diff options
1442 files changed, 42971 insertions, 19078 deletions
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. 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> </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> </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>->ncpus</tt> + field. + The <tt>rcu_state</tt> structure's <tt>->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>->expmaskinitnext</tt> field. + The <tt>rcu_node</tt> structure's <tt>->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>->ncpus</tt> and + <tt>->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>->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>->expmaskinit</tt> + field from its <tt>->expmaskinitnext</tt> field. +<li> Each <tt>rcu_node</tt> structure's <tt>->expmaskinit</tt> + field is used to initialize that structure's + <tt>->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>->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> </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> </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>->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)&~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>->exp_seq_rq</tt> field and moves up +to the next level in the tree. +Otherwise, if the <tt>->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>->exp_wq[]</tt> array, using the second-from-bottom +and third-from bottom bits as an index. +An <tt>->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>->exp_seq_rq</tt> field +and the red cells representing the elements of the +<tt>->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 A +and Task 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>->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>->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 A and B will move up to the root +<tt>rcu_node</tt> structure. +Suppose that Task 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 A now advances to initiate a new grace period, while Task B +moves up to the root <tt>rcu_node</tt> structure, and, seeing that +its desired sequence number is already recorded, blocks on +<tt>->exp_wq[1]</tt>. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + Why <tt>->exp_wq[1]</tt>? + Given that the value of these tasks' desired sequence number is + two, so shouldn't they instead block on <tt>->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>->exp_wq[1]</tt>. +</font></td></tr> +<tr><td> </td></tr> +</table> + +<p> +If Tasks C and 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>->exp_wq[1]</tt> fields, as shown below: + +<p><img src="Funnel3.svg" alt="Funnel3.svg" width="75%"> + +<p> +Task A now acquires the <tt>rcu_state</tt> structure's +<tt>->exp_mutex</tt> and initiates the grace period, which +increments <tt>->expedited_sequence</tt>. +Therefore, if Tasks E and 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 E and F will propagate up the <tt>rcu_node</tt> +combining tree, with Task F blocking on the root <tt>rcu_node</tt> +structure and Task E wait for Task 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 A +starts waking up the tasks waiting for this grace period to complete, +increments the <tt>->expedited_sequence</tt>, +acquires the <tt>->exp_wake_mutex</tt> and then releases the +<tt>->exp_mutex</tt>. +This results in the following state: + +<p><img src="Funnel6.svg" alt="Funnel6.svg" width="75%"> + +<p> +Task E can then acquire <tt>->exp_mutex</tt> and increment +<tt>->expedited_sequence</tt> to the value three. +If new tasks G and 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 A will wake up the +tasks blocked on the <tt>->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 E and H completing +their grace periods and carrying out their wakeups. + +<table> +<tr><th> </th></tr> +<tr><th align="left">Quick Quiz:</th></tr> +<tr><td> + What happens if Task A takes so long to do its wakeups + that Task E's grace period completes? +</td></tr> +<tr><th align="left">Answer:</th></tr> +<tr><td bgcolor="#ffffff"><font color="ffffff"> + Then Task E will block on the <tt>->exp_wake_mutex</tt>, + which will also prevent it from releasing <tt>->exp_mutex</tt>, + which in turn will prevent the next grace period from starting. + This last is important in preventing overflow of the + <tt>->exp_wq[]</tt> array. +</font></td></tr> +<tr><td> </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>->exp_mutex</tt> +guard expedited grace-period processing and the +<tt>->exp_wake_mutex</tt> guard wakeups. +The key point is that the <tt>->exp_mutex</tt> is not released +until the first wakeup is complete, which means that the +<tt>->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> </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> </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">->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">->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">->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">->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">->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">->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">->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">->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">->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 “tramopolines” to handle the +Some forms of tracing use “trampolines” 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/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 = <®_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/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/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/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/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/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 008ecb588317..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 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 864e1fd31f0c..a0fb98c6399a 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 @@ -1788,7 +1788,7 @@ 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. @@ -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> @@ -5274,7 +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> @@ -7534,6 +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> @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 10 SUBLEVEL = 0 -EXTRAVERSION = -rc8 +EXTRAVERSION = NAME = Fearless Coyote # *DOCUMENTATION* @@ -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 @@ -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/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/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/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-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-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-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/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/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/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/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(¤t->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/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/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/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/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/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/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/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 195a9fc8f81c..9e8e771f8acb 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -249,9 +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)); @@ -262,9 +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/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/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/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/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/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/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/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/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 22ef4f72cf32..22054ca49026 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -771,6 +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), {}, }; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 1ab45976474d..758c1aa5009d 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1328,6 +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), {}, }; 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 2266f864b747..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; 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/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 bd6b8c270c24..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); } @@ -1875,6 +1875,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_ack = irq_chip_ack_parent, .irq_eoi = ioapic_ack_level, .irq_set_affinity = ioapic_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; @@ -1886,6 +1887,7 @@ static struct irq_chip ioapic_ir_chip __read_mostly = { .irq_ack = irq_chip_ack_parent, .irq_eoi = ioapic_ir_ack_level, .irq_set_affinity = ioapic_set_affinity, + .irq_retrigger = irq_chip_retrigger_hierarchy, .flags = IRQCHIP_SKIP_SET_WAKE, }; 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 2b4cf04239b6..4e95b2e0d95f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -555,8 +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 ede03e849a8b..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); @@ -1035,10 +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); @@ -1056,6 +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); @@ -1097,10 +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 537c6647d84c..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). @@ -2189,7 +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; 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 079e81733a58..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; @@ -316,184 +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 - if (!initrd_gone) - 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; @@ -631,60 +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); @@ -697,8 +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 73102d932760..b4a4cd39b358 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -66,19 +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); @@ -94,18 +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; @@ -133,23 +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; @@ -167,22 +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; @@ -201,7 +230,7 @@ static int __init save_microcode_in_initrd(void) break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - ret = save_microcode_in_initrd_amd(c->x86); + return save_microcode_in_initrd_amd(cpuid_eax(1)); break; default: break; 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 de7234401275..e1114f070c2d 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -9,7 +9,6 @@ #include <asm/fpu/regset.h> #include <asm/fpu/signal.h> #include <asm/fpu/types.h> -#include <asm/fpu/xstate.h> #include <asm/traps.h> #include <linux/hardirq.h> @@ -179,14 +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 | - xfeatures_mask; - + 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/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(¶virt_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 99b920d0e516..a0d38685f7df 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1347,8 +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 37e7cf544e51..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) 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/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 8aa6bea1cd6c..58b5bee7ea27 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -18,6 +18,7 @@ #include <linux/sched.h> #include <linux/seq_file.h> +#include <asm/kasan.h> #include <asm/pgtable.h> /* @@ -51,6 +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 @@ -76,6 +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 @@ -327,18 +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); @@ -349,6 +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++; } } 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 2f25a363068c..a4695da42d77 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -414,10 +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)) { @@ -426,6 +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; @@ -446,15 +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(¶virt_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/block/cfq-iosched.c b/block/cfq-iosched.c index 921262770636..137944777859 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3760,7 +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; @@ -3777,15 +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 @@ -3806,9 +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 ** @@ -4452,11 +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) { @@ -4492,6 +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; } 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 b0399e8f6d27..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 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 01e1b3d63fc0..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 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/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 54abb26b7366..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"), + }, + }, {}, }; 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/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/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: ®map_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 ®map_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: ®map_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/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 d305f05be648..615e5b5178a0 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -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_req.c b/drivers/block/drbd/drbd_req.c index cb6bdb75d52d..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) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 588721f30a22..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 diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index a363170e45b1..024b473524c0 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -814,7 +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); 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 c94360671f41..7281a2c19c36 100644 --- a/drivers/cpufreq/brcmstb-avs-cpufreq.c +++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c @@ -878,7 +878,6 @@ unmap_intr_base: iounmap(priv->avs_intr_base); unmap_base: iounmap(priv->base); - platform_set_drvdata(pdev, NULL); return ret; } @@ -1042,7 +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 50bd6d987fc3..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); @@ -1007,35 +1007,57 @@ 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 ************************/ @@ -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, @@ -1364,48 +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; } @@ -2072,6 +2204,20 @@ 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 && @@ -2299,6 +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; @@ -2486,9 +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; @@ -2520,45 +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/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/pl330.c b/drivers/dma/pl330.c index 7539f73df9e0..f37f4978dabb 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -1859,9 +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__); 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/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/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/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/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/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 8098677a3916..1974ccb781de 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -642,7 +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/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/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/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/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-ids.h b/drivers/hid/hid-ids.h index 350accfee8e8..86c95d30ac80 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -323,7 +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 @@ -630,9 +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 @@ -725,12 +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-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 30a2977e2645..d6847a664446 100644 --- a/drivers/hid/usbhid/hid-quirks.c +++ b/drivers/hid/usbhid/hid-quirks.c @@ -85,7 +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 }, @@ -103,12 +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 }, @@ -297,7 +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) @@ -361,7 +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 672145b0d8f5..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. @@ -1192,6 +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; @@ -1446,7 +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; @@ -1473,6 +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; } @@ -1552,12 +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); @@ -1565,7 +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: @@ -1580,6 +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) { @@ -1622,17 +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; } @@ -1670,20 +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, @@ -2058,8 +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: @@ -2068,7 +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; @@ -2123,8 +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); @@ -2142,6 +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) @@ -2669,6 +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: @@ -2779,8 +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)) { @@ -2840,6 +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: @@ -2986,6 +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); @@ -3094,6 +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: @@ -3290,6 +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; @@ -3391,6 +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; @@ -3949,6 +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 }; @@ -4115,6 +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) }, @@ -4123,6 +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/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/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/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_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/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index 8cd4d054a87e..d19662f635b1 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -672,14 +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); diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 04c1c382dedb..d4fd2f5c8326 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1580,7 +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; 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/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(®ion->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(®ion->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(®ion->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(®ion->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(®ion->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(®->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(®ion->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(®ion->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-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/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, ®->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, ®->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/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/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/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-crypt.c b/drivers/md/dm-crypt.c index 8a9f742d8ed7..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; diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c index a6dde7cab458..758d90cc2733 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/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/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/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/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/vxlan.c b/drivers/net/vxlan.c index 50b62db213b0..30b04cf2bb1e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2439,7 +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); @@ -2450,7 +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); 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/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/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/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/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, ®); + 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, ®); + 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, ®); + 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, ®); + 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 a3ade9e4ef47..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, 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(®ulator_list_mutex); - return map->regulator; + r = map->regulator; + break; } } mutex_unlock(®ulator_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 == ®ulator_class) + if (consumer->dev && consumer->dev->class == ®ulator_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(®ulator_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, + ®ulator->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/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/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/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/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/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..63bef4566548 100644 --- a/drivers/scsi/lpfc/lpfc_els.c +++ b/drivers/scsi/lpfc/lpfc_els.c @@ -3690,7 +3690,7 @@ 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); 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_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/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/scsi_lib.c b/drivers/scsi/scsi_lib.c index 90f65c8f487a..912fbc3b4543 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1089,7 +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) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index e0e308b7e01a..e831e01f9fa6 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1757,6 +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); 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 RafaÅ‚ MiÅ‚ecki <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("RafaÅ‚ MiÅ‚ecki <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) ®_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(®_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/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/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/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/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/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index fd80c1b9c823..e6a17455adac 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -3698,7 +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/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/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/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/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); @@ -1086,8 +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, 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/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/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 c0e5b9a8bf5f..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); 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/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/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 87c9a9aacda3..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), 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/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/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/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/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/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/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/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/cpumask.h b/include/linux/cpumask.h index b3d2c1a89ac4..96f1e88b767c 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -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/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/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/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/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/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/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 39e3254e5769..f887351aa80e 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -732,6 +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) @@ -748,6 +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/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/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/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/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/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-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/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/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/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/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/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/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/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/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/init/Kconfig b/init/Kconfig index 4dd8bd232a1d..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 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(¤t->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 = ¤t->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/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 e235bb991bdd..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 = this_cpu_ptr(&cgrp_cpuctx_list); + list_for_each_entry(cpuctx, list, cgrp_cpuctx_entry) { + WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0); - 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 */ - - /* - * 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) { @@ -2226,7 +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; @@ -2234,7 +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, @@ -2249,13 +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); } @@ -2302,7 +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); } @@ -2469,7 +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)); } /* @@ -2896,7 +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); } } @@ -2943,7 +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; @@ -3133,8 +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); @@ -3449,6 +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; @@ -3462,15 +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); @@ -8044,6 +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; @@ -8214,6 +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; @@ -8221,6 +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) @@ -8236,6 +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 */ @@ -8275,24 +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); @@ -8301,6 +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) @@ -8652,37 +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); } @@ -8886,8 +8925,6 @@ skip_type: cpuctx->ctx.pmu = pmu; __perf_mux_hrtimer_init(cpuctx, cpu); - - cpuctx->unique_pmu = pmu; } got_cpu_context: @@ -9005,6 +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(); @@ -10265,7 +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 @@ -10714,6 +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 b59e6768c5e9..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 * @@ -1408,6 +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/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_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((¶virt_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((¶virt_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(¤t->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(¶virt_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/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 1aea594a54db..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, 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/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/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/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/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/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, &_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, &_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/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/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/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index e164684456df..7cebee58e55b 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1022,8 +1022,10 @@ 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))) - return -EAFNOSUPPORT; + !(ipv6_addr_v4mapped(&fl6->daddr) || ipv6_addr_any(&fl6->daddr))) { + err = -EAFNOSUPPORT; + goto out_err_release; + } return 0; 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/packet/af_packet.c b/net/packet/af_packet.c index 0f03f6a53b4d..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); } @@ -1693,7 +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; @@ -1718,7 +1721,12 @@ out: 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; @@ -1728,17 +1736,17 @@ static void fanout_release(struct sock *sk) if (f) { po->fanout = NULL; - if (atomic_dec_and_test(&f->sk_ref)) { + if (atomic_dec_and_test(&f->sk_ref)) list_del(&f->list); - dev_remove_pack(&f->prot_hook); - fanout_release_data(f); - kfree(f); - } + else + f = NULL; if (po->rollover) kfree_rcu(po->rollover, rcu); } mutex_unlock(&fanout_mutex); + + return f; } static bool packet_extra_vlan_len_allowed(const struct net_device *dev, @@ -2912,6 +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; @@ -2951,9 +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. */ @@ -3905,7 +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/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/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/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/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/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('<', '<').replace('>', '>') + 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→</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}"> {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('<', '<').replace('>', '>') 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>←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→</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/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/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/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.h b/tools/lib/bpf/bpf.h index 4ac6c4b84100..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); 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/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 933aeec46f4a..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; @@ -1195,6 +1235,9 @@ 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); } @@ -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/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 8b610dd9e2f6..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; 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 7d1b7d33e644..32c6a939e4cc 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -2446,8 +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/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/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; +} |
