+	n = ndoms_cur;
+	if (doms_new == NULL) {
+		n = 0;
+		doms_new = &fallback_doms;
+		cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
+		WARN_ON_ONCE(dattr_new);
+	}
+
+	/* Build new domains: */
+	for (i = 0; i < ndoms_new; i++) {
+		for (j = 0; j < n && !new_topology; j++) {
+			if (cpumask_equal(doms_new[i], doms_cur[j])
+			    && dattrs_equal(dattr_new, i, dattr_cur, j))
+				goto match2;
+		}
+		/* No match - add a new doms_new */
+		build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
+match2:
+		;
+	}
+
+	/* Remember the new sched domains: */
+	if (doms_cur != &fallback_doms)
+		free_sched_domains(doms_cur, ndoms_cur);
+
+	kfree(dattr_cur);
+	doms_cur = doms_new;
+	dattr_cur = dattr_new;
+	ndoms_cur = ndoms_new;
+
+	register_sched_domain_sysctl();
+
+	mutex_unlock(&sched_domains_mutex);
+}
+
diff --git a/kernel/signal.c b/kernel/signal.c
index 3603d93a1968..13f9def8b24a 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1581,7 +1581,7 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 	unsigned long flags;
 	struct sighand_struct *psig;
 	bool autoreap = false;
-	cputime_t utime, stime;
+	u64 utime, stime;
 
 	BUG_ON(sig == -1);
 
@@ -1620,8 +1620,8 @@ bool do_notify_parent(struct task_struct *tsk, int sig)
 	rcu_read_unlock();
 
 	task_cputime(tsk, &utime, &stime);
-	info.si_utime = cputime_to_clock_t(utime + tsk->signal->utime);
-	info.si_stime = cputime_to_clock_t(stime + tsk->signal->stime);
+	info.si_utime = nsec_to_clock_t(utime + tsk->signal->utime);
+	info.si_stime = nsec_to_clock_t(stime + tsk->signal->stime);
 
 	info.si_status = tsk->exit_code & 0x7f;
 	if (tsk->exit_code & 0x80)
@@ -1685,7 +1685,7 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
 	unsigned long flags;
 	struct task_struct *parent;
 	struct sighand_struct *sighand;
-	cputime_t utime, stime;
+	u64 utime, stime;
 
 	if (for_ptracer) {
 		parent = tsk->parent;
@@ -1705,8 +1705,8 @@ static void do_notify_parent_cldstop(struct task_struct *tsk,
 	rcu_read_unlock();
 
 	task_cputime(tsk, &utime, &stime);
-	info.si_utime = cputime_to_clock_t(utime);
-	info.si_stime = cputime_to_clock_t(stime);
+	info.si_utime = nsec_to_clock_t(utime);
+	info.si_stime = nsec_to_clock_t(stime);
 
  	info.si_code = why;
  	switch (why) {
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index b6e4c16377c7..9c15a9124e83 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -18,10 +18,8 @@ void print_stack_trace(struct stack_trace *trace, int spaces)
 	if (WARN_ON(!trace->entries))
 		return;
 
-	for (i = 0; i < trace->nr_entries; i++) {
-		printk("%*c", 1 + spaces, ' ');
-		print_ip_sym(trace->entries[i]);
-	}
+	for (i = 0; i < trace->nr_entries; i++)
+		printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]);
 }
 EXPORT_SYMBOL_GPL(print_stack_trace);
 
@@ -29,7 +27,6 @@ int snprint_stack_trace(char *buf, size_t size,
 			struct stack_trace *trace, int spaces)
 {
 	int i;
-	unsigned long ip;
 	int generated;
 	int total = 0;
 
@@ -37,9 +34,8 @@ int snprint_stack_trace(char *buf, size_t size,
 		return 0;
 
 	for (i = 0; i < trace->nr_entries; i++) {
-		ip = trace->entries[i];
-		generated = snprintf(buf, size, "%*c[<%p>] %pS\n",
-				1 + spaces, ' ', (void *) ip, (void *) ip);
+		generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ',
+				     (void *)trace->entries[i]);
 
 		total += generated;
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 842914ef7de4..7d4a9a6df956 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -881,15 +881,15 @@ SYSCALL_DEFINE0(getegid)
 
 void do_sys_times(struct tms *tms)
 {
-	cputime_t tgutime, tgstime, cutime, cstime;
+	u64 tgutime, tgstime, cutime, cstime;
 
 	thread_group_cputime_adjusted(current, &tgutime, &tgstime);
 	cutime = current->signal->cutime;
 	cstime = current->signal->cstime;
-	tms->tms_utime = cputime_to_clock_t(tgutime);
-	tms->tms_stime = cputime_to_clock_t(tgstime);
-	tms->tms_cutime = cputime_to_clock_t(cutime);
-	tms->tms_cstime = cputime_to_clock_t(cstime);
+	tms->tms_utime = nsec_to_clock_t(tgutime);
+	tms->tms_stime = nsec_to_clock_t(tgstime);
+	tms->tms_cutime = nsec_to_clock_t(cutime);
+	tms->tms_cstime = nsec_to_clock_t(cstime);
 }
 
 SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
@@ -1544,7 +1544,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 {
 	struct task_struct *t;
 	unsigned long flags;
-	cputime_t tgutime, tgstime, utime, stime;
+	u64 tgutime, tgstime, utime, stime;
 	unsigned long maxrss = 0;
 
 	memset((char *)r, 0, sizeof (*r));
@@ -1600,8 +1600,8 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	unlock_task_sighand(p, &flags);
 
 out:
-	cputime_to_timeval(utime, &r->ru_utime);
-	cputime_to_timeval(stime, &r->ru_stime);
+	r->ru_utime = ns_to_timeval(utime);
+	r->ru_stime = ns_to_timeval(stime);
 
 	if (who != RUSAGE_CHILDREN) {
 		struct mm_struct *mm = get_task_mm(p);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 8dbaec0e4f7f..bb260ceb3718 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -416,7 +416,7 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.procname	= "sched_rr_timeslice_ms",
-		.data		= &sched_rr_timeslice,
+		.data		= &sysctl_sched_rr_timeslice,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= sched_rr_handler,
@@ -2475,6 +2475,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int
 				break;
 			if (neg)
 				continue;
+			val = convmul * val / convdiv;
 			if ((min && val < *min) || (max && val > *max))
 				continue;
 			*i = val;
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 976840d29a71..938dbf33ef49 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -15,6 +15,5 @@ ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
 endif
 obj-$(CONFIG_GENERIC_SCHED_CLOCK)		+= sched_clock.o
 obj-$(CONFIG_TICK_ONESHOT)			+= tick-oneshot.o tick-sched.o
-obj-$(CONFIG_TIMER_STATS)			+= timer_stats.o
 obj-$(CONFIG_DEBUG_FS)				+= timekeeping_debug.o
 obj-$(CONFIG_TEST_UDELAY)			+= test_udelay.o
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 665985b0a89a..93621ae718d3 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -141,6 +141,10 @@ static void __clocksource_unstable(struct clocksource *cs)
 {
 	cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG);
 	cs->flags |= CLOCK_SOURCE_UNSTABLE;
+
+	if (cs->mark_unstable)
+		cs->mark_unstable(cs);
+
 	if (finished_booting)
 		schedule_work(&watchdog_work);
 }
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index c6ecedd3b839..8e11d8d9f419 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -94,17 +94,15 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) =
 };
 
 static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = {
+	/* Make sure we catch unsupported clockids */
+	[0 ... MAX_CLOCKS - 1]	= HRTIMER_MAX_CLOCK_BASES,
+
 	[CLOCK_REALTIME]	= HRTIMER_BASE_REALTIME,
 	[CLOCK_MONOTONIC]	= HRTIMER_BASE_MONOTONIC,
 	[CLOCK_BOOTTIME]	= HRTIMER_BASE_BOOTTIME,
 	[CLOCK_TAI]		= HRTIMER_BASE_TAI,
 };
 
-static inline int hrtimer_clockid_to_base(clockid_t clock_id)
-{
-	return hrtimer_clock_to_base_table[clock_id];
-}
-
 /*
  * Functions and macros which are different for UP/SMP systems are kept in a
  * single place
@@ -766,34 +764,6 @@ void hrtimers_resume(void)
 	clock_was_set_delayed();
 }
 
-static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer)
-{
-#ifdef CONFIG_TIMER_STATS
-	if (timer->start_site)
-		return;
-	timer->start_site = __builtin_return_address(0);
-	memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
-	timer->start_pid = current->pid;
-#endif
-}
-
-static inline void timer_stats_hrtimer_clear_start_info(struct hrtimer *timer)
-{
-#ifdef CONFIG_TIMER_STATS
-	timer->start_site = NULL;
-#endif
-}
-
-static inline void timer_stats_account_hrtimer(struct hrtimer *timer)
-{
-#ifdef CONFIG_TIMER_STATS
-	if (likely(!timer_stats_active))
-		return;
-	timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
-				 timer->function, timer->start_comm, 0);
-#endif
-}
-
 /*
  * Counterpart to lock_hrtimer_base above:
  */
@@ -932,7 +902,6 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool rest
 		 * rare case and less expensive than a smp call.
 		 */
 		debug_deactivate(timer);
-		timer_stats_hrtimer_clear_start_info(timer);
 		reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases);
 
 		if (!restart)
@@ -990,8 +959,6 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Switch the timer base, if necessary: */
 	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
 
-	timer_stats_hrtimer_set_start_info(timer);
-
 	leftmost = enqueue_hrtimer(timer, new_base);
 	if (!leftmost)
 		goto unlock;
@@ -1112,6 +1079,18 @@ u64 hrtimer_get_next_event(void)
 }
 #endif
 
+static inline int hrtimer_clockid_to_base(clockid_t clock_id)
+{
+	if (likely(clock_id < MAX_CLOCKS)) {
+		int base = hrtimer_clock_to_base_table[clock_id];
+
+		if (likely(base != HRTIMER_MAX_CLOCK_BASES))
+			return base;
+	}
+	WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id);
+	return HRTIMER_BASE_MONOTONIC;
+}
+
 static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 			   enum hrtimer_mode mode)
 {
@@ -1128,12 +1107,6 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id,
 	base = hrtimer_clockid_to_base(clock_id);
 	timer->base = &cpu_base->clock_base[base];
 	timerqueue_init(&timer->node);
-
-#ifdef CONFIG_TIMER_STATS
-	timer->start_site = NULL;
-	timer->start_pid = -1;
-	memset(timer->start_comm, 0, TASK_COMM_LEN);
-#endif
 }
 
 /**
@@ -1217,7 +1190,6 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
 	raw_write_seqcount_barrier(&cpu_base->seq);
 
 	__remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0);
-	timer_stats_account_hrtimer(timer);
 	fn = timer->function;
 
 	/*
diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c
index 8c89143f9ebf..a95f13c31464 100644
--- a/kernel/time/itimer.c
+++ b/kernel/time/itimer.c
@@ -45,16 +45,16 @@ static struct timeval itimer_get_remtime(struct hrtimer *timer)
 static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
 			   struct itimerval *const value)
 {
-	cputime_t cval, cinterval;
+	u64 val, interval;
 	struct cpu_itimer *it = &tsk->signal->it[clock_id];
 
 	spin_lock_irq(&tsk->sighand->siglock);
 
-	cval = it->expires;
-	cinterval = it->incr;
-	if (cval) {
+	val = it->expires;
+	interval = it->incr;
+	if (val) {
 		struct task_cputime cputime;
-		cputime_t t;
+		u64 t;
 
 		thread_group_cputimer(tsk, &cputime);
 		if (clock_id == CPUCLOCK_PROF)
@@ -63,17 +63,17 @@ static void get_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
 			/* CPUCLOCK_VIRT */
 			t = cputime.utime;
 
-		if (cval < t)
+		if (val < t)
 			/* about to fire */
-			cval = cputime_one_jiffy;
+			val = TICK_NSEC;
 		else
-			cval = cval - t;
+			val -= t;
 	}
 
 	spin_unlock_irq(&tsk->sighand->siglock);
 
-	cputime_to_timeval(cval, &value->it_value);
-	cputime_to_timeval(cinterval, &value->it_interval);
+	value->it_value = ns_to_timeval(val);
+	value->it_interval = ns_to_timeval(interval);
 }
 
 int do_getitimer(int which, struct itimerval *value)
@@ -129,55 +129,35 @@ enum hrtimer_restart it_real_fn(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-static inline u32 cputime_sub_ns(cputime_t ct, s64 real_ns)
-{
-	struct timespec ts;
-	s64 cpu_ns;
-
-	cputime_to_timespec(ct, &ts);
-	cpu_ns = timespec_to_ns(&ts);
-
-	return (cpu_ns <= real_ns) ? 0 : cpu_ns - real_ns;
-}
-
 static void set_cpu_itimer(struct task_struct *tsk, unsigned int clock_id,
 			   const struct itimerval *const value,
 			   struct itimerval *const ovalue)
 {
-	cputime_t cval, nval, cinterval, ninterval;
-	s64 ns_ninterval, ns_nval;
-	u32 error, incr_error;
+	u64 oval, nval, ointerval, ninterval;
 	struct cpu_itimer *it = &tsk->signal->it[clock_id];
 
-	nval = timeval_to_cputime(&value->it_value);
-	ns_nval = timeval_to_ns(&value->it_value);
-	ninterval = timeval_to_cputime(&value->it_interval);
-	ns_ninterval = timeval_to_ns(&value->it_interval);
-
-	error = cputime_sub_ns(nval, ns_nval);
-	incr_error = cputime_sub_ns(ninterval, ns_ninterval);
+	nval = timeval_to_ns(&value->it_value);
+	ninterval = timeval_to_ns(&value->it_interval);
 
 	spin_lock_irq(&tsk->sighand->siglock);
 
-	cval = it->expires;
-	cinterval = it->incr;
-	if (cval || nval) {
+	oval = it->expires;
+	ointerval = it->incr;
+	if (oval || nval) {
 		if (nval > 0)
-			nval += cputime_one_jiffy;
-		set_process_cpu_timer(tsk, clock_id, &nval, &cval);
+			nval += TICK_NSEC;
+		set_process_cpu_timer(tsk, clock_id, &nval, &oval);
 	}
 	it->expires = nval;
 	it->incr = ninterval;
-	it->error = error;
-	it->incr_error = incr_error;
 	trace_itimer_state(clock_id == CPUCLOCK_VIRT ?
 			   ITIMER_VIRTUAL : ITIMER_PROF, value, nval);
 
 	spin_unlock_irq(&tsk->sighand->siglock);
 
 	if (ovalue) {
-		cputime_to_timeval(cval, &ovalue->it_value);
-		cputime_to_timeval(cinterval, &ovalue->it_interval);
+		ovalue->it_value = ns_to_timeval(oval);
+		ovalue->it_interval = ns_to_timeval(ointerval);
 	}
 }
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index a4a0e478e44d..7906b3f0c41a 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -27,19 +27,8 @@
 
 #include "timekeeping.h"
 
-/* The Jiffies based clocksource is the lowest common
- * denominator clock source which should function on
- * all systems. It has the same coarse resolution as
- * the timer interrupt frequency HZ and it suffers
- * inaccuracies caused by missed or lost timer
- * interrupts and the inability for the timer
- * interrupt hardware to accuratly tick at the
- * requested HZ value. It is also not recommended
- * for "tick-less" systems.
- */
-#define NSEC_PER_JIFFY	((NSEC_PER_SEC+HZ/2)/HZ)
 
-/* Since jiffies uses a simple NSEC_PER_JIFFY multiplier
+/* Since jiffies uses a simple TICK_NSEC multiplier
  * conversion, the .shift value could be zero. However
  * this would make NTP adjustments impossible as they are
  * in units of 1/2^.shift. Thus we use JIFFIES_SHIFT to
@@ -47,8 +36,8 @@
  * amount, and give ntp adjustments in units of 1/2^8
  *
  * The value 8 is somewhat carefully chosen, as anything
- * larger can result in overflows. NSEC_PER_JIFFY grows as
- * HZ shrinks, so values greater than 8 overflow 32bits when
+ * larger can result in overflows. TICK_NSEC grows as HZ
+ * shrinks, so values greater than 8 overflow 32bits when
  * HZ=100.
  */
 #if HZ < 34
@@ -64,12 +53,23 @@ static u64 jiffies_read(struct clocksource *cs)
 	return (u64) jiffies;
 }
 
+/*
+ * The Jiffies based clocksource is the lowest common
+ * denominator clock source which should function on
+ * all systems. It has the same coarse resolution as
+ * the timer interrupt frequency HZ and it suffers
+ * inaccuracies caused by missed or lost timer
+ * interrupts and the inability for the timer
+ * interrupt hardware to accuratly tick at the
+ * requested HZ value. It is also not recommended
+ * for "tick-less" systems.
+ */
 static struct clocksource clocksource_jiffies = {
 	.name		= "jiffies",
 	.rating		= 1, /* lowest valid rating*/
 	.read		= jiffies_read,
 	.mask		= CLOCKSOURCE_MASK(32),
-	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
+	.mult		= TICK_NSEC << JIFFIES_SHIFT, /* details above */
 	.shift		= JIFFIES_SHIFT,
 	.max_cycles	= 10,
 };
@@ -125,7 +125,7 @@ int register_refined_jiffies(long cycles_per_second)
 	shift_hz += cycles_per_tick/2;
 	do_div(shift_hz, cycles_per_tick);
 	/* Calculate nsec_per_tick using shift_hz */
-	nsec_per_tick = (u64)NSEC_PER_SEC << 8;
+	nsec_per_tick = (u64)TICK_NSEC << 8;
 	nsec_per_tick += (u32)shift_hz/2;
 	do_div(nsec_per_tick, (u32)shift_hz);
 
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index e9e8c10f0d9a..b4377a5e4269 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -20,10 +20,10 @@
  */
 void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
 {
-	cputime_t cputime = secs_to_cputime(rlim_new);
+	u64 nsecs = rlim_new * NSEC_PER_SEC;
 
 	spin_lock_irq(&task->sighand->siglock);
-	set_process_cpu_timer(task, CPUCLOCK_PROF, &cputime, NULL);
+	set_process_cpu_timer(task, CPUCLOCK_PROF, &nsecs, NULL);
 	spin_unlock_irq(&task->sighand->siglock);
 }
 
@@ -50,39 +50,14 @@ static int check_clock(const clockid_t which_clock)
 	return error;
 }
 
-static inline unsigned long long
-timespec_to_sample(const clockid_t which_clock, const struct timespec *tp)
-{
-	unsigned long long ret;
-
-	ret = 0;		/* high half always zero when .cpu used */
-	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) {
-		ret = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec;
-	} else {
-		ret = cputime_to_expires(timespec_to_cputime(tp));
-	}
-	return ret;
-}
-
-static void sample_to_timespec(const clockid_t which_clock,
-			       unsigned long long expires,
-			       struct timespec *tp)
-{
-	if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED)
-		*tp = ns_to_timespec(expires);
-	else
-		cputime_to_timespec((__force cputime_t)expires, tp);
-}
-
 /*
  * Update expiry time from increment, and increase overrun count,
  * given the current clock sample.
  */
-static void bump_cpu_timer(struct k_itimer *timer,
-			   unsigned long long now)
+static void bump_cpu_timer(struct k_itimer *timer, u64 now)
 {
 	int i;
-	unsigned long long delta, incr;
+	u64 delta, incr;
 
 	if (timer->it.cpu.incr == 0)
 		return;
@@ -122,21 +97,21 @@ static inline int task_cputime_zero(const struct task_cputime *cputime)
 	return 0;
 }
 
-static inline unsigned long long prof_ticks(struct task_struct *p)
+static inline u64 prof_ticks(struct task_struct *p)
 {
-	cputime_t utime, stime;
+	u64 utime, stime;
 
 	task_cputime(p, &utime, &stime);
 
-	return cputime_to_expires(utime + stime);
+	return utime + stime;
 }
-static inline unsigned long long virt_ticks(struct task_struct *p)
+static inline u64 virt_ticks(struct task_struct *p)
 {
-	cputime_t utime, stime;
+	u64 utime, stime;
 
 	task_cputime(p, &utime, &stime);
 
-	return cputime_to_expires(utime);
+	return utime;
 }
 
 static int
@@ -176,8 +151,8 @@ posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp)
 /*
  * Sample a per-thread clock for the given task.
  */
-static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
-			    unsigned long long *sample)
+static int cpu_clock_sample(const clockid_t which_clock,
+			    struct task_struct *p, u64 *sample)
 {
 	switch (CPUCLOCK_WHICH(which_clock)) {
 	default:
@@ -260,7 +235,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times)
  */
 static int cpu_clock_sample_group(const clockid_t which_clock,
 				  struct task_struct *p,
-				  unsigned long long *sample)
+				  u64 *sample)
 {
 	struct task_cputime cputime;
 
@@ -269,11 +244,11 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 		return -EINVAL;
 	case CPUCLOCK_PROF:
 		thread_group_cputime(p, &cputime);
-		*sample = cputime_to_expires(cputime.utime + cputime.stime);
+		*sample = cputime.utime + cputime.stime;
 		break;
 	case CPUCLOCK_VIRT:
 		thread_group_cputime(p, &cputime);
-		*sample = cputime_to_expires(cputime.utime);
+		*sample = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
 		thread_group_cputime(p, &cputime);
@@ -288,7 +263,7 @@ static int posix_cpu_clock_get_task(struct task_struct *tsk,
 				    struct timespec *tp)
 {
 	int err = -EINVAL;
-	unsigned long long rtn;
+	u64 rtn;
 
 	if (CPUCLOCK_PERTHREAD(which_clock)) {
 		if (same_thread_group(tsk, current))
@@ -299,7 +274,7 @@ static int posix_cpu_clock_get_task(struct task_struct *tsk,
 	}
 
 	if (!err)
-		sample_to_timespec(which_clock, rtn, tp);
+		*tp = ns_to_timespec(rtn);
 
 	return err;
 }
@@ -453,7 +428,7 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk)
 	cleanup_timers(tsk->signal->cpu_timers);
 }
 
-static inline int expires_gt(cputime_t expires, cputime_t new_exp)
+static inline int expires_gt(u64 expires, u64 new_exp)
 {
 	return expires == 0 || expires > new_exp;
 }
@@ -488,7 +463,7 @@ static void arm_timer(struct k_itimer *timer)
 	list_add(&nt->entry, listpos);
 
 	if (listpos == head) {
-		unsigned long long exp = nt->expires;
+		u64 exp = nt->expires;
 
 		/*
 		 * We are the new earliest-expiring POSIX 1.b timer, hence
@@ -499,16 +474,15 @@ static void arm_timer(struct k_itimer *timer)
 
 		switch (CPUCLOCK_WHICH(timer->it_clock)) {
 		case CPUCLOCK_PROF:
-			if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp)))
-				cputime_expires->prof_exp = expires_to_cputime(exp);
+			if (expires_gt(cputime_expires->prof_exp, exp))
+				cputime_expires->prof_exp = exp;
 			break;
 		case CPUCLOCK_VIRT:
-			if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp)))
-				cputime_expires->virt_exp = expires_to_cputime(exp);
+			if (expires_gt(cputime_expires->virt_exp, exp))
+				cputime_expires->virt_exp = exp;
 			break;
 		case CPUCLOCK_SCHED:
-			if (cputime_expires->sched_exp == 0 ||
-			    cputime_expires->sched_exp > exp)
+			if (expires_gt(cputime_expires->sched_exp, exp))
 				cputime_expires->sched_exp = exp;
 			break;
 		}
@@ -559,8 +533,7 @@ static void cpu_timer_fire(struct k_itimer *timer)
  * traversal.
  */
 static int cpu_timer_sample_group(const clockid_t which_clock,
-				  struct task_struct *p,
-				  unsigned long long *sample)
+				  struct task_struct *p, u64 *sample)
 {
 	struct task_cputime cputime;
 
@@ -569,10 +542,10 @@ static int cpu_timer_sample_group(const clockid_t which_clock,
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
-		*sample = cputime_to_expires(cputime.utime + cputime.stime);
+		*sample = cputime.utime + cputime.stime;
 		break;
 	case CPUCLOCK_VIRT:
-		*sample = cputime_to_expires(cputime.utime);
+		*sample = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
 		*sample = cputime.sum_exec_runtime;
@@ -593,12 +566,12 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	unsigned long flags;
 	struct sighand_struct *sighand;
 	struct task_struct *p = timer->it.cpu.task;
-	unsigned long long old_expires, new_expires, old_incr, val;
+	u64 old_expires, new_expires, old_incr, val;
 	int ret;
 
 	WARN_ON_ONCE(p == NULL);
 
-	new_expires = timespec_to_sample(timer->it_clock, &new->it_value);
+	new_expires = timespec_to_ns(&new->it_value);
 
 	/*
 	 * Protect against sighand release/switch in exit/exec and p->cpu_timers
@@ -659,9 +632,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 			bump_cpu_timer(timer, val);
 			if (val < timer->it.cpu.expires) {
 				old_expires = timer->it.cpu.expires - val;
-				sample_to_timespec(timer->it_clock,
-						   old_expires,
-						   &old->it_value);
+				old->it_value = ns_to_timespec(old_expires);
 			} else {
 				old->it_value.tv_nsec = 1;
 				old->it_value.tv_sec = 0;
@@ -699,8 +670,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 	 * Install the new reload setting, and
 	 * set up the signal and overrun bookkeeping.
 	 */
-	timer->it.cpu.incr = timespec_to_sample(timer->it_clock,
-						&new->it_interval);
+	timer->it.cpu.incr = timespec_to_ns(&new->it_interval);
 
 	/*
 	 * This acts as a modification timestamp for the timer,
@@ -723,17 +693,15 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
 
 	ret = 0;
  out:
-	if (old) {
-		sample_to_timespec(timer->it_clock,
-				   old_incr, &old->it_interval);
-	}
+	if (old)
+		old->it_interval = ns_to_timespec(old_incr);
 
 	return ret;
 }
 
 static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 {
-	unsigned long long now;
+	u64 now;
 	struct task_struct *p = timer->it.cpu.task;
 
 	WARN_ON_ONCE(p == NULL);
@@ -741,8 +709,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	/*
 	 * Easy part: convert the reload time.
 	 */
-	sample_to_timespec(timer->it_clock,
-			   timer->it.cpu.incr, &itp->it_interval);
+	itp->it_interval = ns_to_timespec(timer->it.cpu.incr);
 
 	if (timer->it.cpu.expires == 0) {	/* Timer not armed at all.  */
 		itp->it_value.tv_sec = itp->it_value.tv_nsec = 0;
@@ -771,8 +738,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 			 * Call the timer disarmed, nothing else to do.
 			 */
 			timer->it.cpu.expires = 0;
-			sample_to_timespec(timer->it_clock, timer->it.cpu.expires,
-					   &itp->it_value);
+			itp->it_value = ns_to_timespec(timer->it.cpu.expires);
 			return;
 		} else {
 			cpu_timer_sample_group(timer->it_clock, p, &now);
@@ -781,9 +747,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp)
 	}
 
 	if (now < timer->it.cpu.expires) {
-		sample_to_timespec(timer->it_clock,
-				   timer->it.cpu.expires - now,
-				   &itp->it_value);
+		itp->it_value = ns_to_timespec(timer->it.cpu.expires - now);
 	} else {
 		/*
 		 * The timer should have expired already, but the firing
@@ -827,7 +791,7 @@ static void check_thread_timers(struct task_struct *tsk,
 	struct list_head *timers = tsk->cpu_timers;
 	struct signal_struct *const sig = tsk->signal;
 	struct task_cputime *tsk_expires = &tsk->cputime_expires;
-	unsigned long long expires;
+	u64 expires;
 	unsigned long soft;
 
 	/*
@@ -838,10 +802,10 @@ static void check_thread_timers(struct task_struct *tsk,
 		return;
 
 	expires = check_timers_list(timers, firing, prof_ticks(tsk));
-	tsk_expires->prof_exp = expires_to_cputime(expires);
+	tsk_expires->prof_exp = expires;
 
 	expires = check_timers_list(++timers, firing, virt_ticks(tsk));
-	tsk_expires->virt_exp = expires_to_cputime(expires);
+	tsk_expires->virt_exp = expires;
 
 	tsk_expires->sched_exp = check_timers_list(++timers, firing,
 						   tsk->se.sum_exec_runtime);
@@ -890,26 +854,17 @@ static inline void stop_process_timers(struct signal_struct *sig)
 	tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER);
 }
 
-static u32 onecputick;
-
 static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
-			     unsigned long long *expires,
-			     unsigned long long cur_time, int signo)
+			     u64 *expires, u64 cur_time, int signo)
 {
 	if (!it->expires)
 		return;
 
 	if (cur_time >= it->expires) {
-		if (it->incr) {
+		if (it->incr)
 			it->expires += it->incr;
-			it->error += it->incr_error;
-			if (it->error >= onecputick) {
-				it->expires -= cputime_one_jiffy;
-				it->error -= onecputick;
-			}
-		} else {
+		else
 			it->expires = 0;
-		}
 
 		trace_itimer_expire(signo == SIGPROF ?
 				    ITIMER_PROF : ITIMER_VIRTUAL,
@@ -917,9 +872,8 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
 		__group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
 	}
 
-	if (it->expires && (!*expires || it->expires < *expires)) {
+	if (it->expires && (!*expires || it->expires < *expires))
 		*expires = it->expires;
-	}
 }
 
 /*
@@ -931,8 +885,8 @@ static void check_process_timers(struct task_struct *tsk,
 				 struct list_head *firing)
 {
 	struct signal_struct *const sig = tsk->signal;
-	unsigned long long utime, ptime, virt_expires, prof_expires;
-	unsigned long long sum_sched_runtime, sched_expires;
+	u64 utime, ptime, virt_expires, prof_expires;
+	u64 sum_sched_runtime, sched_expires;
 	struct list_head *timers = sig->cpu_timers;
 	struct task_cputime cputime;
 	unsigned long soft;
@@ -954,8 +908,8 @@ static void check_process_timers(struct task_struct *tsk,
 	 * Collect the current process totals.
 	 */
 	thread_group_cputimer(tsk, &cputime);
-	utime = cputime_to_expires(cputime.utime);
-	ptime = utime + cputime_to_expires(cputime.stime);
+	utime = cputime.utime;
+	ptime = utime + cputime.stime;
 	sum_sched_runtime = cputime.sum_exec_runtime;
 
 	prof_expires = check_timers_list(timers, firing, ptime);
@@ -971,10 +925,10 @@ static void check_process_timers(struct task_struct *tsk,
 			 SIGVTALRM);
 	soft = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
 	if (soft != RLIM_INFINITY) {
-		unsigned long psecs = cputime_to_secs(ptime);
+		unsigned long psecs = div_u64(ptime, NSEC_PER_SEC);
 		unsigned long hard =
 			READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_max);
-		cputime_t x;
+		u64 x;
 		if (psecs >= hard) {
 			/*
 			 * At the hard limit, we just die.
@@ -993,14 +947,13 @@ static void check_process_timers(struct task_struct *tsk,
 				sig->rlim[RLIMIT_CPU].rlim_cur = soft;
 			}
 		}
-		x = secs_to_cputime(soft);
-		if (!prof_expires || x < prof_expires) {
+		x = soft * NSEC_PER_SEC;
+		if (!prof_expires || x < prof_expires)
 			prof_expires = x;
-		}
 	}
 
-	sig->cputime_expires.prof_exp = expires_to_cputime(prof_expires);
-	sig->cputime_expires.virt_exp = expires_to_cputime(virt_expires);
+	sig->cputime_expires.prof_exp = prof_expires;
+	sig->cputime_expires.virt_exp = virt_expires;
 	sig->cputime_expires.sched_exp = sched_expires;
 	if (task_cputime_zero(&sig->cputime_expires))
 		stop_process_timers(sig);
@@ -1017,7 +970,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer)
 	struct sighand_struct *sighand;
 	unsigned long flags;
 	struct task_struct *p = timer->it.cpu.task;
-	unsigned long long now;
+	u64 now;
 
 	WARN_ON_ONCE(p == NULL);
 
@@ -1214,9 +1167,9 @@ void run_posix_cpu_timers(struct task_struct *tsk)
  * The tsk->sighand->siglock must be held by the caller.
  */
 void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
-			   cputime_t *newval, cputime_t *oldval)
+			   u64 *newval, u64 *oldval)
 {
-	unsigned long long now;
+	u64 now;
 
 	WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED);
 	cpu_timer_sample_group(clock_idx, tsk, &now);
@@ -1230,7 +1183,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 		if (*oldval) {
 			if (*oldval <= now) {
 				/* Just about to fire. */
-				*oldval = cputime_one_jiffy;
+				*oldval = TICK_NSEC;
 			} else {
 				*oldval -= now;
 			}
@@ -1310,7 +1263,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
 		/*
 		 * We were interrupted by a signal.
 		 */
-		sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp);
+		*rqtp = ns_to_timespec(timer.it.cpu.expires);
 		error = posix_cpu_timer_set(&timer, 0, &zero_it, it);
 		if (!error) {
 			/*
@@ -1476,15 +1429,10 @@ static __init int init_posix_cpu_timers(void)
 		.clock_get	= thread_cpu_clock_get,
 		.timer_create	= thread_cpu_timer_create,
 	};
-	struct timespec ts;
 
 	posix_timers_register_clock(CLOCK_PROCESS_CPUTIME_ID, &process);
 	posix_timers_register_clock(CLOCK_THREAD_CPUTIME_ID, &thread);
 
-	cputime_to_timespec(cputime_one_jiffy, &ts);
-	onecputick = ts.tv_nsec;
-	WARN_ON(ts.tv_sec != 0);
-
 	return 0;
 }
 __initcall(init_posix_cpu_timers);
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 3109204c87cc..987e496bb51a 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -29,12 +29,13 @@
  */
 
 static struct tick_device tick_broadcast_device;
-static cpumask_var_t tick_broadcast_mask;
-static cpumask_var_t tick_broadcast_on;
-static cpumask_var_t tmpmask;
-static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
+static cpumask_var_t tick_broadcast_mask __cpumask_var_read_mostly;
+static cpumask_var_t tick_broadcast_on __cpumask_var_read_mostly;
+static cpumask_var_t tmpmask __cpumask_var_read_mostly;
 static int tick_broadcast_forced;
 
+static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
+
 #ifdef CONFIG_TICK_ONESHOT
 static void tick_broadcast_clear_oneshot(int cpu);
 static void tick_resume_broadcast_oneshot(struct clock_event_device *bc);
@@ -347,17 +348,16 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
  *
  * Called when the system enters a state where affected tick devices
  * might stop. Note: TICK_BROADCAST_FORCE cannot be undone.
- *
- * Called with interrupts disabled, so clockevents_lock is not
- * required here because the local clock event device cannot go away
- * under us.
  */
 void tick_broadcast_control(enum tick_broadcast_mode mode)
 {
 	struct clock_event_device *bc, *dev;
 	struct tick_device *td;
 	int cpu, bc_stopped;
+	unsigned long flags;
 
+	/* Protects also the local clockevent device. */
+	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 	td = this_cpu_ptr(&tick_cpu_device);
 	dev = td->evtdev;
 
@@ -365,12 +365,11 @@ void tick_broadcast_control(enum tick_broadcast_mode mode)
 	 * Is the device not affected by the powerstate ?
 	 */
 	if (!dev || !(dev->features & CLOCK_EVT_FEAT_C3STOP))
-		return;
+		goto out;
 
 	if (!tick_device_is_functional(dev))
-		return;
+		goto out;
 
-	raw_spin_lock(&tick_broadcast_lock);
 	cpu = smp_processor_id();
 	bc = tick_broadcast_device.evtdev;
 	bc_stopped = cpumask_empty(tick_broadcast_mask);
@@ -420,7 +419,8 @@ void tick_broadcast_control(enum tick_broadcast_mode mode)
 				tick_broadcast_setup_oneshot(bc);
 		}
 	}
-	raw_spin_unlock(&tick_broadcast_lock);
+out:
+	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 EXPORT_SYMBOL_GPL(tick_broadcast_control);
 
@@ -517,9 +517,9 @@ void tick_resume_broadcast(void)
 
 #ifdef CONFIG_TICK_ONESHOT
 
-static cpumask_var_t tick_broadcast_oneshot_mask;
-static cpumask_var_t tick_broadcast_pending_mask;
-static cpumask_var_t tick_broadcast_force_mask;
+static cpumask_var_t tick_broadcast_oneshot_mask __cpumask_var_read_mostly;
+static cpumask_var_t tick_broadcast_pending_mask __cpumask_var_read_mostly;
+static cpumask_var_t tick_broadcast_force_mask __cpumask_var_read_mostly;
 
 /*
  * Exposed for debugging: see timer_list.c
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 74e0388cc88d..2c115fdab397 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -767,7 +767,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	tick = expires;
 
 	/* Skip reprogram of event if its not changed */
-	if (ts->tick_stopped && (expires == ts->next_tick))
+	if (ts->tick_stopped && (expires == dev->next_event))
 		goto out;
 
 	/*
@@ -787,8 +787,6 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 		trace_tick_stop(1, TICK_DEP_MASK_NONE);
 	}
 
-	ts->next_tick = tick;
-
 	/*
 	 * If the expiration time == KTIME_MAX, then we simply stop
 	 * the tick timer.
@@ -804,10 +802,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	else
 		tick_program_event(tick, 1);
 out:
-	/*
-	 * Update the estimated sleep length until the next timer
-	 * (not only the tick).
-	 */
+	/* Update the estimated sleep length */
 	ts->sleep_length = ktime_sub(dev->next_event, now);
 	return tick;
 }
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 075444e3d48e..bf38226e5c17 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -27,7 +27,6 @@ enum tick_nohz_mode {
  *			timer is modified for nohz sleeps. This is necessary
  *			to resume the tick timer operation in the timeline
  *			when the CPU returns from nohz sleep.
- * @next_tick:		Next tick to be fired when in dynticks mode.
  * @tick_stopped:	Indicator that the idle tick has been stopped
  * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
  * @idle_calls:		Total number of idle calls
@@ -45,7 +44,6 @@ struct tick_sched {
 	unsigned long			check_clocks;
 	enum tick_nohz_mode		nohz_mode;
 	ktime_t				last_tick;
-	ktime_t				next_tick;
 	int				inidle;
 	int				tick_stopped;
 	unsigned long			idle_jiffies;
diff --git a/kernel/time/time.c b/kernel/time/time.c
index a3a9a8a029dc..25bdd2504571 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -702,6 +702,16 @@ u64 nsec_to_clock_t(u64 x)
 #endif
 }
 
+u64 jiffies64_to_nsecs(u64 j)
+{
+#if !(NSEC_PER_SEC % HZ)
+	return (NSEC_PER_SEC / HZ) * j;
+# else
+	return div_u64(j * HZ_TO_NSEC_NUM, HZ_TO_NSEC_DEN);
+#endif
+}
+EXPORT_SYMBOL(jiffies64_to_nsecs);
+
 /**
  * nsecs_to_jiffies64 - Convert nsecs in u64 to jiffies64
  *
diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc
index c48688904f9f..f83bbb81600b 100644
--- a/kernel/time/timeconst.bc
+++ b/kernel/time/timeconst.bc
@@ -98,6 +98,12 @@ define timeconst(hz) {
 		print "#define HZ_TO_USEC_DEN\t\t", hz/cd, "\n"
 		print "#define USEC_TO_HZ_NUM\t\t", hz/cd, "\n"
 		print "#define USEC_TO_HZ_DEN\t\t", 1000000/cd, "\n"
+
+		cd=gcd(hz,1000000000)
+		print "#define HZ_TO_NSEC_NUM\t\t", 1000000000/cd, "\n"
+		print "#define HZ_TO_NSEC_DEN\t\t", hz/cd, "\n"
+		print "#define NSEC_TO_HZ_NUM\t\t", hz/cd, "\n"
+		print "#define NSEC_TO_HZ_DEN\t\t", 1000000000/cd, "\n"
 		print "\n"
 
 		print "#endif /* KERNEL_TIMECONST_H */\n"
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index db087d7e106d..95b258dd75db 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1275,27 +1275,8 @@ error: /* even if we error out, we forwarded the time, so call update */
 }
 EXPORT_SYMBOL(timekeeping_inject_offset);
 
-
-/**
- * timekeeping_get_tai_offset - Returns current TAI offset from UTC
- *
- */
-s32 timekeeping_get_tai_offset(void)
-{
-	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned int seq;
-	s32 ret;
-
-	do {
-		seq = read_seqcount_begin(&tk_core.seq);
-		ret = tk->tai_offset;
-	} while (read_seqcount_retry(&tk_core.seq, seq));
-
-	return ret;
-}
-
 /**
- * __timekeeping_set_tai_offset - Lock free worker function
+ * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic
  *
  */
 static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
@@ -1305,24 +1286,6 @@ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
 }
 
 /**
- * timekeeping_set_tai_offset - Sets the current TAI offset from UTC
- *
- */
-void timekeeping_set_tai_offset(s32 tai_offset)
-{
-	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&timekeeper_lock, flags);
-	write_seqcount_begin(&tk_core.seq);
-	__timekeeping_set_tai_offset(tk, tai_offset);
-	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
-	write_seqcount_end(&tk_core.seq);
-	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
-	clock_was_set();
-}
-
-/**
  * change_clocksource - Swaps clocksources if a new one is available
  *
  * Accumulates current time interval and initializes new clocksource
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 704f595ce83f..d0914676d4c5 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -11,8 +11,6 @@ extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq,
 extern int timekeeping_valid_for_hres(void);
 extern u64 timekeeping_max_deferment(void);
 extern int timekeeping_inject_offset(struct timespec *ts);
-extern s32 timekeeping_get_tai_offset(void);
-extern void timekeeping_set_tai_offset(s32 tai_offset);
 extern int timekeeping_suspend(void);
 extern void timekeeping_resume(void);
 
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index ca9fb800336b..38bc4d2208e8 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -75,7 +75,7 @@ void tk_debug_account_sleep_time(struct timespec64 *t)
 	int bin = min(fls(t->tv_sec), NUM_BINS-1);
 
 	sleep_time_bin[bin]++;
-	pr_info("Suspended for %lld.%03lu seconds\n", (s64)t->tv_sec,
-			t->tv_nsec / NSEC_PER_MSEC);
+	printk_deferred(KERN_INFO "Suspended for %lld.%03lu seconds\n",
+			(s64)t->tv_sec, t->tv_nsec / NSEC_PER_MSEC);
 }
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index ec33a6933eae..82a6bfa0c307 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -571,38 +571,6 @@ internal_add_timer(struct timer_base *base, struct timer_list *timer)
 	trigger_dyntick_cpu(base, timer);
 }
 
-#ifdef CONFIG_TIMER_STATS
-void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
-{
-	if (timer->start_site)
-		return;
-
-	timer->start_site = addr;
-	memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
-	timer->start_pid = current->pid;
-}
-
-static void timer_stats_account_timer(struct timer_list *timer)
-{
-	void *site;
-
-	/*
-	 * start_site can be concurrently reset by
-	 * timer_stats_timer_clear_start_info()
-	 */
-	site = READ_ONCE(timer->start_site);
-	if (likely(!site))
-		return;
-
-	timer_stats_update_stats(timer, timer->start_pid, site,
-				 timer->function, timer->start_comm,
-				 timer->flags);
-}
-
-#else
-static void timer_stats_account_timer(struct timer_list *timer) {}
-#endif
-
 #ifdef CONFIG_DEBUG_OBJECTS_TIMERS
 
 static struct debug_obj_descr timer_debug_descr;
@@ -789,11 +757,6 @@ static void do_init_timer(struct timer_list *timer, unsigned int flags,
 {
 	timer->entry.pprev = NULL;
 	timer->flags = flags | raw_smp_processor_id();
-#ifdef CONFIG_TIMER_STATS
-	timer->start_site = NULL;
-	timer->start_pid = -1;
-	memset(timer->start_comm, 0, TASK_COMM_LEN);
-#endif
 	lockdep_init_map(&timer->lockdep_map, name, key, 0);
 }
 
@@ -1001,8 +964,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
 		base = lock_timer_base(timer, &flags);
 	}
 
-	timer_stats_timer_set_start_info(timer);
-
 	ret = detach_if_pending(timer, base, false);
 	if (!ret && pending_only)
 		goto out_unlock;
@@ -1130,7 +1091,6 @@ void add_timer_on(struct timer_list *timer, int cpu)
 	struct timer_base *new_base, *base;
 	unsigned long flags;
 
-	timer_stats_timer_set_start_info(timer);
 	BUG_ON(timer_pending(timer) || !timer->function);
 
 	new_base = get_timer_cpu_base(timer->flags, cpu);
@@ -1176,7 +1136,6 @@ int del_timer(struct timer_list *timer)
 
 	debug_assert_init(timer);
 
-	timer_stats_timer_clear_start_info(timer);
 	if (timer_pending(timer)) {
 		base = lock_timer_base(timer, &flags);
 		ret = detach_if_pending(timer, base, true);
@@ -1204,10 +1163,9 @@ int try_to_del_timer_sync(struct timer_list *timer)
 
 	base = lock_timer_base(timer, &flags);
 
-	if (base->running_timer != timer) {
-		timer_stats_timer_clear_start_info(timer);
+	if (base->running_timer != timer)
 		ret = detach_if_pending(timer, base, true);
-	}
+
 	spin_unlock_irqrestore(&base->lock, flags);
 
 	return ret;
@@ -1331,7 +1289,6 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head)
 		unsigned long data;
 
 		timer = hlist_entry(head->first, struct timer_list, entry);
-		timer_stats_account_timer(timer);
 
 		base->running_timer = timer;
 		detach_timer(timer, true);
@@ -1868,7 +1825,6 @@ static void __init init_timer_cpus(void)
 void __init init_timers(void)
 {
 	init_timer_cpus();
-	init_timer_stats();
 	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
 }
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index afe6cd1944fc..ff8d5c13d04b 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -62,21 +62,11 @@ static void
 print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer,
 	    int idx, u64 now)
 {
-#ifdef CONFIG_TIMER_STATS
-	char tmp[TASK_COMM_LEN + 1];
-#endif
 	SEQ_printf(m, " #%d: ", idx);
 	print_name_offset(m, taddr);
 	SEQ_printf(m, ", ");
 	print_name_offset(m, timer->function);
 	SEQ_printf(m, ", S:%02x", timer->state);
-#ifdef CONFIG_TIMER_STATS
-	SEQ_printf(m, ", ");
-	print_name_offset(m, timer->start_site);
-	memcpy(tmp, timer->start_comm, TASK_COMM_LEN);
-	tmp[TASK_COMM_LEN] = 0;
-	SEQ_printf(m, ", %s/%d", tmp, timer->start_pid);
-#endif
 	SEQ_printf(m, "\n");
 	SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n",
 		(unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)),
@@ -127,7 +117,7 @@ print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
 	SEQ_printf(m, "  .base:       %pK\n", base);
 	SEQ_printf(m, "  .index:      %d\n", base->index);
 
-	SEQ_printf(m, "  .resolution: %u nsecs\n", (unsigned) hrtimer_resolution);
+	SEQ_printf(m, "  .resolution: %u nsecs\n", hrtimer_resolution);
 
 	SEQ_printf(m,   "  .get_time:   ");
 	print_name_offset(m, base->get_time);
diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c
deleted file mode 100644
index afddded947df..000000000000
--- a/kernel/time/timer_stats.c
+++ /dev/null
@@ -1,425 +0,0 @@
-/*
- * kernel/time/timer_stats.c
- *
- * Collect timer usage statistics.
- *
- * Copyright(C) 2006, Red Hat, Inc., Ingo Molnar
- * Copyright(C) 2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
- *
- * timer_stats is based on timer_top, a similar functionality which was part of
- * Con Kolivas dyntick patch set. It was developed by Daniel Petrini at the
- * Instituto Nokia de Tecnologia - INdT - Manaus. timer_top's design was based
- * on dynamic allocation of the statistics entries and linear search based
- * lookup combined with a global lock, rather than the static array, hash
- * and per-CPU locking which is used by timer_stats. It was written for the
- * pre hrtimer kernel code and therefore did not take hrtimers into account.
- * Nevertheless it provided the base for the timer_stats implementation and
- * was a helpful source of inspiration. Kudos to Daniel and the Nokia folks
- * for this effort.
- *
- * timer_top.c is
- *	Copyright (C) 2005 Instituto Nokia de Tecnologia - INdT - Manaus
- *	Written by Daniel Petrini <d.pensator@gmail.com>
- *	timer_top.c was released under the GNU General Public License version 2
- *
- * We export the addresses and counting of timer functions being called,
- * the pid and cmdline from the owner process if applicable.
- *
- * Start/stop data collection:
- * # echo [1|0] >/proc/timer_stats
- *
- * Display the information collected so far:
- * # cat /proc/timer_stats
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/proc_fs.h>
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <linux/sched.h>
-#include <linux/seq_file.h>
-#include <linux/kallsyms.h>
-
-#include <linux/uaccess.h>
-
-/*
- * This is our basic unit of interest: a timer expiry event identified
- * by the timer, its start/expire functions and the PID of the task that
- * started the timer. We count the number of times an event happens:
- */
-struct entry {
-	/*
-	 * Hash list:
-	 */
-	struct entry		*next;
-
-	/*
-	 * Hash keys:
-	 */
-	void			*timer;
-	void			*start_func;
-	void			*expire_func;
-	pid_t			pid;
-
-	/*
-	 * Number of timeout events:
-	 */
-	unsigned long		count;
-	u32			flags;
-
-	/*
-	 * We save the command-line string to preserve
-	 * this information past task exit:
-	 */
-	char			comm[TASK_COMM_LEN + 1];
-
-} ____cacheline_aligned_in_smp;
-
-/*
- * Spinlock protecting the tables - not taken during lookup:
- */
-static DEFINE_RAW_SPINLOCK(table_lock);
-
-/*
- * Per-CPU lookup locks for fast hash lookup:
- */
-static DEFINE_PER_CPU(raw_spinlock_t, tstats_lookup_lock);
-
-/*
- * Mutex to serialize state changes with show-stats activities:
- */
-static DEFINE_MUTEX(show_mutex);
-
-/*
- * Collection status, active/inactive:
- */
-int __read_mostly timer_stats_active;
-
-/*
- * Beginning/end timestamps of measurement:
- */
-static ktime_t time_start, time_stop;
-
-/*
- * tstat entry structs only get allocated while collection is
- * active and never freed during that time - this simplifies
- * things quite a bit.
- *
- * They get freed when a new collection period is started.
- */
-#define MAX_ENTRIES_BITS	10
-#define MAX_ENTRIES		(1UL << MAX_ENTRIES_BITS)
-
-static unsigned long nr_entries;
-static struct entry entries[MAX_ENTRIES];
-
-static atomic_t overflow_count;
-
-/*
- * The entries are in a hash-table, for fast lookup:
- */
-#define TSTAT_HASH_BITS		(MAX_ENTRIES_BITS - 1)
-#define TSTAT_HASH_SIZE		(1UL << TSTAT_HASH_BITS)
-#define TSTAT_HASH_MASK		(TSTAT_HASH_SIZE - 1)
-
-#define __tstat_hashfn(entry)						\
-	(((unsigned long)(entry)->timer       ^				\
-	  (unsigned long)(entry)->start_func  ^				\
-	  (unsigned long)(entry)->expire_func ^				\
-	  (unsigned long)(entry)->pid		) & TSTAT_HASH_MASK)
-
-#define tstat_hashentry(entry)	(tstat_hash_table + __tstat_hashfn(entry))
-
-static struct entry *tstat_hash_table[TSTAT_HASH_SIZE] __read_mostly;
-
-static void reset_entries(void)
-{
-	nr_entries = 0;
-	memset(entries, 0, sizeof(entries));
-	memset(tstat_hash_table, 0, sizeof(tstat_hash_table));
-	atomic_set(&overflow_count, 0);
-}
-
-static struct entry *alloc_entry(void)
-{
-	if (nr_entries >= MAX_ENTRIES)
-		return NULL;
-
-	return entries + nr_entries++;
-}
-
-static int match_entries(struct entry *entry1, struct entry *entry2)
-{
-	return entry1->timer       == entry2->timer	  &&
-	       entry1->start_func  == entry2->start_func  &&
-	       entry1->expire_func == entry2->expire_func &&
-	       entry1->pid	   == entry2->pid;
-}
-
-/*
- * Look up whether an entry matching this item is present
- * in the hash already. Must be called with irqs off and the
- * lookup lock held:
- */
-static struct entry *tstat_lookup(struct entry *entry, char *comm)
-{
-	struct entry **head, *curr, *prev;
-
-	head = tstat_hashentry(entry);
-	curr = *head;
-
-	/*
-	 * The fastpath is when the entry is already hashed,
-	 * we do this with the lookup lock held, but with the
-	 * table lock not held:
-	 */
-	while (curr) {
-		if (match_entries(curr, entry))
-			return curr;
-
-		curr = curr->next;
-	}
-	/*
-	 * Slowpath: allocate, set up and link a new hash entry:
-	 */
-	prev = NULL;
-	curr = *head;
-
-	raw_spin_lock(&table_lock);
-	/*
-	 * Make sure we have not raced with another CPU:
-	 */
-	while (curr) {
-		if (match_entries(curr, entry))
-			goto out_unlock;
-
-		prev = curr;
-		curr = curr->next;
-	}
-
-	curr = alloc_entry();
-	if (curr) {
-		*curr = *entry;
-		curr->count = 0;
-		curr->next = NULL;
-		memcpy(curr->comm, comm, TASK_COMM_LEN);
-
-		smp_mb(); /* Ensure that curr is initialized before insert */
-
-		if (prev)
-			prev->next = curr;
-		else
-			*head = curr;
-	}
- out_unlock:
-	raw_spin_unlock(&table_lock);
-
-	return curr;
-}
-
-/**
- * timer_stats_update_stats - Update the statistics for a timer.
- * @timer:	pointer to either a timer_list or a hrtimer
- * @pid:	the pid of the task which set up the timer
- * @startf:	pointer to the function which did the timer setup
- * @timerf:	pointer to the timer callback function of the timer
- * @comm:	name of the process which set up the timer
- * @tflags:	The flags field of the timer
- *
- * When the timer is already registered, then the event counter is
- * incremented. Otherwise the timer is registered in a free slot.
- */
-void timer_stats_update_stats(void *timer, pid_t pid, void *startf,
-			      void *timerf, char *comm, u32 tflags)
-{
-	/*
-	 * It doesn't matter which lock we take:
-	 */
-	raw_spinlock_t *lock;
-	struct entry *entry, input;
-	unsigned long flags;
-
-	if (likely(!timer_stats_active))
-		return;
-
-	lock = &per_cpu(tstats_lookup_lock, raw_smp_processor_id());
-
-	input.timer = timer;
-	input.start_func = startf;
-	input.expire_func = timerf;
-	input.pid = pid;
-	input.flags = tflags;
-
-	raw_spin_lock_irqsave(lock, flags);
-	if (!timer_stats_active)
-		goto out_unlock;
-
-	entry = tstat_lookup(&input, comm);
-	if (likely(entry))
-		entry->count++;
-	else
-		atomic_inc(&overflow_count);
-
- out_unlock:
-	raw_spin_unlock_irqrestore(lock, flags);
-}
-
-static void print_name_offset(struct seq_file *m, unsigned long addr)
-{
-	char symname[KSYM_NAME_LEN];
-
-	if (lookup_symbol_name(addr, symname) < 0)
-		seq_printf(m, "<%p>", (void *)addr);
-	else
-		seq_printf(m, "%s", symname);
-}
-
-static int tstats_show(struct seq_file *m, void *v)
-{
-	struct timespec64 period;
-	struct entry *entry;
-	unsigned long ms;
-	long events = 0;
-	ktime_t time;
-	int i;
-
-	mutex_lock(&show_mutex);
-	/*
-	 * If still active then calculate up to now:
-	 */
-	if (timer_stats_active)
-		time_stop = ktime_get();
-
-	time = ktime_sub(time_stop, time_start);
-
-	period = ktime_to_timespec64(time);
-	ms = period.tv_nsec / 1000000;
-
-	seq_puts(m, "Timer Stats Version: v0.3\n");
-	seq_printf(m, "Sample period: %ld.%03ld s\n", (long)period.tv_sec, ms);
-	if (atomic_read(&overflow_count))
-		seq_printf(m, "Overflow: %d entries\n", atomic_read(&overflow_count));
-	seq_printf(m, "Collection: %s\n", timer_stats_active ? "active" : "inactive");
-
-	for (i = 0; i < nr_entries; i++) {
-		entry = entries + i;
-		if (entry->flags & TIMER_DEFERRABLE) {
-			seq_printf(m, "%4luD, %5d %-16s ",
-				entry->count, entry->pid, entry->comm);
-		} else {
-			seq_printf(m, " %4lu, %5d %-16s ",
-				entry->count, entry->pid, entry->comm);
-		}
-
-		print_name_offset(m, (unsigned long)entry->start_func);
-		seq_puts(m, " (");
-		print_name_offset(m, (unsigned long)entry->expire_func);
-		seq_puts(m, ")\n");
-
-		events += entry->count;
-	}
-
-	ms += period.tv_sec * 1000;
-	if (!ms)
-		ms = 1;
-
-	if (events && period.tv_sec)
-		seq_printf(m, "%ld total events, %ld.%03ld events/sec\n",
-			   events, events * 1000 / ms,
-			   (events * 1000000 / ms) % 1000);
-	else
-		seq_printf(m, "%ld total events\n", events);
-
-	mutex_unlock(&show_mutex);
-
-	return 0;
-}
-
-/*
- * After a state change, make sure all concurrent lookup/update
- * activities have stopped:
- */
-static void sync_access(void)
-{
-	unsigned long flags;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		raw_spinlock_t *lock = &per_cpu(tstats_lookup_lock, cpu);
-
-		raw_spin_lock_irqsave(lock, flags);
-		/* nothing */
-		raw_spin_unlock_irqrestore(lock, flags);
-	}
-}
-
-static ssize_t tstats_write(struct file *file, const char __user *buf,
-			    size_t count, loff_t *offs)
-{
-	char ctl[2];
-
-	if (count != 2 || *offs)
-		return -EINVAL;
-
-	if (copy_from_user(ctl, buf, count))
-		return -EFAULT;
-
-	mutex_lock(&show_mutex);
-	switch (ctl[0]) {
-	case '0':
-		if (timer_stats_active) {
-			timer_stats_active = 0;
-			time_stop = ktime_get();
-			sync_access();
-		}
-		break;
-	case '1':
-		if (!timer_stats_active) {
-			reset_entries();
-			time_start = ktime_get();
-			smp_mb();
-			timer_stats_active = 1;
-		}
-		break;
-	default:
-		count = -EINVAL;
-	}
-	mutex_unlock(&show_mutex);
-
-	return count;
-}
-
-static int tstats_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, tstats_show, NULL);
-}
-
-static const struct file_operations tstats_fops = {
-	.open		= tstats_open,
-	.read		= seq_read,
-	.write		= tstats_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-void __init init_timer_stats(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		raw_spin_lock_init(&per_cpu(tstats_lookup_lock, cpu));
-}
-
-static int __init init_tstats_procfs(void)
-{
-	struct proc_dir_entry *pe;
-
-	pe = proc_create("timer_stats", 0644, NULL, &tstats_fops);
-	if (!pe)
-		return -ENOMEM;
-	return 0;
-}
-__initcall(init_tstats_procfs);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 95cecbf67f5c..b2058a7f94bd 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -28,6 +28,8 @@
 #include <linux/uaccess.h>
 #include <linux/list.h>
 
+#include "../../block/blk.h"
+
 #include <trace/events/block.h>
 
 #include "trace_output.h"
@@ -292,9 +294,6 @@ record_it:
 	local_irq_restore(flags);
 }
 
-static struct dentry *blk_tree_root;
-static DEFINE_MUTEX(blk_tree_mutex);
-
 static void blk_trace_free(struct blk_trace *bt)
 {
 	debugfs_remove(bt->msg_file);
@@ -433,9 +432,9 @@ static void blk_trace_setup_lba(struct blk_trace *bt,
 /*
  * Setup everything required to start tracing
  */
-int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
-		       struct block_device *bdev,
-		       struct blk_user_trace_setup *buts)
+static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+			      struct block_device *bdev,
+			      struct blk_user_trace_setup *buts)
 {
 	struct blk_trace *bt = NULL;
 	struct dentry *dir = NULL;
@@ -468,22 +467,15 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = -ENOENT;
 
-	mutex_lock(&blk_tree_mutex);
-	if (!blk_tree_root) {
-		blk_tree_root = debugfs_create_dir("block", NULL);
-		if (!blk_tree_root) {
-			mutex_unlock(&blk_tree_mutex);
-			goto err;
-		}
-	}
-	mutex_unlock(&blk_tree_mutex);
-
-	dir = debugfs_create_dir(buts->name, blk_tree_root);
+	if (!blk_debugfs_root)
+		goto err;
 
+	dir = debugfs_lookup(buts->name, blk_debugfs_root);
+	if (!dir)
+		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
 	if (!dir)
 		goto err;
 
-	bt->dir = dir;
 	bt->dev = dev;
 	atomic_set(&bt->dropped, 0);
 	INIT_LIST_HEAD(&bt->running_list);
@@ -525,9 +517,12 @@ int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (atomic_inc_return(&blk_probes_ref) == 1)
 		blk_register_tracepoints();
 
-	return 0;
+	ret = 0;
 err:
-	blk_trace_free(bt);
+	if (dir && !bt->dir)
+		dput(dir);
+	if (ret)
+		blk_trace_free(bt);
 	return ret;
 }
 
@@ -712,15 +707,13 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
 	if (likely(!bt))
 		return;
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
+	if (blk_rq_is_passthrough(rq))
 		what |= BLK_TC_ACT(BLK_TC_PC);
-		__blk_add_trace(bt, 0, nr_bytes, req_op(rq), rq->cmd_flags,
-				what, rq->errors, rq->cmd_len, rq->cmd);
-	} else  {
+	else
 		what |= BLK_TC_ACT(BLK_TC_FS);
-		__blk_add_trace(bt, blk_rq_pos(rq), nr_bytes, req_op(rq),
-				rq->cmd_flags, what, rq->errors, 0, NULL);
-	}
+
+	__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
+			rq->cmd_flags, what, rq->errors, 0, NULL);
 }
 
 static void blk_add_trace_rq_abort(void *ignore,
@@ -972,11 +965,7 @@ void blk_add_driver_data(struct request_queue *q,
 	if (likely(!bt))
 		return;
 
-	if (rq->cmd_type == REQ_TYPE_BLOCK_PC)
-		__blk_add_trace(bt, 0, blk_rq_bytes(rq), 0, 0,
-				BLK_TA_DRV_DATA, rq->errors, len, data);
-	else
-		__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), 0, 0,
+	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
 				BLK_TA_DRV_DATA, rq->errors, len, data);
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
@@ -1752,31 +1741,6 @@ void blk_trace_remove_sysfs(struct device *dev)
 
 #ifdef CONFIG_EVENT_TRACING
 
-void blk_dump_cmd(char *buf, struct request *rq)
-{
-	int i, end;
-	int len = rq->cmd_len;
-	unsigned char *cmd = rq->cmd;
-
-	if (rq->cmd_type != REQ_TYPE_BLOCK_PC) {
-		buf[0] = '\0';
-		return;
-	}
-
-	for (end = len - 1; end >= 0; end--)
-		if (cmd[end])
-			break;
-	end++;
-
-	for (i = 0; i < len; i++) {
-		buf += sprintf(buf, "%s%02x", i == 0 ? "" : " ", cmd[i]);
-		if (i == end && end != len - 1) {
-			sprintf(buf, " ..");
-			break;
-		}
-	}
-}
-
 void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes)
 {
 	int i = 0;
diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index 775569ec50d0..af344a1bf0d0 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -266,7 +266,7 @@ out:
 static struct cpumask save_cpumask;
 static bool disable_migrate;
 
-static void move_to_next_cpu(void)
+static void move_to_next_cpu(bool initmask)
 {
 	static struct cpumask *current_mask;
 	int next_cpu;
@@ -275,7 +275,7 @@ static void move_to_next_cpu(void)
 		return;
 
 	/* Just pick the first CPU on first iteration */
-	if (!current_mask) {
+	if (initmask) {
 		current_mask = &save_cpumask;
 		get_online_cpus();
 		cpumask_and(current_mask, cpu_online_mask, tracing_buffer_mask);
@@ -330,10 +330,12 @@ static void move_to_next_cpu(void)
 static int kthread_fn(void *data)
 {
 	u64 interval;
+	bool initmask = true;
 
 	while (!kthread_should_stop()) {
 
-		move_to_next_cpu();
+		move_to_next_cpu(initmask);
+		initmask = false;
 
 		local_irq_disable();
 		get_sample();
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index a133ecd741e4..7ad9e53ad174 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1372,7 +1372,7 @@ kprobe_trace_selftest_target(int a1, int a2, int a3, int a4, int a5, int a6)
 	return a1 + a2 + a3 + a4 + a5 + a6;
 }
 
-static struct __init trace_event_file *
+static __init struct trace_event_file *
 find_trace_probe_file(struct trace_kprobe *tk, struct trace_array *tr)
 {
 	struct trace_event_file *file;
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index f8e26ab963ed..5c21f0535056 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -31,7 +31,7 @@ void bacct_add_tsk(struct user_namespace *user_ns,
 		   struct taskstats *stats, struct task_struct *tsk)
 {
 	const struct cred *tcred;
-	cputime_t utime, stime, utimescaled, stimescaled;
+	u64 utime, stime, utimescaled, stimescaled;
 	u64 delta;
 
 	BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN);
@@ -67,12 +67,12 @@ void bacct_add_tsk(struct user_namespace *user_ns,
 	rcu_read_unlock();
 
 	task_cputime(tsk, &utime, &stime);
-	stats->ac_utime = cputime_to_usecs(utime);
-	stats->ac_stime = cputime_to_usecs(stime);
+	stats->ac_utime = div_u64(utime, NSEC_PER_USEC);
+	stats->ac_stime = div_u64(stime, NSEC_PER_USEC);
 
 	task_cputime_scaled(tsk, &utimescaled, &stimescaled);
-	stats->ac_utimescaled = cputime_to_usecs(utimescaled);
-	stats->ac_stimescaled = cputime_to_usecs(stimescaled);
+	stats->ac_utimescaled = div_u64(utimescaled, NSEC_PER_USEC);
+	stats->ac_stimescaled = div_u64(stimescaled, NSEC_PER_USEC);
 
 	stats->ac_minflt = tsk->min_flt;
 	stats->ac_majflt = tsk->maj_flt;
@@ -123,18 +123,15 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 #undef MB
 
 static void __acct_update_integrals(struct task_struct *tsk,
-				    cputime_t utime, cputime_t stime)
+				    u64 utime, u64 stime)
 {
-	cputime_t time, dtime;
-	u64 delta;
+	u64 time, delta;
 
 	if (!likely(tsk->mm))
 		return;
 
 	time = stime + utime;
-	dtime = time - tsk->acct_timexpd;
-	/* Avoid division: cputime_t is often in nanoseconds already. */
-	delta = cputime_to_nsecs(dtime);
+	delta = time - tsk->acct_timexpd;
 
 	if (delta < TICK_NSEC)
 		return;
@@ -155,7 +152,7 @@ static void __acct_update_integrals(struct task_struct *tsk,
  */
 void acct_update_integrals(struct task_struct *tsk)
 {
-	cputime_t utime, stime;
+	u64 utime, stime;
 	unsigned long flags;
 
 	local_irq_save(flags);
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 9d20d5dd298a..95c6336fc2b3 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -128,10 +128,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 	struct hlist_head *hashent = ucounts_hashentry(ns, uid);
 	struct ucounts *ucounts, *new;
 
-	spin_lock(&ucounts_lock);
+	spin_lock_irq(&ucounts_lock);
 	ucounts = find_ucounts(ns, uid, hashent);
 	if (!ucounts) {
-		spin_unlock(&ucounts_lock);
+		spin_unlock_irq(&ucounts_lock);
 
 		new = kzalloc(sizeof(*new), GFP_KERNEL);
 		if (!new)
@@ -141,7 +141,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 		new->uid = uid;
 		atomic_set(&new->count, 0);
 
-		spin_lock(&ucounts_lock);
+		spin_lock_irq(&ucounts_lock);
 		ucounts = find_ucounts(ns, uid, hashent);
 		if (ucounts) {
 			kfree(new);
@@ -152,16 +152,18 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 	}
 	if (!atomic_add_unless(&ucounts->count, 1, INT_MAX))
 		ucounts = NULL;
-	spin_unlock(&ucounts_lock);
+	spin_unlock_irq(&ucounts_lock);
 	return ucounts;
 }
 
 static void put_ucounts(struct ucounts *ucounts)
 {
+	unsigned long flags;
+
 	if (atomic_dec_and_test(&ucounts->count)) {
-		spin_lock(&ucounts_lock);
+		spin_lock_irqsave(&ucounts_lock, flags);
 		hlist_del_init(&ucounts->node);
-		spin_unlock(&ucounts_lock);
+		spin_unlock_irqrestore(&ucounts_lock, flags);
 
 		kfree(ucounts);
 	}
@@ -225,11 +227,10 @@ static __init int user_namespace_sysctl_init(void)
 	 * properly.
 	 */
 	user_header = register_sysctl("user", empty);
+	kmemleak_ignore(user_header);
 	BUG_ON(!user_header);
 	BUG_ON(!setup_userns_sysctls(&init_user_ns));
 #endif
 	return 0;
 }
 subsys_initcall(user_namespace_sysctl_init);
-
-
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index d4b0fa01cae3..63177be0159e 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -49,6 +49,8 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 #define for_each_watchdog_cpu(cpu) \
 	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
 
+atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
+
 /*
  * The 'watchdog_running' variable is set to 1 when the watchdog threads
  * are registered/started and is set to 0 when the watchdog threads are
@@ -260,6 +262,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	int duration;
 	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
 
+	if (atomic_read(&watchdog_park_in_progress) != 0)
+		return HRTIMER_NORESTART;
+
 	/* kick the hardlockup detector */
 	watchdog_interrupt_count();
 
@@ -467,12 +472,16 @@ static int watchdog_park_threads(void)
 {
 	int cpu, ret = 0;
 
+	atomic_set(&watchdog_park_in_progress, 1);
+
 	for_each_watchdog_cpu(cpu) {
 		ret = kthread_park(per_cpu(softlockup_watchdog, cpu));
 		if (ret)
 			break;
 	}
 
+	atomic_set(&watchdog_park_in_progress, 0);
+
 	return ret;
 }
 
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 84016c8aee6b..12b8dd640786 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -84,6 +84,9 @@ static void watchdog_overflow_callback(struct perf_event *event,
 	/* Ensure the watchdog never gets throttled */
 	event->hw.interrupts = 0;
 
+	if (atomic_read(&watchdog_park_in_progress) != 0)
+		return;
+
 	if (__this_cpu_read(watchdog_nmi_touch) == true) {
 		__this_cpu_write(watchdog_nmi_touch, false);
 		return;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1d9fb6543a66..072cbc9b175d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1523,8 +1523,6 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 		return;
 	}
 
-	timer_stats_timer_set_start_info(&dwork->timer);
-
 	dwork->wq = wq;
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index eb9e9a7870fa..acedbe626d47 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -716,6 +716,19 @@ source "lib/Kconfig.kmemcheck"
 
 source "lib/Kconfig.kasan"
 
+config DEBUG_REFCOUNT
+	bool "Verbose refcount checks"
+	help
+	  Say Y here if you want reference counters (refcount_t and kref) to
+	  generate WARNs on dubious usage. Without this refcount_t will still
+	  be a saturating counter and avoid Use-After-Free by turning it into
+	  a resource leak Denial-Of-Service.
+
+	  Use of this option will increase kernel text size but will alert the
+	  admin of potential abuse.
+
+	  If in doubt, say "N".
+
 endmenu # "Memory Debugging"
 
 config ARCH_HAS_KCOV
@@ -980,20 +993,6 @@ config DEBUG_TIMEKEEPING
 
 	  If unsure, say N.
 
-config TIMER_STATS
-	bool "Collect kernel timers statistics"
-	depends on DEBUG_KERNEL && PROC_FS
-	help
-	  If you say Y here, additional code will be inserted into the
-	  timer routines to collect statistics about kernel timers being
-	  reprogrammed. The statistics can be read from /proc/timer_stats.
-	  The statistics collection is started by writing 1 to /proc/timer_stats,
-	  writing 0 stops it. This feature is useful to collect information
-	  about timer usage patterns in kernel and userspace. This feature
-	  is lightweight if enabled in the kernel config but not activated
-	  (it defaults to deactivated on bootup and will only be activated
-	  if some application like powertop activates it explicitly).
-
 config DEBUG_PREEMPT
 	bool "Debug preemptible kernel"
 	depends on DEBUG_KERNEL && PREEMPT && TRACE_IRQFLAGS_SUPPORT
@@ -1180,6 +1179,18 @@ config LOCK_TORTURE_TEST
 	  Say M if you want these torture tests to build as a module.
 	  Say N if you are unsure.
 
+config WW_MUTEX_SELFTEST
+	tristate "Wait/wound mutex selftests"
+	help
+	  This option provides a kernel module that runs tests on the
+	  on the struct ww_mutex locking API.
+
+	  It is recommended to enable DEBUG_WW_MUTEX_SLOWPATH in conjunction
+	  with this test harness.
+
+	  Say M if you want these self tests to build as a module.
+	  Say N if you are unsure.
+
 endmenu # lock debugging
 
 config TRACE_IRQFLAGS
@@ -1450,6 +1461,7 @@ config RCU_CPU_STALL_TIMEOUT
 config RCU_TRACE
 	bool "Enable tracing for RCU"
 	depends on DEBUG_KERNEL
+	default y if TREE_RCU
 	select TRACE_CLOCK
 	help
 	  This option provides tracing in RCU which presents stats
diff --git a/lib/Makefile b/lib/Makefile
index bc4073a8cd08..19ea76149a37 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -31,7 +31,7 @@ lib-$(CONFIG_HAS_DMA) += dma-noop.o
 lib-y	+= kobject.o klist.o
 obj-y	+= lockref.o
 
-obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
+obj-y += bcd.o div64.o sort.o parser.o debug_locks.o random32.o \
 	 bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \
 	 bsearch.o find_bit.o llist.o memweight.o kfifo.o \
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 04c1ef717fe0..8c28cbd7e104 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -52,9 +52,18 @@ static int			debug_objects_fixups __read_mostly;
 static int			debug_objects_warnings __read_mostly;
 static int			debug_objects_enabled __read_mostly
 				= CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT;
-
+static int			debug_objects_pool_size __read_mostly
+				= ODEBUG_POOL_SIZE;
+static int			debug_objects_pool_min_level __read_mostly
+				= ODEBUG_POOL_MIN_LEVEL;
 static struct debug_obj_descr	*descr_test  __read_mostly;
 
+/*
+ * Track numbers of kmem_cache_alloc()/free() calls done.
+ */
+static int			debug_objects_allocated;
+static int			debug_objects_freed;
+
 static void free_obj_work(struct work_struct *work);
 static DECLARE_WORK(debug_obj_work, free_obj_work);
 
@@ -88,13 +97,13 @@ static void fill_pool(void)
 	struct debug_obj *new;
 	unsigned long flags;
 
-	if (likely(obj_pool_free >= ODEBUG_POOL_MIN_LEVEL))
+	if (likely(obj_pool_free >= debug_objects_pool_min_level))
 		return;
 
 	if (unlikely(!obj_cache))
 		return;
 
-	while (obj_pool_free < ODEBUG_POOL_MIN_LEVEL) {
+	while (obj_pool_free < debug_objects_pool_min_level) {
 
 		new = kmem_cache_zalloc(obj_cache, gfp);
 		if (!new)
@@ -102,6 +111,7 @@ static void fill_pool(void)
 
 		raw_spin_lock_irqsave(&pool_lock, flags);
 		hlist_add_head(&new->node, &obj_pool);
+		debug_objects_allocated++;
 		obj_pool_free++;
 		raw_spin_unlock_irqrestore(&pool_lock, flags);
 	}
@@ -162,24 +172,39 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
 
 /*
  * workqueue function to free objects.
+ *
+ * To reduce contention on the global pool_lock, the actual freeing of
+ * debug objects will be delayed if the pool_lock is busy. We also free
+ * the objects in a batch of 4 for each lock/unlock cycle.
  */
+#define ODEBUG_FREE_BATCH	4
+
 static void free_obj_work(struct work_struct *work)
 {
-	struct debug_obj *obj;
+	struct debug_obj *objs[ODEBUG_FREE_BATCH];
 	unsigned long flags;
+	int i;
 
-	raw_spin_lock_irqsave(&pool_lock, flags);
-	while (obj_pool_free > ODEBUG_POOL_SIZE) {
-		obj = hlist_entry(obj_pool.first, typeof(*obj), node);
-		hlist_del(&obj->node);
-		obj_pool_free--;
+	if (!raw_spin_trylock_irqsave(&pool_lock, flags))
+		return;
+	while (obj_pool_free >= debug_objects_pool_size + ODEBUG_FREE_BATCH) {
+		for (i = 0; i < ODEBUG_FREE_BATCH; i++) {
+			objs[i] = hlist_entry(obj_pool.first,
+					      typeof(*objs[0]), node);
+			hlist_del(&objs[i]->node);
+		}
+
+		obj_pool_free -= ODEBUG_FREE_BATCH;
+		debug_objects_freed += ODEBUG_FREE_BATCH;
 		/*
 		 * We release pool_lock across kmem_cache_free() to
 		 * avoid contention on pool_lock.
 		 */
 		raw_spin_unlock_irqrestore(&pool_lock, flags);
-		kmem_cache_free(obj_cache, obj);
-		raw_spin_lock_irqsave(&pool_lock, flags);
+		for (i = 0; i < ODEBUG_FREE_BATCH; i++)
+			kmem_cache_free(obj_cache, objs[i]);
+		if (!raw_spin_trylock_irqsave(&pool_lock, flags))
+			return;
 	}
 	raw_spin_unlock_irqrestore(&pool_lock, flags);
 }
@@ -198,7 +223,7 @@ static void free_object(struct debug_obj *obj)
 	 * schedule work when the pool is filled and the cache is
 	 * initialized:
 	 */
-	if (obj_pool_free > ODEBUG_POOL_SIZE && obj_cache)
+	if (obj_pool_free > debug_objects_pool_size && obj_cache)
 		sched = 1;
 	hlist_add_head(&obj->node, &obj_pool);
 	obj_pool_free++;
@@ -758,6 +783,8 @@ static int debug_stats_show(struct seq_file *m, void *v)
 	seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free);
 	seq_printf(m, "pool_used     :%d\n", obj_pool_used);
 	seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used);
+	seq_printf(m, "objs_allocated:%d\n", debug_objects_allocated);
+	seq_printf(m, "objs_freed    :%d\n", debug_objects_freed);
 	return 0;
 }
 
@@ -1116,4 +1143,11 @@ void __init debug_objects_mem_init(void)
 		pr_warn("out of memory.\n");
 	} else
 		debug_objects_selftest();
+
+	/*
+	 * Increase the thresholds for allocating and freeing objects
+	 * according to the number of possible CPUs available in the system.
+	 */
+	debug_objects_pool_size += num_possible_cpus() * 32;
+	debug_objects_pool_min_level += num_possible_cpus() * 4;
 }
diff --git a/lib/halfmd4.c b/lib/halfmd4.c
deleted file mode 100644
index 137e861d9690..000000000000
--- a/lib/halfmd4.c
+++ /dev/null
@@ -1,67 +0,0 @@
-#include <linux/compiler.h>
-#include <linux/export.h>
-#include <linux/cryptohash.h>
-#include <linux/bitops.h>
-
-/* F, G and H are basic MD4 functions: selection, majority, parity */
-#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
-#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
-#define H(x, y, z) ((x) ^ (y) ^ (z))
-
-/*
- * The generic round function.  The application is so specific that
- * we don't bother protecting all the arguments with parens, as is generally
- * good macro practice, in favor of extra legibility.
- * Rotation is separate from addition to prevent recomputation
- */
-#define ROUND(f, a, b, c, d, x, s)	\
-	(a += f(b, c, d) + x, a = rol32(a, s))
-#define K1 0
-#define K2 013240474631UL
-#define K3 015666365641UL
-
-/*
- * Basic cut-down MD4 transform.  Returns only 32 bits of result.
- */
-__u32 half_md4_transform(__u32 buf[4], __u32 const in[8])
-{
-	__u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3];
-
-	/* Round 1 */
-	ROUND(F, a, b, c, d, in[0] + K1,  3);
-	ROUND(F, d, a, b, c, in[1] + K1,  7);
-	ROUND(F, c, d, a, b, in[2] + K1, 11);
-	ROUND(F, b, c, d, a, in[3] + K1, 19);
-	ROUND(F, a, b, c, d, in[4] + K1,  3);
-	ROUND(F, d, a, b, c, in[5] + K1,  7);
-	ROUND(F, c, d, a, b, in[6] + K1, 11);
-	ROUND(F, b, c, d, a, in[7] + K1, 19);
-
-	/* Round 2 */
-	ROUND(G, a, b, c, d, in[1] + K2,  3);
-	ROUND(G, d, a, b, c, in[3] + K2,  5);
-	ROUND(G, c, d, a, b, in[5] + K2,  9);
-	ROUND(G, b, c, d, a, in[7] + K2, 13);
-	ROUND(G, a, b, c, d, in[0] + K2,  3);
-	ROUND(G, d, a, b, c, in[2] + K2,  5);
-	ROUND(G, c, d, a, b, in[4] + K2,  9);
-	ROUND(G, b, c, d, a, in[6] + K2, 13);
-
-	/* Round 3 */
-	ROUND(H, a, b, c, d, in[3] + K3,  3);
-	ROUND(H, d, a, b, c, in[7] + K3,  9);
-	ROUND(H, c, d, a, b, in[2] + K3, 11);
-	ROUND(H, b, c, d, a, in[6] + K3, 15);
-	ROUND(H, a, b, c, d, in[1] + K3,  3);
-	ROUND(H, d, a, b, c, in[5] + K3,  9);
-	ROUND(H, c, d, a, b, in[0] + K3, 11);
-	ROUND(H, b, c, d, a, in[4] + K3, 15);
-
-	buf[0] += a;
-	buf[1] += b;
-	buf[2] += c;
-	buf[3] += d;
-
-	return buf[1]; /* "most hashed" word */
-}
-EXPORT_SYMBOL(half_md4_transform);
diff --git a/lib/ioremap.c b/lib/ioremap.c
index 86c8911b0e3a..a3e14ce92a56 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -144,4 +144,3 @@ int ioremap_page_range(unsigned long addr,
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(ioremap_page_range);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 0b92d605fb69..84812a9fb16f 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -769,7 +769,7 @@ static void radix_tree_free_nodes(struct radix_tree_node *node)
 			struct radix_tree_node *old = child;
 			offset = child->offset + 1;
 			child = child->parent;
-			WARN_ON_ONCE(!list_empty(&node->private_list));
+			WARN_ON_ONCE(!list_empty(&old->private_list));
 			radix_tree_node_free(old);
 			if (old == entry_to_node(node))
 				return;
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 2cecf05c82fd..55e11c4b2f3b 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -17,6 +17,7 @@
 
 #include <linux/random.h>
 #include <linux/sbitmap.h>
+#include <linux/seq_file.h>
 
 int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
 		      gfp_t flags, int node)
@@ -180,6 +181,62 @@ unsigned int sbitmap_weight(const struct sbitmap *sb)
 }
 EXPORT_SYMBOL_GPL(sbitmap_weight);
 
+void sbitmap_show(struct sbitmap *sb, struct seq_file *m)
+{
+	seq_printf(m, "depth=%u\n", sb->depth);
+	seq_printf(m, "busy=%u\n", sbitmap_weight(sb));
+	seq_printf(m, "bits_per_word=%u\n", 1U << sb->shift);
+	seq_printf(m, "map_nr=%u\n", sb->map_nr);
+}
+EXPORT_SYMBOL_GPL(sbitmap_show);
+
+static inline void emit_byte(struct seq_file *m, unsigned int offset, u8 byte)
+{
+	if ((offset & 0xf) == 0) {
+		if (offset != 0)
+			seq_putc(m, '\n');
+		seq_printf(m, "%08x:", offset);
+	}
+	if ((offset & 0x1) == 0)
+		seq_putc(m, ' ');
+	seq_printf(m, "%02x", byte);
+}
+
+void sbitmap_bitmap_show(struct sbitmap *sb, struct seq_file *m)
+{
+	u8 byte = 0;
+	unsigned int byte_bits = 0;
+	unsigned int offset = 0;
+	int i;
+
+	for (i = 0; i < sb->map_nr; i++) {
+		unsigned long word = READ_ONCE(sb->map[i].word);
+		unsigned int word_bits = READ_ONCE(sb->map[i].depth);
+
+		while (word_bits > 0) {
+			unsigned int bits = min(8 - byte_bits, word_bits);
+
+			byte |= (word & (BIT(bits) - 1)) << byte_bits;
+			byte_bits += bits;
+			if (byte_bits == 8) {
+				emit_byte(m, offset, byte);
+				byte = 0;
+				byte_bits = 0;
+				offset++;
+			}
+			word >>= bits;
+			word_bits -= bits;
+		}
+	}
+	if (byte_bits) {
+		emit_byte(m, offset, byte);
+		offset++;
+	}
+	if (offset)
+		seq_putc(m, '\n');
+}
+EXPORT_SYMBOL_GPL(sbitmap_bitmap_show);
+
 static unsigned int sbq_calc_wake_batch(unsigned int depth)
 {
 	unsigned int wake_batch;
@@ -239,7 +296,19 @@ EXPORT_SYMBOL_GPL(sbitmap_queue_init_node);
 
 void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth)
 {
-	sbq->wake_batch = sbq_calc_wake_batch(depth);
+	unsigned int wake_batch = sbq_calc_wake_batch(depth);
+	int i;
+
+	if (sbq->wake_batch != wake_batch) {
+		WRITE_ONCE(sbq->wake_batch, wake_batch);
+		/*
+		 * Pairs with the memory barrier in sbq_wake_up() to ensure that
+		 * the batch size is updated before the wait counts.
+		 */
+		smp_mb__before_atomic();
+		for (i = 0; i < SBQ_WAIT_QUEUES; i++)
+			atomic_set(&sbq->ws[i].wait_cnt, 1);
+	}
 	sbitmap_resize(&sbq->sb, depth);
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_resize);
@@ -297,20 +366,39 @@ static struct sbq_wait_state *sbq_wake_ptr(struct sbitmap_queue *sbq)
 static void sbq_wake_up(struct sbitmap_queue *sbq)
 {
 	struct sbq_wait_state *ws;
+	unsigned int wake_batch;
 	int wait_cnt;
 
-	/* Ensure that the wait list checks occur after clear_bit(). */
-	smp_mb();
+	/*
+	 * Pairs with the memory barrier in set_current_state() to ensure the
+	 * proper ordering of clear_bit()/waitqueue_active() in the waker and
+	 * test_and_set_bit()/prepare_to_wait()/finish_wait() in the waiter. See
+	 * the comment on waitqueue_active(). This is __after_atomic because we
+	 * just did clear_bit() in the caller.
+	 */
+	smp_mb__after_atomic();
 
 	ws = sbq_wake_ptr(sbq);
 	if (!ws)
 		return;
 
 	wait_cnt = atomic_dec_return(&ws->wait_cnt);
-	if (unlikely(wait_cnt < 0))
-		wait_cnt = atomic_inc_return(&ws->wait_cnt);
-	if (wait_cnt == 0) {
-		atomic_add(sbq->wake_batch, &ws->wait_cnt);
+	if (wait_cnt <= 0) {
+		wake_batch = READ_ONCE(sbq->wake_batch);
+		/*
+		 * Pairs with the memory barrier in sbitmap_queue_resize() to
+		 * ensure that we see the batch size update before the wait
+		 * count is reset.
+		 */
+		smp_mb__before_atomic();
+		/*
+		 * If there are concurrent callers to sbq_wake_up(), the last
+		 * one to decrement the wait count below zero will bump it back
+		 * up. If there is a concurrent resize, the count reset will
+		 * either cause the cmpxchg to fail or overwrite after the
+		 * cmpxchg.
+		 */
+		atomic_cmpxchg(&ws->wait_cnt, wait_cnt, wait_cnt + wake_batch);
 		sbq_index_atomic_inc(&sbq->wake_index);
 		wake_up(&ws->wait);
 	}
@@ -331,7 +419,8 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq)
 	int i, wake_index;
 
 	/*
-	 * Make sure all changes prior to this are visible from other CPUs.
+	 * Pairs with the memory barrier in set_current_state() like in
+	 * sbq_wake_up().
 	 */
 	smp_mb();
 	wake_index = atomic_read(&sbq->wake_index);
@@ -345,3 +434,37 @@ void sbitmap_queue_wake_all(struct sbitmap_queue *sbq)
 	}
 }
 EXPORT_SYMBOL_GPL(sbitmap_queue_wake_all);
+
+void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m)
+{
+	bool first;
+	int i;
+
+	sbitmap_show(&sbq->sb, m);
+
+	seq_puts(m, "alloc_hint={");
+	first = true;
+	for_each_possible_cpu(i) {
+		if (!first)
+			seq_puts(m, ", ");
+		first = false;
+		seq_printf(m, "%u", *per_cpu_ptr(sbq->alloc_hint, i));
+	}
+	seq_puts(m, "}\n");
+
+	seq_printf(m, "wake_batch=%u\n", sbq->wake_batch);
+	seq_printf(m, "wake_index=%d\n", atomic_read(&sbq->wake_index));
+
+	seq_puts(m, "ws={\n");
+	for (i = 0; i < SBQ_WAIT_QUEUES; i++) {
+		struct sbq_wait_state *ws = &sbq->ws[i];
+
+		seq_printf(m, "\t{.wait_cnt=%d, .wait=%s},\n",
+			   atomic_read(&ws->wait_cnt),
+			   waitqueue_active(&ws->wait) ? "active" : "inactive");
+	}
+	seq_puts(m, "}\n");
+
+	seq_printf(m, "round_robin=%d\n", sbq->round_robin);
+}
+EXPORT_SYMBOL_GPL(sbitmap_queue_show);
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
index adc6ee0a5126..4a720ed4fdaf 100644
--- a/lib/timerqueue.c
+++ b/lib/timerqueue.c
@@ -80,8 +80,7 @@ bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node)
 	if (head->next == node) {
 		struct rb_node *rbn = rb_next(&node->node);
 
-		head->next = rbn ?
-			rb_entry(rbn, struct timerqueue_node, node) : NULL;
+		head->next = rb_entry_safe(rbn, struct timerqueue_node, node);
 	}
 	rb_erase(&node->node, &head->head);
 	RB_CLEAR_NODE(&node->node);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 3bfed5ab2475..39ce616a9d71 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -237,6 +237,7 @@ static __init int bdi_class_init(void)
 
 	bdi_class->dev_groups = bdi_dev_groups;
 	bdi_debug_init();
+
 	return 0;
 }
 postcore_initcall(bdi_class_init);
@@ -758,15 +759,20 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 	if (!bdi->wb_congested)
 		return -ENOMEM;
 
+	atomic_set(&bdi->wb_congested->refcnt, 1);
+
 	err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
 	if (err) {
-		kfree(bdi->wb_congested);
+		wb_congested_put(bdi->wb_congested);
 		return err;
 	}
 	return 0;
 }
 
-static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }
+static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
+{
+	wb_congested_put(bdi->wb_congested);
+}
 
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
@@ -776,6 +782,7 @@ int bdi_init(struct backing_dev_info *bdi)
 
 	bdi->dev = NULL;
 
+	kref_init(&bdi->refcnt);
 	bdi->min_ratio = 0;
 	bdi->max_ratio = 100;
 	bdi->max_prop_frac = FPROP_FRAC_BASE;
@@ -791,6 +798,22 @@ int bdi_init(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_init);
 
+struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id)
+{
+	struct backing_dev_info *bdi;
+
+	bdi = kmalloc_node(sizeof(struct backing_dev_info),
+			   gfp_mask | __GFP_ZERO, node_id);
+	if (!bdi)
+		return NULL;
+
+	if (bdi_init(bdi)) {
+		kfree(bdi);
+		return NULL;
+	}
+	return bdi;
+}
+
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...)
 {
@@ -871,12 +894,26 @@ void bdi_unregister(struct backing_dev_info *bdi)
 	}
 }
 
-void bdi_exit(struct backing_dev_info *bdi)
+static void bdi_exit(struct backing_dev_info *bdi)
 {
 	WARN_ON_ONCE(bdi->dev);
 	wb_exit(&bdi->wb);
 }
 
+static void release_bdi(struct kref *ref)
+{
+	struct backing_dev_info *bdi =
+			container_of(ref, struct backing_dev_info, refcnt);
+
+	bdi_exit(bdi);
+	kfree(bdi);
+}
+
+void bdi_put(struct backing_dev_info *bdi)
+{
+	kref_put(&bdi->refcnt, release_bdi);
+}
+
 void bdi_destroy(struct backing_dev_info *bdi)
 {
 	bdi_unregister(bdi);
diff --git a/mm/filemap.c b/mm/filemap.c
index b772a33ef640..3f9afded581b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1791,6 +1791,11 @@ static ssize_t do_generic_file_read(struct file *filp, loff_t *ppos,
 
 		cond_resched();
 find_page:
+		if (fatal_signal_pending(current)) {
+			error = -EINTR;
+			goto out;
+		}
+
 		page = find_get_page(mapping, index);
 		if (!page) {
 			page_cache_sync_readahead(mapping,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9a6bd6c8d55a..5f3ad65c85de 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -783,6 +783,12 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 	assert_spin_locked(pmd_lockptr(mm, pmd));
 
+	/*
+	 * When we COW a devmap PMD entry, we split it into PTEs, so we should
+	 * not be in this function with `flags & FOLL_COW` set.
+	 */
+	WARN_ONCE(flags & FOLL_COW, "mm: In follow_devmap_pmd with FOLL_COW set");
+
 	if (flags & FOLL_WRITE && !pmd_write(*pmd))
 		return NULL;
 
@@ -1128,6 +1134,16 @@ out_unlock:
 	return ret;
 }
 
+/*
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+static inline bool can_follow_write_pmd(pmd_t pmd, unsigned int flags)
+{
+	return pmd_write(pmd) ||
+	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pmd_dirty(pmd));
+}
+
 struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 				   unsigned long addr,
 				   pmd_t *pmd,
@@ -1138,7 +1154,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 
 	assert_spin_locked(pmd_lockptr(mm, pmd));
 
-	if (flags & FOLL_WRITE && !pmd_write(*pmd))
+	if (flags & FOLL_WRITE && !can_follow_write_pmd(*pmd, flags))
 		goto out;
 
 	/* Avoid dumping huge zero page */
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index b82b3e215157..f479365530b6 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <linux/ftrace.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/printk.h>
@@ -300,6 +301,8 @@ void kasan_report(unsigned long addr, size_t size,
 	if (likely(!kasan_report_enabled()))
 		return;
 
+	disable_trace_on_warning();
+
 	info.access_addr = (void *)addr;
 	info.access_size = size;
 	info.is_write = is_write;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a63a8f832664..b822e158b319 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4353,9 +4353,9 @@ static int mem_cgroup_do_precharge(unsigned long count)
 		return ret;
 	}
 
-	/* Try charges one by one with reclaim */
+	/* Try charges one by one with reclaim, but do not retry */
 	while (count--) {
-		ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
+		ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1);
 		if (ret)
 			return ret;
 		mc.precharge++;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e43142c15631..b8c11e063ff0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1033,36 +1033,39 @@ static void node_states_set_node(int node, struct memory_notify *arg)
 	node_set_state(node, N_MEMORY);
 }
 
-int zone_can_shift(unsigned long pfn, unsigned long nr_pages,
-		   enum zone_type target)
+bool zone_can_shift(unsigned long pfn, unsigned long nr_pages,
+		   enum zone_type target, int *zone_shift)
 {
 	struct zone *zone = page_zone(pfn_to_page(pfn));
 	enum zone_type idx = zone_idx(zone);
 	int i;
 
+	*zone_shift = 0;
+
 	if (idx < target) {
 		/* pages must be at end of current zone */
 		if (pfn + nr_pages != zone_end_pfn(zone))
-			return 0;
+			return false;
 
 		/* no zones in use between current zone and target */
 		for (i = idx + 1; i < target; i++)
 			if (zone_is_initialized(zone - idx + i))
-				return 0;
+				return false;
 	}
 
 	if (target < idx) {
 		/* pages must be at beginning of current zone */
 		if (pfn != zone->zone_start_pfn)
-			return 0;
+			return false;
 
 		/* no zones in use between current zone and target */
 		for (i = target + 1; i < idx; i++)
 			if (zone_is_initialized(zone - idx + i))
-				return 0;
+				return false;
 	}
 
-	return target - idx;
+	*zone_shift = target - idx;
+	return true;
 }
 
 /* Must be protected by mem_hotplug_begin() */
@@ -1089,10 +1092,13 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	    !can_online_high_movable(zone))
 		return -EINVAL;
 
-	if (online_type == MMOP_ONLINE_KERNEL)
-		zone_shift = zone_can_shift(pfn, nr_pages, ZONE_NORMAL);
-	else if (online_type == MMOP_ONLINE_MOVABLE)
-		zone_shift = zone_can_shift(pfn, nr_pages, ZONE_MOVABLE);
+	if (online_type == MMOP_ONLINE_KERNEL) {
+		if (!zone_can_shift(pfn, nr_pages, ZONE_NORMAL, &zone_shift))
+			return -EINVAL;
+	} else if (online_type == MMOP_ONLINE_MOVABLE) {
+		if (!zone_can_shift(pfn, nr_pages, ZONE_MOVABLE, &zone_shift))
+			return -EINVAL;
+	}
 
 	zone = move_pfn_range(zone_shift, pfn, pfn + nr_pages);
 	if (!zone)
@@ -1477,17 +1483,20 @@ bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
 }
 
 /*
- * Confirm all pages in a range [start, end) is belongs to the same zone.
+ * Confirm all pages in a range [start, end) belong to the same zone.
+ * When true, return its valid [start, end).
  */
-int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
+int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
+			 unsigned long *valid_start, unsigned long *valid_end)
 {
 	unsigned long pfn, sec_end_pfn;
+	unsigned long start, end;
 	struct zone *zone = NULL;
 	struct page *page;
 	int i;
-	for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn);
+	for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn + 1);
 	     pfn < end_pfn;
-	     pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) {
+	     pfn = sec_end_pfn, sec_end_pfn += PAGES_PER_SECTION) {
 		/* Make sure the memory section is present first */
 		if (!present_section_nr(pfn_to_section_nr(pfn)))
 			continue;
@@ -1503,10 +1512,20 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
 			page = pfn_to_page(pfn + i);
 			if (zone && page_zone(page) != zone)
 				return 0;
+			if (!zone)
+				start = pfn + i;
 			zone = page_zone(page);
+			end = pfn + MAX_ORDER_NR_PAGES;
 		}
 	}
-	return 1;
+
+	if (zone) {
+		*valid_start = start;
+		*valid_end = end;
+		return 1;
+	} else {
+		return 0;
+	}
 }
 
 /*
@@ -1833,6 +1852,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	long offlined_pages;
 	int ret, drain, retry_max, node;
 	unsigned long flags;
+	unsigned long valid_start, valid_end;
 	struct zone *zone;
 	struct memory_notify arg;
 
@@ -1843,10 +1863,10 @@ static int __ref __offline_pages(unsigned long start_pfn,
 		return -EINVAL;
 	/* This makes hotplug much easier...and readable.
 	   we assume this for now. .*/
-	if (!test_pages_in_a_zone(start_pfn, end_pfn))
+	if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end))
 		return -EINVAL;
 
-	zone = page_zone(pfn_to_page(start_pfn));
+	zone = page_zone(pfn_to_page(valid_start));
 	node = zone_to_nid(zone);
 	nr_pages = end_pfn - start_pfn;
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2e346645eb80..1e7873e40c9a 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2017,8 +2017,8 @@ retry_cpuset:
 
 	nmask = policy_nodemask(gfp, pol);
 	zl = policy_zonelist(gfp, pol, node);
-	mpol_cond_put(pol);
 	page = __alloc_pages_nodemask(gfp, order, zl, nmask);
+	mpol_cond_put(pol);
 out:
 	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
 		goto retry_cpuset;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 290e8b7d3181..216449825859 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1988,11 +1988,11 @@ void laptop_mode_timer_fn(unsigned long data)
 	 * We want to write everything out, not just down to the dirty
 	 * threshold
 	 */
-	if (!bdi_has_dirty_io(&q->backing_dev_info))
+	if (!bdi_has_dirty_io(q->backing_dev_info))
 		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(wb, &q->backing_dev_info.wb_list, bdi_node)
+	list_for_each_entry_rcu(wb, &q->backing_dev_info->wb_list, bdi_node)
 		if (wb_has_dirty_io(wb))
 			wb_start_writeback(wb, nr_pages, true,
 					   WB_REASON_LAPTOP_TIMER);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d604d2596b7b..f3e0c69a97b7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3523,12 +3523,13 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	struct page *page = NULL;
 	unsigned int alloc_flags;
 	unsigned long did_some_progress;
-	enum compact_priority compact_priority = DEF_COMPACT_PRIORITY;
+	enum compact_priority compact_priority;
 	enum compact_result compact_result;
-	int compaction_retries = 0;
-	int no_progress_loops = 0;
+	int compaction_retries;
+	int no_progress_loops;
 	unsigned long alloc_start = jiffies;
 	unsigned int stall_timeout = 10 * HZ;
+	unsigned int cpuset_mems_cookie;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -3549,6 +3550,23 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 				(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
 		gfp_mask &= ~__GFP_ATOMIC;
 
+retry_cpuset:
+	compaction_retries = 0;
+	no_progress_loops = 0;
+	compact_priority = DEF_COMPACT_PRIORITY;
+	cpuset_mems_cookie = read_mems_allowed_begin();
+	/*
+	 * We need to recalculate the starting point for the zonelist iterator
+	 * because we might have used different nodemask in the fast path, or
+	 * there was a cpuset modification and we are retrying - otherwise we
+	 * could end up iterating over non-eligible zones endlessly.
+	 */
+	ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+					ac->high_zoneidx, ac->nodemask);
+	if (!ac->preferred_zoneref->zone)
+		goto nopage;
+
+
 	/*
 	 * The fast path uses conservative alloc_flags to succeed only until
 	 * kswapd needs to be woken up, and to avoid the cost of setting up
@@ -3708,6 +3726,13 @@ retry:
 				&compaction_retries))
 		goto retry;
 
+	/*
+	 * It's possible we raced with cpuset update so the OOM would be
+	 * premature (see below the nopage: label for full explanation).
+	 */
+	if (read_mems_allowed_retry(cpuset_mems_cookie))
+		goto retry_cpuset;
+
 	/* Reclaim has failed us, start killing things */
 	page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
 	if (page)
@@ -3720,6 +3745,16 @@ retry:
 	}
 
 nopage:
+	/*
+	 * When updating a task's mems_allowed or mempolicy nodemask, it is
+	 * possible to race with parallel threads in such a way that our
+	 * allocation can fail while the mask is being updated. If we are about
+	 * to fail, check if the cpuset changed during allocation and if so,
+	 * retry.
+	 */
+	if (read_mems_allowed_retry(cpuset_mems_cookie))
+		goto retry_cpuset;
+
 	warn_alloc(gfp_mask,
 			"page allocation failure: order:%u", order);
 got_pg:
@@ -3734,7 +3769,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 			struct zonelist *zonelist, nodemask_t *nodemask)
 {
 	struct page *page;
-	unsigned int cpuset_mems_cookie;
 	unsigned int alloc_flags = ALLOC_WMARK_LOW;
 	gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
 	struct alloc_context ac = {
@@ -3771,9 +3805,6 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE)
 		alloc_flags |= ALLOC_CMA;
 
-retry_cpuset:
-	cpuset_mems_cookie = read_mems_allowed_begin();
-
 	/* Dirty zone balancing only done in the fast path */
 	ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
 
@@ -3784,8 +3815,13 @@ retry_cpuset:
 	 */
 	ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
 					ac.high_zoneidx, ac.nodemask);
-	if (!ac.preferred_zoneref) {
+	if (!ac.preferred_zoneref->zone) {
 		page = NULL;
+		/*
+		 * This might be due to race with cpuset_current_mems_allowed
+		 * update, so make sure we retry with original nodemask in the
+		 * slow path.
+		 */
 		goto no_zone;
 	}
 
@@ -3794,6 +3830,7 @@ retry_cpuset:
 	if (likely(page))
 		goto out;
 
+no_zone:
 	/*
 	 * Runtime PM, block IO and its error handling path can deadlock
 	 * because I/O on the device might not complete.
@@ -3805,21 +3842,10 @@ retry_cpuset:
 	 * Restore the original nodemask if it was potentially replaced with
 	 * &cpuset_current_mems_allowed to optimize the fast-path attempt.
 	 */
-	if (cpusets_enabled())
+	if (unlikely(ac.nodemask != nodemask))
 		ac.nodemask = nodemask;
-	page = __alloc_pages_slowpath(alloc_mask, order, &ac);
 
-no_zone:
-	/*
-	 * When updating a task's mems_allowed, it is possible to race with
-	 * parallel threads in such a way that an allocation can fail while
-	 * the mask is being updated. If a page allocation is about to fail,
-	 * check if the cpuset changed during allocation and if so, retry.
-	 */
-	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) {
-		alloc_mask = gfp_mask;
-		goto retry_cpuset;
-	}
+	page = __alloc_pages_slowpath(alloc_mask, order, &ac);
 
 out:
 	if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
@@ -7248,6 +7274,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 		.zone = page_zone(pfn_to_page(start)),
 		.mode = MIGRATE_SYNC,
 		.ignore_skip_hint = true,
+		.gfp_mask = GFP_KERNEL,
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
 
diff --git a/mm/shmem.c b/mm/shmem.c
index bb53285a1d99..3a7587a0314d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -415,6 +415,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 		struct shrink_control *sc, unsigned long nr_to_split)
 {
 	LIST_HEAD(list), *pos, *next;
+	LIST_HEAD(to_remove);
 	struct inode *inode;
 	struct shmem_inode_info *info;
 	struct page *page;
@@ -441,9 +442,8 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 		/* Check if there's anything to gain */
 		if (round_up(inode->i_size, PAGE_SIZE) ==
 				round_up(inode->i_size, HPAGE_PMD_SIZE)) {
-			list_del_init(&info->shrinklist);
+			list_move(&info->shrinklist, &to_remove);
 			removed++;
-			iput(inode);
 			goto next;
 		}
 
@@ -454,6 +454,13 @@ next:
 	}
 	spin_unlock(&sbinfo->shrinklist_lock);
 
+	list_for_each_safe(pos, next, &to_remove) {
+		info = list_entry(pos, struct shmem_inode_info, shrinklist);
+		inode = &info->vfs_inode;
+		list_del_init(&info->shrinklist);
+		iput(inode);
+	}
+
 	list_for_each_safe(pos, next, &list) {
 		int ret;
 
diff --git a/mm/slub.c b/mm/slub.c
index 067598a00849..7ec0a965c6a3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -496,10 +496,11 @@ static inline int check_valid_pointer(struct kmem_cache *s,
 	return 1;
 }
 
-static void print_section(char *text, u8 *addr, unsigned int length)
+static void print_section(char *level, char *text, u8 *addr,
+			  unsigned int length)
 {
 	metadata_access_enable();
-	print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
+	print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, 16, 1, addr,
 			length, 1);
 	metadata_access_disable();
 }
@@ -636,14 +637,15 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 	       p, p - addr, get_freepointer(s, p));
 
 	if (s->flags & SLAB_RED_ZONE)
-		print_section("Redzone ", p - s->red_left_pad, s->red_left_pad);
+		print_section(KERN_ERR, "Redzone ", p - s->red_left_pad,
+			      s->red_left_pad);
 	else if (p > addr + 16)
-		print_section("Bytes b4 ", p - 16, 16);
+		print_section(KERN_ERR, "Bytes b4 ", p - 16, 16);
 
-	print_section("Object ", p, min_t(unsigned long, s->object_size,
-				PAGE_SIZE));
+	print_section(KERN_ERR, "Object ", p,
+		      min_t(unsigned long, s->object_size, PAGE_SIZE));
 	if (s->flags & SLAB_RED_ZONE)
-		print_section("Redzone ", p + s->object_size,
+		print_section(KERN_ERR, "Redzone ", p + s->object_size,
 			s->inuse - s->object_size);
 
 	if (s->offset)
@@ -658,7 +660,8 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 
 	if (off != size_from_object(s))
 		/* Beginning of the filler is the free pointer */
-		print_section("Padding ", p + off, size_from_object(s) - off);
+		print_section(KERN_ERR, "Padding ", p + off,
+			      size_from_object(s) - off);
 
 	dump_stack();
 }
@@ -820,7 +823,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
 		end--;
 
 	slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
-	print_section("Padding ", end - remainder, remainder);
+	print_section(KERN_ERR, "Padding ", end - remainder, remainder);
 
 	restore_bytes(s, "slab padding", POISON_INUSE, end - remainder, end);
 	return 0;
@@ -973,7 +976,7 @@ static void trace(struct kmem_cache *s, struct page *page, void *object,
 			page->freelist);
 
 		if (!alloc)
-			print_section("Object ", (void *)object,
+			print_section(KERN_INFO, "Object ", (void *)object,
 					s->object_size);
 
 		dump_stack();
@@ -1419,6 +1422,10 @@ static int init_cache_random_seq(struct kmem_cache *s)
 	int err;
 	unsigned long i, count = oo_objects(s->oo);
 
+	/* Bailout if already initialised */
+	if (s->random_seq)
+		return 0;
+
 	err = cache_random_seq_create(s, count, GFP_KERNEL);
 	if (err) {
 		pr_err("SLUB: Unable to initialize free list for %s\n",
diff --git a/mm/zswap.c b/mm/zswap.c
index 067a0d62f318..cabf09e0128b 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -78,7 +78,13 @@ static u64 zswap_duplicate_entry;
 
 /* Enable/disable zswap (disabled by default) */
 static bool zswap_enabled;
-module_param_named(enabled, zswap_enabled, bool, 0644);
+static int zswap_enabled_param_set(const char *,
+				   const struct kernel_param *);
+static struct kernel_param_ops zswap_enabled_param_ops = {
+	.set =		zswap_enabled_param_set,
+	.get =		param_get_bool,
+};
+module_param_cb(enabled, &zswap_enabled_param_ops, &zswap_enabled, 0644);
 
 /* Crypto compressor to use */
 #define ZSWAP_COMPRESSOR_DEFAULT "lzo"
@@ -176,6 +182,9 @@ static atomic_t zswap_pools_count = ATOMIC_INIT(0);
 /* used by param callback function */
 static bool zswap_init_started;
 
+/* fatal error during init */
+static bool zswap_init_failed;
+
 /*********************************
 * helpers and fwd declarations
 **********************************/
@@ -624,6 +633,11 @@ static int __zswap_param_set(const char *val, const struct kernel_param *kp,
 	char *s = strstrip((char *)val);
 	int ret;
 
+	if (zswap_init_failed) {
+		pr_err("can't set param, initialization failed\n");
+		return -ENODEV;
+	}
+
 	/* no change required */
 	if (!strcmp(s, *(char **)kp->arg))
 		return 0;
@@ -703,6 +717,17 @@ static int zswap_zpool_param_set(const char *val,
 	return __zswap_param_set(val, kp, NULL, zswap_compressor);
 }
 
+static int zswap_enabled_param_set(const char *val,
+				   const struct kernel_param *kp)
+{
+	if (zswap_init_failed) {
+		pr_err("can't enable, initialization failed\n");
+		return -ENODEV;
+	}
+
+	return param_set_bool(val, kp);
+}
+
 /*********************************
 * writeback code
 **********************************/
@@ -1201,6 +1226,9 @@ hp_fail:
 dstmem_fail:
 	zswap_entry_cache_destroy();
 cache_fail:
+	/* if built-in, we aren't unloaded on failure; don't allow use */
+	zswap_init_failed = true;
+	zswap_enabled = false;
 	return -ENOMEM;
 }
 /* must be late so crypto has time to come up */
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 9c561e683f4b..0854ebd8613e 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -474,7 +474,7 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 	if (!primary_if) {
 		ret = -EINVAL;
-		goto put_primary_if;
+		goto free_skb;
 	}
 
 	/* Create one header to be copied to all fragments */
@@ -502,7 +502,7 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 		skb_fragment = batadv_frag_create(skb, &frag_header, mtu);
 		if (!skb_fragment) {
 			ret = -ENOMEM;
-			goto free_skb;
+			goto put_primary_if;
 		}
 
 		batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_TX);
@@ -511,7 +511,7 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 		ret = batadv_send_unicast_skb(skb_fragment, neigh_node);
 		if (ret != NET_XMIT_SUCCESS) {
 			ret = NET_XMIT_DROP;
-			goto free_skb;
+			goto put_primary_if;
 		}
 
 		frag_header.no++;
@@ -519,7 +519,7 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 		/* The initial check in this function should cover this case */
 		if (frag_header.no == BATADV_FRAG_MAX_FRAGMENTS - 1) {
 			ret = -EINVAL;
-			goto free_skb;
+			goto put_primary_if;
 		}
 	}
 
@@ -527,7 +527,7 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 	if (batadv_skb_head_push(skb, header_size) < 0 ||
 	    pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0) {
 		ret = -ENOMEM;
-		goto free_skb;
+		goto put_primary_if;
 	}
 
 	memcpy(skb->data, &frag_header, header_size);
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 1904a93f47d5..d491529332f4 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -920,7 +920,7 @@ static void chan_close_cb(struct l2cap_chan *chan)
 			BT_DBG("dev %p removing %speer %p", dev,
 			       last ? "last " : "1 ", peer);
 			BT_DBG("chan %p orig refcnt %d", chan,
-			       atomic_read(&chan->kref.refcount));
+			       kref_read(&chan->kref));
 
 			l2cap_chan_put(chan);
 			break;
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 5f123c3320a7..f0095fd79818 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -810,7 +810,7 @@ static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked)
 /* AMP Manager functions */
 struct amp_mgr *amp_mgr_get(struct amp_mgr *mgr)
 {
-	BT_DBG("mgr %p orig refcnt %d", mgr, atomic_read(&mgr->kref.refcount));
+	BT_DBG("mgr %p orig refcnt %d", mgr, kref_read(&mgr->kref));
 
 	kref_get(&mgr->kref);
 
@@ -833,7 +833,7 @@ static void amp_mgr_destroy(struct kref *kref)
 
 int amp_mgr_put(struct amp_mgr *mgr)
 {
-	BT_DBG("mgr %p orig refcnt %d", mgr, atomic_read(&mgr->kref.refcount));
+	BT_DBG("mgr %p orig refcnt %d", mgr, kref_read(&mgr->kref));
 
 	return kref_put(&mgr->kref, &amp_mgr_destroy);
 }
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index e32f34189007..02a4ccc04e1e 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -24,7 +24,7 @@
 void amp_ctrl_get(struct amp_ctrl *ctrl)
 {
 	BT_DBG("ctrl %p orig refcnt %d", ctrl,
-	       atomic_read(&ctrl->kref.refcount));
+	       kref_read(&ctrl->kref));
 
 	kref_get(&ctrl->kref);
 }
@@ -42,7 +42,7 @@ static void amp_ctrl_destroy(struct kref *kref)
 int amp_ctrl_put(struct amp_ctrl *ctrl)
 {
 	BT_DBG("ctrl %p orig refcnt %d", ctrl,
-	       atomic_read(&ctrl->kref.refcount));
+	       kref_read(&ctrl->kref));
 
 	return kref_put(&ctrl->kref, &amp_ctrl_destroy);
 }
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ce0b5dd01953..fc7f321a3823 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -481,14 +481,14 @@ static void l2cap_chan_destroy(struct kref *kref)
 
 void l2cap_chan_hold(struct l2cap_chan *c)
 {
-	BT_DBG("chan %p orig refcnt %d", c, atomic_read(&c->kref.refcount));
+	BT_DBG("chan %p orig refcnt %d", c, kref_read(&c->kref));
 
 	kref_get(&c->kref);
 }
 
 void l2cap_chan_put(struct l2cap_chan *c)
 {
-	BT_DBG("chan %p orig refcnt %d", c, atomic_read(&c->kref.refcount));
+	BT_DBG("chan %p orig refcnt %d", c, kref_read(&c->kref));
 
 	kref_put(&c->kref, l2cap_chan_destroy);
 }
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 71c7453268c1..7109b389ea58 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -781,20 +781,6 @@ static int br_validate(struct nlattr *tb[], struct nlattr *data[])
 	return 0;
 }
 
-static int br_dev_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[])
-{
-	struct net_bridge *br = netdev_priv(dev);
-
-	if (tb[IFLA_ADDRESS]) {
-		spin_lock_bh(&br->lock);
-		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
-		spin_unlock_bh(&br->lock);
-	}
-
-	return register_netdevice(dev);
-}
-
 static int br_port_slave_changelink(struct net_device *brdev,
 				    struct net_device *dev,
 				    struct nlattr *tb[],
@@ -1115,6 +1101,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	return 0;
 }
 
+static int br_dev_newlink(struct net *src_net, struct net_device *dev,
+			  struct nlattr *tb[], struct nlattr *data[])
+{
+	struct net_bridge *br = netdev_priv(dev);
+	int err;
+
+	if (tb[IFLA_ADDRESS]) {
+		spin_lock_bh(&br->lock);
+		br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
+		spin_unlock_bh(&br->lock);
+	}
+
+	err = br_changelink(dev, tb, data);
+	if (err)
+		return err;
+
+	return register_netdevice(dev);
+}
+
 static size_t br_get_size(const struct net_device *brdev)
 {
 	return nla_total_size(sizeof(u32)) +	/* IFLA_BR_FORWARD_DELAY  */
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 1108079d934f..5488e4a6ccd0 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -445,6 +445,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  * @func: callback function on filter match
  * @data: returned parameter for callback function
  * @ident: string for calling module identification
+ * @sk: socket pointer (might be NULL)
  *
  * Description:
  *  Invokes the callback function with the received sk_buff and the given
@@ -468,7 +469,7 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
  */
 int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		    void (*func)(struct sk_buff *, void *), void *data,
-		    char *ident)
+		    char *ident, struct sock *sk)
 {
 	struct receiver *r;
 	struct hlist_head *rl;
@@ -496,6 +497,7 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
 		r->func    = func;
 		r->data    = data;
 		r->ident   = ident;
+		r->sk      = sk;
 
 		hlist_add_head_rcu(&r->list, rl);
 		d->entries++;
@@ -520,8 +522,11 @@ EXPORT_SYMBOL(can_rx_register);
 static void can_rx_delete_receiver(struct rcu_head *rp)
 {
 	struct receiver *r = container_of(rp, struct receiver, rcu);
+	struct sock *sk = r->sk;
 
 	kmem_cache_free(rcv_cache, r);
+	if (sk)
+		sock_put(sk);
 }
 
 /**
@@ -596,8 +601,11 @@ void can_rx_unregister(struct net_device *dev, canid_t can_id, canid_t mask,
 	spin_unlock(&can_rcvlists_lock);
 
 	/* schedule the receiver item for deletion */
-	if (r)
+	if (r) {
+		if (r->sk)
+			sock_hold(r->sk);
 		call_rcu(&r->rcu, can_rx_delete_receiver);
+	}
 }
 EXPORT_SYMBOL(can_rx_unregister);
 
diff --git a/net/can/af_can.h b/net/can/af_can.h
index fca0fe9fc45a..b86f5129e838 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -50,13 +50,14 @@
 
 struct receiver {
 	struct hlist_node list;
-	struct rcu_head rcu;
 	canid_t can_id;
 	canid_t mask;
 	unsigned long matches;
 	void (*func)(struct sk_buff *, void *);
 	void *data;
 	char *ident;
+	struct sock *sk;
+	struct rcu_head rcu;
 };
 
 #define CAN_SFF_RCV_ARRAY_SZ (1 << CAN_SFF_ID_BITS)
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 21ac75390e3d..95d13b233c65 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -734,14 +734,23 @@ static struct bcm_op *bcm_find_op(struct list_head *ops,
 
 static void bcm_remove_op(struct bcm_op *op)
 {
-	hrtimer_cancel(&op->timer);
-	hrtimer_cancel(&op->thrtimer);
-
-	if (op->tsklet.func)
-		tasklet_kill(&op->tsklet);
+	if (op->tsklet.func) {
+		while (test_bit(TASKLET_STATE_SCHED, &op->tsklet.state) ||
+		       test_bit(TASKLET_STATE_RUN, &op->tsklet.state) ||
+		       hrtimer_active(&op->timer)) {
+			hrtimer_cancel(&op->timer);
+			tasklet_kill(&op->tsklet);
+		}
+	}
 
-	if (op->thrtsklet.func)
-		tasklet_kill(&op->thrtsklet);
+	if (op->thrtsklet.func) {
+		while (test_bit(TASKLET_STATE_SCHED, &op->thrtsklet.state) ||
+		       test_bit(TASKLET_STATE_RUN, &op->thrtsklet.state) ||
+		       hrtimer_active(&op->thrtimer)) {
+			hrtimer_cancel(&op->thrtimer);
+			tasklet_kill(&op->thrtsklet);
+		}
+	}
 
 	if ((op->frames) && (op->frames != &op->sframe))
 		kfree(op->frames);
@@ -1216,7 +1225,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 				err = can_rx_register(dev, op->can_id,
 						      REGMASK(op->can_id),
 						      bcm_rx_handler, op,
-						      "bcm");
+						      "bcm", sk);
 
 				op->rx_reg_dev = dev;
 				dev_put(dev);
@@ -1225,7 +1234,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 		} else
 			err = can_rx_register(NULL, op->can_id,
 					      REGMASK(op->can_id),
-					      bcm_rx_handler, op, "bcm");
+					      bcm_rx_handler, op, "bcm", sk);
 		if (err) {
 			/* this bcm rx op is broken -> remove it */
 			list_del(&op->list);
diff --git a/net/can/gw.c b/net/can/gw.c
index a54ab0c82104..7056a1a2bb70 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -442,7 +442,7 @@ static inline int cgw_register_filter(struct cgw_job *gwj)
 {
 	return can_rx_register(gwj->src.dev, gwj->ccgw.filter.can_id,
 			       gwj->ccgw.filter.can_mask, can_can_gw_rcv,
-			       gwj, "gw");
+			       gwj, "gw", NULL);
 }
 
 static inline void cgw_unregister_filter(struct cgw_job *gwj)
diff --git a/net/can/raw.c b/net/can/raw.c
index b075f028d7e2..6dc546a06673 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -190,7 +190,7 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk,
 	for (i = 0; i < count; i++) {
 		err = can_rx_register(dev, filter[i].can_id,
 				      filter[i].can_mask,
-				      raw_rcv, sk, "raw");
+				      raw_rcv, sk, "raw", sk);
 		if (err) {
 			/* clean up successfully registered filters */
 			while (--i >= 0)
@@ -211,7 +211,7 @@ static int raw_enable_errfilter(struct net_device *dev, struct sock *sk,
 
 	if (err_mask)
 		err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG,
-				      raw_rcv, sk, "raw");
+				      raw_rcv, sk, "raw", sk);
 
 	return err;
 }
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 770c52701efa..bad3d4ae43f6 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -3425,7 +3425,7 @@ static void ceph_msg_release(struct kref *kref)
 struct ceph_msg *ceph_msg_get(struct ceph_msg *msg)
 {
 	dout("%s %p (was %d)\n", __func__, msg,
-	     atomic_read(&msg->kref.refcount));
+	     kref_read(&msg->kref));
 	kref_get(&msg->kref);
 	return msg;
 }
@@ -3434,7 +3434,7 @@ EXPORT_SYMBOL(ceph_msg_get);
 void ceph_msg_put(struct ceph_msg *msg)
 {
 	dout("%s %p (was %d)\n", __func__, msg,
-	     atomic_read(&msg->kref.refcount));
+	     kref_read(&msg->kref));
 	kref_put(&msg->kref, ceph_msg_release);
 }
 EXPORT_SYMBOL(ceph_msg_put);
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 842f049abb86..f3378ba1a828 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -438,7 +438,7 @@ static void ceph_osdc_release_request(struct kref *kref)
 void ceph_osdc_get_request(struct ceph_osd_request *req)
 {
 	dout("%s %p (was %d)\n", __func__, req,
-	     atomic_read(&req->r_kref.refcount));
+	     kref_read(&req->r_kref));
 	kref_get(&req->r_kref);
 }
 EXPORT_SYMBOL(ceph_osdc_get_request);
@@ -447,7 +447,7 @@ void ceph_osdc_put_request(struct ceph_osd_request *req)
 {
 	if (req) {
 		dout("%s %p (was %d)\n", __func__, req,
-		     atomic_read(&req->r_kref.refcount));
+		     kref_read(&req->r_kref));
 		kref_put(&req->r_kref, ceph_osdc_release_request);
 	}
 }
@@ -487,11 +487,11 @@ static void request_reinit(struct ceph_osd_request *req)
 	struct ceph_msg *reply_msg = req->r_reply;
 
 	dout("%s req %p\n", __func__, req);
-	WARN_ON(atomic_read(&req->r_kref.refcount) != 1);
+	WARN_ON(kref_read(&req->r_kref) != 1);
 	request_release_checks(req);
 
-	WARN_ON(atomic_read(&request_msg->kref.refcount) != 1);
-	WARN_ON(atomic_read(&reply_msg->kref.refcount) != 1);
+	WARN_ON(kref_read(&request_msg->kref) != 1);
+	WARN_ON(kref_read(&reply_msg->kref) != 1);
 	target_destroy(&req->r_t);
 
 	request_init(req);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 662bea587165..ea633342ab0d 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -332,7 +332,9 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len)
 EXPORT_SYMBOL(__skb_free_datagram_locked);
 
 int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
-			unsigned int flags)
+			unsigned int flags,
+			void (*destructor)(struct sock *sk,
+					   struct sk_buff *skb))
 {
 	int err = 0;
 
@@ -342,6 +344,8 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb,
 		if (skb == skb_peek(&sk->sk_receive_queue)) {
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			atomic_dec(&skb->users);
+			if (destructor)
+				destructor(sk, skb);
 			err = 0;
 		}
 		spin_unlock_bh(&sk->sk_receive_queue.lock);
@@ -375,7 +379,7 @@ EXPORT_SYMBOL(__sk_queue_drop_skb);
 
 int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
 {
-	int err = __sk_queue_drop_skb(sk, skb, flags);
+	int err = __sk_queue_drop_skb(sk, skb, flags, NULL);
 
 	kfree_skb(skb);
 	sk_mem_reclaim_partial(sk);
diff --git a/net/core/dev.c b/net/core/dev.c
index 07b307b0b414..29101c98399f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1695,24 +1695,19 @@ EXPORT_SYMBOL_GPL(net_dec_egress_queue);
 
 static struct static_key netstamp_needed __read_mostly;
 #ifdef HAVE_JUMP_LABEL
-/* We are not allowed to call static_key_slow_dec() from irq context
- * If net_disable_timestamp() is called from irq context, defer the
- * static_key_slow_dec() calls.
- */
 static atomic_t netstamp_needed_deferred;
-#endif
-
-void net_enable_timestamp(void)
+static void netstamp_clear(struct work_struct *work)
 {
-#ifdef HAVE_JUMP_LABEL
 	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
 
-	if (deferred) {
-		while (--deferred)
-			static_key_slow_dec(&netstamp_needed);
-		return;
-	}
+	while (deferred--)
+		static_key_slow_dec(&netstamp_needed);
+}
+static DECLARE_WORK(netstamp_work, netstamp_clear);
 #endif
+
+void net_enable_timestamp(void)
+{
 	static_key_slow_inc(&netstamp_needed);
 }
 EXPORT_SYMBOL(net_enable_timestamp);
@@ -1720,12 +1715,12 @@ EXPORT_SYMBOL(net_enable_timestamp);
 void net_disable_timestamp(void)
 {
 #ifdef HAVE_JUMP_LABEL
-	if (in_interrupt()) {
-		atomic_inc(&netstamp_needed_deferred);
-		return;
-	}
-#endif
+	/* net_disable_timestamp() can be called from non process context */
+	atomic_inc(&netstamp_needed_deferred);
+	schedule_work(&netstamp_work);
+#else
 	static_key_slow_dec(&netstamp_needed);
+#endif
 }
 EXPORT_SYMBOL(net_disable_timestamp);
 
@@ -2795,9 +2790,9 @@ static netdev_features_t harmonize_features(struct sk_buff *skb,
 	if (skb->ip_summed != CHECKSUM_NONE &&
 	    !can_checksum_protocol(features, type)) {
 		features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
-	} else if (illegal_highdma(skb->dev, skb)) {
-		features &= ~NETIF_F_SG;
 	}
+	if (illegal_highdma(skb->dev, skb))
+		features &= ~NETIF_F_SG;
 
 	return features;
 }
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index e23766c7e3ba..d92de0a1f0a4 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1405,9 +1405,12 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr)
 	if (regs.len > reglen)
 		regs.len = reglen;
 
-	regbuf = vzalloc(reglen);
-	if (reglen && !regbuf)
-		return -ENOMEM;
+	regbuf = NULL;
+	if (reglen) {
+		regbuf = vzalloc(reglen);
+		if (!regbuf)
+			return -ENOMEM;
+	}
 
 	ops->get_regs(dev, &regs, regbuf);
 
@@ -1712,7 +1715,7 @@ static noinline_for_stack int ethtool_get_channels(struct net_device *dev,
 static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
 						   void __user *useraddr)
 {
-	struct ethtool_channels channels, max;
+	struct ethtool_channels channels, max = { .cmd = ETHTOOL_GCHANNELS };
 	u32 max_rx_in_use = 0;
 
 	if (!dev->ethtool_ops->set_channels || !dev->ethtool_ops->get_channels)
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 71bb3e2eca08..b3eef90b2df9 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -386,6 +386,7 @@ static const struct lwtunnel_encap_ops bpf_encap_ops = {
 	.fill_encap	= bpf_fill_encap_info,
 	.get_encap_size = bpf_encap_nlsize,
 	.cmp_encap	= bpf_encap_cmp,
+	.owner		= THIS_MODULE,
 };
 
 static int __init bpf_lwt_init(void)
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index a5d4e866ce88..c23465005f2f 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -26,6 +26,7 @@
 #include <net/lwtunnel.h>
 #include <net/rtnetlink.h>
 #include <net/ip6_fib.h>
+#include <net/nexthop.h>
 
 #ifdef CONFIG_MODULES
 
@@ -114,25 +115,77 @@ int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[encap_type]);
+	if (likely(ops && ops->build_state && try_module_get(ops->owner))) {
+		ret = ops->build_state(dev, encap, family, cfg, lws);
+		if (ret)
+			module_put(ops->owner);
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(lwtunnel_build_state);
+
+int lwtunnel_valid_encap_type(u16 encap_type)
+{
+	const struct lwtunnel_encap_ops *ops;
+	int ret = -EINVAL;
+
+	if (encap_type == LWTUNNEL_ENCAP_NONE ||
+	    encap_type > LWTUNNEL_ENCAP_MAX)
+		return ret;
+
+	rcu_read_lock();
+	ops = rcu_dereference(lwtun_encaps[encap_type]);
+	rcu_read_unlock();
 #ifdef CONFIG_MODULES
 	if (!ops) {
 		const char *encap_type_str = lwtunnel_encap_str(encap_type);
 
 		if (encap_type_str) {
-			rcu_read_unlock();
+			__rtnl_unlock();
 			request_module("rtnl-lwt-%s", encap_type_str);
+			rtnl_lock();
+
 			rcu_read_lock();
 			ops = rcu_dereference(lwtun_encaps[encap_type]);
+			rcu_read_unlock();
 		}
 	}
 #endif
-	if (likely(ops && ops->build_state))
-		ret = ops->build_state(dev, encap, family, cfg, lws);
-	rcu_read_unlock();
+	return ops ? 0 : -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(lwtunnel_valid_encap_type);
 
-	return ret;
+int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
+{
+	struct rtnexthop *rtnh = (struct rtnexthop *)attr;
+	struct nlattr *nla_entype;
+	struct nlattr *attrs;
+	struct nlattr *nla;
+	u16 encap_type;
+	int attrlen;
+
+	while (rtnh_ok(rtnh, remaining)) {
+		attrlen = rtnh_attrlen(rtnh);
+		if (attrlen > 0) {
+			attrs = rtnh_attrs(rtnh);
+			nla = nla_find(attrs, attrlen, RTA_ENCAP);
+			nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
+
+			if (nla_entype) {
+				encap_type = nla_get_u16(nla_entype);
+
+				if (lwtunnel_valid_encap_type(encap_type) != 0)
+					return -EOPNOTSUPP;
+			}
+		}
+		rtnh = rtnh_next(rtnh, &remaining);
+	}
+
+	return 0;
 }
-EXPORT_SYMBOL(lwtunnel_build_state);
+EXPORT_SYMBOL(lwtunnel_valid_encap_type_attr);
 
 void lwtstate_free(struct lwtunnel_state *lws)
 {
@@ -144,6 +197,7 @@ void lwtstate_free(struct lwtunnel_state *lws)
 	} else {
 		kfree(lws);
 	}
+	module_put(ops->owner);
 }
 EXPORT_SYMBOL(lwtstate_free);
 
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7bb12e07ffef..e7c12caa20c8 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2923,7 +2923,8 @@ static void neigh_proc_update(struct ctl_table *ctl, int write)
 		return;
 
 	set_bit(index, p->data_state);
-	call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
+	if (index == NEIGH_VAR_DELAY_PROBE_TIME)
+		call_netevent_notifiers(NETEVENT_DELAY_PROBE_TIME_UPDATE, p);
 	if (!dev) /* NULL dev means this is default value */
 		neigh_copy_dflt_parms(net, p, index);
 }
diff --git a/net/dccp/input.c b/net/dccp/input.c
index ba347184bda9..8fedc2d49770 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -606,7 +606,8 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 			if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
 								    skb) < 0)
 				return 1;
-			goto discard;
+			consume_skb(skb);
+			return 0;
 		}
 		if (dh->dccph_type == DCCP_PKT_RESET)
 			goto discard;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index adfc790f7193..c4e879c02186 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -227,7 +227,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
 		opt = ireq->ipv6_opt;
 		if (!opt)
 			opt = rcu_dereference(np->opt);
-		err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
+		err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -281,7 +281,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
 	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(skb, dst);
-		ip6_xmit(ctl_sk, skb, &fl6, NULL, 0);
+		ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0);
 		DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
 		DCCP_INC_STATS(DCCP_MIB_OUTRSTS);
 		return;
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index da3862124545..0f99297b2fb3 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -273,6 +273,7 @@ static int dsa_user_port_apply(struct device_node *port, u32 index,
 	if (err) {
 		dev_warn(ds->dev, "Failed to create slave %d: %d\n",
 			 index, err);
+		ds->ports[index].netdev = NULL;
 		return err;
 	}
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 68c9eea00518..7d4596110851 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1105,10 +1105,8 @@ static int dsa_slave_phy_connect(struct dsa_slave_priv *p,
 	/* Use already configured phy mode */
 	if (p->phy_interface == PHY_INTERFACE_MODE_NA)
 		p->phy_interface = p->phy->interface;
-	phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
-			   p->phy_interface);
-
-	return 0;
+	return phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
+				  p->phy_interface);
 }
 
 static int dsa_slave_phy_setup(struct dsa_slave_priv *p,
@@ -1203,6 +1201,8 @@ int dsa_slave_suspend(struct net_device *slave_dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(slave_dev);
 
+	netif_device_detach(slave_dev);
+
 	if (p->phy) {
 		phy_stop(p->phy);
 		p->old_pause = -1;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 8c5a479681ca..516c87e75de7 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -356,6 +356,7 @@ void ether_setup(struct net_device *dev)
 	dev->header_ops		= &eth_header_ops;
 	dev->type		= ARPHRD_ETHER;
 	dev->hard_header_len 	= ETH_HLEN;
+	dev->min_header_len	= ETH_HLEN;
 	dev->mtu		= ETH_DATA_LEN;
 	dev->min_mtu		= ETH_MIN_MTU;
 	dev->max_mtu		= ETH_DATA_LEN;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 89a8cac4726a..51b27ae09fbd 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1263,7 +1263,7 @@ void __init arp_init(void)
 /*
  *	ax25 -> ASCII conversion
  */
-static char *ax2asc2(ax25_address *a, char *buf)
+static void ax2asc2(ax25_address *a, char *buf)
 {
 	char c, *s;
 	int n;
@@ -1285,10 +1285,10 @@ static char *ax2asc2(ax25_address *a, char *buf)
 	*s++ = n + '0';
 	*s++ = '\0';
 
-	if (*buf == '\0' || *buf == '-')
-		return "*";
-
-	return buf;
+	if (*buf == '\0' || *buf == '-') {
+		buf[0] = '*';
+		buf[1] = '\0';
+	}
 }
 #endif /* CONFIG_AX25 */
 
@@ -1322,7 +1322,7 @@ static void arp_format_neigh_entry(struct seq_file *seq,
 	}
 #endif
 	sprintf(tbuf, "%pI4", n->primary_key);
-	seq_printf(seq, "%-16s 0x%-10x0x%-10x%s     *        %s\n",
+	seq_printf(seq, "%-16s 0x%-10x0x%-10x%-17s     *        %s\n",
 		   tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name);
 	read_unlock(&n->lock);
 }
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 72d6f056d863..ae206163c273 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -1587,6 +1587,10 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
 				goto validate_return_locked;
 			}
 
+		if (opt_iter + 1 == opt_len) {
+			err_offset = opt_iter;
+			goto validate_return_locked;
+		}
 		tag_len = tag[1];
 		if (tag_len > (opt_len - opt_iter)) {
 			err_offset = opt_iter + 1;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index eae0332b0e8c..7db2ad2e82d3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -46,6 +46,7 @@
 #include <net/rtnetlink.h>
 #include <net/xfrm.h>
 #include <net/l3mdev.h>
+#include <net/lwtunnel.h>
 #include <trace/events/fib.h>
 
 #ifndef CONFIG_IP_MULTIPLE_TABLES
@@ -677,6 +678,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			cfg->fc_mx_len = nla_len(attr);
 			break;
 		case RTA_MULTIPATH:
+			err = lwtunnel_valid_encap_type_attr(nla_data(attr),
+							     nla_len(attr));
+			if (err < 0)
+				goto errout;
 			cfg->fc_mp = nla_data(attr);
 			cfg->fc_mp_len = nla_len(attr);
 			break;
@@ -691,6 +696,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			break;
 		case RTA_ENCAP_TYPE:
 			cfg->fc_encap_type = nla_get_u16(attr);
+			err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+			if (err < 0)
+				goto errout;
 			break;
 		}
 	}
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 5b15459955f8..44fd86de2823 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1172,6 +1172,7 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 				psf->sf_crcount = im->crcount;
 		}
 		in_dev_put(pmc->interface);
+		kfree(pmc);
 	}
 	spin_unlock_bh(&im->lock);
 }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index fac275c48108..b67719f45953 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1629,6 +1629,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
 	sk->sk_sndbuf = sysctl_wmem_default;
+	sk->sk_mark = fl4.flowi4_mark;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
 	if (unlikely(err)) {
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 53ae0c6315ad..900011709e3b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1238,7 +1238,14 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		pktinfo->ipi_ifindex = 0;
 		pktinfo->ipi_spec_dst.s_addr = 0;
 	}
-	skb_dst_drop(skb);
+	/* We need to keep the dst for __ip_options_echo()
+	 * We could restrict the test to opt.ts_needtime || opt.srr,
+	 * but the following is good enough as IP options are not often used.
+	 */
+	if (unlikely(IPCB(skb)->opt.optlen))
+		skb_dst_force(skb);
+	else
+		skb_dst_drop(skb);
 }
 
 int ip_setsockopt(struct sock *sk, int level,
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index fed3d29f9eb3..0fd1976ab63b 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -313,6 +313,7 @@ static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
 	.fill_encap = ip_tun_fill_encap_info,
 	.get_encap_size = ip_tun_encap_nlsize,
 	.cmp_encap = ip_tun_cmp_encap,
+	.owner = THIS_MODULE,
 };
 
 static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
@@ -403,6 +404,7 @@ static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = {
 	.fill_encap = ip6_tun_fill_encap_info,
 	.get_encap_size = ip6_tun_encap_nlsize,
 	.cmp_encap = ip_tun_cmp_encap,
+	.owner = THIS_MODULE,
 };
 
 void __init ip_tunnel_core_init(void)
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index a6b8c1a4102b..0a783cd73faf 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -144,7 +144,12 @@ clusterip_config_find_get(struct net *net, __be32 clusterip, int entry)
 	rcu_read_lock_bh();
 	c = __clusterip_config_find(net, clusterip);
 	if (c) {
-		if (!c->pde || unlikely(!atomic_inc_not_zero(&c->refcount)))
+#ifdef CONFIG_PROC_FS
+		if (!c->pde)
+			c = NULL;
+		else
+#endif
+		if (unlikely(!atomic_inc_not_zero(&c->refcount)))
 			c = NULL;
 		else if (entry)
 			atomic_inc(&c->entries);
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index f273098e48fd..37fb9552e858 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -63,10 +63,10 @@ static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4,
 	return dev_match || flags & XT_RPFILTER_LOOSE;
 }
 
-static bool rpfilter_is_local(const struct sk_buff *skb)
+static bool
+rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in)
 {
-	const struct rtable *rt = skb_rtable(skb);
-	return rt && (rt->rt_flags & RTCF_LOCAL);
+	return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK;
 }
 
 static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
@@ -79,7 +79,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	info = par->matchinfo;
 	invert = info->flags & XT_RPFILTER_INVERT;
 
-	if (rpfilter_is_local(skb))
+	if (rpfilter_is_loopback(skb, xt_in(par)))
 		return true ^ invert;
 
 	iph = ip_hdr(skb);
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index fd8220213afc..146d86105183 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -126,6 +126,8 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 	/* ip_route_me_harder expects skb->dst to be set */
 	skb_dst_set_noref(nskb, skb_dst(oldskb));
 
+	nskb->mark = IP4_REPLY_MARK(net, oldskb->mark);
+
 	skb_reserve(nskb, LL_MAX_HEADER);
 	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
 				   ip4_dst_hoplimit(skb_dst(nskb)));
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 965b1a161369..2981291910dd 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -26,13 +26,6 @@ static __be32 get_saddr(__be32 addr)
 	return addr;
 }
 
-static bool fib4_is_local(const struct sk_buff *skb)
-{
-	const struct rtable *rt = skb_rtable(skb);
-
-	return rt && (rt->rt_flags & RTCF_LOCAL);
-}
-
 #define DSCP_BITS     0xfc
 
 void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs,
@@ -95,8 +88,10 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	else
 		oif = NULL;
 
-	if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib4_is_local(pkt->skb)) {
-		nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX);
+	if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
+	    nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
+		nft_fib_store_result(dest, priv->result, pkt,
+				     nft_in(pkt)->ifindex);
 		return;
 	}
 
@@ -131,7 +126,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	switch (res.type) {
 	case RTN_UNICAST:
 		break;
-	case RTN_LOCAL:	/* should not appear here, see fib4_is_local() above */
+	case RTN_LOCAL: /* Should not see RTN_LOCAL here */
 		return;
 	default:
 		break;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 86cca610f4c2..68d77b1f1495 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -642,6 +642,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
 {
 	struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
 
+	if (!skb)
+		return 0;
 	pfh->wcheck = csum_partial((char *)&pfh->icmph,
 		sizeof(struct icmphdr), pfh->wcheck);
 	pfh->icmph.checksum = csum_fold(pfh->wcheck);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4a044964da66..0efb4c7f6704 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -770,6 +770,12 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 				ret = -EAGAIN;
 				break;
 			}
+			/* if __tcp_splice_read() got nothing while we have
+			 * an skb in receive queue, we do not want to loop.
+			 * This might happen with URG data.
+			 */
+			if (!skb_queue_empty(&sk->sk_receive_queue))
+				break;
 			sk_wait_data(sk, &timeo, NULL);
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index f51919535ca7..dd2560c83a85 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -205,6 +205,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	 * scaled. So correct it appropriately.
 	 */
 	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
+	tp->max_window = tp->snd_wnd;
 
 	/* Activate the retrans timer so that SYNACK can be retransmitted.
 	 * The request socket is not added to the ehash
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6c790754ae3e..41dcbd568cbe 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5078,7 +5078,7 @@ static void tcp_check_space(struct sock *sk)
 	if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
 		sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
 		/* pairs with tcp_poll() */
-		smp_mb__after_atomic();
+		smp_mb();
 		if (sk->sk_socket &&
 		    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
 			tcp_new_space(sk);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1d5331a1b1dc..8ce50dc3ab8c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2518,9 +2518,11 @@ u32 __tcp_select_window(struct sock *sk)
 	int full_space = min_t(int, tp->window_clamp, allowed_space);
 	int window;
 
-	if (mss > full_space)
+	if (unlikely(mss > full_space)) {
 		mss = full_space;
-
+		if (mss <= 0)
+			return 0;
+	}
 	if (free_space < (full_space >> 1)) {
 		icsk->icsk_ack.quick = 0;
 
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index f6c50af24a64..3d063eb37848 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -117,7 +117,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 	     (fwmark > 0 && skb->mark == fwmark)) &&
 	    (full || tp->snd_cwnd != tcp_probe.lastcwnd)) {
 
-		spin_lock(&tcp_probe.lock);
+		spin_lock_bh(&tcp_probe.lock);
 		/* If log fills, just silently drop */
 		if (tcp_probe_avail() > 1) {
 			struct tcp_log *p = tcp_probe.log + tcp_probe.head;
@@ -157,7 +157,7 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 			tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
 		}
 		tcp_probe.lastcwnd = tp->snd_cwnd;
-		spin_unlock(&tcp_probe.lock);
+		spin_unlock_bh(&tcp_probe.lock);
 
 		wake_up(&tcp_probe.wait);
 	}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1307a7c2e544..8aab7d78d25b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1501,7 +1501,7 @@ try_again:
 	return err;
 
 csum_copy_err:
-	if (!__sk_queue_drop_skb(sk, skb, flags)) {
+	if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) {
 		UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
 		UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 	}
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c1e124bc8e1e..a7bcc0ab5e99 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3386,9 +3386,15 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			}
 
 			if (idev) {
-				if (idev->if_flags & IF_READY)
-					/* device is already configured. */
+				if (idev->if_flags & IF_READY) {
+					/* device is already configured -
+					 * but resend MLD reports, we might
+					 * have roamed and need to update
+					 * multicast snooping switches
+					 */
+					ipv6_mc_up(idev);
 					break;
+				}
 				idev->if_flags |= IF_READY;
 			}
 
@@ -4009,6 +4015,12 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id)
 
 	if (bump_id)
 		rt_genid_bump_ipv6(dev_net(dev));
+
+	/* Make sure that a new temporary address will be created
+	 * before this temporary address becomes deprecated.
+	 */
+	if (ifp->flags & IFA_F_TEMPORARY)
+		addrconf_verify_rtnl();
 }
 
 static void addrconf_dad_run(struct inet6_dev *idev)
@@ -5540,8 +5552,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
 	struct net_device *dev;
 	struct inet6_dev *idev;
 
-	rcu_read_lock();
-	for_each_netdev_rcu(net, dev) {
+	for_each_netdev(net, dev) {
 		idev = __in6_dev_get(dev);
 		if (idev) {
 			int changed = (!idev->cnf.disable_ipv6) ^ (!newf);
@@ -5550,7 +5561,6 @@ static void addrconf_disable_change(struct net *net, __s32 newf)
 				dev_disable_change(idev);
 		}
 	}
-	rcu_read_unlock();
 }
 
 static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf)
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index a3eaafd87100..eec27f87efac 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -167,18 +167,22 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr,
 	if (np->sndflow)
 		fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
 
-	addr_type = ipv6_addr_type(&usin->sin6_addr);
-
-	if (addr_type == IPV6_ADDR_ANY) {
+	if (ipv6_addr_any(&usin->sin6_addr)) {
 		/*
 		 *	connect to self
 		 */
-		usin->sin6_addr.s6_addr[15] = 0x01;
+		if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+					       &usin->sin6_addr);
+		else
+			usin->sin6_addr = in6addr_loopback;
 	}
 
+	addr_type = ipv6_addr_type(&usin->sin6_addr);
+
 	daddr = &usin->sin6_addr;
 
-	if (addr_type == IPV6_ADDR_MAPPED) {
+	if (addr_type & IPV6_ADDR_MAPPED) {
 		struct sockaddr_in sin;
 
 		if (__ipv6_only_sock(sk)) {
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index e4198502fd98..275cac628a95 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -327,7 +327,6 @@ static int ipv6_srh_rcv(struct sk_buff *skb)
 	struct ipv6_sr_hdr *hdr;
 	struct inet6_dev *idev;
 	struct in6_addr *addr;
-	bool cleanup = false;
 	int accept_seg6;
 
 	hdr = (struct ipv6_sr_hdr *)skb_transport_header(skb);
@@ -351,11 +350,7 @@ static int ipv6_srh_rcv(struct sk_buff *skb)
 #endif
 
 looped_back:
-	if (hdr->segments_left > 0) {
-		if (hdr->nexthdr != NEXTHDR_IPV6 && hdr->segments_left == 1 &&
-		    sr_has_cleanup(hdr))
-			cleanup = true;
-	} else {
+	if (hdr->segments_left == 0) {
 		if (hdr->nexthdr == NEXTHDR_IPV6) {
 			int offset = (hdr->hdrlen + 1) << 3;
 
@@ -418,21 +413,6 @@ looped_back:
 
 	ipv6_hdr(skb)->daddr = *addr;
 
-	if (cleanup) {
-		int srhlen = (hdr->hdrlen + 1) << 3;
-		int nh = hdr->nexthdr;
-
-		skb_pull_rcsum(skb, sizeof(struct ipv6hdr) + srhlen);
-		memmove(skb_network_header(skb) + srhlen,
-			skb_network_header(skb),
-			(unsigned char *)hdr - skb_network_header(skb));
-		skb->network_header += srhlen;
-		ipv6_hdr(skb)->nexthdr = nh;
-		ipv6_hdr(skb)->payload_len = htons(skb->len -
-						   sizeof(struct ipv6hdr));
-		skb_push_rcsum(skb, sizeof(struct ipv6hdr));
-	}
-
 	skb_dst_drop(skb);
 
 	ip6_route_input(skb);
@@ -453,13 +433,8 @@ looped_back:
 		}
 		ipv6_hdr(skb)->hop_limit--;
 
-		/* be sure that srh is still present before reinjecting */
-		if (!cleanup) {
-			skb_pull(skb, sizeof(struct ipv6hdr));
-			goto looped_back;
-		}
-		skb_set_transport_header(skb, sizeof(struct ipv6hdr));
-		IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
+		skb_pull(skb, sizeof(struct ipv6hdr));
+		goto looped_back;
 	}
 
 	dst_input(skb);
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index a7bc54ab46e2..13b5e85fe0d5 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -238,6 +238,7 @@ static const struct lwtunnel_encap_ops ila_encap_ops = {
 	.fill_encap = ila_fill_encap_info,
 	.get_encap_size = ila_encap_nlsize,
 	.cmp_encap = ila_encap_cmp,
+	.owner = THIS_MODULE,
 };
 
 int ila_lwt_init(void)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 7396e75e161b..75c308239243 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -176,7 +176,7 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused
 	/* Restore final destination back after routing done */
 	fl6.daddr = sk->sk_v6_daddr;
 
-	res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt),
+	res = ip6_xmit(sk, skb, &fl6, sk->sk_mark, rcu_dereference(np->opt),
 		       np->tclass);
 	rcu_read_unlock();
 	return res;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 75b6108234dd..630b73be5999 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -367,35 +367,37 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
 
 
 static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
-		u8 type, u8 code, int offset, __be32 info)
+		       u8 type, u8 code, int offset, __be32 info)
 {
-	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data;
-	__be16 *p = (__be16 *)(skb->data + offset);
-	int grehlen = offset + 4;
+	const struct gre_base_hdr *greh;
+	const struct ipv6hdr *ipv6h;
+	int grehlen = sizeof(*greh);
 	struct ip6_tnl *t;
+	int key_off = 0;
 	__be16 flags;
+	__be32 key;
 
-	flags = p[0];
-	if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
-		if (flags&(GRE_VERSION|GRE_ROUTING))
-			return;
-		if (flags&GRE_KEY) {
-			grehlen += 4;
-			if (flags&GRE_CSUM)
-				grehlen += 4;
-		}
+	if (!pskb_may_pull(skb, offset + grehlen))
+		return;
+	greh = (const struct gre_base_hdr *)(skb->data + offset);
+	flags = greh->flags;
+	if (flags & (GRE_VERSION | GRE_ROUTING))
+		return;
+	if (flags & GRE_CSUM)
+		grehlen += 4;
+	if (flags & GRE_KEY) {
+		key_off = grehlen + offset;
+		grehlen += 4;
 	}
 
-	/* If only 8 bytes returned, keyed message will be dropped here */
-	if (!pskb_may_pull(skb, grehlen))
+	if (!pskb_may_pull(skb, offset + grehlen))
 		return;
 	ipv6h = (const struct ipv6hdr *)skb->data;
-	p = (__be16 *)(skb->data + offset);
+	greh = (const struct gre_base_hdr *)(skb->data + offset);
+	key = key_off ? *(__be32 *)(skb->data + key_off) : 0;
 
 	t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
-				flags & GRE_KEY ?
-				*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
-				p[1]);
+				 key, greh->protocol);
 	if (!t)
 		return;
 
@@ -582,6 +584,9 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev)
 		return -1;
 
 	offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+	/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+	ipv6h = ipv6_hdr(skb);
+
 	if (offset > 0) {
 		struct ipv6_tlv_tnl_enc_lim *tel;
 		tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 38122d04fadc..7cebee58e55b 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -172,7 +172,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
  * which are using proper atomic operations or spinlocks.
  */
 int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
-	     struct ipv6_txoptions *opt, int tclass)
+	     __u32 mark, struct ipv6_txoptions *opt, int tclass)
 {
 	struct net *net = sock_net(sk);
 	const struct ipv6_pinfo *np = inet6_sk(sk);
@@ -240,7 +240,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = sk->sk_priority;
-	skb->mark = sk->sk_mark;
+	skb->mark = mark;
 
 	mtu = dst_mtu(dst);
 	if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) {
@@ -1021,6 +1021,11 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
 		}
 	}
 #endif
+	if (ipv6_addr_v4mapped(&fl6->saddr) &&
+	    !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) {
+		err = -EAFNOSUPPORT;
+		goto out_err_release;
+	}
 
 	return 0;
 
@@ -1344,7 +1349,7 @@ emsgsize:
 	 */
 	if (transhdrlen && sk->sk_protocol == IPPROTO_UDP &&
 	    headersize == sizeof(struct ipv6hdr) &&
-	    length < mtu - headersize &&
+	    length <= mtu - headersize &&
 	    !(flags & MSG_MORE) &&
 	    rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
 		csummode = CHECKSUM_PARTIAL;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 753d6d0860fb..75fac933c209 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -400,18 +400,19 @@ ip6_tnl_dev_uninit(struct net_device *dev)
 
 __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 {
-	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw;
-	__u8 nexthdr = ipv6h->nexthdr;
-	__u16 off = sizeof(*ipv6h);
+	const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw;
+	unsigned int nhoff = raw - skb->data;
+	unsigned int off = nhoff + sizeof(*ipv6h);
+	u8 next, nexthdr = ipv6h->nexthdr;
 
 	while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
-		__u16 optlen = 0;
 		struct ipv6_opt_hdr *hdr;
-		if (raw + off + sizeof(*hdr) > skb->data &&
-		    !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr)))
+		u16 optlen;
+
+		if (!pskb_may_pull(skb, off + sizeof(*hdr)))
 			break;
 
-		hdr = (struct ipv6_opt_hdr *) (raw + off);
+		hdr = (struct ipv6_opt_hdr *)(skb->data + off);
 		if (nexthdr == NEXTHDR_FRAGMENT) {
 			struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
 			if (frag_hdr->frag_off)
@@ -422,20 +423,29 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 		} else {
 			optlen = ipv6_optlen(hdr);
 		}
+		/* cache hdr->nexthdr, since pskb_may_pull() might
+		 * invalidate hdr
+		 */
+		next = hdr->nexthdr;
 		if (nexthdr == NEXTHDR_DEST) {
-			__u16 i = off + 2;
+			u16 i = 2;
+
+			/* Remember : hdr is no longer valid at this point. */
+			if (!pskb_may_pull(skb, off + optlen))
+				break;
+
 			while (1) {
 				struct ipv6_tlv_tnl_enc_lim *tel;
 
 				/* No more room for encapsulation limit */
-				if (i + sizeof (*tel) > off + optlen)
+				if (i + sizeof(*tel) > optlen)
 					break;
 
-				tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i];
+				tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i);
 				/* return index of option if found and valid */
 				if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
 				    tel->length == 1)
-					return i;
+					return i + off - nhoff;
 				/* else jump to next option */
 				if (tel->type)
 					i += tel->length + 2;
@@ -443,7 +453,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 					i++;
 			}
 		}
-		nexthdr = hdr->nexthdr;
+		nexthdr = next;
 		off += optlen;
 	}
 	return 0;
@@ -1303,6 +1313,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		fl6.flowlabel = key->label;
 	} else {
 		offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
+		/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
+		ipv6h = ipv6_hdr(skb);
 		if (offset > 0) {
 			struct ipv6_tlv_tnl_enc_lim *tel;
 
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7139fffd61b6..1bdc703cb966 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -779,6 +779,7 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 				psf->sf_crcount = im->mca_crcount;
 		}
 		in6_dev_put(pmc->idev);
+		kfree(pmc);
 	}
 	spin_unlock_bh(&im->mca_lock);
 }
diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c
index d5263dc364a9..b12e61b7b16c 100644
--- a/net/ipv6/netfilter/ip6t_rpfilter.c
+++ b/net/ipv6/netfilter/ip6t_rpfilter.c
@@ -72,10 +72,10 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb,
 	return ret;
 }
 
-static bool rpfilter_is_local(const struct sk_buff *skb)
+static bool
+rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in)
 {
-	const struct rt6_info *rt = (const void *) skb_dst(skb);
-	return rt && (rt->rt6i_flags & RTF_LOCAL);
+	return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK;
 }
 
 static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
@@ -85,7 +85,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	struct ipv6hdr *iph;
 	bool invert = info->flags & XT_RPFILTER_INVERT;
 
-	if (rpfilter_is_local(skb))
+	if (rpfilter_is_loopback(skb, xt_in(par)))
 		return true ^ invert;
 
 	iph = ipv6_hdr(skb);
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 10090400c72f..eedee5d108d9 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -157,6 +157,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 	fl6.fl6_sport = otcph->dest;
 	fl6.fl6_dport = otcph->source;
 	fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev);
+	fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark);
 	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst->error) {
@@ -180,6 +181,8 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 
 	skb_dst_set(nskb, dst);
 
+	nskb->mark = fl6.flowi6_mark;
+
 	skb_reserve(nskb, hh_len + dst->header_len);
 	ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
 				    ip6_dst_hoplimit(dst));
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index c947aad8bcc6..765facf03d45 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -18,13 +18,6 @@
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>
 
-static bool fib6_is_local(const struct sk_buff *skb)
-{
-	const struct rt6_info *rt = (const void *)skb_dst(skb);
-
-	return rt && (rt->rt6i_flags & RTF_LOCAL);
-}
-
 static int get_ifindex(const struct net_device *dev)
 {
 	return dev ? dev->ifindex : 0;
@@ -164,8 +157,10 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 
 	lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif);
 
-	if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib6_is_local(pkt->skb)) {
-		nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX);
+	if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
+	    nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
+		nft_fib_store_result(dest, priv->result, pkt,
+				     nft_in(pkt)->ifindex);
 		return;
 	}
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4f6b067c8753..7ea85370c11c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2896,6 +2896,11 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RTA_MULTIPATH]) {
 		cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
 		cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
+
+		err = lwtunnel_valid_encap_type_attr(cfg->fc_mp,
+						     cfg->fc_mp_len);
+		if (err < 0)
+			goto errout;
 	}
 
 	if (tb[RTA_PREF]) {
@@ -2909,9 +2914,14 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RTA_ENCAP])
 		cfg->fc_encap = tb[RTA_ENCAP];
 
-	if (tb[RTA_ENCAP_TYPE])
+	if (tb[RTA_ENCAP_TYPE]) {
 		cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
 
+		err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+		if (err < 0)
+			goto errout;
+	}
+
 	if (tb[RTA_EXPIRES]) {
 		unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ);
 
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index b172d85c650a..a855eb325b03 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -176,6 +176,8 @@ static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info)
 
 	val = nla_data(info->attrs[SEG6_ATTR_DST]);
 	t_new = kmemdup(val, sizeof(*val), GFP_KERNEL);
+	if (!t_new)
+		return -ENOMEM;
 
 	mutex_lock(&sdata->lock);
 
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 03a064803626..6ef3dfb6e811 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -174,7 +174,7 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
 	 * hash function (RadioGatun) with up to 1216 bits
 	 */
 
-	/* saddr(16) + first_seg(1) + cleanup(1) + keyid(4) + seglist(16n) */
+	/* saddr(16) + first_seg(1) + flags(1) + keyid(4) + seglist(16n) */
 	plen = 16 + 1 + 1 + 4 + (hdr->first_segment + 1) * 16;
 
 	/* this limit allows for 14 segments */
@@ -186,7 +186,7 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
 	 *
 	 * 1. Source IPv6 address (128 bits)
 	 * 2. first_segment value (8 bits)
-	 * 3. cleanup flag (8 bits: highest bit is cleanup value, others are 0)
+	 * 3. Flags (8 bits)
 	 * 4. HMAC Key ID (32 bits)
 	 * 5. All segments in the segments list (n * 128 bits)
 	 */
@@ -202,8 +202,8 @@ int seg6_hmac_compute(struct seg6_hmac_info *hinfo, struct ipv6_sr_hdr *hdr,
 	/* first_segment value */
 	*off++ = hdr->first_segment;
 
-	/* cleanup flag */
-	*off++ = !!(sr_has_cleanup(hdr)) << 7;
+	/* flags */
+	*off++ = hdr->flags;
 
 	/* HMAC Key ID */
 	memcpy(off, &hmackeyid, 4);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 1d60cb132835..c46f8cbf5ab5 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -422,6 +422,7 @@ static const struct lwtunnel_encap_ops seg6_iptun_ops = {
 	.fill_encap = seg6_fill_encap_info,
 	.get_encap_size = seg6_encap_nlsize,
 	.cmp_encap = seg6_encap_cmp,
+	.owner = THIS_MODULE,
 };
 
 int __init seg6_iptunnel_init(void)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index fad992ad4bc8..99853c6e33a8 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1380,6 +1380,7 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
 	if (err) {
 		free_percpu(dev->tstats);
+		dev->tstats = NULL;
 		return err;
 	}
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 73bc8fc68acd..4c60c6f71cd3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -148,8 +148,13 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	 *	connect() to INADDR_ANY means loopback (BSD'ism).
 	 */
 
-	if (ipv6_addr_any(&usin->sin6_addr))
-		usin->sin6_addr.s6_addr[15] = 0x1;
+	if (ipv6_addr_any(&usin->sin6_addr)) {
+		if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
+			ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+					       &usin->sin6_addr);
+		else
+			usin->sin6_addr = in6addr_loopback;
+	}
 
 	addr_type = ipv6_addr_type(&usin->sin6_addr);
 
@@ -188,7 +193,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	 *	TCP over IPv4
 	 */
 
-	if (addr_type == IPV6_ADDR_MAPPED) {
+	if (addr_type & IPV6_ADDR_MAPPED) {
 		u32 exthdrlen = icsk->icsk_ext_hdr_len;
 		struct sockaddr_in sin;
 
@@ -469,7 +474,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 		opt = ireq->ipv6_opt;
 		if (!opt)
 			opt = rcu_dereference(np->opt);
-		err = ip6_xmit(sk, skb, fl6, opt, np->tclass);
+		err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -840,7 +845,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
-		ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass);
+		ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass);
 		TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 		if (rst)
 			TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
@@ -991,6 +996,16 @@ drop:
 	return 0; /* don't send reset */
 }
 
+static void tcp_v6_restore_cb(struct sk_buff *skb)
+{
+	/* We need to move header back to the beginning if xfrm6_policy_check()
+	 * and tcp_v6_fill_cb() are going to be called again.
+	 * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
+	 */
+	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
+		sizeof(struct inet6_skb_parm));
+}
+
 static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 					 struct request_sock *req,
 					 struct dst_entry *dst,
@@ -1182,8 +1197,10 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 						      sk_gfp_mask(sk, GFP_ATOMIC));
 			consume_skb(ireq->pktopts);
 			ireq->pktopts = NULL;
-			if (newnp->pktoptions)
+			if (newnp->pktoptions) {
+				tcp_v6_restore_cb(newnp->pktoptions);
 				skb_set_owner_r(newnp->pktoptions, newsk);
+			}
 		}
 	}
 
@@ -1198,16 +1215,6 @@ out:
 	return NULL;
 }
 
-static void tcp_v6_restore_cb(struct sk_buff *skb)
-{
-	/* We need to move header back to the beginning if xfrm6_policy_check()
-	 * and tcp_v6_fill_cb() are going to be called again.
-	 * ip6_datagram_recv_specific_ctl() also expects IP6CB to be there.
-	 */
-	memmove(IP6CB(skb), &TCP_SKB_CB(skb)->header.h6,
-		sizeof(struct inet6_skb_parm));
-}
-
 /* The socket must have it's spinlock held when we get
  * here, unless it is a TCP_LISTEN socket.
  *
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4d5c4eee4b3f..221825a9407a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -441,7 +441,7 @@ try_again:
 	return err;
 
 csum_copy_err:
-	if (!__sk_queue_drop_skb(sk, skb, flags)) {
+	if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) {
 		if (is_udp4) {
 			UDP_INC_STATS(sock_net(sk),
 				      UDP_MIB_CSUMERRORS, is_udplite);
@@ -1033,6 +1033,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			if (addr_len < SIN6_LEN_RFC2133)
 				return -EINVAL;
 			daddr = &sin6->sin6_addr;
+			if (ipv6_addr_any(daddr) &&
+			    ipv6_addr_v4mapped(&np->saddr))
+				ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
+						       daddr);
 			break;
 		case AF_INET:
 			goto do_udp_sendmsg;
diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c
index acbe61c7e683..160dc89335e2 100644
--- a/net/irda/irqueue.c
+++ b/net/irda/irqueue.c
@@ -383,9 +383,6 @@ EXPORT_SYMBOL(hashbin_new);
  *    for deallocating this structure if it's complex. If not the user can
  *    just supply kfree, which should take care of the job.
  */
-#ifdef CONFIG_LOCKDEP
-static int hashbin_lock_depth = 0;
-#endif
 int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 {
 	irda_queue_t* queue;
@@ -396,22 +393,27 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 	IRDA_ASSERT(hashbin->magic == HB_MAGIC, return -1;);
 
 	/* Synchronize */
-	if ( hashbin->hb_type & HB_LOCK ) {
-		spin_lock_irqsave_nested(&hashbin->hb_spinlock, flags,
-					 hashbin_lock_depth++);
-	}
+	if (hashbin->hb_type & HB_LOCK)
+		spin_lock_irqsave(&hashbin->hb_spinlock, flags);
 
 	/*
 	 *  Free the entries in the hashbin, TODO: use hashbin_clear when
 	 *  it has been shown to work
 	 */
 	for (i = 0; i < HASHBIN_SIZE; i ++ ) {
-		queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]);
-		while (queue ) {
-			if (free_func)
-				(*free_func)(queue);
-			queue = dequeue_first(
-				(irda_queue_t**) &hashbin->hb_queue[i]);
+		while (1) {
+			queue = dequeue_first((irda_queue_t**) &hashbin->hb_queue[i]);
+
+			if (!queue)
+				break;
+
+			if (free_func) {
+				if (hashbin->hb_type & HB_LOCK)
+					spin_unlock_irqrestore(&hashbin->hb_spinlock, flags);
+				free_func(queue);
+				if (hashbin->hb_type & HB_LOCK)
+					spin_lock_irqsave(&hashbin->hb_spinlock, flags);
+			}
 		}
 	}
 
@@ -420,12 +422,8 @@ int hashbin_delete( hashbin_t* hashbin, FREE_FUNC free_func)
 	hashbin->magic = ~HB_MAGIC;
 
 	/* Release lock */
-	if ( hashbin->hb_type & HB_LOCK) {
+	if (hashbin->hb_type & HB_LOCK)
 		spin_unlock_irqrestore(&hashbin->hb_spinlock, flags);
-#ifdef CONFIG_LOCKDEP
-		hashbin_lock_depth--;
-#endif
-	}
 
 	/*
 	 *  Free the hashbin structure
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 7e08a4d3d77d..a646f3481240 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -929,23 +929,25 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 			goto out_error;
 	}
 
-	/* New message, alloc head skb */
-	head = alloc_skb(0, sk->sk_allocation);
-	while (!head) {
-		kcm_push(kcm);
-		err = sk_stream_wait_memory(sk, &timeo);
-		if (err)
-			goto out_error;
-
+	if (msg_data_left(msg)) {
+		/* New message, alloc head skb */
 		head = alloc_skb(0, sk->sk_allocation);
-	}
+		while (!head) {
+			kcm_push(kcm);
+			err = sk_stream_wait_memory(sk, &timeo);
+			if (err)
+				goto out_error;
 
-	skb = head;
+			head = alloc_skb(0, sk->sk_allocation);
+		}
 
-	/* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling
-	 * csum_and_copy_from_iter from skb_do_copy_data_nocache.
-	 */
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb = head;
+
+		/* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling
+		 * csum_and_copy_from_iter from skb_do_copy_data_nocache.
+		 */
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
 
 start:
 	while (msg_data_left(msg)) {
@@ -1018,10 +1020,12 @@ wait_for_memory:
 	if (eor) {
 		bool not_busy = skb_queue_empty(&sk->sk_write_queue);
 
-		/* Message complete, queue it on send buffer */
-		__skb_queue_tail(&sk->sk_write_queue, head);
-		kcm->seq_skb = NULL;
-		KCM_STATS_INCR(kcm->stats.tx_msgs);
+		if (head) {
+			/* Message complete, queue it on send buffer */
+			__skb_queue_tail(&sk->sk_write_queue, head);
+			kcm->seq_skb = NULL;
+			KCM_STATS_INCR(kcm->stats.tx_msgs);
+		}
 
 		if (msg->msg_flags & MSG_BATCH) {
 			kcm->tx_wait_more = true;
@@ -1040,8 +1044,10 @@ wait_for_memory:
 	} else {
 		/* Message not complete, save state */
 partial_message:
-		kcm->seq_skb = head;
-		kcm_tx_msg(head)->last_skb = skb;
+		if (head) {
+			kcm->seq_skb = head;
+			kcm_tx_msg(head)->last_skb = skb;
+		}
 	}
 
 	KCM_STATS_ADD(kcm->stats.tx_bytes, copied);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 8f560f7140a0..aebf281d09ee 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -263,6 +263,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb,
 int l2tp_nl_register_ops(enum l2tp_pwtype pw_type,
 			 const struct l2tp_nl_cmd_ops *ops);
 void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 
 /* Session reference counts. Incremented when code obtains a reference
  * to a session.
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 3d73278b86ca..28c21546d5b6 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -11,6 +11,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <asm/ioctls.h>
 #include <linux/icmp.h>
 #include <linux/module.h>
 #include <linux/skbuff.h>
@@ -553,6 +554,30 @@ out:
 	return err ? err : copied;
 }
 
+int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+{
+	struct sk_buff *skb;
+	int amount;
+
+	switch (cmd) {
+	case SIOCOUTQ:
+		amount = sk_wmem_alloc_get(sk);
+		break;
+	case SIOCINQ:
+		spin_lock_bh(&sk->sk_receive_queue.lock);
+		skb = skb_peek(&sk->sk_receive_queue);
+		amount = skb ? skb->len : 0;
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
+		break;
+
+	default:
+		return -ENOIOCTLCMD;
+	}
+
+	return put_user(amount, (int __user *)arg);
+}
+EXPORT_SYMBOL(l2tp_ioctl);
+
 static struct proto l2tp_ip_prot = {
 	.name		   = "L2TP/IP",
 	.owner		   = THIS_MODULE,
@@ -561,7 +586,7 @@ static struct proto l2tp_ip_prot = {
 	.bind		   = l2tp_ip_bind,
 	.connect	   = l2tp_ip_connect,
 	.disconnect	   = l2tp_ip_disconnect,
-	.ioctl		   = udp_ioctl,
+	.ioctl		   = l2tp_ioctl,
 	.destroy	   = l2tp_ip_destroy_sock,
 	.setsockopt	   = ip_setsockopt,
 	.getsockopt	   = ip_getsockopt,
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 331ccf5a7bad..f47c45250f86 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -722,7 +722,7 @@ static struct proto l2tp_ip6_prot = {
 	.bind		   = l2tp_ip6_bind,
 	.connect	   = l2tp_ip6_connect,
 	.disconnect	   = l2tp_ip6_disconnect,
-	.ioctl		   = udp_ioctl,
+	.ioctl		   = l2tp_ioctl,
 	.destroy	   = l2tp_ip6_destroy_sock,
 	.setsockopt	   = ipv6_setsockopt,
 	.getsockopt	   = ipv6_getsockopt,
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 3e821daf9dd4..8bc5a1bd2d45 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -821,7 +821,10 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb)
 		 * another trick required to cope with how the PROCOM state
 		 * machine works. -acme
 		 */
+		skb_orphan(skb);
+		sock_hold(sk);
 		skb->sk = sk;
+		skb->destructor = sock_efree;
 	}
 	if (!sock_owned_by_user(sk))
 		llc_conn_rcv(sk, skb);
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c
index d0e1e804ebd7..5404d0d195cc 100644
--- a/net/llc/llc_sap.c
+++ b/net/llc/llc_sap.c
@@ -290,7 +290,10 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb,
 
 	ev->type   = LLC_SAP_EV_TYPE_PDU;
 	ev->reason = 0;
+	skb_orphan(skb);
+	sock_hold(sk);
 	skb->sk = sk;
+	skb->destructor = sock_efree;
 	llc_sap_state_process(sap, skb);
 }
 
diff --git a/net/mac80211/fils_aead.c b/net/mac80211/fils_aead.c
index ecfdd97758a3..5c3af5eb4052 100644
--- a/net/mac80211/fils_aead.c
+++ b/net/mac80211/fils_aead.c
@@ -124,7 +124,7 @@ static int aes_siv_encrypt(const u8 *key, size_t key_len,
 
 	/* CTR */
 
-	tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, 0);
+	tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm2)) {
 		kfree(tmp);
 		return PTR_ERR(tfm2);
@@ -183,7 +183,7 @@ static int aes_siv_decrypt(const u8 *key, size_t key_len,
 
 	/* CTR */
 
-	tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, 0);
+	tfm2 = crypto_alloc_skcipher("ctr(aes)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(tfm2))
 		return PTR_ERR(tfm2);
 	/* K2 for CTR */
@@ -272,7 +272,7 @@ int fils_encrypt_assoc_req(struct sk_buff *skb,
 	crypt_len = skb->data + skb->len - encr;
 	skb_put(skb, AES_BLOCK_SIZE);
 	return aes_siv_encrypt(assoc_data->fils_kek, assoc_data->fils_kek_len,
-			       encr, crypt_len, 1, addr, len, encr);
+			       encr, crypt_len, 5, addr, len, encr);
 }
 
 int fils_decrypt_assoc_resp(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 42120d965263..50e1b7f78bd4 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -339,7 +339,7 @@ int mesh_add_vendor_ies(struct ieee80211_sub_if_data *sdata,
 	/* fast-forward to vendor IEs */
 	offset = ieee80211_ie_split_vendor(ifmsh->ie, ifmsh->ie_len, 0);
 
-	if (offset) {
+	if (offset < ifmsh->ie_len) {
 		len = ifmsh->ie_len - offset;
 		data = ifmsh->ie + offset;
 		if (skb_tailroom(skb) < len)
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index 9e2641d45587..206698bc93f4 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -40,8 +40,6 @@ void rate_control_rate_init(struct sta_info *sta)
 
 	ieee80211_sta_set_rx_nss(sta);
 
-	ieee80211_recalc_min_chandef(sta->sdata);
-
 	if (!ref)
 		return;
 
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 15fe97644ffe..5b77377e5a15 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -98,18 +98,19 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 }
 EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
 
-static u32 mpls_multipath_hash(struct mpls_route *rt,
-			       struct sk_buff *skb, bool bos)
+static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb)
 {
 	struct mpls_entry_decoded dec;
+	unsigned int mpls_hdr_len = 0;
 	struct mpls_shim_hdr *hdr;
 	bool eli_seen = false;
 	int label_index;
 	u32 hash = 0;
 
-	for (label_index = 0; label_index < MAX_MP_SELECT_LABELS && !bos;
+	for (label_index = 0; label_index < MAX_MP_SELECT_LABELS;
 	     label_index++) {
-		if (!pskb_may_pull(skb, sizeof(*hdr) * label_index))
+		mpls_hdr_len += sizeof(*hdr);
+		if (!pskb_may_pull(skb, mpls_hdr_len))
 			break;
 
 		/* Read and decode the current label */
@@ -134,37 +135,38 @@ static u32 mpls_multipath_hash(struct mpls_route *rt,
 			eli_seen = true;
 		}
 
-		bos = dec.bos;
-		if (bos && pskb_may_pull(skb, sizeof(*hdr) * label_index +
-					 sizeof(struct iphdr))) {
+		if (!dec.bos)
+			continue;
+
+		/* found bottom label; does skb have room for a header? */
+		if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) {
 			const struct iphdr *v4hdr;
 
-			v4hdr = (const struct iphdr *)(mpls_hdr(skb) +
-						       label_index);
+			v4hdr = (const struct iphdr *)(hdr + 1);
 			if (v4hdr->version == 4) {
 				hash = jhash_3words(ntohl(v4hdr->saddr),
 						    ntohl(v4hdr->daddr),
 						    v4hdr->protocol, hash);
 			} else if (v4hdr->version == 6 &&
-				pskb_may_pull(skb, sizeof(*hdr) * label_index +
-					      sizeof(struct ipv6hdr))) {
+				   pskb_may_pull(skb, mpls_hdr_len +
+						 sizeof(struct ipv6hdr))) {
 				const struct ipv6hdr *v6hdr;
 
-				v6hdr = (const struct ipv6hdr *)(mpls_hdr(skb) +
-								label_index);
-
+				v6hdr = (const struct ipv6hdr *)(hdr + 1);
 				hash = __ipv6_addr_jhash(&v6hdr->saddr, hash);
 				hash = __ipv6_addr_jhash(&v6hdr->daddr, hash);
 				hash = jhash_1word(v6hdr->nexthdr, hash);
 			}
 		}
+
+		break;
 	}
 
 	return hash;
 }
 
 static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
-					     struct sk_buff *skb, bool bos)
+					     struct sk_buff *skb)
 {
 	int alive = ACCESS_ONCE(rt->rt_nhn_alive);
 	u32 hash = 0;
@@ -180,7 +182,7 @@ static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
 	if (alive <= 0)
 		return NULL;
 
-	hash = mpls_multipath_hash(rt, skb, bos);
+	hash = mpls_multipath_hash(rt, skb);
 	nh_index = hash % alive;
 	if (alive == rt->rt_nhn)
 		goto out;
@@ -278,17 +280,11 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 	hdr = mpls_hdr(skb);
 	dec = mpls_entry_decode(hdr);
 
-	/* Pop the label */
-	skb_pull(skb, sizeof(*hdr));
-	skb_reset_network_header(skb);
-
-	skb_orphan(skb);
-
 	rt = mpls_route_input_rcu(net, dec.label);
 	if (!rt)
 		goto drop;
 
-	nh = mpls_select_multipath(rt, skb, dec.bos);
+	nh = mpls_select_multipath(rt, skb);
 	if (!nh)
 		goto drop;
 
@@ -297,6 +293,12 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 	if (!mpls_output_possible(out_dev))
 		goto drop;
 
+	/* Pop the label */
+	skb_pull(skb, sizeof(*hdr));
+	skb_reset_network_header(skb);
+
+	skb_orphan(skb);
+
 	if (skb_warn_if_lro(skb))
 		goto drop;
 
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 2f7ccd934416..1d281c1ff7c1 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -215,6 +215,7 @@ static const struct lwtunnel_encap_ops mpls_iptun_ops = {
 	.fill_encap = mpls_fill_encap_info,
 	.get_encap_size = mpls_encap_nlsize,
 	.cmp_encap = mpls_encap_cmp,
+	.owner = THIS_MODULE,
 };
 
 static int __init mpls_iptunnel_init(void)
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 63729b489c2c..bbc45f8a7b2d 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -494,7 +494,7 @@ config NFT_CT
 	depends on NF_CONNTRACK
 	tristate "Netfilter nf_tables conntrack module"
 	help
-	  This option adds the "meta" expression that you can use to match
+	  This option adds the "ct" expression that you can use to match
 	  connection tracking information such as the flow state.
 
 config NFT_SET_RBTREE
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 3a073cd9fcf4..4e8083c5e01d 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -85,11 +85,11 @@ static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
 static __read_mostly bool nf_conntrack_locks_all;
 
 /* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */
-#define GC_MAX_BUCKETS_DIV	64u
-/* upper bound of scan intervals */
-#define GC_INTERVAL_MAX		(2 * HZ)
-/* maximum conntracks to evict per gc run */
-#define GC_MAX_EVICTS		256u
+#define GC_MAX_BUCKETS_DIV	128u
+/* upper bound of full table scan */
+#define GC_MAX_SCAN_JIFFIES	(16u * HZ)
+/* desired ratio of entries found to be expired */
+#define GC_EVICT_RATIO	50u
 
 static struct conntrack_gc_work conntrack_gc_work;
 
@@ -938,6 +938,7 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
 
 static void gc_worker(struct work_struct *work)
 {
+	unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u);
 	unsigned int i, goal, buckets = 0, expired_count = 0;
 	struct conntrack_gc_work *gc_work;
 	unsigned int ratio, scanned = 0;
@@ -979,8 +980,7 @@ static void gc_worker(struct work_struct *work)
 		 */
 		rcu_read_unlock();
 		cond_resched_rcu_qs();
-	} while (++buckets < goal &&
-		 expired_count < GC_MAX_EVICTS);
+	} while (++buckets < goal);
 
 	if (gc_work->exiting)
 		return;
@@ -997,27 +997,25 @@ static void gc_worker(struct work_struct *work)
 	 * 1. Minimize time until we notice a stale entry
 	 * 2. Maximize scan intervals to not waste cycles
 	 *
-	 * Normally, expired_count will be 0, this increases the next_run time
-	 * to priorize 2) above.
+	 * Normally, expire ratio will be close to 0.
 	 *
-	 * As soon as a timed-out entry is found, move towards 1) and increase
-	 * the scan frequency.
-	 * In case we have lots of evictions next scan is done immediately.
+	 * As soon as a sizeable fraction of the entries have expired
+	 * increase scan frequency.
 	 */
 	ratio = scanned ? expired_count * 100 / scanned : 0;
-	if (ratio >= 90 || expired_count == GC_MAX_EVICTS) {
-		gc_work->next_gc_run = 0;
-		next_run = 0;
-	} else if (expired_count) {
-		gc_work->next_gc_run /= 2U;
-		next_run = msecs_to_jiffies(1);
+	if (ratio > GC_EVICT_RATIO) {
+		gc_work->next_gc_run = min_interval;
 	} else {
-		if (gc_work->next_gc_run < GC_INTERVAL_MAX)
-			gc_work->next_gc_run += msecs_to_jiffies(1);
+		unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV;
 
-		next_run = gc_work->next_gc_run;
+		BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0);
+
+		gc_work->next_gc_run += min_interval;
+		if (gc_work->next_gc_run > max)
+			gc_work->next_gc_run = max;
 	}
 
+	next_run = gc_work->next_gc_run;
 	gc_work->last_bucket = i;
 	queue_delayed_work(system_long_wq, &gc_work->dwork, next_run);
 }
@@ -1025,7 +1023,7 @@ static void gc_worker(struct work_struct *work)
 static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
 {
 	INIT_DELAYED_WORK(&gc_work->dwork, gc_worker);
-	gc_work->next_gc_run = GC_INTERVAL_MAX;
+	gc_work->next_gc_run = HZ;
 	gc_work->exiting = false;
 }
 
@@ -1917,7 +1915,7 @@ int nf_conntrack_init_start(void)
 	nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
 
 	conntrack_gc_work_init(&conntrack_gc_work);
-	queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, GC_INTERVAL_MAX);
+	queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, HZ);
 
 	return 0;
 
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 3dca90dc24ad..ffb9e8ada899 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -13,7 +13,6 @@
 /* Internal logging interface, which relies on the real
    LOG target modules */
 
-#define NF_LOG_PREFIXLEN		128
 #define NFLOGGER_NAME_LEN		64
 
 static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0db5f9782265..1b913760f205 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -928,7 +928,8 @@ static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table,
 }
 
 static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
-	[NFTA_CHAIN_TABLE]	= { .type = NLA_STRING },
+	[NFTA_CHAIN_TABLE]	= { .type = NLA_STRING,
+				    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_CHAIN_HANDLE]	= { .type = NLA_U64 },
 	[NFTA_CHAIN_NAME]	= { .type = NLA_STRING,
 				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
@@ -1854,7 +1855,8 @@ static struct nft_rule *nf_tables_rule_lookup(const struct nft_chain *chain,
 }
 
 static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = {
-	[NFTA_RULE_TABLE]	= { .type = NLA_STRING },
+	[NFTA_RULE_TABLE]	= { .type = NLA_STRING,
+				    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_RULE_CHAIN]	= { .type = NLA_STRING,
 				    .len = NFT_CHAIN_MAXNAMELEN - 1 },
 	[NFTA_RULE_HANDLE]	= { .type = NLA_U64 },
@@ -2443,7 +2445,8 @@ nft_select_set_ops(const struct nlattr * const nla[],
 }
 
 static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
-	[NFTA_SET_TABLE]		= { .type = NLA_STRING },
+	[NFTA_SET_TABLE]		= { .type = NLA_STRING,
+					    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_SET_NAME]			= { .type = NLA_STRING,
 					    .len = NFT_SET_MAXNAMELEN - 1 },
 	[NFTA_SET_FLAGS]		= { .type = NLA_U32 },
@@ -3084,9 +3087,9 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk,
 }
 
 static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx,
-					const struct nft_set *set,
+					struct nft_set *set,
 					const struct nft_set_iter *iter,
-					const struct nft_set_elem *elem)
+					struct nft_set_elem *elem)
 {
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	enum nft_registers dreg;
@@ -3192,8 +3195,10 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = {
 };
 
 static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = {
-	[NFTA_SET_ELEM_LIST_TABLE]	= { .type = NLA_STRING },
-	[NFTA_SET_ELEM_LIST_SET]	= { .type = NLA_STRING },
+	[NFTA_SET_ELEM_LIST_TABLE]	= { .type = NLA_STRING,
+					    .len = NFT_TABLE_MAXNAMELEN - 1 },
+	[NFTA_SET_ELEM_LIST_SET]	= { .type = NLA_STRING,
+					    .len = NFT_SET_MAXNAMELEN - 1 },
 	[NFTA_SET_ELEM_LIST_ELEMENTS]	= { .type = NLA_NESTED },
 	[NFTA_SET_ELEM_LIST_SET_ID]	= { .type = NLA_U32 },
 };
@@ -3303,9 +3308,9 @@ struct nft_set_dump_args {
 };
 
 static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
-				  const struct nft_set *set,
+				  struct nft_set *set,
 				  const struct nft_set_iter *iter,
-				  const struct nft_set_elem *elem)
+				  struct nft_set_elem *elem)
 {
 	struct nft_set_dump_args *args;
 
@@ -3317,7 +3322,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
 	u8 genmask = nft_genmask_cur(net);
-	const struct nft_set *set;
+	struct nft_set *set;
 	struct nft_set_dump_args args;
 	struct nft_ctx ctx;
 	struct nlattr *nla[NFTA_SET_ELEM_LIST_MAX + 1];
@@ -3740,10 +3745,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		goto err5;
 	}
 
+	if (set->size &&
+	    !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact)) {
+		err = -ENFILE;
+		goto err6;
+	}
+
 	nft_trans_elem(trans) = elem;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 	return 0;
 
+err6:
+	set->ops->remove(set, &elem);
 err5:
 	kfree(trans);
 err4:
@@ -3790,15 +3803,9 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk,
 		return -EBUSY;
 
 	nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) {
-		if (set->size &&
-		    !atomic_add_unless(&set->nelems, 1, set->size + set->ndeact))
-			return -ENFILE;
-
 		err = nft_add_set_elem(&ctx, set, attr, nlh->nlmsg_flags);
-		if (err < 0) {
-			atomic_dec(&set->nelems);
+		if (err < 0)
 			break;
-		}
 	}
 	return err;
 }
@@ -3883,9 +3890,9 @@ err1:
 }
 
 static int nft_flush_set(const struct nft_ctx *ctx,
-			 const struct nft_set *set,
+			 struct nft_set *set,
 			 const struct nft_set_iter *iter,
-			 const struct nft_set_elem *elem)
+			 struct nft_set_elem *elem)
 {
 	struct nft_trans *trans;
 	int err;
@@ -3899,9 +3906,10 @@ static int nft_flush_set(const struct nft_ctx *ctx,
 		err = -ENOENT;
 		goto err1;
 	}
+	set->ndeact++;
 
-	nft_trans_elem_set(trans) = (struct nft_set *)set;
-	nft_trans_elem(trans) = *((struct nft_set_elem *)elem);
+	nft_trans_elem_set(trans) = set;
+	nft_trans_elem(trans) = *elem;
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 
 	return 0;
@@ -4032,8 +4040,10 @@ struct nft_object *nf_tables_obj_lookup(const struct nft_table *table,
 EXPORT_SYMBOL_GPL(nf_tables_obj_lookup);
 
 static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
-	[NFTA_OBJ_TABLE]	= { .type = NLA_STRING },
-	[NFTA_OBJ_NAME]		= { .type = NLA_STRING },
+	[NFTA_OBJ_TABLE]	= { .type = NLA_STRING,
+				    .len = NFT_TABLE_MAXNAMELEN - 1 },
+	[NFTA_OBJ_NAME]		= { .type = NLA_STRING,
+				    .len = NFT_OBJ_MAXNAMELEN - 1 },
 	[NFTA_OBJ_TYPE]		= { .type = NLA_U32 },
 	[NFTA_OBJ_DATA]		= { .type = NLA_NESTED },
 };
@@ -4262,10 +4272,11 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
 				if (idx > s_idx)
 					memset(&cb->args[1], 0,
 					       sizeof(cb->args) - sizeof(cb->args[0]));
-				if (filter->table[0] &&
+				if (filter && filter->table[0] &&
 				    strcmp(filter->table, table->name))
 					goto cont;
-				if (filter->type != NFT_OBJECT_UNSPEC &&
+				if (filter &&
+				    filter->type != NFT_OBJECT_UNSPEC &&
 				    obj->type->type != filter->type)
 					goto cont;
 
@@ -5009,9 +5020,9 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 				 const struct nft_chain *chain);
 
 static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx,
-					const struct nft_set *set,
+					struct nft_set *set,
 					const struct nft_set_iter *iter,
-					const struct nft_set_elem *elem)
+					struct nft_set_elem *elem)
 {
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
 	const struct nft_data *data;
@@ -5035,7 +5046,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
 {
 	const struct nft_rule *rule;
 	const struct nft_expr *expr, *last;
-	const struct nft_set *set;
+	struct nft_set *set;
 	struct nft_set_binding *binding;
 	struct nft_set_iter iter;
 
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 7de2f46734a4..049ad2d9ee66 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -98,7 +98,8 @@ out:
 }
 
 static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = {
-	[NFTA_DYNSET_SET_NAME]	= { .type = NLA_STRING },
+	[NFTA_DYNSET_SET_NAME]	= { .type = NLA_STRING,
+				    .len = NFT_SET_MAXNAMELEN - 1 },
 	[NFTA_DYNSET_SET_ID]	= { .type = NLA_U32 },
 	[NFTA_DYNSET_OP]	= { .type = NLA_U32 },
 	[NFTA_DYNSET_SREG_KEY]	= { .type = NLA_U32 },
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 6271e40a3dd6..6f6e64423643 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -39,7 +39,8 @@ static void nft_log_eval(const struct nft_expr *expr,
 
 static const struct nla_policy nft_log_policy[NFTA_LOG_MAX + 1] = {
 	[NFTA_LOG_GROUP]	= { .type = NLA_U16 },
-	[NFTA_LOG_PREFIX]	= { .type = NLA_STRING },
+	[NFTA_LOG_PREFIX]	= { .type = NLA_STRING,
+				    .len = NF_LOG_PREFIXLEN - 1 },
 	[NFTA_LOG_SNAPLEN]	= { .type = NLA_U32 },
 	[NFTA_LOG_QTHRESHOLD]	= { .type = NLA_U16 },
 	[NFTA_LOG_LEVEL]	= { .type = NLA_U32 },
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index d4f97fa7e21d..e21aea7e5ec8 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -49,7 +49,8 @@ static void nft_lookup_eval(const struct nft_expr *expr,
 }
 
 static const struct nla_policy nft_lookup_policy[NFTA_LOOKUP_MAX + 1] = {
-	[NFTA_LOOKUP_SET]	= { .type = NLA_STRING },
+	[NFTA_LOOKUP_SET]	= { .type = NLA_STRING,
+				    .len = NFT_SET_MAXNAMELEN - 1 },
 	[NFTA_LOOKUP_SET_ID]	= { .type = NLA_U32 },
 	[NFTA_LOOKUP_SREG]	= { .type = NLA_U32 },
 	[NFTA_LOOKUP_DREG]	= { .type = NLA_U32 },
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 415a65ba2b85..1ae8c49ca4a1 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -193,10 +193,12 @@ nft_objref_select_ops(const struct nft_ctx *ctx,
 }
 
 static const struct nla_policy nft_objref_policy[NFTA_OBJREF_MAX + 1] = {
-	[NFTA_OBJREF_IMM_NAME]	= { .type = NLA_STRING },
+	[NFTA_OBJREF_IMM_NAME]	= { .type = NLA_STRING,
+				    .len = NFT_OBJ_MAXNAMELEN - 1 },
 	[NFTA_OBJREF_IMM_TYPE]	= { .type = NLA_U32 },
 	[NFTA_OBJREF_SET_SREG]	= { .type = NLA_U32 },
-	[NFTA_OBJREF_SET_NAME]	= { .type = NLA_STRING },
+	[NFTA_OBJREF_SET_NAME]	= { .type = NLA_STRING,
+				    .len = NFT_SET_MAXNAMELEN - 1 },
 	[NFTA_OBJREF_SET_ID]	= { .type = NLA_U32 },
 };
 
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 1e20e2bbb6d9..e36069fb76ae 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -212,7 +212,7 @@ static void nft_hash_remove(const struct nft_set *set,
 	rhashtable_remove_fast(&priv->ht, &he->node, nft_hash_params);
 }
 
-static void nft_hash_walk(const struct nft_ctx *ctx, const struct nft_set *set,
+static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set,
 			  struct nft_set_iter *iter)
 {
 	struct nft_hash *priv = nft_set_priv(set);
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 08376e50f6cd..f06f55ee516d 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -221,7 +221,7 @@ static void *nft_rbtree_deactivate(const struct net *net,
 }
 
 static void nft_rbtree_walk(const struct nft_ctx *ctx,
-			    const struct nft_set *set,
+			    struct nft_set *set,
 			    struct nft_set_iter *iter)
 {
 	const struct nft_rbtree *priv = nft_set_priv(set);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index b9e1a13b4ba3..70f5b6a4683c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1497,6 +1497,8 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po)
 	f->arr[f->num_members] = sk;
 	smp_wmb();
 	f->num_members++;
+	if (f->num_members == 1)
+		dev_add_pack(&f->prot_hook);
 	spin_unlock(&f->lock);
 }
 
@@ -1513,6 +1515,8 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
 	BUG_ON(i >= f->num_members);
 	f->arr[i] = f->arr[f->num_members - 1];
 	f->num_members--;
+	if (f->num_members == 0)
+		__dev_remove_pack(&f->prot_hook);
 	spin_unlock(&f->lock);
 }
 
@@ -1619,6 +1623,7 @@ static void fanout_release_data(struct packet_fanout *f)
 
 static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 {
+	struct packet_rollover *rollover = NULL;
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f, *match;
 	u8 type = type_flags & 0xff;
@@ -1641,23 +1646,28 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		return -EINVAL;
 	}
 
+	mutex_lock(&fanout_mutex);
+
+	err = -EINVAL;
 	if (!po->running)
-		return -EINVAL;
+		goto out;
 
+	err = -EALREADY;
 	if (po->fanout)
-		return -EALREADY;
+		goto out;
 
 	if (type == PACKET_FANOUT_ROLLOVER ||
 	    (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) {
-		po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL);
-		if (!po->rollover)
-			return -ENOMEM;
-		atomic_long_set(&po->rollover->num, 0);
-		atomic_long_set(&po->rollover->num_huge, 0);
-		atomic_long_set(&po->rollover->num_failed, 0);
+		err = -ENOMEM;
+		rollover = kzalloc(sizeof(*rollover), GFP_KERNEL);
+		if (!rollover)
+			goto out;
+		atomic_long_set(&rollover->num, 0);
+		atomic_long_set(&rollover->num_huge, 0);
+		atomic_long_set(&rollover->num_failed, 0);
+		po->rollover = rollover;
 	}
 
-	mutex_lock(&fanout_mutex);
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
 		if (f->id == id &&
@@ -1687,7 +1697,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		match->prot_hook.func = packet_rcv_fanout;
 		match->prot_hook.af_packet_priv = match;
 		match->prot_hook.id_match = match_fanout_group;
-		dev_add_pack(&match->prot_hook);
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
@@ -1704,36 +1713,40 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		}
 	}
 out:
-	mutex_unlock(&fanout_mutex);
-	if (err) {
-		kfree(po->rollover);
+	if (err && rollover) {
+		kfree(rollover);
 		po->rollover = NULL;
 	}
+	mutex_unlock(&fanout_mutex);
 	return err;
 }
 
-static void fanout_release(struct sock *sk)
+/* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes
+ * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout.
+ * It is the responsibility of the caller to call fanout_release_data() and
+ * free the returned packet_fanout (after synchronize_net())
+ */
+static struct packet_fanout *fanout_release(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f;
 
+	mutex_lock(&fanout_mutex);
 	f = po->fanout;
-	if (!f)
-		return;
+	if (f) {
+		po->fanout = NULL;
 
-	mutex_lock(&fanout_mutex);
-	po->fanout = NULL;
+		if (atomic_dec_and_test(&f->sk_ref))
+			list_del(&f->list);
+		else
+			f = NULL;
 
-	if (atomic_dec_and_test(&f->sk_ref)) {
-		list_del(&f->list);
-		dev_remove_pack(&f->prot_hook);
-		fanout_release_data(f);
-		kfree(f);
+		if (po->rollover)
+			kfree_rcu(po->rollover, rcu);
 	}
 	mutex_unlock(&fanout_mutex);
 
-	if (po->rollover)
-		kfree_rcu(po->rollover, rcu);
+	return f;
 }
 
 static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
@@ -1976,7 +1989,7 @@ static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb,
 		return -EINVAL;
 	*len -= sizeof(vnet_hdr);
 
-	if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le()))
+	if (virtio_net_hdr_from_skb(skb, &vnet_hdr, vio_le(), true))
 		return -EINVAL;
 
 	return memcpy_to_msg(msg, (void *)&vnet_hdr, sizeof(vnet_hdr));
@@ -2237,7 +2250,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (po->has_vnet_hdr) {
 		if (virtio_net_hdr_from_skb(skb, h.raw + macoff -
 					    sizeof(struct virtio_net_hdr),
-					    vio_le())) {
+					    vio_le(), true)) {
 			spin_lock(&sk->sk_receive_queue.lock);
 			goto drop_n_account;
 		}
@@ -2755,7 +2768,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int offset = 0;
 	struct packet_sock *po = pkt_sk(sk);
-	int hlen, tlen;
+	int hlen, tlen, linear;
 	int extra_len = 0;
 
 	/*
@@ -2816,8 +2829,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	err = -ENOBUFS;
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
-	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len,
-			       __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len),
+	linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len);
+	linear = max(linear, min_t(int, len, dev->hard_header_len));
+	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear,
 			       msg->msg_flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out_unlock;
@@ -2906,6 +2920,7 @@ static int packet_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po;
+	struct packet_fanout *f;
 	struct net *net;
 	union tpacket_req_u req_u;
 
@@ -2945,9 +2960,14 @@ static int packet_release(struct socket *sock)
 		packet_set_ring(sk, &req_u, 1, 1);
 	}
 
-	fanout_release(sk);
+	f = fanout_release(sk);
 
 	synchronize_net();
+
+	if (f) {
+		fanout_release_data(f);
+		kfree(f);
+	}
 	/*
 	 *	Now the socket is dead. No more input will appear.
 	 */
@@ -3899,7 +3919,6 @@ static int packet_notifier(struct notifier_block *this,
 				}
 				if (msg == NETDEV_UNREGISTER) {
 					packet_cached_dev_reset(po);
-					fanout_release(sk);
 					po->ifindex = -1;
 					if (po->prot_hook.dev)
 						dev_put(po->prot_hook.dev);
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 970db7a41684..5752789acc13 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -568,9 +568,9 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 			       &mask->icmp.type,
 			       TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,
 			       sizeof(key->icmp.type));
-		fl_set_key_val(tb, &key->icmp.code, TCA_FLOWER_KEY_ICMPV4_CODE,
+		fl_set_key_val(tb, &key->icmp.code, TCA_FLOWER_KEY_ICMPV6_CODE,
 			       &mask->icmp.code,
-			       TCA_FLOWER_KEY_ICMPV4_CODE_MASK,
+			       TCA_FLOWER_KEY_ICMPV6_CODE_MASK,
 			       sizeof(key->icmp.code));
 	}
 
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index f935429bd5ef..b12bc2abea93 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -16,16 +16,11 @@
 #include <net/sch_generic.h>
 #include <net/pkt_cls.h>
 
-struct cls_mall_filter {
+struct cls_mall_head {
 	struct tcf_exts exts;
 	struct tcf_result res;
 	u32 handle;
-	struct rcu_head	rcu;
 	u32 flags;
-};
-
-struct cls_mall_head {
-	struct cls_mall_filter *filter;
 	struct rcu_head	rcu;
 };
 
@@ -33,38 +28,29 @@ static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			 struct tcf_result *res)
 {
 	struct cls_mall_head *head = rcu_dereference_bh(tp->root);
-	struct cls_mall_filter *f = head->filter;
 
-	if (tc_skip_sw(f->flags))
+	if (tc_skip_sw(head->flags))
 		return -1;
 
-	return tcf_exts_exec(skb, &f->exts, res);
+	return tcf_exts_exec(skb, &head->exts, res);
 }
 
 static int mall_init(struct tcf_proto *tp)
 {
-	struct cls_mall_head *head;
-
-	head = kzalloc(sizeof(*head), GFP_KERNEL);
-	if (!head)
-		return -ENOBUFS;
-
-	rcu_assign_pointer(tp->root, head);
-
 	return 0;
 }
 
-static void mall_destroy_filter(struct rcu_head *head)
+static void mall_destroy_rcu(struct rcu_head *rcu)
 {
-	struct cls_mall_filter *f = container_of(head, struct cls_mall_filter, rcu);
+	struct cls_mall_head *head = container_of(rcu, struct cls_mall_head,
+						  rcu);
 
-	tcf_exts_destroy(&f->exts);
-
-	kfree(f);
+	tcf_exts_destroy(&head->exts);
+	kfree(head);
 }
 
 static int mall_replace_hw_filter(struct tcf_proto *tp,
-				  struct cls_mall_filter *f,
+				  struct cls_mall_head *head,
 				  unsigned long cookie)
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
@@ -74,7 +60,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 	offload.type = TC_SETUP_MATCHALL;
 	offload.cls_mall = &mall_offload;
 	offload.cls_mall->command = TC_CLSMATCHALL_REPLACE;
-	offload.cls_mall->exts = &f->exts;
+	offload.cls_mall->exts = &head->exts;
 	offload.cls_mall->cookie = cookie;
 
 	return dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol,
@@ -82,7 +68,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 }
 
 static void mall_destroy_hw_filter(struct tcf_proto *tp,
-				   struct cls_mall_filter *f,
+				   struct cls_mall_head *head,
 				   unsigned long cookie)
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
@@ -103,29 +89,20 @@ static bool mall_destroy(struct tcf_proto *tp, bool force)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
 	struct net_device *dev = tp->q->dev_queue->dev;
-	struct cls_mall_filter *f = head->filter;
 
-	if (!force && f)
-		return false;
+	if (!head)
+		return true;
 
-	if (f) {
-		if (tc_should_offload(dev, tp, f->flags))
-			mall_destroy_hw_filter(tp, f, (unsigned long) f);
+	if (tc_should_offload(dev, tp, head->flags))
+		mall_destroy_hw_filter(tp, head, (unsigned long) head);
 
-		call_rcu(&f->rcu, mall_destroy_filter);
-	}
-	kfree_rcu(head, rcu);
+	call_rcu(&head->rcu, mall_destroy_rcu);
 	return true;
 }
 
 static unsigned long mall_get(struct tcf_proto *tp, u32 handle)
 {
-	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct cls_mall_filter *f = head->filter;
-
-	if (f && f->handle == handle)
-		return (unsigned long) f;
-	return 0;
+	return 0UL;
 }
 
 static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
@@ -134,7 +111,7 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
 };
 
 static int mall_set_parms(struct net *net, struct tcf_proto *tp,
-			  struct cls_mall_filter *f,
+			  struct cls_mall_head *head,
 			  unsigned long base, struct nlattr **tb,
 			  struct nlattr *est, bool ovr)
 {
@@ -147,11 +124,11 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp,
 		return err;
 
 	if (tb[TCA_MATCHALL_CLASSID]) {
-		f->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]);
-		tcf_bind_filter(tp, &f->res, base);
+		head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]);
+		tcf_bind_filter(tp, &head->res, base);
 	}
 
-	tcf_exts_change(tp, &f->exts, &e);
+	tcf_exts_change(tp, &head->exts, &e);
 
 	return 0;
 }
@@ -162,21 +139,17 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 		       unsigned long *arg, bool ovr)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct cls_mall_filter *fold = (struct cls_mall_filter *) *arg;
 	struct net_device *dev = tp->q->dev_queue->dev;
-	struct cls_mall_filter *f;
 	struct nlattr *tb[TCA_MATCHALL_MAX + 1];
+	struct cls_mall_head *new;
 	u32 flags = 0;
 	int err;
 
 	if (!tca[TCA_OPTIONS])
 		return -EINVAL;
 
-	if (head->filter)
-		return -EBUSY;
-
-	if (fold)
-		return -EINVAL;
+	if (head)
+		return -EEXIST;
 
 	err = nla_parse_nested(tb, TCA_MATCHALL_MAX,
 			       tca[TCA_OPTIONS], mall_policy);
@@ -189,23 +162,23 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 	}
 
-	f = kzalloc(sizeof(*f), GFP_KERNEL);
-	if (!f)
+	new = kzalloc(sizeof(*new), GFP_KERNEL);
+	if (!new)
 		return -ENOBUFS;
 
-	tcf_exts_init(&f->exts, TCA_MATCHALL_ACT, 0);
+	tcf_exts_init(&new->exts, TCA_MATCHALL_ACT, 0);
 
 	if (!handle)
 		handle = 1;
-	f->handle = handle;
-	f->flags = flags;
+	new->handle = handle;
+	new->flags = flags;
 
-	err = mall_set_parms(net, tp, f, base, tb, tca[TCA_RATE], ovr);
+	err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], ovr);
 	if (err)
 		goto errout;
 
 	if (tc_should_offload(dev, tp, flags)) {
-		err = mall_replace_hw_filter(tp, f, (unsigned long) f);
+		err = mall_replace_hw_filter(tp, new, (unsigned long) new);
 		if (err) {
 			if (tc_skip_sw(flags))
 				goto errout;
@@ -214,39 +187,29 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 		}
 	}
 
-	*arg = (unsigned long) f;
-	rcu_assign_pointer(head->filter, f);
-
+	*arg = (unsigned long) head;
+	rcu_assign_pointer(tp->root, new);
+	if (head)
+		call_rcu(&head->rcu, mall_destroy_rcu);
 	return 0;
 
 errout:
-	kfree(f);
+	kfree(new);
 	return err;
 }
 
 static int mall_delete(struct tcf_proto *tp, unsigned long arg)
 {
-	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct cls_mall_filter *f = (struct cls_mall_filter *) arg;
-	struct net_device *dev = tp->q->dev_queue->dev;
-
-	if (tc_should_offload(dev, tp, f->flags))
-		mall_destroy_hw_filter(tp, f, (unsigned long) f);
-
-	RCU_INIT_POINTER(head->filter, NULL);
-	tcf_unbind_filter(tp, &f->res);
-	call_rcu(&f->rcu, mall_destroy_filter);
-	return 0;
+	return -EOPNOTSUPP;
 }
 
 static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct cls_mall_filter *f = head->filter;
 
 	if (arg->count < arg->skip)
 		goto skip;
-	if (arg->fn(tp, (unsigned long) f, arg) < 0)
+	if (arg->fn(tp, (unsigned long) head, arg) < 0)
 		arg->stop = 1;
 skip:
 	arg->count++;
@@ -255,28 +218,28 @@ skip:
 static int mall_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 		     struct sk_buff *skb, struct tcmsg *t)
 {
-	struct cls_mall_filter *f = (struct cls_mall_filter *) fh;
+	struct cls_mall_head *head = (struct cls_mall_head *) fh;
 	struct nlattr *nest;
 
-	if (!f)
+	if (!head)
 		return skb->len;
 
-	t->tcm_handle = f->handle;
+	t->tcm_handle = head->handle;
 
 	nest = nla_nest_start(skb, TCA_OPTIONS);
 	if (!nest)
 		goto nla_put_failure;
 
-	if (f->res.classid &&
-	    nla_put_u32(skb, TCA_MATCHALL_CLASSID, f->res.classid))
+	if (head->res.classid &&
+	    nla_put_u32(skb, TCA_MATCHALL_CLASSID, head->res.classid))
 		goto nla_put_failure;
 
-	if (tcf_exts_dump(skb, &f->exts))
+	if (tcf_exts_dump(skb, &head->exts))
 		goto nla_put_failure;
 
 	nla_nest_end(skb, nest);
 
-	if (tcf_exts_dump_stats(skb, &f->exts) < 0)
+	if (tcf_exts_dump_stats(skb, &head->exts) < 0)
 		goto nla_put_failure;
 
 	return skb->len;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 5ed8e79bf102..64dfd35ccdcc 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -222,7 +222,8 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 	SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
 
 	rcu_read_lock();
-	res = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), np->tclass);
+	res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt),
+		       np->tclass);
 	rcu_read_unlock();
 	return res;
 }
diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 7e869d0cca69..4f5a2b580aa5 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -68,7 +68,7 @@ static struct sk_buff *sctp_gso_segment(struct sk_buff *skb,
 		goto out;
 	}
 
-	segs = skb_segment(skb, features | NETIF_F_HW_CSUM);
+	segs = skb_segment(skb, features | NETIF_F_HW_CSUM | NETIF_F_SG);
 	if (IS_ERR(segs))
 		goto out;
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 318c6786d653..1b5d669e3029 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -235,8 +235,12 @@ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk,
 					      sctp_assoc_t id)
 {
 	struct sctp_association *addr_asoc = NULL, *id_asoc = NULL;
-	struct sctp_transport *transport;
+	struct sctp_af *af = sctp_get_af_specific(addr->ss_family);
 	union sctp_addr *laddr = (union sctp_addr *)addr;
+	struct sctp_transport *transport;
+
+	if (!af || sctp_verify_addr(sk, laddr, af->sockaddr_len))
+		return NULL;
 
 	addr_asoc = sctp_endpoint_lookup_assoc(sctp_sk(sk)->ep,
 					       laddr,
@@ -7422,7 +7426,8 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
 		 */
 		release_sock(sk);
 		current_timeo = schedule_timeout(current_timeo);
-		BUG_ON(sk != asoc->base.sk);
+		if (sk != asoc->base.sk)
+			goto do_error;
 		lock_sock(sk);
 
 		*timeo_p = current_timeo;
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index dc6fb79a361f..25d9a9cf7b66 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -260,7 +260,7 @@ static int gssx_dec_option_array(struct xdr_stream *xdr,
 	if (!oa->data)
 		return -ENOMEM;
 
-	creds = kmalloc(sizeof(struct svc_cred), GFP_KERNEL);
+	creds = kzalloc(sizeof(struct svc_cred), GFP_KERNEL);
 	if (!creds) {
 		kfree(oa->data);
 		return -ENOMEM;
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 8147e8d56eb2..f39e3e11f9aa 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1358,7 +1358,7 @@ static int c_show(struct seq_file *m, void *p)
 	ifdebug(CACHE)
 		seq_printf(m, "# expiry=%ld refcnt=%d flags=%lx\n",
 			   convert_to_wallclock(cp->expiry_time),
-			   atomic_read(&cp->ref.refcount), cp->flags);
+			   kref_read(&cp->ref), cp->flags);
 	cache_get(cp);
 	if (cache_check(cd, cp, NULL))
 		/* cache_check does a cache_put on failure */
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 1efbe48e794f..1dc9f3bac099 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -336,6 +336,11 @@ out:
 
 static DEFINE_IDA(rpc_clids);
 
+void rpc_cleanup_clids(void)
+{
+	ida_destroy(&rpc_clids);
+}
+
 static int rpc_alloc_clid(struct rpc_clnt *clnt)
 {
 	int clid;
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index d1c330a7953a..c73de181467a 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -119,6 +119,7 @@ out:
 static void __exit
 cleanup_sunrpc(void)
 {
+	rpc_cleanup_clids();
 	rpcauth_remove_module();
 	cleanup_socket_xprt();
 	svc_cleanup_xprt_sock();
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 9c9db55a0c1e..7bfe1fb42add 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -490,7 +490,7 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
 		svc_xprt_get(xprt);
 
 		dprintk("svc: transport %p dequeued, inuse=%d\n",
-			xprt, atomic_read(&xprt->xpt_ref.refcount));
+			xprt, kref_read(&xprt->xpt_ref));
 	}
 	spin_unlock_bh(&pool->sp_lock);
 out:
@@ -822,7 +822,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 		/* XPT_DATA|XPT_DEFERRED case: */
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
 			rqstp, rqstp->rq_pool->sp_id, xprt,
-			atomic_read(&xprt->xpt_ref.refcount));
+			kref_read(&xprt->xpt_ref));
 		rqstp->rq_deferred = svc_deferred_dequeue(xprt);
 		if (rqstp->rq_deferred)
 			len = svc_deferred_recv(rqstp);
@@ -980,7 +980,7 @@ static void svc_age_temp_xprts(unsigned long closure)
 		 * through, close it. */
 		if (!test_and_set_bit(XPT_OLD, &xprt->xpt_flags))
 			continue;
-		if (atomic_read(&xprt->xpt_ref.refcount) > 1 ||
+		if (kref_read(&xprt->xpt_ref) > 1 ||
 		    test_bit(XPT_BUSY, &xprt->xpt_flags))
 			continue;
 		list_del_init(le);
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index e112da8005b5..bb8db3cb8032 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -126,13 +126,18 @@ EXPORT_SYMBOL_GPL(svc_auth_unregister);
 static struct hlist_head	auth_domain_table[DN_HASHMAX];
 static DEFINE_SPINLOCK(auth_domain_lock);
 
+static void auth_domain_release(struct kref *kref)
+{
+	struct auth_domain *dom = container_of(kref, struct auth_domain, ref);
+
+	hlist_del(&dom->hash);
+	dom->flavour->domain_release(dom);
+	spin_unlock(&auth_domain_lock);
+}
+
 void auth_domain_put(struct auth_domain *dom)
 {
-	if (atomic_dec_and_lock(&dom->ref.refcount, &auth_domain_lock)) {
-		hlist_del(&dom->hash);
-		dom->flavour->domain_release(dom);
-		spin_unlock(&auth_domain_lock);
-	}
+	kref_put_lock(&dom->ref, auth_domain_release, &auth_domain_lock);
 }
 EXPORT_SYMBOL_GPL(auth_domain_put);
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index ca2799af05a6..39652d390a9c 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -1201,9 +1201,9 @@ static void __svc_rdma_free(struct work_struct *work)
 		ib_drain_qp(rdma->sc_qp);
 
 	/* We should only be called from kref_put */
-	if (atomic_read(&xprt->xpt_ref.refcount) != 0)
+	if (kref_read(&xprt->xpt_ref) != 0)
 		pr_err("svcrdma: sc_xprt still in use? (%d)\n",
-		       atomic_read(&xprt->xpt_ref.refcount));
+		       kref_read(&xprt->xpt_ref));
 
 	/*
 	 * Destroy queued, but not processed read completions. Note
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 9d2f4c2b08ab..27753325e06e 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -263,6 +263,11 @@ static void tipc_node_write_lock(struct tipc_node *n)
 	write_lock_bh(&n->lock);
 }
 
+static void tipc_node_write_unlock_fast(struct tipc_node *n)
+{
+	write_unlock_bh(&n->lock);
+}
+
 static void tipc_node_write_unlock(struct tipc_node *n)
 {
 	struct net *net = n->net;
@@ -417,7 +422,7 @@ void tipc_node_subscribe(struct net *net, struct list_head *subscr, u32 addr)
 	}
 	tipc_node_write_lock(n);
 	list_add_tail(subscr, &n->publ_list);
-	tipc_node_write_unlock(n);
+	tipc_node_write_unlock_fast(n);
 	tipc_node_put(n);
 }
 
@@ -435,7 +440,7 @@ void tipc_node_unsubscribe(struct net *net, struct list_head *subscr, u32 addr)
 	}
 	tipc_node_write_lock(n);
 	list_del_init(subscr);
-	tipc_node_write_unlock(n);
+	tipc_node_write_unlock_fast(n);
 	tipc_node_put(n);
 }
 
diff --git a/net/tipc/server.c b/net/tipc/server.c
index 215849ce453d..3cd6402e812c 100644
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@ -86,12 +86,12 @@ struct outqueue_entry {
 static void tipc_recv_work(struct work_struct *work);
 static void tipc_send_work(struct work_struct *work);
 static void tipc_clean_outqueues(struct tipc_conn *con);
-static void tipc_sock_release(struct tipc_conn *con);
 
 static void tipc_conn_kref_release(struct kref *kref)
 {
 	struct tipc_conn *con = container_of(kref, struct tipc_conn, kref);
-	struct sockaddr_tipc *saddr = con->server->saddr;
+	struct tipc_server *s = con->server;
+	struct sockaddr_tipc *saddr = s->saddr;
 	struct socket *sock = con->sock;
 	struct sock *sk;
 
@@ -103,9 +103,13 @@ static void tipc_conn_kref_release(struct kref *kref)
 		}
 		saddr->scope = -TIPC_NODE_SCOPE;
 		kernel_bind(sock, (struct sockaddr *)saddr, sizeof(*saddr));
-		tipc_sock_release(con);
 		sock_release(sock);
 		con->sock = NULL;
+
+		spin_lock_bh(&s->idr_lock);
+		idr_remove(&s->conn_idr, con->conid);
+		s->idr_in_use--;
+		spin_unlock_bh(&s->idr_lock);
 	}
 
 	tipc_clean_outqueues(con);
@@ -128,8 +132,10 @@ static struct tipc_conn *tipc_conn_lookup(struct tipc_server *s, int conid)
 
 	spin_lock_bh(&s->idr_lock);
 	con = idr_find(&s->conn_idr, conid);
-	if (con)
+	if (con && test_bit(CF_CONNECTED, &con->flags))
 		conn_get(con);
+	else
+		con = NULL;
 	spin_unlock_bh(&s->idr_lock);
 	return con;
 }
@@ -186,26 +192,15 @@ static void tipc_unregister_callbacks(struct tipc_conn *con)
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
-static void tipc_sock_release(struct tipc_conn *con)
-{
-	struct tipc_server *s = con->server;
-
-	if (con->conid)
-		s->tipc_conn_release(con->conid, con->usr_data);
-
-	tipc_unregister_callbacks(con);
-}
-
 static void tipc_close_conn(struct tipc_conn *con)
 {
 	struct tipc_server *s = con->server;
 
 	if (test_and_clear_bit(CF_CONNECTED, &con->flags)) {
+		tipc_unregister_callbacks(con);
 
-		spin_lock_bh(&s->idr_lock);
-		idr_remove(&s->conn_idr, con->conid);
-		s->idr_in_use--;
-		spin_unlock_bh(&s->idr_lock);
+		if (con->conid)
+			s->tipc_conn_release(con->conid, con->usr_data);
 
 		/* We shouldn't flush pending works as we may be in the
 		 * thread. In fact the races with pending rx/tx work structs
@@ -458,6 +453,11 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid,
 	if (!con)
 		return -EINVAL;
 
+	if (!test_bit(CF_CONNECTED, &con->flags)) {
+		conn_put(con);
+		return 0;
+	}
+
 	e = tipc_alloc_entry(data, len);
 	if (!e) {
 		conn_put(con);
@@ -471,12 +471,8 @@ int tipc_conn_sendmsg(struct tipc_server *s, int conid,
 	list_add_tail(&e->list, &con->outqueue);
 	spin_unlock_bh(&con->outqueue_lock);
 
-	if (test_bit(CF_CONNECTED, &con->flags)) {
-		if (!queue_work(s->send_wq, &con->swork))
-			conn_put(con);
-	} else {
+	if (!queue_work(s->send_wq, &con->swork))
 		conn_put(con);
-	}
 	return 0;
 }
 
@@ -500,7 +496,7 @@ static void tipc_send_to_sock(struct tipc_conn *con)
 	int ret;
 
 	spin_lock_bh(&con->outqueue_lock);
-	while (1) {
+	while (test_bit(CF_CONNECTED, &con->flags)) {
 		e = list_entry(con->outqueue.next, struct outqueue_entry,
 			       list);
 		if ((struct list_head *) e == &con->outqueue)
@@ -623,14 +619,12 @@ int tipc_server_start(struct tipc_server *s)
 void tipc_server_stop(struct tipc_server *s)
 {
 	struct tipc_conn *con;
-	int total = 0;
 	int id;
 
 	spin_lock_bh(&s->idr_lock);
-	for (id = 0; total < s->idr_in_use; id++) {
+	for (id = 0; s->idr_in_use; id++) {
 		con = idr_find(&s->conn_idr, id);
 		if (con) {
-			total++;
 			spin_unlock_bh(&s->idr_lock);
 			tipc_close_conn(con);
 			spin_lock_bh(&s->idr_lock);
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index 0dd02244e21d..9d94e65d0894 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -54,6 +54,8 @@ struct tipc_subscriber {
 
 static void tipc_subscrp_delete(struct tipc_subscription *sub);
 static void tipc_subscrb_put(struct tipc_subscriber *subscriber);
+static void tipc_subscrp_put(struct tipc_subscription *subscription);
+static void tipc_subscrp_get(struct tipc_subscription *subscription);
 
 /**
  * htohl - convert value to endianness used by destination
@@ -123,6 +125,7 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
 {
 	struct tipc_name_seq seq;
 
+	tipc_subscrp_get(sub);
 	tipc_subscrp_convert_seq(&sub->evt.s.seq, sub->swap, &seq);
 	if (!tipc_subscrp_check_overlap(&seq, found_lower, found_upper))
 		return;
@@ -132,30 +135,23 @@ void tipc_subscrp_report_overlap(struct tipc_subscription *sub, u32 found_lower,
 
 	tipc_subscrp_send_event(sub, found_lower, found_upper, event, port_ref,
 				node);
+	tipc_subscrp_put(sub);
 }
 
 static void tipc_subscrp_timeout(unsigned long data)
 {
 	struct tipc_subscription *sub = (struct tipc_subscription *)data;
-	struct tipc_subscriber *subscriber = sub->subscriber;
 
 	/* Notify subscriber of timeout */
 	tipc_subscrp_send_event(sub, sub->evt.s.seq.lower, sub->evt.s.seq.upper,
 				TIPC_SUBSCR_TIMEOUT, 0, 0);
 
-	spin_lock_bh(&subscriber->lock);
-	tipc_subscrp_delete(sub);
-	spin_unlock_bh(&subscriber->lock);
-
-	tipc_subscrb_put(subscriber);
+	tipc_subscrp_put(sub);
 }
 
 static void tipc_subscrb_kref_release(struct kref *kref)
 {
-	struct tipc_subscriber *subcriber = container_of(kref,
-					    struct tipc_subscriber, kref);
-
-	kfree(subcriber);
+	kfree(container_of(kref,struct tipc_subscriber, kref));
 }
 
 static void tipc_subscrb_put(struct tipc_subscriber *subscriber)
@@ -168,6 +164,59 @@ static void tipc_subscrb_get(struct tipc_subscriber *subscriber)
 	kref_get(&subscriber->kref);
 }
 
+static void tipc_subscrp_kref_release(struct kref *kref)
+{
+	struct tipc_subscription *sub = container_of(kref,
+						     struct tipc_subscription,
+						     kref);
+	struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
+	struct tipc_subscriber *subscriber = sub->subscriber;
+
+	spin_lock_bh(&subscriber->lock);
+	tipc_nametbl_unsubscribe(sub);
+	list_del(&sub->subscrp_list);
+	atomic_dec(&tn->subscription_count);
+	spin_unlock_bh(&subscriber->lock);
+	kfree(sub);
+	tipc_subscrb_put(subscriber);
+}
+
+static void tipc_subscrp_put(struct tipc_subscription *subscription)
+{
+	kref_put(&subscription->kref, tipc_subscrp_kref_release);
+}
+
+static void tipc_subscrp_get(struct tipc_subscription *subscription)
+{
+	kref_get(&subscription->kref);
+}
+
+/* tipc_subscrb_subscrp_delete - delete a specific subscription or all
+ * subscriptions for a given subscriber.
+ */
+static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber,
+					struct tipc_subscr *s)
+{
+	struct list_head *subscription_list = &subscriber->subscrp_list;
+	struct tipc_subscription *sub, *temp;
+
+	spin_lock_bh(&subscriber->lock);
+	list_for_each_entry_safe(sub, temp, subscription_list,  subscrp_list) {
+		if (s && memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr)))
+			continue;
+
+		tipc_subscrp_get(sub);
+		spin_unlock_bh(&subscriber->lock);
+		tipc_subscrp_delete(sub);
+		tipc_subscrp_put(sub);
+		spin_lock_bh(&subscriber->lock);
+
+		if (s)
+			break;
+	}
+	spin_unlock_bh(&subscriber->lock);
+}
+
 static struct tipc_subscriber *tipc_subscrb_create(int conid)
 {
 	struct tipc_subscriber *subscriber;
@@ -177,8 +226,8 @@ static struct tipc_subscriber *tipc_subscrb_create(int conid)
 		pr_warn("Subscriber rejected, no memory\n");
 		return NULL;
 	}
-	kref_init(&subscriber->kref);
 	INIT_LIST_HEAD(&subscriber->subscrp_list);
+	kref_init(&subscriber->kref);
 	subscriber->conid = conid;
 	spin_lock_init(&subscriber->lock);
 
@@ -187,55 +236,22 @@ static struct tipc_subscriber *tipc_subscrb_create(int conid)
 
 static void tipc_subscrb_delete(struct tipc_subscriber *subscriber)
 {
-	struct tipc_subscription *sub, *temp;
-	u32 timeout;
-
-	spin_lock_bh(&subscriber->lock);
-	/* Destroy any existing subscriptions for subscriber */
-	list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list,
-				 subscrp_list) {
-		timeout = htohl(sub->evt.s.timeout, sub->swap);
-		if ((timeout == TIPC_WAIT_FOREVER) || del_timer(&sub->timer)) {
-			tipc_subscrp_delete(sub);
-			tipc_subscrb_put(subscriber);
-		}
-	}
-	spin_unlock_bh(&subscriber->lock);
-
+	tipc_subscrb_subscrp_delete(subscriber, NULL);
 	tipc_subscrb_put(subscriber);
 }
 
 static void tipc_subscrp_delete(struct tipc_subscription *sub)
 {
-	struct tipc_net *tn = net_generic(sub->net, tipc_net_id);
+	u32 timeout = htohl(sub->evt.s.timeout, sub->swap);
 
-	tipc_nametbl_unsubscribe(sub);
-	list_del(&sub->subscrp_list);
-	kfree(sub);
-	atomic_dec(&tn->subscription_count);
+	if (timeout == TIPC_WAIT_FOREVER || del_timer(&sub->timer))
+		tipc_subscrp_put(sub);
 }
 
 static void tipc_subscrp_cancel(struct tipc_subscr *s,
 				struct tipc_subscriber *subscriber)
 {
-	struct tipc_subscription *sub, *temp;
-	u32 timeout;
-
-	spin_lock_bh(&subscriber->lock);
-	/* Find first matching subscription, exit if not found */
-	list_for_each_entry_safe(sub, temp, &subscriber->subscrp_list,
-				 subscrp_list) {
-		if (!memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) {
-			timeout = htohl(sub->evt.s.timeout, sub->swap);
-			if ((timeout == TIPC_WAIT_FOREVER) ||
-			    del_timer(&sub->timer)) {
-				tipc_subscrp_delete(sub);
-				tipc_subscrb_put(subscriber);
-			}
-			break;
-		}
-	}
-	spin_unlock_bh(&subscriber->lock);
+	tipc_subscrb_subscrp_delete(subscriber, s);
 }
 
 static struct tipc_subscription *tipc_subscrp_create(struct net *net,
@@ -272,6 +288,7 @@ static struct tipc_subscription *tipc_subscrp_create(struct net *net,
 	sub->swap = swap;
 	memcpy(&sub->evt.s, s, sizeof(*s));
 	atomic_inc(&tn->subscription_count);
+	kref_init(&sub->kref);
 	return sub;
 }
 
@@ -288,17 +305,16 @@ static void tipc_subscrp_subscribe(struct net *net, struct tipc_subscr *s,
 
 	spin_lock_bh(&subscriber->lock);
 	list_add(&sub->subscrp_list, &subscriber->subscrp_list);
-	tipc_subscrb_get(subscriber);
 	sub->subscriber = subscriber;
 	tipc_nametbl_subscribe(sub);
+	tipc_subscrb_get(subscriber);
 	spin_unlock_bh(&subscriber->lock);
 
+	setup_timer(&sub->timer, tipc_subscrp_timeout, (unsigned long)sub);
 	timeout = htohl(sub->evt.s.timeout, swap);
-	if (timeout == TIPC_WAIT_FOREVER)
-		return;
 
-	setup_timer(&sub->timer, tipc_subscrp_timeout, (unsigned long)sub);
-	mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout));
+	if (timeout != TIPC_WAIT_FOREVER)
+		mod_timer(&sub->timer, jiffies + msecs_to_jiffies(timeout));
 }
 
 /* Handle one termination request for the subscriber */
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index be60103082c9..ffdc214c117a 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -57,6 +57,7 @@ struct tipc_subscriber;
  * @evt: template for events generated by subscription
  */
 struct tipc_subscription {
+	struct kref kref;
 	struct tipc_subscriber *subscriber;
 	struct net *net;
 	struct timer_list timer;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 127656ebe7be..cef79873b09d 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -995,6 +995,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	unsigned int hash;
 	struct unix_address *addr;
 	struct hlist_head *list;
+	struct path path = { NULL, NULL };
 
 	err = -EINVAL;
 	if (sunaddr->sun_family != AF_UNIX)
@@ -1010,9 +1011,20 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		goto out;
 	addr_len = err;
 
+	if (sun_path[0]) {
+		umode_t mode = S_IFSOCK |
+		       (SOCK_INODE(sock)->i_mode & ~current_umask());
+		err = unix_mknod(sun_path, mode, &path);
+		if (err) {
+			if (err == -EEXIST)
+				err = -EADDRINUSE;
+			goto out;
+		}
+	}
+
 	err = mutex_lock_interruptible(&u->bindlock);
 	if (err)
-		goto out;
+		goto out_put;
 
 	err = -EINVAL;
 	if (u->addr)
@@ -1029,16 +1041,6 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	atomic_set(&addr->refcnt, 1);
 
 	if (sun_path[0]) {
-		struct path path;
-		umode_t mode = S_IFSOCK |
-		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = unix_mknod(sun_path, mode, &path);
-		if (err) {
-			if (err == -EEXIST)
-				err = -EADDRINUSE;
-			unix_release_addr(addr);
-			goto out_up;
-		}
 		addr->hash = UNIX_HASH_SIZE;
 		hash = d_backing_inode(path.dentry)->i_ino & (UNIX_HASH_SIZE - 1);
 		spin_lock(&unix_table_lock);
@@ -1065,6 +1067,9 @@ out_unlock:
 	spin_unlock(&unix_table_lock);
 out_up:
 	mutex_unlock(&u->bindlock);
+out_put:
+	if (err)
+		path_put(&path);
 out:
 	return err;
 }
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 5c1b267e22be..aee396b9f190 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5916,6 +5916,7 @@ do {									    \
 			break;
 		}
 		cfg->ht_opmode = ht_opmode;
+		mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1));
 	}
 	FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathToRootTimeout,
 				  1, 65535, mask,
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 396e204888b3..b86ee54da2d1 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -277,6 +277,11 @@ int load_bpf_file(char *path)
 	Elf_Data *data, *data_prog, *symbols = NULL;
 	char *shname, *shname_prog;
 
+	/* reset global variables */
+	kern_version = 0;
+	memset(license, 0, sizeof(license));
+	memset(processed_sec, 0, sizeof(processed_sec));
+
 	if (elf_version(EV_CURRENT) == EV_NONE)
 		return 1;
 
@@ -328,6 +333,8 @@ int load_bpf_file(char *path)
 
 	/* load programs that need map fixup (relocations) */
 	for (i = 1; i < ehdr.e_shnum; i++) {
+		if (processed_sec[i])
+			continue;
 
 		if (get_sec(elf, i, &ehdr, &shname, &shdr, &data))
 			continue;
diff --git a/samples/bpf/tc_l2_redirect_kern.c b/samples/bpf/tc_l2_redirect_kern.c
index 92a44729dbe4..7ef2a12b25b2 100644
--- a/samples/bpf/tc_l2_redirect_kern.c
+++ b/samples/bpf/tc_l2_redirect_kern.c
@@ -4,6 +4,7 @@
  * modify it under the terms of version 2 of the GNU General Public
  * License as published by the Free Software Foundation.
  */
+#define KBUILD_MODNAME "foo"
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/if_ether.h>
 #include <uapi/linux/if_packet.h>
diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c
index 504058631ffc..4bfcaf93fcf3 100644
--- a/samples/bpf/test_cgrp2_attach.c
+++ b/samples/bpf/test_cgrp2_attach.c
@@ -104,7 +104,7 @@ static int attach_filter(int cg_fd, int type, int verdict)
 		return EXIT_FAILURE;
 	}
 
-	ret = bpf_prog_attach(prog_fd, cg_fd, type);
+	ret = bpf_prog_attach(prog_fd, cg_fd, type, 0);
 	if (ret < 0) {
 		printf("Failed to attach prog to cgroup: '%s'\n",
 		       strerror(errno));
diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c
index 6e69be37f87f..3049b1f26267 100644
--- a/samples/bpf/test_cgrp2_attach2.c
+++ b/samples/bpf/test_cgrp2_attach2.c
@@ -79,11 +79,12 @@ int main(int argc, char **argv)
 	if (join_cgroup(FOO))
 		goto err;
 
-	if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS)) {
+	if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 1)) {
 		log_err("Attaching prog to /foo");
 		goto err;
 	}
 
+	printf("Attached DROP prog. This ping in cgroup /foo should fail...\n");
 	assert(system(PING_CMD) != 0);
 
 	/* Create cgroup /foo/bar, get fd, and join it */
@@ -94,24 +95,27 @@ int main(int argc, char **argv)
 	if (join_cgroup(BAR))
 		goto err;
 
+	printf("Attached DROP prog. This ping in cgroup /foo/bar should fail...\n");
 	assert(system(PING_CMD) != 0);
 
-	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS)) {
+	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
 		log_err("Attaching prog to /foo/bar");
 		goto err;
 	}
 
+	printf("Attached PASS prog. This ping in cgroup /foo/bar should pass...\n");
 	assert(system(PING_CMD) == 0);
 
-
 	if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) {
 		log_err("Detaching program from /foo/bar");
 		goto err;
 	}
 
+	printf("Detached PASS from /foo/bar while DROP is attached to /foo.\n"
+	       "This ping in cgroup /foo/bar should fail...\n");
 	assert(system(PING_CMD) != 0);
 
-	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS)) {
+	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
 		log_err("Attaching prog to /foo/bar");
 		goto err;
 	}
@@ -121,8 +125,60 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
+	printf("Attached PASS from /foo/bar and detached DROP from /foo.\n"
+	       "This ping in cgroup /foo/bar should pass...\n");
 	assert(system(PING_CMD) == 0);
 
+	if (bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
+		log_err("Attaching prog to /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) {
+		errno = 0;
+		log_err("Unexpected success attaching prog to /foo/bar");
+		goto err;
+	}
+
+	if (bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS)) {
+		log_err("Detaching program from /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS)) {
+		errno = 0;
+		log_err("Unexpected success in double detach from /foo");
+		goto err;
+	}
+
+	if (bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) {
+		log_err("Attaching non-overridable prog to /foo");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0)) {
+		errno = 0;
+		log_err("Unexpected success attaching non-overridable prog to /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 1)) {
+		errno = 0;
+		log_err("Unexpected success attaching overridable prog to /foo/bar");
+		goto err;
+	}
+
+	if (!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 1)) {
+		errno = 0;
+		log_err("Unexpected success attaching overridable prog to /foo");
+		goto err;
+	}
+
+	if (bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0)) {
+		log_err("Attaching different non-overridable prog to /foo");
+		goto err;
+	}
+
 	goto out;
 
 err:
@@ -132,5 +188,9 @@ out:
 	close(foo);
 	close(bar);
 	cleanup_cgroup_environment();
+	if (!rc)
+		printf("PASS\n");
+	else
+		printf("FAIL\n");
 	return rc;
 }
diff --git a/samples/bpf/test_cgrp2_sock.c b/samples/bpf/test_cgrp2_sock.c
index 0791b949cbe4..c3cfb23e23b5 100644
--- a/samples/bpf/test_cgrp2_sock.c
+++ b/samples/bpf/test_cgrp2_sock.c
@@ -75,7 +75,7 @@ int main(int argc, char **argv)
 		return EXIT_FAILURE;
 	}
 
-	ret = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_INET_SOCK_CREATE);
+	ret = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_INET_SOCK_CREATE, 0);
 	if (ret < 0) {
 		printf("Failed to attach prog to cgroup: '%s'\n",
 		       strerror(errno));
diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c
index 455ef0d06e93..db036077b644 100644
--- a/samples/bpf/test_cgrp2_sock2.c
+++ b/samples/bpf/test_cgrp2_sock2.c
@@ -55,7 +55,7 @@ int main(int argc, char **argv)
 	}
 
 	ret = bpf_prog_attach(prog_fd[filter_id], cg_fd,
-			      BPF_CGROUP_INET_SOCK_CREATE);
+			      BPF_CGROUP_INET_SOCK_CREATE, 0);
 	if (ret < 0) {
 		printf("Failed to attach prog to cgroup: '%s'\n",
 		       strerror(errno));
diff --git a/samples/bpf/tracex5_kern.c b/samples/bpf/tracex5_kern.c
index fd12d7154d42..7e4cf74553ff 100644
--- a/samples/bpf/tracex5_kern.c
+++ b/samples/bpf/tracex5_kern.c
@@ -8,6 +8,7 @@
 #include <linux/version.h>
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/seccomp.h>
+#include <uapi/linux/unistd.h>
 #include "bpf_helpers.h"
 
 #define PROG(F) SEC("kprobe/"__stringify(F)) int bpf_func_##F
diff --git a/samples/bpf/xdp_tx_iptunnel_kern.c b/samples/bpf/xdp_tx_iptunnel_kern.c
index 85c38ecd3a2d..0f4f6e8c8611 100644
--- a/samples/bpf/xdp_tx_iptunnel_kern.c
+++ b/samples/bpf/xdp_tx_iptunnel_kern.c
@@ -8,6 +8,7 @@
  * encapsulating the incoming packet in an IPv4/v6 header
  * and then XDP_TX it out.
  */
+#define KBUILD_MODNAME "foo"
 #include <uapi/linux/bpf.h>
 #include <linux/in.h>
 #include <linux/if_ether.h>
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index eadcd4d359d9..d883116ebaa4 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -164,6 +164,7 @@ cmd_gensymtypes_c =                                                         \
     $(CPP) -D__GENKSYMS__ $(c_flags) $< |                                   \
     $(GENKSYMS) $(if $(1), -T $(2))                                         \
      $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX))             \
+     $(patsubst y,-R,$(CONFIG_MODULE_REL_CRCS))                             \
      $(if $(KBUILD_PRESERVE),-p)                                            \
      -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null))
 
@@ -337,6 +338,7 @@ cmd_gensymtypes_S =                                                         \
     $(CPP) -D__GENKSYMS__ $(c_flags) -xc - |                                \
     $(GENKSYMS) $(if $(1), -T $(2))                                         \
      $(patsubst y,-s _,$(CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX))             \
+     $(patsubst y,-R,$(CONFIG_MODULE_REL_CRCS))                             \
      $(if $(KBUILD_PRESERVE),-p)                                            \
      -r $(firstword $(wildcard $(2:.symtypes=.symref) /dev/null))
 
diff --git a/scripts/analyze_suspend.py b/scripts/analyze_suspend.py
index a0ba48fa2c5e..20cdb2bc1dae 100755
--- a/scripts/analyze_suspend.py
+++ b/scripts/analyze_suspend.py
@@ -24,11 +24,6 @@
 #	   https://01.org/suspendresume
 #	 Source repo
 #	   https://github.com/01org/suspendresume
-#	 Documentation
-#	   Getting Started
-#	     https://01.org/suspendresume/documentation/getting-started
-#	   Command List:
-#	     https://01.org/suspendresume/documentation/command-list
 #
 # Description:
 #	 This tool is designed to assist kernel and OS developers in optimizing
@@ -66,6 +61,8 @@ import platform
 from datetime import datetime
 import struct
 import ConfigParser
+from threading import Thread
+from subprocess import call, Popen, PIPE
 
 # ----------------- CLASSES --------------------
 
@@ -75,11 +72,15 @@ import ConfigParser
 #	 store system values and test parameters
 class SystemValues:
 	ansi = False
-	version = '4.2'
+	version = '4.5'
 	verbose = False
 	addlogs = False
-	mindevlen = 0.001
-	mincglen = 1.0
+	mindevlen = 0.0
+	mincglen = 0.0
+	cgphase = ''
+	cgtest = -1
+	callloopmaxgap = 0.0001
+	callloopmaxlen = 0.005
 	srgap = 0
 	cgexp = False
 	outdir = ''
@@ -92,6 +93,7 @@ class SystemValues:
 		'device_pm_callback_end',
 		'device_pm_callback_start'
 	]
+	logmsg = ''
 	testcommand = ''
 	mempath = '/dev/mem'
 	powerfile = '/sys/power/state'
@@ -117,19 +119,19 @@ class SystemValues:
 	usetracemarkers = True
 	usekprobes = True
 	usedevsrc = False
+	useprocmon = False
 	notestrun = False
+	mixedphaseheight = True
 	devprops = dict()
-	postresumetime = 0
+	predelay = 0
+	postdelay = 0
+	procexecfmt = 'ps - (?P<ps>.*)$'
 	devpropfmt = '# Device Properties: .*'
 	tracertypefmt = '# tracer: (?P<t>.*)'
 	firmwarefmt = '# fwsuspend (?P<s>[0-9]*) fwresume (?P<r>[0-9]*)$'
-	postresumefmt = '# post resume time (?P<t>[0-9]*)$'
 	stampfmt = '# suspend-(?P<m>[0-9]{2})(?P<d>[0-9]{2})(?P<y>[0-9]{2})-'+\
 				'(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\
 				' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$'
-	kprobecolor = 'rgba(204,204,204,0.5)'
-	synccolor = 'rgba(204,204,204,0.5)'
-	debugfuncs = []
 	tracefuncs = {
 		'sys_sync': dict(),
 		'pm_prepare_console': dict(),
@@ -152,44 +154,66 @@ class SystemValues:
 		'CPU_OFF': {
 			'func':'_cpu_down',
 			'args_x86_64': {'cpu':'%di:s32'},
-			'format': 'CPU_OFF[{cpu}]',
-			'mask': 'CPU_.*_DOWN'
+			'format': 'CPU_OFF[{cpu}]'
 		},
 		'CPU_ON': {
 			'func':'_cpu_up',
 			'args_x86_64': {'cpu':'%di:s32'},
-			'format': 'CPU_ON[{cpu}]',
-			'mask': 'CPU_.*_UP'
+			'format': 'CPU_ON[{cpu}]'
 		},
 	}
 	dev_tracefuncs = {
 		# general wait/delay/sleep
-		'msleep': { 'args_x86_64': {'time':'%di:s32'} },
-		'udelay': { 'func':'__const_udelay', 'args_x86_64': {'loops':'%di:s32'} },
-		'acpi_os_stall': dict(),
+		'msleep': { 'args_x86_64': {'time':'%di:s32'}, 'ub': 1 },
+		'schedule_timeout_uninterruptible': { 'args_x86_64': {'timeout':'%di:s32'}, 'ub': 1 },
+		'schedule_timeout': { 'args_x86_64': {'timeout':'%di:s32'}, 'ub': 1 },
+		'udelay': { 'func':'__const_udelay', 'args_x86_64': {'loops':'%di:s32'}, 'ub': 1 },
+		'usleep_range': { 'args_x86_64': {'min':'%di:s32', 'max':'%si:s32'}, 'ub': 1 },
+		'mutex_lock_slowpath': { 'func':'__mutex_lock_slowpath', 'ub': 1 },
+		'acpi_os_stall': {'ub': 1},
 		# ACPI
 		'acpi_resume_power_resources': dict(),
 		'acpi_ps_parse_aml': dict(),
 		# filesystem
 		'ext4_sync_fs': dict(),
+		# 80211
+		'iwlagn_mac_start': dict(),
+		'iwlagn_alloc_bcast_station': dict(),
+		'iwl_trans_pcie_start_hw': dict(),
+		'iwl_trans_pcie_start_fw': dict(),
+		'iwl_run_init_ucode': dict(),
+		'iwl_load_ucode_wait_alive': dict(),
+		'iwl_alive_start': dict(),
+		'iwlagn_mac_stop': dict(),
+		'iwlagn_mac_suspend': dict(),
+		'iwlagn_mac_resume': dict(),
+		'iwlagn_mac_add_interface': dict(),
+		'iwlagn_mac_remove_interface': dict(),
+		'iwlagn_mac_change_interface': dict(),
+		'iwlagn_mac_config': dict(),
+		'iwlagn_configure_filter': dict(),
+		'iwlagn_mac_hw_scan': dict(),
+		'iwlagn_bss_info_changed': dict(),
+		'iwlagn_mac_channel_switch': dict(),
+		'iwlagn_mac_flush': dict(),
 		# ATA
 		'ata_eh_recover': { 'args_x86_64': {'port':'+36(%di):s32'} },
 		# i915
-		'i915_gem_restore_gtt_mappings': dict(),
+		'i915_gem_resume': dict(),
+		'i915_restore_state': dict(),
 		'intel_opregion_setup': dict(),
+		'g4x_pre_enable_dp': dict(),
+		'vlv_pre_enable_dp': dict(),
+		'chv_pre_enable_dp': dict(),
+		'g4x_enable_dp': dict(),
+		'vlv_enable_dp': dict(),
+		'intel_hpd_init': dict(),
+		'intel_opregion_register': dict(),
 		'intel_dp_detect': dict(),
 		'intel_hdmi_detect': dict(),
 		'intel_opregion_init': dict(),
+		'intel_fbdev_set_suspend': dict(),
 	}
-	kprobes_postresume = [
-		{
-			'name': 'ataportrst',
-			'func': 'ata_eh_recover',
-			'args': {'port':'+36(%di):s32'},
-			'format': 'ata{port}_port_reset',
-			'mask': 'ata.*_port_reset'
-		}
-	]
 	kprobes = dict()
 	timeformat = '%.3f'
 	def __init__(self):
@@ -198,6 +222,7 @@ class SystemValues:
 			self.embedded = True
 			self.addlogs = True
 			self.htmlfile = os.environ['LOG_FILE']
+		self.archargs = 'args_'+platform.machine()
 		self.hostname = platform.node()
 		if(self.hostname == ''):
 			self.hostname = 'localhost'
@@ -214,6 +239,13 @@ class SystemValues:
 		if num < 0 or num > 6:
 			return
 		self.timeformat = '%.{0}f'.format(num)
+	def setOutputFolder(self, value):
+		args = dict()
+		n = datetime.now()
+		args['date'] = n.strftime('%y%m%d')
+		args['time'] = n.strftime('%H%M%S')
+		args['hostname'] = self.hostname
+		self.outdir = value.format(**args)
 	def setOutputFile(self):
 		if((self.htmlfile == '') and (self.dmesgfile != '')):
 			m = re.match('(?P<name>.*)_dmesg\.txt$', self.dmesgfile)
@@ -253,10 +285,14 @@ class SystemValues:
 			self.testdir+'/'+self.prefix+'_'+self.suspendmode+'.html'
 		if not os.path.isdir(self.testdir):
 			os.mkdir(self.testdir)
-	def setDeviceFilter(self, devnames):
-		self.devicefilter = string.split(devnames)
+	def setDeviceFilter(self, value):
+		self.devicefilter = []
+		if value:
+			value = value.split(',')
+		for i in value:
+			self.devicefilter.append(i.strip())
 	def rtcWakeAlarmOn(self):
-		os.system('echo 0 > '+self.rtcpath+'/wakealarm')
+		call('echo 0 > '+self.rtcpath+'/wakealarm', shell=True)
 		outD = open(self.rtcpath+'/date', 'r').read().strip()
 		outT = open(self.rtcpath+'/time', 'r').read().strip()
 		mD = re.match('^(?P<y>[0-9]*)-(?P<m>[0-9]*)-(?P<d>[0-9]*)', outD)
@@ -272,12 +308,12 @@ class SystemValues:
 			# if hardware time fails, use the software time
 			nowtime = int(datetime.now().strftime('%s'))
 		alarm = nowtime + self.rtcwaketime
-		os.system('echo %d > %s/wakealarm' % (alarm, self.rtcpath))
+		call('echo %d > %s/wakealarm' % (alarm, self.rtcpath), shell=True)
 	def rtcWakeAlarmOff(self):
-		os.system('echo 0 > %s/wakealarm' % self.rtcpath)
+		call('echo 0 > %s/wakealarm' % self.rtcpath, shell=True)
 	def initdmesg(self):
 		# get the latest time stamp from the dmesg log
-		fp = os.popen('dmesg')
+		fp = Popen('dmesg', stdout=PIPE).stdout
 		ktime = '0'
 		for line in fp:
 			line = line.replace('\r\n', '')
@@ -291,7 +327,7 @@ class SystemValues:
 		self.dmesgstart = float(ktime)
 	def getdmesg(self):
 		# store all new dmesg lines since initdmesg was called
-		fp = os.popen('dmesg')
+		fp = Popen('dmesg', stdout=PIPE).stdout
 		op = open(self.dmesgfile, 'a')
 		for line in fp:
 			line = line.replace('\r\n', '')
@@ -317,25 +353,18 @@ class SystemValues:
 	def getFtraceFilterFunctions(self, current):
 		rootCheck(True)
 		if not current:
-			os.system('cat '+self.tpath+'available_filter_functions')
+			call('cat '+self.tpath+'available_filter_functions', shell=True)
 			return
 		fp = open(self.tpath+'available_filter_functions')
 		master = fp.read().split('\n')
 		fp.close()
-		if len(self.debugfuncs) > 0:
-			for i in self.debugfuncs:
-				if i in master:
-					print i
-				else:
-					print self.colorText(i)
-		else:
-			for i in self.tracefuncs:
-				if 'func' in self.tracefuncs[i]:
-					i = self.tracefuncs[i]['func']
-				if i in master:
-					print i
-				else:
-					print self.colorText(i)
+		for i in self.tracefuncs:
+			if 'func' in self.tracefuncs[i]:
+				i = self.tracefuncs[i]['func']
+			if i in master:
+				print i
+			else:
+				print self.colorText(i)
 	def setFtraceFilterFunctions(self, list):
 		fp = open(self.tpath+'available_filter_functions')
 		master = fp.read().split('\n')
@@ -351,22 +380,15 @@ class SystemValues:
 		fp = open(self.tpath+'set_graph_function', 'w')
 		fp.write(flist)
 		fp.close()
-	def kprobeMatch(self, name, target):
-		if name not in self.kprobes:
-			return False
-		if re.match(self.kprobes[name]['mask'], target):
-			return True
-		return False
 	def basicKprobe(self, name):
-		self.kprobes[name] = {'name': name,'func': name,'args': dict(),'format': name,'mask': name}
+		self.kprobes[name] = {'name': name,'func': name,'args': dict(),'format': name}
 	def defaultKprobe(self, name, kdata):
 		k = kdata
-		for field in ['name', 'format', 'mask', 'func']:
+		for field in ['name', 'format', 'func']:
 			if field not in k:
 				k[field] = name
-		archargs = 'args_'+platform.machine()
-		if archargs in k:
-			k['args'] = k[archargs]
+		if self.archargs in k:
+			k['args'] = k[self.archargs]
 		else:
 			k['args'] = dict()
 			k['format'] = name
@@ -403,49 +425,80 @@ class SystemValues:
 		out = fmt.format(**arglist)
 		out = out.replace(' ', '_').replace('"', '')
 		return out
-	def kprobeText(self, kprobe):
-		name, fmt, func, args = kprobe['name'], kprobe['format'], kprobe['func'], kprobe['args']
+	def kprobeText(self, kname, kprobe):
+		name = fmt = func = kname
+		args = dict()
+		if 'name' in kprobe:
+			name = kprobe['name']
+		if 'format' in kprobe:
+			fmt = kprobe['format']
+		if 'func' in kprobe:
+			func = kprobe['func']
+		if self.archargs in kprobe:
+			args = kprobe[self.archargs]
+		if 'args' in kprobe:
+			args = kprobe['args']
 		if re.findall('{(?P<n>[a-z,A-Z,0-9]*)}', func):
-			doError('Kprobe "%s" has format info in the function name "%s"' % (name, func), False)
+			doError('Kprobe "%s" has format info in the function name "%s"' % (name, func))
 		for arg in re.findall('{(?P<n>[a-z,A-Z,0-9]*)}', fmt):
 			if arg not in args:
-				doError('Kprobe "%s" is missing argument "%s"' % (name, arg), False)
+				doError('Kprobe "%s" is missing argument "%s"' % (name, arg))
 		val = 'p:%s_cal %s' % (name, func)
 		for i in sorted(args):
 			val += ' %s=%s' % (i, args[i])
 		val += '\nr:%s_ret %s $retval\n' % (name, func)
 		return val
-	def addKprobes(self):
+	def addKprobes(self, output=False):
+		if len(sysvals.kprobes) < 1:
+			return
+		if output:
+			print('    kprobe functions in this kernel:')
 		# first test each kprobe
-		print('INITIALIZING KPROBES...')
 		rejects = []
+		# sort kprobes: trace, ub-dev, custom, dev
+		kpl = [[], [], [], []]
 		for name in sorted(self.kprobes):
-			if not self.testKprobe(self.kprobes[name]):
+			res = self.colorText('YES', 32)
+			if not self.testKprobe(name, self.kprobes[name]):
+				res = self.colorText('NO')
 				rejects.append(name)
+			else:
+				if name in self.tracefuncs:
+					kpl[0].append(name)
+				elif name in self.dev_tracefuncs:
+					if 'ub' in self.dev_tracefuncs[name]:
+						kpl[1].append(name)
+					else:
+						kpl[3].append(name)
+				else:
+					kpl[2].append(name)
+			if output:
+				print('         %s: %s' % (name, res))
+		kplist = kpl[0] + kpl[1] + kpl[2] + kpl[3]
 		# remove all failed ones from the list
 		for name in rejects:
-			vprint('Skipping KPROBE: %s' % name)
 			self.kprobes.pop(name)
+		# set the kprobes all at once
 		self.fsetVal('', 'kprobe_events')
 		kprobeevents = ''
-		# set the kprobes all at once
-		for kp in self.kprobes:
-			val = self.kprobeText(self.kprobes[kp])
-			vprint('Adding KPROBE: %s\n%s' % (kp, val.strip()))
-			kprobeevents += self.kprobeText(self.kprobes[kp])
+		for kp in kplist:
+			kprobeevents += self.kprobeText(kp, self.kprobes[kp])
 		self.fsetVal(kprobeevents, 'kprobe_events')
 		# verify that the kprobes were set as ordered
 		check = self.fgetVal('kprobe_events')
-		linesout = len(kprobeevents.split('\n'))
-		linesack = len(check.split('\n'))
-		if linesack < linesout:
-			# if not, try appending the kprobes 1 by 1
-			for kp in self.kprobes:
-				kprobeevents = self.kprobeText(self.kprobes[kp])
-				self.fsetVal(kprobeevents, 'kprobe_events', 'a')
+		linesout = len(kprobeevents.split('\n')) - 1
+		linesack = len(check.split('\n')) - 1
+		if output:
+			res = '%d/%d' % (linesack, linesout)
+			if linesack < linesout:
+				res = self.colorText(res, 31)
+			else:
+				res = self.colorText(res, 32)
+			print('    working kprobe functions enabled: %s' % res)
 		self.fsetVal('1', 'events/kprobes/enable')
-	def testKprobe(self, kprobe):
-		kprobeevents = self.kprobeText(kprobe)
+	def testKprobe(self, kname, kprobe):
+		self.fsetVal('0', 'events/kprobes/enable')
+		kprobeevents = self.kprobeText(kname, kprobe)
 		if not kprobeevents:
 			return False
 		try:
@@ -463,8 +516,9 @@ class SystemValues:
 		if not os.path.exists(file):
 			return False
 		try:
-			fp = open(file, mode)
+			fp = open(file, mode, 0)
 			fp.write(val)
+			fp.flush()
 			fp.close()
 		except:
 			pass
@@ -491,21 +545,17 @@ class SystemValues:
 		for name in self.dev_tracefuncs:
 			self.defaultKprobe(name, self.dev_tracefuncs[name])
 	def isCallgraphFunc(self, name):
-		if len(self.debugfuncs) < 1 and self.suspendmode == 'command':
-			return True
-		if name in self.debugfuncs:
+		if len(self.tracefuncs) < 1 and self.suspendmode == 'command':
 			return True
-		funclist = []
 		for i in self.tracefuncs:
 			if 'func' in self.tracefuncs[i]:
-				funclist.append(self.tracefuncs[i]['func'])
+				f = self.tracefuncs[i]['func']
 			else:
-				funclist.append(i)
-		if name in funclist:
-			return True
+				f = i
+			if name == f:
+				return True
 		return False
 	def initFtrace(self, testing=False):
-		tp = self.tpath
 		print('INITIALIZING FTRACE...')
 		# turn trace off
 		self.fsetVal('0', 'tracing_on')
@@ -518,18 +568,7 @@ class SystemValues:
 		# go no further if this is just a status check
 		if testing:
 			return
-		if self.usekprobes:
-			# add tracefunc kprobes so long as were not using full callgraph
-			if(not self.usecallgraph or len(self.debugfuncs) > 0):
-				for name in self.tracefuncs:
-					self.defaultKprobe(name, self.tracefuncs[name])
-				if self.usedevsrc:
-					for name in self.dev_tracefuncs:
-						self.defaultKprobe(name, self.dev_tracefuncs[name])
-			else:
-				self.usedevsrc = False
-			self.addKprobes()
-		# initialize the callgraph trace, unless this is an x2 run
+		# initialize the callgraph trace
 		if(self.usecallgraph):
 			# set trace type
 			self.fsetVal('function_graph', 'current_tracer')
@@ -545,20 +584,24 @@ class SystemValues:
 			self.fsetVal('context-info', 'trace_options')
 			self.fsetVal('graph-time', 'trace_options')
 			self.fsetVal('0', 'max_graph_depth')
-			if len(self.debugfuncs) > 0:
-				self.setFtraceFilterFunctions(self.debugfuncs)
-			elif self.suspendmode == 'command':
-				self.fsetVal('', 'set_graph_function')
-			else:
-				cf = ['dpm_run_callback']
-				if(self.usetraceeventsonly):
-					cf += ['dpm_prepare', 'dpm_complete']
-				for fn in self.tracefuncs:
-					if 'func' in self.tracefuncs[fn]:
-						cf.append(self.tracefuncs[fn]['func'])
-					else:
-						cf.append(fn)
-				self.setFtraceFilterFunctions(cf)
+			cf = ['dpm_run_callback']
+			if(self.usetraceeventsonly):
+				cf += ['dpm_prepare', 'dpm_complete']
+			for fn in self.tracefuncs:
+				if 'func' in self.tracefuncs[fn]:
+					cf.append(self.tracefuncs[fn]['func'])
+				else:
+					cf.append(fn)
+			self.setFtraceFilterFunctions(cf)
+		# initialize the kprobe trace
+		elif self.usekprobes:
+			for name in self.tracefuncs:
+				self.defaultKprobe(name, self.tracefuncs[name])
+			if self.usedevsrc:
+				for name in self.dev_tracefuncs:
+					self.defaultKprobe(name, self.dev_tracefuncs[name])
+			print('INITIALIZING KPROBES...')
+			self.addKprobes(self.verbose)
 		if(self.usetraceevents):
 			# turn trace events on
 			events = iter(self.traceevents)
@@ -590,10 +633,10 @@ class SystemValues:
 			if(os.path.exists(tp+f) == False):
 				return False
 		return True
-	def colorText(self, str):
+	def colorText(self, str, color=31):
 		if not self.ansi:
 			return str
-		return '\x1B[31;40m'+str+'\x1B[m'
+		return '\x1B[%d;40m%s\x1B[m' % (color, str)
 
 sysvals = SystemValues()
 
@@ -625,8 +668,8 @@ class DevProps:
 		if self.xtraclass:
 			return ' '+self.xtraclass
 		if self.async:
-			return ' async'
-		return ' sync'
+			return ' async_device'
+		return ' sync_device'
 
 # Class: DeviceNode
 # Description:
@@ -646,8 +689,6 @@ class DeviceNode:
 #	 The primary container for suspend/resume test data. There is one for
 #	 each test run. The data is organized into a cronological hierarchy:
 #	 Data.dmesg {
-#		root structure, started as dmesg & ftrace, but now only ftrace
-#		contents: times for suspend start/end, resume start/end, fwdata
 #		phases {
 #			10 sequential, non-overlapping phases of S/R
 #			contents: times for phase start/end, order/color data for html
@@ -658,7 +699,7 @@ class DeviceNode:
 #					contents: start/stop times, pid/cpu/driver info
 #						parents/children, html id for timeline/callgraph
 #						optionally includes an ftrace callgraph
-#						optionally includes intradev trace events
+#						optionally includes dev/ps data
 #				}
 #			}
 #		}
@@ -671,19 +712,24 @@ class Data:
 	end = 0.0   # test end
 	tSuspended = 0.0 # low-level suspend start
 	tResumed = 0.0   # low-level resume start
+	tKernSus = 0.0   # kernel level suspend start
+	tKernRes = 0.0   # kernel level resume end
 	tLow = 0.0       # time spent in low-level suspend (standby/freeze)
 	fwValid = False  # is firmware data available
 	fwSuspend = 0    # time spent in firmware suspend
 	fwResume = 0     # time spent in firmware resume
 	dmesgtext = []   # dmesg text file in memory
+	pstl = 0         # process timeline
 	testnumber = 0
 	idstr = ''
 	html_device_id = 0
 	stamp = 0
 	outfile = ''
-	dev_ubiquitous = ['msleep', 'udelay']
+	devpids = []
+	kerror = False
 	def __init__(self, num):
-		idchar = 'abcdefghijklmnopqrstuvwxyz'
+		idchar = 'abcdefghij'
+		self.pstl = dict()
 		self.testnumber = num
 		self.idstr = idchar[num]
 		self.dmesgtext = []
@@ -714,16 +760,39 @@ class Data:
 		self.devicegroups = []
 		for phase in self.phases:
 			self.devicegroups.append([phase])
-	def getStart(self):
-		return self.dmesg[self.phases[0]]['start']
+		self.errorinfo = {'suspend':[],'resume':[]}
+	def extractErrorInfo(self, dmesg):
+		error = ''
+		tm = 0.0
+		for i in range(len(dmesg)):
+			if 'Call Trace:' in dmesg[i]:
+				m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) .*', dmesg[i])
+				if not m:
+					continue
+				tm = float(m.group('ktime'))
+				if tm < self.start or tm > self.end:
+					continue
+				for j in range(i-10, i+1):
+					error += dmesg[j]
+				continue
+			if error:
+				m = re.match('[ \t]*\[ *[0-9\.]*\]  \[\<[0-9a-fA-F]*\>\] .*', dmesg[i])
+				if m:
+					error += dmesg[i]
+				else:
+					if tm < self.tSuspended:
+						dir = 'suspend'
+					else:
+						dir = 'resume'
+					error = error.replace('<', '&lt').replace('>', '&gt')
+					vprint('kernel error found in %s at %f' % (dir, tm))
+					self.errorinfo[dir].append((tm, error))
+					self.kerror = True
+					error = ''
 	def setStart(self, time):
 		self.start = time
-		self.dmesg[self.phases[0]]['start'] = time
-	def getEnd(self):
-		return self.dmesg[self.phases[-1]]['end']
 	def setEnd(self, time):
 		self.end = time
-		self.dmesg[self.phases[-1]]['end'] = time
 	def isTraceEventOutsideDeviceCalls(self, pid, time):
 		for phase in self.phases:
 			list = self.dmesg[phase]['list']
@@ -733,39 +802,67 @@ class Data:
 					time < d['end']):
 					return False
 		return True
-	def targetDevice(self, phaselist, start, end, pid=-1):
+	def sourcePhase(self, start):
+		for phase in self.phases:
+			pend = self.dmesg[phase]['end']
+			if start <= pend:
+				return phase
+		return 'resume_complete'
+	def sourceDevice(self, phaselist, start, end, pid, type):
 		tgtdev = ''
 		for phase in phaselist:
 			list = self.dmesg[phase]['list']
 			for devname in list:
 				dev = list[devname]
-				if(pid >= 0 and dev['pid'] != pid):
+				# pid must match
+				if dev['pid'] != pid:
 					continue
 				devS = dev['start']
 				devE = dev['end']
-				if(start < devS or start >= devE or end <= devS or end > devE):
-					continue
+				if type == 'device':
+					# device target event is entirely inside the source boundary
+					if(start < devS or start >= devE or end <= devS or end > devE):
+						continue
+				elif type == 'thread':
+					# thread target event will expand the source boundary
+					if start < devS:
+						dev['start'] = start
+					if end > devE:
+						dev['end'] = end
 				tgtdev = dev
 				break
 		return tgtdev
 	def addDeviceFunctionCall(self, displayname, kprobename, proc, pid, start, end, cdata, rdata):
-		machstart = self.dmesg['suspend_machine']['start']
-		machend = self.dmesg['resume_machine']['end']
-		tgtdev = self.targetDevice(self.phases, start, end, pid)
-		if not tgtdev and start >= machstart and end < machend:
-			# device calls in machine phases should be serial
-			tgtdev = self.targetDevice(['suspend_machine', 'resume_machine'], start, end)
+		# try to place the call in a device
+		tgtdev = self.sourceDevice(self.phases, start, end, pid, 'device')
+		# calls with device pids that occur outside device bounds are dropped
+		# TODO: include these somehow
+		if not tgtdev and pid in self.devpids:
+			return False
+		# try to place the call in a thread
 		if not tgtdev:
-			if 'scsi_eh' in proc:
-				self.newActionGlobal(proc, start, end, pid)
-				self.addDeviceFunctionCall(displayname, kprobename, proc, pid, start, end, cdata, rdata)
+			tgtdev = self.sourceDevice(self.phases, start, end, pid, 'thread')
+		# create new thread blocks, expand as new calls are found
+		if not tgtdev:
+			if proc == '<...>':
+				threadname = 'kthread-%d' % (pid)
 			else:
-				vprint('IGNORE: %s[%s](%d) [%f - %f] | %s | %s | %s' % (displayname, kprobename,
-					pid, start, end, cdata, rdata, proc))
+				threadname = '%s-%d' % (proc, pid)
+			tgtphase = self.sourcePhase(start)
+			self.newAction(tgtphase, threadname, pid, '', start, end, '', ' kth', '')
+			return self.addDeviceFunctionCall(displayname, kprobename, proc, pid, start, end, cdata, rdata)
+		# this should not happen
+		if not tgtdev:
+			vprint('[%f - %f] %s-%d %s %s %s' % \
+				(start, end, proc, pid, kprobename, cdata, rdata))
 			return False
-		# detail block fits within tgtdev
+		# place the call data inside the src element of the tgtdev
 		if('src' not in tgtdev):
 			tgtdev['src'] = []
+		dtf = sysvals.dev_tracefuncs
+		ubiquitous = False
+		if kprobename in dtf and 'ub' in dtf[kprobename]:
+			ubiquitous = True
 		title = cdata+' '+rdata
 		mstr = '\(.*\) *(?P<args>.*) *\((?P<caller>.*)\+.* arg1=(?P<ret>.*)'
 		m = re.match(mstr, title)
@@ -777,14 +874,81 @@ class Data:
 				r = ''
 			else:
 				r = 'ret=%s ' % r
-			l = '%0.3fms' % ((end - start) * 1000)
-			if kprobename in self.dev_ubiquitous:
-				title = '%s(%s) <- %s, %s(%s)' % (displayname, a, c, r, l)
-			else:
-				title = '%s(%s) %s(%s)' % (displayname, a, r, l)
-		e = TraceEvent(title, kprobename, start, end - start)
+			if ubiquitous and c in dtf and 'ub' in dtf[c]:
+				return False
+		color = sysvals.kprobeColor(kprobename)
+		e = DevFunction(displayname, a, c, r, start, end, ubiquitous, proc, pid, color)
 		tgtdev['src'].append(e)
 		return True
+	def overflowDevices(self):
+		# get a list of devices that extend beyond the end of this test run
+		devlist = []
+		for phase in self.phases:
+			list = self.dmesg[phase]['list']
+			for devname in list:
+				dev = list[devname]
+				if dev['end'] > self.end:
+					devlist.append(dev)
+		return devlist
+	def mergeOverlapDevices(self, devlist):
+		# merge any devices that overlap devlist
+		for dev in devlist:
+			devname = dev['name']
+			for phase in self.phases:
+				list = self.dmesg[phase]['list']
+				if devname not in list:
+					continue
+				tdev = list[devname]
+				o = min(dev['end'], tdev['end']) - max(dev['start'], tdev['start'])
+				if o <= 0:
+					continue
+				dev['end'] = tdev['end']
+				if 'src' not in dev or 'src' not in tdev:
+					continue
+				dev['src'] += tdev['src']
+				del list[devname]
+	def usurpTouchingThread(self, name, dev):
+		# the caller test has priority of this thread, give it to him
+		for phase in self.phases:
+			list = self.dmesg[phase]['list']
+			if name in list:
+				tdev = list[name]
+				if tdev['start'] - dev['end'] < 0.1:
+					dev['end'] = tdev['end']
+					if 'src' not in dev:
+						dev['src'] = []
+					if 'src' in tdev:
+						dev['src'] += tdev['src']
+					del list[name]
+				break
+	def stitchTouchingThreads(self, testlist):
+		# merge any threads between tests that touch
+		for phase in self.phases:
+			list = self.dmesg[phase]['list']
+			for devname in list:
+				dev = list[devname]
+				if 'htmlclass' not in dev or 'kth' not in dev['htmlclass']:
+					continue
+				for data in testlist:
+					data.usurpTouchingThread(devname, dev)
+	def optimizeDevSrc(self):
+		# merge any src call loops to reduce timeline size
+		for phase in self.phases:
+			list = self.dmesg[phase]['list']
+			for dev in list:
+				if 'src' not in list[dev]:
+					continue
+				src = list[dev]['src']
+				p = 0
+				for e in sorted(src, key=lambda event: event.time):
+					if not p or not e.repeat(p):
+						p = e
+						continue
+					# e is another iteration of p, move it into p
+					p.end = e.end
+					p.length = p.end - p.time
+					p.count += 1
+					src.remove(e)
 	def trimTimeVal(self, t, t0, dT, left):
 		if left:
 			if(t > t0):
@@ -804,6 +968,8 @@ class Data:
 		self.tSuspended = self.trimTimeVal(self.tSuspended, t0, dT, left)
 		self.tResumed = self.trimTimeVal(self.tResumed, t0, dT, left)
 		self.start = self.trimTimeVal(self.start, t0, dT, left)
+		self.tKernSus = self.trimTimeVal(self.tKernSus, t0, dT, left)
+		self.tKernRes = self.trimTimeVal(self.tKernRes, t0, dT, left)
 		self.end = self.trimTimeVal(self.end, t0, dT, left)
 		for phase in self.phases:
 			p = self.dmesg[phase]
@@ -832,36 +998,6 @@ class Data:
 			else:
 				self.trimTime(self.tSuspended, \
 					self.tResumed-self.tSuspended, False)
-	def newPhaseWithSingleAction(self, phasename, devname, start, end, color):
-		for phase in self.phases:
-			self.dmesg[phase]['order'] += 1
-		self.html_device_id += 1
-		devid = '%s%d' % (self.idstr, self.html_device_id)
-		list = dict()
-		list[devname] = \
-			{'start': start, 'end': end, 'pid': 0, 'par': '',
-			'length': (end-start), 'row': 0, 'id': devid, 'drv': '' };
-		self.dmesg[phasename] = \
-			{'list': list, 'start': start, 'end': end,
-			'row': 0, 'color': color, 'order': 0}
-		self.phases = self.sortedPhases()
-	def newPhase(self, phasename, start, end, color, order):
-		if(order < 0):
-			order = len(self.phases)
-		for phase in self.phases[order:]:
-			self.dmesg[phase]['order'] += 1
-		if(order > 0):
-			p = self.phases[order-1]
-			self.dmesg[p]['end'] = start
-		if(order < len(self.phases)):
-			p = self.phases[order]
-			self.dmesg[p]['start'] = end
-		list = dict()
-		self.dmesg[phasename] = \
-			{'list': list, 'start': start, 'end': end,
-			'row': 0, 'color': color, 'order': order}
-		self.phases = self.sortedPhases()
-		self.devicegroups.append([phasename])
 	def setPhase(self, phase, ktime, isbegin):
 		if(isbegin):
 			self.dmesg[phase]['start'] = ktime
@@ -881,7 +1017,7 @@ class Data:
 		for t in sorted(tmp):
 			slist.append(tmp[t])
 		return slist
-	def fixupInitcalls(self, phase, end):
+	def fixupInitcalls(self, phase):
 		# if any calls never returned, clip them at system resume end
 		phaselist = self.dmesg[phase]['list']
 		for devname in phaselist:
@@ -893,37 +1029,23 @@ class Data:
 						break
 				vprint('%s (%s): callback didnt return' % (devname, phase))
 	def deviceFilter(self, devicefilter):
-		# remove all by the relatives of the filter devnames
-		filter = []
-		for phase in self.phases:
-			list = self.dmesg[phase]['list']
-			for name in devicefilter:
-				dev = name
-				while(dev in list):
-					if(dev not in filter):
-						filter.append(dev)
-					dev = list[dev]['par']
-				children = self.deviceDescendants(name, phase)
-				for dev in children:
-					if(dev not in filter):
-						filter.append(dev)
 		for phase in self.phases:
 			list = self.dmesg[phase]['list']
 			rmlist = []
 			for name in list:
-				pid = list[name]['pid']
-				if(name not in filter and pid >= 0):
+				keep = False
+				for filter in devicefilter:
+					if filter in name or \
+						('drv' in list[name] and filter in list[name]['drv']):
+						keep = True
+				if not keep:
 					rmlist.append(name)
 			for name in rmlist:
 				del list[name]
 	def fixupInitcallsThatDidntReturn(self):
 		# if any calls never returned, clip them at system resume end
 		for phase in self.phases:
-			self.fixupInitcalls(phase, self.getEnd())
-	def isInsideTimeline(self, start, end):
-		if(self.start <= start and self.end > start):
-			return True
-		return False
+			self.fixupInitcalls(phase)
 	def phaseOverlap(self, phases):
 		rmgroups = []
 		newgroup = []
@@ -940,30 +1062,35 @@ class Data:
 			self.devicegroups.remove(group)
 		self.devicegroups.append(newgroup)
 	def newActionGlobal(self, name, start, end, pid=-1, color=''):
-		# if event starts before timeline start, expand timeline
-		if(start < self.start):
-			self.setStart(start)
-		# if event ends after timeline end, expand the timeline
-		if(end > self.end):
-			self.setEnd(end)
-		# which phase is this device callback or action "in"
-		targetphase = "none"
+		# which phase is this device callback or action in
+		targetphase = 'none'
 		htmlclass = ''
 		overlap = 0.0
 		phases = []
 		for phase in self.phases:
 			pstart = self.dmesg[phase]['start']
 			pend = self.dmesg[phase]['end']
+			# see if the action overlaps this phase
 			o = max(0, min(end, pend) - max(start, pstart))
 			if o > 0:
 				phases.append(phase)
+			# set the target phase to the one that overlaps most
 			if o > overlap:
 				if overlap > 0 and phase == 'post_resume':
 					continue
 				targetphase = phase
 				overlap = o
+		# if no target phase was found, pin it to the edge
+		if targetphase == 'none':
+			p0start = self.dmesg[self.phases[0]]['start']
+			if start <= p0start:
+				targetphase = self.phases[0]
+			else:
+				targetphase = self.phases[-1]
 		if pid == -2:
 			htmlclass = ' bg'
+		elif pid == -3:
+			htmlclass = ' ps'
 		if len(phases) > 1:
 			htmlclass = ' bg'
 			self.phaseOverlap(phases)
@@ -985,29 +1112,13 @@ class Data:
 			while(name in list):
 				name = '%s[%d]' % (origname, i)
 				i += 1
-		list[name] = {'start': start, 'end': end, 'pid': pid, 'par': parent,
-					  'length': length, 'row': 0, 'id': devid, 'drv': drv }
+		list[name] = {'name': name, 'start': start, 'end': end, 'pid': pid,
+			'par': parent, 'length': length, 'row': 0, 'id': devid, 'drv': drv }
 		if htmlclass:
 			list[name]['htmlclass'] = htmlclass
 		if color:
 			list[name]['color'] = color
 		return name
-	def deviceIDs(self, devlist, phase):
-		idlist = []
-		list = self.dmesg[phase]['list']
-		for devname in list:
-			if devname in devlist:
-				idlist.append(list[devname]['id'])
-		return idlist
-	def deviceParentID(self, devname, phase):
-		pdev = ''
-		pdevid = ''
-		list = self.dmesg[phase]['list']
-		if devname in list:
-			pdev = list[devname]['par']
-		if pdev in list:
-			return list[pdev]['id']
-		return pdev
 	def deviceChildren(self, devname, phase):
 		devlist = []
 		list = self.dmesg[phase]['list']
@@ -1015,21 +1126,15 @@ class Data:
 			if(list[child]['par'] == devname):
 				devlist.append(child)
 		return devlist
-	def deviceDescendants(self, devname, phase):
-		children = self.deviceChildren(devname, phase)
-		family = children
-		for child in children:
-			family += self.deviceDescendants(child, phase)
-		return family
-	def deviceChildrenIDs(self, devname, phase):
-		devlist = self.deviceChildren(devname, phase)
-		return self.deviceIDs(devlist, phase)
 	def printDetails(self):
+		vprint('Timeline Details:')
 		vprint('          test start: %f' % self.start)
+		vprint('kernel suspend start: %f' % self.tKernSus)
 		for phase in self.phases:
 			dc = len(self.dmesg[phase]['list'])
 			vprint('    %16s: %f - %f (%d devices)' % (phase, \
 				self.dmesg[phase]['start'], self.dmesg[phase]['end'], dc))
+		vprint('   kernel resume end: %f' % self.tKernRes)
 		vprint('            test end: %f' % self.end)
 	def deviceChildrenAllPhases(self, devname):
 		devlist = []
@@ -1108,21 +1213,134 @@ class Data:
 				if width != '0.000000' and length >= mindevlen:
 					devlist.append(dev)
 			self.tdevlist[phase] = devlist
-
-# Class: TraceEvent
+	def addHorizontalDivider(self, devname, devend):
+		phase = 'suspend_prepare'
+		self.newAction(phase, devname, -2, '', \
+			self.start, devend, '', ' sec', '')
+		if phase not in self.tdevlist:
+			self.tdevlist[phase] = []
+		self.tdevlist[phase].append(devname)
+		d = DevItem(0, phase, self.dmesg[phase]['list'][devname])
+		return d
+	def addProcessUsageEvent(self, name, times):
+		# get the start and end times for this process
+		maxC = 0
+		tlast = 0
+		start = -1
+		end = -1
+		for t in sorted(times):
+			if tlast == 0:
+				tlast = t
+				continue
+			if name in self.pstl[t]:
+				if start == -1 or tlast < start:
+					start = tlast
+				if end == -1 or t > end:
+					end = t
+			tlast = t
+		if start == -1 or end == -1:
+			return 0
+		# add a new action for this process and get the object
+		out = self.newActionGlobal(name, start, end, -3)
+		if not out:
+			return 0
+		phase, devname = out
+		dev = self.dmesg[phase]['list'][devname]
+		# get the cpu exec data
+		tlast = 0
+		clast = 0
+		cpuexec = dict()
+		for t in sorted(times):
+			if tlast == 0 or t <= start or t > end:
+				tlast = t
+				continue
+			list = self.pstl[t]
+			c = 0
+			if name in list:
+				c = list[name]
+			if c > maxC:
+				maxC = c
+			if c != clast:
+				key = (tlast, t)
+				cpuexec[key] = c
+				tlast = t
+				clast = c
+		dev['cpuexec'] = cpuexec
+		return maxC
+	def createProcessUsageEvents(self):
+		# get an array of process names
+		proclist = []
+		for t in self.pstl:
+			pslist = self.pstl[t]
+			for ps in pslist:
+				if ps not in proclist:
+					proclist.append(ps)
+		# get a list of data points for suspend and resume
+		tsus = []
+		tres = []
+		for t in sorted(self.pstl):
+			if t < self.tSuspended:
+				tsus.append(t)
+			else:
+				tres.append(t)
+		# process the events for suspend and resume
+		if len(proclist) > 0:
+			vprint('Process Execution:')
+		for ps in proclist:
+			c = self.addProcessUsageEvent(ps, tsus)
+			if c > 0:
+				vprint('%25s (sus): %d' % (ps, c))
+			c = self.addProcessUsageEvent(ps, tres)
+			if c > 0:
+				vprint('%25s (res): %d' % (ps, c))
+
+# Class: DevFunction
 # Description:
-#	 A container for trace event data found in the ftrace file
-class TraceEvent:
-	text = ''
-	time = 0.0
-	length = 0.0
-	title = ''
+#	 A container for kprobe function data we want in the dev timeline
+class DevFunction:
 	row = 0
-	def __init__(self, a, n, t, l):
-		self.title = a
-		self.text = n
-		self.time = t
-		self.length = l
+	count = 1
+	def __init__(self, name, args, caller, ret, start, end, u, proc, pid, color):
+		self.name = name
+		self.args = args
+		self.caller = caller
+		self.ret = ret
+		self.time = start
+		self.length = end - start
+		self.end = end
+		self.ubiquitous = u
+		self.proc = proc
+		self.pid = pid
+		self.color = color
+	def title(self):
+		cnt = ''
+		if self.count > 1:
+			cnt = '(x%d)' % self.count
+		l = '%0.3fms' % (self.length * 1000)
+		if self.ubiquitous:
+			title = '%s(%s)%s <- %s, %s(%s)' % \
+				(self.name, self.args, cnt, self.caller, self.ret, l)
+		else:
+			title = '%s(%s) %s%s(%s)' % (self.name, self.args, self.ret, cnt, l)
+		return title.replace('"', '')
+	def text(self):
+		if self.count > 1:
+			text = '%s(x%d)' % (self.name, self.count)
+		else:
+			text = self.name
+		return text
+	def repeat(self, tgt):
+		# is the tgt call just a repeat of this call (e.g. are we in a loop)
+		dt = self.time - tgt.end
+		# only combine calls if -all- attributes are identical
+		if tgt.caller == self.caller and \
+			tgt.name == self.name and tgt.args == self.args and \
+			tgt.proc == self.proc and tgt.pid == self.pid and \
+			tgt.ret == self.ret and dt >= 0 and \
+			dt <= sysvals.callloopmaxgap and \
+			self.length < sysvals.callloopmaxlen:
+			return True
+		return False
 
 # Class: FTraceLine
 # Description:
@@ -1226,7 +1444,6 @@ class FTraceLine:
 			print('%s -- %f (%02d): %s() { (%.3f us)' % (dev, self.time, \
 				self.depth, self.name, self.length*1000000))
 	def startMarker(self):
-		global sysvals
 		# Is this the starting line of a suspend?
 		if not self.fevent:
 			return False
@@ -1506,6 +1723,16 @@ class FTraceCallGraph:
 					l.depth, l.name, l.length*1000000))
 		print(' ')
 
+class DevItem:
+	def __init__(self, test, phase, dev):
+		self.test = test
+		self.phase = phase
+		self.dev = dev
+	def isa(self, cls):
+		if 'htmlclass' in self.dev and cls in self.dev['htmlclass']:
+			return True
+		return False
+
 # Class: Timeline
 # Description:
 #	 A container for a device timeline which calculates
@@ -1517,12 +1744,11 @@ class Timeline:
 	rowH = 30	# device row height
 	bodyH = 0	# body height
 	rows = 0	# total timeline rows
-	phases = []
-	rowmaxlines = dict()
-	rowcount = dict()
+	rowlines = dict()
 	rowheight = dict()
-	def __init__(self, rowheight):
+	def __init__(self, rowheight, scaleheight):
 		self.rowH = rowheight
+		self.scaleH = scaleheight
 		self.html = {
 			'header': '',
 			'timeline': '',
@@ -1537,21 +1763,19 @@ class Timeline:
 	#	 The total number of rows needed to display this phase of the timeline
 	def getDeviceRows(self, rawlist):
 		# clear all rows and set them to undefined
-		lendict = dict()
+		sortdict = dict()
 		for item in rawlist:
 			item.row = -1
-			lendict[item] = item.length
-		list = []
-		for i in sorted(lendict, key=lendict.get, reverse=True):
-			list.append(i)
-		remaining = len(list)
+			sortdict[item] = item.length
+		sortlist = sorted(sortdict, key=sortdict.get, reverse=True)
+		remaining = len(sortlist)
 		rowdata = dict()
 		row = 1
 		# try to pack each row with as many ranges as possible
 		while(remaining > 0):
 			if(row not in rowdata):
 				rowdata[row] = []
-			for i in list:
+			for i in sortlist:
 				if(i.row >= 0):
 					continue
 				s = i.time
@@ -1575,81 +1799,86 @@ class Timeline:
 	#	 Organize the timeline entries into the smallest
 	#	 number of rows possible, with no entry overlapping
 	# Arguments:
-	#	 list: the list of devices/actions for a single phase
-	#	 devlist: string list of device names to use
+	#	 devlist: the list of devices/actions in a group of contiguous phases
 	# Output:
 	#	 The total number of rows needed to display this phase of the timeline
-	def getPhaseRows(self, dmesg, devlist):
+	def getPhaseRows(self, devlist, row=0):
 		# clear all rows and set them to undefined
 		remaining = len(devlist)
 		rowdata = dict()
-		row = 0
-		lendict = dict()
+		sortdict = dict()
 		myphases = []
+		# initialize all device rows to -1 and calculate devrows
 		for item in devlist:
-			if item[0] not in self.phases:
-				self.phases.append(item[0])
-			if item[0] not in myphases:
-				myphases.append(item[0])
-				self.rowmaxlines[item[0]] = dict()
-				self.rowheight[item[0]] = dict()
-			dev = dmesg[item[0]]['list'][item[1]]
+			dev = item.dev
+			tp = (item.test, item.phase)
+			if tp not in myphases:
+				myphases.append(tp)
 			dev['row'] = -1
-			lendict[item] = float(dev['end']) - float(dev['start'])
+			# sort by length 1st, then name 2nd
+			sortdict[item] = (float(dev['end']) - float(dev['start']), item.dev['name'])
 			if 'src' in dev:
 				dev['devrows'] = self.getDeviceRows(dev['src'])
-		lenlist = []
-		for i in sorted(lendict, key=lendict.get, reverse=True):
-			lenlist.append(i)
+		# sort the devlist by length so that large items graph on top
+		sortlist = sorted(sortdict, key=sortdict.get, reverse=True)
 		orderedlist = []
-		for item in lenlist:
-			dev = dmesg[item[0]]['list'][item[1]]
-			if dev['pid'] == -2:
+		for item in sortlist:
+			if item.dev['pid'] == -2:
 				orderedlist.append(item)
-		for item in lenlist:
+		for item in sortlist:
 			if item not in orderedlist:
 				orderedlist.append(item)
-		# try to pack each row with as many ranges as possible
+		# try to pack each row with as many devices as possible
 		while(remaining > 0):
 			rowheight = 1
 			if(row not in rowdata):
 				rowdata[row] = []
 			for item in orderedlist:
-				dev = dmesg[item[0]]['list'][item[1]]
+				dev = item.dev
 				if(dev['row'] < 0):
 					s = dev['start']
 					e = dev['end']
 					valid = True
 					for ritem in rowdata[row]:
-						rs = ritem['start']
-						re = ritem['end']
+						rs = ritem.dev['start']
+						re = ritem.dev['end']
 						if(not (((s <= rs) and (e <= rs)) or
 							((s >= re) and (e >= re)))):
 							valid = False
 							break
 					if(valid):
-						rowdata[row].append(dev)
+						rowdata[row].append(item)
 						dev['row'] = row
 						remaining -= 1
 						if 'devrows' in dev and dev['devrows'] > rowheight:
 							rowheight = dev['devrows']
-			for phase in myphases:
-				self.rowmaxlines[phase][row] = rowheight
-				self.rowheight[phase][row] = rowheight * self.rowH
+			for t, p in myphases:
+				if t not in self.rowlines or t not in self.rowheight:
+					self.rowlines[t] = dict()
+					self.rowheight[t] = dict()
+				if p not in self.rowlines[t] or p not in self.rowheight[t]:
+					self.rowlines[t][p] = dict()
+					self.rowheight[t][p] = dict()
+				rh = self.rowH
+				# section headers should use a different row height
+				if len(rowdata[row]) == 1 and \
+					'htmlclass' in rowdata[row][0].dev and \
+					'sec' in rowdata[row][0].dev['htmlclass']:
+					rh = 15
+				self.rowlines[t][p][row] = rowheight
+				self.rowheight[t][p][row] = rowheight * rh
 			row += 1
 		if(row > self.rows):
 			self.rows = int(row)
-		for phase in myphases:
-			self.rowcount[phase] = row
 		return row
-	def phaseRowHeight(self, phase, row):
-		return self.rowheight[phase][row]
-	def phaseRowTop(self, phase, row):
+	def phaseRowHeight(self, test, phase, row):
+		return self.rowheight[test][phase][row]
+	def phaseRowTop(self, test, phase, row):
 		top = 0
-		for i in sorted(self.rowheight[phase]):
+		for i in sorted(self.rowheight[test][phase]):
 			if i >= row:
 				break
-			top += self.rowheight[phase][i]
+			top += self.rowheight[test][phase][i]
 		return top
 	# Function: calcTotalRows
 	# Description:
@@ -1657,19 +1886,21 @@ class Timeline:
 	def calcTotalRows(self):
 		maxrows = 0
 		standardphases = []
-		for phase in self.phases:
-			total = 0
-			for i in sorted(self.rowmaxlines[phase]):
-				total += self.rowmaxlines[phase][i]
-			if total > maxrows:
-				maxrows = total
-			if total == self.rowcount[phase]:
-				standardphases.append(phase)
+		for t in self.rowlines:
+			for p in self.rowlines[t]:
+				total = 0
+				for i in sorted(self.rowlines[t][p]):
+					total += self.rowlines[t][p][i]
+				if total > maxrows:
+					maxrows = total
+				if total == len(self.rowlines[t][p]):
+					standardphases.append((t, p))
 		self.height = self.scaleH + (maxrows*self.rowH)
 		self.bodyH = self.height - self.scaleH
-		for phase in standardphases:
-			for i in sorted(self.rowheight[phase]):
-				self.rowheight[phase][i] = self.bodyH/self.rowcount[phase]
+		# if there is 1 line per row, draw them the standard way
+		for t, p in standardphases:
+			for i in sorted(self.rowheight[t][p]):
+				self.rowheight[t][p][i] = self.bodyH/len(self.rowlines[t][p])
 	# Function: createTimeScale
 	# Description:
 	#	 Create the timescale for a timeline block
@@ -1716,7 +1947,6 @@ class Timeline:
 #	 A list of values describing the properties of these test runs
 class TestProps:
 	stamp = ''
-	tracertype = ''
 	S0i3 = False
 	fwdata = []
 	ftrace_line_fmt_fg = \
@@ -1734,14 +1964,13 @@ class TestProps:
 	def __init__(self):
 		self.ktemp = dict()
 	def setTracerType(self, tracer):
-		self.tracertype = tracer
 		if(tracer == 'function_graph'):
 			self.cgformat = True
 			self.ftrace_line_fmt = self.ftrace_line_fmt_fg
 		elif(tracer == 'nop'):
 			self.ftrace_line_fmt = self.ftrace_line_fmt_nop
 		else:
-			doError('Invalid tracer format: [%s]' % tracer, False)
+			doError('Invalid tracer format: [%s]' % tracer)
 
 # Class: TestRun
 # Description:
@@ -1756,6 +1985,51 @@ class TestRun:
 		self.ftemp = dict()
 		self.ttemp = dict()
 
+class ProcessMonitor:
+	proclist = dict()
+	running = False
+	def procstat(self):
+		c = ['cat /proc/[1-9]*/stat 2>/dev/null']
+		process = Popen(c, shell=True, stdout=PIPE)
+		running = dict()
+		for line in process.stdout:
+			data = line.split()
+			pid = data[0]
+			name = re.sub('[()]', '', data[1])
+			user = int(data[13])
+			kern = int(data[14])
+			kjiff = ujiff = 0
+			if pid not in self.proclist:
+				self.proclist[pid] = {'name' : name, 'user' : user, 'kern' : kern}
+			else:
+				val = self.proclist[pid]
+				ujiff = user - val['user']
+				kjiff = kern - val['kern']
+				val['user'] = user
+				val['kern'] = kern
+			if ujiff > 0 or kjiff > 0:
+				running[pid] = ujiff + kjiff
+		result = process.wait()
+		out = ''
+		for pid in running:
+			jiffies = running[pid]
+			val = self.proclist[pid]
+			if out:
+				out += ','
+			out += '%s-%s %d' % (val['name'], pid, jiffies)
+		return 'ps - '+out
+	def processMonitor(self, tid):
+		while self.running:
+			out = self.procstat()
+			if out:
+				sysvals.fsetVal(out, 'trace_marker')
+	def start(self):
+		self.thread = Thread(target=self.processMonitor, args=(0,))
+		self.running = True
+		self.thread.start()
+	def stop(self):
+		self.running = False
+
 # ----------------- FUNCTIONS --------------------
 
 # Function: vprint
@@ -1764,7 +2038,7 @@ class TestRun:
 # Arguments:
 #	 msg: the debug/log message to print
 def vprint(msg):
-	global sysvals
+	sysvals.logmsg += msg+'\n'
 	if(sysvals.verbose):
 		print(msg)
 
@@ -1775,8 +2049,6 @@ def vprint(msg):
 # Arguments:
 #	 m: the valid re.match output for the stamp line
 def parseStamp(line, data):
-	global sysvals
-
 	m = re.match(sysvals.stampfmt, line)
 	data.stamp = {'time': '', 'host': '', 'mode': ''}
 	dt = datetime(int(m.group('y'))+2000, int(m.group('m')),
@@ -1788,6 +2060,14 @@ def parseStamp(line, data):
 	data.stamp['kernel'] = m.group('kernel')
 	sysvals.hostname = data.stamp['host']
 	sysvals.suspendmode = data.stamp['mode']
+	if sysvals.suspendmode == 'command' and sysvals.ftracefile != '':
+		modes = ['on', 'freeze', 'standby', 'mem']
+		out = Popen(['grep', 'suspend_enter', sysvals.ftracefile],
+			stderr=PIPE, stdout=PIPE).stdout.read()
+		m = re.match('.* suspend_enter\[(?P<mode>.*)\]', out)
+		if m and m.group('mode') in ['1', '2', '3']:
+			sysvals.suspendmode = modes[int(m.group('mode'))]
+			data.stamp['mode'] = sysvals.suspendmode
 	if not sysvals.stamp:
 		sysvals.stamp = data.stamp
 
@@ -1817,18 +2097,17 @@ def diffStamp(stamp1, stamp2):
 #	 required for primary parsing. Set the usetraceevents and/or
 #	 usetraceeventsonly flags in the global sysvals object
 def doesTraceLogHaveTraceEvents():
-	global sysvals
-
 	# check for kprobes
 	sysvals.usekprobes = False
-	out = os.system('grep -q "_cal: (" '+sysvals.ftracefile)
+	out = call('grep -q "_cal: (" '+sysvals.ftracefile, shell=True)
 	if(out == 0):
 		sysvals.usekprobes = True
 	# check for callgraph data on trace event blocks
-	out = os.system('grep -q "_cpu_down()" '+sysvals.ftracefile)
+	out = call('grep -q "_cpu_down()" '+sysvals.ftracefile, shell=True)
 	if(out == 0):
 		sysvals.usekprobes = True
-	out = os.popen('head -1 '+sysvals.ftracefile).read().replace('\n', '')
+	out = Popen(['head', '-1', sysvals.ftracefile],
+		stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '')
 	m = re.match(sysvals.stampfmt, out)
 	if m and m.group('mode') == 'command':
 		sysvals.usetraceeventsonly = True
@@ -1838,14 +2117,14 @@ def doesTraceLogHaveTraceEvents():
 	sysvals.usetraceeventsonly = True
 	sysvals.usetraceevents = False
 	for e in sysvals.traceevents:
-		out = os.system('grep -q "'+e+': " '+sysvals.ftracefile)
+		out = call('grep -q "'+e+': " '+sysvals.ftracefile, shell=True)
 		if(out != 0):
 			sysvals.usetraceeventsonly = False
 		if(e == 'suspend_resume' and out == 0):
 			sysvals.usetraceevents = True
 	# determine is this log is properly formatted
 	for e in ['SUSPEND START', 'RESUME COMPLETE']:
-		out = os.system('grep -q "'+e+'" '+sysvals.ftracefile)
+		out = call('grep -q "'+e+'" '+sysvals.ftracefile, shell=True)
 		if(out != 0):
 			sysvals.usetracemarkers = False
 
@@ -1860,8 +2139,6 @@ def doesTraceLogHaveTraceEvents():
 # Arguments:
 #	 testruns: the array of Data objects obtained from parseKernelLog
 def appendIncompleteTraceLog(testruns):
-	global sysvals
-
 	# create TestRun vessels for ftrace parsing
 	testcnt = len(testruns)
 	testidx = 0
@@ -2052,8 +2329,7 @@ def appendIncompleteTraceLog(testruns):
 								dev['ftrace'] = cg
 						break
 
-		if(sysvals.verbose):
-			test.data.printDetails()
+		test.data.printDetails()
 
 # Function: parseTraceLog
 # Description:
@@ -2064,14 +2340,12 @@ def appendIncompleteTraceLog(testruns):
 # Output:
 #	 An array of Data objects
 def parseTraceLog():
-	global sysvals
-
 	vprint('Analyzing the ftrace data...')
 	if(os.path.exists(sysvals.ftracefile) == False):
-		doError('%s does not exist' % sysvals.ftracefile, False)
+		doError('%s does not exist' % sysvals.ftracefile)
 
 	sysvals.setupAllKprobes()
-	tracewatch = ['suspend_enter']
+	tracewatch = []
 	if sysvals.usekprobes:
 		tracewatch += ['sync_filesystems', 'freeze_processes', 'syscore_suspend',
 			'syscore_resume', 'resume_console', 'thaw_processes', 'CPU_ON', 'CPU_OFF']
@@ -2102,17 +2376,13 @@ def parseTraceLog():
 		if(m):
 			tp.setTracerType(m.group('t'))
 			continue
-		# post resume time line: did this test run include post-resume data
-		m = re.match(sysvals.postresumefmt, line)
-		if(m):
-			t = int(m.group('t'))
-			if(t > 0):
-				sysvals.postresumetime = t
-			continue
 		# device properties line
 		if(re.match(sysvals.devpropfmt, line)):
 			devProps(line)
 			continue
+		# ignore all other commented lines
+		if line[0] == '#':
+			continue
 		# ftrace line: parse only valid lines
 		m = re.match(tp.ftrace_line_fmt, line)
 		if(not m):
@@ -2142,20 +2412,36 @@ def parseTraceLog():
 			testrun = TestRun(data)
 			testruns.append(testrun)
 			parseStamp(tp.stamp, data)
-			if len(tp.fwdata) > data.testnumber:
-				data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber]
-				if(data.fwSuspend > 0 or data.fwResume > 0):
-					data.fwValid = True
 			data.setStart(t.time)
+			data.tKernSus = t.time
 			continue
 		if(not data):
 			continue
+		# process cpu exec line
+		if t.type == 'tracing_mark_write':
+			m = re.match(sysvals.procexecfmt, t.name)
+			if(m):
+				proclist = dict()
+				for ps in m.group('ps').split(','):
+					val = ps.split()
+					if not val:
+						continue
+					name = val[0].replace('--', '-')
+					proclist[name] = int(val[1])
+				data.pstl[t.time] = proclist
+				continue
 		# find the end of resume
 		if(t.endMarker()):
-			if(sysvals.usetracemarkers and sysvals.postresumetime > 0):
-				phase = 'post_resume'
-				data.newPhase(phase, t.time, t.time, '#F0F0F0', -1)
 			data.setEnd(t.time)
+			if data.tKernRes == 0.0:
+				data.tKernRes = t.time
+			if data.dmesg['resume_complete']['end'] < 0:
+				data.dmesg['resume_complete']['end'] = t.time
+			if sysvals.suspendmode == 'mem' and len(tp.fwdata) > data.testnumber:
+				data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber]
+				if(data.tSuspended != 0 and data.tResumed != 0 and \
+					(data.fwSuspend > 0 or data.fwResume > 0)):
+					data.fwValid = True
 			if(not sysvals.usetracemarkers):
 				# no trace markers? then quit and be sure to finish recording
 				# the event we used to trigger resume end
@@ -2190,8 +2476,14 @@ def parseTraceLog():
 				if(name.split('[')[0] in tracewatch):
 					continue
 				# -- phase changes --
+				# start of kernel suspend
+				if(re.match('suspend_enter\[.*', t.name)):
+					if(isbegin):
+						data.dmesg[phase]['start'] = t.time
+						data.tKernSus = t.time
+					continue
 				# suspend_prepare start
-				if(re.match('dpm_prepare\[.*', t.name)):
+				elif(re.match('dpm_prepare\[.*', t.name)):
 					phase = 'suspend_prepare'
 					if(not isbegin):
 						data.dmesg[phase]['end'] = t.time
@@ -2291,6 +2583,8 @@ def parseTraceLog():
 				p = m.group('p')
 				if(n and p):
 					data.newAction(phase, n, pid, p, t.time, -1, drv)
+					if pid not in data.devpids:
+						data.devpids.append(pid)
 			# device callback finish
 			elif(t.type == 'device_pm_callback_end'):
 				m = re.match('(?P<drv>.*) (?P<d>.*), err.*', t.name);
@@ -2332,6 +2626,12 @@ def parseTraceLog():
 				else:
 					e['end'] = t.time
 					e['rdata'] = kprobedata
+				# end of kernel resume
+				if(kprobename == 'pm_notifier_call_chain' or \
+					kprobename == 'pm_restore_console'):
+					data.dmesg[phase]['end'] = t.time
+					data.tKernRes = t.time
+
 		# callgraph processing
 		elif sysvals.usecallgraph:
 			# create a callgraph object for the data
@@ -2348,24 +2648,37 @@ def parseTraceLog():
 	if sysvals.suspendmode == 'command':
 		for test in testruns:
 			for p in test.data.phases:
-				if p == 'resume_complete':
+				if p == 'suspend_prepare':
 					test.data.dmesg[p]['start'] = test.data.start
 					test.data.dmesg[p]['end'] = test.data.end
 				else:
-					test.data.dmesg[p]['start'] = test.data.start
-					test.data.dmesg[p]['end'] = test.data.start
-			test.data.tSuspended = test.data.start
-			test.data.tResumed = test.data.start
+					test.data.dmesg[p]['start'] = test.data.end
+					test.data.dmesg[p]['end'] = test.data.end
+			test.data.tSuspended = test.data.end
+			test.data.tResumed = test.data.end
 			test.data.tLow = 0
 			test.data.fwValid = False
 
-	for test in testruns:
+	# dev source and procmon events can be unreadable with mixed phase height
+	if sysvals.usedevsrc or sysvals.useprocmon:
+		sysvals.mixedphaseheight = False
+
+	for i in range(len(testruns)):
+		test = testruns[i]
+		data = test.data
+		# find the total time range for this test (begin, end)
+		tlb, tle = data.start, data.end
+		if i < len(testruns) - 1:
+			tle = testruns[i+1].data.start
+		# add the process usage data to the timeline
+		if sysvals.useprocmon:
+			data.createProcessUsageEvents()
 		# add the traceevent data to the device hierarchy
 		if(sysvals.usetraceevents):
 			# add actual trace funcs
 			for name in test.ttemp:
 				for event in test.ttemp[name]:
-					test.data.newActionGlobal(name, event['begin'], event['end'], event['pid'])
+					data.newActionGlobal(name, event['begin'], event['end'], event['pid'])
 			# add the kprobe based virtual tracefuncs as actual devices
 			for key in tp.ktemp:
 				name, pid = key
@@ -2373,24 +2686,20 @@ def parseTraceLog():
 					continue
 				for e in tp.ktemp[key]:
 					kb, ke = e['begin'], e['end']
-					if kb == ke or not test.data.isInsideTimeline(kb, ke):
+					if kb == ke or tlb > kb or tle <= kb:
 						continue
-					test.data.newActionGlobal(e['name'], kb, ke, pid)
+					color = sysvals.kprobeColor(name)
+					data.newActionGlobal(e['name'], kb, ke, pid, color)
 			# add config base kprobes and dev kprobes
-			for key in tp.ktemp:
-				name, pid = key
-				if name in sysvals.tracefuncs:
-					continue
-				for e in tp.ktemp[key]:
-					kb, ke = e['begin'], e['end']
-					if kb == ke or not test.data.isInsideTimeline(kb, ke):
+			if sysvals.usedevsrc:
+				for key in tp.ktemp:
+					name, pid = key
+					if name in sysvals.tracefuncs or name not in sysvals.dev_tracefuncs:
 						continue
-					color = sysvals.kprobeColor(e['name'])
-					if name not in sysvals.dev_tracefuncs:
-						# config base kprobe
-						test.data.newActionGlobal(e['name'], kb, ke, -2, color)
-					elif sysvals.usedevsrc:
-						# dev kprobe
+					for e in tp.ktemp[key]:
+						kb, ke = e['begin'], e['end']
+						if kb == ke or tlb > kb or tle <= kb:
+							continue
 						data.addDeviceFunctionCall(e['name'], name, e['proc'], pid, kb,
 							ke, e['cdata'], e['rdata'])
 		if sysvals.usecallgraph:
@@ -2407,7 +2716,7 @@ def parseTraceLog():
 							id+', ignoring this callback')
 						continue
 					# match cg data to devices
-					if sysvals.suspendmode == 'command' or not cg.deviceMatch(pid, test.data):
+					if sysvals.suspendmode == 'command' or not cg.deviceMatch(pid, data):
 						sortkey = '%f%f%d' % (cg.start, cg.end, pid)
 						sortlist[sortkey] = cg
 			# create blocks for orphan cg data
@@ -2416,12 +2725,11 @@ def parseTraceLog():
 				name = cg.list[0].name
 				if sysvals.isCallgraphFunc(name):
 					vprint('Callgraph found for task %d: %.3fms, %s' % (cg.pid, (cg.end - cg.start)*1000, name))
-					cg.newActionFromFunction(test.data)
+					cg.newActionFromFunction(data)
 
 	if sysvals.suspendmode == 'command':
-		if(sysvals.verbose):
-			for data in testdata:
-				data.printDetails()
+		for data in testdata:
+			data.printDetails()
 		return testdata
 
 	# fill in any missing phases
@@ -2429,7 +2737,7 @@ def parseTraceLog():
 		lp = data.phases[0]
 		for p in data.phases:
 			if(data.dmesg[p]['start'] < 0 and data.dmesg[p]['end'] < 0):
-				print('WARNING: phase "%s" is missing!' % p)
+				vprint('WARNING: phase "%s" is missing!' % p)
 			if(data.dmesg[p]['start'] < 0):
 				data.dmesg[p]['start'] = data.dmesg[lp]['end']
 				if(p == 'resume_machine'):
@@ -2438,60 +2746,27 @@ def parseTraceLog():
 					data.tLow = 0
 			if(data.dmesg[p]['end'] < 0):
 				data.dmesg[p]['end'] = data.dmesg[p]['start']
+			if(p != lp and not ('machine' in p and 'machine' in lp)):
+				data.dmesg[lp]['end'] = data.dmesg[p]['start']
 			lp = p
 
 		if(len(sysvals.devicefilter) > 0):
 			data.deviceFilter(sysvals.devicefilter)
 		data.fixupInitcallsThatDidntReturn()
-		if(sysvals.verbose):
-			data.printDetails()
+		if sysvals.usedevsrc:
+			data.optimizeDevSrc()
+		data.printDetails()
 
+	# x2: merge any overlapping devices between test runs
+	if sysvals.usedevsrc and len(testdata) > 1:
+		tc = len(testdata)
+		for i in range(tc - 1):
+			devlist = testdata[i].overflowDevices()
+			for j in range(i + 1, tc):
+				testdata[j].mergeOverlapDevices(devlist)
+		testdata[0].stitchTouchingThreads(testdata[1:])
 	return testdata
 
-# Function: loadRawKernelLog
-# Description:
-#	 Load a raw kernel log that wasn't created by this tool, it might be
-#	 possible to extract a valid suspend/resume log
-def loadRawKernelLog(dmesgfile):
-	global sysvals
-
-	stamp = {'time': '', 'host': '', 'mode': 'mem', 'kernel': ''}
-	stamp['time'] = datetime.now().strftime('%B %d %Y, %I:%M:%S %p')
-	stamp['host'] = sysvals.hostname
-
-	testruns = []
-	data = 0
-	lf = open(dmesgfile, 'r')
-	for line in lf:
-		line = line.replace('\r\n', '')
-		idx = line.find('[')
-		if idx > 1:
-			line = line[idx:]
-		m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
-		if(not m):
-			continue
-		msg = m.group("msg")
-		m = re.match('PM: Syncing filesystems.*', msg)
-		if(m):
-			if(data):
-				testruns.append(data)
-			data = Data(len(testruns))
-			data.stamp = stamp
-		if(data):
-			m = re.match('.* *(?P<k>[0-9]\.[0-9]{2}\.[0-9]-.*) .*', msg)
-			if(m):
-				stamp['kernel'] = m.group('k')
-			m = re.match('PM: Preparing system for (?P<m>.*) sleep', msg)
-			if(m):
-				stamp['mode'] = m.group('m')
-			data.dmesgtext.append(line)
-	if(data):
-		testruns.append(data)
-		sysvals.stamp = stamp
-		sysvals.suspendmode = stamp['mode']
-	lf.close()
-	return testruns
-
 # Function: loadKernelLog
 # Description:
 #	 [deprecated for kernel 3.15.0 or newer]
@@ -2499,15 +2774,16 @@ def loadRawKernelLog(dmesgfile):
 #	 The dmesg filename is taken from sysvals
 # Output:
 #	 An array of empty Data objects with only their dmesgtext attributes set
-def loadKernelLog():
-	global sysvals
-
+def loadKernelLog(justtext=False):
 	vprint('Analyzing the dmesg data...')
 	if(os.path.exists(sysvals.dmesgfile) == False):
-		doError('%s does not exist' % sysvals.dmesgfile, False)
+		doError('%s does not exist' % sysvals.dmesgfile)
 
+	if justtext:
+		dmesgtext = []
 	# there can be multiple test runs in a single file
 	tp = TestProps()
+	tp.stamp = datetime.now().strftime('# suspend-%m%d%y-%H%M%S localhost mem unknown')
 	testruns = []
 	data = 0
 	lf = open(sysvals.dmesgfile, 'r')
@@ -2528,6 +2804,9 @@ def loadKernelLog():
 		if(not m):
 			continue
 		msg = m.group("msg")
+		if justtext:
+			dmesgtext.append(line)
+			continue
 		if(re.match('PM: Syncing filesystems.*', msg)):
 			if(data):
 				testruns.append(data)
@@ -2537,24 +2816,24 @@ def loadKernelLog():
 				data.fwSuspend, data.fwResume = tp.fwdata[data.testnumber]
 				if(data.fwSuspend > 0 or data.fwResume > 0):
 					data.fwValid = True
-		if(re.match('ACPI: resume from mwait', msg)):
-			print('NOTE: This suspend appears to be freeze rather than'+\
-				' %s, it will be treated as such' % sysvals.suspendmode)
-			sysvals.suspendmode = 'freeze'
 		if(not data):
 			continue
+		m = re.match('.* *(?P<k>[0-9]\.[0-9]{2}\.[0-9]-.*) .*', msg)
+		if(m):
+			sysvals.stamp['kernel'] = m.group('k')
+		m = re.match('PM: Preparing system for (?P<m>.*) sleep', msg)
+		if(m):
+			sysvals.stamp['mode'] = sysvals.suspendmode = m.group('m')
 		data.dmesgtext.append(line)
-	if(data):
-		testruns.append(data)
 	lf.close()
 
-	if(len(testruns) < 1):
-		# bad log, but see if you can extract something meaningful anyway
-		testruns = loadRawKernelLog(sysvals.dmesgfile)
-
-	if(len(testruns) < 1):
-		doError(' dmesg log is completely unreadable: %s' \
-			% sysvals.dmesgfile, False)
+	if justtext:
+		return dmesgtext
+	if data:
+		testruns.append(data)
+	if len(testruns) < 1:
+		doError(' dmesg log has no suspend/resume data: %s' \
+			% sysvals.dmesgfile)
 
 	# fix lines with same timestamp/function with the call and return swapped
 	for data in testruns:
@@ -2586,8 +2865,6 @@ def loadKernelLog():
 # Output:
 #	 The filled Data object
 def parseKernelLog(data):
-	global sysvals
-
 	phase = 'suspend_runtime'
 
 	if(data.fwValid):
@@ -2645,7 +2922,6 @@ def parseKernelLog(data):
 	prevktime = -1.0
 	actions = dict()
 	for line in data.dmesgtext:
-		# -- preprocessing --
 		# parse each dmesg line into the time and message
 		m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line)
 		if(m):
@@ -2653,8 +2929,6 @@ def parseKernelLog(data):
 			try:
 				ktime = float(val)
 			except:
-				doWarning('INVALID DMESG LINE: '+\
-					line.replace('\n', ''), 'dmesg')
 				continue
 			msg = m.group('msg')
 			# initialize data start to first line time
@@ -2672,12 +2946,12 @@ def parseKernelLog(data):
 			phase = 'resume_noirq'
 			data.dmesg[phase]['start'] = ktime
 
-		# -- phase changes --
 		# suspend start
 		if(re.match(dm['suspend_prepare'], msg)):
 			phase = 'suspend_prepare'
 			data.dmesg[phase]['start'] = ktime
 			data.setStart(ktime)
+			data.tKernSus = ktime
 		# suspend start
 		elif(re.match(dm['suspend'], msg)):
 			data.dmesg['suspend_prepare']['end'] = ktime
@@ -2734,7 +3008,7 @@ def parseKernelLog(data):
 		elif(re.match(dm['post_resume'], msg)):
 			data.dmesg['resume_complete']['end'] = ktime
 			data.setEnd(ktime)
-			phase = 'post_resume'
+			data.tKernRes = ktime
 			break
 
 		# -- device callbacks --
@@ -2761,7 +3035,6 @@ def parseKernelLog(data):
 					dev['length'] = int(t)
 					dev['end'] = ktime
 
-		# -- non-devicecallback actions --
 		# if trace events are not available, these are better than nothing
 		if(not sysvals.usetraceevents):
 			# look for known actions
@@ -2821,8 +3094,7 @@ def parseKernelLog(data):
 		for event in actions[name]:
 			data.newActionGlobal(name, event['begin'], event['end'])
 
-	if(sysvals.verbose):
-		data.printDetails()
+	data.printDetails()
 	if(len(sysvals.devicefilter) > 0):
 		data.deviceFilter(sysvals.devicefilter)
 	data.fixupInitcallsThatDidntReturn()
@@ -2834,8 +3106,6 @@ def parseKernelLog(data):
 # Arguments:
 #	 testruns: array of Data objects from parseTraceLog
 def createHTMLSummarySimple(testruns, htmlfile):
-	global sysvals
-
 	# print out the basic summary of all the tests
 	hf = open(htmlfile, 'w')
 
@@ -2960,7 +3230,6 @@ def createHTMLSummarySimple(testruns, htmlfile):
 	hf.close()
 
 def htmlTitle():
-	global sysvals
 	modename = {
 		'freeze': 'Freeze (S0)',
 		'standby': 'Standby (S1)',
@@ -2993,13 +3262,14 @@ def ordinal(value):
 # Output:
 #	 True if the html file was created, false if it failed
 def createHTML(testruns):
-	global sysvals
-
 	if len(testruns) < 1:
 		print('ERROR: Not enough test data to build a timeline')
 		return
 
+	kerror = False
 	for data in testruns:
+		if data.kerror:
+			kerror = True
 		data.normalizeTime(testruns[-1].tSuspended)
 
 	x2changes = ['', 'absolute']
@@ -3009,53 +3279,59 @@ def createHTML(testruns):
 	headline_version = '<div class="version"><a href="https://01.org/suspendresume">AnalyzeSuspend v%s</a></div>' % sysvals.version
 	headline_stamp = '<div class="stamp">{0} {1} {2} {3}</div>\n'
 	html_devlist1 = '<button id="devlist1" class="devlist" style="float:left;">Device Detail%s</button>' % x2changes[0]
-	html_zoombox = '<center><button id="zoomin">ZOOM IN</button><button id="zoomout">ZOOM OUT</button><button id="zoomdef">ZOOM 1:1</button></center>\n'
+	html_zoombox = '<center><button id="zoomin">ZOOM IN +</button><button id="zoomout">ZOOM OUT -</button><button id="zoomdef">ZOOM 1:1</button></center>\n'
 	html_devlist2 = '<button id="devlist2" class="devlist" style="float:right;">Device Detail2</button>\n'
 	html_timeline = '<div id="dmesgzoombox" class="zoombox">\n<div id="{0}" class="timeline" style="height:{1}px">\n'
-	html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;">\n'
+	html_tblock = '<div id="block{0}" class="tblock" style="left:{1}%;width:{2}%;"><div class="tback" style="height:{3}px"></div>\n'
 	html_device = '<div id="{0}" title="{1}" class="thread{7}" style="left:{2}%;top:{3}px;height:{4}px;width:{5}%;{8}">{6}</div>\n'
-	html_traceevent = '<div title="{0}" class="traceevent" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;">{5}</div>\n'
+	html_error = '<div id="{1}" title="kernel error/warning" class="err" style="right:{0}%">ERROR&rarr;</div>\n'
+	html_traceevent = '<div title="{0}" class="traceevent{6}" style="left:{1}%;top:{2}px;height:{3}px;width:{4}%;line-height:{3}px;{7}">{5}</div>\n'
+	html_cpuexec = '<div class="jiffie" style="left:{0}%;top:{1}px;height:{2}px;width:{3}%;background:{4};"></div>\n'
 	html_phase = '<div class="phase" style="left:{0}%;width:{1}%;top:{2}px;height:{3}px;background-color:{4}">{5}</div>\n'
-	html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background-color:{3}"></div>\n'
+	html_phaselet = '<div id="{0}" class="phaselet" style="left:{1}%;width:{2}%;background:{3}"></div>\n'
 	html_legend = '<div id="p{3}" class="square" style="left:{0}%;background-color:{1}">&nbsp;{2}</div>\n'
 	html_timetotal = '<table class="time1">\n<tr>'\
-		'<td class="green">{2} Suspend Time: <b>{0} ms</b></td>'\
-		'<td class="yellow">{2} Resume Time: <b>{1} ms</b></td>'\
+		'<td class="green" title="{3}">{2} Suspend Time: <b>{0} ms</b></td>'\
+		'<td class="yellow" title="{4}">{2} Resume Time: <b>{1} ms</b></td>'\
 		'</tr>\n</table>\n'
 	html_timetotal2 = '<table class="time1">\n<tr>'\
-		'<td class="green">{3} Suspend Time: <b>{0} ms</b></td>'\
-		'<td class="gray">'+sysvals.suspendmode+' time: <b>{1} ms</b></td>'\
-		'<td class="yellow">{3} Resume Time: <b>{2} ms</b></td>'\
+		'<td class="green" title="{4}">{3} Suspend Time: <b>{0} ms</b></td>'\
+		'<td class="gray" title="time spent in low-power mode with clock running">'+sysvals.suspendmode+' time: <b>{1} ms</b></td>'\
+		'<td class="yellow" title="{5}">{3} Resume Time: <b>{2} ms</b></td>'\
 		'</tr>\n</table>\n'
 	html_timetotal3 = '<table class="time1">\n<tr>'\
 		'<td class="green">Execution Time: <b>{0} ms</b></td>'\
 		'<td class="yellow">Command: <b>{1}</b></td>'\
 		'</tr>\n</table>\n'
 	html_timegroups = '<table class="time2">\n<tr>'\
-		'<td class="green">{4}Kernel Suspend: {0} ms</td>'\
+		'<td class="green" title="time from kernel enter_state({5}) to firmware mode [kernel time only]">{4}Kernel Suspend: {0} ms</td>'\
 		'<td class="purple">{4}Firmware Suspend: {1} ms</td>'\
 		'<td class="purple">{4}Firmware Resume: {2} ms</td>'\
-		'<td class="yellow">{4}Kernel Resume: {3} ms</td>'\
+		'<td class="yellow" title="time from firmware mode to return from kernel enter_state({5}) [kernel time only]">{4}Kernel Resume: {3} ms</td>'\
 		'</tr>\n</table>\n'
 
 	# html format variables
-	rowheight = 30
-	devtextS = '14px'
-	devtextH = '30px'
-	hoverZ = 'z-index:10;'
-
+	hoverZ = 'z-index:8;'
 	if sysvals.usedevsrc:
 		hoverZ = ''
+	scaleH = 20
+	scaleTH = 20
+	if kerror:
+		scaleH = 40
+		scaleTH = 60
 
 	# device timeline
 	vprint('Creating Device Timeline...')
 
-	devtl = Timeline(rowheight)
+	devtl = Timeline(30, scaleH)
 
 	# Generate the header for this timeline
 	for data in testruns:
 		tTotal = data.end - data.start
-		tEnd = data.dmesg['resume_complete']['end']
+		sktime = (data.dmesg['suspend_machine']['end'] - \
+			data.tKernSus) * 1000
+		rktime = (data.dmesg['resume_complete']['end'] - \
+			data.dmesg['resume_machine']['start']) * 1000
 		if(tTotal == 0):
 			print('ERROR: No timeline data')
 			sys.exit()
@@ -3072,59 +3348,85 @@ def createHTML(testruns):
 			thtml = html_timetotal3.format(run_time, testdesc)
 			devtl.html['header'] += thtml
 		elif data.fwValid:
-			suspend_time = '%.0f'%((data.tSuspended-data.start)*1000 + \
-				(data.fwSuspend/1000000.0))
-			resume_time = '%.0f'%((tEnd-data.tSuspended)*1000 + \
-				(data.fwResume/1000000.0))
+			suspend_time = '%.0f'%(sktime + (data.fwSuspend/1000000.0))
+			resume_time = '%.0f'%(rktime + (data.fwResume/1000000.0))
 			testdesc1 = 'Total'
 			testdesc2 = ''
+			stitle = 'time from kernel enter_state(%s) to low-power mode [kernel & firmware time]' % sysvals.suspendmode
+			rtitle = 'time from low-power mode to return from kernel enter_state(%s) [firmware & kernel time]' % sysvals.suspendmode
 			if(len(testruns) > 1):
 				testdesc1 = testdesc2 = ordinal(data.testnumber+1)
 				testdesc2 += ' '
 			if(data.tLow == 0):
 				thtml = html_timetotal.format(suspend_time, \
-					resume_time, testdesc1)
+					resume_time, testdesc1, stitle, rtitle)
 			else:
 				thtml = html_timetotal2.format(suspend_time, low_time, \
-					resume_time, testdesc1)
+					resume_time, testdesc1, stitle, rtitle)
 			devtl.html['header'] += thtml
-			sktime = '%.3f'%((data.dmesg['suspend_machine']['end'] - \
-				data.getStart())*1000)
 			sftime = '%.3f'%(data.fwSuspend / 1000000.0)
 			rftime = '%.3f'%(data.fwResume / 1000000.0)
-			rktime = '%.3f'%((data.dmesg['resume_complete']['end'] - \
-				data.dmesg['resume_machine']['start'])*1000)
-			devtl.html['header'] += html_timegroups.format(sktime, \
-				sftime, rftime, rktime, testdesc2)
+			devtl.html['header'] += html_timegroups.format('%.3f'%sktime, \
+				sftime, rftime, '%.3f'%rktime, testdesc2, sysvals.suspendmode)
 		else:
-			suspend_time = '%.0f'%((data.tSuspended-data.start)*1000)
-			resume_time = '%.0f'%((tEnd-data.tSuspended)*1000)
+			suspend_time = '%.3f' % sktime
+			resume_time = '%.3f' % rktime
 			testdesc = 'Kernel'
+			stitle = 'time from kernel enter_state(%s) to firmware mode [kernel time only]' % sysvals.suspendmode
+			rtitle = 'time from firmware mode to return from kernel enter_state(%s) [kernel time only]' % sysvals.suspendmode
 			if(len(testruns) > 1):
 				testdesc = ordinal(data.testnumber+1)+' '+testdesc
 			if(data.tLow == 0):
 				thtml = html_timetotal.format(suspend_time, \
-					resume_time, testdesc)
+					resume_time, testdesc, stitle, rtitle)
 			else:
 				thtml = html_timetotal2.format(suspend_time, low_time, \
-					resume_time, testdesc)
+					resume_time, testdesc, stitle, rtitle)
 			devtl.html['header'] += thtml
 
 	# time scale for potentially multiple datasets
 	t0 = testruns[0].start
 	tMax = testruns[-1].end
-	tSuspended = testruns[-1].tSuspended
 	tTotal = tMax - t0
 
 	# determine the maximum number of rows we need to draw
+	fulllist = []
+	threadlist = []
+	pscnt = 0
+	devcnt = 0
 	for data in testruns:
 		data.selectTimelineDevices('%f', tTotal, sysvals.mindevlen)
 		for group in data.devicegroups:
 			devlist = []
 			for phase in group:
 				for devname in data.tdevlist[phase]:
-					devlist.append((phase,devname))
-			devtl.getPhaseRows(data.dmesg, devlist)
+					d = DevItem(data.testnumber, phase, data.dmesg[phase]['list'][devname])
+					devlist.append(d)
+					if d.isa('kth'):
+						threadlist.append(d)
+					else:
+						if d.isa('ps'):
+							pscnt += 1
+						else:
+							devcnt += 1
+						fulllist.append(d)
+			if sysvals.mixedphaseheight:
+				devtl.getPhaseRows(devlist)
+	if not sysvals.mixedphaseheight:
+		if len(threadlist) > 0 and len(fulllist) > 0:
+			if pscnt > 0 and devcnt > 0:
+				msg = 'user processes & device pm callbacks'
+			elif pscnt > 0:
+				msg = 'user processes'
+			else:
+				msg = 'device pm callbacks'
+			d = testruns[0].addHorizontalDivider(msg, testruns[-1].end)
+			fulllist.insert(0, d)
+		devtl.getPhaseRows(fulllist)
+		if len(threadlist) > 0:
+			d = testruns[0].addHorizontalDivider('asynchronous kernel threads', testruns[-1].end)
+			threadlist.insert(0, d)
+			devtl.getPhaseRows(threadlist, devtl.rows)
 	devtl.calcTotalRows()
 
 	# create bounding box, add buttons
@@ -3145,18 +3447,6 @@ def createHTML(testruns):
 
 	# draw each test run chronologically
 	for data in testruns:
-		# if nore than one test, draw a block to represent user mode
-		if(data.testnumber > 0):
-			m0 = testruns[data.testnumber-1].end
-			mMax = testruns[data.testnumber].start
-			mTotal = mMax - m0
-			name = 'usermode%d' % data.testnumber
-			top = '%d' % devtl.scaleH
-			left = '%f' % (((m0-t0)*100.0)/tTotal)
-			width = '%f' % ((mTotal*100.0)/tTotal)
-			title = 'user mode (%0.3f ms) ' % (mTotal*1000)
-			devtl.html['timeline'] += html_device.format(name, \
-				title, left, top, '%d'%devtl.bodyH, width, '', '', '')
 		# now draw the actual timeline blocks
 		for dir in phases:
 			# draw suspend and resume blocks separately
@@ -3169,13 +3459,16 @@ def createHTML(testruns):
 			else:
 				m0 = testruns[data.testnumber].tSuspended
 				mMax = testruns[data.testnumber].end
+				# in an x2 run, remove any gap between blocks
+				if len(testruns) > 1 and data.testnumber == 0:
+					mMax = testruns[1].start
 				mTotal = mMax - m0
 				left = '%f' % ((((m0-t0)*100.0)+sysvals.srgap/2)/tTotal)
 			# if a timeline block is 0 length, skip altogether
 			if mTotal == 0:
 				continue
 			width = '%f' % (((mTotal*100.0)-sysvals.srgap/2)/tTotal)
-			devtl.html['timeline'] += html_tblock.format(bname, left, width)
+			devtl.html['timeline'] += html_tblock.format(bname, left, width, devtl.scaleH)
 			for b in sorted(phases[dir]):
 				# draw the phase color background
 				phase = data.dmesg[b]
@@ -3185,6 +3478,12 @@ def createHTML(testruns):
 				devtl.html['timeline'] += html_phase.format(left, width, \
 					'%.3f'%devtl.scaleH, '%.3f'%devtl.bodyH, \
 					data.dmesg[b]['color'], '')
+			for e in data.errorinfo[dir]:
+				# draw red lines for any kernel errors found
+				t, err = e
+				right = '%f' % (((mMax-t)*100.0)/mTotal)
+				devtl.html['timeline'] += html_error.format(right, err)
+			for b in sorted(phases[dir]):
 				# draw the devices for this phase
 				phaselist = data.dmesg[b]['list']
 				for d in data.tdevlist[b]:
@@ -3196,46 +3495,62 @@ def createHTML(testruns):
 					xtrastyle = ''
 					if 'htmlclass' in dev:
 						xtraclass = dev['htmlclass']
-						xtrainfo = dev['htmlclass']
 					if 'color' in dev:
 						xtrastyle = 'background-color:%s;' % dev['color']
 					if(d in sysvals.devprops):
 						name = sysvals.devprops[d].altName(d)
 						xtraclass = sysvals.devprops[d].xtraClass()
 						xtrainfo = sysvals.devprops[d].xtraInfo()
+					elif xtraclass == ' kth':
+						xtrainfo = ' kernel_thread'
 					if('drv' in dev and dev['drv']):
 						drv = ' {%s}' % dev['drv']
-					rowheight = devtl.phaseRowHeight(b, dev['row'])
-					rowtop = devtl.phaseRowTop(b, dev['row'])
+					rowheight = devtl.phaseRowHeight(data.testnumber, b, dev['row'])
+					rowtop = devtl.phaseRowTop(data.testnumber, b, dev['row'])
 					top = '%.3f' % (rowtop + devtl.scaleH)
 					left = '%f' % (((dev['start']-m0)*100)/mTotal)
 					width = '%f' % (((dev['end']-dev['start'])*100)/mTotal)
 					length = ' (%0.3f ms) ' % ((dev['end']-dev['start'])*1000)
+					title = name+drv+xtrainfo+length
 					if sysvals.suspendmode == 'command':
-						title = name+drv+xtrainfo+length+'cmdexec'
+						title += sysvals.testcommand
+					elif xtraclass == ' ps':
+						if 'suspend' in b:
+							title += 'pre_suspend_process'
+						else:
+							title += 'post_resume_process'
 					else:
-						title = name+drv+xtrainfo+length+b
+						title += b
 					devtl.html['timeline'] += html_device.format(dev['id'], \
 						title, left, top, '%.3f'%rowheight, width, \
 						d+drv, xtraclass, xtrastyle)
+					if('cpuexec' in dev):
+						for t in sorted(dev['cpuexec']):
+							start, end = t
+							j = float(dev['cpuexec'][t]) / 5
+							if j > 1.0:
+								j = 1.0
+							height = '%.3f' % (rowheight/3)
+							top = '%.3f' % (rowtop + devtl.scaleH + 2*rowheight/3)
+							left = '%f' % (((start-m0)*100)/mTotal)
+							width = '%f' % ((end-start)*100/mTotal)
+							color = 'rgba(255, 0, 0, %f)' % j
+							devtl.html['timeline'] += \
+								html_cpuexec.format(left, top, height, width, color)
 					if('src' not in dev):
 						continue
 					# draw any trace events for this device
-					vprint('Debug trace events found for device %s' % d)
-					vprint('%20s %20s %10s %8s' % ('title', \
-						'name', 'time(ms)', 'length(ms)'))
 					for e in dev['src']:
-						vprint('%20s %20s %10.3f %8.3f' % (e.title, \
-							e.text, e.time*1000, e.length*1000))
-						height = devtl.rowH
+						height = '%.3f' % devtl.rowH
 						top = '%.3f' % (rowtop + devtl.scaleH + (e.row*devtl.rowH))
 						left = '%f' % (((e.time-m0)*100)/mTotal)
 						width = '%f' % (e.length*100/mTotal)
-						color = 'rgba(204,204,204,0.5)'
+						xtrastyle = ''
+						if e.color:
+							xtrastyle = 'background:%s;' % e.color
 						devtl.html['timeline'] += \
-							html_traceevent.format(e.title, \
-								left, top, '%.3f'%height, \
-								width, e.text)
+							html_traceevent.format(e.title(), \
+								left, top, height, width, e.text(), '', xtrastyle)
 			# draw the time scale, try to make the number of labels readable
 			devtl.html['timeline'] += devtl.createTimeScale(m0, mMax, tTotal, dir)
 			devtl.html['timeline'] += '</div>\n'
@@ -3284,8 +3599,7 @@ def createHTML(testruns):
 		t2 {color:black;font:25px Times;}\n\
 		t3 {color:black;font:20px Times;white-space:nowrap;}\n\
 		t4 {color:black;font:bold 30px Times;line-height:60px;white-space:nowrap;}\n\
-		cS {color:blue;font:bold 11px Times;}\n\
-		cR {color:red;font:bold 11px Times;}\n\
+		cS {font:bold 13px Times;}\n\
 		table {width:100%;}\n\
 		.gray {background-color:rgba(80,80,80,0.1);}\n\
 		.green {background-color:rgba(204,255,204,0.4);}\n\
@@ -3302,20 +3616,22 @@ def createHTML(testruns):
 		.pf:'+cgchk+' + label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/><rect x="8" y="4" width="2" height="10" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
 		.pf:'+cgnchk+' ~ label {background:url(\'data:image/svg+xml;utf,<?xml version="1.0" standalone="no"?><svg xmlns="http://www.w3.org/2000/svg" height="18" width="18" version="1.1"><circle cx="9" cy="9" r="8" stroke="black" stroke-width="1" fill="white"/><rect x="4" y="8" width="10" height="2" style="fill:black;stroke-width:0"/></svg>\') no-repeat left center;}\n\
 		.pf:'+cgchk+' ~ *:not(:nth-child(2)) {display:none;}\n\
-		.zoombox {position:relative;width:100%;overflow-x:scroll;}\n\
+		.zoombox {position:relative;width:100%;overflow-x:scroll;-webkit-user-select:none;-moz-user-select:none;user-select:none;}\n\
 		.timeline {position:relative;font-size:14px;cursor:pointer;width:100%; overflow:hidden;background:linear-gradient(#cccccc, white);}\n\
-		.thread {position:absolute;height:0%;overflow:hidden;line-height:'+devtextH+';font-size:'+devtextS+';border:1px solid;text-align:center;white-space:nowrap;background-color:rgba(204,204,204,0.5);}\n\
-		.thread.sync {background-color:'+sysvals.synccolor+';}\n\
-		.thread.bg {background-color:'+sysvals.kprobecolor+';}\n\
+		.thread {position:absolute;height:0%;overflow:hidden;z-index:7;line-height:30px;font-size:14px;border:1px solid;text-align:center;white-space:nowrap;}\n\
+		.thread.ps {border-radius:3px;background:linear-gradient(to top, #ccc, #eee);}\n\
 		.thread:hover {background-color:white;border:1px solid red;'+hoverZ+'}\n\
+		.thread.sec,.thread.sec:hover {background-color:black;border:0;color:white;line-height:15px;font-size:10px;}\n\
 		.hover {background-color:white;border:1px solid red;'+hoverZ+'}\n\
 		.hover.sync {background-color:white;}\n\
-		.hover.bg {background-color:white;}\n\
-		.traceevent {position:absolute;font-size:10px;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,rgba(204,204,204,1),rgba(150,150,150,1));}\n\
-		.traceevent:hover {background:white;}\n\
+		.hover.bg,.hover.kth,.hover.sync,.hover.ps {background-color:white;}\n\
+		.jiffie {position:absolute;pointer-events: none;z-index:8;}\n\
+		.traceevent {position:absolute;font-size:10px;z-index:7;overflow:hidden;color:black;text-align:center;white-space:nowrap;border-radius:5px;border:1px solid black;background:linear-gradient(to bottom right,#CCC,#969696);}\n\
+		.traceevent:hover {color:white;font-weight:bold;border:1px solid white;}\n\
 		.phase {position:absolute;overflow:hidden;border:0px;text-align:center;}\n\
 		.phaselet {position:absolute;overflow:hidden;border:0px;text-align:center;height:100px;font-size:24px;}\n\
-		.t {z-index:2;position:absolute;pointer-events:none;top:0%;height:100%;border-right:1px solid black;}\n\
+		.t {position:absolute;line-height:'+('%d'%scaleTH)+'px;pointer-events:none;top:0;height:100%;border-right:1px solid black;z-index:6;}\n\
+		.err {position:absolute;top:0%;height:100%;border-right:3px solid red;color:red;font:bold 14px Times;line-height:18px;}\n\
 		.legend {position:relative; width:100%; height:40px; text-align:center;margin-bottom:20px}\n\
 		.legend .square {position:absolute;cursor:pointer;top:10px; width:0px;height:20px;border:1px solid;padding-left:20px;}\n\
 		button {height:40px;width:200px;margin-bottom:20px;margin-top:20px;font-size:24px;}\n\
@@ -3327,7 +3643,8 @@ def createHTML(testruns):
 		a:active {color:white;}\n\
 		.version {position:relative;float:left;color:white;font-size:10px;line-height:30px;margin-left:10px;}\n\
 		#devicedetail {height:100px;box-shadow:5px 5px 20px black;}\n\
-		.tblock {position:absolute;height:100%;}\n\
+		.tblock {position:absolute;height:100%;background-color:#ddd;}\n\
+		.tback {position:absolute;width:100%;background:linear-gradient(#ccc, #ddd);}\n\
 		.bg {z-index:1;}\n\
 	</style>\n</head>\n<body>\n'
 
@@ -3342,6 +3659,8 @@ def createHTML(testruns):
 	# write the test title and general info header
 	if(sysvals.stamp['time'] != ""):
 		hf.write(headline_version)
+		if sysvals.logmsg:
+			hf.write('<button id="showtest" class="logbtn">log</button>')
 		if sysvals.addlogs and sysvals.dmesgfile:
 			hf.write('<button id="showdmesg" class="logbtn">dmesg</button>')
 		if sysvals.addlogs and sysvals.ftracefile:
@@ -3359,6 +3678,9 @@ def createHTML(testruns):
 	# draw the colored boxes for the device detail section
 	for data in testruns:
 		hf.write('<div id="devicedetail%d">\n' % data.testnumber)
+		pscolor = 'linear-gradient(to top left, #ccc, #eee)'
+		hf.write(html_phaselet.format('pre_suspend_process', \
+			'0', '0', pscolor))
 		for b in data.phases:
 			phase = data.dmesg[b]
 			length = phase['end']-phase['start']
@@ -3366,14 +3688,18 @@ def createHTML(testruns):
 			width = '%.3f' % ((length*100.0)/tTotal)
 			hf.write(html_phaselet.format(b, left, width, \
 				data.dmesg[b]['color']))
+		hf.write(html_phaselet.format('post_resume_process', \
+			'0', '0', pscolor))
 		if sysvals.suspendmode == 'command':
-			hf.write(html_phaselet.format('cmdexec', '0', '0', \
-				data.dmesg['resume_complete']['color']))
+			hf.write(html_phaselet.format('cmdexec', '0', '0', pscolor))
 		hf.write('</div>\n')
 	hf.write('</div>\n')
 
 	# write the ftrace data (callgraph)
-	data = testruns[-1]
+	if sysvals.cgtest >= 0 and len(testruns) > sysvals.cgtest:
+		data = testruns[sysvals.cgtest]
+	else:
+		data = testruns[-1]
 	if(sysvals.usecallgraph and not sysvals.embedded):
 		hf.write('<section id="callgraphs" class="callgraph">\n')
 		# write out the ftrace data converted to html
@@ -3383,6 +3709,8 @@ def createHTML(testruns):
 		html_func_leaf = '<article>{0} {1}</article>\n'
 		num = 0
 		for p in data.phases:
+			if sysvals.cgphase and p != sysvals.cgphase:
+				continue
 			list = data.dmesg[p]['list']
 			for devname in data.sortedDevices(p):
 				if('ftrace' not in list[devname]):
@@ -3420,11 +3748,15 @@ def createHTML(testruns):
 				hf.write(html_func_end)
 		hf.write('\n\n    </section>\n')
 
+	# add the test log as a hidden div
+	if sysvals.logmsg:
+		hf.write('<div id="testlog" style="display:none;">\n'+sysvals.logmsg+'</div>\n')
 	# add the dmesg log as a hidden div
 	if sysvals.addlogs and sysvals.dmesgfile:
 		hf.write('<div id="dmesglog" style="display:none;">\n')
 		lf = open(sysvals.dmesgfile, 'r')
 		for line in lf:
+			line = line.replace('<', '&lt').replace('>', '&gt')
 			hf.write(line)
 		lf.close()
 		hf.write('</div>\n')
@@ -3475,8 +3807,9 @@ def addScriptCode(hf, testruns):
 	script_code = \
 	'<script type="text/javascript">\n'+detail+\
 	'	var resolution = -1;\n'\
+	'	var dragval = [0, 0];\n'\
 	'	function redrawTimescale(t0, tMax, tS) {\n'\
-	'		var rline = \'<div class="t" style="left:0;border-left:1px solid black;border-right:0;"><cR><-R</cR></div>\';\n'\
+	'		var rline = \'<div class="t" style="left:0;border-left:1px solid black;border-right:0;"><cS>&larr;R</cS></div>\';\n'\
 	'		var tTotal = tMax - t0;\n'\
 	'		var list = document.getElementsByClassName("tblock");\n'\
 	'		for (var i = 0; i < list.length; i++) {\n'\
@@ -3501,7 +3834,7 @@ def addScriptCode(hf, testruns):
 	'					pos = 100 - (((j)*tS*100)/mTotal) - divEdge;\n'\
 	'					val = (j-divTotal+1)*tS;\n'\
 	'					if(j == divTotal - 1)\n'\
-	'						htmlline = \'<div class="t" style="right:\'+pos+\'%"><cS>S-></cS></div>\';\n'\
+	'						htmlline = \'<div class="t" style="right:\'+pos+\'%"><cS>S&rarr;</cS></div>\';\n'\
 	'					else\n'\
 	'						htmlline = \'<div class="t" style="right:\'+pos+\'%">\'+val+\'ms</div>\';\n'\
 	'				}\n'\
@@ -3513,6 +3846,7 @@ def addScriptCode(hf, testruns):
 	'	function zoomTimeline() {\n'\
 	'		var dmesg = document.getElementById("dmesg");\n'\
 	'		var zoombox = document.getElementById("dmesgzoombox");\n'\
+	'		var left = zoombox.scrollLeft;\n'\
 	'		var val = parseFloat(dmesg.style.width);\n'\
 	'		var newval = 100;\n'\
 	'		var sh = window.outerWidth / 2;\n'\
@@ -3520,12 +3854,12 @@ def addScriptCode(hf, testruns):
 	'			newval = val * 1.2;\n'\
 	'			if(newval > 910034) newval = 910034;\n'\
 	'			dmesg.style.width = newval+"%";\n'\
-	'			zoombox.scrollLeft = ((zoombox.scrollLeft + sh) * newval / val) - sh;\n'\
+	'			zoombox.scrollLeft = ((left + sh) * newval / val) - sh;\n'\
 	'		} else if (this.id == "zoomout") {\n'\
 	'			newval = val / 1.2;\n'\
 	'			if(newval < 100) newval = 100;\n'\
 	'			dmesg.style.width = newval+"%";\n'\
-	'			zoombox.scrollLeft = ((zoombox.scrollLeft + sh) * newval / val) - sh;\n'\
+	'			zoombox.scrollLeft = ((left + sh) * newval / val) - sh;\n'\
 	'		} else {\n'\
 	'			zoombox.scrollLeft = 0;\n'\
 	'			dmesg.style.width = "100%";\n'\
@@ -3542,8 +3876,12 @@ def addScriptCode(hf, testruns):
 	'		resolution = tS[i];\n'\
 	'		redrawTimescale(t0, tMax, tS[i]);\n'\
 	'	}\n'\
+	'	function deviceName(title) {\n'\
+	'		var name = title.slice(0, title.indexOf(" ("));\n'\
+	'		return name;\n'\
+	'	}\n'\
 	'	function deviceHover() {\n'\
-	'		var name = this.title.slice(0, this.title.indexOf(" ("));\n'\
+	'		var name = deviceName(this.title);\n'\
 	'		var dmesg = document.getElementById("dmesg");\n'\
 	'		var dev = dmesg.getElementsByClassName("thread");\n'\
 	'		var cpu = -1;\n'\
@@ -3552,7 +3890,7 @@ def addScriptCode(hf, testruns):
 	'		else if(name.match("CPU_OFF\[[0-9]*\]"))\n'\
 	'			cpu = parseInt(name.slice(8));\n'\
 	'		for (var i = 0; i < dev.length; i++) {\n'\
-	'			dname = dev[i].title.slice(0, dev[i].title.indexOf(" ("));\n'\
+	'			dname = deviceName(dev[i].title);\n'\
 	'			var cname = dev[i].className.slice(dev[i].className.indexOf("thread"));\n'\
 	'			if((cpu >= 0 && dname.match("CPU_O[NF]*\\\[*"+cpu+"\\\]")) ||\n'\
 	'				(name == dname))\n'\
@@ -3578,7 +3916,7 @@ def addScriptCode(hf, testruns):
 	'			total[2] = (total[2]+total[4])/2;\n'\
 	'		}\n'\
 	'		var devtitle = document.getElementById("devicedetailtitle");\n'\
-	'		var name = title.slice(0, title.indexOf(" ("));\n'\
+	'		var name = deviceName(title);\n'\
 	'		if(cpu >= 0) name = "CPU"+cpu;\n'\
 	'		var driver = "";\n'\
 	'		var tS = "<t2>(</t2>";\n'\
@@ -3600,7 +3938,7 @@ def addScriptCode(hf, testruns):
 	'	function deviceDetail() {\n'\
 	'		var devinfo = document.getElementById("devicedetail");\n'\
 	'		devinfo.style.display = "block";\n'\
-	'		var name = this.title.slice(0, this.title.indexOf(" ("));\n'\
+	'		var name = deviceName(this.title);\n'\
 	'		var cpu = -1;\n'\
 	'		if(name.match("CPU_ON\[[0-9]*\]"))\n'\
 	'			cpu = parseInt(name.slice(7));\n'\
@@ -3615,7 +3953,7 @@ def addScriptCode(hf, testruns):
 	'		var pd = pdata[0];\n'\
 	'		var total = [0.0, 0.0, 0.0];\n'\
 	'		for (var i = 0; i < dev.length; i++) {\n'\
-	'			dname = dev[i].title.slice(0, dev[i].title.indexOf(" ("));\n'\
+	'			dname = deviceName(dev[i].title);\n'\
 	'			if((cpu >= 0 && dname.match("CPU_O[NF]*\\\[*"+cpu+"\\\]")) ||\n'\
 	'				(name == dname))\n'\
 	'			{\n'\
@@ -3656,7 +3994,7 @@ def addScriptCode(hf, testruns):
 	'					phases[i].title = phases[i].id+" "+pd[phases[i].id]+" ms";\n'\
 	'					left += w;\n'\
 	'					var time = "<t4 style=\\"font-size:"+fs+"px\\">"+pd[phases[i].id]+" ms<br></t4>";\n'\
-	'					var pname = "<t3 style=\\"font-size:"+fs2+"px\\">"+phases[i].id.replace("_", " ")+"</t3>";\n'\
+	'					var pname = "<t3 style=\\"font-size:"+fs2+"px\\">"+phases[i].id.replace(new RegExp("_", "g"), " ")+"</t3>";\n'\
 	'					phases[i].innerHTML = time+pname;\n'\
 	'				} else {\n'\
 	'					phases[i].style.width = "0%";\n'\
@@ -3677,12 +4015,7 @@ def addScriptCode(hf, testruns):
 	'		}\n'\
 	'	}\n'\
 	'	function devListWindow(e) {\n'\
-	'		var sx = e.clientX;\n'\
-	'		if(sx > window.innerWidth - 440)\n'\
-	'			sx = window.innerWidth - 440;\n'\
-	'		var cfg="top="+e.screenY+", left="+sx+", width=440, height=720, scrollbars=yes";\n'\
-	'		var win = window.open("", "_blank", cfg);\n'\
-	'		if(window.chrome) win.moveBy(sx, 0);\n'\
+	'		var win = window.open();\n'\
 	'		var html = "<title>"+e.target.innerHTML+"</title>"+\n'\
 	'			"<style type=\\"text/css\\">"+\n'\
 	'			"   ul {list-style-type:circle;padding-left:10px;margin-left:10px;}"+\n'\
@@ -3692,6 +4025,12 @@ def addScriptCode(hf, testruns):
 	'			dt = devtable[1];\n'\
 	'		win.document.write(html+dt);\n'\
 	'	}\n'\
+	'	function errWindow() {\n'\
+	'		var text = this.id;\n'\
+	'		var win = window.open();\n'\
+	'		win.document.write("<pre>"+text+"</pre>");\n'\
+	'		win.document.close();\n'\
+	'	}\n'\
 	'	function logWindow(e) {\n'\
 	'		var name = e.target.id.slice(4);\n'\
 	'		var win = window.open();\n'\
@@ -3702,16 +4041,46 @@ def addScriptCode(hf, testruns):
 	'	}\n'\
 	'	function onClickPhase(e) {\n'\
 	'	}\n'\
+	'	function onMouseDown(e) {\n'\
+	'		dragval[0] = e.clientX;\n'\
+	'		dragval[1] = document.getElementById("dmesgzoombox").scrollLeft;\n'\
+	'		document.onmousemove = onMouseMove;\n'\
+	'	}\n'\
+	'	function onMouseMove(e) {\n'\
+	'		var zoombox = document.getElementById("dmesgzoombox");\n'\
+	'		zoombox.scrollLeft = dragval[1] + dragval[0] - e.clientX;\n'\
+	'	}\n'\
+	'	function onMouseUp(e) {\n'\
+	'		document.onmousemove = null;\n'\
+	'	}\n'\
+	'	function onKeyPress(e) {\n'\
+	'		var c = e.charCode;\n'\
+	'		if(c != 42 && c != 43 && c != 45) return;\n'\
+	'		var click = document.createEvent("Events");\n'\
+	'		click.initEvent("click", true, false);\n'\
+	'		if(c == 43)  \n'\
+	'			document.getElementById("zoomin").dispatchEvent(click);\n'\
+	'		else if(c == 45)\n'\
+	'			document.getElementById("zoomout").dispatchEvent(click);\n'\
+	'		else if(c == 42)\n'\
+	'			document.getElementById("zoomdef").dispatchEvent(click);\n'\
+	'	}\n'\
 	'	window.addEventListener("resize", function () {zoomTimeline();});\n'\
 	'	window.addEventListener("load", function () {\n'\
 	'		var dmesg = document.getElementById("dmesg");\n'\
 	'		dmesg.style.width = "100%"\n'\
+	'		dmesg.onmousedown = onMouseDown;\n'\
+	'		document.onmouseup = onMouseUp;\n'\
+	'		document.onkeypress = onKeyPress;\n'\
 	'		document.getElementById("zoomin").onclick = zoomTimeline;\n'\
 	'		document.getElementById("zoomout").onclick = zoomTimeline;\n'\
 	'		document.getElementById("zoomdef").onclick = zoomTimeline;\n'\
 	'		var list = document.getElementsByClassName("square");\n'\
 	'		for (var i = 0; i < list.length; i++)\n'\
 	'			list[i].onclick = onClickPhase;\n'\
+	'		var list = document.getElementsByClassName("err");\n'\
+	'		for (var i = 0; i < list.length; i++)\n'\
+	'			list[i].onclick = errWindow;\n'\
 	'		var list = document.getElementsByClassName("logbtn");\n'\
 	'		for (var i = 0; i < list.length; i++)\n'\
 	'			list[i].onclick = logWindow;\n'\
@@ -3734,9 +4103,7 @@ def addScriptCode(hf, testruns):
 #	 Execute system suspend through the sysfs interface, then copy the output
 #	 dmesg and ftrace files to the test output directory.
 def executeSuspend():
-	global sysvals
-
-	t0 = time.time()*1000
+	pm = ProcessMonitor()
 	tp = sysvals.tpath
 	fwdata = []
 	# mark the start point in the kernel ring buffer just as we start
@@ -3745,30 +4112,39 @@ def executeSuspend():
 	if(sysvals.usecallgraph or sysvals.usetraceevents):
 		print('START TRACING')
 		sysvals.fsetVal('1', 'tracing_on')
+		if sysvals.useprocmon:
+			pm.start()
 	# execute however many s/r runs requested
 	for count in range(1,sysvals.execcount+1):
-		# if this is test2 and there's a delay, start here
+		# x2delay in between test runs
 		if(count > 1 and sysvals.x2delay > 0):
-			tN = time.time()*1000
-			while (tN - t0) < sysvals.x2delay:
-				tN = time.time()*1000
-				time.sleep(0.001)
-		# initiate suspend
-		if(sysvals.usecallgraph or sysvals.usetraceevents):
-			sysvals.fsetVal('SUSPEND START', 'trace_marker')
-		if sysvals.suspendmode == 'command':
+			sysvals.fsetVal('WAIT %d' % sysvals.x2delay, 'trace_marker')
+			time.sleep(sysvals.x2delay/1000.0)
+			sysvals.fsetVal('WAIT END', 'trace_marker')
+		# start message
+		if sysvals.testcommand != '':
 			print('COMMAND START')
-			if(sysvals.rtcwake):
-				print('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime)
-				sysvals.rtcWakeAlarmOn()
-			os.system(sysvals.testcommand)
 		else:
 			if(sysvals.rtcwake):
 				print('SUSPEND START')
-				print('will autoresume in %d seconds' % sysvals.rtcwaketime)
-				sysvals.rtcWakeAlarmOn()
 			else:
 				print('SUSPEND START (press a key to resume)')
+		# set rtcwake
+		if(sysvals.rtcwake):
+			print('will issue an rtcwake in %d seconds' % sysvals.rtcwaketime)
+			sysvals.rtcWakeAlarmOn()
+		# start of suspend trace marker
+		if(sysvals.usecallgraph or sysvals.usetraceevents):
+			sysvals.fsetVal('SUSPEND START', 'trace_marker')
+		# predelay delay
+		if(count == 1 and sysvals.predelay > 0):
+			sysvals.fsetVal('WAIT %d' % sysvals.predelay, 'trace_marker')
+			time.sleep(sysvals.predelay/1000.0)
+			sysvals.fsetVal('WAIT END', 'trace_marker')
+		# initiate suspend or command
+		if sysvals.testcommand != '':
+			call(sysvals.testcommand+' 2>&1', shell=True);
+		else:
 			pf = open(sysvals.powerfile, 'w')
 			pf.write(sysvals.suspendmode)
 			# execution will pause here
@@ -3776,26 +4152,27 @@ def executeSuspend():
 				pf.close()
 			except:
 				pass
-		t0 = time.time()*1000
 		if(sysvals.rtcwake):
 			sysvals.rtcWakeAlarmOff()
+		# postdelay delay
+		if(count == sysvals.execcount and sysvals.postdelay > 0):
+			sysvals.fsetVal('WAIT %d' % sysvals.postdelay, 'trace_marker')
+			time.sleep(sysvals.postdelay/1000.0)
+			sysvals.fsetVal('WAIT END', 'trace_marker')
 		# return from suspend
 		print('RESUME COMPLETE')
 		if(sysvals.usecallgraph or sysvals.usetraceevents):
 			sysvals.fsetVal('RESUME COMPLETE', 'trace_marker')
-		if(sysvals.suspendmode == 'mem'):
+		if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'):
 			fwdata.append(getFPDT(False))
-	# look for post resume events after the last test run
-	t = sysvals.postresumetime
-	if(t > 0):
-		print('Waiting %d seconds for POST-RESUME trace events...' % t)
-		time.sleep(t)
 	# stop ftrace
 	if(sysvals.usecallgraph or sysvals.usetraceevents):
+		if sysvals.useprocmon:
+			pm.stop()
 		sysvals.fsetVal('0', 'tracing_on')
 		print('CAPTURING TRACE')
 		writeDatafileHeader(sysvals.ftracefile, fwdata)
-		os.system('cat '+tp+'trace >> '+sysvals.ftracefile)
+		call('cat '+tp+'trace >> '+sysvals.ftracefile, shell=True)
 		sysvals.fsetVal('', 'trace')
 		devProps()
 	# grab a copy of the dmesg output
@@ -3804,17 +4181,12 @@ def executeSuspend():
 	sysvals.getdmesg()
 
 def writeDatafileHeader(filename, fwdata):
-	global sysvals
-
-	prt = sysvals.postresumetime
 	fp = open(filename, 'a')
 	fp.write(sysvals.teststamp+'\n')
-	if(sysvals.suspendmode == 'mem'):
+	if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'):
 		for fw in fwdata:
 			if(fw):
 				fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1]))
-	if(prt > 0):
-		fp.write('# post resume time %u\n' % prt)
 	fp.close()
 
 # Function: setUSBDevicesAuto
@@ -3824,18 +4196,16 @@ def writeDatafileHeader(filename, fwdata):
 #	 to always-on since the kernel cant determine if the device can
 #	 properly autosuspend
 def setUSBDevicesAuto():
-	global sysvals
-
 	rootCheck(True)
 	for dirname, dirnames, filenames in os.walk('/sys/devices'):
 		if(re.match('.*/usb[0-9]*.*', dirname) and
 			'idVendor' in filenames and 'idProduct' in filenames):
-			os.system('echo auto > %s/power/control' % dirname)
+			call('echo auto > %s/power/control' % dirname, shell=True)
 			name = dirname.split('/')[-1]
-			desc = os.popen('cat %s/product 2>/dev/null' % \
-				dirname).read().replace('\n', '')
-			ctrl = os.popen('cat %s/power/control 2>/dev/null' % \
-				dirname).read().replace('\n', '')
+			desc = Popen(['cat', '%s/product' % dirname],
+				stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '')
+			ctrl = Popen(['cat', '%s/power/control' % dirname],
+				stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '')
 			print('control is %s for %6s: %s' % (ctrl, name, desc))
 
 # Function: yesno
@@ -3872,8 +4242,6 @@ def ms2nice(val):
 #	 Detect all the USB hosts and devices currently connected and add
 #	 a list of USB device names to sysvals for better timeline readability
 def detectUSB():
-	global sysvals
-
 	field = {'idVendor':'', 'idProduct':'', 'product':'', 'speed':''}
 	power = {'async':'', 'autosuspend':'', 'autosuspend_delay_ms':'',
 			 'control':'', 'persist':'', 'runtime_enabled':'',
@@ -3899,12 +4267,12 @@ def detectUSB():
 		if(re.match('.*/usb[0-9]*.*', dirname) and
 			'idVendor' in filenames and 'idProduct' in filenames):
 			for i in field:
-				field[i] = os.popen('cat %s/%s 2>/dev/null' % \
-					(dirname, i)).read().replace('\n', '')
+				field[i] = Popen(['cat', '%s/%s' % (dirname, i)],
+					stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '')
 			name = dirname.split('/')[-1]
 			for i in power:
-				power[i] = os.popen('cat %s/power/%s 2>/dev/null' % \
-					(dirname, i)).read().replace('\n', '')
+				power[i] = Popen(['cat', '%s/power/%s' % (dirname, i)],
+					stderr=PIPE, stdout=PIPE).stdout.read().replace('\n', '')
 			if(re.match('usb[0-9]*', name)):
 				first = '%-8s' % name
 			else:
@@ -3928,7 +4296,6 @@ def detectUSB():
 # Description:
 #	 Retrieve a list of properties for all devices in the trace log
 def devProps(data=0):
-	global sysvals
 	props = dict()
 
 	if data:
@@ -3953,7 +4320,7 @@ def devProps(data=0):
 		return
 
 	if(os.path.exists(sysvals.ftracefile) == False):
-		doError('%s does not exist' % sysvals.ftracefile, False)
+		doError('%s does not exist' % sysvals.ftracefile)
 
 	# first get the list of devices we need properties for
 	msghead = 'Additional data added by AnalyzeSuspend'
@@ -3976,7 +4343,7 @@ def devProps(data=0):
 		m = re.match('.*: (?P<drv>.*) (?P<d>.*), parent: *(?P<p>.*), .*', m.group('msg'));
 		if(not m):
 			continue
-		drv, dev, par = m.group('drv'), m.group('d'), m.group('p')
+		dev = m.group('d')
 		if dev not in props:
 			props[dev] = DevProps()
 	tf.close()
@@ -4052,7 +4419,6 @@ def devProps(data=0):
 # Output:
 #	 A string list of the available modes
 def getModes():
-	global sysvals
 	modes = ''
 	if(os.path.exists(sysvals.powerfile)):
 		fp = open(sysvals.powerfile, 'r')
@@ -4066,8 +4432,6 @@ def getModes():
 # Arguments:
 #	 output: True to output the info to stdout, False otherwise
 def getFPDT(output):
-	global sysvals
-
 	rectype = {}
 	rectype[0] = 'Firmware Basic Boot Performance Record'
 	rectype[1] = 'S3 Performance Table Record'
@@ -4078,19 +4442,19 @@ def getFPDT(output):
 	rootCheck(True)
 	if(not os.path.exists(sysvals.fpdtpath)):
 		if(output):
-			doError('file does not exist: %s' % sysvals.fpdtpath, False)
+			doError('file does not exist: %s' % sysvals.fpdtpath)
 		return False
 	if(not os.access(sysvals.fpdtpath, os.R_OK)):
 		if(output):
-			doError('file is not readable: %s' % sysvals.fpdtpath, False)
+			doError('file is not readable: %s' % sysvals.fpdtpath)
 		return False
 	if(not os.path.exists(sysvals.mempath)):
 		if(output):
-			doError('file does not exist: %s' % sysvals.mempath, False)
+			doError('file does not exist: %s' % sysvals.mempath)
 		return False
 	if(not os.access(sysvals.mempath, os.R_OK)):
 		if(output):
-			doError('file is not readable: %s' % sysvals.mempath, False)
+			doError('file is not readable: %s' % sysvals.mempath)
 		return False
 
 	fp = open(sysvals.fpdtpath, 'rb')
@@ -4100,7 +4464,7 @@ def getFPDT(output):
 	if(len(buf) < 36):
 		if(output):
 			doError('Invalid FPDT table data, should '+\
-				'be at least 36 bytes', False)
+				'be at least 36 bytes')
 		return False
 
 	table = struct.unpack('4sIBB6s8sI4sI', buf[0:36])
@@ -4199,7 +4563,6 @@ def getFPDT(output):
 # Output:
 #	 True if the test will work, False if not
 def statusCheck(probecheck=False):
-	global sysvals
 	status = True
 
 	print('Checking this system (%s)...' % platform.node())
@@ -4282,37 +4645,14 @@ def statusCheck(probecheck=False):
 	if not probecheck:
 		return status
 
-	if (sysvals.usecallgraph and len(sysvals.debugfuncs) > 0) or len(sysvals.kprobes) > 0:
-		sysvals.initFtrace(True)
-
-	# verify callgraph debugfuncs
-	if sysvals.usecallgraph and len(sysvals.debugfuncs) > 0:
-		print('    verifying these ftrace callgraph functions work:')
-		sysvals.setFtraceFilterFunctions(sysvals.debugfuncs)
-		fp = open(sysvals.tpath+'set_graph_function', 'r')
-		flist = fp.read().split('\n')
-		fp.close()
-		for func in sysvals.debugfuncs:
-			res = sysvals.colorText('NO')
-			if func in flist:
-				res = 'YES'
-			else:
-				for i in flist:
-					if ' [' in i and func == i.split(' ')[0]:
-						res = 'YES'
-						break
-			print('         %s: %s' % (func, res))
-
 	# verify kprobes
-	if len(sysvals.kprobes) > 0:
-		print('    verifying these kprobes work:')
-		for name in sorted(sysvals.kprobes):
-			if name in sysvals.tracefuncs:
-				continue
-			res = sysvals.colorText('NO')
-			if sysvals.testKprobe(sysvals.kprobes[name]):
-				res = 'YES'
-			print('         %s: %s' % (name, res))
+	if sysvals.usekprobes:
+		for name in sysvals.tracefuncs:
+			sysvals.defaultKprobe(name, sysvals.tracefuncs[name])
+		if sysvals.usedevsrc:
+			for name in sysvals.dev_tracefuncs:
+				sysvals.defaultKprobe(name, sysvals.dev_tracefuncs[name])
+		sysvals.addKprobes(True)
 
 	return status
 
@@ -4322,33 +4662,20 @@ def statusCheck(probecheck=False):
 # Arguments:
 #	 msg: the error message to print
 #	 help: True if printHelp should be called after, False otherwise
-def doError(msg, help):
+def doError(msg, help=False):
 	if(help == True):
 		printHelp()
 	print('ERROR: %s\n') % msg
 	sys.exit()
 
-# Function: doWarning
-# Description:
-#	 generic warning function for non-catastrophic anomalies
-# Arguments:
-#	 msg: the warning message to print
-#	 file: If not empty, a filename to request be sent to the owner for debug
-def doWarning(msg, file=''):
-	print('/* %s */') % msg
-	if(file):
-		print('/* For a fix, please send this'+\
-			' %s file to <todd.e.brandt@intel.com> */' % file)
-
 # Function: rootCheck
 # Description:
 #	 quick check to see if we have root access
 def rootCheck(fatal):
-	global sysvals
 	if(os.access(sysvals.powerfile, os.W_OK)):
 		return True
 	if fatal:
-		doError('This command must be run as root', False)
+		doError('This command must be run as root')
 	return False
 
 # Function: getArgInt
@@ -4389,71 +4716,61 @@ def getArgFloat(name, args, min, max, main=True):
 		doError(name+': value should be between %f and %f' % (min, max), True)
 	return val
 
-# Function: rerunTest
-# Description:
-#	 generate an output from an existing set of ftrace/dmesg logs
-def rerunTest():
-	global sysvals
-
-	if(sysvals.ftracefile != ''):
-		doesTraceLogHaveTraceEvents()
-	if(sysvals.dmesgfile == '' and not sysvals.usetraceeventsonly):
-		doError('recreating this html output '+\
-			'requires a dmesg file', False)
-	sysvals.setOutputFile()
-	vprint('Output file: %s' % sysvals.htmlfile)
+def processData():
 	print('PROCESSING DATA')
 	if(sysvals.usetraceeventsonly):
 		testruns = parseTraceLog()
+		if sysvals.dmesgfile:
+			dmesgtext = loadKernelLog(True)
+			for data in testruns:
+				data.extractErrorInfo(dmesgtext)
 	else:
 		testruns = loadKernelLog()
 		for data in testruns:
 			parseKernelLog(data)
-		if(sysvals.ftracefile != ''):
+		if(sysvals.ftracefile and (sysvals.usecallgraph or sysvals.usetraceevents)):
 			appendIncompleteTraceLog(testruns)
 	createHTML(testruns)
 
+# Function: rerunTest
+# Description:
+#	 generate an output from an existing set of ftrace/dmesg logs
+def rerunTest():
+	if sysvals.ftracefile:
+		doesTraceLogHaveTraceEvents()
+	if not sysvals.dmesgfile and not sysvals.usetraceeventsonly:
+		doError('recreating this html output requires a dmesg file')
+	sysvals.setOutputFile()
+	vprint('Output file: %s' % sysvals.htmlfile)
+	if(os.path.exists(sysvals.htmlfile) and not os.access(sysvals.htmlfile, os.W_OK)):
+		doError('missing permission to write to %s' % sysvals.htmlfile)
+	processData()
+
 # Function: runTest
 # Description:
 #	 execute a suspend/resume, gather the logs, and generate the output
 def runTest(subdir, testpath=''):
-	global sysvals
-
 	# prepare for the test
 	sysvals.initFtrace()
 	sysvals.initTestOutput(subdir, testpath)
-
-	vprint('Output files:\n    %s' % sysvals.dmesgfile)
-	if(sysvals.usecallgraph or
-		sysvals.usetraceevents or
-		sysvals.usetraceeventsonly):
-		vprint('    %s' % sysvals.ftracefile)
-	vprint('    %s' % sysvals.htmlfile)
+	vprint('Output files:\n\t%s\n\t%s\n\t%s' % \
+		(sysvals.dmesgfile, sysvals.ftracefile, sysvals.htmlfile))
 
 	# execute the test
 	executeSuspend()
 	sysvals.cleanupFtrace()
+	processData()
 
-	# analyze the data and create the html output
-	print('PROCESSING DATA')
-	if(sysvals.usetraceeventsonly):
-		# data for kernels 3.15 or newer is entirely in ftrace
-		testruns = parseTraceLog()
-	else:
-		# data for kernels older than 3.15 is primarily in dmesg
-		testruns = loadKernelLog()
-		for data in testruns:
-			parseKernelLog(data)
-		if(sysvals.usecallgraph or sysvals.usetraceevents):
-			appendIncompleteTraceLog(testruns)
-	createHTML(testruns)
+	# if running as root, change output dir owner to sudo_user
+	if os.path.isdir(sysvals.testdir) and os.getuid() == 0 and \
+		'SUDO_USER' in os.environ:
+		cmd = 'chown -R {0}:{0} {1} > /dev/null 2>&1'
+		call(cmd.format(os.environ['SUDO_USER'], sysvals.testdir), shell=True)
 
 # Function: runSummary
 # Description:
 #	 create a summary of tests in a sub-directory
 def runSummary(subdir, output):
-	global sysvals
-
 	# get a list of ftrace output files
 	files = []
 	for dirname, dirnames, filenames in os.walk(subdir):
@@ -4509,12 +4826,12 @@ def checkArgBool(value):
 # Description:
 #	 Configure the script via the info in a config file
 def configFromFile(file):
-	global sysvals
 	Config = ConfigParser.ConfigParser()
 
-	ignorekprobes = False
 	Config.read(file)
 	sections = Config.sections()
+	overridekprobes = False
+	overridedevkprobes = False
 	if 'Settings' in sections:
 		for opt in Config.options('Settings'):
 			value = Config.get('Settings', opt).lower()
@@ -4524,19 +4841,19 @@ def configFromFile(file):
 				sysvals.addlogs = checkArgBool(value)
 			elif(opt.lower() == 'dev'):
 				sysvals.usedevsrc = checkArgBool(value)
-			elif(opt.lower() == 'ignorekprobes'):
-				ignorekprobes = checkArgBool(value)
+			elif(opt.lower() == 'proc'):
+				sysvals.useprocmon = checkArgBool(value)
 			elif(opt.lower() == 'x2'):
 				if checkArgBool(value):
 					sysvals.execcount = 2
 			elif(opt.lower() == 'callgraph'):
 				sysvals.usecallgraph = checkArgBool(value)
-			elif(opt.lower() == 'callgraphfunc'):
-				sysvals.debugfuncs = []
-				if value:
-					value = value.split(',')
-				for i in value:
-					sysvals.debugfuncs.append(i.strip())
+			elif(opt.lower() == 'override-timeline-functions'):
+				overridekprobes = checkArgBool(value)
+			elif(opt.lower() == 'override-dev-timeline-functions'):
+				overridedevkprobes = checkArgBool(value)
+			elif(opt.lower() == 'devicefilter'):
+				sysvals.setDeviceFilter(value)
 			elif(opt.lower() == 'expandcg'):
 				sysvals.cgexp = checkArgBool(value)
 			elif(opt.lower() == 'srgap'):
@@ -4548,8 +4865,10 @@ def configFromFile(file):
 				sysvals.testcommand = value
 			elif(opt.lower() == 'x2delay'):
 				sysvals.x2delay = getArgInt('-x2delay', value, 0, 60000, False)
-			elif(opt.lower() == 'postres'):
-				sysvals.postresumetime = getArgInt('-postres', value, 0, 3600, False)
+			elif(opt.lower() == 'predelay'):
+				sysvals.predelay = getArgInt('-predelay', value, 0, 60000, False)
+			elif(opt.lower() == 'postdelay'):
+				sysvals.postdelay = getArgInt('-postdelay', value, 0, 60000, False)
 			elif(opt.lower() == 'rtcwake'):
 				sysvals.rtcwake = True
 				sysvals.rtcwaketime = getArgInt('-rtcwake', value, 0, 3600, False)
@@ -4557,53 +4876,50 @@ def configFromFile(file):
 				sysvals.setPrecision(getArgInt('-timeprec', value, 0, 6, False))
 			elif(opt.lower() == 'mindev'):
 				sysvals.mindevlen = getArgFloat('-mindev', value, 0.0, 10000.0, False)
+			elif(opt.lower() == 'callloop-maxgap'):
+				sysvals.callloopmaxgap = getArgFloat('-callloop-maxgap', value, 0.0, 1.0, False)
+			elif(opt.lower() == 'callloop-maxlen'):
+				sysvals.callloopmaxgap = getArgFloat('-callloop-maxlen', value, 0.0, 1.0, False)
 			elif(opt.lower() == 'mincg'):
 				sysvals.mincglen = getArgFloat('-mincg', value, 0.0, 10000.0, False)
-			elif(opt.lower() == 'kprobecolor'):
-				try:
-					val = int(value, 16)
-					sysvals.kprobecolor = '#'+value
-				except:
-					sysvals.kprobecolor = value
-			elif(opt.lower() == 'synccolor'):
-				try:
-					val = int(value, 16)
-					sysvals.synccolor = '#'+value
-				except:
-					sysvals.synccolor = value
 			elif(opt.lower() == 'output-dir'):
-				args = dict()
-				n = datetime.now()
-				args['date'] = n.strftime('%y%m%d')
-				args['time'] = n.strftime('%H%M%S')
-				args['hostname'] = sysvals.hostname
-				sysvals.outdir = value.format(**args)
+				sysvals.setOutputFolder(value)
 
 	if sysvals.suspendmode == 'command' and not sysvals.testcommand:
-		doError('No command supplied for mode "command"', False)
+		doError('No command supplied for mode "command"')
+
+	# compatibility errors
 	if sysvals.usedevsrc and sysvals.usecallgraph:
-		doError('dev and callgraph cannot both be true', False)
-	if sysvals.usecallgraph and sysvals.execcount > 1:
-		doError('-x2 is not compatible with -f', False)
+		doError('-dev is not compatible with -f')
+	if sysvals.usecallgraph and sysvals.useprocmon:
+		doError('-proc is not compatible with -f')
 
-	if ignorekprobes:
-		return
+	if overridekprobes:
+		sysvals.tracefuncs = dict()
+	if overridedevkprobes:
+		sysvals.dev_tracefuncs = dict()
 
 	kprobes = dict()
-	archkprobe = 'Kprobe_'+platform.machine()
-	if archkprobe in sections:
-		for name in Config.options(archkprobe):
-			kprobes[name] = Config.get(archkprobe, name)
-	if 'Kprobe' in sections:
-		for name in Config.options('Kprobe'):
-			kprobes[name] = Config.get('Kprobe', name)
+	kprobesec = 'dev_timeline_functions_'+platform.machine()
+	if kprobesec in sections:
+		for name in Config.options(kprobesec):
+			text = Config.get(kprobesec, name)
+			kprobes[name] = (text, True)
+	kprobesec = 'timeline_functions_'+platform.machine()
+	if kprobesec in sections:
+		for name in Config.options(kprobesec):
+			if name in kprobes:
+				doError('Duplicate timeline function found "%s"' % (name))
+			text = Config.get(kprobesec, name)
+			kprobes[name] = (text, False)
 
 	for name in kprobes:
 		function = name
 		format = name
 		color = ''
 		args = dict()
-		data = kprobes[name].split()
+		text, dev = kprobes[name]
+		data = text.split()
 		i = 0
 		for val in data:
 			# bracketted strings are special formatting, read them separately
@@ -4626,28 +4942,30 @@ def configFromFile(file):
 				args[d[0]] = d[1]
 			i += 1
 		if not function or not format:
-			doError('Invalid kprobe: %s' % name, False)
+			doError('Invalid kprobe: %s' % name)
 		for arg in re.findall('{(?P<n>[a-z,A-Z,0-9]*)}', format):
 			if arg not in args:
-				doError('Kprobe "%s" is missing argument "%s"' % (name, arg), False)
-		if name in sysvals.kprobes:
-			doError('Duplicate kprobe found "%s"' % (name), False)
-		vprint('Adding KPROBE: %s %s %s %s' % (name, function, format, args))
-		sysvals.kprobes[name] = {
+				doError('Kprobe "%s" is missing argument "%s"' % (name, arg))
+		if (dev and name in sysvals.dev_tracefuncs) or (not dev and name in sysvals.tracefuncs):
+			doError('Duplicate timeline function found "%s"' % (name))
+
+		kp = {
 			'name': name,
 			'func': function,
 			'format': format,
-			'args': args,
-			'mask': re.sub('{(?P<n>[a-z,A-Z,0-9]*)}', '.*', format)
+			sysvals.archargs: args
 		}
 		if color:
-			sysvals.kprobes[name]['color'] = color
+			kp['color'] = color
+		if dev:
+			sysvals.dev_tracefuncs[name] = kp
+		else:
+			sysvals.tracefuncs[name] = kp
 
 # Function: printHelp
 # Description:
 #	 print out the help text
 def printHelp():
-	global sysvals
 	modes = getModes()
 
 	print('')
@@ -4670,44 +4988,47 @@ def printHelp():
 	print('')
 	print('Options:')
 	print('  [general]')
-	print('    -h          Print this help text')
-	print('    -v          Print the current tool version')
-	print('    -config file Pull arguments and config options from a file')
-	print('    -verbose    Print extra information during execution and analysis')
-	print('    -status     Test to see if the system is enabled to run this tool')
-	print('    -modes      List available suspend modes')
-	print('    -m mode     Mode to initiate for suspend %s (default: %s)') % (modes, sysvals.suspendmode)
-	print('    -o subdir   Override the output subdirectory')
+	print('   -h           Print this help text')
+	print('   -v           Print the current tool version')
+	print('   -config fn   Pull arguments and config options from file fn')
+	print('   -verbose     Print extra information during execution and analysis')
+	print('   -status      Test to see if the system is enabled to run this tool')
+	print('   -modes       List available suspend modes')
+	print('   -m mode      Mode to initiate for suspend %s (default: %s)') % (modes, sysvals.suspendmode)
+	print('   -o subdir    Override the output subdirectory')
+	print('   -rtcwake t   Use rtcwake to autoresume after <t> seconds (default: disabled)')
+	print('   -addlogs     Add the dmesg and ftrace logs to the html output')
+	print('   -srgap       Add a visible gap in the timeline between sus/res (default: disabled)')
 	print('  [advanced]')
-	print('    -rtcwake t  Use rtcwake to autoresume after <t> seconds (default: disabled)')
-	print('    -addlogs    Add the dmesg and ftrace logs to the html output')
-	print('    -multi n d  Execute <n> consecutive tests at <d> seconds intervals. The outputs will')
+	print('   -cmd {s}     Run the timeline over a custom command, e.g. "sync -d"')
+	print('   -proc        Add usermode process info into the timeline (default: disabled)')
+	print('   -dev         Add kernel function calls and threads to the timeline (default: disabled)')
+	print('   -x2          Run two suspend/resumes back to back (default: disabled)')
+	print('   -x2delay t   Include t ms delay between multiple test runs (default: 0 ms)')
+	print('   -predelay t  Include t ms delay before 1st suspend (default: 0 ms)')
+	print('   -postdelay t Include t ms delay after last resume (default: 0 ms)')
+	print('   -mindev ms   Discard all device blocks shorter than ms milliseconds (e.g. 0.001 for us)')
+	print('   -multi n d   Execute <n> consecutive tests at <d> seconds intervals. The outputs will')
 	print('                be created in a new subdirectory with a summary page.')
-	print('    -srgap      Add a visible gap in the timeline between sus/res (default: disabled)')
-	print('    -cmd {s}    Instead of suspend/resume, run a command, e.g. "sync -d"')
-	print('    -mindev ms  Discard all device blocks shorter than ms milliseconds (e.g. 0.001 for us)')
-	print('    -mincg  ms  Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
-	print('    -timeprec N Number of significant digits in timestamps (0:S, [3:ms], 6:us)')
 	print('  [debug]')
-	print('    -f          Use ftrace to create device callgraphs (default: disabled)')
-	print('    -expandcg   pre-expand the callgraph data in the html output (default: disabled)')
-	print('    -flist      Print the list of functions currently being captured in ftrace')
-	print('    -flistall   Print all functions capable of being captured in ftrace')
-	print('    -fadd file  Add functions to be graphed in the timeline from a list in a text file')
-	print('    -filter "d1 d2 ..." Filter out all but this list of device names')
-	print('    -dev        Display common low level functions in the timeline')
-	print('  [post-resume task analysis]')
-	print('    -x2         Run two suspend/resumes back to back (default: disabled)')
-	print('    -x2delay t  Minimum millisecond delay <t> between the two test runs (default: 0 ms)')
-	print('    -postres t  Time after resume completion to wait for post-resume events (default: 0 S)')
+	print('   -f           Use ftrace to create device callgraphs (default: disabled)')
+	print('   -expandcg    pre-expand the callgraph data in the html output (default: disabled)')
+	print('   -flist       Print the list of functions currently being captured in ftrace')
+	print('   -flistall    Print all functions capable of being captured in ftrace')
+	print('   -fadd file   Add functions to be graphed in the timeline from a list in a text file')
+	print('   -filter "d1,d2,..." Filter out all but this comma-delimited list of device names')
+	print('   -mincg  ms   Discard all callgraphs shorter than ms milliseconds (e.g. 0.001 for us)')
+	print('   -cgphase P   Only show callgraph data for phase P (e.g. suspend_late)')
+	print('   -cgtest N    Only show callgraph data for test N (e.g. 0 or 1 in an x2 run)')
+	print('   -timeprec N  Number of significant digits in timestamps (0:S, [3:ms], 6:us)')
 	print('  [utilities]')
-	print('    -fpdt       Print out the contents of the ACPI Firmware Performance Data Table')
-	print('    -usbtopo    Print out the current USB topology with power info')
-	print('    -usbauto    Enable autosuspend for all connected USB devices')
+	print('   -fpdt        Print out the contents of the ACPI Firmware Performance Data Table')
+	print('   -usbtopo     Print out the current USB topology with power info')
+	print('   -usbauto     Enable autosuspend for all connected USB devices')
 	print('  [re-analyze data from previous runs]')
-	print('    -ftrace ftracefile  Create HTML output using ftrace input')
-	print('    -dmesg dmesgfile    Create HTML output using dmesg (not needed for kernel >= 3.15)')
-	print('    -summary directory  Create a summary of all test in this dir')
+	print('   -ftrace ftracefile  Create HTML output using ftrace input')
+	print('   -dmesg dmesgfile    Create HTML output using dmesg (not needed for kernel >= 3.15)')
+	print('   -summary directory  Create a summary of all test in this dir')
 	print('')
 	return True
 
@@ -4739,26 +5060,22 @@ if __name__ == '__main__':
 			sys.exit()
 		elif(arg == '-x2'):
 			sysvals.execcount = 2
-			if(sysvals.usecallgraph):
-				doError('-x2 is not compatible with -f', False)
 		elif(arg == '-x2delay'):
 			sysvals.x2delay = getArgInt('-x2delay', args, 0, 60000)
-		elif(arg == '-postres'):
-			sysvals.postresumetime = getArgInt('-postres', args, 0, 3600)
+		elif(arg == '-predelay'):
+			sysvals.predelay = getArgInt('-predelay', args, 0, 60000)
+		elif(arg == '-postdelay'):
+			sysvals.postdelay = getArgInt('-postdelay', args, 0, 60000)
 		elif(arg == '-f'):
 			sysvals.usecallgraph = True
-			if(sysvals.execcount > 1):
-				doError('-x2 is not compatible with -f', False)
-			if(sysvals.usedevsrc):
-				doError('-dev is not compatible with -f', False)
 		elif(arg == '-addlogs'):
 			sysvals.addlogs = True
 		elif(arg == '-verbose'):
 			sysvals.verbose = True
+		elif(arg == '-proc'):
+			sysvals.useprocmon = True
 		elif(arg == '-dev'):
 			sysvals.usedevsrc = True
-			if(sysvals.usecallgraph):
-				doError('-dev is not compatible with -f', False)
 		elif(arg == '-rtcwake'):
 			sysvals.rtcwake = True
 			sysvals.rtcwaketime = getArgInt('-rtcwake', args, 0, 3600)
@@ -4768,6 +5085,21 @@ if __name__ == '__main__':
 			sysvals.mindevlen = getArgFloat('-mindev', args, 0.0, 10000.0)
 		elif(arg == '-mincg'):
 			sysvals.mincglen = getArgFloat('-mincg', args, 0.0, 10000.0)
+		elif(arg == '-cgtest'):
+			sysvals.cgtest = getArgInt('-cgtest', args, 0, 1)
+		elif(arg == '-cgphase'):
+			try:
+				val = args.next()
+			except:
+				doError('No phase name supplied', True)
+			d = Data(0)
+			if val not in d.phases:
+				doError('Invalid phase, valid phaess are %s' % d.phases, True)
+			sysvals.cgphase = val
+		elif(arg == '-callloop-maxgap'):
+			sysvals.callloopmaxgap = getArgFloat('-callloop-maxgap', args, 0.0, 1.0)
+		elif(arg == '-callloop-maxlen'):
+			sysvals.callloopmaxlen = getArgFloat('-callloop-maxlen', args, 0.0, 1.0)
 		elif(arg == '-cmd'):
 			try:
 				val = args.next()
@@ -4788,14 +5120,14 @@ if __name__ == '__main__':
 				val = args.next()
 			except:
 				doError('No subdirectory name supplied', True)
-			sysvals.outdir = val
+			sysvals.setOutputFolder(val)
 		elif(arg == '-config'):
 			try:
 				val = args.next()
 			except:
 				doError('No text file supplied', True)
 			if(os.path.exists(val) == False):
-				doError('%s does not exist' % val, False)
+				doError('%s does not exist' % val)
 			configFromFile(val)
 		elif(arg == '-fadd'):
 			try:
@@ -4803,7 +5135,7 @@ if __name__ == '__main__':
 			except:
 				doError('No text file supplied', True)
 			if(os.path.exists(val) == False):
-				doError('%s does not exist' % val, False)
+				doError('%s does not exist' % val)
 			sysvals.addFtraceFilterFunctions(val)
 		elif(arg == '-dmesg'):
 			try:
@@ -4813,7 +5145,7 @@ if __name__ == '__main__':
 			sysvals.notestrun = True
 			sysvals.dmesgfile = val
 			if(os.path.exists(sysvals.dmesgfile) == False):
-				doError('%s does not exist' % sysvals.dmesgfile, False)
+				doError('%s does not exist' % sysvals.dmesgfile)
 		elif(arg == '-ftrace'):
 			try:
 				val = args.next()
@@ -4822,7 +5154,7 @@ if __name__ == '__main__':
 			sysvals.notestrun = True
 			sysvals.ftracefile = val
 			if(os.path.exists(sysvals.ftracefile) == False):
-				doError('%s does not exist' % sysvals.ftracefile, False)
+				doError('%s does not exist' % sysvals.ftracefile)
 		elif(arg == '-summary'):
 			try:
 				val = args.next()
@@ -4832,7 +5164,7 @@ if __name__ == '__main__':
 			cmdarg = val
 			sysvals.notestrun = True
 			if(os.path.isdir(val) == False):
-				doError('%s is not accesible' % val, False)
+				doError('%s is not accesible' % val)
 		elif(arg == '-filter'):
 			try:
 				val = args.next()
@@ -4842,6 +5174,12 @@ if __name__ == '__main__':
 		else:
 			doError('Invalid argument: '+arg, True)
 
+	# compatibility errors
+	if(sysvals.usecallgraph and sysvals.usedevsrc):
+		doError('-dev is not compatible with -f')
+	if(sysvals.usecallgraph and sysvals.useprocmon):
+		doError('-proc is not compatible with -f')
+
 	# callgraph size cannot exceed device size
 	if sysvals.mincglen < sysvals.mindevlen:
 		sysvals.mincglen = sysvals.mindevlen
@@ -4855,8 +5193,7 @@ if __name__ == '__main__':
 		elif(cmd == 'usbtopo'):
 			detectUSB()
 		elif(cmd == 'modes'):
-			modes = getModes()
-			print modes
+			print getModes()
 		elif(cmd == 'flist'):
 			sysvals.getFtraceFilterFunctions(True)
 		elif(cmd == 'flistall'):
diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index 06121ce524a7..c9235d8340f1 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -44,7 +44,7 @@ char *cur_filename, *source_file;
 int in_source_file;
 
 static int flag_debug, flag_dump_defs, flag_reference, flag_dump_types,
-	   flag_preserve, flag_warnings;
+	   flag_preserve, flag_warnings, flag_rel_crcs;
 static const char *mod_prefix = "";
 
 static int errors;
@@ -693,7 +693,10 @@ void export_symbol(const char *name)
 			fputs(">\n", debugfile);
 
 		/* Used as a linker script. */
-		printf("%s__crc_%s = 0x%08lx ;\n", mod_prefix, name, crc);
+		printf(!flag_rel_crcs ? "%s__crc_%s = 0x%08lx;\n" :
+		       "SECTIONS { .rodata : ALIGN(4) { "
+		       "%s__crc_%s = .; LONG(0x%08lx); } }\n",
+		       mod_prefix, name, crc);
 	}
 }
 
@@ -730,7 +733,7 @@ void error_with_pos(const char *fmt, ...)
 
 static void genksyms_usage(void)
 {
-	fputs("Usage:\n" "genksyms [-adDTwqhV] > /path/to/.tmp_obj.ver\n" "\n"
+	fputs("Usage:\n" "genksyms [-adDTwqhVR] > /path/to/.tmp_obj.ver\n" "\n"
 #ifdef __GNU_LIBRARY__
 	      "  -s, --symbol-prefix   Select symbol prefix\n"
 	      "  -d, --debug           Increment the debug level (repeatable)\n"
@@ -742,6 +745,7 @@ static void genksyms_usage(void)
 	      "  -q, --quiet           Disable warnings (default)\n"
 	      "  -h, --help            Print this message\n"
 	      "  -V, --version         Print the release version\n"
+	      "  -R, --relative-crc    Emit section relative symbol CRCs\n"
 #else				/* __GNU_LIBRARY__ */
 	      "  -s                    Select symbol prefix\n"
 	      "  -d                    Increment the debug level (repeatable)\n"
@@ -753,6 +757,7 @@ static void genksyms_usage(void)
 	      "  -q                    Disable warnings (default)\n"
 	      "  -h                    Print this message\n"
 	      "  -V                    Print the release version\n"
+	      "  -R                    Emit section relative symbol CRCs\n"
 #endif				/* __GNU_LIBRARY__ */
 	      , stderr);
 }
@@ -774,13 +779,14 @@ int main(int argc, char **argv)
 		{"preserve", 0, 0, 'p'},
 		{"version", 0, 0, 'V'},
 		{"help", 0, 0, 'h'},
+		{"relative-crc", 0, 0, 'R'},
 		{0, 0, 0, 0}
 	};
 
-	while ((o = getopt_long(argc, argv, "s:dwqVDr:T:ph",
+	while ((o = getopt_long(argc, argv, "s:dwqVDr:T:phR",
 				&long_opts[0], NULL)) != EOF)
 #else				/* __GNU_LIBRARY__ */
-	while ((o = getopt(argc, argv, "s:dwqVDr:T:ph")) != EOF)
+	while ((o = getopt(argc, argv, "s:dwqVDr:T:phR")) != EOF)
 #endif				/* __GNU_LIBRARY__ */
 		switch (o) {
 		case 's':
@@ -823,6 +829,9 @@ int main(int argc, char **argv)
 		case 'h':
 			genksyms_usage();
 			return 0;
+		case 'R':
+			flag_rel_crcs = 1;
+			break;
 		default:
 			genksyms_usage();
 			return 1;
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 299b92ca1ae0..5d554419170b 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -219,6 +219,10 @@ static int symbol_valid(struct sym_entry *s)
 		"_SDA2_BASE_",		/* ppc */
 		NULL };
 
+	static char *special_prefixes[] = {
+		"__crc_",		/* modversions */
+		NULL };
+
 	static char *special_suffixes[] = {
 		"_veneer",		/* arm */
 		"_from_arm",		/* arm */
@@ -259,6 +263,14 @@ static int symbol_valid(struct sym_entry *s)
 		if (strcmp(sym_name, special_symbols[i]) == 0)
 			return 0;
 
+	for (i = 0; special_prefixes[i]; i++) {
+		int l = strlen(special_prefixes[i]);
+
+		if (l <= strlen(sym_name) &&
+		    strncmp(sym_name, special_prefixes[i], l) == 0)
+			return 0;
+	}
+
 	for (i = 0; special_suffixes[i]; i++) {
 		int l = strlen(sym_name) - strlen(special_suffixes[i]);
 
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 29c89a6bad3d..4dedd0d3d3a7 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -621,6 +621,16 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 	if (strncmp(symname, CRC_PFX, strlen(CRC_PFX)) == 0) {
 		is_crc = true;
 		crc = (unsigned int) sym->st_value;
+		if (sym->st_shndx != SHN_UNDEF && sym->st_shndx != SHN_ABS) {
+			unsigned int *crcp;
+
+			/* symbol points to the CRC in the ELF object */
+			crcp = (void *)info->hdr + sym->st_value +
+			       info->sechdrs[sym->st_shndx].sh_offset -
+			       (info->hdr->e_type != ET_REL ?
+				info->sechdrs[sym->st_shndx].sh_addr : 0);
+			crc = *crcp;
+		}
 		sym_update_crc(symname + strlen(CRC_PFX), mod, crc,
 				export);
 	}
diff --git a/security/apparmor/include/apparmor.h b/security/apparmor/include/apparmor.h
index 5d721e990876..f067be814626 100644
--- a/security/apparmor/include/apparmor.h
+++ b/security/apparmor/include/apparmor.h
@@ -78,12 +78,6 @@ static inline void *kvzalloc(size_t size)
 	return __aa_kvmalloc(size, __GFP_ZERO);
 }
 
-/* returns 0 if kref not incremented */
-static inline int kref_get_not0(struct kref *kref)
-{
-	return atomic_inc_not_zero(&kref->refcount);
-}
-
 /**
  * aa_strneq - compare null terminated @str to a non null terminated substring
  * @str: a null terminated string
diff --git a/security/apparmor/include/policy.h b/security/apparmor/include/policy.h
index 52275f040a5f..46467aaa557b 100644
--- a/security/apparmor/include/policy.h
+++ b/security/apparmor/include/policy.h
@@ -287,7 +287,7 @@ static inline struct aa_profile *aa_get_profile(struct aa_profile *p)
  */
 static inline struct aa_profile *aa_get_profile_not0(struct aa_profile *p)
 {
-	if (p && kref_get_not0(&p->count))
+	if (p && kref_get_unless_zero(&p->count))
 		return p;
 
 	return NULL;
@@ -307,7 +307,7 @@ static inline struct aa_profile *aa_get_profile_rcu(struct aa_profile __rcu **p)
 	rcu_read_lock();
 	do {
 		c = rcu_dereference(*p);
-	} while (c && !kref_get_not0(&c->count));
+	} while (c && !kref_get_unless_zero(&c->count));
 	rcu_read_unlock();
 
 	return c;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index c7c6619431d5..d98550abe16d 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -5887,7 +5887,7 @@ static int selinux_setprocattr(struct task_struct *p,
 		return error;
 
 	/* Obtain a SID for the context, if one was specified. */
-	if (size && str[1] && str[1] != '\n') {
+	if (size && str[0] && str[0] != '\n') {
 		if (str[size-1] == '\n') {
 			str[size-1] = 0;
 			size--;
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index c850345c43b5..dfa5156f3585 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -419,7 +419,6 @@ int snd_seq_pool_done(struct snd_seq_pool *pool)
 {
 	unsigned long flags;
 	struct snd_seq_event_cell *ptr;
-	int max_count = 5 * HZ;
 
 	if (snd_BUG_ON(!pool))
 		return -EINVAL;
@@ -432,14 +431,8 @@ int snd_seq_pool_done(struct snd_seq_pool *pool)
 	if (waitqueue_active(&pool->output_sleep))
 		wake_up(&pool->output_sleep);
 
-	while (atomic_read(&pool->counter) > 0) {
-		if (max_count == 0) {
-			pr_warn("ALSA: snd_seq_pool_done timeout: %d cells remain\n", atomic_read(&pool->counter));
-			break;
-		}
+	while (atomic_read(&pool->counter) > 0)
 		schedule_timeout_uninterruptible(1);
-		max_count--;
-	}
 	
 	/* release all resources */
 	spin_lock_irqsave(&pool->lock, flags);
diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c
index 0bec02e89d51..450c5187eecb 100644
--- a/sound/core/seq/seq_queue.c
+++ b/sound/core/seq/seq_queue.c
@@ -181,6 +181,8 @@ void __exit snd_seq_queues_delete(void)
 	}
 }
 
+static void queue_use(struct snd_seq_queue *queue, int client, int use);
+
 /* allocate a new queue -
  * return queue index value or negative value for error
  */
@@ -192,11 +194,11 @@ int snd_seq_queue_alloc(int client, int locked, unsigned int info_flags)
 	if (q == NULL)
 		return -ENOMEM;
 	q->info_flags = info_flags;
+	queue_use(q, client, 1);
 	if (queue_list_add(q) < 0) {
 		queue_delete(q);
 		return -ENOMEM;
 	}
-	snd_seq_queue_use(q->queue, client, 1); /* use this queue */
 	return q->queue;
 }
 
@@ -502,19 +504,9 @@ int snd_seq_queue_timer_set_tempo(int queueid, int client,
 	return result;
 }
 
-
-/* use or unuse this queue -
- * if it is the first client, starts the timer.
- * if it is not longer used by any clients, stop the timer.
- */
-int snd_seq_queue_use(int queueid, int client, int use)
+/* use or unuse this queue */
+static void queue_use(struct snd_seq_queue *queue, int client, int use)
 {
-	struct snd_seq_queue *queue;
-
-	queue = queueptr(queueid);
-	if (queue == NULL)
-		return -EINVAL;
-	mutex_lock(&queue->timer_mutex);
 	if (use) {
 		if (!test_and_set_bit(client, queue->clients_bitmap))
 			queue->clients++;
@@ -529,6 +521,21 @@ int snd_seq_queue_use(int queueid, int client, int use)
 	} else {
 		snd_seq_timer_close(queue);
 	}
+}
+
+/* use or unuse this queue -
+ * if it is the first client, starts the timer.
+ * if it is not longer used by any clients, stop the timer.
+ */
+int snd_seq_queue_use(int queueid, int client, int use)
+{
+	struct snd_seq_queue *queue;
+
+	queue = queueptr(queueid);
+	if (queue == NULL)
+		return -EINVAL;
+	mutex_lock(&queue->timer_mutex);
+	queue_use(queue, client, use);
 	mutex_unlock(&queue->timer_mutex);
 	queuefree(queue);
 	return 0;
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index cf9bc042fe96..3fc201c3b95a 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -3639,6 +3639,7 @@ HDA_CODEC_ENTRY(0x10de0070, "GPU 70 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0071, "GPU 71 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0072, "GPU 72 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de007d, "GPU 7d HDMI/DP",	patch_nvhdmi),
+HDA_CODEC_ENTRY(0x10de0080, "GPU 80 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0082, "GPU 82 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de0083, "GPU 83 HDMI/DP",	patch_nvhdmi),
 HDA_CODEC_ENTRY(0x10de8001, "MCP73 HDMI",	patch_nvhdmi_2ch),
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index 90009c0b3a92..ab3c280a23d1 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -754,8 +754,9 @@ int line6_probe(struct usb_interface *interface,
 		goto error;
 	}
 
+	line6_get_interval(line6);
+
 	if (properties->capabilities & LINE6_CAP_CONTROL) {
-		line6_get_interval(line6);
 		ret = line6_init_cap_control(line6);
 		if (ret < 0)
 			goto error;
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index a2b3eb313a25..af05f8e0903e 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -84,6 +84,15 @@ struct kvm_regs {
 #define KVM_VGIC_V2_DIST_SIZE		0x1000
 #define KVM_VGIC_V2_CPU_SIZE		0x2000
 
+/* Supported VGICv3 address types  */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST	2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
+#define KVM_VGIC_ITS_ADDR_TYPE		4
+
+#define KVM_VGIC_V3_DIST_SIZE		SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
+#define KVM_VGIC_V3_ITS_SIZE		(2 * SZ_64K)
+
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_PSCI_0_2		1 /* CPU uses PSCI v0.2 */
 
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index c93cf35ce379..3603b6f51b11 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -573,6 +573,10 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_SPRG9	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba)
 #define KVM_REG_PPC_DBSR	(KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb)
 
+/* POWER9 registers */
+#define KVM_REG_PPC_TIDR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
+#define KVM_REG_PPC_PSSCR	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
+
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
  */
@@ -596,6 +600,7 @@ struct kvm_get_htab_header {
 #define KVM_REG_PPC_TM_VSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67)
 #define KVM_REG_PPC_TM_DSCR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68)
 #define KVM_REG_PPC_TM_TAR	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69)
+#define KVM_REG_PPC_TM_XER	(KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a)
 
 /* PPC64 eXternal Interrupt Controller Specification */
 #define KVM_DEV_XICS_GRP_SOURCES	1	/* 64-bit source attributes */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index cddd5d06e1cb..293149a1c6a1 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -105,6 +105,7 @@
 #define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
 #define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
@@ -188,10 +189,14 @@
 
 #define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
 #define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2	( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3	( 7*32+ 6) /* Code and Data Prioritization L3 */
 
 #define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
 
+#define X86_FEATURE_INTEL_PPIN	( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
@@ -220,11 +225,13 @@
 #define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
 #define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
 #define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_RDT_A	( 9*32+15) /* Resource Director Technology Allocation */
 #define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
 #define X86_FEATURE_AVX512DQ	( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
 #define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA  ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
 #define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
 #define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
@@ -278,8 +285,11 @@
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
+#define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
 #define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
+#define X86_FEATURE_RDPID	(16*32+ 22) /* RDPID instruction */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
@@ -310,4 +320,6 @@
 #define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
 #define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
 #define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
+#define X86_BUG_AMD_E400	X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index 37fee272618f..14458658e988 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -65,6 +65,8 @@
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
 #define EXIT_REASON_APIC_ACCESS         44
 #define EXIT_REASON_EOI_INDUCED         45
+#define EXIT_REASON_GDTR_IDTR           46
+#define EXIT_REASON_LDTR_TR             47
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_INVEPT              50
@@ -113,6 +115,8 @@
 	{ EXIT_REASON_MCE_DURING_VMENTRY,    "MCE_DURING_VMENTRY" }, \
 	{ EXIT_REASON_TPR_BELOW_THRESHOLD,   "TPR_BELOW_THRESHOLD" }, \
 	{ EXIT_REASON_APIC_ACCESS,           "APIC_ACCESS" }, \
+	{ EXIT_REASON_GDTR_IDTR,	     "GDTR_IDTR" }, \
+	{ EXIT_REASON_LDTR_TR,		     "LDTR_TR" }, \
 	{ EXIT_REASON_EPT_VIOLATION,         "EPT_VIOLATION" }, \
 	{ EXIT_REASON_EPT_MISCONFIG,         "EPT_MISCONFIG" }, \
 	{ EXIT_REASON_INVEPT,                "INVEPT" }, \
@@ -129,6 +133,7 @@
 	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
+#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 99c0ccd2f176..e279a71c650d 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -19,6 +19,16 @@ else
   Q=@
 endif
 
+ifneq ($(filter 4.%,$(MAKE_VERSION)),)	# make-4
+ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
+  quiet=silent_
+endif
+else					# make-3.8x
+ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
+  quiet=silent_
+endif
+endif
+
 build-dir := $(srctree)/tools/build
 
 # Define $(fixdep) for dep-cmd function
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
new file mode 100644
index 000000000000..48af2f10a42d
--- /dev/null
+++ b/tools/include/linux/compiler-gcc.h
@@ -0,0 +1,14 @@
+#ifndef _TOOLS_LINUX_COMPILER_H_
+#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
+#endif
+
+/*
+ * Common definitions for all gcc versions go here.
+ */
+#define GCC_VERSION (__GNUC__ * 10000		\
+		     + __GNUC_MINOR__ * 100	\
+		     + __GNUC_PATCHLEVEL__)
+
+#if GCC_VERSION >= 70000 && !defined(__CHECKER__)
+# define __fallthrough __attribute__ ((fallthrough))
+#endif
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index e33fc1df3935..6326ede9aece 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -1,6 +1,10 @@
 #ifndef _TOOLS_LINUX_COMPILER_H_
 #define _TOOLS_LINUX_COMPILER_H_
 
+#ifdef __GNUC__
+#include <linux/compiler-gcc.h>
+#endif
+
 /* Optimization barrier */
 /* The "volatile" is due to gcc bugs */
 #define barrier() __asm__ __volatile__("": : :"memory")
@@ -126,4 +130,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 #define WRITE_ONCE(x, val) \
 	({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
 
+
+#ifndef __fallthrough
+# define __fallthrough
+#endif
+
 #endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0eb0e87dbe9f..d2b0ac799d03 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -116,6 +116,12 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
+ * to the given target_fd cgroup the descendent cgroup will be able to
+ * override effective bpf program that was inherited from this cgroup
+ */
+#define BPF_F_ALLOW_OVERRIDE	(1U << 0)
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -171,6 +177,7 @@ union bpf_attr {
 		__u32		target_fd;	/* container object to attach to */
 		__u32		attach_bpf_fd;	/* eBPF program to attach */
 		__u32		attach_type;
+		__u32		attach_flags;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/tools/leds/Makefile b/tools/leds/Makefile
index c03a79ebf9c8..078b666fd78b 100644
--- a/tools/leds/Makefile
+++ b/tools/leds/Makefile
@@ -3,11 +3,11 @@
 CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra -g -I../../include/uapi
 
-all: uledmon
+all: uledmon led_hw_brightness_mon
 %: %.c
 	$(CC) $(CFLAGS) -o $@ $^
 
 clean:
-	$(RM) uledmon
+	$(RM) uledmon led_hw_brightness_mon
 
 .PHONY: all clean
diff --git a/tools/leds/led_hw_brightness_mon.c b/tools/leds/led_hw_brightness_mon.c
new file mode 100644
index 000000000000..64642ccfe442
--- /dev/null
+++ b/tools/leds/led_hw_brightness_mon.c
@@ -0,0 +1,84 @@
+/*
+ * led_hw_brightness_mon.c
+ *
+ * This program monitors LED brightness level changes having its origin
+ * in hardware/firmware, i.e. outside of kernel control.
+ * A timestamp and brightness value is printed each time the brightness changes.
+ *
+ * Usage: led_hw_brightness_mon <device-name>
+ *
+ * <device-name> is the name of the LED class device to be monitored. Pressing
+ * CTRL+C will exit.
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include <unistd.h>
+
+#include <linux/uleds.h>
+
+int main(int argc, char const *argv[])
+{
+	int fd, ret;
+	char brightness_file_path[LED_MAX_NAME_SIZE + 11];
+	struct pollfd pollfd;
+	struct timespec ts;
+	char buf[11];
+
+	if (argc != 2) {
+		fprintf(stderr, "Requires <device-name> argument\n");
+		return 1;
+	}
+
+	snprintf(brightness_file_path, LED_MAX_NAME_SIZE,
+		 "/sys/class/leds/%s/brightness_hw_changed", argv[1]);
+
+	fd = open(brightness_file_path, O_RDONLY);
+	if (fd == -1) {
+		printf("Failed to open %s file\n", brightness_file_path);
+		return 1;
+	}
+
+	/*
+	 * read may fail if no hw brightness change has occurred so far,
+	 * but it is required to avoid spurious poll notifications in
+	 * the opposite case.
+	 */
+	read(fd, buf, sizeof(buf));
+
+	pollfd.fd = fd;
+	pollfd.events = POLLPRI;
+
+	while (1) {
+		ret = poll(&pollfd, 1, -1);
+		if (ret == -1) {
+			printf("Failed to poll %s file (%d)\n",
+				brightness_file_path, ret);
+			ret = 1;
+			break;
+		}
+
+		clock_gettime(CLOCK_MONOTONIC, &ts);
+
+		ret = read(fd, buf, sizeof(buf));
+		if (ret < 0)
+			break;
+
+		ret = lseek(pollfd.fd, 0, SEEK_SET);
+		if (ret < 0) {
+			printf("lseek failed (%d)\n", ret);
+			break;
+		}
+
+		printf("[%ld.%09ld] %d\n", ts.tv_sec, ts.tv_nsec, atoi(buf));
+	}
+
+	close(fd);
+
+	return ret;
+}
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index adba83b325d5..eb6e0b36bfc1 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -17,7 +17,13 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libapi.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+
+ifeq ($(CC), clang)
+  CFLAGS += -O3
+else
+  CFLAGS += -O6
+endif
 
 # Treat warnings as errors unless directed not to
 ifneq ($(WERROR),0)
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index f99f49e4a31e..4b6bfc43cccf 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -38,6 +38,10 @@
 #define HUGETLBFS_MAGIC        0x958458f6
 #endif
 
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC           0xcafe4a11
+#endif
+
 static const char * const sysfs__fs_known_mountpoints[] = {
 	"/sys",
 	0,
@@ -75,6 +79,11 @@ static const char * const hugetlbfs__known_mountpoints[] = {
 	0,
 };
 
+static const char * const bpf_fs__known_mountpoints[] = {
+	"/sys/fs/bpf",
+	0,
+};
+
 struct fs {
 	const char		*name;
 	const char * const	*mounts;
@@ -89,6 +98,7 @@ enum {
 	FS__DEBUGFS = 2,
 	FS__TRACEFS = 3,
 	FS__HUGETLBFS = 4,
+	FS__BPF_FS = 5,
 };
 
 #ifndef TRACEFS_MAGIC
@@ -121,6 +131,11 @@ static struct fs fs__entries[] = {
 		.mounts = hugetlbfs__known_mountpoints,
 		.magic	= HUGETLBFS_MAGIC,
 	},
+	[FS__BPF_FS] = {
+		.name	= "bpf",
+		.mounts = bpf_fs__known_mountpoints,
+		.magic	= BPF_FS_MAGIC,
+	},
 };
 
 static bool fs__read_mounts(struct fs *fs)
@@ -280,6 +295,7 @@ FS(procfs,  FS__PROCFS);
 FS(debugfs, FS__DEBUGFS);
 FS(tracefs, FS__TRACEFS);
 FS(hugetlbfs, FS__HUGETLBFS);
+FS(bpf_fs, FS__BPF_FS);
 
 int filename__read_int(const char *filename, int *value)
 {
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index a63269f5d20c..6b332dc74498 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -22,6 +22,7 @@ FS(procfs)
 FS(debugfs)
 FS(tracefs)
 FS(hugetlbfs)
+FS(bpf_fs)
 
 #undef FS
 
diff --git a/tools/lib/api/fs/tracing_path.c b/tools/lib/api/fs/tracing_path.c
index 251b7c342a87..3e606b9c443e 100644
--- a/tools/lib/api/fs/tracing_path.c
+++ b/tools/lib/api/fs/tracing_path.c
@@ -86,9 +86,13 @@ void put_tracing_file(char *file)
 	free(file);
 }
 
-static int strerror_open(int err, char *buf, size_t size, const char *filename)
+int tracing_path__strerror_open_tp(int err, char *buf, size_t size,
+				   const char *sys, const char *name)
 {
 	char sbuf[128];
+	char filename[PATH_MAX];
+
+	snprintf(filename, PATH_MAX, "%s/%s", sys, name ?: "*");
 
 	switch (err) {
 	case ENOENT:
@@ -99,10 +103,19 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename)
 		 * - jirka
 		 */
 		if (debugfs__configured() || tracefs__configured()) {
-			snprintf(buf, size,
-				 "Error:\tFile %s/%s not found.\n"
-				 "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
-				 tracing_events_path, filename);
+			/* sdt markers */
+			if (!strncmp(filename, "sdt_", 4)) {
+				snprintf(buf, size,
+					"Error:\tFile %s/%s not found.\n"
+					"Hint:\tSDT event cannot be directly recorded on.\n"
+					"\tPlease first use 'perf probe %s:%s' before recording it.\n",
+					tracing_events_path, filename, sys, name);
+			} else {
+				snprintf(buf, size,
+					 "Error:\tFile %s/%s not found.\n"
+					 "Hint:\tPerhaps this kernel misses some CONFIG_ setting to enable this feature?.\n",
+					 tracing_events_path, filename);
+			}
 			break;
 		}
 		snprintf(buf, size, "%s",
@@ -125,12 +138,3 @@ static int strerror_open(int err, char *buf, size_t size, const char *filename)
 
 	return 0;
 }
-
-int tracing_path__strerror_open_tp(int err, char *buf, size_t size, const char *sys, const char *name)
-{
-	char path[PATH_MAX];
-
-	snprintf(path, PATH_MAX, "%s/%s", sys, name ?: "*");
-
-	return strerror_open(err, buf, size, path);
-}
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 3ddb58a36d3c..ae752fa4eaa7 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -168,7 +168,8 @@ int bpf_obj_get(const char *pathname)
 	return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
 }
 
-int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
+int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
+		    unsigned int flags)
 {
 	union bpf_attr attr;
 
@@ -176,6 +177,7 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
 	attr.target_fd	   = target_fd;
 	attr.attach_bpf_fd = prog_fd;
 	attr.attach_type   = type;
+	attr.attach_flags  = flags;
 
 	return sys_bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index a2f9853dd882..44fb7c5f8ae6 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -22,6 +22,7 @@
 #define __BPF_BPF_H
 
 #include <linux/bpf.h>
+#include <stddef.h>
 
 int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size,
 		   int max_entries, __u32 map_flags);
@@ -41,7 +42,8 @@ int bpf_map_delete_elem(int fd, void *key);
 int bpf_map_get_next_key(int fd, void *key, void *next_key);
 int bpf_obj_pin(int fd, const char *pathname);
 int bpf_obj_get(const char *pathname);
-int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type);
+int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
+		    unsigned int flags);
 int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
 
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 84e6b35da4bd..ac6eb863b2a4 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU Lesser General Public
@@ -22,15 +23,21 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <stdarg.h>
+#include <libgen.h>
 #include <inttypes.h>
 #include <string.h>
 #include <unistd.h>
 #include <fcntl.h>
 #include <errno.h>
 #include <asm/unistd.h>
+#include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/list.h>
+#include <linux/limits.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/vfs.h>
 #include <libelf.h>
 #include <gelf.h>
 
@@ -41,6 +48,10 @@
 #define EM_BPF 247
 #endif
 
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC		0xcafe4a11
+#endif
+
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
 __printf(1, 2)
@@ -779,7 +790,7 @@ static int
 bpf_program__collect_reloc(struct bpf_program *prog,
 			   size_t nr_maps, GElf_Shdr *shdr,
 			   Elf_Data *data, Elf_Data *symbols,
-			   int maps_shndx)
+			   int maps_shndx, struct bpf_map *maps)
 {
 	int i, nrels;
 
@@ -829,7 +840,15 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 			return -LIBBPF_ERRNO__RELOC;
 		}
 
-		map_idx = sym.st_value / sizeof(struct bpf_map_def);
+		/* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
+		for (map_idx = 0; map_idx < nr_maps; map_idx++) {
+			if (maps[map_idx].offset == sym.st_value) {
+				pr_debug("relocation: find map %zd (%s) for insn %u\n",
+					 map_idx, maps[map_idx].name, insn_idx);
+				break;
+			}
+		}
+
 		if (map_idx >= nr_maps) {
 			pr_warning("bpf relocation: map_idx %d large than %d\n",
 				   (int)map_idx, (int)nr_maps - 1);
@@ -953,7 +972,8 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 		err = bpf_program__collect_reloc(prog, nr_maps,
 						 shdr, data,
 						 obj->efile.symbols,
-						 obj->efile.maps_shndx);
+						 obj->efile.maps_shndx,
+						 obj->maps);
 		if (err)
 			return err;
 	}
@@ -1227,6 +1247,191 @@ out:
 	return err;
 }
 
+static int check_path(const char *path)
+{
+	struct statfs st_fs;
+	char *dname, *dir;
+	int err = 0;
+
+	if (path == NULL)
+		return -EINVAL;
+
+	dname = strdup(path);
+	if (dname == NULL)
+		return -ENOMEM;
+
+	dir = dirname(dname);
+	if (statfs(dir, &st_fs)) {
+		pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
+		err = -errno;
+	}
+	free(dname);
+
+	if (!err && st_fs.f_type != BPF_FS_MAGIC) {
+		pr_warning("specified path %s is not on BPF FS\n", path);
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
+			      int instance)
+{
+	int err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (prog == NULL) {
+		pr_warning("invalid program pointer\n");
+		return -EINVAL;
+	}
+
+	if (instance < 0 || instance >= prog->instances.nr) {
+		pr_warning("invalid prog instance %d of prog %s (max %d)\n",
+			   instance, prog->section_name, prog->instances.nr);
+		return -EINVAL;
+	}
+
+	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
+		pr_warning("failed to pin program: %s\n", strerror(errno));
+		return -errno;
+	}
+	pr_debug("pinned program '%s'\n", path);
+
+	return 0;
+}
+
+static int make_dir(const char *path)
+{
+	int err = 0;
+
+	if (mkdir(path, 0700) && errno != EEXIST)
+		err = -errno;
+
+	if (err)
+		pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
+	return err;
+}
+
+int bpf_program__pin(struct bpf_program *prog, const char *path)
+{
+	int i, err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (prog == NULL) {
+		pr_warning("invalid program pointer\n");
+		return -EINVAL;
+	}
+
+	if (prog->instances.nr <= 0) {
+		pr_warning("no instances of prog %s to pin\n",
+			   prog->section_name);
+		return -EINVAL;
+	}
+
+	err = make_dir(path);
+	if (err)
+		return err;
+
+	for (i = 0; i < prog->instances.nr; i++) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%d", path, i);
+		if (len < 0)
+			return -EINVAL;
+		else if (len >= PATH_MAX)
+			return -ENAMETOOLONG;
+
+		err = bpf_program__pin_instance(prog, buf, i);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int bpf_map__pin(struct bpf_map *map, const char *path)
+{
+	int err;
+
+	err = check_path(path);
+	if (err)
+		return err;
+
+	if (map == NULL) {
+		pr_warning("invalid map pointer\n");
+		return -EINVAL;
+	}
+
+	if (bpf_obj_pin(map->fd, path)) {
+		pr_warning("failed to pin map: %s\n", strerror(errno));
+		return -errno;
+	}
+
+	pr_debug("pinned map '%s'\n", path);
+	return 0;
+}
+
+int bpf_object__pin(struct bpf_object *obj, const char *path)
+{
+	struct bpf_program *prog;
+	struct bpf_map *map;
+	int err;
+
+	if (!obj)
+		return -ENOENT;
+
+	if (!obj->loaded) {
+		pr_warning("object not yet loaded; load it first\n");
+		return -ENOENT;
+	}
+
+	err = make_dir(path);
+	if (err)
+		return err;
+
+	bpf_map__for_each(map, obj) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       bpf_map__name(map));
+		if (len < 0)
+			return -EINVAL;
+		else if (len >= PATH_MAX)
+			return -ENAMETOOLONG;
+
+		err = bpf_map__pin(map, buf);
+		if (err)
+			return err;
+	}
+
+	bpf_object__for_each_program(prog, obj) {
+		char buf[PATH_MAX];
+		int len;
+
+		len = snprintf(buf, PATH_MAX, "%s/%s", path,
+			       prog->section_name);
+		if (len < 0)
+			return -EINVAL;
+		else if (len >= PATH_MAX)
+			return -ENAMETOOLONG;
+
+		err = bpf_program__pin(prog, buf);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 void bpf_object__close(struct bpf_object *obj)
 {
 	size_t i;
@@ -1419,37 +1624,33 @@ static void bpf_program__set_type(struct bpf_program *prog,
 	prog->type = type;
 }
 
-int bpf_program__set_tracepoint(struct bpf_program *prog)
-{
-	if (!prog)
-		return -EINVAL;
-	bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-	return 0;
-}
-
-int bpf_program__set_kprobe(struct bpf_program *prog)
-{
-	if (!prog)
-		return -EINVAL;
-	bpf_program__set_type(prog, BPF_PROG_TYPE_KPROBE);
-	return 0;
-}
-
 static bool bpf_program__is_type(struct bpf_program *prog,
 				 enum bpf_prog_type type)
 {
 	return prog ? (prog->type == type) : false;
 }
 
-bool bpf_program__is_tracepoint(struct bpf_program *prog)
-{
-	return bpf_program__is_type(prog, BPF_PROG_TYPE_TRACEPOINT);
-}
-
-bool bpf_program__is_kprobe(struct bpf_program *prog)
-{
-	return bpf_program__is_type(prog, BPF_PROG_TYPE_KPROBE);
-}
+#define BPF_PROG_TYPE_FNS(NAME, TYPE)			\
+int bpf_program__set_##NAME(struct bpf_program *prog)	\
+{							\
+	if (!prog)					\
+		return -EINVAL;				\
+	bpf_program__set_type(prog, TYPE);		\
+	return 0;					\
+}							\
+							\
+bool bpf_program__is_##NAME(struct bpf_program *prog)	\
+{							\
+	return bpf_program__is_type(prog, TYPE);	\
+}							\
+
+BPF_PROG_TYPE_FNS(socket_filter, BPF_PROG_TYPE_SOCKET_FILTER);
+BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE);
+BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS);
+BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT);
+BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT);
+BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP);
+BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT);
 
 int bpf_map__fd(struct bpf_map *map)
 {
@@ -1537,3 +1738,10 @@ bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset)
 	}
 	return ERR_PTR(-ENOENT);
 }
+
+long libbpf_get_error(const void *ptr)
+{
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+	return 0;
+}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index a5a8b86a06fe..b30394f9947a 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -22,8 +22,8 @@
 #define __BPF_LIBBPF_H
 
 #include <stdio.h>
+#include <stdint.h>
 #include <stdbool.h>
-#include <linux/err.h>
 #include <sys/types.h>  // for size_t
 
 enum libbpf_errno {
@@ -65,6 +65,7 @@ struct bpf_object *bpf_object__open(const char *path);
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 					   size_t obj_buf_sz,
 					   const char *name);
+int bpf_object__pin(struct bpf_object *object, const char *path);
 void bpf_object__close(struct bpf_object *object);
 
 /* Load/unload object into/from kernel */
@@ -106,6 +107,9 @@ void *bpf_program__priv(struct bpf_program *prog);
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
 int bpf_program__fd(struct bpf_program *prog);
+int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
+			      int instance);
+int bpf_program__pin(struct bpf_program *prog, const char *path);
 
 struct bpf_insn;
 
@@ -174,11 +178,21 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n);
 /*
  * Adjust type of bpf program. Default is kprobe.
  */
+int bpf_program__set_socket_filter(struct bpf_program *prog);
 int bpf_program__set_tracepoint(struct bpf_program *prog);
 int bpf_program__set_kprobe(struct bpf_program *prog);
+int bpf_program__set_sched_cls(struct bpf_program *prog);
+int bpf_program__set_sched_act(struct bpf_program *prog);
+int bpf_program__set_xdp(struct bpf_program *prog);
+int bpf_program__set_perf_event(struct bpf_program *prog);
 
+bool bpf_program__is_socket_filter(struct bpf_program *prog);
 bool bpf_program__is_tracepoint(struct bpf_program *prog);
 bool bpf_program__is_kprobe(struct bpf_program *prog);
+bool bpf_program__is_sched_cls(struct bpf_program *prog);
+bool bpf_program__is_sched_act(struct bpf_program *prog);
+bool bpf_program__is_xdp(struct bpf_program *prog);
+bool bpf_program__is_perf_event(struct bpf_program *prog);
 
 /*
  * We don't need __attribute__((packed)) now since it is
@@ -223,5 +237,8 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 int bpf_map__set_priv(struct bpf_map *map, void *priv,
 		      bpf_map_clear_priv_t clear_priv);
 void *bpf_map__priv(struct bpf_map *map);
+int bpf_map__pin(struct bpf_map *map, const char *path);
+
+long libbpf_get_error(const void *ptr);
 
 #endif
diff --git a/tools/lib/subcmd/Makefile b/tools/lib/subcmd/Makefile
index 3f8cc44a0dbd..3d1c3b5b5150 100644
--- a/tools/lib/subcmd/Makefile
+++ b/tools/lib/subcmd/Makefile
@@ -19,7 +19,13 @@ MAKEFLAGS += --no-print-directory
 LIBFILE = $(OUTPUT)libsubcmd.a
 
 CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
-CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC
+
+ifeq ($(CC), clang)
+  CFLAGS += -O3
+else
+  CFLAGS += -O6
+endif
 
 # Treat warnings as errors unless directed not to
 ifneq ($(WERROR),0)
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index 8aad81151d50..6bc24025d054 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -270,6 +270,8 @@ static int get_value(struct parse_opt_ctx_t *p,
 		}
 		if (get_arg(p, opt, flags, &arg))
 			return -1;
+		if (arg[0] == '-')
+			return opterror(opt, "expects an unsigned numerical value", flags);
 		*(unsigned int *)opt->value = strtol(arg, (char **)&s, 10);
 		if (*s)
 			return opterror(opt, "expects a numerical value", flags);
@@ -302,6 +304,8 @@ static int get_value(struct parse_opt_ctx_t *p,
 		}
 		if (get_arg(p, opt, flags, &arg))
 			return -1;
+		if (arg[0] == '-')
+			return opterror(opt, "expects an unsigned numerical value", flags);
 		*(u64 *)opt->value = strtoull(arg, (char **)&s, 10);
 		if (*s)
 			return opterror(opt, "expects a numerical value", flags);
diff --git a/tools/lib/subcmd/parse-options.h b/tools/lib/subcmd/parse-options.h
index 11c3be3bcce7..f054ca1b899d 100644
--- a/tools/lib/subcmd/parse-options.h
+++ b/tools/lib/subcmd/parse-options.h
@@ -1,6 +1,7 @@
 #ifndef __SUBCMD_PARSE_OPTIONS_H
 #define __SUBCMD_PARSE_OPTIONS_H
 
+#include <linux/kernel.h>
 #include <stdbool.h>
 #include <stdint.h>
 
@@ -132,32 +133,32 @@ struct option {
 #define OPT_UINTEGER(s, l, v, h)    { .type = OPTION_UINTEGER, .short_name = (s), .long_name = (l), .value = check_vtype(v, unsigned int *), .help = (h) }
 #define OPT_LONG(s, l, v, h)        { .type = OPTION_LONG, .short_name = (s), .long_name = (l), .value = check_vtype(v, long *), .help = (h) }
 #define OPT_U64(s, l, v, h)         { .type = OPTION_U64, .short_name = (s), .long_name = (l), .value = check_vtype(v, u64 *), .help = (h) }
-#define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h) }
+#define OPT_STRING(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h) }
 #define OPT_STRING_OPTARG(s, l, v, a, h, d) \
 	{ .type = OPTION_STRING,  .short_name = (s), .long_name = (l), \
-	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .value = check_vtype(v, const char **), .argh =(a), .help = (h), \
 	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d) }
 #define OPT_STRING_OPTARG_SET(s, l, v, os, a, h, d) \
 	{ .type = OPTION_STRING, .short_name = (s), .long_name = (l), \
-	  .value = check_vtype(v, const char **), (a), .help = (h), \
+	  .value = check_vtype(v, const char **), .argh = (a), .help = (h), \
 	  .flags = PARSE_OPT_OPTARG, .defval = (intptr_t)(d), \
 	  .set = check_vtype(os, bool *)}
-#define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
+#define OPT_STRING_NOEMPTY(s, l, v, a, h)   { .type = OPTION_STRING,  .short_name = (s), .long_name = (l), .value = check_vtype(v, const char **), .argh = (a), .help = (h), .flags = PARSE_OPT_NOEMPTY}
 #define OPT_DATE(s, l, v, h) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = "time", .help = (h), .callback = parse_opt_approxidate_cb }
 #define OPT_CALLBACK(s, l, v, a, h, f) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f) }
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f) }
 #define OPT_CALLBACK_NOOPT(s, l, v, a, h, f) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .flags = PARSE_OPT_NOARG }
 #define OPT_CALLBACK_DEFAULT(s, l, v, a, h, f, d) \
-	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
+	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), .value = (v), .argh = (a), .help = (h), .callback = (f), .defval = (intptr_t)d, .flags = PARSE_OPT_LASTARG_DEFAULT }
 #define OPT_CALLBACK_DEFAULT_NOOPT(s, l, v, a, h, f, d) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l),\
-	.value = (v), (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
+	.value = (v), .arg = (a), .help = (h), .callback = (f), .defval = (intptr_t)d,\
 	.flags = PARSE_OPT_LASTARG_DEFAULT | PARSE_OPT_NOARG}
 #define OPT_CALLBACK_OPTARG(s, l, v, d, a, h, f) \
 	{ .type = OPTION_CALLBACK, .short_name = (s), .long_name = (l), \
-	  .value = (v), (a), .help = (h), .callback = (f), \
+	  .value = (v), .argh = (a), .help = (h), .callback = (f), \
 	  .flags = PARSE_OPT_OPTARG, .data = (d) }
 
 /* parse_options() will filter out the processed options and leave the
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 2616c66e10c1..47076b15eebe 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -257,10 +257,16 @@ define do_install_plugins
 endef
 
 define do_generate_dynamic_list_file
-	(echo '{';							\
-	$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;	\
-	echo '};';							\
-	) > $2
+	symbol_type=`$(NM) -u -D $1 | awk 'NF>1 {print $$1}' | \
+	xargs echo "U W w" | tr ' ' '\n' | sort -u | xargs echo`;\
+	if [ "$$symbol_type" = "U W w" ];then				\
+		(echo '{';						\
+		$(NM) -u -D $1 | awk 'NF>1 {print "\t"$$2";"}' | sort -u;\
+		echo '};';						\
+		) > $2;							\
+	else								\
+		(echo Either missing one of [$1] or bad version of $(NM)) 1>&2;\
+	fi
 endef
 
 install_lib: all_cmd install_plugins
diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c
index 65984f1c2974..c94e3641b046 100644
--- a/tools/lib/traceevent/kbuffer-parse.c
+++ b/tools/lib/traceevent/kbuffer-parse.c
@@ -315,6 +315,7 @@ static unsigned int old_update_pointers(struct kbuffer *kbuf)
 		extend += delta;
 		delta = extend;
 		ptr += 4;
+		length = 0;
 		break;
 
 	case OLD_RINGBUF_TYPE_TIME_STAMP:
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index a00ec190821a..42dbf73758f3 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -130,7 +130,7 @@ static int function_handler(struct trace_seq *s, struct pevent_record *record,
 	unsigned long long pfunction;
 	const char *func;
 	const char *parent;
-	int index;
+	int index = 0;
 
 	if (pevent_get_field_val(s, event, "ip", record, &function, 1))
 		return trace_seq_putc(s, '!');
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 5e0dea2cdc01..039636ffb6c8 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -150,9 +150,9 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		*type = INSN_RETURN;
 		break;
 
-	case 0xc5: /* iret */
 	case 0xca: /* retf */
 	case 0xcb: /* retf */
+	case 0xcf: /* iret */
 		*type = INSN_CONTEXT_SWITCH;
 		break;
 
diff --git a/tools/perf/Build b/tools/perf/Build
index b12d5d1666e3..9b79f8d7db50 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -3,10 +3,12 @@ perf-y += builtin-annotate.o
 perf-y += builtin-config.o
 perf-y += builtin-diff.o
 perf-y += builtin-evlist.o
+perf-y += builtin-ftrace.o
 perf-y += builtin-help.o
 perf-y += builtin-sched.o
 perf-y += builtin-buildid-list.o
 perf-y += builtin-buildid-cache.o
+perf-y += builtin-kallsyms.o
 perf-y += builtin-list.o
 perf-y += builtin-record.o
 perf-y += builtin-report.o
@@ -39,8 +41,7 @@ CFLAGS_builtin-help.o      += $(paths)
 CFLAGS_builtin-timechart.o += $(paths)
 CFLAGS_perf.o              += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))"	\
 			      -DPERF_EXEC_PATH="BUILD_STR($(perfexecdir_SQ))"	\
-			      -DPREFIX="BUILD_STR($(prefix_SQ))"		\
-			      -include $(OUTPUT)PERF-VERSION-FILE
+			      -DPREFIX="BUILD_STR($(prefix_SQ))"
 CFLAGS_builtin-trace.o	   += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))"
 CFLAGS_builtin-report.o	   += -DTIPDIR="BUILD_STR($(tipdir_SQ))"
 CFLAGS_builtin-report.o	   += -DDOCDIR="BUILD_STR($(srcdir_SQ)/Documentation)"
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 3f06730c7f47..2da07e51e119 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -248,7 +248,7 @@ output fields set for caheline offsets output:
              Code address, Code symbol, Shared Object, Source line
   dso   - coalesced by shared object
 
-By default the coalescing is setup with 'pid,tid,iaddr'.
+By default the coalescing is setup with 'pid,iaddr'.
 
 STDIO OUTPUT
 ------------
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 9365b75fd04f..5b4fff3adc4b 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -498,6 +498,18 @@ record.*::
 		But if this option is 'no-cache', it will not update the build-id cache.
 		'skip' skips post-processing and does not update the cache.
 
+diff.*::
+	diff.order::
+		This option sets the number of columns to sort the result.
+		The default is 0, which means sorting by baseline.
+		Setting it to 1 will sort the result by delta (or other
+		compute method selected).
+
+	diff.compute::
+		This options sets the method for computing the diff result.
+		Possible values are 'delta', 'delta-abs', 'ratio' and
+		'wdiff'.  Default is 'delta'.
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 3e9490b9c533..66dbe3dee74b 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -86,8 +86,9 @@ OPTIONS
 
 -c::
 --compute::
-        Differential computation selection - delta,ratio,wdiff (default is delta).
-        See COMPARISON METHODS section for more info.
+        Differential computation selection - delta, ratio, wdiff, delta-abs
+        (default is delta-abs).  Default can be changed using diff.compute
+        config option.  See COMPARISON METHODS section for more info.
 
 -p::
 --period::
@@ -99,7 +100,11 @@ OPTIONS
 
 -o::
 --order::
-       Specify compute sorting column number.
+       Specify compute sorting column number.  0 means sorting by baseline
+       overhead and 1 (default) means sorting by computed value of column 1
+       (data from the first file other base baseline).  Values more than 1
+       can be used only if enough data files are provided.
+       The default value can be set using the diff.order config option.
 
 --percentage::
 	Determine how to display the overhead percentage of filtered entries.
@@ -181,6 +186,10 @@ with:
     relative to how entries are filtered.  Use --percentage=absolute to
     prevent such fluctuation.
 
+delta-abs
+~~~~~~~~~
+Same as 'delta` method, but sort the result with the absolute values.
+
 ratio
 ~~~~~
 If specified the 'Ratio' column is displayed with value 'r' computed as:
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
new file mode 100644
index 000000000000..2d96de6132a9
--- /dev/null
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -0,0 +1,36 @@
+perf-ftrace(1)
+=============
+
+NAME
+----
+perf-ftrace - simple wrapper for kernel's ftrace functionality
+
+
+SYNOPSIS
+--------
+[verse]
+'perf ftrace' <command>
+
+DESCRIPTION
+-----------
+The 'perf ftrace' command is a simple wrapper of kernel's ftrace
+functionality.  It only supports single thread tracing currently and
+just reads trace_pipe in text and then write it to stdout.
+
+The following options apply to perf ftrace.
+
+OPTIONS
+-------
+
+-t::
+--tracer=::
+	Tracer to use: function_graph or function.
+
+-v::
+--verbose=::
+        Verbosity level.
+
+
+SEE ALSO
+--------
+linkperf:perf-record[1], linkperf:perf-trace[1]
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
new file mode 100644
index 000000000000..954ea9e21236
--- /dev/null
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -0,0 +1,24 @@
+perf-kallsyms(1)
+==============
+
+NAME
+----
+perf-kallsyms - Searches running kernel for symbols
+
+SYNOPSIS
+--------
+[verse]
+'perf kallsyms <options> symbol_name[,symbol_name...]'
+
+DESCRIPTION
+-----------
+This command searches the running kernel kallsyms file for the given symbol(s)
+and prints information about it, including the DSO, the kallsyms begin/end
+addresses and the addresses in the ELF kallsyms symbol table (for symbols in
+modules).
+
+OPTIONS
+-------
+-v::
+--verbose=::
+	Increase verbosity level, showing details about symbol table loading, etc.
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 5054d9147f0f..27256bc68eda 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -421,9 +421,19 @@ Configure all used events to run in user space.
 --timestamp-filename
 Append timestamp to output file name.
 
---switch-output::
+--switch-output[=mode]::
 Generate multiple perf.data files, timestamp prefixed, switching to a new one
-when receiving a SIGUSR2.
+based on 'mode' value:
+  "signal" - when receiving a SIGUSR2 (default value) or
+  <size>   - when reaching the size threshold, size is expected to
+             be a number with appended unit character - B/K/M/G
+  <time>   - when reaching the time threshold, size is expected to
+             be a number with appended unit character - s/m/h/d
+
+             Note: the precision of  the size  threshold  hugely depends
+             on your configuration  - the number and size of  your  ring
+             buffers (-m). It is generally more precise for higher sizes
+             (like >5M), for lower values expect different sizes.
 
 A possible use case is to, given an external event, slice the perf.data file
 that gets then processed, possibly via a perf script, to decide if that
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 76173969ab80..d33deddb0146 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -143,6 +143,8 @@ OPTIONS for 'perf sched timehist'
 	stop time is not given (i.e, time string is 'x.y,') then analysis goes
 	to end of file.
 
+--state::
+	Show task state when it switched out.
 
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 5dc5c6a09ac4..4ed5f239ba7d 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -36,7 +36,7 @@ There are several variants of perf script:
 
   'perf script report <script> [args]' to run and display the results
   of <script>.  <script> is the name displayed in the output of 'perf
-  trace --list' i.e. the actual script name minus any language
+  script --list' i.e. the actual script name minus any language
   extension.  The perf.data output from a previous run of 'perf script
   record <script>' is used and should be present for this command to
   succeed.  [args] refers to the (mainly optional) args expected by
@@ -76,7 +76,7 @@ OPTIONS
 	Any command you can specify in a shell.
 
 -D::
---dump-raw-script=::
+--dump-raw-trace=::
         Display verbose dump of the trace data.
 
 -L::
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 781b019751a4..afd728672b6f 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -35,7 +35,10 @@ OPTIONS
 
 -e::
 --expr::
-	List of syscalls to show, currently only syscall names.
+--event::
+	List of syscalls and other perf events (tracepoints, HW cache events,
+	etc) to show.
+	See 'perf list' for a complete list of events.
 	Prefixing with ! shows all syscalls but the ones specified.  You may
 	need to escape it.
 
@@ -135,9 +138,6 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 --kernel-syscall-graph::
 	 Show the kernel callchains on the syscall exit path.
 
---event::
-	Trace other events, see 'perf list' for a complete list.
-
 --max-stack::
         Set the stack depth limit when parsing the callchain, anything
         beyond the specified depth will be ignored. Note that at this point
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index a511e5f31e36..8672f835ae4e 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -61,6 +61,7 @@ tools/include/asm-generic/bitops.h
 tools/include/linux/atomic.h
 tools/include/linux/bitops.h
 tools/include/linux/compiler.h
+tools/include/linux/compiler-gcc.h
 tools/include/linux/coresight-pmu.h
 tools/include/linux/filter.h
 tools/include/linux/hash.h
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 76c84f0eec52..2b941efadb04 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -144,8 +144,12 @@ ifndef DEBUG
 endif
 
 ifeq ($(DEBUG),0)
+ifeq ($(CC), clang)
+  CFLAGS += -O3
+else
   CFLAGS += -O6
 endif
+endif
 
 ifdef PARSER_DEBUG
   PARSER_DEBUG_BISON := -t
@@ -291,8 +295,10 @@ else
       endif
     endif
     ifneq ($(feature-dwarf), 1)
-      msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
-      NO_DWARF := 1
+      ifndef NO_DWARF
+        msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
+        NO_DWARF := 1
+      endif
     else
       ifneq ($(feature-dwarf_getlocations), 1)
         msg := $(warning Old libdw.h, finding variables at given 'perf probe' point will not work, install elfutils-devel/libdw-dev >= 0.157);
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 8bb16aa9d661..4da19b6ba94a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -661,6 +661,7 @@ ifndef NO_PERF_READ_VDSOX32
 endif
 ifndef NO_JVMTI
 	$(call QUIET_INSTALL, $(LIBJVMTI)) \
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(libdir_SQ)'; \
 		$(INSTALL) $(OUTPUT)$(LIBJVMTI) '$(DESTDIR_SQ)$(libdir_SQ)';
 endif
 	$(call QUIET_INSTALL, libexec) \
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 18b13518d8d8..eebe1ec9d2ee 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -2,3 +2,4 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
+PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
diff --git a/tools/perf/arch/arm64/include/dwarf-regs-table.h b/tools/perf/arch/arm64/include/dwarf-regs-table.h
index 26759363f921..36e375f5a211 100644
--- a/tools/perf/arch/arm64/include/dwarf-regs-table.h
+++ b/tools/perf/arch/arm64/include/dwarf-regs-table.h
@@ -2,12 +2,12 @@
 /* This is included in perf/util/dwarf-regs.c */
 
 static const char * const aarch64_regstr_tbl[] = {
-	"%r0", "%r1", "%r2", "%r3", "%r4",
-	"%r5", "%r6", "%r7", "%r8", "%r9",
-	"%r10", "%r11", "%r12", "%r13", "%r14",
-	"%r15", "%r16", "%r17", "%r18", "%r19",
-	"%r20", "%r21", "%r22", "%r23", "%r24",
-	"%r25", "%r26", "%r27", "%r28", "%r29",
+	"%x0", "%x1", "%x2", "%x3", "%x4",
+	"%x5", "%x6", "%x7", "%x8", "%x9",
+	"%x10", "%x11", "%x12", "%x13", "%x14",
+	"%x15", "%x16", "%x17", "%x18", "%x19",
+	"%x20", "%x21", "%x22", "%x23", "%x24",
+	"%x25", "%x26", "%x27", "%x28", "%x29",
 	"%lr", "%sp",
 };
 #endif
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
index d49efeb8172e..068b6189157b 100644
--- a/tools/perf/arch/arm64/util/dwarf-regs.c
+++ b/tools/perf/arch/arm64/util/dwarf-regs.c
@@ -10,17 +10,20 @@
 
 #include <stddef.h>
 #include <dwarf-regs.h>
+#include <linux/ptrace.h> /* for struct user_pt_regs */
+#include "util.h"
 
 struct pt_regs_dwarfnum {
 	const char *name;
 	unsigned int dwarfnum;
 };
 
-#define STR(s) #s
 #define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
 #define GPR_DWARFNUM_NAME(num) \
 	{.name = STR(%x##num), .dwarfnum = num}
 #define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+#define DWARFNUM2OFFSET(index) \
+	(index * sizeof((struct user_pt_regs *)0)->regs[0])
 
 /*
  * Reference:
@@ -78,3 +81,13 @@ const char *get_arch_regstr(unsigned int n)
 			return roff->name;
 	return NULL;
 }
+
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_dwarfnum *roff;
+
+	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return DWARFNUM2OFFSET(roff->dwarfnum);
+	return -EINVAL;
+}
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index bfbb6b5f609c..da04b8c5568a 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -130,8 +130,6 @@ int bench_futex_hash(int argc, const char **argv,
 	}
 
 	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
-	nsecs = futexbench_sanitize_numeric(nsecs);
-	nfutexes = futexbench_sanitize_numeric(nfutexes);
 
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
@@ -139,8 +137,6 @@ int bench_futex_hash(int argc, const char **argv,
 
 	if (!nthreads) /* default to the number of CPUs */
 		nthreads = ncpus;
-	else
-		nthreads = futexbench_sanitize_numeric(nthreads);
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker)
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 6d9d6c40a916..91877777ec6e 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -152,7 +152,6 @@ int bench_futex_lock_pi(int argc, const char **argv,
 		goto err;
 
 	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
-	nsecs = futexbench_sanitize_numeric(nsecs);
 
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
@@ -160,8 +159,6 @@ int bench_futex_lock_pi(int argc, const char **argv,
 
 	if (!nthreads)
 		nthreads = ncpus;
-	else
-		nthreads = futexbench_sanitize_numeric(nthreads);
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker)
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index fd4ee95b689a..2b9705a8734c 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -128,8 +128,6 @@ int bench_futex_requeue(int argc, const char **argv,
 
 	if (!nthreads)
 		nthreads = ncpus;
-	else
-		nthreads = futexbench_sanitize_numeric(nthreads);
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker)
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index beaa6c142477..2c8fa67ad537 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -217,12 +217,8 @@ int bench_futex_wake_parallel(int argc, const char **argv,
 	sigaction(SIGINT, &act, NULL);
 
 	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
-	nwaking_threads = futexbench_sanitize_numeric(nwaking_threads);
-
 	if (!nblocked_threads)
 		nblocked_threads = ncpus;
-	else
-		nblocked_threads = futexbench_sanitize_numeric(nblocked_threads);
 
 	/* some sanity checks */
 	if (nwaking_threads > nblocked_threads || !nwaking_threads)
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 46efcb98b5a4..e246b1b8388a 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -129,7 +129,6 @@ int bench_futex_wake(int argc, const char **argv,
 	}
 
 	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
-	nwakes = futexbench_sanitize_numeric(nwakes);
 
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
@@ -137,8 +136,6 @@ int bench_futex_wake(int argc, const char **argv,
 
 	if (!nthreads)
 		nthreads = ncpus;
-	else
-		nthreads = futexbench_sanitize_numeric(nthreads);
 
 	worker = calloc(nthreads, sizeof(*worker));
 	if (!worker)
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index ba7c735c0c62..b2e06d1190d0 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -7,7 +7,6 @@
 #ifndef _FUTEX_H
 #define _FUTEX_H
 
-#include <stdlib.h>
 #include <unistd.h>
 #include <sys/syscall.h>
 #include <sys/types.h>
@@ -100,7 +99,4 @@ static inline int pthread_attr_setaffinity_np(pthread_attr_t *attr,
 }
 #endif
 
-/* User input sanitation */
-#define futexbench_sanitize_numeric(__n) abs((__n))
-
 #endif /* _FUTEX_H */
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 8efe904e486b..3083fc36282b 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -43,6 +43,7 @@
 /*
  * Debug printf:
  */
+#undef dprintf
 #define dprintf(x...) do { if (g && g->p.show_details >= 1) printf(x); } while (0)
 
 struct thread_data {
@@ -1573,13 +1574,13 @@ static int __bench_numa(const char *name)
 		"GB/sec,", "total-speed",	"GB/sec total speed");
 
 	if (g->p.show_details >= 2) {
-		char tname[32];
+		char tname[14 + 2 * 10 + 1];
 		struct thread_data *td;
 		for (p = 0; p < g->p.nr_proc; p++) {
 			for (t = 0; t < g->p.nr_threads; t++) {
-				memset(tname, 0, 32);
+				memset(tname, 0, sizeof(tname));
 				td = g->threads + p*g->p.nr_threads + t;
-				snprintf(tname, 32, "process%d:thread%d", p, t);
+				snprintf(tname, sizeof(tname), "process%d:thread%d", p, t);
 				print_res(tname, td->speed_gbs,
 					"GB/sec",	"thread-speed", "GB/sec/thread speed");
 				print_res(tname, td->system_time_ns / NSEC_PER_SEC,
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index f8ca7a4ebabc..e2b21723bbf8 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -58,7 +58,7 @@ struct c2c_hist_entry {
 	struct hist_entry	he;
 };
 
-static char const *coalesce_default = "pid,tid,iaddr";
+static char const *coalesce_default = "pid,iaddr";
 
 struct perf_c2c {
 	struct perf_tool	tool;
@@ -2476,6 +2476,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
 		"mean_rmt,"
 		"mean_lcl,"
 		"mean_load,"
+		"tot_recs,"
 		"cpucnt,",
 		add_sym ? "symbol," : "",
 		add_dso ? "dso," : "",
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 9ff0db4e2d0c..70a289347591 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -17,6 +17,7 @@
 #include "util/symbol.h"
 #include "util/util.h"
 #include "util/data.h"
+#include "util/config.h"
 
 #include <stdlib.h>
 #include <math.h>
@@ -30,6 +31,7 @@ enum {
 	PERF_HPP_DIFF__RATIO,
 	PERF_HPP_DIFF__WEIGHTED_DIFF,
 	PERF_HPP_DIFF__FORMULA,
+	PERF_HPP_DIFF__DELTA_ABS,
 
 	PERF_HPP_DIFF__MAX_INDEX
 };
@@ -64,7 +66,7 @@ static bool force;
 static bool show_period;
 static bool show_formula;
 static bool show_baseline_only;
-static unsigned int sort_compute;
+static unsigned int sort_compute = 1;
 
 static s64 compute_wdiff_w1;
 static s64 compute_wdiff_w2;
@@ -73,19 +75,22 @@ enum {
 	COMPUTE_DELTA,
 	COMPUTE_RATIO,
 	COMPUTE_WEIGHTED_DIFF,
+	COMPUTE_DELTA_ABS,
 	COMPUTE_MAX,
 };
 
 const char *compute_names[COMPUTE_MAX] = {
 	[COMPUTE_DELTA] = "delta",
+	[COMPUTE_DELTA_ABS] = "delta-abs",
 	[COMPUTE_RATIO] = "ratio",
 	[COMPUTE_WEIGHTED_DIFF] = "wdiff",
 };
 
-static int compute;
+static int compute = COMPUTE_DELTA_ABS;
 
 static int compute_2_hpp[COMPUTE_MAX] = {
 	[COMPUTE_DELTA]		= PERF_HPP_DIFF__DELTA,
+	[COMPUTE_DELTA_ABS]	= PERF_HPP_DIFF__DELTA_ABS,
 	[COMPUTE_RATIO]		= PERF_HPP_DIFF__RATIO,
 	[COMPUTE_WEIGHTED_DIFF]	= PERF_HPP_DIFF__WEIGHTED_DIFF,
 };
@@ -111,6 +116,10 @@ static struct header_column {
 		.name  = "Delta",
 		.width = 7,
 	},
+	[PERF_HPP_DIFF__DELTA_ABS] = {
+		.name  = "Delta Abs",
+		.width = 7,
+	},
 	[PERF_HPP_DIFF__RATIO] = {
 		.name  = "Ratio",
 		.width = 14,
@@ -298,6 +307,7 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair,
 {
 	switch (compute) {
 	case COMPUTE_DELTA:
+	case COMPUTE_DELTA_ABS:
 		return formula_delta(he, pair, buf, size);
 	case COMPUTE_RATIO:
 		return formula_ratio(he, pair, buf, size);
@@ -461,6 +471,7 @@ static void hists__precompute(struct hists *hists)
 
 			switch (compute) {
 			case COMPUTE_DELTA:
+			case COMPUTE_DELTA_ABS:
 				compute_delta(he, pair);
 				break;
 			case COMPUTE_RATIO:
@@ -498,6 +509,13 @@ __hist_entry__cmp_compute(struct hist_entry *left, struct hist_entry *right,
 
 		return cmp_doubles(l, r);
 	}
+	case COMPUTE_DELTA_ABS:
+	{
+		double l = fabs(left->diff.period_ratio_delta);
+		double r = fabs(right->diff.period_ratio_delta);
+
+		return cmp_doubles(l, r);
+	}
 	case COMPUTE_RATIO:
 	{
 		double l = left->diff.period_ratio;
@@ -564,7 +582,7 @@ hist_entry__cmp_compute_idx(struct hist_entry *left, struct hist_entry *right,
 	if (!p_left || !p_right)
 		return p_left ? -1 : 1;
 
-	if (c != COMPUTE_DELTA) {
+	if (c != COMPUTE_DELTA && c != COMPUTE_DELTA_ABS) {
 		/*
 		 * The delta can be computed without the baseline, but
 		 * others are not.  Put those entries which have no
@@ -607,6 +625,15 @@ hist_entry__cmp_delta(struct perf_hpp_fmt *fmt,
 }
 
 static int64_t
+hist_entry__cmp_delta_abs(struct perf_hpp_fmt *fmt,
+		      struct hist_entry *left, struct hist_entry *right)
+{
+	struct data__file *d = fmt_to_data_file(fmt);
+
+	return hist_entry__cmp_compute(right, left, COMPUTE_DELTA_ABS, d->idx);
+}
+
+static int64_t
 hist_entry__cmp_ratio(struct perf_hpp_fmt *fmt,
 		      struct hist_entry *left, struct hist_entry *right)
 {
@@ -633,6 +660,14 @@ hist_entry__cmp_delta_idx(struct perf_hpp_fmt *fmt __maybe_unused,
 }
 
 static int64_t
+hist_entry__cmp_delta_abs_idx(struct perf_hpp_fmt *fmt __maybe_unused,
+			      struct hist_entry *left, struct hist_entry *right)
+{
+	return hist_entry__cmp_compute_idx(right, left, COMPUTE_DELTA_ABS,
+					   sort_compute);
+}
+
+static int64_t
 hist_entry__cmp_ratio_idx(struct perf_hpp_fmt *fmt __maybe_unused,
 			  struct hist_entry *left, struct hist_entry *right)
 {
@@ -775,7 +810,7 @@ static const struct option options[] = {
 	OPT_BOOLEAN('b', "baseline-only", &show_baseline_only,
 		    "Show only items with match in baseline"),
 	OPT_CALLBACK('c', "compute", &compute,
-		     "delta,ratio,wdiff:w1,w2 (default delta)",
+		     "delta,delta-abs,ratio,wdiff:w1,w2 (default delta-abs)",
 		     "Entries differential computation selection",
 		     setup_compute),
 	OPT_BOOLEAN('p', "period", &show_period,
@@ -945,6 +980,7 @@ hpp__entry_pair(struct hist_entry *he, struct hist_entry *pair,
 
 	switch (idx) {
 	case PERF_HPP_DIFF__DELTA:
+	case PERF_HPP_DIFF__DELTA_ABS:
 		if (pair->diff.computed)
 			diff = pair->diff.period_ratio_delta;
 		else
@@ -1118,6 +1154,10 @@ static void data__hpp_register(struct data__file *d, int idx)
 		fmt->color = hpp__color_wdiff;
 		fmt->sort  = hist_entry__cmp_wdiff;
 		break;
+	case PERF_HPP_DIFF__DELTA_ABS:
+		fmt->color = hpp__color_delta;
+		fmt->sort  = hist_entry__cmp_delta_abs;
+		break;
 	default:
 		fmt->sort  = hist_entry__cmp_nop;
 		break;
@@ -1195,11 +1235,14 @@ static int ui_init(void)
 	case COMPUTE_WEIGHTED_DIFF:
 		fmt->sort = hist_entry__cmp_wdiff_idx;
 		break;
+	case COMPUTE_DELTA_ABS:
+		fmt->sort = hist_entry__cmp_delta_abs_idx;
+		break;
 	default:
 		BUG_ON(1);
 	}
 
-	perf_hpp__register_sort_field(fmt);
+	perf_hpp__prepend_sort_field(fmt);
 	return 0;
 }
 
@@ -1249,6 +1292,31 @@ static int data_init(int argc, const char **argv)
 	return 0;
 }
 
+static int diff__config(const char *var, const char *value,
+			void *cb __maybe_unused)
+{
+	if (!strcmp(var, "diff.order")) {
+		sort_compute = perf_config_int(var, value);
+		return 0;
+	}
+	if (!strcmp(var, "diff.compute")) {
+		if (!strcmp(value, "delta")) {
+			compute = COMPUTE_DELTA;
+		} else if (!strcmp(value, "delta-abs")) {
+			compute = COMPUTE_DELTA_ABS;
+		} else if (!strcmp(value, "ratio")) {
+			compute = COMPUTE_RATIO;
+		} else if (!strcmp(value, "wdiff")) {
+			compute = COMPUTE_WEIGHTED_DIFF;
+		} else {
+			pr_err("Invalid compute method: %s\n", value);
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
 int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int ret = hists__init();
@@ -1256,6 +1324,8 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (ret < 0)
 		return ret;
 
+	perf_config(diff__config, NULL);
+
 	argc = parse_options(argc, argv, options, diff_usage, 0);
 
 	if (symbol__init(NULL) < 0)
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
new file mode 100644
index 000000000000..c3e643666c72
--- /dev/null
+++ b/tools/perf/builtin-ftrace.c
@@ -0,0 +1,265 @@
+/*
+ * builtin-ftrace.c
+ *
+ * Copyright (c) 2013  LG Electronics,  Namhyung Kim <namhyung@kernel.org>
+ *
+ * Released under the GPL v2.
+ */
+
+#include "builtin.h"
+#include "perf.h"
+
+#include <unistd.h>
+#include <signal.h>
+
+#include "debug.h"
+#include <subcmd/parse-options.h>
+#include "evlist.h"
+#include "target.h"
+#include "thread_map.h"
+#include "util/config.h"
+
+
+#define DEFAULT_TRACER  "function_graph"
+
+struct perf_ftrace {
+	struct perf_evlist *evlist;
+	struct target target;
+	const char *tracer;
+};
+
+static bool done;
+
+static void sig_handler(int sig __maybe_unused)
+{
+	done = true;
+}
+
+/*
+ * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
+ * we asked by setting its exec_error to the function below,
+ * ftrace__workload_exec_failed_signal.
+ *
+ * XXX We need to handle this more appropriately, emitting an error, etc.
+ */
+static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
+						siginfo_t *info __maybe_unused,
+						void *ucontext __maybe_unused)
+{
+	/* workload_exec_errno = info->si_value.sival_int; */
+	done = true;
+}
+
+static int write_tracing_file(const char *name, const char *val)
+{
+	char *file;
+	int fd, ret = -1;
+	ssize_t size = strlen(val);
+
+	file = get_tracing_file(name);
+	if (!file) {
+		pr_debug("cannot get tracing file: %s\n", name);
+		return -1;
+	}
+
+	fd = open(file, O_WRONLY);
+	if (fd < 0) {
+		pr_debug("cannot open tracing file: %s\n", name);
+		goto out;
+	}
+
+	if (write(fd, val, size) == size)
+		ret = 0;
+	else
+		pr_debug("write '%s' to tracing/%s failed\n", val, name);
+
+	close(fd);
+out:
+	put_tracing_file(file);
+	return ret;
+}
+
+static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
+{
+	if (write_tracing_file("tracing_on", "0") < 0)
+		return -1;
+
+	if (write_tracing_file("current_tracer", "nop") < 0)
+		return -1;
+
+	if (write_tracing_file("set_ftrace_pid", " ") < 0)
+		return -1;
+
+	return 0;
+}
+
+static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
+{
+	char *trace_file;
+	int trace_fd;
+	char *trace_pid;
+	char buf[4096];
+	struct pollfd pollfd = {
+		.events = POLLIN,
+	};
+
+	if (geteuid() != 0) {
+		pr_err("ftrace only works for root!\n");
+		return -1;
+	}
+
+	if (argc < 1)
+		return -1;
+
+	signal(SIGINT, sig_handler);
+	signal(SIGUSR1, sig_handler);
+	signal(SIGCHLD, sig_handler);
+
+	reset_tracing_files(ftrace);
+
+	/* reset ftrace buffer */
+	if (write_tracing_file("trace", "0") < 0)
+		goto out;
+
+	if (perf_evlist__prepare_workload(ftrace->evlist, &ftrace->target,
+					  argv, false, ftrace__workload_exec_failed_signal) < 0)
+		goto out;
+
+	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
+		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
+		goto out;
+	}
+
+	if (asprintf(&trace_pid, "%d", thread_map__pid(ftrace->evlist->threads, 0)) < 0) {
+		pr_err("failed to allocate pid string\n");
+		goto out;
+	}
+
+	if (write_tracing_file("set_ftrace_pid", trace_pid) < 0) {
+		pr_err("failed to set pid: %s\n", trace_pid);
+		goto out_free_pid;
+	}
+
+	trace_file = get_tracing_file("trace_pipe");
+	if (!trace_file) {
+		pr_err("failed to open trace_pipe\n");
+		goto out_free_pid;
+	}
+
+	trace_fd = open(trace_file, O_RDONLY);
+
+	put_tracing_file(trace_file);
+
+	if (trace_fd < 0) {
+		pr_err("failed to open trace_pipe\n");
+		goto out_free_pid;
+	}
+
+	fcntl(trace_fd, F_SETFL, O_NONBLOCK);
+	pollfd.fd = trace_fd;
+
+	if (write_tracing_file("tracing_on", "1") < 0) {
+		pr_err("can't enable tracing\n");
+		goto out_close_fd;
+	}
+
+	perf_evlist__start_workload(ftrace->evlist);
+
+	while (!done) {
+		if (poll(&pollfd, 1, -1) < 0)
+			break;
+
+		if (pollfd.revents & POLLIN) {
+			int n = read(trace_fd, buf, sizeof(buf));
+			if (n < 0)
+				break;
+			if (fwrite(buf, n, 1, stdout) != 1)
+				break;
+		}
+	}
+
+	write_tracing_file("tracing_on", "0");
+
+	/* read remaining buffer contents */
+	while (true) {
+		int n = read(trace_fd, buf, sizeof(buf));
+		if (n <= 0)
+			break;
+		if (fwrite(buf, n, 1, stdout) != 1)
+			break;
+	}
+
+out_close_fd:
+	close(trace_fd);
+out_free_pid:
+	free(trace_pid);
+out:
+	reset_tracing_files(ftrace);
+
+	return done ? 0 : -1;
+}
+
+static int perf_ftrace_config(const char *var, const char *value, void *cb)
+{
+	struct perf_ftrace *ftrace = cb;
+
+	if (prefixcmp(var, "ftrace."))
+		return 0;
+
+	if (strcmp(var, "ftrace.tracer"))
+		return -1;
+
+	if (!strcmp(value, "function_graph") ||
+	    !strcmp(value, "function")) {
+		ftrace->tracer = value;
+		return 0;
+	}
+
+	pr_err("Please select \"function_graph\" (default) or \"function\"\n");
+	return -1;
+}
+
+int cmd_ftrace(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	int ret;
+	struct perf_ftrace ftrace = {
+		.tracer = DEFAULT_TRACER,
+		.target = { .uid = UINT_MAX, },
+	};
+	const char * const ftrace_usage[] = {
+		"perf ftrace [<options>] <command>",
+		"perf ftrace [<options>] -- <command> [<options>]",
+		NULL
+	};
+	const struct option ftrace_options[] = {
+	OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
+		   "tracer to use: function_graph(default) or function"),
+	OPT_INCR('v', "verbose", &verbose,
+		 "be more verbose"),
+	OPT_END()
+	};
+
+	ret = perf_config(perf_ftrace_config, &ftrace);
+	if (ret < 0)
+		return -1;
+
+	argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
+			    PARSE_OPT_STOP_AT_NON_OPTION);
+	if (!argc)
+		usage_with_options(ftrace_usage, ftrace_options);
+
+	ftrace.evlist = perf_evlist__new();
+	if (ftrace.evlist == NULL)
+		return -ENOMEM;
+
+	ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
+	if (ret < 0)
+		goto out_delete_evlist;
+
+	ret = __cmd_ftrace(&ftrace, argc, argv);
+
+out_delete_evlist:
+	perf_evlist__delete(ftrace.evlist);
+
+	return ret;
+}
diff --git a/tools/perf/builtin-help.c b/tools/perf/builtin-help.c
index 3bdb2c78a21b..aed0d844e8c2 100644
--- a/tools/perf/builtin-help.c
+++ b/tools/perf/builtin-help.c
@@ -434,7 +434,7 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 	const char * const builtin_help_subcommands[] = {
 		"buildid-cache", "buildid-list", "diff", "evlist", "help", "list",
 		"record", "report", "bench", "stat", "timechart", "top", "annotate",
-		"script", "sched", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
+		"script", "sched", "kallsyms", "kmem", "lock", "kvm", "test", "inject", "mem", "data",
 #ifdef HAVE_LIBELF_SUPPORT
 		"probe",
 #endif
@@ -447,11 +447,13 @@ int cmd_help(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 	const char *alias;
-	int rc = 0;
+	int rc;
 
 	load_command_list("perf-", &main_cmds, &other_cmds);
 
-	perf_config(perf_help_config, &help_format);
+	rc = perf_config(perf_help_config, &help_format);
+	if (rc)
+		return rc;
 
 	argc = parse_options_subcommand(argc, argv, builtin_help_options,
 			builtin_help_subcommands, builtin_help_usage, 0);
diff --git a/tools/perf/builtin-kallsyms.c b/tools/perf/builtin-kallsyms.c
new file mode 100644
index 000000000000..224bfc454b4a
--- /dev/null
+++ b/tools/perf/builtin-kallsyms.c
@@ -0,0 +1,67 @@
+/*
+ * builtin-kallsyms.c
+ *
+ * Builtin command: Look for a symbol in the running kernel and its modules
+ *
+ * Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ *
+ * Released under the GPL v2. (and only v2, not any later version)
+ */
+#include "builtin.h"
+#include <linux/compiler.h>
+#include <subcmd/parse-options.h>
+#include "debug.h"
+#include "machine.h"
+#include "symbol.h"
+
+static int __cmd_kallsyms(int argc, const char **argv)
+{
+	int i;
+	struct machine *machine = machine__new_kallsyms();
+
+	if (machine == NULL) {
+		pr_err("Couldn't read /proc/kallsyms\n");
+		return -1;
+	}
+
+	for (i = 0; i < argc; ++i) {
+		struct map *map;
+		struct symbol *symbol = machine__find_kernel_function_by_name(machine, argv[i], &map);
+
+		if (symbol == NULL) {
+			printf("%s: not found\n", argv[i]);
+			continue;
+		}
+
+		printf("%s: %s %s %#" PRIx64 "-%#" PRIx64 " (%#" PRIx64 "-%#" PRIx64")\n",
+			symbol->name, map->dso->short_name, map->dso->long_name,
+			map->unmap_ip(map, symbol->start), map->unmap_ip(map, symbol->end),
+			symbol->start, symbol->end);
+	}
+
+	machine__delete(machine);
+	return 0;
+}
+
+int cmd_kallsyms(int argc, const char **argv, const char *prefix __maybe_unused)
+{
+	const struct option options[] = {
+	OPT_INCR('v', "verbose", &verbose, "be more verbose (show counter open errors, etc)"),
+	OPT_END()
+	};
+	const char * const kallsyms_usage[] = {
+		"perf kallsyms [<options>] symbol_name",
+		NULL
+	};
+
+	argc = parse_options(argc, argv, options, kallsyms_usage, 0);
+	if (argc < 1)
+		usage_with_options(kallsyms_usage, options);
+
+	symbol_conf.sort_by_name = true;
+	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
+	if (symbol__init(NULL) < 0)
+		return -1;
+
+	return __cmd_kallsyms(argc, argv);
+}
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 915869e00d86..6da8d083e4e5 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1065,7 +1065,7 @@ static void __print_page_alloc_result(struct perf_session *session, int n_lines)
 
 		data = rb_entry(next, struct page_stat, node);
 		sym = machine__find_kernel_function(machine, data->callsite, &map);
-		if (sym && sym->name)
+		if (sym)
 			caller = sym->name;
 		else
 			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
@@ -1107,7 +1107,7 @@ static void __print_page_caller_result(struct perf_session *session, int n_lines
 
 		data = rb_entry(next, struct page_stat, node);
 		sym = machine__find_kernel_function(machine, data->callsite, &map);
-		if (sym && sym->name)
+		if (sym)
 			caller = sym->name;
 		else
 			scnprintf(buf, sizeof(buf), "%"PRIx64, data->callsite);
@@ -1920,10 +1920,12 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 		NULL
 	};
 	struct perf_session *session;
-	int ret = -1;
 	const char errmsg[] = "No %s allocation events found.  Have you run 'perf kmem record --%s'?\n";
+	int ret = perf_config(kmem_config, NULL);
+
+	if (ret)
+		return ret;
 
-	perf_config(kmem_config, NULL);
 	argc = parse_options_subcommand(argc, argv, kmem_options,
 					kmem_subcommands, kmem_usage, 0);
 
@@ -1948,6 +1950,8 @@ int cmd_kmem(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (session == NULL)
 		return -1;
 
+	ret = -1;
+
 	if (kmem_slab) {
 		if (!perf_evlist__find_tracepoint_by_name(session->evlist,
 							  "kmem:kmalloc")) {
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index ba9322ff858b..3b9d98b5feef 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -14,6 +14,7 @@
 #include "util/parse-events.h"
 #include "util/cache.h"
 #include "util/pmu.h"
+#include "util/debug.h"
 #include <subcmd/parse-options.h>
 
 static bool desc_flag = true;
@@ -29,6 +30,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			    "Print extra event descriptions. --no-desc to not print."),
 		OPT_BOOLEAN('v', "long-desc", &long_desc_flag,
 			    "Print longer event descriptions."),
+		OPT_INCR(0, "debug", &verbose,
+			     "Enable debugging output"),
 		OPT_END()
 	};
 	const char * const list_usage[] = {
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index f87996b0cb29..1fcebc31a508 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -552,6 +552,8 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
 	OPT_BOOLEAN(0, "cache", &probe_conf.cache, "Manipulate probe cache"),
+	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
+		   "Look for files with symbols relative to this directory"),
 	OPT_END()
 	};
 	int ret;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4ec10e9427d9..6cd6776052e7 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -46,6 +46,15 @@
 #include <asm/bug.h>
 #include <linux/time64.h>
 
+struct switch_output {
+	bool		 enabled;
+	bool		 signal;
+	unsigned long	 size;
+	unsigned long	 time;
+	const char	*str;
+	bool		 set;
+};
+
 struct record {
 	struct perf_tool	tool;
 	struct record_opts	opts;
@@ -62,10 +71,33 @@ struct record {
 	bool			no_buildid_cache_set;
 	bool			buildid_all;
 	bool			timestamp_filename;
-	bool			switch_output;
+	struct switch_output	switch_output;
 	unsigned long long	samples;
 };
 
+static volatile int auxtrace_record__snapshot_started;
+static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
+static DEFINE_TRIGGER(switch_output_trigger);
+
+static bool switch_output_signal(struct record *rec)
+{
+	return rec->switch_output.signal &&
+	       trigger_is_ready(&switch_output_trigger);
+}
+
+static bool switch_output_size(struct record *rec)
+{
+	return rec->switch_output.size &&
+	       trigger_is_ready(&switch_output_trigger) &&
+	       (rec->bytes_written >= rec->switch_output.size);
+}
+
+static bool switch_output_time(struct record *rec)
+{
+	return rec->switch_output.time &&
+	       trigger_is_ready(&switch_output_trigger);
+}
+
 static int record__write(struct record *rec, void *bf, size_t size)
 {
 	if (perf_data_file__write(rec->session->file, bf, size) < 0) {
@@ -74,6 +106,10 @@ static int record__write(struct record *rec, void *bf, size_t size)
 	}
 
 	rec->bytes_written += size;
+
+	if (switch_output_size(rec))
+		trigger_hit(&switch_output_trigger);
+
 	return 0;
 }
 
@@ -193,10 +229,6 @@ static volatile int done;
 static volatile int signr = -1;
 static volatile int child_finished;
 
-static volatile int auxtrace_record__snapshot_started;
-static DEFINE_TRIGGER(auxtrace_snapshot_trigger);
-static DEFINE_TRIGGER(switch_output_trigger);
-
 static void sig_handler(int sig)
 {
 	if (sig == SIGCHLD)
@@ -386,7 +418,7 @@ static int record__mmap(struct record *rec)
 
 static int record__open(struct record *rec)
 {
-	char msg[512];
+	char msg[BUFSIZ];
 	struct perf_evsel *pos;
 	struct perf_evlist *evlist = rec->evlist;
 	struct perf_session *session = rec->session;
@@ -623,22 +655,23 @@ record__finish_output(struct record *rec)
 
 static int record__synthesize_workload(struct record *rec, bool tail)
 {
-	struct {
-		struct thread_map map;
-		struct thread_map_data map_data;
-	} thread_map;
+	int err;
+	struct thread_map *thread_map;
 
 	if (rec->opts.tail_synthesize != tail)
 		return 0;
 
-	thread_map.map.nr = 1;
-	thread_map.map.map[0].pid = rec->evlist->workload.pid;
-	thread_map.map.map[0].comm = NULL;
-	return perf_event__synthesize_thread_map(&rec->tool, &thread_map.map,
+	thread_map = thread_map__new_by_tid(rec->evlist->workload.pid);
+	if (thread_map == NULL)
+		return -1;
+
+	err = perf_event__synthesize_thread_map(&rec->tool, thread_map,
 						 process_synthesized_event,
 						 &rec->session->machines.host,
 						 rec->opts.sample_address,
 						 rec->opts.proc_map_timeout);
+	thread_map__put(thread_map);
+	return err;
 }
 
 static int record__synthesize(struct record *rec, bool tail);
@@ -712,6 +745,7 @@ static void workload_exec_failed_signal(int signo __maybe_unused,
 }
 
 static void snapshot_sig_handler(int sig);
+static void alarm_sig_handler(int sig);
 
 int __weak
 perf_event__synth_time_conv(const struct perf_event_mmap_page *pc __maybe_unused,
@@ -842,11 +876,11 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	signal(SIGTERM, sig_handler);
 	signal(SIGSEGV, sigsegv_handler);
 
-	if (rec->opts.auxtrace_snapshot_mode || rec->switch_output) {
+	if (rec->opts.auxtrace_snapshot_mode || rec->switch_output.enabled) {
 		signal(SIGUSR2, snapshot_sig_handler);
 		if (rec->opts.auxtrace_snapshot_mode)
 			trigger_on(&auxtrace_snapshot_trigger);
-		if (rec->switch_output)
+		if (rec->switch_output.enabled)
 			trigger_on(&switch_output_trigger);
 	} else {
 		signal(SIGUSR2, SIG_IGN);
@@ -1043,6 +1077,10 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 				err = fd;
 				goto out_child;
 			}
+
+			/* re-arm the alarm */
+			if (rec->switch_output.time)
+				alarm(rec->switch_output.time);
 		}
 
 		if (hits == rec->samples) {
@@ -1352,6 +1390,78 @@ out_free:
 	return ret;
 }
 
+static void switch_output_size_warn(struct record *rec)
+{
+	u64 wakeup_size = perf_evlist__mmap_size(rec->opts.mmap_pages);
+	struct switch_output *s = &rec->switch_output;
+
+	wakeup_size /= 2;
+
+	if (s->size < wakeup_size) {
+		char buf[100];
+
+		unit_number__scnprintf(buf, sizeof(buf), wakeup_size);
+		pr_warning("WARNING: switch-output data size lower than "
+			   "wakeup kernel buffer size (%s) "
+			   "expect bigger perf.data sizes\n", buf);
+	}
+}
+
+static int switch_output_setup(struct record *rec)
+{
+	struct switch_output *s = &rec->switch_output;
+	static struct parse_tag tags_size[] = {
+		{ .tag  = 'B', .mult = 1       },
+		{ .tag  = 'K', .mult = 1 << 10 },
+		{ .tag  = 'M', .mult = 1 << 20 },
+		{ .tag  = 'G', .mult = 1 << 30 },
+		{ .tag  = 0 },
+	};
+	static struct parse_tag tags_time[] = {
+		{ .tag  = 's', .mult = 1        },
+		{ .tag  = 'm', .mult = 60       },
+		{ .tag  = 'h', .mult = 60*60    },
+		{ .tag  = 'd', .mult = 60*60*24 },
+		{ .tag  = 0 },
+	};
+	unsigned long val;
+
+	if (!s->set)
+		return 0;
+
+	if (!strcmp(s->str, "signal")) {
+		s->signal = true;
+		pr_debug("switch-output with SIGUSR2 signal\n");
+		goto enabled;
+	}
+
+	val = parse_tag_value(s->str, tags_size);
+	if (val != (unsigned long) -1) {
+		s->size = val;
+		pr_debug("switch-output with %s size threshold\n", s->str);
+		goto enabled;
+	}
+
+	val = parse_tag_value(s->str, tags_time);
+	if (val != (unsigned long) -1) {
+		s->time = val;
+		pr_debug("switch-output with %s time threshold (%lu seconds)\n",
+			 s->str, s->time);
+		goto enabled;
+	}
+
+	return -1;
+
+enabled:
+	rec->timestamp_filename = true;
+	s->enabled              = true;
+
+	if (s->size && !rec->opts.no_buffering)
+		switch_output_size_warn(rec);
+
+	return 0;
+}
+
 static const char * const __record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
@@ -1519,8 +1629,10 @@ static struct option __record_options[] = {
 		    "Record build-id of all DSOs regardless of hits"),
 	OPT_BOOLEAN(0, "timestamp-filename", &record.timestamp_filename,
 		    "append timestamp to output filename"),
-	OPT_BOOLEAN(0, "switch-output", &record.switch_output,
-		    "Switch output when receive SIGUSR2"),
+	OPT_STRING_OPTARG_SET(0, "switch-output", &record.switch_output.str,
+			  &record.switch_output.set, "signal,size,time",
+			  "Switch output when receive SIGUSR2 or cross size,time threshold",
+			  "signal"),
 	OPT_BOOLEAN(0, "dry-run", &dry_run,
 		    "Parse options then exit"),
 	OPT_END()
@@ -1559,7 +1671,9 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (rec->evlist == NULL)
 		return -ENOMEM;
 
-	perf_config(perf_record_config, rec);
+	err = perf_config(perf_record_config, rec);
+	if (err)
+		return err;
 
 	argc = parse_options(argc, argv, record_options, record_usage,
 			    PARSE_OPT_STOP_AT_NON_OPTION);
@@ -1578,8 +1692,15 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -EINVAL;
 	}
 
-	if (rec->switch_output)
-		rec->timestamp_filename = true;
+	if (switch_output_setup(rec)) {
+		parse_options_usage(record_usage, record_options, "switch-output", 0);
+		return -EINVAL;
+	}
+
+	if (rec->switch_output.time) {
+		signal(SIGALRM, alarm_sig_handler);
+		alarm(rec->switch_output.time);
+	}
 
 	if (!rec->itr) {
 		rec->itr = auxtrace_record__init(rec->evlist, &err);
@@ -1629,7 +1750,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	if (rec->no_buildid_cache || rec->no_buildid) {
 		disable_buildid_cache();
-	} else if (rec->switch_output) {
+	} else if (rec->switch_output.enabled) {
 		/*
 		 * In 'perf record --switch-output', disable buildid
 		 * generation by default to reduce data file switching
@@ -1721,6 +1842,8 @@ out:
 
 static void snapshot_sig_handler(int sig __maybe_unused)
 {
+	struct record *rec = &record;
+
 	if (trigger_is_ready(&auxtrace_snapshot_trigger)) {
 		trigger_hit(&auxtrace_snapshot_trigger);
 		auxtrace_record__snapshot_started = 1;
@@ -1728,6 +1851,14 @@ static void snapshot_sig_handler(int sig __maybe_unused)
 			trigger_error(&auxtrace_snapshot_trigger);
 	}
 
-	if (trigger_is_ready(&switch_output_trigger))
+	if (switch_output_signal(rec))
+		trigger_hit(&switch_output_trigger);
+}
+
+static void alarm_sig_handler(int sig __maybe_unused)
+{
+	struct record *rec = &record;
+
+	if (switch_output_time(rec))
 		trigger_hit(&switch_output_trigger);
 }
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 06cc759a4597..dbd7fa028861 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -847,7 +847,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (ret < 0)
 		return ret;
 
-	perf_config(report__config, &report);
+	ret = perf_config(report__config, &report);
+	if (ret)
+		return ret;
 
 	argc = parse_options(argc, argv, options, report_usage, 0);
 	if (argc) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 5b134b0d1ff3..270eb2d8ca6b 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -77,6 +77,22 @@ struct sched_atom {
 
 #define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
 
+/* task state bitmask, copied from include/linux/sched.h */
+#define TASK_RUNNING		0
+#define TASK_INTERRUPTIBLE	1
+#define TASK_UNINTERRUPTIBLE	2
+#define __TASK_STOPPED		4
+#define __TASK_TRACED		8
+/* in tsk->exit_state */
+#define EXIT_DEAD		16
+#define EXIT_ZOMBIE		32
+#define EXIT_TRACE		(EXIT_ZOMBIE | EXIT_DEAD)
+/* in tsk->state again */
+#define TASK_DEAD		64
+#define TASK_WAKEKILL		128
+#define TASK_WAKING		256
+#define TASK_PARKED		512
+
 enum thread_state {
 	THREAD_SLEEPING = 0,
 	THREAD_WAIT_CPU,
@@ -206,6 +222,7 @@ struct perf_sched {
 	bool		show_cpu_visual;
 	bool		show_wakeups;
 	bool		show_migrations;
+	bool		show_state;
 	u64		skipped_samples;
 	const char	*time_str;
 	struct perf_time_interval ptime;
@@ -216,13 +233,20 @@ struct perf_sched {
 struct thread_runtime {
 	u64 last_time;      /* time of previous sched in/out event */
 	u64 dt_run;         /* run time */
-	u64 dt_wait;        /* time between CPU access (off cpu) */
+	u64 dt_sleep;       /* time between CPU access by sleep (off cpu) */
+	u64 dt_iowait;      /* time between CPU access by iowait (off cpu) */
+	u64 dt_preempt;     /* time between CPU access by preempt (off cpu) */
 	u64 dt_delay;       /* time between wakeup and sched-in */
 	u64 ready_to_run;   /* time of wakeup */
 
 	struct stats run_stats;
 	u64 total_run_time;
+	u64 total_sleep_time;
+	u64 total_iowait_time;
+	u64 total_preempt_time;
+	u64 total_delay_time;
 
+	int last_state;
 	u64 migrations;
 };
 
@@ -1821,6 +1845,9 @@ static void timehist_header(struct perf_sched *sched)
 	printf(" %-*s  %9s  %9s  %9s", comm_width,
 		"task name", "wait time", "sch delay", "run time");
 
+	if (sched->show_state)
+		printf("  %s", "state");
+
 	printf("\n");
 
 	/*
@@ -1831,9 +1858,14 @@ static void timehist_header(struct perf_sched *sched)
 	if (sched->show_cpu_visual)
 		printf(" %*s ", ncpus, "");
 
-	printf(" %-*s  %9s  %9s  %9s\n", comm_width,
+	printf(" %-*s  %9s  %9s  %9s", comm_width,
 	       "[tid/pid]", "(msec)", "(msec)", "(msec)");
 
+	if (sched->show_state)
+		printf("  %5s", "");
+
+	printf("\n");
+
 	/*
 	 * separator
 	 */
@@ -1846,18 +1878,34 @@ static void timehist_header(struct perf_sched *sched)
 		graph_dotted_line, graph_dotted_line, graph_dotted_line,
 		graph_dotted_line);
 
+	if (sched->show_state)
+		printf("  %.5s", graph_dotted_line);
+
 	printf("\n");
 }
 
+static char task_state_char(struct thread *thread, int state)
+{
+	static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
+	unsigned bit = state ? ffs(state) : 0;
+
+	/* 'I' for idle */
+	if (thread->tid == 0)
+		return 'I';
+
+	return bit < sizeof(state_to_char) - 1 ? state_to_char[bit] : '?';
+}
+
 static void timehist_print_sample(struct perf_sched *sched,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
 				  struct thread *thread,
-				  u64 t)
+				  u64 t, int state)
 {
 	struct thread_runtime *tr = thread__priv(thread);
 	u32 max_cpus = sched->max_cpu + 1;
 	char tstr[64];
+	u64 wait_time;
 
 	timestamp__scnprintf_usec(t, tstr, sizeof(tstr));
 	printf("%15s [%04d] ", tstr, sample->cpu);
@@ -1880,10 +1928,15 @@ static void timehist_print_sample(struct perf_sched *sched,
 
 	printf(" %-*s ", comm_width, timehist_get_commstr(thread));
 
-	print_sched_time(tr->dt_wait, 6);
+	wait_time = tr->dt_sleep + tr->dt_iowait + tr->dt_preempt;
+	print_sched_time(wait_time, 6);
+
 	print_sched_time(tr->dt_delay, 6);
 	print_sched_time(tr->dt_run, 6);
 
+	if (sched->show_state)
+		printf(" %5c ", task_state_char(thread, state));
+
 	if (sched->show_wakeups)
 		printf("  %-*s", comm_width, "");
 
@@ -1930,8 +1983,11 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 					 u64 t, u64 tprev)
 {
 	r->dt_delay   = 0;
-	r->dt_wait    = 0;
+	r->dt_sleep   = 0;
+	r->dt_iowait  = 0;
+	r->dt_preempt = 0;
 	r->dt_run     = 0;
+
 	if (tprev) {
 		r->dt_run = t - tprev;
 		if (r->ready_to_run) {
@@ -1943,12 +1999,25 @@ static void timehist_update_runtime_stats(struct thread_runtime *r,
 
 		if (r->last_time > tprev)
 			pr_debug("time travel: last sched out time for task > previous sched_switch event\n");
-		else if (r->last_time)
-			r->dt_wait = tprev - r->last_time;
+		else if (r->last_time) {
+			u64 dt_wait = tprev - r->last_time;
+
+			if (r->last_state == TASK_RUNNING)
+				r->dt_preempt = dt_wait;
+			else if (r->last_state == TASK_UNINTERRUPTIBLE)
+				r->dt_iowait = dt_wait;
+			else
+				r->dt_sleep = dt_wait;
+		}
 	}
 
 	update_stats(&r->run_stats, r->dt_run);
-	r->total_run_time += r->dt_run;
+
+	r->total_run_time     += r->dt_run;
+	r->total_delay_time   += r->dt_delay;
+	r->total_sleep_time   += r->dt_sleep;
+	r->total_iowait_time  += r->dt_iowait;
+	r->total_preempt_time += r->dt_preempt;
 }
 
 static bool is_idle_sample(struct perf_sample *sample,
@@ -1998,7 +2067,7 @@ static void save_task_callchain(struct perf_sched *sched,
 			break;
 
 		sym = node->sym;
-		if (sym && sym->name) {
+		if (sym) {
 			if (!strcmp(sym->name, "schedule") ||
 			    !strcmp(sym->name, "__schedule") ||
 			    !strcmp(sym->name, "preempt_schedule"))
@@ -2373,6 +2442,8 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	struct thread_runtime *tr = NULL;
 	u64 tprev, t = sample->time;
 	int rc = 0;
+	int state = perf_evsel__intval(evsel, sample, "prev_state");
+
 
 	if (machine__resolve(machine, &al, sample) < 0) {
 		pr_err("problem processing %d event. skipping it\n",
@@ -2447,8 +2518,10 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 			 * time.  we only care total run time and run stat.
 			 */
 			last_tr->dt_run = 0;
-			last_tr->dt_wait = 0;
 			last_tr->dt_delay = 0;
+			last_tr->dt_sleep = 0;
+			last_tr->dt_iowait = 0;
+			last_tr->dt_preempt = 0;
 
 			if (itr->cursor.nr)
 				callchain_append(&itr->callchain, &itr->cursor, t - tprev);
@@ -2458,7 +2531,7 @@ static int timehist_sched_change_event(struct perf_tool *tool,
 	}
 
 	if (!sched->summary_only)
-		timehist_print_sample(sched, sample, &al, thread, t);
+		timehist_print_sample(sched, sample, &al, thread, t, state);
 
 out:
 	if (sched->hist_time.start == 0 && t >= ptime->start)
@@ -2470,6 +2543,9 @@ out:
 		/* time of this sched_switch event becomes last time task seen */
 		tr->last_time = sample->time;
 
+		/* last state is used to determine where to account wait time */
+		tr->last_state = state;
+
 		/* sched out event for task so reset ready to run time */
 		tr->ready_to_run = 0;
 	}
@@ -2526,7 +2602,26 @@ static void print_thread_runtime(struct thread *t,
 	printf("\n");
 }
 
+static void print_thread_waittime(struct thread *t,
+				  struct thread_runtime *r)
+{
+	printf("%*s   %5d  %9" PRIu64 " ",
+	       comm_width, timehist_get_commstr(t), t->ppid,
+	       (u64) r->run_stats.n);
+
+	print_sched_time(r->total_run_time, 8);
+	print_sched_time(r->total_sleep_time, 6);
+	printf(" ");
+	print_sched_time(r->total_iowait_time, 6);
+	printf(" ");
+	print_sched_time(r->total_preempt_time, 6);
+	printf(" ");
+	print_sched_time(r->total_delay_time, 6);
+	printf("\n");
+}
+
 struct total_run_stats {
+	struct perf_sched *sched;
 	u64  sched_count;
 	u64  task_count;
 	u64  total_run_time;
@@ -2545,7 +2640,11 @@ static int __show_thread_runtime(struct thread *t, void *priv)
 		stats->task_count++;
 		stats->sched_count += r->run_stats.n;
 		stats->total_run_time += r->total_run_time;
-		print_thread_runtime(t, r);
+
+		if (stats->sched->show_state)
+			print_thread_waittime(t, r);
+		else
+			print_thread_runtime(t, r);
 	}
 
 	return 0;
@@ -2633,18 +2732,24 @@ static void timehist_print_summary(struct perf_sched *sched,
 	u64 hist_time = sched->hist_time.end - sched->hist_time.start;
 
 	memset(&totals, 0, sizeof(totals));
+	totals.sched = sched;
 
 	if (sched->idle_hist) {
 		printf("\nIdle-time summary\n");
 		printf("%*s  parent  sched-out  ", comm_width, "comm");
 		printf("  idle-time   min-idle    avg-idle    max-idle  stddev  migrations\n");
+	} else if (sched->show_state) {
+		printf("\nWait-time summary\n");
+		printf("%*s  parent   sched-in  ", comm_width, "comm");
+		printf("   run-time      sleep      iowait     preempt       delay\n");
 	} else {
 		printf("\nRuntime summary\n");
 		printf("%*s  parent   sched-in  ", comm_width, "comm");
 		printf("   run-time    min-run     avg-run     max-run  stddev  migrations\n");
 	}
 	printf("%*s            (count)  ", comm_width, "");
-	printf("     (msec)     (msec)      (msec)      (msec)       %%\n");
+	printf("     (msec)     (msec)      (msec)      (msec)       %s\n",
+	       sched->show_state ? "(msec)" : "%");
 	printf("%.117s\n", graph_dotted_line);
 
 	machine__for_each_thread(m, show_thread_runtime, &totals);
@@ -3240,6 +3345,7 @@ int cmd_sched(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN('I', "idle-hist", &sched.idle_hist, "Show idle events only"),
 	OPT_STRING(0, "time", &sched.time_str, "str",
 		   "Time span for analysis (start,stop)"),
+	OPT_BOOLEAN(0, "state", &sched.show_state, "Show task state when sched-out"),
 	OPT_PARENT(sched_options)
 	};
 
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 2f3ff69fc4e7..c0783b4f7b6c 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2180,7 +2180,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Show the mmap events"),
 	OPT_BOOLEAN('\0', "show-switch-events", &script.show_switch_events,
 		    "Show context switch events (if recorded)"),
-	OPT_BOOLEAN('f', "force", &file.force, "don't complain, do it"),
+	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
 	OPT_BOOLEAN(0, "ns", &nanosecs,
 		    "Use 9 decimal places when displaying time"),
 	OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
@@ -2212,6 +2212,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused)
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 
 	file.path = input_name;
+	file.force = symbol_conf.force;
 
 	if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
 		rec_script_path = get_script_path(argv[1], RECORD_SUFFIX);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a02f2e965628..f28719178b51 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -533,7 +533,7 @@ static int store_counter_ids(struct perf_evsel *counter)
 static int __run_perf_stat(int argc, const char **argv)
 {
 	int interval = stat_config.interval;
-	char msg[512];
+	char msg[BUFSIZ];
 	unsigned long long t0, t1;
 	struct perf_evsel *counter;
 	struct timespec ts;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 3df4178ba378..5a7fd7af3a6d 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -643,7 +643,7 @@ repeat:
 		case -1:
 			if (errno == EINTR)
 				continue;
-			/* Fall trhu */
+			__fallthrough;
 		default:
 			c = getc(stdin);
 			tcsetattr(0, TCSAFLUSH, &save);
@@ -859,7 +859,7 @@ static void perf_top__mmap_read(struct perf_top *top)
 
 static int perf_top__start_counters(struct perf_top *top)
 {
-	char msg[512];
+	char msg[BUFSIZ];
 	struct perf_evsel *counter;
 	struct perf_evlist *evlist = top->evlist;
 	struct record_opts *opts = &top->record_opts;
@@ -1216,7 +1216,9 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	if (top.evlist == NULL)
 		return -ENOMEM;
 
-	perf_config(perf_top_config, &top);
+	status = perf_config(perf_top_config, &top);
+	if (status)
+		return status;
 
 	argc = parse_options(argc, argv, options, top_usage, 0);
 	if (argc)
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 206bf72b77fc..40ef9b293d1b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -40,6 +40,7 @@
 
 #include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
 #include <stdlib.h>
+#include <string.h>
 #include <linux/err.h>
 #include <linux/filter.h>
 #include <linux/audit.h>
@@ -2699,6 +2700,91 @@ static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
 		evsel->handler = handler;
 }
 
+/*
+ * XXX: Hackish, just splitting the combined -e+--event (syscalls
+ * (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
+ * existing facilities unchanged (trace->ev_qualifier + parse_options()).
+ *
+ * It'd be better to introduce a parse_options() variant that would return a
+ * list with the terms it didn't match to an event...
+ */
+static int trace__parse_events_option(const struct option *opt, const char *str,
+				      int unset __maybe_unused)
+{
+	struct trace *trace = (struct trace *)opt->value;
+	const char *s = str;
+	char *sep = NULL, *lists[2] = { NULL, NULL, };
+	int len = strlen(str), err = -1, list;
+	char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
+	char group_name[PATH_MAX];
+
+	if (strace_groups_dir == NULL)
+		return -1;
+
+	if (*s == '!') {
+		++s;
+		trace->not_ev_qualifier = true;
+	}
+
+	while (1) {
+		if ((sep = strchr(s, ',')) != NULL)
+			*sep = '\0';
+
+		list = 0;
+		if (syscalltbl__id(trace->sctbl, s) >= 0) {
+			list = 1;
+		} else {
+			path__join(group_name, sizeof(group_name), strace_groups_dir, s);
+			if (access(group_name, R_OK) == 0)
+				list = 1;
+		}
+
+		if (lists[list]) {
+			sprintf(lists[list] + strlen(lists[list]), ",%s", s);
+		} else {
+			lists[list] = malloc(len);
+			if (lists[list] == NULL)
+				goto out;
+			strcpy(lists[list], s);
+		}
+
+		if (!sep)
+			break;
+
+		*sep = ',';
+		s = sep + 1;
+	}
+
+	if (lists[1] != NULL) {
+		struct strlist_config slist_config = {
+			.dirname = strace_groups_dir,
+		};
+
+		trace->ev_qualifier = strlist__new(lists[1], &slist_config);
+		if (trace->ev_qualifier == NULL) {
+			fputs("Not enough memory to parse event qualifier", trace->output);
+			goto out;
+		}
+
+		if (trace__validate_ev_qualifier(trace))
+			goto out;
+	}
+
+	err = 0;
+
+	if (lists[0]) {
+		struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
+					       "event selector. use 'perf list' to list available events",
+					       parse_events_option);
+		err = parse_events_option(&o, lists[0], 0);
+	}
+out:
+	if (sep)
+		*sep = ',';
+
+	return err;
+}
+
 int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	const char *trace_usage[] = {
@@ -2730,15 +2816,15 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		.max_stack = UINT_MAX,
 	};
 	const char *output_name = NULL;
-	const char *ev_qualifier_str = NULL;
 	const struct option trace_options[] = {
-	OPT_CALLBACK(0, "event", &trace.evlist, "event",
-		     "event selector. use 'perf list' to list available events",
-		     parse_events_option),
+	OPT_CALLBACK('e', "event", &trace, "event",
+		     "event/syscall selector. use 'perf list' to list available events",
+		     trace__parse_events_option),
 	OPT_BOOLEAN(0, "comm", &trace.show_comm,
 		    "show the thread COMM next to its id"),
 	OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
-	OPT_STRING('e', "expr", &ev_qualifier_str, "expr", "list of syscalls to trace"),
+	OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace",
+		     trace__parse_events_option),
 	OPT_STRING('o', "output", &output_name, "file", "output file name"),
 	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
 	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
@@ -2863,7 +2949,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 		return -1;
 	}
 
-	if (!trace.trace_syscalls && ev_qualifier_str) {
+	if (!trace.trace_syscalls && trace.ev_qualifier) {
 		pr_err("The -e option can't be used with --no-syscalls.\n");
 		goto out;
 	}
@@ -2878,28 +2964,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
 
 	trace.open_id = syscalltbl__id(trace.sctbl, "open");
 
-	if (ev_qualifier_str != NULL) {
-		const char *s = ev_qualifier_str;
-		struct strlist_config slist_config = {
-			.dirname = system_path(STRACE_GROUPS_DIR),
-		};
-
-		trace.not_ev_qualifier = *s == '!';
-		if (trace.not_ev_qualifier)
-			++s;
-		trace.ev_qualifier = strlist__new(s, &slist_config);
-		if (trace.ev_qualifier == NULL) {
-			fputs("Not enough memory to parse event qualifier",
-			      trace.output);
-			err = -ENOMEM;
-			goto out_close;
-		}
-
-		err = trace__validate_ev_qualifier(&trace);
-		if (err)
-			goto out_close;
-	}
-
 	err = target__validate(&trace.opts.target);
 	if (err) {
 		target__strerror(&trace.opts.target, err, bf, sizeof(bf));
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 0bcf68e98ccc..036e1e35b1a8 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -23,6 +23,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix);
 int cmd_evlist(int argc, const char **argv, const char *prefix);
 int cmd_help(int argc, const char **argv, const char *prefix);
 int cmd_sched(int argc, const char **argv, const char *prefix);
+int cmd_kallsyms(int argc, const char **argv, const char *prefix);
 int cmd_list(int argc, const char **argv, const char *prefix);
 int cmd_record(int argc, const char **argv, const char *prefix);
 int cmd_report(int argc, const char **argv, const char *prefix);
@@ -40,6 +41,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix);
 int cmd_inject(int argc, const char **argv, const char *prefix);
 int cmd_mem(int argc, const char **argv, const char *prefix);
 int cmd_data(int argc, const char **argv, const char *prefix);
+int cmd_ftrace(int argc, const char **argv, const char *prefix);
 
 int find_scripts(char **scripts_array, char **scripts_path_array);
 #endif
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index ab5cbaa170d0..ac3efd396a72 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -11,7 +11,9 @@ perf-data			mainporcelain common
 perf-diff			mainporcelain common
 perf-config			mainporcelain common
 perf-evlist			mainporcelain common
+perf-ftrace			mainporcelain common
 perf-inject			mainporcelain common
+perf-kallsyms			mainporcelain common
 perf-kmem			mainporcelain common
 perf-kvm			mainporcelain common
 perf-list			mainporcelain common
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index aa23b3347d6b..6d5479e03e0d 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -29,7 +29,6 @@ const char perf_usage_string[] =
 const char perf_more_info_string[] =
 	"See 'perf help COMMAND' for more information on a specific command.";
 
-int use_browser = -1;
 static int use_pager = -1;
 const char *input_name;
 
@@ -47,6 +46,7 @@ static struct cmd_struct commands[] = {
 	{ "diff",	cmd_diff,	0 },
 	{ "evlist",	cmd_evlist,	0 },
 	{ "help",	cmd_help,	0 },
+	{ "kallsyms",	cmd_kallsyms,	0 },
 	{ "list",	cmd_list,	0 },
 	{ "record",	cmd_record,	0 },
 	{ "report",	cmd_report,	0 },
@@ -71,6 +71,7 @@ static struct cmd_struct commands[] = {
 	{ "inject",	cmd_inject,	0 },
 	{ "mem",	cmd_mem,	0 },
 	{ "data",	cmd_data,	0 },
+	{ "ftrace",	cmd_ftrace,	0 },
 };
 
 struct pager_config {
@@ -89,11 +90,12 @@ static int pager_command_config(const char *var, const char *value, void *data)
 /* returns 0 for "no pager", 1 for "use pager", and -1 for "not specified" */
 int check_pager_config(const char *cmd)
 {
+	int err;
 	struct pager_config c;
 	c.cmd = cmd;
 	c.val = -1;
-	perf_config(pager_command_config, &c);
-	return c.val;
+	err = perf_config(pager_command_config, &c);
+	return err ?: c.val;
 }
 
 static int browser_command_config(const char *var, const char *value, void *data)
@@ -112,11 +114,12 @@ static int browser_command_config(const char *var, const char *value, void *data
  */
 static int check_browser_config(const char *cmd)
 {
+	int err;
 	struct pager_config c;
 	c.cmd = cmd;
 	c.val = -1;
-	perf_config(browser_command_config, &c);
-	return c.val;
+	err = perf_config(browser_command_config, &c);
+	return err ?: c.val;
 }
 
 static void commit_pager_choice(void)
@@ -329,8 +332,6 @@ static int handle_alias(int *argcp, const char ***argv)
 	return ret;
 }
 
-const char perf_version_string[] = PERF_VERSION;
-
 #define RUN_SETUP	(1<<0)
 #define USE_PAGER	(1<<1)
 
@@ -510,6 +511,7 @@ static void cache_line_size(int *cacheline_sizep)
 
 int main(int argc, const char **argv)
 {
+	int err;
 	const char *cmd;
 	char sbuf[STRERR_BUFSIZE];
 	int value;
@@ -535,7 +537,9 @@ int main(int argc, const char **argv)
 	srandom(time(NULL));
 
 	perf_config__init();
-	perf_config(perf_default_config, NULL);
+	err = perf_config(perf_default_config, NULL);
+	if (err)
+		return err;
 	set_buildid_dir(NULL);
 
 	/* get debugfs/tracefs mount point from /proc/mounts */
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
new file mode 100644
index 000000000000..076459c51d4e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_C_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x34",
+        "EventName": "UNC_C_LLC_LOOKUP.ANY",
+        "Filter": "filter_state=0x1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x11",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x37",
+        "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "filter_opc=0x187",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_READ",
+        "Filter": "filter_opc=0x187,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_WRITE",
+        "Filter": "filter_opc=0x18f,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+        "Filter": "filter_opc=0x190",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x191",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+        "Filter": "filter_opc=0x192",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+        "Filter": "filter_opc=0x180,filter_tid=0x3e",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x181",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "filter_opc=0x18c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "filter_opc=0x18d",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0xC",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+        "PerPkg": "1",
+        "UMask": "0x40",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x20",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPS",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x8",
+        "Unit": "HA"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
new file mode 100644
index 000000000000..d17dc235f734
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x86",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
new file mode 100644
index 000000000000..b44d43088bbb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-power.json
@@ -0,0 +1,84 @@
+[
+    {
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA",
+        "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+        "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x6",
+        "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5",
+        "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x74",
+        "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
new file mode 100644
index 000000000000..076459c51d4e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_C_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x34",
+        "EventName": "UNC_C_LLC_LOOKUP.ANY",
+        "Filter": "filter_state=0x1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x11",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x37",
+        "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "filter_opc=0x187",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_READ",
+        "Filter": "filter_opc=0x187,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_WRITE",
+        "Filter": "filter_opc=0x18f,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+        "Filter": "filter_opc=0x190",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x191",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+        "Filter": "filter_opc=0x192",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+        "Filter": "filter_opc=0x180,filter_tid=0x3e",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x181",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "filter_opc=0x18c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "filter_opc=0x18d",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0xC",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+        "PerPkg": "1",
+        "UMask": "0x40",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x20",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPS",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x8",
+        "Unit": "HA"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
new file mode 100644
index 000000000000..39387f7909b2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json
@@ -0,0 +1,28 @@
+[
+    {
+        "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x14",
+        "EventName": "UNC_Q_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x2",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x4",
+        "Unit": "QPI LL"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
new file mode 100644
index 000000000000..d17dc235f734
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x86",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
new file mode 100644
index 000000000000..b44d43088bbb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-power.json
@@ -0,0 +1,84 @@
+[
+    {
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA",
+        "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+        "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x6",
+        "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5",
+        "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x74",
+        "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
new file mode 100644
index 000000000000..076459c51d4e
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-cache.json
@@ -0,0 +1,317 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_C_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x34",
+        "EventName": "UNC_C_LLC_LOOKUP.ANY",
+        "Filter": "filter_state=0x1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x11",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x37",
+        "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads (from cpu) . Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "filter_opc=0x187",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_READ",
+        "Filter": "filter_opc=0x187,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "MMIO writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.MMIO_WRITE",
+        "Filter": "filter_opc=0x18f,filter_nc=1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+        "Filter": "filter_opc=0x190",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x191",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+        "Filter": "filter_opc=0x192",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "ItoM write misses (as part of fast string memcpy stores) + PCIe full line writes. Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write misses (full cache line). Derived from unc_c_tor_inserts.miss_opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe writes (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+        "Filter": "filter_opc=0x180,filter_tid=0x3e",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "L2 demand and L2 prefetch code references to LLC. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x181",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "filter_opc=0x18c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "filter_opc=0x18d",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe write references (full cache line). Derived from unc_c_tor_inserts.opcode",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_WRITE",
+        "Filter": "filter_opc=0x1c8,filter_tid=0x3e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to local home agent. Derived from unc_h_requests.reads_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "read requests to remote home agent. Derived from unc_h_requests.reads_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0xC",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to local home agent. Derived from unc_h_requests.writes_local",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to remote home agent. Derived from unc_h_requests.writes_remote",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Conflict requests (requests for same address from multiple agents simultaneously). Derived from unc_h_snoop_resp.rspcnflct",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPCNFLCT",
+        "PerPkg": "1",
+        "UMask": "0x40",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x20",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPS",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x8",
+        "Unit": "HA"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
new file mode 100644
index 000000000000..39387f7909b2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json
@@ -0,0 +1,28 @@
+[
+    {
+        "BriefDescription": "QPI clock ticks. Derived from unc_q_clockticks",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x14",
+        "EventName": "UNC_Q_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x2",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x4",
+        "Unit": "QPI LL"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
new file mode 100644
index 000000000000..d17dc235f734
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-memory.json
@@ -0,0 +1,83 @@
+[
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks. Derived from unc_m_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x86",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charges due to page misses. Derived from unc_m_pre_count.page_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for reads. Derived from unc_m_pre_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x4",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Pre-charge for writes. Derived from unc_m_pre_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0x8",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
new file mode 100644
index 000000000000..b44d43088bbb
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-power.json
@@ -0,0 +1,84 @@
+[
+    {
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C0 and C1. Derived from unc_p_power_state_occupancy.cores_c0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C3. Derived from unc_p_power_state_occupancy.cores_c3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "C6 and C7. Derived from unc_p_power_state_occupancy.cores_c6",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "External Prochot. Derived from unc_p_prochot_external_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xA",
+        "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+        "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Thermal Strongest Upper Limit Cycles. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "OS Strongest Upper Limit Cycles. Derived from unc_p_freq_max_os_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x6",
+        "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Power Strongest Upper Limit Cycles. Derived from unc_p_freq_max_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5",
+        "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x74",
+        "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
new file mode 100644
index 000000000000..2efdc6772e0b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-cache.json
@@ -0,0 +1,322 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_C_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "Counter": "0,1",
+        "EventCode": "0x34",
+        "EventName": "UNC_C_LLC_LOOKUP.ANY",
+        "Filter": "filter_state=0x1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x11",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "Counter": "0,1",
+        "EventCode": "0x37",
+        "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "filter_opc=0x187",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for RFO. Derived from unc_c_tor_inserts.miss_opcode.rfo_prefetch",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.RFO_LLC_PREFETCH",
+        "Filter": "filter_opc=0x190",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for code reads. Derived from unc_c_tor_inserts.miss_opcode.code",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.CODE_LLC_PREFETCH",
+        "Filter": "filter_opc=0x191",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC prefetch misses for data reads. Derived from unc_c_tor_inserts.miss_opcode.data_read",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_LLC_PREFETCH",
+        "Filter": "filter_opc=0x192",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "Filter": "filter_opc=0x19c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe read current. Derived from unc_c_tor_inserts.miss_opcode.pcie_read",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.ITOM_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe non-snoop reads. Derived from unc_c_tor_inserts.miss_opcode.pcie_read",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_NON_SNOOP_READ",
+        "Filter": "filter_opc=0x1e4",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.miss_opcode.pcie_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_NON_SNOOP_WRITE",
+        "Filter": "filter_opc=0x1e6",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "filter_opc=0x18c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "filter_opc=0x18d",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ",
+        "Filter": "filter_opc=0x195",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_WRITE",
+        "Filter": "filter_opc=0x19c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.ITOM_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_READ",
+        "Filter": "filter_opc=0x1e4",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+        "Filter": "filter_opc=0x1e5",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_WRITE",
+        "Filter": "filter_opc=0x1e6",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy for all LLC misses that are addressed to local memory. Derived from unc_c_tor_occupancy.miss_local",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.MISS_LOCAL",
+        "PerPkg": "1",
+        "UMask": "0x2A",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy for all LLC misses that are addressed to remote memory. Derived from unc_c_tor_occupancy.miss_remote",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.MISS_REMOTE",
+        "PerPkg": "1",
+        "UMask": "0x8A",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Read requests to home agent. Derived from unc_h_requests.reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Write requests to home agent. Derived from unc_h_requests.writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0xC",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache along with writeback to memory. Derived from unc_h_snoop_resp.rsp_fwd_wb",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSP_FWD_WB",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x20",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "M line forwarded from remote cache with no writeback to memory. Derived from unc_h_snoop_resp.rspifwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPIFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x4",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line response from remote cache. Derived from unc_h_snoop_resp.rsps",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPS",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x2",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "Shared line forwarded from remote cache. Derived from unc_h_snoop_resp.rspsfwd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x21",
+        "EventName": "UNC_H_SNOOP_RESP.RSPSFWD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x8",
+        "Unit": "HA"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
new file mode 100644
index 000000000000..d7e2fda1d695
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json
@@ -0,0 +1,46 @@
+[
+    {
+        "BriefDescription": "QPI clock ticks. Use to get percentages for QPI cycles events. Derived from unc_q_clockticks",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x14",
+        "EventName": "UNC_Q_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x10",
+        "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
+        "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
+        "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x2",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x4",
+        "Unit": "QPI LL"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
new file mode 100644
index 000000000000..ac4ad4d6357b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-memory.json
@@ -0,0 +1,75 @@
+[
+    {
+        "BriefDescription": "Memory page activates for reads and writes. Derived from unc_m_act_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_M_ACT_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Umask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0xC",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks. Use to generate percentages for memory controller CYCLES events. Derived from unc_m_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x86",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
new file mode 100644
index 000000000000..dc2586db0dfc
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-power.json
@@ -0,0 +1,249 @@
+[
+    {
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_BAND0_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_BAND1_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_BAND2_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_BAND3_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c6",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xa",
+        "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+        "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when thermal conditions are the upper limit on frequency.  This is related to the THERMAL_THROTTLE CYCLES_ABOVE_TEMP event, which always counts cycles when we are above the thermal temperature.  This event (STRONGEST_UPPER_LIMIT) is sampled at the output of the algorithm that determines the actual frequency, while THERMAL_THROTTLE looks at the input. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x6",
+        "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5",
+        "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x7",
+        "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when the system is changing frequency.  This can not be filtered by thread ID.  One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system. Derived from unc_p_freq_trans_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x60",
+        "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
+        "Filter": "filter_band0=1200",
+        "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
+        "Filter": "filter_band1=2000",
+        "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
+        "Filter": "filter_band2=3000",
+        "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
+        "Filter": "filter_band3=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band0=1200",
+        "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band1=2000",
+        "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band2=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band3=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
new file mode 100644
index 000000000000..2f23cf0129e7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-cache.json
@@ -0,0 +1,209 @@
+[
+    {
+        "BriefDescription": "Uncore cache clock ticks. Derived from unc_c_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_C_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "All LLC Misses (code+ data rd + data wr - including demand and prefetch). Derived from unc_c_llc_lookup.any",
+        "Counter": "0,1",
+        "EventCode": "0x34",
+        "EventName": "UNC_C_LLC_LOOKUP.ANY",
+        "Filter": "filter_state=0x1",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x11",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "M line evictions from LLC (writebacks to memory). Derived from unc_c_llc_victims.m_state",
+        "Counter": "0,1",
+        "EventCode": "0x37",
+        "EventName": "UNC_C_LLC_VICTIMS.M_STATE",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - demand and prefetch data reads - excludes LLC prefetches. Derived from unc_c_tor_inserts.miss_opcode.demand",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.DATA_READ",
+        "Filter": "filter_opc=0x182",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses - Uncacheable reads. Derived from unc_c_tor_inserts.miss_opcode.uncacheable",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.UNCACHEABLE",
+        "Filter": "filter_opc=0x187",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe allocating writes that miss LLC - DDIO misses. Derived from unc_c_tor_inserts.miss_opcode.ddio_miss",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.PCIE_WRITE",
+        "Filter": "filter_opc=0x19c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "LLC misses for ItoM writes (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.miss_opcode.itom_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_MISSES.ITOM_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (full cache line). Derived from unc_c_tor_inserts.opcode.streaming_full",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_FULL",
+        "Filter": "filter_opc=0x18c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Streaming stores (partial cache line). Derived from unc_c_tor_inserts.opcode.streaming_partial",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.STREAMING_PARTIAL",
+        "Filter": "filter_opc=0x18d",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Partial PCIe reads. Derived from unc_c_tor_inserts.opcode.pcie_partial",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_PARTIAL_READ",
+        "Filter": "filter_opc=0x195",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe allocating writes that hit in LLC (DDIO hits). Derived from unc_c_tor_inserts.opcode.ddio_hit",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_WRITE",
+        "Filter": "filter_opc=0x19c",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe read current. Derived from unc_c_tor_inserts.opcode.pcie_read_current",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_READ",
+        "Filter": "filter_opc=0x19e",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "ItoM write hits (as part of fast string memcpy stores). Derived from unc_c_tor_inserts.opcode.itom_write_hit",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.ITOM_WRITE",
+        "Filter": "filter_opc=0x1c8",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop reads. Derived from unc_c_tor_inserts.opcode.pcie_read",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_READ",
+        "Filter": "filter_opc=0x1e4",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop writes (partial). Derived from unc_c_tor_inserts.opcode.pcie_partial_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_PARTIAL_WRITE",
+        "Filter": "filter_opc=0x1e5",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "PCIe non-snoop writes (full line). Derived from unc_c_tor_inserts.opcode.pcie_full_write",
+        "Counter": "0,1",
+        "EventCode": "0x35",
+        "EventName": "LLC_REFERENCES.PCIE_NS_WRITE",
+        "Filter": "filter_opc=0x1e6",
+        "PerPkg": "1",
+        "ScaleUnit": "64Bytes",
+        "UMask": "0x1",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for all LLC misses; we divide this by UNC_C_CLOCKTICKS to get average Q depth. Derived from unc_c_tor_occupancy.miss_all",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.MISS_ALL",
+        "Filter": "filter_opc=0x182",
+        "MetricExpr": "(UNC_C_TOR_OCCUPANCY.MISS_ALL / UNC_C_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "UMask": "0xa",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "Occupancy counter for LLC data reads (demand and L2 prefetch). Derived from unc_c_tor_occupancy.miss_opcode.llc_data_read",
+        "EventCode": "0x36",
+        "EventName": "UNC_C_TOR_OCCUPANCY.LLC_DATA_READ",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "CBO"
+    },
+    {
+        "BriefDescription": "read requests to home agent. Derived from unc_h_requests.reads",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.READS",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "HA"
+    },
+    {
+        "BriefDescription": "write requests to home agent. Derived from unc_h_requests.writes",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_H_REQUESTS.WRITES",
+        "PerPkg": "1",
+        "UMask": "0xc",
+        "Unit": "HA"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
new file mode 100644
index 000000000000..63351876eb57
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json
@@ -0,0 +1,46 @@
+[
+    {
+        "BriefDescription": "QPI clock ticks. Used to get percentages of QPI cycles events. Derived from unc_q_clockticks",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x14",
+        "EventName": "UNC_Q_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Cycles where receiving QPI link is in half-width mode. Derived from unc_q_rxl0p_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x10",
+        "EventName": "UNC_Q_RxL0P_POWER_CYCLES",
+        "MetricExpr": "(UNC_Q_RxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Cycles where transmitting QPI link is in half-width mode. Derived from unc_q_txl0p_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_Q_TxL0P_POWER_CYCLES",
+        "MetricExpr": "(UNC_Q_TxL0P_POWER_CYCLES / UNC_Q_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of data flits transmitted . Derived from unc_q_txl_flits_g0.data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x2",
+        "Unit": "QPI LL"
+    },
+    {
+        "BriefDescription": "Number of non data (control) flits transmitted . Derived from unc_q_txl_flits_g0.non_data",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_Q_TxL_FLITS_G0.NON_DATA",
+        "PerPkg": "1",
+        "ScaleUnit": "8Bytes",
+        "UMask": "0x4",
+        "Unit": "QPI LL"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
new file mode 100644
index 000000000000..e2cf6daa7b37
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-memory.json
@@ -0,0 +1,79 @@
+[
+    {
+        "BriefDescription": "Memory page activates. Derived from unc_m_act_count",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x1",
+        "EventName": "UNC_M_ACT_COUNT",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "read requests to memory controller. Derived from unc_m_cas_count.rd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "UMask": "0x3",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "write requests to memory controller. Derived from unc_m_cas_count.wr",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "UMask": "0xc",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory controller clock ticks. Used to get percentages of memory controller cycles events. Derived from unc_m_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_M_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles where DRAM ranks are in power down (CKE) mode. Derived from unc_m_power_channel_ppd",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x85",
+        "EventName": "UNC_M_POWER_CHANNEL_PPD",
+        "MetricExpr": "(UNC_M_POWER_CHANNEL_PPD / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles all ranks are in critical thermal throttle. Derived from unc_m_power_critical_throttle_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x86",
+        "EventName": "UNC_M_POWER_CRITICAL_THROTTLE_CYCLES",
+        "MetricExpr": "(UNC_M_POWER_CRITICAL_THROTTLE_CYCLES / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Cycles Memory is in self refresh power mode. Derived from unc_m_power_self_refresh",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x43",
+        "EventName": "UNC_M_POWER_SELF_REFRESH",
+        "MetricExpr": "(UNC_M_POWER_SELF_REFRESH / UNC_M_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Memory page conflicts. Derived from unc_m_pre_count.page_miss",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x2",
+        "EventName": "UNC_M_PRE_COUNT.PAGE_MISS",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "iMC"
+    },
+    {
+        "BriefDescription": "Occupancy counter for memory read queue. Derived from unc_m_rpq_occupancy",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_M_RPQ_OCCUPANCY",
+        "PerPkg": "1",
+        "Unit": "iMC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
new file mode 100644
index 000000000000..bbe36d547386
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-power.json
@@ -0,0 +1,248 @@
+[
+    {
+        "BriefDescription": "PCU clock ticks. Use to get percentages of PCU cycles events. Derived from unc_p_clockticks",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_CLOCKTICKS",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_BAND0_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_BAND1_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_BAND2_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_BAND3_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band0=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_BAND0_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND0_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transistioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band1=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_BAND1_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND1_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band2=XXX with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_BAND2_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND2_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to the frequency that is configured in the filter.  (filter_band3=XXX, with XXX in 100Mhz units). One can also use inversion (filter_inv=1) to track cycles when we were less than the configured frequency. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_BAND3_TRANSITIONS",
+        "Filter": "edge=1",
+        "MetricExpr": "(UNC_P_FREQ_BAND3_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C0.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c0",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C0 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C3.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events and occupancy triggering to capture other details. Derived from unc_p_power_state_occupancy.cores_c3",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C3 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "This is an occupancy event that tracks the number of cores that are in C6.  It can be used by itself to get the average number of cores in C0, with threshholding to generate histograms, or with other PCU events . Derived from unc_p_power_state_occupancy.cores_c6",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x80",
+        "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
+        "MetricExpr": "(UNC_P_POWER_STATE_OCCUPANCY.CORES_C6 / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that we are in external PROCHOT mode.  This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip. Derived from unc_p_prochot_external_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xa",
+        "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES",
+        "MetricExpr": "(UNC_P_PROCHOT_EXTERNAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when temperature is the upper limit on frequency. Derived from unc_p_freq_max_limit_thermal_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x4",
+        "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when the OS is the upper limit on frequency. Derived from unc_p_freq_max_os_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x6",
+        "EventName": "UNC_P_FREQ_MAX_OS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_OS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when power is the upper limit on frequency. Derived from unc_p_freq_max_power_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x5",
+        "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_POWER_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles when current is the upper limit on frequency. Derived from unc_p_freq_max_current_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x7",
+        "EventName": "UNC_P_FREQ_MAX_CURRENT_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_MAX_CURRENT_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Cycles spent changing Frequency. Derived from unc_p_freq_trans_cycles",
+        "Counter": "0,1,2,3",
+        "EventName": "UNC_P_FREQ_TRANS_CYCLES",
+        "MetricExpr": "(UNC_P_FREQ_TRANS_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_GE_1200MHZ_CYCLES",
+        "Filter": "filter_band0=1200",
+        "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_GE_2000MHZ_CYCLES",
+        "Filter": "filter_band1=2000",
+        "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_GE_3000MHZ_CYCLES",
+        "Filter": "filter_band2=3000",
+        "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore was running at a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_GE_4000MHZ_CYCLES",
+        "Filter": "filter_band3=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 1.2Ghz. Derived from unc_p_freq_band0_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xb",
+        "EventName": "UNC_P_FREQ_GE_1200MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band0=1200",
+        "MetricExpr": "(UNC_P_FREQ_GE_1200MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of times that the uncore transitioned to a frequency greater than or equal to 2Ghz. Derived from unc_p_freq_band1_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xc",
+        "EventName": "UNC_P_FREQ_GE_2000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band1=2000",
+        "MetricExpr": "(UNC_P_FREQ_GE_2000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 3Ghz. Derived from unc_p_freq_band2_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xd",
+        "EventName": "UNC_P_FREQ_GE_3000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band2=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_3000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    },
+    {
+        "BriefDescription": "Counts the number of cycles that the uncore transitioned to a frequency greater than or equal to 4Ghz. Derived from unc_p_freq_band3_cycles",
+        "Counter": "0,1,2,3",
+        "EventCode": "0xe",
+        "EventName": "UNC_P_FREQ_GE_4000MHZ_TRANSITIONS",
+        "Filter": "edge=1,filter_band3=4000",
+        "MetricExpr": "(UNC_P_FREQ_GE_4000MHZ_CYCLES / UNC_P_CLOCKTICKS) * 100.",
+        "PerPkg": "1",
+        "Unit": "PCU"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json
new file mode 100644
index 000000000000..e3bcd86c4f56
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-memory.json
@@ -0,0 +1,42 @@
+[
+    {
+        "BriefDescription": "ddr bandwidth read (CPU traffic only) (MB/sec). ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x03",
+        "EventName": "UNC_M_CAS_COUNT.RD",
+        "PerPkg": "1",
+        "ScaleUnit": "6.4e-05MiB",
+        "UMask": "0x01",
+        "Unit": "imc"
+    },
+    {
+        "BriefDescription": "ddr bandwidth write (CPU traffic only) (MB/sec). ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x03",
+        "EventName": "UNC_M_CAS_COUNT.WR",
+        "PerPkg": "1",
+        "ScaleUnit": "6.4e-05MiB",
+        "UMask": "0x02",
+        "Unit": "imc"
+    },
+    {
+        "BriefDescription": "mcdram bandwidth read (CPU traffic only) (MB/sec). ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x01",
+        "EventName": "UNC_E_RPQ_INSERTS",
+        "PerPkg": "1",
+        "ScaleUnit": "6.4e-05MiB",
+        "UMask": "0x01",
+        "Unit": "edc_eclk"
+    },
+    {
+        "BriefDescription": "mcdram bandwidth write (CPU traffic only) (MB/sec). ",
+        "Counter": "0,1,2,3",
+        "EventCode": "0x02",
+        "EventName": "UNC_E_WPQ_INSERTS",
+        "PerPkg": "1",
+        "ScaleUnit": "6.4e-05MiB",
+        "UMask": "0x01",
+        "Unit": "edc_eclk"
+    }
+]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 41611d7f9873..eed09346a72a 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -135,7 +135,6 @@ static struct field {
 	const char *field;
 	const char *kernel;
 } fields[] = {
-	{ "EventCode",	"event=" },
 	{ "UMask",	"umask=" },
 	{ "CounterMask", "cmask=" },
 	{ "Invert",	"inv=" },
@@ -189,6 +188,27 @@ static struct msrmap *lookup_msr(char *map, jsmntok_t *val)
 	return NULL;
 }
 
+static struct map {
+	const char *json;
+	const char *perf;
+} unit_to_pmu[] = {
+	{ "CBO", "uncore_cbox" },
+	{ "QPI LL", "uncore_qpi" },
+	{ "SBO", "uncore_sbox" },
+	{}
+};
+
+static const char *field_to_perf(struct map *table, char *map, jsmntok_t *val)
+{
+	int i;
+
+	for (i = 0; table[i].json; i++) {
+		if (json_streq(map, val, table[i].json))
+			return table[i].perf;
+	}
+	return NULL;
+}
+
 #define EXPECT(e, t, m) do { if (!(e)) {			\
 	jsmntok_t *loc = (t);					\
 	if (!(t)->start && (t) > tokens)			\
@@ -270,7 +290,8 @@ static void print_events_table_prefix(FILE *fp, const char *tblname)
 }
 
 static int print_events_table_entry(void *data, char *name, char *event,
-				    char *desc, char *long_desc)
+				    char *desc, char *long_desc,
+				    char *pmu, char *unit, char *perpkg)
 {
 	struct perf_entry_data *pd = data;
 	FILE *outfp = pd->outfp;
@@ -288,7 +309,12 @@ static int print_events_table_entry(void *data, char *name, char *event,
 	fprintf(outfp, "\t.topic = \"%s\",\n", topic);
 	if (long_desc && long_desc[0])
 		fprintf(outfp, "\t.long_desc = \"%s\",\n", long_desc);
-
+	if (pmu)
+		fprintf(outfp, "\t.pmu = \"%s\",\n", pmu);
+	if (unit)
+		fprintf(outfp, "\t.unit = \"%s\",\n", unit);
+	if (perpkg)
+		fprintf(outfp, "\t.perpkg = \"%s\",\n", perpkg);
 	fprintf(outfp, "},\n");
 
 	return 0;
@@ -335,7 +361,8 @@ static char *real_event(const char *name, char *event)
 /* Call func with each event in the json file */
 int json_events(const char *fn,
 	  int (*func)(void *data, char *name, char *event, char *desc,
-		      char *long_desc),
+		      char *long_desc,
+		      char *pmu, char *unit, char *perpkg),
 	  void *data)
 {
 	int err = -EIO;
@@ -343,6 +370,7 @@ int json_events(const char *fn,
 	jsmntok_t *tokens, *tok;
 	int i, j, len;
 	char *map;
+	char buf[128];
 
 	if (!fn)
 		return -ENOENT;
@@ -356,6 +384,11 @@ int json_events(const char *fn,
 		char *event = NULL, *desc = NULL, *name = NULL;
 		char *long_desc = NULL;
 		char *extra_desc = NULL;
+		char *pmu = NULL;
+		char *filter = NULL;
+		char *perpkg = NULL;
+		char *unit = NULL;
+		unsigned long long eventcode = 0;
 		struct msrmap *msr = NULL;
 		jsmntok_t *msrval = NULL;
 		jsmntok_t *precise = NULL;
@@ -376,6 +409,16 @@ int json_events(const char *fn,
 			nz = !json_streq(map, val, "0");
 			if (match_field(map, field, nz, &event, val)) {
 				/* ok */
+			} else if (json_streq(map, field, "EventCode")) {
+				char *code = NULL;
+				addfield(map, &code, "", "", val);
+				eventcode |= strtoul(code, NULL, 0);
+				free(code);
+			} else if (json_streq(map, field, "ExtSel")) {
+				char *code = NULL;
+				addfield(map, &code, "", "", val);
+				eventcode |= strtoul(code, NULL, 0) << 21;
+				free(code);
 			} else if (json_streq(map, field, "EventName")) {
 				addfield(map, &name, "", "", val);
 			} else if (json_streq(map, field, "BriefDescription")) {
@@ -399,6 +442,28 @@ int json_events(const char *fn,
 				addfield(map, &extra_desc, ". ",
 					" Supports address when precise",
 					NULL);
+			} else if (json_streq(map, field, "Unit")) {
+				const char *ppmu;
+				char *s;
+
+				ppmu = field_to_perf(unit_to_pmu, map, val);
+				if (ppmu) {
+					pmu = strdup(ppmu);
+				} else {
+					if (!pmu)
+						pmu = strdup("uncore_");
+					addfield(map, &pmu, "", "", val);
+					for (s = pmu; *s; s++)
+						*s = tolower(*s);
+				}
+				addfield(map, &desc, ". ", "Unit: ", NULL);
+				addfield(map, &desc, "", pmu, NULL);
+			} else if (json_streq(map, field, "Filter")) {
+				addfield(map, &filter, "", "", val);
+			} else if (json_streq(map, field, "ScaleUnit")) {
+				addfield(map, &unit, "", "", val);
+			} else if (json_streq(map, field, "PerPkg")) {
+				addfield(map, &perpkg, "", "", val);
 			}
 			/* ignore unknown fields */
 		}
@@ -410,20 +475,29 @@ int json_events(const char *fn,
 				addfield(map, &extra_desc, " ",
 						"(Precise event)", NULL);
 		}
+		snprintf(buf, sizeof buf, "event=%#llx", eventcode);
+		addfield(map, &event, ",", buf, NULL);
 		if (desc && extra_desc)
 			addfield(map, &desc, " ", extra_desc, NULL);
 		if (long_desc && extra_desc)
 			addfield(map, &long_desc, " ", extra_desc, NULL);
+		if (filter)
+			addfield(map, &event, ",", filter, NULL);
 		if (msr != NULL)
 			addfield(map, &event, ",", msr->pname, msrval);
 		fixname(name);
 
-		err = func(data, name, real_event(name, event), desc, long_desc);
+		err = func(data, name, real_event(name, event), desc, long_desc,
+				pmu, unit, perpkg);
 		free(event);
 		free(desc);
 		free(name);
 		free(long_desc);
 		free(extra_desc);
+		free(pmu);
+		free(filter);
+		free(perpkg);
+		free(unit);
 		if (err)
 			break;
 		tok += j;
diff --git a/tools/perf/pmu-events/jevents.h b/tools/perf/pmu-events/jevents.h
index b0eb2744b498..71e13de31092 100644
--- a/tools/perf/pmu-events/jevents.h
+++ b/tools/perf/pmu-events/jevents.h
@@ -3,7 +3,9 @@
 
 int json_events(const char *fn,
 		int (*func)(void *data, char *name, char *event, char *desc,
-				char *long_desc),
+				char *long_desc,
+				char *pmu,
+				char *unit, char *perpkg),
 		void *data);
 char *get_cpu_str(void);
 
diff --git a/tools/perf/pmu-events/pmu-events.h b/tools/perf/pmu-events/pmu-events.h
index 2eaef595d8a0..c669a3cdb9f0 100644
--- a/tools/perf/pmu-events/pmu-events.h
+++ b/tools/perf/pmu-events/pmu-events.h
@@ -10,6 +10,9 @@ struct pmu_event {
 	const char *desc;
 	const char *topic;
 	const char *long_desc;
+	const char *pmu;
+	const char *unit;
+	const char *perpkg;
 };
 
 /*
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 6676c2dd6dcb..1cb3d9b540e9 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -44,6 +44,7 @@ perf-y += is_printable_array.o
 perf-y += bitmap.o
 perf-y += perf-hooks.o
 perf-y += clang.o
+perf-y += unit_number__scnprintf.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 92343f43e44a..1a04fe77487d 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -5,11 +5,13 @@
 #include <util/evlist.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <api/fs/fs.h>
 #include <bpf/bpf.h>
 #include "tests.h"
 #include "llvm.h"
 #include "debug.h"
 #define NR_ITERS       111
+#define PERF_TEST_BPF_PATH "/sys/fs/bpf/perf_test"
 
 #ifdef HAVE_LIBBPF_SUPPORT
 
@@ -54,6 +56,7 @@ static struct {
 	const char *msg_load_fail;
 	int (*target_func)(void);
 	int expect_result;
+	bool	pin;
 } bpf_testcase_table[] = {
 	{
 		LLVM_TESTCASE_BASE,
@@ -63,6 +66,17 @@ static struct {
 		"load bpf object failed",
 		&epoll_wait_loop,
 		(NR_ITERS + 1) / 2,
+		false,
+	},
+	{
+		LLVM_TESTCASE_BASE,
+		"BPF pinning",
+		"[bpf_pinning]",
+		"fix kbuild first",
+		"check your vmlinux setting?",
+		&epoll_wait_loop,
+		(NR_ITERS + 1) / 2,
+		true,
 	},
 #ifdef HAVE_BPF_PROLOGUE
 	{
@@ -73,6 +87,7 @@ static struct {
 		"check your vmlinux setting?",
 		&llseek_loop,
 		(NR_ITERS + 1) / 4,
+		false,
 	},
 #endif
 	{
@@ -83,6 +98,7 @@ static struct {
 		"libbpf error when dealing with relocation",
 		NULL,
 		0,
+		false,
 	},
 };
 
@@ -226,10 +242,34 @@ static int __test__bpf(int idx)
 		goto out;
 	}
 
-	if (obj)
+	if (obj) {
 		ret = do_test(obj,
 			      bpf_testcase_table[idx].target_func,
 			      bpf_testcase_table[idx].expect_result);
+		if (ret != TEST_OK)
+			goto out;
+		if (bpf_testcase_table[idx].pin) {
+			int err;
+
+			if (!bpf_fs__mount()) {
+				pr_debug("BPF filesystem not mounted\n");
+				ret = TEST_FAIL;
+				goto out;
+			}
+			err = mkdir(PERF_TEST_BPF_PATH, 0777);
+			if (err && errno != EEXIST) {
+				pr_debug("Failed to make perf_test dir: %s\n",
+					 strerror(errno));
+				ret = TEST_FAIL;
+				goto out;
+			}
+			if (bpf_object__pin(obj, PERF_TEST_BPF_PATH))
+				ret = TEST_FAIL;
+			if (rm_rf(PERF_TEST_BPF_PATH))
+				ret = TEST_FAIL;
+		}
+	}
+
 out:
 	bpf__clear();
 	return ret;
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index a77dcc0d24e3..37e326bfd2dc 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -247,6 +247,10 @@ static struct test generic_tests[] = {
 		}
 	},
 	{
+		.desc = "unit_number__scnprintf",
+		.func = test__unit_number__scnprint,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/llvm.c b/tools/perf/tests/llvm.c
index 02a33ebcd992..d357dab72e68 100644
--- a/tools/perf/tests/llvm.c
+++ b/tools/perf/tests/llvm.c
@@ -13,7 +13,7 @@ static int test__bpf_parsing(void *obj_buf, size_t obj_buf_sz)
 	struct bpf_object *obj;
 
 	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, NULL);
-	if (IS_ERR(obj))
+	if (libbpf_get_error(obj))
 		return TEST_FAIL;
 	bpf_object__close(obj);
 	return TEST_OK;
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 20c2e641c422..aa9276bfe3e9 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1779,15 +1779,14 @@ static int test_pmu_events(void)
 	}
 
 	while (!ret && (ent = readdir(dir))) {
-#define MAX_NAME 100
 		struct evlist_test e;
-		char name[MAX_NAME];
+		char name[2 * NAME_MAX + 1 + 12 + 3];
 
 		/* Names containing . are special and cannot be used directly */
 		if (strchr(ent->d_name, '.'))
 			continue;
 
-		snprintf(name, MAX_NAME, "cpu/event=%s/u", ent->d_name);
+		snprintf(name, sizeof(name), "cpu/event=%s/u", ent->d_name);
 
 		e.name  = name;
 		e.check = test__checkevent_pmu_events;
@@ -1795,11 +1794,10 @@ static int test_pmu_events(void)
 		ret = test_event(&e);
 		if (ret)
 			break;
-		snprintf(name, MAX_NAME, "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
+		snprintf(name, sizeof(name), "%s:u,cpu/event=%s/u", ent->d_name, ent->d_name);
 		e.name  = name;
 		e.check = test__checkevent_pmu_events_mix;
 		ret = test_event(&e);
-#undef MAX_NAME
 	}
 
 	closedir(dir);
diff --git a/tools/perf/tests/parse-no-sample-id-all.c b/tools/perf/tests/parse-no-sample-id-all.c
index 81c6eeaca0f5..65dcf48a92fb 100644
--- a/tools/perf/tests/parse-no-sample-id-all.c
+++ b/tools/perf/tests/parse-no-sample-id-all.c
@@ -50,7 +50,8 @@ static int process_events(union perf_event **events, size_t count)
 }
 
 struct test_attr_event {
-	struct attr_event attr;
+	struct perf_event_header header;
+	struct perf_event_attr	 attr;
 	u64 id;
 };
 
@@ -71,20 +72,16 @@ int test__parse_no_sample_id_all(int subtest __maybe_unused)
 	int err;
 
 	struct test_attr_event event1 = {
-		.attr = {
-			.header = {
-				.type = PERF_RECORD_HEADER_ATTR,
-				.size = sizeof(struct test_attr_event),
-			},
+		.header = {
+			.type = PERF_RECORD_HEADER_ATTR,
+			.size = sizeof(struct test_attr_event),
 		},
 		.id = 1,
 	};
 	struct test_attr_event event2 = {
-		.attr = {
-			.header = {
-				.type = PERF_RECORD_HEADER_ATTR,
-				.size = sizeof(struct test_attr_event),
-			},
+		.header = {
+			.type = PERF_RECORD_HEADER_ATTR,
+			.size = sizeof(struct test_attr_event),
 		},
 		.id = 2,
 	};
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 8f2e1de6d0ea..541da7a68f91 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -66,7 +66,7 @@ int test__PERF_RECORD(int subtest __maybe_unused)
 	if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */
 		evlist = perf_evlist__new_default();
 
-	if (evlist == NULL || argv == NULL) {
+	if (evlist == NULL) {
 		pr_debug("Not enough memory to create evlist\n");
 		goto out;
 	}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index a512f0c8ff5b..1fa9b9d83aa5 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -96,6 +96,7 @@ int test__perf_hooks(int subtest);
 int test__clang(int subtest);
 const char *test__clang_subtest_get_desc(int subtest);
 int test__clang_subtest_get_nr(void);
+int test__unit_number__scnprint(int subtest);
 
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
diff --git a/tools/perf/tests/unit_number__scnprintf.c b/tools/perf/tests/unit_number__scnprintf.c
new file mode 100644
index 000000000000..623c2aa53c4a
--- /dev/null
+++ b/tools/perf/tests/unit_number__scnprintf.c
@@ -0,0 +1,37 @@
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include "tests.h"
+#include "util.h"
+#include "debug.h"
+
+int test__unit_number__scnprint(int subtest __maybe_unused)
+{
+	struct {
+		u64		 n;
+		const char	*str;
+	} test[] = {
+		{ 1,			"1B"	},
+		{ 10*1024,		"10K"	},
+		{ 20*1024*1024,		"20M"	},
+		{ 30*1024*1024*1024ULL,	"30G"	},
+		{ 0,			"0B"	},
+		{ 0,			NULL	},
+	};
+	unsigned i = 0;
+
+	while (test[i].str) {
+		char buf[100];
+
+		unit_number__scnprintf(buf, sizeof(buf), test[i].n);
+
+		pr_debug("n %" PRIu64 ", str '%s', buf '%s'\n",
+			 test[i].n, test[i].str, buf);
+
+		if (strcmp(test[i].str, buf))
+			return TEST_FAIL;
+
+		i++;
+	}
+
+	return TEST_OK;
+}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 641b40234a9d..fc4fb669ceee 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -501,8 +501,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
 	return n;
 }
 
-static void hist_entry__set_folding(struct hist_entry *he,
-				    struct hist_browser *hb, bool unfold)
+static void __hist_entry__set_folding(struct hist_entry *he,
+				      struct hist_browser *hb, bool unfold)
 {
 	hist_entry__init_have_children(he);
 	he->unfolded = unfold ? he->has_children : false;
@@ -520,12 +520,34 @@ static void hist_entry__set_folding(struct hist_entry *he,
 		he->nr_rows = 0;
 }
 
+static void hist_entry__set_folding(struct hist_entry *he,
+				    struct hist_browser *browser, bool unfold)
+{
+	double percent;
+
+	percent = hist_entry__get_percent_limit(he);
+	if (he->filtered || percent < browser->min_pcnt)
+		return;
+
+	__hist_entry__set_folding(he, browser, unfold);
+
+	if (!he->depth || unfold)
+		browser->nr_hierarchy_entries++;
+	if (he->leaf)
+		browser->nr_callchain_rows += he->nr_rows;
+	else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+		browser->nr_hierarchy_entries++;
+		he->has_no_entry = true;
+		he->nr_rows = 1;
+	} else
+		he->has_no_entry = false;
+}
+
 static void
 __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 {
 	struct rb_node *nd;
 	struct hist_entry *he;
-	double percent;
 
 	nd = rb_first(&browser->hists->entries);
 	while (nd) {
@@ -535,21 +557,6 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 		nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);
 
 		hist_entry__set_folding(he, browser, unfold);
-
-		percent = hist_entry__get_percent_limit(he);
-		if (he->filtered || percent < browser->min_pcnt)
-			continue;
-
-		if (!he->depth || unfold)
-			browser->nr_hierarchy_entries++;
-		if (he->leaf)
-			browser->nr_callchain_rows += he->nr_rows;
-		else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
-			browser->nr_hierarchy_entries++;
-			he->has_no_entry = true;
-			he->nr_rows = 1;
-		} else
-			he->has_no_entry = false;
 	}
 }
 
@@ -564,6 +571,15 @@ static void hist_browser__set_folding(struct hist_browser *browser, bool unfold)
 	ui_browser__reset_index(&browser->b);
 }
 
+static void hist_browser__set_folding_selected(struct hist_browser *browser, bool unfold)
+{
+	if (!browser->he_selection)
+		return;
+
+	hist_entry__set_folding(browser->he_selection, browser, unfold);
+	browser->b.nr_entries = hist_browser__nr_entries(browser);
+}
+
 static void ui_browser__warn_lost_events(struct ui_browser *browser)
 {
 	ui_browser__warning(browser, 4,
@@ -637,10 +653,18 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
 			/* Collapse the whole world. */
 			hist_browser__set_folding(browser, false);
 			break;
+		case 'c':
+			/* Collapse the selected entry. */
+			hist_browser__set_folding_selected(browser, false);
+			break;
 		case 'E':
 			/* Expand the whole world. */
 			hist_browser__set_folding(browser, true);
 			break;
+		case 'e':
+			/* Expand the selected entry. */
+			hist_browser__set_folding_selected(browser, true);
+			break;
 		case 'H':
 			browser->show_headers = !browser->show_headers;
 			hist_browser__update_rows(browser);
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 37388397b5bc..18cfcdc90356 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -521,6 +521,12 @@ void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
 	list_add_tail(&format->sort_list, &list->sorts);
 }
 
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+				       struct perf_hpp_fmt *format)
+{
+	list_add(&format->sort_list, &list->sorts);
+}
+
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
 	list_del(&format->list);
@@ -560,6 +566,10 @@ void perf_hpp__setup_output_field(struct perf_hpp_list *list)
 	perf_hpp_list__for_each_sort_list(list, fmt) {
 		struct perf_hpp_fmt *pos;
 
+		/* skip sort-only fields ("sort_compute" in perf diff) */
+		if (!fmt->entry && !fmt->color)
+			continue;
+
 		perf_hpp_list__for_each_format(list, pos) {
 			if (fmt_equal(fmt, pos))
 				goto next;
diff --git a/tools/perf/ui/setup.c b/tools/perf/ui/setup.c
index 1f6b0994f4f4..50d13e58210f 100644
--- a/tools/perf/ui/setup.c
+++ b/tools/perf/ui/setup.c
@@ -7,6 +7,7 @@
 
 pthread_mutex_t ui__lock = PTHREAD_MUTEX_INITIALIZER;
 void *perf_gtk_handle;
+int use_browser = -1;
 
 #ifdef HAVE_GTK2_SUPPORT
 static int setup_gtk_browser(void)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 3840e3a87057..5da376bc1afc 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -162,6 +162,7 @@ CFLAGS_rbtree.o        += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ET
 CFLAGS_libstring.o     += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_hweight.o       += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))"
 CFLAGS_parse-events.o  += -Wno-redundant-decls
+CFLAGS_header.o        += -include $(OUTPUT)PERF-VERSION-FILE
 
 $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE
 	$(call rule_mkdir)
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 36c861103291..bc6bc7062eb4 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -670,13 +670,13 @@ int bpf__probe(struct bpf_object *obj)
 
 		err = convert_perf_probe_events(pev, 1);
 		if (err < 0) {
-			pr_debug("bpf_probe: failed to convert perf probe events");
+			pr_debug("bpf_probe: failed to convert perf probe events\n");
 			goto out;
 		}
 
 		err = apply_perf_probe_events(pev, 1);
 		if (err < 0) {
-			pr_debug("bpf_probe: failed to apply perf probe events");
+			pr_debug("bpf_probe: failed to apply perf probe events\n");
 			goto out;
 		}
 
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 42922512c1c6..aba953421a03 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -48,6 +48,8 @@ static int parse_callchain_mode(const char *value)
 		callchain_param.mode = CHAIN_FOLDED;
 		return 0;
 	}
+
+	pr_err("Invalid callchain mode: %s\n", value);
 	return -1;
 }
 
@@ -63,6 +65,8 @@ static int parse_callchain_order(const char *value)
 		callchain_param.order_set = true;
 		return 0;
 	}
+
+	pr_err("Invalid callchain order: %s\n", value);
 	return -1;
 }
 
@@ -80,6 +84,8 @@ static int parse_callchain_sort_key(const char *value)
 		callchain_param.branch_callstack = 1;
 		return 0;
 	}
+
+	pr_err("Invalid callchain sort key: %s\n", value);
 	return -1;
 }
 
@@ -97,6 +103,8 @@ static int parse_callchain_value(const char *value)
 		callchain_param.value = CCVAL_COUNT;
 		return 0;
 	}
+
+	pr_err("Invalid callchain config key: %s\n", value);
 	return -1;
 }
 
@@ -210,13 +218,17 @@ int perf_callchain_config(const char *var, const char *value)
 		return parse_callchain_sort_key(value);
 	if (!strcmp(var, "threshold")) {
 		callchain_param.min_percent = strtod(value, &endptr);
-		if (value == endptr)
+		if (value == endptr) {
+			pr_err("Invalid callchain threshold: %s\n", value);
 			return -1;
+		}
 	}
 	if (!strcmp(var, "print-limit")) {
 		callchain_param.print_limit = strtod(value, &endptr);
-		if (value == endptr)
+		if (value == endptr) {
+			pr_err("Invalid callchain print limit: %s\n", value);
 			return -1;
+		}
 	}
 
 	return 0;
@@ -437,7 +449,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		}
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
-		call->ms.map = cursor_node->map;
+		call->ms.map = map__get(cursor_node->map);
 
 		if (cursor_node->branch) {
 			call->branch_count = 1;
@@ -477,6 +489,7 @@ add_child(struct callchain_node *parent,
 
 		list_for_each_entry_safe(call, tmp, &new->val, list) {
 			list_del(&call->list);
+			map__zput(call->ms.map);
 			free(call);
 		}
 		free(new);
@@ -761,6 +774,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
 					list->ms.map, list->ms.sym,
 					false, NULL, 0, 0);
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
@@ -811,7 +825,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 	}
 
 	node->ip = ip;
-	node->map = map;
+	map__zput(node->map);
+	node->map = map__get(map);
 	node->sym = sym;
 	node->branch = branch;
 	node->nr_loop_iter = nr_loop_iter;
@@ -1142,11 +1157,13 @@ static void free_callchain_node(struct callchain_node *node)
 
 	list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
 	list_for_each_entry_safe(list, tmp, &node->val, list) {
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
@@ -1210,6 +1227,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 				goto out;
 			*new = *chain;
 			new->has_children = false;
+			map__get(new->ms.map);
 			list_add_tail(&new->list, &head);
 		}
 		parent = parent->parent;
@@ -1230,6 +1248,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 out:
 	list_for_each_entry_safe(chain, new, &head, list) {
 		list_del(&chain->list);
+		map__zput(chain->ms.map);
 		free(chain);
 	}
 	return -ENOMEM;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 35c8e379530f..4f4b60f1558a 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -5,6 +5,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include "event.h"
+#include "map.h"
 #include "symbol.h"
 
 #define HELP_PAD "\t\t\t\t"
@@ -184,8 +185,13 @@ int callchain_merge(struct callchain_cursor *cursor,
  */
 static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 {
+	struct callchain_cursor_node *node;
+
 	cursor->nr = 0;
 	cursor->last = &cursor->first;
+
+	for (node = cursor->first; node != NULL; node = node->next)
+		map__zput(node->map);
 }
 
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,
diff --git a/tools/perf/util/config.c b/tools/perf/util/config.c
index 3d906dbbef74..0c7d5a4975cd 100644
--- a/tools/perf/util/config.c
+++ b/tools/perf/util/config.c
@@ -386,8 +386,10 @@ static int perf_buildid_config(const char *var, const char *value)
 	if (!strcmp(var, "buildid.dir")) {
 		const char *dir = perf_config_dirname(var, value);
 
-		if (!dir)
+		if (!dir) {
+			pr_err("Invalid buildid directory!\n");
 			return -1;
+		}
 		strncpy(buildid_dir, dir, MAXPATHLEN-1);
 		buildid_dir[MAXPATHLEN-1] = '\0';
 	}
@@ -405,10 +407,9 @@ static int perf_default_core_config(const char *var __maybe_unused,
 static int perf_ui_config(const char *var, const char *value)
 {
 	/* Add other config variables here. */
-	if (!strcmp(var, "ui.show-headers")) {
+	if (!strcmp(var, "ui.show-headers"))
 		symbol_conf.show_hist_headers = perf_config_bool(var, value);
-		return 0;
-	}
+
 	return 0;
 }
 
@@ -646,8 +647,13 @@ static int perf_config_set__init(struct perf_config_set *set)
 			goto out;
 		}
 
-		if (stat(user_config, &st) < 0)
+		if (stat(user_config, &st) < 0) {
+			if (errno == ENOENT)
+				ret = 0;
 			goto out_free;
+		}
+
+		ret = 0;
 
 		if (st.st_uid && (st.st_uid != geteuid())) {
 			warning("File %s not owned by current user or root, "
@@ -655,11 +661,8 @@ static int perf_config_set__init(struct perf_config_set *set)
 			goto out_free;
 		}
 
-		if (!st.st_size)
-			goto out_free;
-
-		ret = perf_config_from_file(collect_config, user_config, set);
-
+		if (st.st_size)
+			ret = perf_config_from_file(collect_config, user_config, set);
 out_free:
 		free(user_config);
 	}
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 7123f4de32cc..4e6cbc99f08e 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -1473,7 +1473,7 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 		},
 	};
 	struct ctf_writer *cw = &c.writer;
-	int err = -1;
+	int err;
 
 	if (opts->all) {
 		c.tool.comm = process_comm_event;
@@ -1481,12 +1481,15 @@ int bt_convert__perf2ctf(const char *input, const char *path,
 		c.tool.fork = process_fork_event;
 	}
 
-	perf_config(convert__config, &c);
+	err = perf_config(convert__config, &c);
+	if (err)
+		return err;
 
 	/* CTF writer */
 	if (ctf_writer__init(cw, path))
 		return -1;
 
+	err = -1;
 	/* perf.data session */
 	session = perf_session__new(&file, 0, &c.tool);
 	if (!session)
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index d2c6cdd9d42b..28d41e709128 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -9,6 +9,13 @@
 #include "debug.h"
 #include "vdso.h"
 
+static const char * const debuglink_paths[] = {
+	"%.0s%s",
+	"%s/%s",
+	"%s/.debug/%s",
+	"/usr/lib/debug%s/%s"
+};
+
 char dso__symtab_origin(const struct dso *dso)
 {
 	static const char origin[] = {
@@ -44,24 +51,43 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	size_t len;
 
 	switch (type) {
-	case DSO_BINARY_TYPE__DEBUGLINK: {
-		char *debuglink;
+	case DSO_BINARY_TYPE__DEBUGLINK:
+	{
+		const char *last_slash;
+		char dso_dir[PATH_MAX];
+		char symfile[PATH_MAX];
+		unsigned int i;
 
 		len = __symbol__join_symfs(filename, size, dso->long_name);
-		debuglink = filename + len;
-		while (debuglink != filename && *debuglink != '/')
-			debuglink--;
-		if (*debuglink == '/')
-			debuglink++;
+		last_slash = filename + len;
+		while (last_slash != filename && *last_slash != '/')
+			last_slash--;
 
-		ret = -1;
-		if (!is_regular_file(filename))
+		strncpy(dso_dir, filename, last_slash - filename);
+		dso_dir[last_slash-filename] = '\0';
+
+		if (!is_regular_file(filename)) {
+			ret = -1;
+			break;
+		}
+
+		ret = filename__read_debuglink(filename, symfile, PATH_MAX);
+		if (ret)
 			break;
 
-		ret = filename__read_debuglink(filename, debuglink,
-					       size - (debuglink - filename));
+		/* Check predefined locations where debug file might reside */
+		ret = -1;
+		for (i = 0; i < ARRAY_SIZE(debuglink_paths); i++) {
+			snprintf(filename, size,
+					debuglink_paths[i], dso_dir, symfile);
+			if (is_regular_file(filename)) {
+				ret = 0;
+				break;
+			}
 		}
+
 		break;
+	}
 	case DSO_BINARY_TYPE__BUILD_ID_CACHE:
 		if (dso__build_id_filename(dso, filename, size) == NULL)
 			ret = -1;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 8ab0d7da956b..4ea7ce72ed9c 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1,5 +1,5 @@
 #include <linux/types.h>
-#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
+#include <linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
 #include <api/fs/fs.h>
 #include "event.h"
 #include "debug.h"
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d92e02006fb8..b601f2814a30 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1184,7 +1184,7 @@ unsigned long perf_event_mlock_kb_in_pages(void)
 	return pages;
 }
 
-static size_t perf_evlist__mmap_size(unsigned long pages)
+size_t perf_evlist__mmap_size(unsigned long pages)
 {
 	if (pages == UINT_MAX)
 		pages = perf_event_mlock_kb_in_pages();
@@ -1224,12 +1224,16 @@ static long parse_pages_arg(const char *str, unsigned long min,
 	if (pages == 0 && min == 0) {
 		/* leave number of pages at 0 */
 	} else if (!is_power_of_2(pages)) {
+		char buf[100];
+
 		/* round pages up to next power of 2 */
 		pages = roundup_pow_of_two(pages);
 		if (!pages)
 			return -EINVAL;
-		pr_info("rounding mmap pages size to %lu bytes (%lu pages)\n",
-			pages * page_size, pages);
+
+		unit_number__scnprintf(buf, sizeof(buf), pages * page_size);
+		pr_info("rounding mmap pages size to %s (%lu pages)\n",
+			buf, pages);
 	}
 
 	if (pages > max)
@@ -1797,7 +1801,7 @@ int perf_evlist__start_workload(struct perf_evlist *evlist)
 		 */
 		ret = write(evlist->workload.cork_fd, &bf, 1);
 		if (ret < 0)
-			perror("enable to write to pipe");
+			perror("unable to write to pipe");
 
 		close(evlist->workload.cork_fd);
 		return ret;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 4fd034f22d2f..389b9ccdf8c7 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -218,6 +218,8 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 		      bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
+size_t perf_evlist__mmap_size(unsigned long pages);
+
 void perf_evlist__disable(struct perf_evlist *evlist);
 void perf_evlist__enable(struct perf_evlist *evlist);
 void perf_evlist__toggle_enable(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 04e536ae4d88..ac59710b79e0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1448,8 +1448,8 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
 	return true;
 }
 
-static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-			      struct thread_map *threads)
+int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
+		     struct thread_map *threads)
 {
 	int cpu, thread, nthreads;
 	unsigned long flags = PERF_FLAG_FD_CLOEXEC;
@@ -1459,6 +1459,30 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 	if (perf_missing_features.write_backward && evsel->attr.write_backward)
 		return -EINVAL;
 
+	if (cpus == NULL) {
+		static struct cpu_map *empty_cpu_map;
+
+		if (empty_cpu_map == NULL) {
+			empty_cpu_map = cpu_map__dummy_new();
+			if (empty_cpu_map == NULL)
+				return -ENOMEM;
+		}
+
+		cpus = empty_cpu_map;
+	}
+
+	if (threads == NULL) {
+		static struct thread_map *empty_thread_map;
+
+		if (empty_thread_map == NULL) {
+			empty_thread_map = thread_map__new_by_tid(-1);
+			if (empty_thread_map == NULL)
+				return -ENOMEM;
+		}
+
+		threads = empty_thread_map;
+	}
+
 	if (evsel->system_wide)
 		nthreads = 1;
 	else
@@ -1655,46 +1679,16 @@ void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads)
 	perf_evsel__free_fd(evsel);
 }
 
-static struct {
-	struct cpu_map map;
-	int cpus[1];
-} empty_cpu_map = {
-	.map.nr	= 1,
-	.cpus	= { -1, },
-};
-
-static struct {
-	struct thread_map map;
-	int threads[1];
-} empty_thread_map = {
-	.map.nr	 = 1,
-	.threads = { -1, },
-};
-
-int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-		     struct thread_map *threads)
-{
-	if (cpus == NULL) {
-		/* Work around old compiler warnings about strict aliasing */
-		cpus = &empty_cpu_map.map;
-	}
-
-	if (threads == NULL)
-		threads = &empty_thread_map.map;
-
-	return __perf_evsel__open(evsel, cpus, threads);
-}
-
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
 			     struct cpu_map *cpus)
 {
-	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
+	return perf_evsel__open(evsel, cpus, NULL);
 }
 
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
 				struct thread_map *threads)
 {
-	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
+	return perf_evsel__open(evsel, NULL, threads);
 }
 
 static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
@@ -2469,7 +2463,9 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 		 "  -1: Allow use of (almost) all events by all users\n"
 		 ">= 0: Disallow raw tracepoint access by users without CAP_IOC_LOCK\n"
 		 ">= 1: Disallow CPU event access by users without CAP_SYS_ADMIN\n"
-		 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN",
+		 ">= 2: Disallow kernel profiling by users without CAP_SYS_ADMIN\n\n"
+		 "To make this setting permanent, edit /etc/sysctl.conf too, e.g.:\n\n"
+		 "	kernel.perf_event_paranoid = -1\n" ,
 				 target->system_wide ? "system-wide " : "",
 				 perf_event_paranoid());
 	case ENOENT:
diff --git a/tools/perf/util/evsel_fprintf.c b/tools/perf/util/evsel_fprintf.c
index 6b2925542c0a..4ef5184819a0 100644
--- a/tools/perf/util/evsel_fprintf.c
+++ b/tools/perf/util/evsel_fprintf.c
@@ -168,7 +168,6 @@ int sample__fprintf_callchain(struct perf_sample *sample, int left_alignment,
 
 			if (symbol_conf.bt_stop_list &&
 			    node->sym &&
-			    node->sym->name &&
 			    strlist__has_entry(symbol_conf.bt_stop_list,
 					       node->sym->name)) {
 				break;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d89c9c7ef4e5..3d12c16e5103 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -41,6 +41,8 @@ static const u64 __perf_magic2_sw = 0x50455246494c4532ULL;
 
 #define PERF_MAGIC	__perf_magic2
 
+const char perf_version_string[] = PERF_VERSION;
+
 struct perf_file_attr {
 	struct perf_event_attr	attr;
 	struct perf_file_section	ids;
@@ -2801,8 +2803,10 @@ static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
 	}
 
 	event = pevent_find_event(pevent, evsel->attr.config);
-	if (event == NULL)
+	if (event == NULL) {
+		pr_debug("cannot find event format for %d\n", (int)evsel->attr.config);
 		return -1;
+	}
 
 	if (!evsel->name) {
 		snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
@@ -3201,6 +3205,7 @@ int perf_event__process_event_update(struct perf_tool *tool __maybe_unused,
 	case PERF_EVENT_UPDATE__SCALE:
 		ev_scale = (struct event_update_event_scale *) ev->data;
 		evsel->scale = ev_scale->scale;
+		break;
 	case PERF_EVENT_UPDATE__CPUS:
 		ev_cpus = (struct event_update_event_cpus *) ev->data;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6770a9645609..32c6a939e4cc 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1,6 +1,7 @@
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
+#include "map.h"
 #include "session.h"
 #include "sort.h"
 #include "evlist.h"
@@ -1019,6 +1020,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg)
 {
 	int err, err2;
+	struct map *alm = NULL;
+
+	if (al && al->map)
+		alm = map__get(al->map);
 
 	err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
 					iter->evsel, al, max_stack_depth);
@@ -1058,6 +1063,8 @@ out:
 	if (!err)
 		err = err2;
 
+	map__put(alm);
+
 	return err;
 }
 
@@ -2439,8 +2446,10 @@ int parse_filter_percentage(const struct option *opt __maybe_unused,
 		symbol_conf.filter_relative = true;
 	else if (!strcmp(arg, "absolute"))
 		symbol_conf.filter_relative = false;
-	else
+	else {
+		pr_debug("Invalud percentage: %s\n", arg);
 		return -1;
+	}
 
 	return 0;
 }
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index d4b6514eeef5..28c216e3d5b7 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -283,6 +283,8 @@ void perf_hpp_list__column_register(struct perf_hpp_list *list,
 				    struct perf_hpp_fmt *format);
 void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
 					struct perf_hpp_fmt *format);
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+				       struct perf_hpp_fmt *format);
 
 static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
 {
@@ -294,6 +296,11 @@ static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
 	perf_hpp_list__register_sort_field(&perf_hpp_list, format);
 }
 
+static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__prepend_sort_field(&perf_hpp_list, format);
+}
+
 #define perf_hpp_list__for_each_format(_list, format) \
 	list_for_each_entry(format, &(_list)->fields, list)
 
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 9b742ea8bfe8..7aca5d6d7e1f 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -23,4 +23,8 @@ $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/in
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder -Wno-override-init
+CFLAGS_intel-pt-insn-decoder.o += -I$(OUTPUT)util/intel-pt-decoder
+
+ifneq ($(CC), clang)
+  CFLAGS_intel-pt-insn-decoder.o += -Wno-override-init
+endif
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index e4e7dc781d21..7cf7f7aca4d2 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -22,6 +22,7 @@
 #include <errno.h>
 #include <stdint.h>
 #include <inttypes.h>
+#include <linux/compiler.h>
 
 #include "../cache.h"
 #include "../util.h"
@@ -1746,6 +1747,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 		switch (decoder->packet.type) {
 		case INTEL_PT_TIP_PGD:
 			decoder->continuous_period = false;
+			__fallthrough;
 		case INTEL_PT_TIP_PGE:
 		case INTEL_PT_TIP:
 			intel_pt_log("ERROR: Unexpected packet\n");
@@ -1799,6 +1801,8 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 			decoder->pge = false;
 			decoder->continuous_period = false;
 			intel_pt_clear_tx_flags(decoder);
+			__fallthrough;
+
 		case INTEL_PT_TNT:
 			decoder->have_tma = false;
 			intel_pt_log("ERROR: Unexpected packet\n");
@@ -1839,6 +1843,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 		switch (decoder->packet.type) {
 		case INTEL_PT_TIP_PGD:
 			decoder->continuous_period = false;
+			__fallthrough;
 		case INTEL_PT_TIP_PGE:
 		case INTEL_PT_TIP:
 			decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD;
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index 4f7b32020487..7528ae4f7e28 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -17,6 +17,7 @@
 #include <string.h>
 #include <endian.h>
 #include <byteswap.h>
+#include <linux/compiler.h>
 
 #include "intel-pt-pkt-decoder.h"
 
@@ -498,6 +499,7 @@ int intel_pt_pkt_desc(const struct intel_pt_pkt *packet, char *buf,
 	case INTEL_PT_FUP:
 		if (!(packet->count))
 			return snprintf(buf, buf_len, "%s no ip", name);
+		__fallthrough;
 	case INTEL_PT_CYC:
 	case INTEL_PT_VMCS:
 	case INTEL_PT_MTC:
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 85d5eeb66c75..da20cd5612e9 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2159,7 +2159,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 
 	addr_filters__init(&pt->filts);
 
-	perf_config(intel_pt_perf_config, pt);
+	err = perf_config(intel_pt_perf_config, pt);
+	if (err)
+		goto err_free;
 
 	err = auxtrace_queues__init(&pt->queues);
 	if (err)
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index b23ff44cf214..824356488ce6 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -48,8 +48,10 @@ int perf_llvm_config(const char *var, const char *value)
 		llvm_param.kbuild_opts = strdup(value);
 	else if (!strcmp(var, "dump-obj"))
 		llvm_param.dump_obj = !!perf_config_bool(var, value);
-	else
+	else {
+		pr_debug("Invalid LLVM config option: %s\n", value);
 		return -1;
+	}
 	llvm_param.user_set_param = true;
 	return 0;
 }
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 9b33bef54581..71c9720d4973 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -87,6 +87,25 @@ out_delete:
 	return NULL;
 }
 
+struct machine *machine__new_kallsyms(void)
+{
+	struct machine *machine = machine__new_host();
+	/*
+	 * FIXME:
+	 * 1) MAP__FUNCTION will go away when we stop loading separate maps for
+	 *    functions and data objects.
+	 * 2) We should switch to machine__load_kallsyms(), i.e. not explicitely
+	 *    ask for not using the kcore parsing code, once this one is fixed
+	 *    to create a map per module.
+	 */
+	if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) {
+		machine__delete(machine);
+		machine = NULL;
+	}
+
+	return machine;
+}
+
 static void dsos__purge(struct dsos *dsos)
 {
 	struct dso *pos, *n;
@@ -763,7 +782,7 @@ static u64 machine__get_running_kernel_start(struct machine *machine,
 
 int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
-	enum map_type type;
+	int type;
 	u64 start = machine__get_running_kernel_start(machine, NULL);
 
 	/* In case of renewal the kernel map, destroy previous one */
@@ -794,7 +813,7 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 
 void machine__destroy_kernel_maps(struct machine *machine)
 {
-	enum map_type type;
+	int type;
 
 	for (type = 0; type < MAP__NR_TYPES; ++type) {
 		struct kmap *kmap;
@@ -1546,7 +1565,7 @@ int machine__process_event(struct machine *machine, union perf_event *event,
 
 static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 {
-	if (sym->name && !regexec(regex, sym->name, 0, NULL, 0))
+	if (!regexec(regex, sym->name, 0, NULL, 0))
 		return 1;
 	return 0;
 }
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 354de6e56109..a28305029711 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -129,6 +129,7 @@ char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
 void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
+struct machine *machine__new_kallsyms(void);
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid);
 void machine__exit(struct machine *machine);
 void machine__delete_threads(struct machine *machine);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 4f9a71c63026..0a943e7b1ea7 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -387,10 +387,10 @@ size_t map__fprintf_dsoname(struct map *map, FILE *fp)
 {
 	const char *dsoname = "[unknown]";
 
-	if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+	if (map && map->dso) {
 		if (symbol_conf.show_kernel_path && map->dso->long_name)
 			dsoname = map->dso->long_name;
-		else if (map->dso->name)
+		else
 			dsoname = map->dso->name;
 	}
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 3c876b8ba4de..281e44af31e2 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -211,6 +211,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 				closedir(evt_dir);
 				closedir(sys_dir);
 				path = zalloc(sizeof(*path));
+				if (!path)
+					return NULL;
 				path->system = malloc(MAX_EVENT_LENGTH);
 				if (!path->system) {
 					free(path);
@@ -252,8 +254,7 @@ struct tracepoint_path *tracepoint_name_to_path(const char *name)
 	if (path->system == NULL || path->name == NULL) {
 		zfree(&path->system);
 		zfree(&path->name);
-		free(path);
-		path = NULL;
+		zfree(&path);
 	}
 
 	return path;
@@ -310,10 +311,11 @@ __add_event(struct list_head *list, int *idx,
 
 	event_attr_init(attr);
 
-	evsel = perf_evsel__new_idx(attr, (*idx)++);
+	evsel = perf_evsel__new_idx(attr, *idx);
 	if (!evsel)
 		return NULL;
 
+	(*idx)++;
 	evsel->cpus     = cpu_map__get(cpus);
 	evsel->own_cpus = cpu_map__get(cpus);
 
@@ -1477,10 +1479,9 @@ static void perf_pmu__parse_cleanup(void)
 
 		for (i = 0; i < perf_pmu_events_list_num; i++) {
 			p = perf_pmu_events_list + i;
-			free(p->symbol);
+			zfree(&p->symbol);
 		}
-		free(perf_pmu_events_list);
-		perf_pmu_events_list = NULL;
+		zfree(&perf_pmu_events_list);
 		perf_pmu_events_list_num = 0;
 	}
 }
@@ -1504,35 +1505,41 @@ static void perf_pmu__parse_init(void)
 	struct perf_pmu_alias *alias;
 	int len = 0;
 
-	pmu = perf_pmu__find("cpu");
-	if ((pmu == NULL) || list_empty(&pmu->aliases)) {
+	pmu = NULL;
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		list_for_each_entry(alias, &pmu->aliases, list) {
+			if (strchr(alias->name, '-'))
+				len++;
+			len++;
+		}
+	}
+
+	if (len == 0) {
 		perf_pmu_events_list_num = -1;
 		return;
 	}
-	list_for_each_entry(alias, &pmu->aliases, list) {
-		if (strchr(alias->name, '-'))
-			len++;
-		len++;
-	}
 	perf_pmu_events_list = malloc(sizeof(struct perf_pmu_event_symbol) * len);
 	if (!perf_pmu_events_list)
 		return;
 	perf_pmu_events_list_num = len;
 
 	len = 0;
-	list_for_each_entry(alias, &pmu->aliases, list) {
-		struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
-		char *tmp = strchr(alias->name, '-');
-
-		if (tmp != NULL) {
-			SET_SYMBOL(strndup(alias->name, tmp - alias->name),
-					PMU_EVENT_SYMBOL_PREFIX);
-			p++;
-			SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX);
-			len += 2;
-		} else {
-			SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL);
-			len++;
+	pmu = NULL;
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		list_for_each_entry(alias, &pmu->aliases, list) {
+			struct perf_pmu_event_symbol *p = perf_pmu_events_list + len;
+			char *tmp = strchr(alias->name, '-');
+
+			if (tmp != NULL) {
+				SET_SYMBOL(strndup(alias->name, tmp - alias->name),
+						PMU_EVENT_SYMBOL_PREFIX);
+				p++;
+				SET_SYMBOL(strdup(++tmp), PMU_EVENT_SYMBOL_SUFFIX);
+				len += 2;
+			} else {
+				SET_SYMBOL(strdup(alias->name), PMU_EVENT_SYMBOL);
+				len++;
+			}
 		}
 	}
 	qsort(perf_pmu_events_list, len,
@@ -1563,7 +1570,7 @@ perf_pmu__parse_check(const char *name)
 	r = bsearch(&p, perf_pmu_events_list,
 			(size_t) perf_pmu_events_list_num,
 			sizeof(struct perf_pmu_event_symbol), comp_pmu);
-	free(p.symbol);
+	zfree(&p.symbol);
 	return r ? r->type : PMU_EVENT_SYMBOL_ERR;
 }
 
@@ -1710,8 +1717,8 @@ static void parse_events_print_error(struct parse_events_error *err,
 		fprintf(stderr, "%*s\\___ %s\n", idx + 1, "", err->str);
 		if (err->help)
 			fprintf(stderr, "\n%s\n", err->help);
-		free(err->str);
-		free(err->help);
+		zfree(&err->str);
+		zfree(&err->help);
 	}
 
 	fprintf(stderr, "Run 'perf list' for a list of valid events\n");
@@ -2013,17 +2020,14 @@ static bool is_event_supported(u8 type, unsigned config)
 		.config = config,
 		.disabled = 1,
 	};
-	struct {
-		struct thread_map map;
-		int threads[1];
-	} tmap = {
-		.map.nr	 = 1,
-		.threads = { 0 },
-	};
+	struct thread_map *tmap = thread_map__new_by_tid(0);
+
+	if (tmap == NULL)
+		return false;
 
 	evsel = perf_evsel__new(&attr);
 	if (evsel) {
-		open_return = perf_evsel__open(evsel, NULL, &tmap.map);
+		open_return = perf_evsel__open(evsel, NULL, tmap);
 		ret = open_return >= 0;
 
 		if (open_return == -EACCES) {
@@ -2035,7 +2039,7 @@ static bool is_event_supported(u8 type, unsigned config)
 			 *
 			 */
 			evsel->attr.exclude_kernel = 1;
-			ret = perf_evsel__open(evsel, NULL, &tmap.map) >= 0;
+			ret = perf_evsel__open(evsel, NULL, tmap) >= 0;
 		}
 		perf_evsel__delete(evsel);
 	}
@@ -2406,7 +2410,7 @@ void parse_events_terms__purge(struct list_head *terms)
 
 	list_for_each_entry_safe(term, h, terms, list) {
 		if (term->array.nr_ranges)
-			free(term->array.ranges);
+			zfree(&term->array.ranges);
 		list_del_init(&term->list);
 		free(term);
 	}
@@ -2422,7 +2426,7 @@ void parse_events_terms__delete(struct list_head *terms)
 
 void parse_events__clear_array(struct parse_events_array *a)
 {
-	free(a->ranges);
+	zfree(&a->ranges);
 }
 
 void parse_events_evlist_error(struct parse_events_evlist *data,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 879115f93edc..a14b47ab3879 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -12,9 +12,13 @@
 #include <linux/list.h>
 #include <linux/types.h>
 #include "util.h"
+#include "pmu.h"
+#include "debug.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
 
+void parse_events_error(YYLTYPE *loc, void *data, void *scanner, char const *msg);
+
 #define ABORT_ON(val) \
 do { \
 	if (val) \
@@ -236,15 +240,34 @@ PE_KERNEL_PMU_EVENT sep_dc
 	struct list_head *head;
 	struct parse_events_term *term;
 	struct list_head *list;
+	struct perf_pmu *pmu = NULL;
+	int ok = 0;
 
-	ALLOC_LIST(head);
-	ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					$1, 1, &@1, NULL));
-	list_add_tail(&term->list, head);
-
+	/* Add it for all PMUs that support the alias */
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
-	parse_events_terms__delete(head);
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		struct perf_pmu_alias *alias;
+
+		list_for_each_entry(alias, &pmu->aliases, list) {
+			if (!strcasecmp(alias->name, $1)) {
+				ALLOC_LIST(head);
+				ABORT_ON(parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+					$1, 1, &@1, NULL));
+				list_add_tail(&term->list, head);
+
+				if (!parse_events_add_pmu(data, list,
+						  pmu->name, head)) {
+					pr_debug("%s -> %s/%s/\n", $1,
+						 pmu->name, alias->str);
+					ok++;
+				}
+
+				parse_events_terms__delete(head);
+			}
+		}
+	}
+	if (!ok)
+		YYABORT;
 	$$ = list;
 }
 |
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index dc6ccaa4e927..49bfee0e3d9e 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -94,32 +94,10 @@ static int pmu_format(const char *name, struct list_head *format)
 	return 0;
 }
 
-static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+static int convert_scale(const char *scale, char **end, double *sval)
 {
-	struct stat st;
-	ssize_t sret;
-	char scale[128];
-	int fd, ret = -1;
-	char path[PATH_MAX];
 	char *lc;
-
-	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
-
-	fd = open(path, O_RDONLY);
-	if (fd == -1)
-		return -1;
-
-	if (fstat(fd, &st) < 0)
-		goto error;
-
-	sret = read(fd, scale, sizeof(scale)-1);
-	if (sret < 0)
-		goto error;
-
-	if (scale[sret - 1] == '\n')
-		scale[sret - 1] = '\0';
-	else
-		scale[sret] = '\0';
+	int ret = 0;
 
 	/*
 	 * save current locale
@@ -134,7 +112,7 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	lc = strdup(lc);
 	if (!lc) {
 		ret = -ENOMEM;
-		goto error;
+		goto out;
 	}
 
 	/*
@@ -144,14 +122,42 @@ static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *
 	 */
 	setlocale(LC_NUMERIC, "C");
 
-	alias->scale = strtod(scale, NULL);
+	*sval = strtod(scale, end);
 
+out:
 	/* restore locale */
 	setlocale(LC_NUMERIC, lc);
-
 	free(lc);
+	return ret;
+}
+
+static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	struct stat st;
+	ssize_t sret;
+	char scale[128];
+	int fd, ret = -1;
+	char path[PATH_MAX];
+
+	snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	if (fstat(fd, &st) < 0)
+		goto error;
+
+	sret = read(fd, scale, sizeof(scale)-1);
+	if (sret < 0)
+		goto error;
 
-	ret = 0;
+	if (scale[sret - 1] == '\n')
+		scale[sret - 1] = '\0';
+	else
+		scale[sret] = '\0';
+
+	ret = convert_scale(scale, NULL, &alias->scale);
 error:
 	close(fd);
 	return ret;
@@ -223,11 +229,13 @@ static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
 }
 
 static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
-				 char *desc, char *val, char *long_desc,
-				 char *topic)
+				 char *desc, char *val,
+				 char *long_desc, char *topic,
+				 char *unit, char *perpkg)
 {
 	struct perf_pmu_alias *alias;
 	int ret;
+	int num;
 
 	alias = malloc(sizeof(*alias));
 	if (!alias)
@@ -261,6 +269,13 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name,
 	alias->long_desc = long_desc ? strdup(long_desc) :
 				desc ? strdup(desc) : NULL;
 	alias->topic = topic ? strdup(topic) : NULL;
+	if (unit) {
+		if (convert_scale(unit, &unit, &alias->scale) < 0)
+			return -1;
+		snprintf(alias->unit, sizeof(alias->unit), "%s", unit);
+	}
+	alias->per_pkg = perpkg && sscanf(perpkg, "%d", &num) == 1 && num == 1;
+	alias->str = strdup(val);
 
 	list_add_tail(&alias->list, list);
 
@@ -278,7 +293,8 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 
 	buf[ret] = 0;
 
-	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL);
+	return __perf_pmu__new_alias(list, dir, name, NULL, buf, NULL, NULL, NULL,
+				     NULL);
 }
 
 static inline bool pmu_alias_info_file(char *name)
@@ -498,7 +514,7 @@ char * __weak get_cpuid_str(void)
  * to the current running CPU. Then, add all PMU events from that table
  * as aliases.
  */
-static void pmu_add_cpu_aliases(struct list_head *head)
+static void pmu_add_cpu_aliases(struct list_head *head, const char *name)
 {
 	int i;
 	struct pmu_events_map *map;
@@ -534,14 +550,21 @@ static void pmu_add_cpu_aliases(struct list_head *head)
 	 */
 	i = 0;
 	while (1) {
+		const char *pname;
+
 		pe = &map->table[i++];
 		if (!pe->name)
 			break;
 
+		pname = pe->pmu ? pe->pmu : "cpu";
+		if (strncmp(pname, name, strlen(pname)))
+			continue;
+
 		/* need type casts to override 'const' */
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
 				(char *)pe->desc, (char *)pe->event,
-				(char *)pe->long_desc, (char *)pe->topic);
+				(char *)pe->long_desc, (char *)pe->topic,
+				(char *)pe->unit, (char *)pe->perpkg);
 	}
 
 out:
@@ -569,15 +592,16 @@ static struct perf_pmu *pmu_lookup(const char *name)
 	if (pmu_format(name, &format))
 		return NULL;
 
-	if (pmu_aliases(name, &aliases))
+	/*
+	 * Check the type first to avoid unnecessary work.
+	 */
+	if (pmu_type(name, &type))
 		return NULL;
 
-	if (!strcmp(name, "cpu"))
-		pmu_add_cpu_aliases(&aliases);
-
-	if (pmu_type(name, &type))
+	if (pmu_aliases(name, &aliases))
 		return NULL;
 
+	pmu_add_cpu_aliases(&aliases, name);
 	pmu = zalloc(sizeof(*pmu));
 	if (!pmu)
 		return NULL;
@@ -921,12 +945,12 @@ static int check_info_data(struct perf_pmu_alias *alias,
 	 * define unit, scale and snapshot, fail
 	 * if there's more than one.
 	 */
-	if ((info->unit && alias->unit) ||
+	if ((info->unit && alias->unit[0]) ||
 	    (info->scale && alias->scale) ||
 	    (info->snapshot && alias->snapshot))
 		return -EINVAL;
 
-	if (alias->unit)
+	if (alias->unit[0])
 		info->unit = alias->unit;
 
 	if (alias->scale)
@@ -1065,6 +1089,8 @@ struct sevent {
 	char *name;
 	char *desc;
 	char *topic;
+	char *str;
+	char *pmu;
 };
 
 static int cmp_sevent(const void *a, const void *b)
@@ -1161,6 +1187,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 			aliases[j].desc = long_desc ? alias->long_desc :
 						alias->desc;
 			aliases[j].topic = alias->topic;
+			aliases[j].str = alias->str;
+			aliases[j].pmu = pmu->name;
 			j++;
 		}
 		if (pmu->selectable &&
@@ -1175,6 +1203,9 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 	len = j;
 	qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
 	for (j = 0; j < len; j++) {
+		/* Skip duplicates */
+		if (j > 0 && !strcmp(aliases[j].name, aliases[j - 1].name))
+			continue;
 		if (name_only) {
 			printf("%s ", aliases[j].name);
 			continue;
@@ -1192,6 +1223,8 @@ void print_pmu_events(const char *event_glob, bool name_only, bool quiet_flag,
 			printf("%*s", 8, "[");
 			wordwrap(aliases[j].desc, 8, columns, 0);
 			printf("]\n");
+			if (verbose)
+				printf("%*s%s/%s/\n", 8, "", aliases[j].pmu, aliases[j].str);
 		} else
 			printf("  %-50s [Kernel PMU event]\n", aliases[j].name);
 		printed++;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 25712034c815..00852ddc7741 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -43,6 +43,7 @@ struct perf_pmu_alias {
 	char *desc;
 	char *long_desc;
 	char *topic;
+	char *str;
 	struct list_head terms; /* HEAD struct parse_events_term -> list */
 	struct list_head list;  /* ELEM */
 	char unit[UNIT_MAX_LEN+1];
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 6a6f44dd594b..35f5b7b7715c 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -2061,7 +2061,7 @@ static int find_perf_probe_point_from_map(struct probe_trace_point *tp,
 					  bool is_kprobe)
 {
 	struct symbol *sym = NULL;
-	struct map *map;
+	struct map *map = NULL;
 	u64 addr = tp->address;
 	int ret = -ENOENT;
 
@@ -3023,20 +3023,17 @@ static int try_to_find_absolute_address(struct perf_probe_event *pev,
 
 	tev->nargs = pev->nargs;
 	tev->args = zalloc(sizeof(struct probe_trace_arg) * tev->nargs);
-	if (!tev->args) {
-		err = -ENOMEM;
+	if (!tev->args)
 		goto errout;
-	}
+
 	for (i = 0; i < tev->nargs; i++)
 		copy_to_probe_trace_arg(&tev->args[i], &pev->args[i]);
 
 	return 1;
 
 errout:
-	if (*tevs) {
-		clear_probe_trace_events(*tevs, 1);
-		*tevs = NULL;
-	}
+	clear_probe_trace_events(*tevs, 1);
+	*tevs = NULL;
 	return err;
 }
 
diff --git a/tools/perf/util/scripting-engines/Build b/tools/perf/util/scripting-engines/Build
index 6516e220c247..82d28c67e0f3 100644
--- a/tools/perf/util/scripting-engines/Build
+++ b/tools/perf/util/scripting-engines/Build
@@ -1,6 +1,6 @@
 libperf-$(CONFIG_LIBPERL)   += trace-event-perl.o
 libperf-$(CONFIG_LIBPYTHON) += trace-event-python.o
 
-CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-undef -Wno-switch-default
+CFLAGS_trace-event-perl.o += $(PERL_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow -Wno-nested-externs -Wno-undef -Wno-switch-default
 
 CFLAGS_trace-event-python.o += $(PYTHON_EMBED_CCOPTS) -Wno-redundant-decls -Wno-strict-prototypes -Wno-unused-parameter -Wno-shadow
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index e55a132f69b7..c1555fd0035a 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -309,10 +309,10 @@ static SV *perl_process_callchain(struct perf_sample *sample,
 		if (node->map) {
 			struct map *map = node->map;
 			const char *dsoname = "[unknown]";
-			if (map && map->dso && (map->dso->name || map->dso->long_name)) {
+			if (map && map->dso) {
 				if (symbol_conf.show_kernel_path && map->dso->long_name)
 					dsoname = map->dso->long_name;
-				else if (map->dso->name)
+				else
 					dsoname = map->dso->name;
 			}
 			if (!hv_stores(elem, "dso", newSVpv(dsoname,0))) {
@@ -350,8 +350,10 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 		return;
 
-	if (!event)
-		die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+	if (!event) {
+		pr_debug("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
+		return;
+	}
 
 	pid = raw_field_value(event, "common_pid", data);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f268201048a0..4cdbc8f5f14d 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1191,7 +1191,7 @@ static int
 	u64 sample_type = evsel->attr.sample_type;
 	u64 read_format = evsel->attr.read_format;
 
-	/* Standard sample delievery. */
+	/* Standard sample delivery. */
 	if (!(sample_type & PERF_SAMPLE_READ))
 		return tool->sample(tool, event, sample, evsel, machine);
 
@@ -1901,7 +1901,7 @@ int maps__set_kallsyms_ref_reloc_sym(struct map **maps,
 				     const char *symbol_name, u64 addr)
 {
 	char *bracket;
-	enum map_type i;
+	int i;
 	struct ref_reloc_sym *ref;
 
 	ref = zalloc(sizeof(struct ref_reloc_sym));
diff --git a/tools/perf/util/strfilter.c b/tools/perf/util/strfilter.c
index bcae659b6546..efb53772e0ec 100644
--- a/tools/perf/util/strfilter.c
+++ b/tools/perf/util/strfilter.c
@@ -269,6 +269,7 @@ static int strfilter_node__sprint(struct strfilter_node *node, char *buf)
 		len = strfilter_node__sprint_pt(node->l, buf);
 		if (len < 0)
 			return len;
+		__fallthrough;
 	case '!':
 		if (buf) {
 			*(buf + len++) = *node->p;
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index d8dfaf64b32e..bddca519dd58 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -21,6 +21,8 @@ s64 perf_atoll(const char *str)
 		case 'b': case 'B':
 			if (*p)
 				goto out_err;
+
+			__fallthrough;
 		case '\0':
 			return length;
 		default:
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index dc93940de351..70e389bc4af7 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1460,9 +1460,11 @@ int dso__load(struct dso *dso, struct map *map)
 	 * DSO_BINARY_TYPE__BUILDID_DEBUGINFO to work
 	 */
 	if (!dso->has_build_id &&
-	    is_regular_file(dso->long_name) &&
-	    filename__read_build_id(dso->long_name, build_id, BUILD_ID_SIZE) > 0)
+	    is_regular_file(dso->long_name)) {
+	    __symbol__join_symfs(name, PATH_MAX, dso->long_name);
+	    if (filename__read_build_id(name, build_id, BUILD_ID_SIZE) > 0)
 		dso__set_build_id(dso, build_id);
+	}
 
 	/*
 	 * Iterate over candidate debug images.
diff --git a/tools/perf/util/symbol_fprintf.c b/tools/perf/util/symbol_fprintf.c
index 7c6b33e8e2d2..63694e174e5c 100644
--- a/tools/perf/util/symbol_fprintf.c
+++ b/tools/perf/util/symbol_fprintf.c
@@ -21,7 +21,7 @@ size_t __symbol__fprintf_symname_offs(const struct symbol *sym,
 	unsigned long offset;
 	size_t length;
 
-	if (sym && sym->name) {
+	if (sym) {
 		length = fprintf(fp, "%s", sym->name);
 		if (al && print_offsets) {
 			if (al->addr < sym->end)
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index f9eab200fd75..7c3fcc538a70 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -93,7 +93,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 {
 	DIR *proc;
 	int max_threads = 32, items, i;
-	char path[256];
+	char path[NAME_MAX + 1 + 6];
 	struct dirent *dirent, **namelist = NULL;
 	struct thread_map *threads = thread_map__alloc(max_threads);
 
diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c
index d995743cb673..e7d60d05596d 100644
--- a/tools/perf/util/trace-event-info.c
+++ b/tools/perf/util/trace-event-info.c
@@ -42,7 +42,7 @@
 #include "evsel.h"
 #include "debug.h"
 
-#define VERSION "0.5"
+#define VERSION "0.6"
 
 static int output_fd;
 
@@ -170,6 +170,12 @@ static bool name_in_tp_list(char *sys, struct tracepoint_path *tps)
 	return false;
 }
 
+#define for_each_event(dir, dent, tps)				\
+	while ((dent = readdir(dir)))				\
+		if (dent->d_type == DT_DIR &&			\
+		    (strcmp(dent->d_name, ".")) &&		\
+		    (strcmp(dent->d_name, "..")))		\
+
 static int copy_event_system(const char *sys, struct tracepoint_path *tps)
 {
 	struct dirent *dent;
@@ -186,12 +192,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
 		return -errno;
 	}
 
-	while ((dent = readdir(dir))) {
-		if (dent->d_type != DT_DIR ||
-		    strcmp(dent->d_name, ".") == 0 ||
-		    strcmp(dent->d_name, "..") == 0 ||
-		    !name_in_tp_list(dent->d_name, tps))
+	for_each_event(dir, dent, tps) {
+		if (!name_in_tp_list(dent->d_name, tps))
 			continue;
+
 		if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
 			err = -ENOMEM;
 			goto out;
@@ -210,12 +214,10 @@ static int copy_event_system(const char *sys, struct tracepoint_path *tps)
 	}
 
 	rewinddir(dir);
-	while ((dent = readdir(dir))) {
-		if (dent->d_type != DT_DIR ||
-		    strcmp(dent->d_name, ".") == 0 ||
-		    strcmp(dent->d_name, "..") == 0 ||
-		    !name_in_tp_list(dent->d_name, tps))
+	for_each_event(dir, dent, tps) {
+		if (!name_in_tp_list(dent->d_name, tps))
 			continue;
+
 		if (asprintf(&format, "%s/%s/format", sys, dent->d_name) < 0) {
 			err = -ENOMEM;
 			goto out;
@@ -290,13 +292,11 @@ static int record_event_files(struct tracepoint_path *tps)
 		goto out;
 	}
 
-	while ((dent = readdir(dir))) {
-		if (dent->d_type != DT_DIR ||
-		    strcmp(dent->d_name, ".") == 0 ||
-		    strcmp(dent->d_name, "..") == 0 ||
-		    strcmp(dent->d_name, "ftrace") == 0 ||
+	for_each_event(dir, dent, tps) {
+		if (strcmp(dent->d_name, "ftrace") == 0 ||
 		    !system_in_tp_list(dent->d_name, tps))
 			continue;
+
 		count++;
 	}
 
@@ -307,13 +307,11 @@ static int record_event_files(struct tracepoint_path *tps)
 	}
 
 	rewinddir(dir);
-	while ((dent = readdir(dir))) {
-		if (dent->d_type != DT_DIR ||
-		    strcmp(dent->d_name, ".") == 0 ||
-		    strcmp(dent->d_name, "..") == 0 ||
-		    strcmp(dent->d_name, "ftrace") == 0 ||
+	for_each_event(dir, dent, tps) {
+		if (strcmp(dent->d_name, "ftrace") == 0 ||
 		    !system_in_tp_list(dent->d_name, tps))
 			continue;
+
 		if (asprintf(&sys, "%s/%s", path, dent->d_name) < 0) {
 			err = -ENOMEM;
 			goto out;
@@ -379,6 +377,34 @@ out:
 	return err;
 }
 
+static int record_saved_cmdline(void)
+{
+	unsigned int size;
+	char *path;
+	struct stat st;
+	int ret, err = 0;
+
+	path = get_tracing_file("saved_cmdlines");
+	if (!path) {
+		pr_debug("can't get tracing/saved_cmdline");
+		return -ENOMEM;
+	}
+
+	ret = stat(path, &st);
+	if (ret < 0) {
+		/* not found */
+		size = 0;
+		if (write(output_fd, &size, 8) != 8)
+			err = -EIO;
+		goto out;
+	}
+	err = record_file(path, 8);
+
+out:
+	put_tracing_file(path);
+	return err;
+}
+
 static void
 put_tracepoints_path(struct tracepoint_path *tps)
 {
@@ -539,6 +565,9 @@ struct tracing_data *tracing_data_get(struct list_head *pattrs,
 	if (err)
 		goto out;
 	err = record_ftrace_printk();
+	if (err)
+		goto out;
+	err = record_saved_cmdline();
 
 out:
 	/*
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 33b52eaa39db..de0078e21408 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -160,6 +160,23 @@ void parse_ftrace_printk(struct pevent *pevent,
 	}
 }
 
+void parse_saved_cmdline(struct pevent *pevent,
+			 char *file, unsigned int size __maybe_unused)
+{
+	char *comm;
+	char *line;
+	char *next = NULL;
+	int pid;
+
+	line = strtok_r(file, "\n", &next);
+	while (line) {
+		sscanf(line, "%d %ms", &pid, &comm);
+		pevent_register_comm(pevent, comm, pid);
+		free(comm);
+		line = strtok_r(NULL, "\n", &next);
+	}
+}
+
 int parse_ftrace_file(struct pevent *pevent, char *buf, unsigned long size)
 {
 	return pevent_parse_event(pevent, buf, size, "ftrace");
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index b67a0ccf5ab9..27420159bf69 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -260,39 +260,53 @@ static int read_header_files(struct pevent *pevent)
 
 static int read_ftrace_file(struct pevent *pevent, unsigned long long size)
 {
+	int ret;
 	char *buf;
 
 	buf = malloc(size);
-	if (buf == NULL)
+	if (buf == NULL) {
+		pr_debug("memory allocation failure\n");
 		return -1;
+	}
 
-	if (do_read(buf, size) < 0) {
-		free(buf);
-		return -1;
+	ret = do_read(buf, size);
+	if (ret < 0) {
+		pr_debug("error reading ftrace file.\n");
+		goto out;
 	}
 
-	parse_ftrace_file(pevent, buf, size);
+	ret = parse_ftrace_file(pevent, buf, size);
+	if (ret < 0)
+		pr_debug("error parsing ftrace file.\n");
+out:
 	free(buf);
-	return 0;
+	return ret;
 }
 
 static int read_event_file(struct pevent *pevent, char *sys,
 			    unsigned long long size)
 {
+	int ret;
 	char *buf;
 
 	buf = malloc(size);
-	if (buf == NULL)
+	if (buf == NULL) {
+		pr_debug("memory allocation failure\n");
 		return -1;
+	}
 
-	if (do_read(buf, size) < 0) {
+	ret = do_read(buf, size);
+	if (ret < 0) {
 		free(buf);
-		return -1;
+		goto out;
 	}
 
-	parse_event_file(pevent, buf, size, sys);
+	ret = parse_event_file(pevent, buf, size, sys);
+	if (ret < 0)
+		pr_debug("error parsing event file.\n");
+out:
 	free(buf);
-	return 0;
+	return ret;
 }
 
 static int read_ftrace_files(struct pevent *pevent)
@@ -341,6 +355,36 @@ static int read_event_files(struct pevent *pevent)
 	return 0;
 }
 
+static int read_saved_cmdline(struct pevent *pevent)
+{
+	unsigned long long size;
+	char *buf;
+	int ret;
+
+	/* it can have 0 size */
+	size = read8(pevent);
+	if (!size)
+		return 0;
+
+	buf = malloc(size + 1);
+	if (buf == NULL) {
+		pr_debug("memory allocation failure\n");
+		return -1;
+	}
+
+	ret = do_read(buf, size);
+	if (ret < 0) {
+		pr_debug("error reading saved cmdlines\n");
+		goto out;
+	}
+
+	parse_saved_cmdline(pevent, buf, size);
+	ret = 0;
+out:
+	free(buf);
+	return ret;
+}
+
 ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 {
 	char buf[BUFSIZ];
@@ -379,10 +423,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 		return -1;
 	if (show_version)
 		printf("version = %s\n", version);
-	free(version);
 
-	if (do_read(buf, 1) < 0)
+	if (do_read(buf, 1) < 0) {
+		free(version);
 		return -1;
+	}
 	file_bigendian = buf[0];
 	host_bigendian = bigendian();
 
@@ -423,6 +468,11 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 	err = read_ftrace_printk(pevent);
 	if (err)
 		goto out;
+	if (atof(version) >= 0.6) {
+		err = read_saved_cmdline(pevent);
+		if (err)
+			goto out;
+	}
 
 	size = trace_data_size;
 	repipe = false;
@@ -438,5 +488,6 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 out:
 	if (pevent)
 		trace_event__cleanup(tevent);
+	free(version);
 	return size;
 }
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index b0af9c81bb0d..1fbc044f9eb0 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -42,6 +42,7 @@ raw_field_value(struct event_format *event, const char *name, void *data);
 
 void parse_proc_kallsyms(struct pevent *pevent, char *file, unsigned int size);
 void parse_ftrace_printk(struct pevent *pevent, char *file, unsigned int size);
+void parse_saved_cmdline(struct pevent *pevent, char *file, unsigned int size);
 
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6fec84dff3f7..bfb9b7987692 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -35,6 +35,7 @@
 #include "util.h"
 #include "debug.h"
 #include "asm/bug.h"
+#include "dso.h"
 
 extern int
 UNW_OBJ(dwarf_search_unwind_table) (unw_addr_space_t as,
@@ -297,15 +298,58 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
 	int fd;
 	u64 ofs = dso->data.debug_frame_offset;
 
+	/* debug_frame can reside in:
+	 *  - dso
+	 *  - debug pointed by symsrc_filename
+	 *  - gnu_debuglink, which doesn't necessary
+	 *    has to be pointed by symsrc_filename
+	 */
 	if (ofs == 0) {
 		fd = dso__data_get_fd(dso, machine);
-		if (fd < 0)
-			return -EINVAL;
+		if (fd >= 0) {
+			ofs = elf_section_offset(fd, ".debug_frame");
+			dso__data_put_fd(dso);
+		}
+
+		if (ofs <= 0) {
+			fd = open(dso->symsrc_filename, O_RDONLY);
+			if (fd >= 0) {
+				ofs = elf_section_offset(fd, ".debug_frame");
+				close(fd);
+			}
+		}
+
+		if (ofs <= 0) {
+			char *debuglink = malloc(PATH_MAX);
+			int ret = 0;
+
+			ret = dso__read_binary_type_filename(
+				dso, DSO_BINARY_TYPE__DEBUGLINK,
+				machine->root_dir, debuglink, PATH_MAX);
+			if (!ret) {
+				fd = open(debuglink, O_RDONLY);
+				if (fd >= 0) {
+					ofs = elf_section_offset(fd,
+							".debug_frame");
+					close(fd);
+				}
+			}
+			if (ofs > 0) {
+				if (dso->symsrc_filename != NULL) {
+					pr_warning(
+						"%s: overwrite symsrc(%s,%s)\n",
+							__func__,
+							dso->symsrc_filename,
+							debuglink);
+					free(dso->symsrc_filename);
+				}
+				dso->symsrc_filename = debuglink;
+			} else {
+				free(debuglink);
+			}
+		}
 
-		/* Check the .debug_frame section for unwinding info */
-		ofs = elf_section_offset(fd, ".debug_frame");
 		dso->data.debug_frame_offset = ofs;
-		dso__data_put_fd(dso);
 	}
 
 	*offset = ofs;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 9ddd98827d12..d8b45cea54d0 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -85,7 +85,7 @@ int mkdir_p(char *path, mode_t mode)
 	return (stat(path, &st) && mkdir(path, mode)) ? -1 : 0;
 }
 
-int rm_rf(char *path)
+int rm_rf(const char *path)
 {
 	DIR *dir;
 	int ret = 0;
@@ -789,3 +789,16 @@ int is_printable_array(char *p, unsigned int len)
 	}
 	return 1;
 }
+
+int unit_number__scnprintf(char *buf, size_t size, u64 n)
+{
+	char unit[4] = "BKMG";
+	int i = 0;
+
+	while (((n / 1024) > 1) && (i < 3)) {
+		n /= 1024;
+		i++;
+	}
+
+	return scnprintf(buf, size, "%" PRIu64 "%c", n, unit[i]);
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 1d639e38aa82..c74708da8571 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -209,7 +209,7 @@ static inline int sane_case(int x, int high)
 }
 
 int mkdir_p(char *path, mode_t mode);
-int rm_rf(char *path);
+int rm_rf(const char *path);
 struct strlist *lsdir(const char *name, bool (*filter)(const char *, struct dirent *));
 bool lsdir_no_dot_filter(const char *name, struct dirent *d);
 int copyfile(const char *from, const char *to);
@@ -363,4 +363,5 @@ int is_printable_array(char *p, unsigned int len);
 
 int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz);
 
+int unit_number__scnprintf(char *buf, size_t size, u64 n);
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c
index bc82596d7354..5b38dc2fec4f 100644
--- a/tools/power/acpi/common/cmfsize.c
+++ b/tools/power/acpi/common/cmfsize.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c
index 3919970f5aea..6e78413bb2cb 100644
--- a/tools/power/acpi/common/getopt.c
+++ b/tools/power/acpi/common/getopt.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
index 546cf4a503b7..82a2ff896a95 100644
--- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
+++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c
index 66c4badf03e5..ea14eaeb268f 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixdir.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c
index cbfbce18783d..cf9b5a54df92 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixmap.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c
index 10648aaf6164..c04e8fea2c60 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixxf.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -318,6 +318,28 @@ acpi_os_physical_table_override(struct acpi_table_header *existing_table,
 
 /******************************************************************************
  *
+ * FUNCTION:    acpi_os_enter_sleep
+ *
+ * PARAMETERS:  sleep_state         - Which sleep state to enter
+ *              rega_value          - Register A value
+ *              regb_value          - Register B value
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: A hook before writing sleep registers to enter the sleep
+ *              state. Return AE_CTRL_TERMINATE to skip further sleep register
+ *              writes.
+ *
+ *****************************************************************************/
+
+acpi_status acpi_os_enter_sleep(u8 sleep_state, u32 rega_value, u32 regb_value)
+{
+
+	return (AE_OK);
+}
+
+/******************************************************************************
+ *
  * FUNCTION:    acpi_os_redirect_output
  *
  * PARAMETERS:  destination         - An open file handle/pointer
diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h
index 00423fc45e7c..d6aa40fce2b1 100644
--- a/tools/power/acpi/tools/acpidump/acpidump.h
+++ b/tools/power/acpi/tools/acpidump/acpidump.h
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c
index 9031be1afe63..60df1fbd4a77 100644
--- a/tools/power/acpi/tools/acpidump/apdump.c
+++ b/tools/power/acpi/tools/acpidump/apdump.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c
index dd5b861dc4a8..31b5a7f74015 100644
--- a/tools/power/acpi/tools/acpidump/apfiles.c
+++ b/tools/power/acpi/tools/acpidump/apfiles.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c
index 7ff46be908f0..dd82afa897bd 100644
--- a/tools/power/acpi/tools/acpidump/apmain.c
+++ b/tools/power/acpi/tools/acpidump/apmain.c
@@ -5,7 +5,7 @@
  *****************************************************************************/
 
 /*
- * Copyright (C) 2000 - 2016, Intel Corp.
+ * Copyright (C) 2000 - 2017, Intel Corp.
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
new file mode 100755
index 000000000000..fd706ac0f347
--- /dev/null
+++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py
@@ -0,0 +1,569 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+#
+""" This utility can be used to debug and tune the performance of the
+intel_pstate driver. This utility can be used in two ways:
+- If there is Linux trace file with pstate_sample events enabled, then
+this utility can parse the trace file and generate performance plots.
+- If user has not specified a trace file as input via command line parameters,
+then this utility enables and collects trace data for a user specified interval
+and generates performance plots.
+
+Prerequisites:
+    Python version 2.7.x
+    gnuplot 5.0 or higher
+    gnuplot-py 1.8
+    (Most of the distributions have these required packages. They may be called
+     gnuplot-py, phython-gnuplot. )
+
+    HWP (Hardware P-States are disabled)
+    Kernel config for Linux trace is enabled
+
+    see print_help(): for Usage and Output details
+
+"""
+from __future__ import print_function
+from datetime import datetime
+import subprocess
+import os
+import time
+import re
+import sys
+import getopt
+import Gnuplot
+from numpy import *
+from decimal import *
+
+__author__ = "Srinivas Pandruvada"
+__copyright__ = " Copyright (c) 2017, Intel Corporation. "
+__license__ = "GPL version 2"
+
+
+MAX_CPUS = 256
+
+# Define the csv file columns
+C_COMM = 18
+C_GHZ = 17
+C_ELAPSED = 16
+C_SAMPLE = 15
+C_DURATION = 14
+C_LOAD = 13
+C_BOOST = 12
+C_FREQ = 11
+C_TSC = 10
+C_APERF = 9
+C_MPERF = 8
+C_TO = 7
+C_FROM = 6
+C_SCALED = 5
+C_CORE = 4
+C_USEC = 3
+C_SEC = 2
+C_CPU = 1
+
+global sample_num, last_sec_cpu, last_usec_cpu, start_time, testname
+
+# 11 digits covers uptime to 115 days
+getcontext().prec = 11
+
+sample_num =0
+last_sec_cpu = [0] * MAX_CPUS
+last_usec_cpu = [0] * MAX_CPUS
+
+def print_help():
+    print('intel_pstate_tracer.py:')
+    print('  Usage:')
+    print('    If the trace file is available, then to simply parse and plot, use (sudo not required):')
+    print('      ./intel_pstate_tracer.py [-c cpus] -t <trace_file> -n <test_name>')
+    print('    Or')
+    print('      ./intel_pstate_tracer.py [--cpu cpus] ---trace_file <trace_file> --name <test_name>')
+    print('    To generate trace file, parse and plot, use (sudo required):')
+    print('      sudo ./intel_pstate_tracer.py [-c cpus] -i <interval> -n <test_name>')
+    print('    Or')
+    print('      sudo ./intel_pstate_tracer.py [--cpu cpus] --interval <interval> --name <test_name>')
+    print('    Optional argument:')
+    print('      cpus:  comma separated list of CPUs')
+    print('  Output:')
+    print('    If not already present, creates a "results/test_name" folder in the current working directory with:')
+    print('      cpu.csv - comma seperated values file with trace contents and some additional calculations.')
+    print('      cpu???.csv - comma seperated values file for CPU number ???.')
+    print('      *.png - a variety of PNG format plot files created from the trace contents and the additional calculations.')
+    print('  Notes:')
+    print('    Avoid the use of _ (underscore) in test names, because in gnuplot it is a subscript directive.')
+    print('    Maximum number of CPUs is {0:d}. If there are more the script will abort with an error.'.format(MAX_CPUS))
+    print('    Off-line CPUs cause the script to list some warnings, and create some empty files. Use the CPU mask feature for a clean run.')
+    print('    Empty y range warnings for autoscaled plots can occur and can be ignored.')
+
+def plot_perf_busy_with_sample(cpu_index):
+    """ Plot method to per cpu information """
+
+    file_name = 'cpu{:0>3}.csv'.format(cpu_index)
+    if os.path.exists(file_name):
+        output_png = "cpu%03d_perf_busy_vs_samples.png" % cpu_index
+        g_plot = common_all_gnuplot_settings(output_png)
+        g_plot('set yrange [0:40]')
+        g_plot('set y2range [0:200]')
+        g_plot('set y2tics 0, 10')
+        g_plot('set title "{} : cpu perf busy vs. sample : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now()))
+#       Override common
+        g_plot('set xlabel "Samples"')
+        g_plot('set ylabel "P-State"')
+        g_plot('set y2label "Scaled Busy/performance/io-busy(%)"')
+        set_4_plot_linestyles(g_plot)
+        g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y2 title "performance",\\'.format(C_SAMPLE, C_CORE))
+        g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 2 axis x1y2 title "scaled-busy",\\'.format(C_SAMPLE, C_SCALED))
+        g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 3 axis x1y2 title "io-boost",\\'.format(C_SAMPLE, C_BOOST))
+        g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 4 axis x1y1 title "P-State"'.format(C_SAMPLE, C_TO))
+
+def plot_perf_busy(cpu_index):
+    """ Plot some per cpu information """
+
+    file_name = 'cpu{:0>3}.csv'.format(cpu_index)
+    if os.path.exists(file_name):
+        output_png = "cpu%03d_perf_busy.png" % cpu_index
+        g_plot = common_all_gnuplot_settings(output_png)
+        g_plot('set yrange [0:40]')
+        g_plot('set y2range [0:200]')
+        g_plot('set y2tics 0, 10')
+        g_plot('set title "{} : perf busy : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now()))
+        g_plot('set ylabel "P-State"')
+        g_plot('set y2label "Scaled Busy/performance/io-busy(%)"')
+        set_4_plot_linestyles(g_plot)
+        g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y2 title "performance",\\'.format(C_ELAPSED, C_CORE))
+        g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 2 axis x1y2 title "scaled-busy",\\'.format(C_ELAPSED, C_SCALED))
+        g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 3 axis x1y2 title "io-boost",\\'.format(C_ELAPSED, C_BOOST))
+        g_plot('"' + file_name + '" using {:d}:{:d} with linespoints linestyle 4 axis x1y1 title "P-State"'.format(C_ELAPSED, C_TO))
+
+def plot_durations(cpu_index):
+    """ Plot per cpu durations """
+
+    file_name = 'cpu{:0>3}.csv'.format(cpu_index)
+    if os.path.exists(file_name):
+        output_png = "cpu%03d_durations.png" % cpu_index
+        g_plot = common_all_gnuplot_settings(output_png)
+#       Should autoscale be used here? Should seconds be used here?
+        g_plot('set yrange [0:5000]')
+        g_plot('set ytics 0, 500')
+        g_plot('set title "{} : durations : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now()))
+        g_plot('set ylabel "Timer Duration (MilliSeconds)"')
+#       override common
+        g_plot('set key off')
+        set_4_plot_linestyles(g_plot)
+        g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_DURATION))
+
+def plot_loads(cpu_index):
+    """ Plot per cpu loads """
+
+    file_name = 'cpu{:0>3}.csv'.format(cpu_index)
+    if os.path.exists(file_name):
+        output_png = "cpu%03d_loads.png" % cpu_index
+        g_plot = common_all_gnuplot_settings(output_png)
+        g_plot('set yrange [0:100]')
+        g_plot('set ytics 0, 10')
+        g_plot('set title "{} : loads : CPU {:0>3} : {:%F %H:%M}"'.format(testname, cpu_index, datetime.now()))
+        g_plot('set ylabel "CPU load (percent)"')
+#       override common
+        g_plot('set key off')
+        set_4_plot_linestyles(g_plot)
+        g_plot('plot "' + file_name + '" using {:d}:{:d} with linespoints linestyle 1 axis x1y1'.format(C_ELAPSED, C_LOAD))
+
+def plot_pstate_cpu_with_sample():
+    """ Plot all cpu information """
+
+    if os.path.exists('cpu.csv'):
+        output_png = 'all_cpu_pstates_vs_samples.png'
+        g_plot = common_all_gnuplot_settings(output_png)
+        g_plot('set yrange [0:40]')
+#       override common
+        g_plot('set xlabel "Samples"')
+        g_plot('set ylabel "P-State"')
+        g_plot('set title "{} : cpu pstate vs. sample : {:%F %H:%M}"'.format(testname, datetime.now()))
+        title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+        plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_SAMPLE, C_TO)
+        g_plot('title_list = "{}"'.format(title_list))
+        g_plot(plot_str)
+
+def plot_pstate_cpu():
+    """ Plot all cpu information from csv files """
+
+    output_png = 'all_cpu_pstates.png'
+    g_plot = common_all_gnuplot_settings(output_png)
+    g_plot('set yrange [0:40]')
+    g_plot('set ylabel "P-State"')
+    g_plot('set title "{} : cpu pstates : {:%F %H:%M}"'.format(testname, datetime.now()))
+
+#    the following command is really cool, but doesn't work with the CPU masking option because it aborts on the first missing file.
+#    plot_str = 'plot for [i=0:*] file=sprintf("cpu%03d.csv",i) title_s=sprintf("cpu%03d",i) file using 16:7 pt 7 ps 1 title title_s'
+#
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_TO)
+    g_plot('title_list = "{}"'.format(title_list))
+    g_plot(plot_str)
+
+def plot_load_cpu():
+    """ Plot all cpu loads """
+
+    output_png = 'all_cpu_loads.png'
+    g_plot = common_all_gnuplot_settings(output_png)
+    g_plot('set yrange [0:100]')
+    g_plot('set ylabel "CPU load (percent)"')
+    g_plot('set title "{} : cpu loads : {:%F %H:%M}"'.format(testname, datetime.now()))
+
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_LOAD)
+    g_plot('title_list = "{}"'.format(title_list))
+    g_plot(plot_str)
+
+def plot_frequency_cpu():
+    """ Plot all cpu frequencies """
+
+    output_png = 'all_cpu_frequencies.png'
+    g_plot = common_all_gnuplot_settings(output_png)
+    g_plot('set yrange [0:4]')
+    g_plot('set ylabel "CPU Frequency (GHz)"')
+    g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(testname, datetime.now()))
+
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ)
+    g_plot('title_list = "{}"'.format(title_list))
+    g_plot(plot_str)
+
+def plot_duration_cpu():
+    """ Plot all cpu durations """
+
+    output_png = 'all_cpu_durations.png'
+    g_plot = common_all_gnuplot_settings(output_png)
+    g_plot('set yrange [0:5000]')
+    g_plot('set ytics 0, 500')
+    g_plot('set ylabel "Timer Duration (MilliSeconds)"')
+    g_plot('set title "{} : cpu durations : {:%F %H:%M}"'.format(testname, datetime.now()))
+
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_DURATION)
+    g_plot('title_list = "{}"'.format(title_list))
+    g_plot(plot_str)
+
+def plot_scaled_cpu():
+    """ Plot all cpu scaled busy """
+
+    output_png = 'all_cpu_scaled.png'
+    g_plot = common_all_gnuplot_settings(output_png)
+#   autoscale this one, no set y range
+    g_plot('set ylabel "Scaled Busy (Unitless)"')
+    g_plot('set title "{} : cpu scaled busy : {:%F %H:%M}"'.format(testname, datetime.now()))
+
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_SCALED)
+    g_plot('title_list = "{}"'.format(title_list))
+    g_plot(plot_str)
+
+def plot_boost_cpu():
+    """ Plot all cpu IO Boosts """
+
+    output_png = 'all_cpu_boost.png'
+    g_plot = common_all_gnuplot_settings(output_png)
+    g_plot('set yrange [0:100]')
+    g_plot('set ylabel "CPU IO Boost (percent)"')
+    g_plot('set title "{} : cpu io boost : {:%F %H:%M}"'.format(testname, datetime.now()))
+
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_BOOST)
+    g_plot('title_list = "{}"'.format(title_list))
+    g_plot(plot_str)
+
+def plot_ghz_cpu():
+    """ Plot all cpu tsc ghz """
+
+    output_png = 'all_cpu_ghz.png'
+    g_plot = common_all_gnuplot_settings(output_png)
+#   autoscale this one, no set y range
+    g_plot('set ylabel "TSC Frequency (GHz)"')
+    g_plot('set title "{} : cpu TSC Frequencies (Sanity check calculation) : {:%F %H:%M}"'.format(testname, datetime.now()))
+
+    title_list = subprocess.check_output('ls cpu???.csv | sed -e \'s/.csv//\'',shell=True).replace('\n', ' ')
+    plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_GHZ)
+    g_plot('title_list = "{}"'.format(title_list))
+    g_plot(plot_str)
+
+def common_all_gnuplot_settings(output_png):
+    """ common gnuplot settings for multiple CPUs one one graph. """
+
+    g_plot = common_gnuplot_settings()
+    g_plot('set output "' + output_png + '"')
+    return(g_plot)
+
+def common_gnuplot_settings():
+    """ common gnuplot settings. """
+
+    g_plot = Gnuplot.Gnuplot(persist=1)
+#   The following line is for rigor only. It seems to be assumed for .csv files
+    g_plot('set datafile separator \",\"')
+    g_plot('set ytics nomirror')
+    g_plot('set xtics nomirror')
+    g_plot('set xtics font ", 10"')
+    g_plot('set ytics font ", 10"')
+    g_plot('set tics out scale 1.0')
+    g_plot('set grid')
+    g_plot('set key out horiz')
+    g_plot('set key bot center')
+    g_plot('set key samplen 2 spacing .8 font ", 9"')
+    g_plot('set term png size 1200, 600')
+    g_plot('set title font ", 11"')
+    g_plot('set ylabel font ", 10"')
+    g_plot('set xlabel font ", 10"')
+    g_plot('set xlabel offset 0, 0.5')
+    g_plot('set xlabel "Elapsed Time (Seconds)"')
+    return(g_plot)
+
+def set_4_plot_linestyles(g_plot):
+    """ set the linestyles used for 4 plots in 1 graphs. """
+
+    g_plot('set style line 1 linetype 1 linecolor rgb "green" pointtype -1')
+    g_plot('set style line 2 linetype 1 linecolor rgb "red" pointtype -1')
+    g_plot('set style line 3 linetype 1 linecolor rgb "purple" pointtype -1')
+    g_plot('set style line 4 linetype 1 linecolor rgb "blue" pointtype -1')
+
+def store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz):
+    """ Store master csv file information """
+
+    global graph_data_present
+
+    if cpu_mask[cpu_int] == 0:
+        return
+
+    try:
+        f_handle = open('cpu.csv', 'a')
+        string_buffer = "CPU_%03u, %05u, %06u, %u, %u, %u, %u, %u, %u, %u, %.4f, %u, %.2f, %.3f, %u, %.3f, %.3f, %s\n" % (cpu_int, int(time_pre_dec), int(time_post_dec), int(core_busy), int(scaled), int(_from), int(_to), int(mperf), int(aperf), int(tsc), freq_ghz, int(io_boost), load, duration_ms, sample_num, elapsed_time, tsc_ghz, common_comm)
+        f_handle.write(string_buffer);
+        f_handle.close()
+    except:
+        print('IO error cpu.csv')
+        return
+
+    graph_data_present = True;
+
+def split_csv():
+    """ seperate the all csv file into per CPU csv files. """
+
+    global current_max_cpu
+
+    if os.path.exists('cpu.csv'):
+        for index in range(0, current_max_cpu + 1):
+            if cpu_mask[int(index)] != 0:
+                os.system('grep -m 1 common_cpu cpu.csv > cpu{:0>3}.csv'.format(index))
+                os.system('grep CPU_{:0>3} cpu.csv >> cpu{:0>3}.csv'.format(index, index))
+
+def cleanup_data_files():
+    """ clean up existing data files """
+
+    if os.path.exists('cpu.csv'):
+        os.remove('cpu.csv')
+    f_handle = open('cpu.csv', 'a')
+    f_handle.write('common_cpu, common_secs, common_usecs, core_busy, scaled_busy, from, to, mperf, aperf, tsc, freq, boost, load, duration_ms, sample_num, elapsed_time, tsc_ghz, common_comm')
+    f_handle.write('\n')
+    f_handle.close()
+
+def clear_trace_file():
+    """ Clear trace file """
+
+    try:
+        f_handle = open('/sys/kernel/debug/tracing/trace', 'w')
+        f_handle.close()
+    except:
+        print('IO error clearing trace file ')
+        quit()
+
+def enable_trace():
+    """ Enable trace """
+
+    try:
+       open('/sys/kernel/debug/tracing/events/power/pstate_sample/enable'
+                 , 'w').write("1")
+    except:
+        print('IO error enabling trace ')
+        quit()
+
+def disable_trace():
+    """ Disable trace """
+
+    try:
+       open('/sys/kernel/debug/tracing/events/power/pstate_sample/enable'
+                 , 'w').write("0")
+    except:
+        print('IO error disabling trace ')
+        quit()
+
+def set_trace_buffer_size():
+    """ Set trace buffer size """
+
+    try:
+       open('/sys/kernel/debug/tracing/buffer_size_kb'
+                 , 'w').write("10240")
+    except:
+        print('IO error setting trace buffer size ')
+        quit()
+
+def read_trace_data(filename):
+    """ Read and parse trace data """
+
+    global current_max_cpu
+    global sample_num, last_sec_cpu, last_usec_cpu, start_time
+
+    try:
+        data = open(filename, 'r').read()
+    except:
+        print('Error opening ', filename)
+        quit()
+
+    for line in data.splitlines():
+        search_obj = \
+            re.search(r'(^(.*?)\[)((\d+)[^\]])(.*?)(\d+)([.])(\d+)(.*?core_busy=)(\d+)(.*?scaled=)(\d+)(.*?from=)(\d+)(.*?to=)(\d+)(.*?mperf=)(\d+)(.*?aperf=)(\d+)(.*?tsc=)(\d+)(.*?freq=)(\d+)'
+                      , line)
+
+        if search_obj:
+            cpu = search_obj.group(3)
+            cpu_int = int(cpu)
+            cpu = str(cpu_int)
+
+            time_pre_dec = search_obj.group(6)
+            time_post_dec = search_obj.group(8)
+            core_busy = search_obj.group(10)
+            scaled = search_obj.group(12)
+            _from = search_obj.group(14)
+            _to = search_obj.group(16)
+            mperf = search_obj.group(18)
+            aperf = search_obj.group(20)
+            tsc = search_obj.group(22)
+            freq = search_obj.group(24)
+            common_comm = search_obj.group(2).replace(' ', '')
+
+            # Not all kernel versions have io_boost field
+            io_boost = '0'
+            search_obj = re.search(r'.*?io_boost=(\d+)', line)
+            if search_obj:
+                io_boost = search_obj.group(1)
+
+            if sample_num == 0 :
+                start_time = Decimal(time_pre_dec) + Decimal(time_post_dec) / Decimal(1000000)
+            sample_num += 1
+
+            if last_sec_cpu[cpu_int] == 0 :
+                last_sec_cpu[cpu_int] = time_pre_dec
+                last_usec_cpu[cpu_int] = time_post_dec
+            else :
+                duration_us = (int(time_pre_dec) - int(last_sec_cpu[cpu_int])) * 1000000 + (int(time_post_dec) - int(last_usec_cpu[cpu_int]))
+                duration_ms = Decimal(duration_us) / Decimal(1000)
+                last_sec_cpu[cpu_int] = time_pre_dec
+                last_usec_cpu[cpu_int] = time_post_dec
+                elapsed_time = Decimal(time_pre_dec) + Decimal(time_post_dec) / Decimal(1000000) - start_time
+                load = Decimal(int(mperf)*100)/ Decimal(tsc)
+                freq_ghz = Decimal(freq)/Decimal(1000000)
+#               Sanity check calculation, typically anomalies indicate missed samples
+#               However, check for 0 (should never occur)
+                tsc_ghz = Decimal(0)
+                if duration_ms != Decimal(0) :
+                    tsc_ghz = Decimal(tsc)/duration_ms/Decimal(1000000)
+                store_csv(cpu_int, time_pre_dec, time_post_dec, core_busy, scaled, _from, _to, mperf, aperf, tsc, freq_ghz, io_boost, common_comm, load, duration_ms, sample_num, elapsed_time, tsc_ghz)
+
+            if cpu_int > current_max_cpu:
+                current_max_cpu = cpu_int
+# End of for each trace line loop
+# Now seperate the main overall csv file into per CPU csv files.
+    split_csv()
+
+interval = ""
+filename = ""
+cpu_list = ""
+testname = ""
+graph_data_present = False;
+
+valid1 = False
+valid2 = False
+
+cpu_mask = zeros((MAX_CPUS,), dtype=int)
+
+try:
+    opts, args = getopt.getopt(sys.argv[1:],"ht:i:c:n:",["help","trace_file=","interval=","cpu=","name="])
+except getopt.GetoptError:
+    print_help()
+    sys.exit(2)
+for opt, arg in opts:
+    if opt == '-h':
+        print()
+        sys.exit()
+    elif opt in ("-t", "--trace_file"):
+        valid1 = True
+        location = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
+        filename = os.path.join(location, arg)
+    elif opt in ("-i", "--interval"):
+        valid1 = True
+        interval = arg
+    elif opt in ("-c", "--cpu"):
+        cpu_list = arg
+    elif opt in ("-n", "--name"):
+        valid2 = True
+        testname = arg
+
+if not (valid1 and valid2):
+    print_help()
+    sys.exit()
+
+if cpu_list:
+    for p in re.split("[,]", cpu_list):
+        if int(p) < MAX_CPUS :
+            cpu_mask[int(p)] = 1
+else:
+    for i in range (0, MAX_CPUS):
+        cpu_mask[i] = 1
+
+if not os.path.exists('results'):
+    os.mkdir('results')
+
+os.chdir('results')
+if os.path.exists(testname):
+    print('The test name directory already exists. Please provide a unique test name. Test re-run not supported, yet.')
+    sys.exit()
+os.mkdir(testname)
+os.chdir(testname)
+
+# Temporary (or perhaps not)
+cur_version = sys.version_info
+print('python version (should be >= 2.7):')
+print(cur_version)
+
+# Left as "cleanup" for potential future re-run ability.
+cleanup_data_files()
+
+if interval:
+    filename = "/sys/kernel/debug/tracing/trace"
+    clear_trace_file()
+    set_trace_buffer_size()
+    enable_trace()
+    print('Sleeping for ', interval, 'seconds')
+    time.sleep(int(interval))
+    disable_trace()
+
+current_max_cpu = 0
+
+read_trace_data(filename)
+
+if graph_data_present == False:
+    print('No valid data to plot')
+    sys.exit(2)
+
+for cpu_no in range(0, current_max_cpu + 1):
+    plot_perf_busy_with_sample(cpu_no)
+    plot_perf_busy(cpu_no)
+    plot_durations(cpu_no)
+    plot_loads(cpu_no)
+
+plot_pstate_cpu_with_sample()
+plot_pstate_cpu()
+plot_load_cpu()
+plot_frequency_cpu()
+plot_duration_cpu()
+plot_scaled_cpu()
+plot_boost_cpu()
+plot_ghz_cpu()
+
+os.chdir('../../')
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 8abbef164b4e..621578aa12d6 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -32,7 +32,6 @@ EXTRA_WARNINGS += -Wold-style-definition
 EXTRA_WARNINGS += -Wpacked
 EXTRA_WARNINGS += -Wredundant-decls
 EXTRA_WARNINGS += -Wshadow
-EXTRA_WARNINGS += -Wstrict-aliasing=3
 EXTRA_WARNINGS += -Wstrict-prototypes
 EXTRA_WARNINGS += -Wswitch-default
 EXTRA_WARNINGS += -Wswitch-enum
@@ -40,12 +39,26 @@ EXTRA_WARNINGS += -Wundef
 EXTRA_WARNINGS += -Wwrite-strings
 EXTRA_WARNINGS += -Wformat
 
+ifneq ($(CC), clang)
+EXTRA_WARNINGS += -Wstrict-aliasing=3
+endif
+
 ifneq ($(findstring $(MAKEFLAGS), w),w)
 PRINT_DIR = --no-print-directory
 else
 NO_SUBDIR = :
 endif
 
+ifneq ($(filter 4.%,$(MAKE_VERSION)),)  # make-4
+ifneq ($(filter %s ,$(firstword x$(MAKEFLAGS))),)
+  silent=1
+endif
+else					# make-3.8x
+ifneq ($(filter s% -s%,$(MAKEFLAGS)),)
+  silent=1
+endif
+endif
+
 #
 # Define a callable command for descending to a new directory
 #
@@ -58,7 +71,7 @@ descend = \
 QUIET_SUBDIR0  = +$(MAKE) $(COMMAND_O) -C # space to separate -C and subdir
 QUIET_SUBDIR1  =
 
-ifneq ($(findstring $(MAKEFLAGS),s),s)
+ifneq ($(silent),1)
   ifneq ($(V),1)
 	QUIET_CC       = @echo '  CC       '$@;
 	QUIET_CC_FPIC  = @echo '  CC FPIC  '$@;
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index b13fed534d76..9f7bd1915c21 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -67,21 +67,23 @@ static int map_equal(int lru_map, int expected)
 	return map_subset(lru_map, expected) && map_subset(expected, lru_map);
 }
 
-static int sched_next_online(int pid, int next_to_try)
+static int sched_next_online(int pid, int *next_to_try)
 {
 	cpu_set_t cpuset;
+	int next = *next_to_try;
+	int ret = -1;
 
-	if (next_to_try == nr_cpus)
-		return -1;
-
-	while (next_to_try < nr_cpus) {
+	while (next < nr_cpus) {
 		CPU_ZERO(&cpuset);
-		CPU_SET(next_to_try++, &cpuset);
-		if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset))
+		CPU_SET(next++, &cpuset);
+		if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) {
+			ret = 0;
 			break;
+		}
 	}
 
-	return next_to_try;
+	*next_to_try = next;
+	return ret;
 }
 
 /* Size of the LRU amp is 2
@@ -96,11 +98,12 @@ static void test_lru_sanity0(int map_type, int map_flags)
 {
 	unsigned long long key, value[nr_cpus];
 	int lru_map_fd, expected_map_fd;
+	int next_cpu = 0;
 
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
-	assert(sched_next_online(0, 0) != -1);
+	assert(sched_next_online(0, &next_cpu) != -1);
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
 		lru_map_fd = create_map(map_type, map_flags, 2 * nr_cpus);
@@ -183,6 +186,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	int lru_map_fd, expected_map_fd;
 	unsigned int batch_size;
 	unsigned int map_size;
+	int next_cpu = 0;
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
 		/* Ther percpu lru list (i.e each cpu has its own LRU
@@ -196,7 +200,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
-	assert(sched_next_online(0, 0) != -1);
+	assert(sched_next_online(0, &next_cpu) != -1);
 
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
@@ -262,6 +266,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	int lru_map_fd, expected_map_fd;
 	unsigned int batch_size;
 	unsigned int map_size;
+	int next_cpu = 0;
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
 		/* Ther percpu lru list (i.e each cpu has its own LRU
@@ -275,7 +280,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
-	assert(sched_next_online(0, 0) != -1);
+	assert(sched_next_online(0, &next_cpu) != -1);
 
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
@@ -370,11 +375,12 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
 	int lru_map_fd, expected_map_fd;
 	unsigned int batch_size;
 	unsigned int map_size;
+	int next_cpu = 0;
 
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
-	assert(sched_next_online(0, 0) != -1);
+	assert(sched_next_online(0, &next_cpu) != -1);
 
 	batch_size = tgt_free / 2;
 	assert(batch_size * 2 == tgt_free);
@@ -430,11 +436,12 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
 	int lru_map_fd, expected_map_fd;
 	unsigned long long key, value[nr_cpus];
 	unsigned long long end_key;
+	int next_cpu = 0;
 
 	printf("%s (map_type:%d map_flags:0x%X): ", __func__, map_type,
 	       map_flags);
 
-	assert(sched_next_online(0, 0) != -1);
+	assert(sched_next_online(0, &next_cpu) != -1);
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
 		lru_map_fd = create_map(map_type, map_flags,
@@ -502,9 +509,8 @@ static void do_test_lru_sanity5(unsigned long long last_key, int map_fd)
 static void test_lru_sanity5(int map_type, int map_flags)
 {
 	unsigned long long key, value[nr_cpus];
-	int next_sched_cpu = 0;
+	int next_cpu = 0;
 	int map_fd;
-	int i;
 
 	if (map_flags & BPF_F_NO_COMMON_LRU)
 		return;
@@ -519,27 +525,20 @@ static void test_lru_sanity5(int map_type, int map_flags)
 	key = 0;
 	assert(!bpf_map_update(map_fd, &key, value, BPF_NOEXIST));
 
-	for (i = 0; i < nr_cpus; i++) {
+	while (sched_next_online(0, &next_cpu) != -1) {
 		pid_t pid;
 
 		pid = fork();
 		if (pid == 0) {
-			next_sched_cpu = sched_next_online(0, next_sched_cpu);
-			if (next_sched_cpu != -1)
-				do_test_lru_sanity5(key, map_fd);
+			do_test_lru_sanity5(key, map_fd);
 			exit(0);
 		} else if (pid == -1) {
-			printf("couldn't spawn #%d process\n", i);
+			printf("couldn't spawn process to test key:%llu\n",
+			       key);
 			exit(1);
 		} else {
 			int status;
 
-			/* It is mostly redundant and just allow the parent
-			 * process to update next_shced_cpu for the next child
-			 * process
-			 */
-			next_sched_cpu = sched_next_online(pid, next_sched_cpu);
-
 			assert(waitpid(pid, &status, 0) == pid);
 			assert(status == 0);
 			key++;
@@ -547,6 +546,8 @@ static void test_lru_sanity5(int map_type, int map_flags)
 	}
 
 	close(map_fd);
+	/* At least one key should be tested */
+	assert(key > 0);
 
 	printf("Pass\n");
 }
diff --git a/tools/testing/selftests/locking/ww_mutex.sh b/tools/testing/selftests/locking/ww_mutex.sh
new file mode 100644
index 000000000000..6905da965f3b
--- /dev/null
+++ b/tools/testing/selftests/locking/ww_mutex.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+# Runs API tests for struct ww_mutex (Wait/Wound mutexes)
+
+if /sbin/modprobe -q test-ww_mutex; then
+       /sbin/modprobe -q -r test-ww_mutex
+       echo "locking/ww_mutex: ok"
+else
+       echo "locking/ww_mutex: [FAIL]"
+       exit 1
+fi
diff --git a/tools/testing/selftests/rcutorture/configs/lock/CFLIST b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
index b9611c523723..41bae5824339 100644
--- a/tools/testing/selftests/rcutorture/configs/lock/CFLIST
+++ b/tools/testing/selftests/rcutorture/configs/lock/CFLIST
@@ -4,3 +4,4 @@ LOCK03
 LOCK04
 LOCK05
 LOCK06
+LOCK07
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK07 b/tools/testing/selftests/rcutorture/configs/lock/LOCK07
new file mode 100644
index 000000000000..1d1da1477fc3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK07
@@ -0,0 +1,6 @@
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_HOTPLUG_CPU=y
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=y
diff --git a/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot b/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot
new file mode 100644
index 000000000000..97dadd1a9e45
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/lock/LOCK07.boot
@@ -0,0 +1 @@
+locktorture.torture_type=ww_mutex_lock
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
index f824b4c9d9d9..d2d2a86139db 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
+++ b/tools/testing/selftests/rcutorture/configs/rcu/CFcommon
@@ -1,5 +1,2 @@
 CONFIG_RCU_TORTURE_TEST=y
 CONFIG_PRINTK_TIME=y
-CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
-CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
-CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY01 b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
index 0a63e073a00c..6db705e55487 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY01
@@ -7,6 +7,7 @@ CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=y
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_TRACE=n
+#CHECK#CONFIG_RCU_STALL_COMMON=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_PREEMPT_COUNT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TINY02 b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
index f1892e0371c9..a59f7686e219 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TINY02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TINY02
@@ -8,7 +8,8 @@ CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=n
 CONFIG_RCU_TRACE=y
 CONFIG_PROVE_LOCKING=y
+CONFIG_PROVE_RCU_REPEATEDLY=y
 #CHECK#CONFIG_PROVE_RCU=y
 CONFIG_DEBUG_LOCK_ALLOC=y
-CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
 CONFIG_PREEMPT_COUNT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01 b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
index f572b873c620..359cb258f639 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01
@@ -16,3 +16,6 @@ CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE02 b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
index ef6a22c44dea..c1ab5926568b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE02
@@ -20,3 +20,7 @@ CONFIG_PROVE_LOCKING=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03 b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
index 7a17c503b382..3b93ee544e70 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03
@@ -17,3 +17,6 @@ CONFIG_RCU_BOOST=y
 CONFIG_RCU_KTHREAD_PRIO=2
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 17cbe098b115..5af758e783c7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -19,3 +19,7 @@ CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
+CONFIG_RCU_EQS_DEBUG=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE05 b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
index 1257d3227b1e..d4cdc0d74e16 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE05
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE05
@@ -19,3 +19,6 @@ CONFIG_PROVE_LOCKING=y
 #CHECK#CONFIG_PROVE_RCU=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE06 b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
index d3e456b74cbe..4cb02bd28f08 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE06
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE06
@@ -20,3 +20,6 @@ CONFIG_PROVE_LOCKING=y
 #CHECK#CONFIG_PROVE_RCU=y
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
 CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index 3956b4131f72..b12a3ea1867e 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -19,3 +19,6 @@ CONFIG_RCU_NOCB_CPU=n
 CONFIG_DEBUG_LOCK_ALLOC=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP=y
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT=y
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08 b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
index bb9b0c1a23c2..099cc63c6a3b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE08
@@ -17,8 +17,8 @@ CONFIG_RCU_FANOUT_LEAF=2
 CONFIG_RCU_NOCB_CPU=y
 CONFIG_RCU_NOCB_CPU_ALL=y
 CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_PROVE_LOCKING=y
-#CHECK#CONFIG_PROVE_RCU=y
+CONFIG_PROVE_LOCKING=n
 CONFIG_RCU_BOOST=n
 CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
 CONFIG_RCU_EXPERT=y
+CONFIG_RCU_EQS_DEBUG=y
diff --git a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
index 4e2b1893d40d..364801b1a230 100644
--- a/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
+++ b/tools/testing/selftests/rcutorture/doc/TREE_RCU-kconfig.txt
@@ -14,6 +14,7 @@ CONFIG_NO_HZ_FULL_SYSIDLE -- Do one.
 CONFIG_PREEMPT -- Do half.  (First three and #8.)
 CONFIG_PROVE_LOCKING -- Do several, covering CONFIG_DEBUG_LOCK_ALLOC=y and not.
 CONFIG_PROVE_RCU -- Hardwired to CONFIG_PROVE_LOCKING.
+CONFIG_PROVE_RCU_REPEATEDLY -- Do one.
 CONFIG_RCU_BOOST -- one of PREEMPT_RCU.
 CONFIG_RCU_KTHREAD_PRIO -- set to 2 for _BOOST testing.
 CONFIG_RCU_FANOUT -- Cover hierarchy, but overlap with others.
@@ -25,7 +26,12 @@ CONFIG_RCU_NOCB_CPU_NONE -- Do one.
 CONFIG_RCU_NOCB_CPU_ZERO -- Do one.
 CONFIG_RCU_TRACE -- Do half.
 CONFIG_SMP -- Need one !SMP for PREEMPT_RCU.
-!RCU_EXPERT -- Do a few, but these have to be vanilla configurations.
+CONFIG_RCU_EXPERT=n -- Do a few, but these have to be vanilla configurations.
+CONFIG_RCU_EQS_DEBUG -- Do at least one for CONFIG_NO_HZ_FULL and not.
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP -- Do for all but a couple TREE scenarios.
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT -- Do for all but a couple TREE scenarios.
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT -- Do for all but a couple TREE scenarios.
+
 RCU-bh: Do one with PREEMPT and one with !PREEMPT.
 RCU-sched: Do one with PREEMPT but not BOOST.
 
@@ -72,7 +78,30 @@ CONFIG_RCU_TORTURE_TEST_RUNNABLE
 
 	Always used in KVM testing.
 
+CONFIG_RCU_TORTURE_TEST_SLOW_PREINIT_DELAY
+CONFIG_RCU_TORTURE_TEST_SLOW_INIT_DELAY
+CONFIG_RCU_TORTURE_TEST_SLOW_CLEANUP_DELAY
+
+	Inspection suffices, ignore.
+
 CONFIG_PREEMPT_RCU
 CONFIG_TREE_RCU
+CONFIG_TINY_RCU
+
+	These are controlled by CONFIG_PREEMPT and/or CONFIG_SMP.
+
+CONFIG_SPARSE_RCU_POINTER
+
+	Makes sense only for sparse runs, not for kernel builds.
+
+CONFIG_SRCU
+CONFIG_TASKS_RCU
+
+	Selected by CONFIG_RCU_TORTURE_TEST, so cannot disable.
+
+CONFIG_RCU_TRACE
+
+	Implied by CONFIG_RCU_TRACE for Tree RCU.
+
 
-	These are controlled by CONFIG_PREEMPT.
+boot parameters ignored: TBD
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore
new file mode 100644
index 000000000000..712a3d41a325
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/.gitignore
@@ -0,0 +1 @@
+srcu.c
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile
new file mode 100644
index 000000000000..16b01559fa55
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/Makefile
@@ -0,0 +1,16 @@
+all: srcu.c store_buffering
+
+LINUX_SOURCE = ../../../../../..
+
+modified_srcu_input = $(LINUX_SOURCE)/include/linux/srcu.h \
+		      $(LINUX_SOURCE)/kernel/rcu/srcu.c
+
+modified_srcu_output = include/linux/srcu.h srcu.c
+
+include/linux/srcu.h: srcu.c
+
+srcu.c: modify_srcu.awk Makefile $(modified_srcu_input)
+	awk -f modify_srcu.awk $(modified_srcu_input) $(modified_srcu_output)
+
+store_buffering:
+	@cd tests/store_buffering; make
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/delay.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/export.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/mutex.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/percpu.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/preempt.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/rcupdate.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/sched.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/smp.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/linux/workqueue.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/empty_includes/uapi/linux/types.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore
new file mode 100644
index 000000000000..1d016e66980a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/.gitignore
@@ -0,0 +1 @@
+srcu.h
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h
new file mode 100644
index 000000000000..f2860dd1b407
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/kconfig.h
@@ -0,0 +1 @@
+#include <LINUX_SOURCE/linux/kconfig.h>
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h
new file mode 100644
index 000000000000..4a3d538fef12
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/include/linux/types.h
@@ -0,0 +1,155 @@
+/*
+ * This header has been modifies to remove definitions of types that
+ * are defined in standard userspace headers or are problematic for some
+ * other reason.
+ */
+
+#ifndef _LINUX_TYPES_H
+#define _LINUX_TYPES_H
+
+#define __EXPORTED_HEADERS__
+#include <uapi/linux/types.h>
+
+#ifndef __ASSEMBLY__
+
+#define DECLARE_BITMAP(name, bits) \
+	unsigned long name[BITS_TO_LONGS(bits)]
+
+typedef __u32 __kernel_dev_t;
+
+/* bsd */
+typedef unsigned char		u_char;
+typedef unsigned short		u_short;
+typedef unsigned int		u_int;
+typedef unsigned long		u_long;
+
+/* sysv */
+typedef unsigned char		unchar;
+typedef unsigned short		ushort;
+typedef unsigned int		uint;
+typedef unsigned long		ulong;
+
+#ifndef __BIT_TYPES_DEFINED__
+#define __BIT_TYPES_DEFINED__
+
+typedef		__u8		u_int8_t;
+typedef		__s8		int8_t;
+typedef		__u16		u_int16_t;
+typedef		__s16		int16_t;
+typedef		__u32		u_int32_t;
+typedef		__s32		int32_t;
+
+#endif /* !(__BIT_TYPES_DEFINED__) */
+
+typedef		__u8		uint8_t;
+typedef		__u16		uint16_t;
+typedef		__u32		uint32_t;
+
+/* this is a special 64bit data type that is 8-byte aligned */
+#define aligned_u64 __u64 __attribute__((aligned(8)))
+#define aligned_be64 __be64 __attribute__((aligned(8)))
+#define aligned_le64 __le64 __attribute__((aligned(8)))
+
+/**
+ * The type used for indexing onto a disc or disc partition.
+ *
+ * Linux always considers sectors to be 512 bytes long independently
+ * of the devices real block size.
+ *
+ * blkcnt_t is the type of the inode's block count.
+ */
+#ifdef CONFIG_LBDAF
+typedef u64 sector_t;
+#else
+typedef unsigned long sector_t;
+#endif
+
+/*
+ * The type of an index into the pagecache.
+ */
+#define pgoff_t unsigned long
+
+/*
+ * A dma_addr_t can hold any valid DMA address, i.e., any address returned
+ * by the DMA API.
+ *
+ * If the DMA API only uses 32-bit addresses, dma_addr_t need only be 32
+ * bits wide.  Bus addresses, e.g., PCI BARs, may be wider than 32 bits,
+ * but drivers do memory-mapped I/O to ioremapped kernel virtual addresses,
+ * so they don't care about the size of the actual bus addresses.
+ */
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+typedef u64 dma_addr_t;
+#else
+typedef u32 dma_addr_t;
+#endif
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+typedef u64 phys_addr_t;
+#else
+typedef u32 phys_addr_t;
+#endif
+
+typedef phys_addr_t resource_size_t;
+
+/*
+ * This type is the placeholder for a hardware interrupt number. It has to be
+ * big enough to enclose whatever representation is used by a given platform.
+ */
+typedef unsigned long irq_hw_number_t;
+
+typedef struct {
+	int counter;
+} atomic_t;
+
+#ifdef CONFIG_64BIT
+typedef struct {
+	long counter;
+} atomic64_t;
+#endif
+
+struct list_head {
+	struct list_head *next, *prev;
+};
+
+struct hlist_head {
+	struct hlist_node *first;
+};
+
+struct hlist_node {
+	struct hlist_node *next, **pprev;
+};
+
+/**
+ * struct callback_head - callback structure for use with RCU and task_work
+ * @next: next update requests in a list
+ * @func: actual update function to call after the grace period.
+ *
+ * The struct is aligned to size of pointer. On most architectures it happens
+ * naturally due ABI requirements, but some architectures (like CRIS) have
+ * weird ABI and we need to ask it explicitly.
+ *
+ * The alignment is required to guarantee that bits 0 and 1 of @next will be
+ * clear under normal conditions -- as long as we use call_rcu(),
+ * call_rcu_bh(), call_rcu_sched(), or call_srcu() to queue callback.
+ *
+ * This guarantee is important for few reasons:
+ *  - future call_rcu_lazy() will make use of lower bits in the pointer;
+ *  - the structure shares storage spacer in struct page with @compound_head,
+ *    which encode PageTail() in bit 0. The guarantee is needed to avoid
+ *    false-positive PageTail().
+ */
+struct callback_head {
+	struct callback_head *next;
+	void (*func)(struct callback_head *head);
+} __attribute__((aligned(sizeof(void *))));
+#define rcu_head callback_head
+
+typedef void (*rcu_callback_t)(struct rcu_head *head);
+typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func);
+
+/* clocksource cycle base type */
+typedef u64 cycle_t;
+
+#endif /*  __ASSEMBLY__ */
+#endif /* _LINUX_TYPES_H */
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk
new file mode 100755
index 000000000000..8ff89043d0a9
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/modify_srcu.awk
@@ -0,0 +1,375 @@
+#!/bin/awk -f
+
+# Modify SRCU for formal verification. The first argument should be srcu.h and
+# the second should be srcu.c. Outputs modified srcu.h and srcu.c into the
+# current directory.
+
+BEGIN {
+	if (ARGC != 5) {
+		print "Usange: input.h input.c output.h output.c" > "/dev/stderr";
+		exit 1;
+	}
+	h_output = ARGV[3];
+	c_output = ARGV[4];
+	ARGC = 3;
+
+	# Tokenize using FS and not RS as FS supports regular expressions. Each
+	# record is one line of source, except that backslashed lines are
+	# combined. Comments are treated as field separators, as are quotes.
+	quote_regexp="\"([^\\\\\"]|\\\\.)*\"";
+	comment_regexp="\\/\\*([^*]|\\*+[^*/])*\\*\\/|\\/\\/.*(\n|$)";
+	FS="([ \\\\\t\n\v\f;,.=(){}+*/<>&|^-]|\\[|\\]|" comment_regexp "|" quote_regexp ")+";
+
+	inside_srcu_struct = 0;
+	inside_srcu_init_def = 0;
+	srcu_init_param_name = "";
+	in_macro = 0;
+	brace_nesting = 0;
+	paren_nesting = 0;
+
+	# Allow the manipulation of the last field separator after has been
+	# seen.
+	last_fs = "";
+	# Whether the last field separator was intended to be output.
+	last_fs_print = 0;
+
+	# rcu_batches stores the initialization for each instance of struct
+	# rcu_batch
+
+	in_comment = 0;
+
+	outputfile = "";
+}
+
+{
+	prev_outputfile = outputfile;
+	if (FILENAME ~ /\.h$/) {
+		outputfile = h_output;
+		if (FNR != NR) {
+			print "Incorrect file order" > "/dev/stderr";
+			exit 1;
+		}
+	}
+	else
+		outputfile = c_output;
+
+	if (prev_outputfile && outputfile != prev_outputfile) {
+		new_outputfile = outputfile;
+		outputfile = prev_outputfile;
+		update_fieldsep("", 0);
+		outputfile = new_outputfile;
+	}
+}
+
+# Combine the next line into $0.
+function combine_line() {
+	ret = getline next_line;
+	if (ret == 0) {
+		# Don't allow two consecutive getlines at the end of the file
+		if (eof_found) {
+			print "Error: expected more input." > "/dev/stderr";
+			exit 1;
+		} else {
+			eof_found = 1;
+		}
+	} else if (ret == -1) {
+		print "Error reading next line of file" FILENAME > "/dev/stderr";
+		exit 1;
+	}
+	$0 = $0 "\n" next_line;
+}
+
+# Combine backslashed lines and multiline comments.
+function combine_backslashes() {
+	while (/\\$|\/\*([^*]|\*+[^*\/])*\**$/) {
+		combine_line();
+	}
+}
+
+function read_line() {
+	combine_line();
+	combine_backslashes();
+}
+
+# Print out field separators and update variables that depend on them. Only
+# print if p is true. Call with sep="" and p=0 to print out the last field
+# separator.
+function update_fieldsep(sep, p) {
+	# Count braces
+	sep_tmp = sep;
+	gsub(quote_regexp "|" comment_regexp, "", sep_tmp);
+	while (1)
+	{
+		if (sub("[^{}()]*\\{", "", sep_tmp)) {
+			brace_nesting++;
+			continue;
+		}
+		if (sub("[^{}()]*\\}", "", sep_tmp)) {
+			brace_nesting--;
+			if (brace_nesting < 0) {
+				print "Unbalanced braces!" > "/dev/stderr";
+				exit 1;
+			}
+			continue;
+		}
+		if (sub("[^{}()]*\\(", "", sep_tmp)) {
+			paren_nesting++;
+			continue;
+		}
+		if (sub("[^{}()]*\\)", "", sep_tmp)) {
+			paren_nesting--;
+			if (paren_nesting < 0) {
+				print "Unbalanced parenthesis!" > "/dev/stderr";
+				exit 1;
+			}
+			continue;
+		}
+
+		break;
+	}
+
+	if (last_fs_print)
+		printf("%s", last_fs) > outputfile;
+	last_fs = sep;
+	last_fs_print = p;
+}
+
+# Shifts the fields down by n positions. Calls next if there are no more. If p
+# is true then print out field separators.
+function shift_fields(n, p) {
+	do {
+		if (match($0, FS) > 0) {
+			update_fieldsep(substr($0, RSTART, RLENGTH), p);
+			if (RSTART + RLENGTH <= length())
+				$0 = substr($0, RSTART + RLENGTH);
+			else
+				$0 = "";
+		} else {
+			update_fieldsep("", 0);
+			print "" > outputfile;
+			next;
+		}
+	} while (--n > 0);
+}
+
+# Shifts and prints the first n fields.
+function print_fields(n) {
+	do {
+		update_fieldsep("", 0);
+		printf("%s", $1) > outputfile;
+		shift_fields(1, 1);
+	} while (--n > 0);
+}
+
+{
+	combine_backslashes();
+}
+
+# Print leading FS
+{
+	if (match($0, "^(" FS ")+") > 0) {
+		update_fieldsep(substr($0, RSTART, RLENGTH), 1);
+		if (RSTART + RLENGTH <= length())
+			$0 = substr($0, RSTART + RLENGTH);
+		else
+			$0 = "";
+	}
+}
+
+# Parse the line.
+{
+	while (NF > 0) {
+		if ($1 == "struct" && NF < 3) {
+			read_line();
+			continue;
+		}
+
+		if (FILENAME ~ /\.h$/ && !inside_srcu_struct &&
+		    brace_nesting == 0 && paren_nesting == 0 &&
+		    $1 == "struct" && $2 == "srcu_struct" &&
+		    $0 ~ "^struct(" FS ")+srcu_struct(" FS ")+\\{") {
+			inside_srcu_struct = 1;
+			print_fields(2);
+			continue;
+		}
+		if (inside_srcu_struct && brace_nesting == 0 &&
+		    paren_nesting == 0) {
+			inside_srcu_struct = 0;
+			update_fieldsep("", 0);
+			for (name in rcu_batches)
+				print "extern struct rcu_batch " name ";" > outputfile;
+		}
+
+		if (inside_srcu_struct && $1 == "struct" && $2 == "rcu_batch") {
+			# Move rcu_batches outside of the struct.
+			rcu_batches[$3] = "";
+			shift_fields(3, 1);
+			sub(/;[[:space:]]*$/, "", last_fs);
+			continue;
+		}
+
+		if (FILENAME ~ /\.h$/ && !inside_srcu_init_def &&
+		    $1 == "#define" && $2 == "__SRCU_STRUCT_INIT") {
+			inside_srcu_init_def = 1;
+			srcu_init_param_name = $3;
+			in_macro = 1;
+			print_fields(3);
+			continue;
+		}
+		if (inside_srcu_init_def && brace_nesting == 0 &&
+		    paren_nesting == 0) {
+			inside_srcu_init_def = 0;
+			in_macro = 0;
+			continue;
+		}
+
+		if (inside_srcu_init_def && brace_nesting == 1 &&
+		    paren_nesting == 0 && last_fs ~ /\.[[:space:]]*$/ &&
+		    $1 ~ /^[[:alnum:]_]+$/) {
+			name = $1;
+			if (name in rcu_batches) {
+				# Remove the dot.
+				sub(/\.[[:space:]]*$/, "", last_fs);
+
+				old_record = $0;
+				do
+					shift_fields(1, 0);
+				while (last_fs !~ /,/ || paren_nesting > 0);
+				end_loc = length(old_record) - length($0);
+				end_loc += index(last_fs, ",") - length(last_fs);
+
+				last_fs = substr(last_fs, index(last_fs, ",") + 1);
+				last_fs_print = 1;
+
+				match(old_record, "^"name"("FS")+=");
+				start_loc = RSTART + RLENGTH;
+
+				len = end_loc - start_loc;
+				initializer = substr(old_record, start_loc, len);
+				gsub(srcu_init_param_name "\\.", "", initializer);
+				rcu_batches[name] = initializer;
+				continue;
+			}
+		}
+
+		# Don't include a nonexistent file
+		if (!in_macro && $1 == "#include" && /^#include[[:space:]]+"rcu\.h"/) {
+			update_fieldsep("", 0);
+			next;
+		}
+
+		# Ignore most preprocessor stuff.
+		if (!in_macro && $1 ~ /#/) {
+			break;
+		}
+
+		if (brace_nesting > 0 && $1 ~ "^[[:alnum:]_]+$" && NF < 2) {
+			read_line();
+			continue;
+		}
+		if (brace_nesting > 0 &&
+		    $0 ~ "^[[:alnum:]_]+[[:space:]]*(\\.|->)[[:space:]]*[[:alnum:]_]+" &&
+		    $2 in rcu_batches) {
+			# Make uses of rcu_batches global. Somewhat unreliable.
+			shift_fields(1, 0);
+			print_fields(1);
+			continue;
+		}
+
+		if ($1 == "static" && NF < 3) {
+			read_line();
+			continue;
+		}
+		if ($1 == "static" && ($2 == "bool" && $3 == "try_check_zero" ||
+		                       $2 == "void" && $3 == "srcu_flip")) {
+			shift_fields(1, 1);
+			print_fields(2);
+			continue;
+		}
+
+		# Distinguish between read-side and write-side memory barriers.
+		if ($1 == "smp_mb" && NF < 2) {
+			read_line();
+			continue;
+		}
+		if (match($0, /^smp_mb[[:space:]();\/*]*[[:alnum:]]/)) {
+			barrier_letter = substr($0, RLENGTH, 1);
+			if (barrier_letter ~ /A|D/)
+				new_barrier_name = "sync_smp_mb";
+			else if (barrier_letter ~ /B|C/)
+				new_barrier_name = "rs_smp_mb";
+			else {
+				print "Unrecognized memory barrier." > "/dev/null";
+				exit 1;
+			}
+
+			shift_fields(1, 1);
+			printf("%s", new_barrier_name) > outputfile;
+			continue;
+		}
+
+		# Skip definition of rcu_synchronize, since it is already
+		# defined in misc.h. Only present in old versions of srcu.
+		if (brace_nesting == 0 && paren_nesting == 0 &&
+		    $1 == "struct" && $2 == "rcu_synchronize" &&
+		    $0 ~ "^struct(" FS ")+rcu_synchronize(" FS ")+\\{") {
+			shift_fields(2, 0);
+			while (brace_nesting) {
+				if (NF < 2)
+					read_line();
+				shift_fields(1, 0);
+			}
+		}
+
+		# Skip definition of wakeme_after_rcu for the same reason
+		if (brace_nesting == 0 && $1 == "static" && $2 == "void" &&
+		    $3 == "wakeme_after_rcu") {
+			while (NF < 5)
+				read_line();
+			shift_fields(3, 0);
+			do {
+				while (NF < 3)
+					read_line();
+				shift_fields(1, 0);
+			} while (paren_nesting || brace_nesting);
+		}
+
+		if ($1 ~ /^(unsigned|long)$/ && NF < 3) {
+			read_line();
+			continue;
+		}
+
+		# Give srcu_batches_completed the correct type for old SRCU.
+		if (brace_nesting == 0 && $1 == "long" &&
+		    $2 == "srcu_batches_completed") {
+			update_fieldsep("", 0);
+			printf("unsigned ") > outputfile;
+			print_fields(2);
+			continue;
+		}
+		if (brace_nesting == 0 && $1 == "unsigned" && $2 == "long" &&
+		    $3 == "srcu_batches_completed") {
+			print_fields(3);
+			continue;
+		}
+
+		# Just print out the input code by default.
+		print_fields(1);
+	}
+	update_fieldsep("", 0);
+	print > outputfile;
+	next;
+}
+
+END {
+	update_fieldsep("", 0);
+
+	if (brace_nesting != 0) {
+		print "Unbalanced braces!" > "/dev/stderr";
+		exit 1;
+	}
+
+	# Define the rcu_batches
+	for (name in rcu_batches)
+		print "struct rcu_batch " name " = " rcu_batches[name] ";" > c_output;
+}
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h
new file mode 100644
index 000000000000..a64955447995
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/assume.h
@@ -0,0 +1,16 @@
+#ifndef ASSUME_H
+#define ASSUME_H
+
+/* Provide an assumption macro that can be disabled for gcc. */
+#ifdef RUN
+#define assume(x) \
+	do { \
+		/* Evaluate x to suppress warnings. */ \
+		(void) (x); \
+	} while (0)
+
+#else
+#define assume(x) __CPROVER_assume(x)
+#endif
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h
new file mode 100644
index 000000000000..6687acc08e6d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/barriers.h
@@ -0,0 +1,41 @@
+#ifndef BARRIERS_H
+#define BARRIERS_H
+
+#define barrier() __asm__ __volatile__("" : : : "memory")
+
+#ifdef RUN
+#define smp_mb() __sync_synchronize()
+#define smp_mb__after_unlock_lock() __sync_synchronize()
+#else
+/*
+ * Copied from CBMC's implementation of __sync_synchronize(), which
+ * seems to be disabled by default.
+ */
+#define smp_mb() __CPROVER_fence("WWfence", "RRfence", "RWfence", "WRfence", \
+				 "WWcumul", "RRcumul", "RWcumul", "WRcumul")
+#define smp_mb__after_unlock_lock() __CPROVER_fence("WWfence", "RRfence", "RWfence", "WRfence", \
+				    "WWcumul", "RRcumul", "RWcumul", "WRcumul")
+#endif
+
+/*
+ * Allow memory barriers to be disabled in either the read or write side
+ * of SRCU individually.
+ */
+
+#ifndef NO_SYNC_SMP_MB
+#define sync_smp_mb() smp_mb()
+#else
+#define sync_smp_mb() do {} while (0)
+#endif
+
+#ifndef NO_READ_SIDE_SMP_MB
+#define rs_smp_mb() smp_mb()
+#else
+#define rs_smp_mb() do {} while (0)
+#endif
+
+#define ACCESS_ONCE(x) (*(volatile typeof(x) *) &(x))
+#define READ_ONCE(x) ACCESS_ONCE(x)
+#define WRITE_ONCE(x, val) (ACCESS_ONCE(x) = (val))
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h
new file mode 100644
index 000000000000..2a80e91f78e7
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/bug_on.h
@@ -0,0 +1,13 @@
+#ifndef BUG_ON_H
+#define BUG_ON_H
+
+#include <assert.h>
+
+#define BUG() assert(0)
+#define BUG_ON(x) assert(!(x))
+
+/* Does it make sense to treat warnings as errors? */
+#define WARN() BUG()
+#define WARN_ON(x) (BUG_ON(x), false)
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c
new file mode 100644
index 000000000000..29eb5d2697ed
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/combined_source.c
@@ -0,0 +1,13 @@
+#include <config.h>
+
+/* Include all source files. */
+
+#include "include_srcu.c"
+
+#include "preempt.c"
+#include "misc.c"
+
+/* Used by test.c files */
+#include <pthread.h>
+#include <stdlib.h>
+#include <linux/srcu.h>
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h
new file mode 100644
index 000000000000..a60038aeea7a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/config.h
@@ -0,0 +1,27 @@
+/* "Cheater" definitions based on restricted Kconfig choices. */
+
+#undef CONFIG_TINY_RCU
+#undef __CHECKER__
+#undef CONFIG_DEBUG_LOCK_ALLOC
+#undef CONFIG_DEBUG_OBJECTS_RCU_HEAD
+#undef CONFIG_HOTPLUG_CPU
+#undef CONFIG_MODULES
+#undef CONFIG_NO_HZ_FULL_SYSIDLE
+#undef CONFIG_PREEMPT_COUNT
+#undef CONFIG_PREEMPT_RCU
+#undef CONFIG_PROVE_RCU
+#undef CONFIG_RCU_NOCB_CPU
+#undef CONFIG_RCU_NOCB_CPU_ALL
+#undef CONFIG_RCU_STALL_COMMON
+#undef CONFIG_RCU_TRACE
+#undef CONFIG_RCU_USER_QS
+#undef CONFIG_TASKS_RCU
+#define CONFIG_TREE_RCU
+
+#define CONFIG_GENERIC_ATOMIC64
+
+#if NR_CPUS > 1
+#define CONFIG_SMP
+#else
+#undef CONFIG_SMP
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c
new file mode 100644
index 000000000000..5ec582a53018
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/include_srcu.c
@@ -0,0 +1,31 @@
+#include <config.h>
+
+#include <assert.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <pthread.h>
+#include <stddef.h>
+#include <string.h>
+#include <sys/types.h>
+
+#include "int_typedefs.h"
+
+#include "barriers.h"
+#include "bug_on.h"
+#include "locks.h"
+#include "misc.h"
+#include "preempt.h"
+#include "percpu.h"
+#include "workqueues.h"
+
+#ifdef USE_SIMPLE_SYNC_SRCU
+#define synchronize_srcu(sp) synchronize_srcu_original(sp)
+#endif
+
+#include <srcu.c>
+
+#ifdef USE_SIMPLE_SYNC_SRCU
+#undef synchronize_srcu
+
+#include "simple_sync_srcu.c"
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h
new file mode 100644
index 000000000000..3aad63917858
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/int_typedefs.h
@@ -0,0 +1,33 @@
+#ifndef INT_TYPEDEFS_H
+#define INT_TYPEDEFS_H
+
+#include <inttypes.h>
+
+typedef int8_t s8;
+typedef uint8_t u8;
+typedef int16_t s16;
+typedef uint16_t u16;
+typedef int32_t s32;
+typedef uint32_t u32;
+typedef int64_t s64;
+typedef uint64_t u64;
+
+typedef int8_t __s8;
+typedef uint8_t __u8;
+typedef int16_t __s16;
+typedef uint16_t __u16;
+typedef int32_t __s32;
+typedef uint32_t __u32;
+typedef int64_t __s64;
+typedef uint64_t __u64;
+
+#define S8_C(x) INT8_C(x)
+#define U8_C(x) UINT8_C(x)
+#define S16_C(x) INT16_C(x)
+#define U16_C(x) UINT16_C(x)
+#define S32_C(x) INT32_C(x)
+#define U32_C(x) UINT32_C(x)
+#define S64_C(x) INT64_C(x)
+#define U64_C(x) UINT64_C(x)
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h
new file mode 100644
index 000000000000..356004665576
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/locks.h
@@ -0,0 +1,220 @@
+#ifndef LOCKS_H
+#define LOCKS_H
+
+#include <limits.h>
+#include <pthread.h>
+#include <stdbool.h>
+
+#include "assume.h"
+#include "bug_on.h"
+#include "preempt.h"
+
+int nondet_int(void);
+
+#define __acquire(x)
+#define __acquires(x)
+#define __release(x)
+#define __releases(x)
+
+/* Only use one lock mechanism. Select which one. */
+#ifdef PTHREAD_LOCK
+struct lock_impl {
+	pthread_mutex_t mutex;
+};
+
+static inline void lock_impl_lock(struct lock_impl *lock)
+{
+	BUG_ON(pthread_mutex_lock(&lock->mutex));
+}
+
+static inline void lock_impl_unlock(struct lock_impl *lock)
+{
+	BUG_ON(pthread_mutex_unlock(&lock->mutex));
+}
+
+static inline bool lock_impl_trylock(struct lock_impl *lock)
+{
+	int err = pthread_mutex_trylock(&lock->mutex);
+
+	if (!err)
+		return true;
+	else if (err == EBUSY)
+		return false;
+	BUG();
+}
+
+static inline void lock_impl_init(struct lock_impl *lock)
+{
+	pthread_mutex_init(&lock->mutex, NULL);
+}
+
+#define LOCK_IMPL_INITIALIZER {.mutex = PTHREAD_MUTEX_INITIALIZER}
+
+#else /* !defined(PTHREAD_LOCK) */
+/* Spinlock that assumes that it always gets the lock immediately. */
+
+struct lock_impl {
+	bool locked;
+};
+
+static inline bool lock_impl_trylock(struct lock_impl *lock)
+{
+#ifdef RUN
+	/* TODO: Should this be a test and set? */
+	return __sync_bool_compare_and_swap(&lock->locked, false, true);
+#else
+	__CPROVER_atomic_begin();
+	bool old_locked = lock->locked;
+	lock->locked = true;
+	__CPROVER_atomic_end();
+
+	/* Minimal barrier to prevent accesses leaking out of lock. */
+	__CPROVER_fence("RRfence", "RWfence");
+
+	return !old_locked;
+#endif
+}
+
+static inline void lock_impl_lock(struct lock_impl *lock)
+{
+	/*
+	 * CBMC doesn't support busy waiting, so just assume that the
+	 * lock is available.
+	 */
+	assume(lock_impl_trylock(lock));
+
+	/*
+	 * If the lock was already held by this thread then the assumption
+	 * is unsatisfiable (deadlock).
+	 */
+}
+
+static inline void lock_impl_unlock(struct lock_impl *lock)
+{
+#ifdef RUN
+	BUG_ON(!__sync_bool_compare_and_swap(&lock->locked, true, false));
+#else
+	/* Minimal barrier to prevent accesses leaking out of lock. */
+	__CPROVER_fence("RWfence", "WWfence");
+
+	__CPROVER_atomic_begin();
+	bool old_locked = lock->locked;
+	lock->locked = false;
+	__CPROVER_atomic_end();
+
+	BUG_ON(!old_locked);
+#endif
+}
+
+static inline void lock_impl_init(struct lock_impl *lock)
+{
+	lock->locked = false;
+}
+
+#define LOCK_IMPL_INITIALIZER {.locked = false}
+
+#endif /* !defined(PTHREAD_LOCK) */
+
+/*
+ * Implement spinlocks using the lock mechanism. Wrap the lock to prevent mixing
+ * locks of different types.
+ */
+typedef struct {
+	struct lock_impl internal_lock;
+} spinlock_t;
+
+#define SPIN_LOCK_UNLOCKED {.internal_lock = LOCK_IMPL_INITIALIZER}
+#define __SPIN_LOCK_UNLOCKED(x) SPIN_LOCK_UNLOCKED
+#define DEFINE_SPINLOCK(x) spinlock_t x = SPIN_LOCK_UNLOCKED
+
+static inline void spin_lock_init(spinlock_t *lock)
+{
+	lock_impl_init(&lock->internal_lock);
+}
+
+static inline void spin_lock(spinlock_t *lock)
+{
+	/*
+	 * Spin locks also need to be removed in order to eliminate all
+	 * memory barriers. They are only used by the write side anyway.
+	 */
+#ifndef NO_SYNC_SMP_MB
+	preempt_disable();
+	lock_impl_lock(&lock->internal_lock);
+#endif
+}
+
+static inline void spin_unlock(spinlock_t *lock)
+{
+#ifndef NO_SYNC_SMP_MB
+	lock_impl_unlock(&lock->internal_lock);
+	preempt_enable();
+#endif
+}
+
+/* Don't bother with interrupts */
+#define spin_lock_irq(lock) spin_lock(lock)
+#define spin_unlock_irq(lock) spin_unlock(lock)
+#define spin_lock_irqsave(lock, flags) spin_lock(lock)
+#define spin_unlock_irqrestore(lock, flags) spin_unlock(lock)
+
+/*
+ * This is supposed to return an int, but I think that a bool should work as
+ * well.
+ */
+static inline bool spin_trylock(spinlock_t *lock)
+{
+#ifndef NO_SYNC_SMP_MB
+	preempt_disable();
+	return lock_impl_trylock(&lock->internal_lock);
+#else
+	return true;
+#endif
+}
+
+struct completion {
+	/* Hopefuly this won't overflow. */
+	unsigned int count;
+};
+
+#define COMPLETION_INITIALIZER(x) {.count = 0}
+#define DECLARE_COMPLETION(x) struct completion x = COMPLETION_INITIALIZER(x)
+#define DECLARE_COMPLETION_ONSTACK(x) DECLARE_COMPLETION(x)
+
+static inline void init_completion(struct completion *c)
+{
+	c->count = 0;
+}
+
+static inline void wait_for_completion(struct completion *c)
+{
+	unsigned int prev_count = __sync_fetch_and_sub(&c->count, 1);
+
+	assume(prev_count);
+}
+
+static inline void complete(struct completion *c)
+{
+	unsigned int prev_count = __sync_fetch_and_add(&c->count, 1);
+
+	BUG_ON(prev_count == UINT_MAX);
+}
+
+/* This function probably isn't very useful for CBMC. */
+static inline bool try_wait_for_completion(struct completion *c)
+{
+	BUG();
+}
+
+static inline bool completion_done(struct completion *c)
+{
+	return c->count;
+}
+
+/* TODO: Implement complete_all */
+static inline void complete_all(struct completion *c)
+{
+	BUG();
+}
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c
new file mode 100644
index 000000000000..ca892e3b2351
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.c
@@ -0,0 +1,11 @@
+#include <config.h>
+
+#include "misc.h"
+#include "bug_on.h"
+
+struct rcu_head;
+
+void wakeme_after_rcu(struct rcu_head *head)
+{
+	BUG();
+}
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h
new file mode 100644
index 000000000000..aca50030f954
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/misc.h
@@ -0,0 +1,58 @@
+#ifndef MISC_H
+#define MISC_H
+
+#include "assume.h"
+#include "int_typedefs.h"
+#include "locks.h"
+
+#include <linux/types.h>
+
+/* Probably won't need to deal with bottom halves. */
+static inline void local_bh_disable(void) {}
+static inline void local_bh_enable(void) {}
+
+#define MODULE_ALIAS(X)
+#define module_param(...)
+#define EXPORT_SYMBOL_GPL(x)
+
+#define container_of(ptr, type, member) ({			\
+	const typeof(((type *)0)->member) *__mptr = (ptr);	\
+	(type *)((char *)__mptr - offsetof(type, member));	\
+})
+
+#ifndef USE_SIMPLE_SYNC_SRCU
+/* Abuse udelay to make sure that busy loops terminate. */
+#define udelay(x) assume(0)
+
+#else
+
+/* The simple custom synchronize_srcu is ok with try_check_zero failing. */
+#define udelay(x) do { } while (0)
+#endif
+
+#define trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \
+	do { } while (0)
+
+#define notrace
+
+/* Avoid including rcupdate.h */
+struct rcu_synchronize {
+	struct rcu_head head;
+	struct completion completion;
+};
+
+void wakeme_after_rcu(struct rcu_head *head);
+
+#define rcu_lock_acquire(a) do { } while (0)
+#define rcu_lock_release(a) do { } while (0)
+#define rcu_lockdep_assert(c, s) do { } while (0)
+#define RCU_LOCKDEP_WARN(c, s) do { } while (0)
+
+/* Let CBMC non-deterministically choose switch between normal and expedited. */
+bool rcu_gp_is_normal(void);
+bool rcu_gp_is_expedited(void);
+
+/* Do the same for old versions of rcu. */
+#define rcu_expedited (rcu_gp_is_expedited())
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h
new file mode 100644
index 000000000000..3de5a49de49b
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/percpu.h
@@ -0,0 +1,92 @@
+#ifndef PERCPU_H
+#define PERCPU_H
+
+#include <stddef.h>
+#include "bug_on.h"
+#include "preempt.h"
+
+#define __percpu
+
+/* Maximum size of any percpu data. */
+#define PERCPU_OFFSET (4 * sizeof(long))
+
+/* Ignore alignment, as CBMC doesn't care about false sharing. */
+#define alloc_percpu(type) __alloc_percpu(sizeof(type), 1)
+
+static inline void *__alloc_percpu(size_t size, size_t align)
+{
+	BUG();
+	return NULL;
+}
+
+static inline void free_percpu(void *ptr)
+{
+	BUG();
+}
+
+#define per_cpu_ptr(ptr, cpu) \
+	((typeof(ptr)) ((char *) (ptr) + PERCPU_OFFSET * cpu))
+
+#define __this_cpu_inc(pcp) __this_cpu_add(pcp, 1)
+#define __this_cpu_dec(pcp) __this_cpu_sub(pcp, 1)
+#define __this_cpu_sub(pcp, n) __this_cpu_add(pcp, -(typeof(pcp)) (n))
+
+#define this_cpu_inc(pcp) this_cpu_add(pcp, 1)
+#define this_cpu_dec(pcp) this_cpu_sub(pcp, 1)
+#define this_cpu_sub(pcp, n) this_cpu_add(pcp, -(typeof(pcp)) (n))
+
+/* Make CBMC use atomics to work around bug. */
+#ifdef RUN
+#define THIS_CPU_ADD_HELPER(ptr, x) (*(ptr) += (x))
+#else
+/*
+ * Split the atomic into a read and a write so that it has the least
+ * possible ordering.
+ */
+#define THIS_CPU_ADD_HELPER(ptr, x) \
+	do { \
+		typeof(ptr) this_cpu_add_helper_ptr = (ptr); \
+		typeof(ptr) this_cpu_add_helper_x = (x); \
+		typeof(*ptr) this_cpu_add_helper_temp; \
+		__CPROVER_atomic_begin(); \
+		this_cpu_add_helper_temp = *(this_cpu_add_helper_ptr); \
+		__CPROVER_atomic_end(); \
+		this_cpu_add_helper_temp += this_cpu_add_helper_x; \
+		__CPROVER_atomic_begin(); \
+		*(this_cpu_add_helper_ptr) = this_cpu_add_helper_temp; \
+		__CPROVER_atomic_end(); \
+	} while (0)
+#endif
+
+/*
+ * For some reason CBMC needs an atomic operation even though this is percpu
+ * data.
+ */
+#define __this_cpu_add(pcp, n) \
+	do { \
+		BUG_ON(preemptible()); \
+		THIS_CPU_ADD_HELPER(per_cpu_ptr(&(pcp), thread_cpu_id), \
+				    (typeof(pcp)) (n)); \
+	} while (0)
+
+#define this_cpu_add(pcp, n) \
+	do { \
+		int this_cpu_add_impl_cpu = get_cpu(); \
+		THIS_CPU_ADD_HELPER(per_cpu_ptr(&(pcp), this_cpu_add_impl_cpu), \
+				    (typeof(pcp)) (n)); \
+		put_cpu(); \
+	} while (0)
+
+/*
+ * This will cause a compiler warning because of the cast from char[][] to
+ * type*. This will cause a compile time error if type is too big.
+ */
+#define DEFINE_PER_CPU(type, name) \
+	char name[NR_CPUS][PERCPU_OFFSET]; \
+	typedef char percpu_too_big_##name \
+		[sizeof(type) > PERCPU_OFFSET ? -1 : 1]
+
+#define for_each_possible_cpu(cpu) \
+	for ((cpu) = 0; (cpu) < NR_CPUS; ++(cpu))
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c
new file mode 100644
index 000000000000..4f1b068e9b7a
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.c
@@ -0,0 +1,78 @@
+#include <config.h>
+
+#include "preempt.h"
+
+#include "assume.h"
+#include "locks.h"
+
+/* Support NR_CPUS of at most 64 */
+#define CPU_PREEMPTION_LOCKS_INIT0 LOCK_IMPL_INITIALIZER
+#define CPU_PREEMPTION_LOCKS_INIT1 \
+	CPU_PREEMPTION_LOCKS_INIT0, CPU_PREEMPTION_LOCKS_INIT0
+#define CPU_PREEMPTION_LOCKS_INIT2 \
+	CPU_PREEMPTION_LOCKS_INIT1, CPU_PREEMPTION_LOCKS_INIT1
+#define CPU_PREEMPTION_LOCKS_INIT3 \
+	CPU_PREEMPTION_LOCKS_INIT2, CPU_PREEMPTION_LOCKS_INIT2
+#define CPU_PREEMPTION_LOCKS_INIT4 \
+	CPU_PREEMPTION_LOCKS_INIT3, CPU_PREEMPTION_LOCKS_INIT3
+#define CPU_PREEMPTION_LOCKS_INIT5 \
+	CPU_PREEMPTION_LOCKS_INIT4, CPU_PREEMPTION_LOCKS_INIT4
+
+/*
+ * Simulate disabling preemption by locking a particular cpu. NR_CPUS
+ * should be the actual number of cpus, not just the maximum.
+ */
+struct lock_impl cpu_preemption_locks[NR_CPUS] = {
+	CPU_PREEMPTION_LOCKS_INIT0
+#if (NR_CPUS - 1) & 1
+	, CPU_PREEMPTION_LOCKS_INIT0
+#endif
+#if (NR_CPUS - 1) & 2
+	, CPU_PREEMPTION_LOCKS_INIT1
+#endif
+#if (NR_CPUS - 1) & 4
+	, CPU_PREEMPTION_LOCKS_INIT2
+#endif
+#if (NR_CPUS - 1) & 8
+	, CPU_PREEMPTION_LOCKS_INIT3
+#endif
+#if (NR_CPUS - 1) & 16
+	, CPU_PREEMPTION_LOCKS_INIT4
+#endif
+#if (NR_CPUS - 1) & 32
+	, CPU_PREEMPTION_LOCKS_INIT5
+#endif
+};
+
+#undef CPU_PREEMPTION_LOCKS_INIT0
+#undef CPU_PREEMPTION_LOCKS_INIT1
+#undef CPU_PREEMPTION_LOCKS_INIT2
+#undef CPU_PREEMPTION_LOCKS_INIT3
+#undef CPU_PREEMPTION_LOCKS_INIT4
+#undef CPU_PREEMPTION_LOCKS_INIT5
+
+__thread int thread_cpu_id;
+__thread int preempt_disable_count;
+
+void preempt_disable(void)
+{
+	BUG_ON(preempt_disable_count < 0 || preempt_disable_count == INT_MAX);
+
+	if (preempt_disable_count++)
+		return;
+
+	thread_cpu_id = nondet_int();
+	assume(thread_cpu_id >= 0);
+	assume(thread_cpu_id < NR_CPUS);
+	lock_impl_lock(&cpu_preemption_locks[thread_cpu_id]);
+}
+
+void preempt_enable(void)
+{
+	BUG_ON(preempt_disable_count < 1);
+
+	if (--preempt_disable_count)
+		return;
+
+	lock_impl_unlock(&cpu_preemption_locks[thread_cpu_id]);
+}
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h
new file mode 100644
index 000000000000..2f95ee0e4dd5
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/preempt.h
@@ -0,0 +1,58 @@
+#ifndef PREEMPT_H
+#define PREEMPT_H
+
+#include <stdbool.h>
+
+#include "bug_on.h"
+
+/* This flag contains garbage if preempt_disable_count is 0. */
+extern __thread int thread_cpu_id;
+
+/* Support recursive preemption disabling. */
+extern __thread int preempt_disable_count;
+
+void preempt_disable(void);
+void preempt_enable(void);
+
+static inline void preempt_disable_notrace(void)
+{
+	preempt_disable();
+}
+
+static inline void preempt_enable_no_resched(void)
+{
+	preempt_enable();
+}
+
+static inline void preempt_enable_notrace(void)
+{
+	preempt_enable();
+}
+
+static inline int preempt_count(void)
+{
+	return preempt_disable_count;
+}
+
+static inline bool preemptible(void)
+{
+	return !preempt_count();
+}
+
+static inline int get_cpu(void)
+{
+	preempt_disable();
+	return thread_cpu_id;
+}
+
+static inline void put_cpu(void)
+{
+	preempt_enable();
+}
+
+static inline void might_sleep(void)
+{
+	BUG_ON(preempt_disable_count);
+}
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c
new file mode 100644
index 000000000000..ac9cbc62b411
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/simple_sync_srcu.c
@@ -0,0 +1,50 @@
+#include <config.h>
+
+#include <assert.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <pthread.h>
+#include <stddef.h>
+#include <string.h>
+#include <sys/types.h>
+
+#include "int_typedefs.h"
+
+#include "barriers.h"
+#include "bug_on.h"
+#include "locks.h"
+#include "misc.h"
+#include "preempt.h"
+#include "percpu.h"
+#include "workqueues.h"
+
+#include <linux/srcu.h>
+
+/* Functions needed from modify_srcu.c */
+bool try_check_zero(struct srcu_struct *sp, int idx, int trycount);
+void srcu_flip(struct srcu_struct *sp);
+
+/* Simpler implementation of synchronize_srcu that ignores batching. */
+void synchronize_srcu(struct srcu_struct *sp)
+{
+	int idx;
+	/*
+	 * This code assumes that try_check_zero will succeed anyway,
+	 * so there is no point in multiple tries.
+	 */
+	const int trycount = 1;
+
+	might_sleep();
+
+	/* Ignore the lock, as multiple writers aren't working yet anyway. */
+
+	idx = 1 ^ (sp->completed & 1);
+
+	/* For comments see srcu_advance_batches. */
+
+	assume(try_check_zero(sp, idx, trycount));
+
+	srcu_flip(sp);
+
+	assume(try_check_zero(sp, idx^1, trycount));
+}
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h
new file mode 100644
index 000000000000..e58c8dfd3e90
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/src/workqueues.h
@@ -0,0 +1,102 @@
+#ifndef WORKQUEUES_H
+#define WORKQUEUES_H
+
+#include <stdbool.h>
+
+#include "barriers.h"
+#include "bug_on.h"
+#include "int_typedefs.h"
+
+#include <linux/types.h>
+
+/* Stub workqueue implementation. */
+
+struct work_struct;
+typedef void (*work_func_t)(struct work_struct *work);
+void delayed_work_timer_fn(unsigned long __data);
+
+struct work_struct {
+/*	atomic_long_t data; */
+	unsigned long data;
+
+	struct list_head entry;
+	work_func_t func;
+#ifdef CONFIG_LOCKDEP
+	struct lockdep_map lockdep_map;
+#endif
+};
+
+struct timer_list {
+	struct hlist_node	entry;
+	unsigned long		expires;
+	void			(*function)(unsigned long);
+	unsigned long		data;
+	u32			flags;
+	int			slack;
+};
+
+struct delayed_work {
+	struct work_struct work;
+	struct timer_list timer;
+
+	/* target workqueue and CPU ->timer uses to queue ->work */
+	struct workqueue_struct *wq;
+	int cpu;
+};
+
+
+static inline bool schedule_work(struct work_struct *work)
+{
+	BUG();
+	return true;
+}
+
+static inline bool schedule_work_on(int cpu, struct work_struct *work)
+{
+	BUG();
+	return true;
+}
+
+static inline bool queue_work(struct workqueue_struct *wq,
+			      struct work_struct *work)
+{
+	BUG();
+	return true;
+}
+
+static inline bool queue_delayed_work(struct workqueue_struct *wq,
+				      struct delayed_work *dwork,
+				      unsigned long delay)
+{
+	BUG();
+	return true;
+}
+
+#define INIT_WORK(w, f) \
+	do { \
+		(w)->data = 0; \
+		(w)->func = (f); \
+	} while (0)
+
+#define INIT_DELAYED_WORK(w, f) INIT_WORK(&(w)->work, (f))
+
+#define __WORK_INITIALIZER(n, f) { \
+		.data = 0, \
+		.entry = { &(n).entry, &(n).entry }, \
+		.func = f \
+	}
+
+/* Don't bother initializing timer. */
+#define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \
+	.work = __WORK_INITIALIZER((n).work, (f)), \
+	}
+
+#define DECLARE_WORK(n, f) \
+	struct workqueue_struct n = __WORK_INITIALIZER
+
+#define DECLARE_DELAYED_WORK(n, f) \
+	struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0)
+
+#define system_power_efficient_wq ((struct workqueue_struct *) NULL)
+
+#endif
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore
new file mode 100644
index 000000000000..f47cb2045f13
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/.gitignore
@@ -0,0 +1 @@
+*.out
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile
new file mode 100644
index 000000000000..3a3aee149225
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/Makefile
@@ -0,0 +1,11 @@
+CBMC_FLAGS = -I../.. -I../../src -I../../include -I../../empty_includes -32 -pointer-check -mm pso
+
+all:
+	for i in ./*.pass; do \
+		echo $$i ; \
+		CBMC_FLAGS="$(CBMC_FLAGS)" sh ../test_script.sh --should-pass $$i > $$i.out 2>&1 ; \
+	done
+	for i in ./*.fail; do \
+		echo $$i ; \
+		CBMC_FLAGS="$(CBMC_FLAGS)" sh ../test_script.sh --should-fail $$i > $$i.out 2>&1 ; \
+	done
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail
new file mode 100644
index 000000000000..40c8075919d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/assert_end.fail
@@ -0,0 +1 @@
+test_cbmc_options="-DASSERT_END"
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail
new file mode 100644
index 000000000000..ada5baf0b60d
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force.fail
@@ -0,0 +1 @@
+test_cbmc_options="-DFORCE_FAILURE"
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail
new file mode 100644
index 000000000000..8fe00c8db466
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force2.fail
@@ -0,0 +1 @@
+test_cbmc_options="-DFORCE_FAILURE_2"
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail
new file mode 100644
index 000000000000..612ed6772844
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/force3.fail
@@ -0,0 +1 @@
+test_cbmc_options="-DFORCE_FAILURE_3"
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/main.pass
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c
new file mode 100644
index 000000000000..470b1105a112
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/store_buffering/test.c
@@ -0,0 +1,72 @@
+#include <src/combined_source.c>
+
+int x;
+int y;
+
+int __unbuffered_tpr_x;
+int __unbuffered_tpr_y;
+
+DEFINE_SRCU(ss);
+
+void rcu_reader(void)
+{
+	int idx;
+
+#ifndef FORCE_FAILURE_3
+	idx = srcu_read_lock(&ss);
+#endif
+	might_sleep();
+
+	__unbuffered_tpr_y = READ_ONCE(y);
+#ifdef FORCE_FAILURE
+	srcu_read_unlock(&ss, idx);
+	idx = srcu_read_lock(&ss);
+#endif
+	WRITE_ONCE(x, 1);
+
+#ifndef FORCE_FAILURE_3
+	srcu_read_unlock(&ss, idx);
+#endif
+	might_sleep();
+}
+
+void *thread_update(void *arg)
+{
+	WRITE_ONCE(y, 1);
+#ifndef FORCE_FAILURE_2
+	synchronize_srcu(&ss);
+#endif
+	might_sleep();
+	__unbuffered_tpr_x = READ_ONCE(x);
+
+	return NULL;
+}
+
+void *thread_process_reader(void *arg)
+{
+	rcu_reader();
+
+	return NULL;
+}
+
+int main(int argc, char *argv[])
+{
+	pthread_t tu;
+	pthread_t tpr;
+
+	if (pthread_create(&tu, NULL, thread_update, NULL))
+		abort();
+	if (pthread_create(&tpr, NULL, thread_process_reader, NULL))
+		abort();
+	if (pthread_join(tu, NULL))
+		abort();
+	if (pthread_join(tpr, NULL))
+		abort();
+	assert(__unbuffered_tpr_y != 0 || __unbuffered_tpr_x != 0);
+
+#ifdef ASSERT_END
+	assert(0);
+#endif
+
+	return 0;
+}
diff --git a/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh
new file mode 100755
index 000000000000..d1545972a0fa
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/formal/srcu-cbmc/tests/test_script.sh
@@ -0,0 +1,102 @@
+#!/bin/sh
+
+# This script expects a mode (either --should-pass or --should-fail) followed by
+# an input file. The script uses the following environment variables. The test C
+# source file is expected to be named test.c in the directory containing the
+# input file.
+#
+# CBMC: The command to run CBMC. Default: cbmc
+# CBMC_FLAGS: Additional flags to pass to CBMC
+# NR_CPUS: Number of cpus to run tests with. Default specified by the test
+# SYNC_SRCU_MODE: Choose implementation of synchronize_srcu. Defaults to simple.
+#                 kernel: Version included in the linux kernel source.
+#                 simple: Use try_check_zero directly.
+#
+# The input file is a script that is sourced by this file. It can define any of
+# the following variables to configure the test.
+#
+# test_cbmc_options: Extra options to pass to CBMC.
+# min_cpus_fail: Minimum number of CPUs (NR_CPUS) for verification to fail.
+#                The test is expected to pass if it is run with fewer. (Only
+#                useful for .fail files)
+# default_cpus: Quantity of CPUs to use for the test, if not specified on the
+#               command line. Default: Larger of 2 and MIN_CPUS_FAIL.
+
+set -e
+
+if test "$#" -ne 2; then
+	echo "Expected one option followed by an input file" 1>&2
+	exit 99
+fi
+
+if test "x$1" = "x--should-pass"; then
+	should_pass="yes"
+elif test "x$1" = "x--should-fail"; then
+	should_pass="no"
+else
+	echo "Unrecognized argument '$1'" 1>&2
+
+	# Exit code 99 indicates a hard error.
+	exit 99
+fi
+
+CBMC=${CBMC:-cbmc}
+
+SYNC_SRCU_MODE=${SYNC_SRCU_MODE:-simple}
+
+case ${SYNC_SRCU_MODE} in
+kernel) sync_srcu_mode_flags="" ;;
+simple) sync_srcu_mode_flags="-DUSE_SIMPLE_SYNC_SRCU" ;;
+
+*)
+	echo "Unrecognized argument '${SYNC_SRCU_MODE}'" 1>&2
+	exit 99
+	;;
+esac
+
+min_cpus_fail=1
+
+c_file=`dirname "$2"`/test.c
+
+# Source the input file.
+. $2
+
+if test ${min_cpus_fail} -gt 2; then
+	default_default_cpus=${min_cpus_fail}
+else
+	default_default_cpus=2
+fi
+default_cpus=${default_cpus:-${default_default_cpus}}
+cpus=${NR_CPUS:-${default_cpus}}
+
+# Check if there are two few cpus to make the test fail.
+if test $cpus -lt ${min_cpus_fail:-0}; then
+	should_pass="yes"
+fi
+
+cbmc_opts="-DNR_CPUS=${cpus} ${sync_srcu_mode_flags} ${test_cbmc_options} ${CBMC_FLAGS}"
+
+echo "Running CBMC: ${CBMC} ${cbmc_opts} ${c_file}"
+if ${CBMC} ${cbmc_opts} "${c_file}"; then
+	# Verification successful. Make sure that it was supposed to verify.
+	test "x${should_pass}" = xyes
+else
+	cbmc_exit_status=$?
+
+	# An exit status of 10 indicates a failed verification.
+	# (see cbmc_parse_optionst::do_bmc in the CBMC source code)
+	if test ${cbmc_exit_status} -eq 10 && test "x${should_pass}" = xno; then
+		:
+	else
+		echo "CBMC returned ${cbmc_exit_status} exit status" 1>&2
+
+		# Parse errors have exit status 6. Any other type of error
+		# should be considered a hard error.
+		if test ${cbmc_exit_status} -ne 6 && \
+		   test ${cbmc_exit_status} -ne 10; then
+			exit 99
+		else
+			exit 1
+		fi
+	fi
+fi
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 8c1cb423cfe6..83d8b1c6cb0e 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -5,12 +5,12 @@ include ../lib.mk
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
 TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \
-			check_initial_reg_state sigreturn ldt_gdt iopl \
+			check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test \
 			protection_keys test_vdso
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
-TARGETS_C_64BIT_ONLY := fsgsbase
+TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
 TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
diff --git a/tools/testing/selftests/x86/sysret_rip.c b/tools/testing/selftests/x86/sysret_rip.c
new file mode 100644
index 000000000000..d85ec5b3671c
--- /dev/null
+++ b/tools/testing/selftests/x86/sysret_rip.c
@@ -0,0 +1,195 @@
+/*
+ * sigreturn.c - tests that x86 avoids Intel SYSRET pitfalls
+ * Copyright (c) 2014-2016 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include <sys/signal.h>
+#include <sys/ucontext.h>
+#include <sys/syscall.h>
+#include <err.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <setjmp.h>
+#include <sys/user.h>
+#include <sys/mman.h>
+#include <assert.h>
+
+
+asm (
+	".pushsection \".text\", \"ax\"\n\t"
+	".balign 4096\n\t"
+	"test_page: .globl test_page\n\t"
+	".fill 4094,1,0xcc\n\t"
+	"test_syscall_insn:\n\t"
+	"syscall\n\t"
+	".ifne . - test_page - 4096\n\t"
+	".error \"test page is not one page long\"\n\t"
+	".endif\n\t"
+	".popsection"
+    );
+
+extern const char test_page[];
+static void const *current_test_page_addr = test_page;
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static void clearhandler(int sig)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = SIG_DFL;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+/* State used by our signal handlers. */
+static gregset_t initial_regs;
+
+static volatile unsigned long rip;
+
+static void sigsegv_for_sigreturn_test(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
+
+	if (rip != ctx->uc_mcontext.gregs[REG_RIP]) {
+		printf("[FAIL]\tRequested RIP=0x%lx but got RIP=0x%lx\n",
+		       rip, (unsigned long)ctx->uc_mcontext.gregs[REG_RIP]);
+		fflush(stdout);
+		_exit(1);
+	}
+
+	memcpy(&ctx->uc_mcontext.gregs, &initial_regs, sizeof(gregset_t));
+
+	printf("[OK]\tGot SIGSEGV at RIP=0x%lx\n", rip);
+}
+
+static void sigusr1(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
+
+	memcpy(&initial_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t));
+
+	/* Set IP and CX to match so that SYSRET can happen. */
+	ctx->uc_mcontext.gregs[REG_RIP] = rip;
+	ctx->uc_mcontext.gregs[REG_RCX] = rip;
+
+	/* R11 and EFLAGS should already match. */
+	assert(ctx->uc_mcontext.gregs[REG_EFL] ==
+	       ctx->uc_mcontext.gregs[REG_R11]);
+
+	sethandler(SIGSEGV, sigsegv_for_sigreturn_test, SA_RESETHAND);
+
+	return;
+}
+
+static void test_sigreturn_to(unsigned long ip)
+{
+	rip = ip;
+	printf("[RUN]\tsigreturn to 0x%lx\n", ip);
+	raise(SIGUSR1);
+}
+
+static jmp_buf jmpbuf;
+
+static void sigsegv_for_fallthrough(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t*)ctx_void;
+
+	if (rip != ctx->uc_mcontext.gregs[REG_RIP]) {
+		printf("[FAIL]\tExpected SIGSEGV at 0x%lx but got RIP=0x%lx\n",
+		       rip, (unsigned long)ctx->uc_mcontext.gregs[REG_RIP]);
+		fflush(stdout);
+		_exit(1);
+	}
+
+	siglongjmp(jmpbuf, 1);
+}
+
+static void test_syscall_fallthrough_to(unsigned long ip)
+{
+	void *new_address = (void *)(ip - 4096);
+	void *ret;
+
+	printf("[RUN]\tTrying a SYSCALL that falls through to 0x%lx\n", ip);
+
+	ret = mremap((void *)current_test_page_addr, 4096, 4096,
+		     MREMAP_MAYMOVE | MREMAP_FIXED, new_address);
+	if (ret == MAP_FAILED) {
+		if (ip <= (1UL << 47) - PAGE_SIZE) {
+			err(1, "mremap to %p", new_address);
+		} else {
+			printf("[OK]\tmremap to %p failed\n", new_address);
+			return;
+		}
+	}
+
+	if (ret != new_address)
+		errx(1, "mremap malfunctioned: asked for %p but got %p\n",
+		     new_address, ret);
+
+	current_test_page_addr = new_address;
+	rip = ip;
+
+	if (sigsetjmp(jmpbuf, 1) == 0) {
+		asm volatile ("call *%[syscall_insn]" :: "a" (SYS_getpid),
+			      [syscall_insn] "rm" (ip - 2));
+		errx(1, "[FAIL]\tSyscall trampoline returned");
+	}
+
+	printf("[OK]\tWe survived\n");
+}
+
+int main()
+{
+	/*
+	 * When the kernel returns from a slow-path syscall, it will
+	 * detect whether SYSRET is appropriate.  If it incorrectly
+	 * thinks that SYSRET is appropriate when RIP is noncanonical,
+	 * it'll crash on Intel CPUs.
+	 */
+	sethandler(SIGUSR1, sigusr1, 0);
+	for (int i = 47; i < 64; i++)
+		test_sigreturn_to(1UL<<i);
+
+	clearhandler(SIGUSR1);
+
+	sethandler(SIGSEGV, sigsegv_for_fallthrough, 0);
+
+	/* One extra test to check that we didn't screw up the mremap logic. */
+	test_syscall_fallthrough_to((1UL << 47) - 2*PAGE_SIZE);
+
+	/* These are the interesting cases. */
+	for (int i = 47; i < 64; i++) {
+		test_syscall_fallthrough_to((1UL<<i) - PAGE_SIZE);
+		test_syscall_fallthrough_to(1UL<<i);
+	}
+
+	return 0;
+}